diff options
1220 files changed, 27126 insertions, 11244 deletions
@@ -199,7 +199,8 @@ Elliot Berman <[email protected]> <[email protected]> Enric Balletbo i Serra <[email protected]> <[email protected]> Enric Balletbo i Serra <[email protected]> <[email protected]> Erik Kaneda <[email protected]> <[email protected]> -Eugen Hristev <[email protected]> <[email protected]> +Eugen Hristev <[email protected]> <[email protected]> +Eugen Hristev <[email protected]> <[email protected]> Evgeniy Polyakov <[email protected]> Ezequiel Garcia <[email protected]> <[email protected]> Faith Ekstrand <[email protected]> <[email protected]> @@ -282,7 +283,7 @@ Jan Glauber <[email protected]> <[email protected]> Jan Kuliga <[email protected]> <[email protected]> Jarkko Sakkinen <[email protected]> <[email protected]> Jarkko Sakkinen <[email protected]> <[email protected]> -Jarkko Sakkinen <[email protected]> <[email protected]> +Jarkko Sakkinen <[email protected]> <[email protected]> Jason Gunthorpe <[email protected]> <[email protected]> Jason Gunthorpe <[email protected]> <[email protected]> Jason Gunthorpe <[email protected]> <[email protected]> @@ -1204,6 +1204,10 @@ S: Dreisbachstrasse 24 S: D-57250 Netphen S: Germany +N: Florian Fainelli +D: DSA + N: Rik Faith D: Future Domain TMC-16x0 SCSI driver (author) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 1518343bbe22..2fb830453dcc 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1546,6 +1546,7 @@ failslab= fail_usercopy= fail_page_alloc= + fail_skb_realloc= fail_make_request=[KNL] General fault injection mechanism. Format: <interval>,<probability>,<space>,<times> diff --git a/Documentation/admin-guide/pm/cpufreq.rst b/Documentation/admin-guide/pm/cpufreq.rst index fe1be4ad88cb..a21369eba034 100644 --- a/Documentation/admin-guide/pm/cpufreq.rst +++ b/Documentation/admin-guide/pm/cpufreq.rst @@ -425,8 +425,8 @@ This governor exposes only one tunable: ``rate_limit_us`` Minimum time (in microseconds) that has to pass between two consecutive - runs of governor computations (default: 1000 times the scaling driver's - transition latency). + runs of governor computations (default: 1.5 times the scaling driver's + transition latency or the maximum 2ms). The purpose of this tunable is to reduce the scheduler context overhead of the governor which might be excessive without it. @@ -474,17 +474,17 @@ This governor exposes the following tunables: This is how often the governor's worker routine should run, in microseconds. - Typically, it is set to values of the order of 10000 (10 ms). Its - default value is equal to the value of ``cpuinfo_transition_latency`` - for each policy this governor is attached to (but since the unit here - is greater by 1000, this means that the time represented by - ``sampling_rate`` is 1000 times greater than the transition latency by - default). + Typically, it is set to values of the order of 2000 (2 ms). Its + default value is to add a 50% breathing room + to ``cpuinfo_transition_latency`` on each policy this governor is + attached to. The minimum is typically the length of two scheduler + ticks. If this tunable is per-policy, the following shell command sets the time - represented by it to be 750 times as high as the transition latency:: + represented by it to be 1.5 times as high as the transition latency + (the default):: - # echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) > ondemand/sampling_rate + # echo `$(($(cat cpuinfo_transition_latency) * 3 / 2)) > ondemand/sampling_rate ``up_threshold`` If the estimated CPU load is above this value (in percent), the governor diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.yaml index 3a82aec9021c..497c0eb4ed0b 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.yaml +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.yaml @@ -63,6 +63,16 @@ properties: - const: sleep power-domains: + description: | + The MediaTek DPI module is typically associated with one of the + following multimedia power domains: + POWER_DOMAIN_DISPLAY + POWER_DOMAIN_VDOSYS + POWER_DOMAIN_MM + The specific power domain used varies depending on the SoC design. + + It is recommended to explicitly add the appropriate power domain + property to the DPI node in the device tree. maxItems: 1 port: @@ -79,20 +89,6 @@ required: - clock-names - port -allOf: - - if: - not: - properties: - compatible: - contains: - enum: - - mediatek,mt6795-dpi - - mediatek,mt8173-dpi - - mediatek,mt8186-dpi - then: - properties: - power-domains: false - additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,split.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,split.yaml index e4affc854f3d..4b6ff546757e 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,split.yaml +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,split.yaml @@ -38,6 +38,7 @@ properties: description: A phandle and PM domain specifier as defined by bindings of the power controller specified by phandle. See Documentation/devicetree/bindings/power/power-domain.yaml for details. + maxItems: 1 mediatek,gce-client-reg: description: @@ -57,6 +58,9 @@ properties: clocks: items: - description: SPLIT Clock + - description: Used for interfacing with the HDMI RX signal source. + - description: Paired with receiving HDMI RX metadata. + minItems: 1 required: - compatible @@ -72,9 +76,24 @@ allOf: const: mediatek,mt8195-mdp3-split then: + properties: + clocks: + minItems: 3 + required: - mediatek,gce-client-reg + - if: + properties: + compatible: + contains: + const: mediatek,mt8173-disp-split + + then: + properties: + clocks: + maxItems: 1 + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/firmware/arm,scmi.yaml b/Documentation/devicetree/bindings/firmware/arm,scmi.yaml index 54d7d11bfed4..ff7a6f12cd00 100644 --- a/Documentation/devicetree/bindings/firmware/arm,scmi.yaml +++ b/Documentation/devicetree/bindings/firmware/arm,scmi.yaml @@ -124,7 +124,7 @@ properties: atomic mode of operation, even if requested. default: 0 - max-rx-timeout-ms: + arm,max-rx-timeout-ms: description: An optional time value, expressed in milliseconds, representing the transport maximum timeout value for the receive channel. The value should diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7380.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7380.yaml index bd19abb867d9..0065d6508824 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7380.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7380.yaml @@ -67,6 +67,10 @@ properties: A 2.5V to 3.3V supply for the external reference voltage. When omitted, the internal 2.5V reference is used. + refin-supply: + description: + A 2.5V to 3.3V supply for external reference voltage, for ad7380-4 only. + aina-supply: description: The common mode voltage supply for the AINA- pin on pseudo-differential @@ -135,6 +139,23 @@ allOf: ainc-supply: false aind-supply: false + # ad7380-4 uses refin-supply as external reference. + # All other chips from ad738x family use refio as optional external reference. + # When refio-supply is omitted, internal reference is used. + - if: + properties: + compatible: + enum: + - adi,ad7380-4 + then: + properties: + refio-supply: false + required: + - refin-supply + else: + properties: + refin-supply: false + examples: - | #include <dt-bindings/interrupt-controller/irq.h> diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml index 30c0c3e6f37a..121a4bbd147b 100644 --- a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml +++ b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml @@ -81,6 +81,26 @@ properties: interrupts: maxItems: 1 + mdio: + $ref: /schemas/net/mdio.yaml# + unevaluatedProperties: false + properties: + mdio-parent-bus: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Phandle pointing to the MDIO bus controller connected to the + secondary MDIO interface. This property should be used when + the internal MDIO bus is accessed via a secondary MDIO + interface rather than the primary management interface. + + patternProperties: + "^ethernet-phy@[0-9a-f]$": + type: object + $ref: /schemas/net/ethernet-phy.yaml# + unevaluatedProperties: false + description: + Integrated PHY node + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/net/fsl,enetc-mdio.yaml b/Documentation/devicetree/bindings/net/fsl,enetc-mdio.yaml index c1dd6aa04321..71c43ece8295 100644 --- a/Documentation/devicetree/bindings/net/fsl,enetc-mdio.yaml +++ b/Documentation/devicetree/bindings/net/fsl,enetc-mdio.yaml @@ -20,10 +20,13 @@ maintainers: properties: compatible: - items: - - enum: - - pci1957,ee01 - - const: fsl,enetc-mdio + oneOf: + - items: + - enum: + - pci1957,ee01 + - const: fsl,enetc-mdio + - items: + - const: pci1131,ee00 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/fsl,enetc.yaml b/Documentation/devicetree/bindings/net/fsl,enetc.yaml index e152c93998fe..ca70f0050171 100644 --- a/Documentation/devicetree/bindings/net/fsl,enetc.yaml +++ b/Documentation/devicetree/bindings/net/fsl,enetc.yaml @@ -20,14 +20,25 @@ maintainers: properties: compatible: - items: + oneOf: + - items: + - enum: + - pci1957,e100 + - const: fsl,enetc - enum: - - pci1957,e100 - - const: fsl,enetc + - pci1131,e101 reg: maxItems: 1 + clocks: + items: + - description: MAC transmit/receive reference clock + + clock-names: + items: + - const: ref + mdio: $ref: mdio.yaml unevaluatedProperties: false @@ -40,6 +51,17 @@ required: allOf: - $ref: /schemas/pci/pci-device.yaml - $ref: ethernet-controller.yaml + - if: + not: + properties: + compatible: + contains: + enum: + - pci1131,e101 + then: + properties: + clocks: false + clock-names: false unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml b/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml index fcafef8d5a33..dedfad526666 100644 --- a/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml +++ b/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml @@ -9,6 +9,7 @@ title: Microchip Sparx5 Ethernet switch controller maintainers: - Steen Hegelund <[email protected]> - Lars Povlsen <[email protected]> + - Daniel Machon <[email protected]> description: | The SparX-5 Enterprise Ethernet switch family provides a rich set of @@ -34,7 +35,24 @@ properties: pattern: "^switch@[0-9a-f]+$" compatible: - const: microchip,sparx5-switch + oneOf: + - enum: + - microchip,lan9691-switch + - microchip,sparx5-switch + - items: + - enum: + - microchip,lan969c-switch + - microchip,lan969b-switch + - microchip,lan969a-switch + - microchip,lan9699-switch + - microchip,lan9698-switch + - microchip,lan9697-switch + - microchip,lan9696-switch + - microchip,lan9695-switch + - microchip,lan9694-switch + - microchip,lan9693-switch + - microchip,lan9692-switch + - const: microchip,lan9691-switch reg: items: diff --git a/Documentation/devicetree/bindings/net/nxp,netc-blk-ctrl.yaml b/Documentation/devicetree/bindings/net/nxp,netc-blk-ctrl.yaml new file mode 100644 index 000000000000..97389fd5dbbf --- /dev/null +++ b/Documentation/devicetree/bindings/net/nxp,netc-blk-ctrl.yaml @@ -0,0 +1,104 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/nxp,netc-blk-ctrl.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NETC Blocks Control + +description: + Usually, NETC has 2 blocks of 64KB registers, integrated endpoint register + block (IERB) and privileged register block (PRB). IERB is used for pre-boot + initialization for all NETC devices, such as ENETC, Timer, EMIDO and so on. + And PRB controls global reset and global error handling for NETC. Moreover, + for the i.MX platform, there is also a NETCMIX block for link configuration, + such as MII protocol, PCS protocol, etc. + +maintainers: + - Wei Fang <[email protected]> + - Clark Wang <[email protected]> + +properties: + compatible: + enum: + - nxp,imx95-netc-blk-ctrl + + reg: + maxItems: 3 + + reg-names: + items: + - const: ierb + - const: prb + - const: netcmix + + "#address-cells": + const: 2 + + "#size-cells": + const: 2 + + ranges: true + + clocks: + maxItems: 1 + + clock-names: + items: + - const: ipg + + power-domains: + maxItems: 1 + +patternProperties: + "^pcie@[0-9a-f]+$": + $ref: /schemas/pci/host-generic-pci.yaml# + +required: + - compatible + - reg + - reg-names + - "#address-cells" + - "#size-cells" + - ranges + +additionalProperties: false + +examples: + - | + bus { + #address-cells = <2>; + #size-cells = <2>; + + system-controller@4cde0000 { + compatible = "nxp,imx95-netc-blk-ctrl"; + reg = <0x0 0x4cde0000 0x0 0x10000>, + <0x0 0x4cdf0000 0x0 0x10000>, + <0x0 0x4c81000c 0x0 0x18>; + reg-names = "ierb", "prb", "netcmix"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + clocks = <&scmi_clk 98>; + clock-names = "ipg"; + power-domains = <&scmi_devpd 18>; + + pcie@4cb00000 { + compatible = "pci-host-ecam-generic"; + reg = <0x0 0x4cb00000 0x0 0x100000>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + bus-range = <0x1 0x1>; + ranges = <0x82000000 0x0 0x4cce0000 0x0 0x4cce0000 0x0 0x20000 + 0xc2000000 0x0 0x4cd10000 0x0 0x4cd10000 0x0 0x10000>; + + mdio@0,0 { + compatible = "pci1131,ee00"; + reg = <0x010000 0 0 0 0>; + #address-cells = <1>; + #size-cells = <0>; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/qcom,ethqos.yaml b/Documentation/devicetree/bindings/net/qcom,ethqos.yaml index 6672327358bc..0bcd593a7bd0 100644 --- a/Documentation/devicetree/bindings/net/qcom,ethqos.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ethqos.yaml @@ -18,11 +18,20 @@ allOf: properties: compatible: - enum: - - qcom,qcs404-ethqos - - qcom,sa8775p-ethqos - - qcom,sc8280xp-ethqos - - qcom,sm8150-ethqos + oneOf: + - items: + - enum: + - qcom,qcs8300-ethqos + - const: qcom,sa8775p-ethqos + - items: + - enum: + - qcom,qcs615-ethqos + - const: qcom,sm8150-ethqos + - enum: + - qcom,qcs404-ethqos + - qcom,sa8775p-ethqos + - qcom,sc8280xp-ethqos + - qcom,sm8150-ethqos reg: maxItems: 2 diff --git a/Documentation/devicetree/bindings/net/renesas,ether.yaml b/Documentation/devicetree/bindings/net/renesas,ether.yaml index 29355ab98569..d6c5983499b8 100644 --- a/Documentation/devicetree/bindings/net/renesas,ether.yaml +++ b/Documentation/devicetree/bindings/net/renesas,ether.yaml @@ -59,6 +59,9 @@ properties: clocks: maxItems: 1 + iommus: + maxItems: 1 + power-domains: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index 4e2ba1bf788c..eb1f3ae41ab9 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -26,6 +26,7 @@ select: - snps,dwmac-3.610 - snps,dwmac-3.70a - snps,dwmac-3.710 + - snps,dwmac-3.72a - snps,dwmac-4.00 - snps,dwmac-4.10a - snps,dwmac-4.20a @@ -90,6 +91,7 @@ properties: - snps,dwmac-3.610 - snps,dwmac-3.70a - snps,dwmac-3.710 + - snps,dwmac-3.72a - snps,dwmac-4.00 - snps,dwmac-4.10a - snps,dwmac-4.20a @@ -99,6 +101,7 @@ properties: - snps,dwxgmac-2.10 - starfive,jh7100-dwmac - starfive,jh7110-dwmac + - thead,th1520-gmac reg: minItems: 1 @@ -560,7 +563,7 @@ properties: max read outstanding req. limit snps,kbbe: - $ref: /schemas/types.yaml#/definitions/uint32 + $ref: /schemas/types.yaml#/definitions/flag description: do not cross 1KiB boundary. diff --git a/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml b/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml new file mode 100644 index 000000000000..6d9de3303762 --- /dev/null +++ b/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml @@ -0,0 +1,110 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/thead,th1520-gmac.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: T-HEAD TH1520 GMAC Ethernet controller + +maintainers: + - Drew Fustini <[email protected]> + +description: | + The TH1520 GMAC is described in the TH1520 Peripheral Interface User Manual + https://git.beagleboard.org/beaglev-ahead/beaglev-ahead/-/tree/main/docs + + Features include + - Compliant with IEEE802.3 Specification + - IEEE 1588-2008 standard for precision networked clock synchronization + - Supports 10/100/1000Mbps data transfer rate + - Supports RGMII/MII interface + - Preamble and start of frame data (SFD) insertion in Transmit path + - Preamble and SFD deletion in the Receive path + - Automatic CRC and pad generation options for receive frames + - MDIO master interface for PHY device configuration and management + + The GMAC Registers consists of two parts + - APB registers are used to configure clock frequency/clock enable/clock + direction/PHY interface type. + - AHB registers are use to configure GMAC core (DesignWare Core part). + GMAC core register consists of DMA registers and GMAC registers. + +select: + properties: + compatible: + contains: + enum: + - thead,th1520-gmac + required: + - compatible + +allOf: + - $ref: snps,dwmac.yaml# + +properties: + compatible: + items: + - enum: + - thead,th1520-gmac + - const: snps,dwmac-3.70a + + reg: + items: + - description: DesignWare GMAC IP core registers + - description: GMAC APB registers + + reg-names: + items: + - const: dwmac + - const: apb + + clocks: + items: + - description: GMAC main clock + - description: Peripheral registers interface clock + + clock-names: + items: + - const: stmmaceth + - const: pclk + + interrupts: + items: + - description: Combined signal for various interrupt events + + interrupt-names: + items: + - const: macirq + +required: + - clocks + - clock-names + +unevaluatedProperties: false + +examples: + - | + gmac0: ethernet@e7070000 { + compatible = "thead,th1520-gmac", "snps,dwmac-3.70a"; + reg = <0xe7070000 0x2000>, <0xec003000 0x1000>; + reg-names = "dwmac", "apb"; + clocks = <&clk 1>, <&clk 2>; + clock-names = "stmmaceth", "pclk"; + interrupts = <66>; + interrupt-names = "macirq"; + phy-mode = "rgmii-id"; + snps,fixed-burst; + snps,axi-config = <&stmmac_axi_setup>; + snps,pbl = <32>; + phy-handle = <&phy0>; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + + phy0: ethernet-phy@0 { + reg = <0>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml b/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml index e95c21628281..fb02e579463c 100644 --- a/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml +++ b/Documentation/devicetree/bindings/net/xlnx,axi-ethernet.yaml @@ -61,7 +61,7 @@ properties: - gmii - rgmii - sgmii - - 1000BaseX + - 1000base-x xlnx,phy-type: description: diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml index dcf4fa55fbba..380a9222a51d 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml @@ -154,8 +154,6 @@ allOf: - qcom,sm8550-qmp-gen4x2-pcie-phy - qcom,sm8650-qmp-gen3x2-pcie-phy - qcom,sm8650-qmp-gen4x2-pcie-phy - - qcom,x1e80100-qmp-gen3x2-pcie-phy - - qcom,x1e80100-qmp-gen4x2-pcie-phy then: properties: clocks: @@ -171,6 +169,8 @@ allOf: - qcom,sc8280xp-qmp-gen3x1-pcie-phy - qcom,sc8280xp-qmp-gen3x2-pcie-phy - qcom,sc8280xp-qmp-gen3x4-pcie-phy + - qcom,x1e80100-qmp-gen3x2-pcie-phy + - qcom,x1e80100-qmp-gen4x2-pcie-phy - qcom,x1e80100-qmp-gen4x4-pcie-phy then: properties: @@ -201,6 +201,7 @@ allOf: - qcom,sm8550-qmp-gen4x2-pcie-phy - qcom,sm8650-qmp-gen4x2-pcie-phy - qcom,x1e80100-qmp-gen4x2-pcie-phy + - qcom,x1e80100-qmp-gen4x4-pcie-phy then: properties: resets: diff --git a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml index ab3206ffa4af..beef193aaaeb 100644 --- a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml +++ b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml @@ -102,21 +102,21 @@ properties: default: 2 interrupts: - oneOf: - - minItems: 1 - items: - - description: TX interrupt - - description: RX interrupt - - items: - - description: common/combined interrupt + minItems: 1 + maxItems: 2 interrupt-names: oneOf: - - minItems: 1 + - description: TX interrupt + const: tx + - description: RX interrupt + const: rx + - description: TX and RX interrupts items: - const: tx - const: rx - - const: common + - description: Common/combined interrupt + const: common fck_parent: $ref: /schemas/types.yaml#/definitions/string diff --git a/Documentation/devicetree/bindings/sound/rockchip,rk3308-codec.yaml b/Documentation/devicetree/bindings/sound/rockchip,rk3308-codec.yaml index ecf3d7d968c8..2cf229a076f0 100644 --- a/Documentation/devicetree/bindings/sound/rockchip,rk3308-codec.yaml +++ b/Documentation/devicetree/bindings/sound/rockchip,rk3308-codec.yaml @@ -48,6 +48,10 @@ properties: - const: mclk_rx - const: hclk + port: + $ref: audio-graph-port.yaml# + unevaluatedProperties: false + resets: maxItems: 1 diff --git a/Documentation/fault-injection/fault-injection.rst b/Documentation/fault-injection/fault-injection.rst index 8b8aeea71c68..1c14ba08fbfc 100644 --- a/Documentation/fault-injection/fault-injection.rst +++ b/Documentation/fault-injection/fault-injection.rst @@ -45,6 +45,32 @@ Available fault injection capabilities ALLOW_ERROR_INJECTION() macro, by setting debugfs entries under /sys/kernel/debug/fail_function. No boot option supported. +- fail_skb_realloc + + inject skb (socket buffer) reallocation events into the network path. The + primary goal is to identify and prevent issues related to pointer + mismanagement in the network subsystem. By forcing skb reallocation at + strategic points, this feature creates scenarios where existing pointers to + skb headers become invalid. + + When the fault is injected and the reallocation is triggered, cached pointers + to skb headers and data no longer reference valid memory locations. This + deliberate invalidation helps expose code paths where proper pointer updating + is neglected after a reallocation event. + + By creating these controlled fault scenarios, the system can catch instances + where stale pointers are used, potentially leading to memory corruption or + system instability. + + To select the interface to act on, write the network name to + /sys/kernel/debug/fail_skb_realloc/devname. + If this field is left empty (which is the default value), skb reallocation + will be forced on all network interfaces. + + The effectiveness of this fault detection is enhanced when KASAN is + enabled, as it helps identify invalid memory references and use-after-free + (UAF) issues. + - NVMe fault injection inject NVMe status code and retry flag on devices permitted by setting @@ -216,6 +242,19 @@ configuration of fault-injection capabilities. use a negative errno, you better use 'printf' instead of 'echo', e.g.: $ printf %#x -12 > retval +- /sys/kernel/debug/fail_skb_realloc/devname: + + Specifies the network interface on which to force SKB reallocation. If + left empty, SKB reallocation will be applied to all network interfaces. + + Example usage:: + + # Force skb reallocation on eth0 + echo "eth0" > /sys/kernel/debug/fail_skb_realloc/devname + + # Clear the selection and force skb reallocation on all interfaces + echo "" > /sys/kernel/debug/fail_skb_realloc/devname + Boot option ^^^^^^^^^^^ @@ -227,6 +266,7 @@ use the boot option:: fail_usercopy= fail_make_request= fail_futex= + fail_skb_realloc= mmc_core.fail_request=<interval>,<probability>,<space>,<times> proc entries diff --git a/Documentation/filesystems/caching/cachefiles.rst b/Documentation/filesystems/caching/cachefiles.rst index e04a27bdbe19..b3ccc782cb3b 100644 --- a/Documentation/filesystems/caching/cachefiles.rst +++ b/Documentation/filesystems/caching/cachefiles.rst @@ -115,7 +115,7 @@ set up cache ready for use. The following script commands are available: This mask can also be set through sysfs, eg:: - echo 5 >/sys/modules/cachefiles/parameters/debug + echo 5 > /sys/module/cachefiles/parameters/debug Starting the Cache diff --git a/Documentation/iio/ad7380.rst b/Documentation/iio/ad7380.rst index 9c784c1e652e..6f70b49b9ef2 100644 --- a/Documentation/iio/ad7380.rst +++ b/Documentation/iio/ad7380.rst @@ -41,13 +41,22 @@ supports only 1 SDO line. Reference voltage ----------------- -2 possible reference voltage sources are supported: +ad7380-4 +~~~~~~~~ + +ad7380-4 supports only an external reference voltage (2.5V to 3.3V). It must be +declared in the device tree as ``refin-supply``. + +All other devices from ad738x family +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +All other devices from ad738x support 2 possible reference voltage sources: - Internal reference (2.5V) - External reference (2.5V to 3.3V) The source is determined by the device tree. If ``refio-supply`` is present, -then the external reference is used, else the internal reference is used. +then it is used as external reference, else the internal reference is used. Oversampling and resolution boost --------------------------------- diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index f2894ca35de8..8feefeae5376 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -86,6 +86,36 @@ definitions: locked on an input pin of type PIN_TYPE_SYNCE_ETH_PORT. render-max: true - + type: enum + name: clock-quality-level + doc: | + level of quality of a clock device. This mainly applies when + the dpll lock-status is DPLL_LOCK_STATUS_HOLDOVER. + The current list is defined according to the table 11-7 contained + in ITU-T G.8264/Y.1364 document. One may extend this list freely + by other ITU-T defined clock qualities, or different ones defined + by another standardization body (for those, please use + different prefix). + entries: + - + name: itu-opt1-prc + value: 1 + - + name: itu-opt1-ssu-a + - + name: itu-opt1-ssu-b + - + name: itu-opt1-eec1 + - + name: itu-opt1-prtc + - + name: itu-opt1-eprtc + - + name: itu-opt1-eeec + - + name: itu-opt1-eprc + render-max: true + - type: const name: temp-divider value: 1000 @@ -252,6 +282,17 @@ attribute-sets: name: lock-status-error type: u32 enum: lock-status-error + - + name: clock-quality-level + type: u32 + enum: clock-quality-level + multi-attr: true + doc: | + Level of quality of a clock device. This mainly applies when + the dpll lock-status is DPLL_LOCK_STATUS_HOLDOVER. This could + be put to message multiple times to indicate possible parallel + quality levels (e.g. one specified by ITU option 1 and another + one specified by option 2). - name: pin enum-name: dpll_a_pin diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml index 30d8342cacc8..dc190bf838fe 100644 --- a/Documentation/netlink/specs/mptcp_pm.yaml +++ b/Documentation/netlink/specs/mptcp_pm.yaml @@ -293,7 +293,6 @@ operations: doc: Get endpoint information attribute-set: attr dont-validate: [ strict ] - flags: [ uns-admin-perm ] do: &get-addr-attrs request: attributes: diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index f9cb97d6106c..cbb544bd6c84 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -263,6 +263,11 @@ attribute-sets: the end of a NAPI cycle. This may add receive latency in exchange for reducing the number of frames processed by the network stack. type: uint + - + name: irq-suspend-timeout + doc: The timeout, in nanoseconds, of how long to suspend irq + processing, if event polling finds events + type: uint - name: queue attributes: @@ -653,6 +658,7 @@ operations: - pid - defer-hard-irqs - gro-flush-timeout + - irq-suspend-timeout dump: request: attributes: @@ -704,6 +710,7 @@ operations: - id - defer-hard-irqs - gro-flush-timeout + - irq-suspend-timeout kernel-family: headers: [ "linux/list.h"] diff --git a/Documentation/netlink/specs/rt_neigh.yaml b/Documentation/netlink/specs/rt_neigh.yaml new file mode 100644 index 000000000000..e670b6dc07be --- /dev/null +++ b/Documentation/netlink/specs/rt_neigh.yaml @@ -0,0 +1,442 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: rt-neigh +protocol: netlink-raw +protonum: 0 + +doc: + IP neighbour management over rtnetlink. + +definitions: + - + name: ndmsg + type: struct + members: + - + name: family + type: u8 + - + name: pad + type: pad + len: 3 + - + name: ifindex + type: s32 + - + name: state + type: u16 + enum: nud-state + - + name: flags + type: u8 + enum: ntf-flags + - + name: type + type: u8 + enum: rtm-type + - + name: ndtmsg + type: struct + members: + - + name: family + type: u8 + - + name: pad + type: pad + len: 3 + - + name: nud-state + type: flags + entries: + - incomplete + - reachable + - stale + - delay + - probe + - failed + - noarp + - permanent + - + name: ntf-flags + type: flags + entries: + - use + - self + - master + - proxy + - ext-learned + - offloaded + - sticky + - router + - + name: ntf-ext-flags + type: flags + entries: + - managed + - locked + - + name: rtm-type + type: enum + entries: + - unspec + - unicast + - local + - broadcast + - anycast + - multicast + - blackhole + - unreachable + - prohibit + - throw + - nat + - xresolve + - + name: nda-cacheinfo + type: struct + members: + - + name: confirmed + type: u32 + - + name: used + type: u32 + - + name: updated + type: u32 + - + name: refcnt + type: u32 + - + name: ndt-config + type: struct + members: + - + name: key-len + type: u16 + - + name: entry-size + type: u16 + - + name: entries + type: u32 + - + name: last-flush + type: u32 + - + name: last-rand + type: u32 + - + name: hash-rnd + type: u32 + - + name: hash-mask + type: u32 + - + name: hash-chain-gc + type: u32 + - + name: proxy-qlen + type: u32 + - + name: ndt-stats + type: struct + members: + - + name: allocs + type: u64 + - + name: destroys + type: u64 + - + name: hash-grows + type: u64 + - + name: res-failed + type: u64 + - + name: lookups + type: u64 + - + name: hits + type: u64 + - + name: rcv-probes-mcast + type: u64 + - + name: rcv-probes-ucast + type: u64 + - + name: periodic-gc-runs + type: u64 + - + name: forced-gc-runs + type: u64 + - + name: table-fulls + type: u64 + +attribute-sets: + - + name: neighbour-attrs + attributes: + - + name: unspec + type: binary + value: 0 + - + name: dst + type: binary + display-hint: ipv4 + - + name: lladr + type: binary + display-hint: mac + - + name: cacheinfo + type: binary + struct: nda-cacheinfo + - + name: probes + type: u32 + - + name: vlan + type: u16 + - + name: port + type: u16 + - + name: vni + type: u32 + - + name: ifindex + type: u32 + - + name: master + type: u32 + - + name: link-netnsid + type: s32 + - + name: src-vni + type: u32 + - + name: protocol + type: u8 + - + name: nh-id + type: u32 + - + name: fdb-ext-attrs + type: binary + - + name: flags-ext + type: u32 + enum: ntf-ext-flags + - + name: ndm-state-mask + type: u16 + - + name: ndm-flags-mask + type: u8 + - + name: ndt-attrs + attributes: + - + name: name + type: string + - + name: thresh1 + type: u32 + - + name: thresh2 + type: u32 + - + name: thresh3 + type: u32 + - + name: config + type: binary + struct: ndt-config + - + name: parms + type: nest + nested-attributes: ndtpa-attrs + - + name: stats + type: binary + struct: ndt-stats + - + name: gc-interval + type: u64 + - + name: pad + type: pad + - + name: ndtpa-attrs + attributes: + - + name: ifindex + type: u32 + - + name: refcnt + type: u32 + - + name: reachable-time + type: u64 + - + name: base-reachable-time + type: u64 + - + name: retrans-time + type: u64 + - + name: gc-staletime + type: u64 + - + name: delay-probe-time + type: u64 + - + name: queue-len + type: u32 + - + name: app-probes + type: u32 + - + name: ucast-probes + type: u32 + - + name: mcast-probes + type: u32 + - + name: anycast-delay + type: u64 + - + name: proxy-delay + type: u64 + - + name: proxy-qlen + type: u32 + - + name: locktime + type: u64 + - + name: queue-lenbytes + type: u32 + - + name: mcast-reprobes + type: u32 + - + name: pad + type: pad + - + name: interval-probe-time-ms + type: u64 + +operations: + enum-model: directional + list: + - + name: newneigh + doc: Add new neighbour entry + fixed-header: ndmsg + attribute-set: neighbour-attrs + do: + request: + value: 28 + attributes: &neighbour-all + - dst + - lladdr + - probes + - vlan + - port + - vni + - ifindex + - master + - protocol + - nh-id + - flags-ext + - fdb-ext-attrs + - + name: delneigh + doc: Remove an existing neighbour entry + fixed-header: ndmsg + attribute-set: neighbour-attrs + do: + request: + value: 29 + attributes: + - dst + - ifindex + - + name: delneigh-ntf + doc: Notify a neighbour deletion + value: 29 + notify: delneigh + fixed-header: ndmsg + - + name: getneigh + doc: Get or dump neighbour entries + fixed-header: ndmsg + attribute-set: neighbour-attrs + do: + request: + value: 30 + attributes: + - dst + reply: + value: 28 + attributes: *neighbour-all + dump: + request: + attributes: + - ifindex + - master + reply: + attributes: *neighbour-all + - + name: newneigh-ntf + doc: Notify a neighbour creation + value: 28 + notify: getneigh + fixed-header: ndmsg + - + name: getneightbl + doc: Get or dump neighbour tables + fixed-header: ndtmsg + attribute-set: ndt-attrs + dump: + request: + value: 66 + reply: + value: 64 + attributes: + - name + - thresh1 + - thresh2 + - thresh3 + - config + - parms + - stats + - gc-interval + - + name: setneightbl + doc: Set neighbour tables + fixed-header: ndtmsg + attribute-set: ndt-attrs + do: + request: + value: 67 + attributes: + - name + - thresh1 + - thresh2 + - thresh3 + - parms + - gc-interval + +mcast-groups: + list: + - + name: rtnlgrp-neigh + value: 3 diff --git a/Documentation/netlink/specs/rt_rule.yaml b/Documentation/netlink/specs/rt_rule.yaml new file mode 100644 index 000000000000..03a8eef7952e --- /dev/null +++ b/Documentation/netlink/specs/rt_rule.yaml @@ -0,0 +1,242 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: rt-rule +protocol: netlink-raw +protonum: 0 + +doc: + FIB rule management over rtnetlink. + +definitions: + - + name: rtgenmsg + type: struct + members: + - + name: family + type: u8 + - + name: pad + type: pad + len: 3 + - + name: fib-rule-hdr + type: struct + members: + - + name: family + type: u8 + - + name: dst-len + type: u8 + - + name: src-len + type: u8 + - + name: tos + type: u8 + - + name: table + type: u8 + - + name: res1 + type: pad + len: 1 + - + name: res2 + type: pad + len: 1 + - + name: action + type: u8 + enum: fr-act + - + name: flags + type: u32 + - + name: fr-act + type: enum + entries: + - unspec + - to-tbl + - goto + - nop + - res3 + - res4 + - blackhole + - unreachable + - prohibit + - + name: fib-rule-port-range + type: struct + members: + - + name: start + type: u16 + - + name: end + type: u16 + - + name: fib-rule-uid-range + type: struct + members: + - + name: start + type: u32 + - + name: end + type: u32 + +attribute-sets: + - + name: fib-rule-attrs + attributes: + - + name: dst + type: u32 + - + name: src + type: u32 + - + name: iifname + type: string + - + name: goto + type: u32 + - + name: unused2 + type: pad + - + name: priority + type: u32 + - + name: unused3 + type: pad + - + name: unused4 + type: pad + - + name: unused5 + type: pad + - + name: fwmark + type: u32 + display-hint: hex + - + name: flow + type: u32 + - + name: tun-id + type: u64 + - + name: suppress-ifgroup + type: u32 + - + name: suppress-prefixlen + type: u32 + display-hint: hex + - + name: table + type: u32 + - + name: fwmask + type: u32 + display-hint: hex + - + name: oifname + type: string + - + name: pad + type: pad + - + name: l3mdev + type: u8 + - + name: uid-range + type: binary + struct: fib-rule-uid-range + - + name: protocol + type: u8 + - + name: ip-proto + type: u8 + - + name: sport-range + type: binary + struct: fib-rule-port-range + - + name: dport-range + type: binary + struct: fib-rule-port-range + - + name: dscp + type: u8 + +operations: + enum-model: directional + fixed-header: fib-rule-hdr + list: + - + name: newrule + doc: Add new FIB rule + attribute-set: fib-rule-attrs + do: + request: + value: 32 + attributes: &fib-rule-all + - iifname + - oifname + - priority + - fwmark + - flow + - tun-id + - fwmask + - table + - suppress-prefixlen + - suppress-ifgroup + - goto + - l3mdev + - uid-range + - protocol + - ip-proto + - sport-range + - dport-range + - dscp + - + name: newrule-ntf + doc: Notify a rule creation + value: 32 + notify: newrule + - + name: delrule + doc: Remove an existing FIB rule + attribute-set: fib-rule-attrs + do: + request: + value: 33 + attributes: *fib-rule-all + - + name: delrule-ntf + doc: Notify a rule deletion + value: 33 + notify: delrule + - + name: getrule + doc: Dump all FIB rules + attribute-set: fib-rule-attrs + dump: + request: + value: 34 + reply: + value: 32 + attributes: *fib-rule-all + +mcast-groups: + list: + - + name: rtnlgrp-ipv4-rule + value: 8 + - + name: rtnlgrp-ipv6-rule + value: 19 diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml index b02d59a0349c..aacccea5dfe4 100644 --- a/Documentation/netlink/specs/tc.yaml +++ b/Documentation/netlink/specs/tc.yaml @@ -622,7 +622,7 @@ definitions: - name: max-P type: u32 - doc: probabilty, high resolution + doc: probability, high resolution - name: stats type: binary diff --git a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst index 1e196cb9ce25..af7db0e91f6b 100644 --- a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst +++ b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst @@ -14,6 +14,7 @@ Contents - `Basic packet flow`_ - `Devlink health reporters`_ - `Quality of service`_ +- `RVU representors`_ Overview ======== @@ -340,3 +341,93 @@ Setup HTB offload # tc class add dev <interface> parent 1: classid 1:2 htb rate 10Gbit prio 2 quantum 188416 # tc class add dev <interface> parent 1: classid 1:3 htb rate 10Gbit prio 2 quantum 32768 + + +RVU Representors +================ + +RVU representor driver adds support for creation of representor devices for +RVU PFs' VFs in the system. Representor devices are created when user enables +the switchdev mode. +Switchdev mode can be enabled either before or after setting up SRIOV numVFs. +All representor devices share a single NIXLF but each has a dedicated Rx/Tx +queues. RVU PF representor driver registers a separate netdev for each +Rx/Tx queue pair. + +Current HW does not support built-in switch which can do L2 learning and +forwarding packets between representee and representor. Hence, packet path +between representee and it's representor is achieved by setting up appropriate +NPC MCAM filters. +Transmit packets matching these filters will be loopbacked through hardware +loopback channel/interface (i.e, instead of sending them out of MAC interface). +Which will again match the installed filters and will be forwarded. +This way representee => representor and representor => representee packet +path is achieved. These rules get installed when representors are created +and gets active/deactivate based on the representor/representee interface state. + +Usage example: + + - Change device to switchdev mode:: + + # devlink dev eswitch set pci/0002:1c:00.0 mode switchdev + + - List of representor devices on the system:: + + # ip link show + Rpf1vf0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000 link/ether f6:43:83:ee:26:21 brd ff:ff:ff:ff:ff:ff + Rpf1vf1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000 link/ether 12:b2:54:0e:24:54 brd ff:ff:ff:ff:ff:ff + Rpf1vf2: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000 link/ether 4a:12:c4:4c:32:62 brd ff:ff:ff:ff:ff:ff + Rpf1vf3: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000 link/ether ca:cb:68:0e:e2:6e brd ff:ff:ff:ff:ff:ff + Rpf2vf0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000 link/ether 06:cc:ad:b4:f0:93 brd ff:ff:ff:ff:ff:ff + + +To delete the representors devices from the system. Change the device to legacy mode. + + - Change device to legacy mode:: + + # devlink dev eswitch set pci/0002:1c:00.0 mode legacy + +RVU representors can be managed using devlink ports +(see :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>`) interface. + + - Show devlink ports of representors:: + + # devlink port + pci/0002:1c:00.0/0: type eth netdev Rpf1vf0 flavour physical port 0 splittable false + pci/0002:1c:00.0/1: type eth netdev Rpf1vf1 flavour pcivf controller 0 pfnum 1 vfnum 1 external false splittable false + pci/0002:1c:00.0/2: type eth netdev Rpf1vf2 flavour pcivf controller 0 pfnum 1 vfnum 2 external false splittable false + pci/0002:1c:00.0/3: type eth netdev Rpf1vf3 flavour pcivf controller 0 pfnum 1 vfnum 3 external false splittable false + +Function attributes +=================== + +The RVU representor support function attributes for representors. +Port function configuration of the representors are supported through devlink eswitch port. + +MAC address setup +----------------- + +RVU representor driver support devlink port function attr mechanism to setup MAC +address. (refer to Documentation/networking/devlink/devlink-port.rst) + + - To setup MAC address for port 2:: + + # devlink port function set pci/0002:1c:00.0/2 hw_addr 5c:a1:1b:5e:43:11 + # devlink port show pci/0002:1c:00.0/2 + pci/0002:1c:00.0/2: type eth netdev Rpf1vf2 flavour pcivf controller 0 pfnum 1 vfnum 2 external false splittable false + function: + hw_addr 5c:a1:1b:5e:43:11 + + +TC offload +========== + +The rvu representor driver implements support for offloading tc rules using port representors. + + - Drop packets with vlan id 3:: + + # tc filter add dev Rpf1vf0 protocol 802.1Q parent ffff: flower vlan_id 3 vlan_ethtype ipv4 skip_sw action drop + + - Redirect packets with vlan id 5 and IPv4 packets to eth1, after stripping vlan header.:: + + # tc filter add dev Rpf1vf0 ingress protocol 802.1Q flower vlan_id 5 vlan_ethtype ipv4 skip_sw action vlan pop action mirred ingress redirect dev eth1 diff --git a/Documentation/networking/device_drivers/wwan/t7xx.rst b/Documentation/networking/device_drivers/wwan/t7xx.rst index f346f5f85f15..e07de7700dfc 100644 --- a/Documentation/networking/device_drivers/wwan/t7xx.rst +++ b/Documentation/networking/device_drivers/wwan/t7xx.rst @@ -7,12 +7,13 @@ ============================================ t7xx driver for MTK PCIe based T700 5G modem ============================================ -The t7xx driver is a WWAN PCIe host driver developed for linux or Chrome OS platforms -for data exchange over PCIe interface between Host platform & MediaTek's T700 5G modem. -The driver exposes an interface conforming to the MBIM protocol [1]. Any front end -application (e.g. Modem Manager) could easily manage the MBIM interface to enable -data communication towards WWAN. The driver also provides an interface to interact -with the MediaTek's modem via AT commands. +The t7xx driver is a WWAN PCIe host driver developed for linux or Chrome OS +platforms for data exchange over PCIe interface between Host platform & +MediaTek's T700 5G modem. +The driver exposes an interface conforming to the MBIM protocol [1]. Any front +end application (e.g. Modem Manager) could easily manage the MBIM interface to +enable data communication towards WWAN. The driver also provides an interface +to interact with the MediaTek's modem via AT commands. Basic usage =========== @@ -45,8 +46,8 @@ The driver provides sysfs interfaces to userspace. t7xx_mode --------- -The sysfs interface provides userspace with access to the device mode, this interface -supports read and write operations. +The sysfs interface provides userspace with access to the device mode, this +interface supports read and write operations. Device mode: @@ -67,6 +68,28 @@ Write from userspace to set the device mode. :: $ echo fastboot_switching > /sys/bus/pci/devices/${bdf}/t7xx_mode +t7xx_debug_ports +---------------- +The sysfs interface provides userspace with access to enable/disable the debug +ports, this interface supports read and write operations. + +Debug port status: + +- ``1`` represents enable debug ports +- ``0`` represents disable debug ports + +Currently supported debug ports (ADB/MIPC). + +Read from userspace to get the current debug ports status. + +:: + $ cat /sys/bus/pci/devices/${bdf}/t7xx_debug_ports + +Write from userspace to set the debug ports status. + +:: + $ echo 1 > /sys/bus/pci/devices/${bdf}/t7xx_debug_ports + Management application development ================================== The driver and userspace interfaces are described below. The MBIM protocol is @@ -139,6 +162,25 @@ Please note that driver needs to be reloaded to export /dev/wwan0fastboot0 port, because device needs a cold reset after enter ``fastboot_switching`` mode. +ADB port userspace ABI +---------------------- + +/dev/wwan0adb0 character device +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +The driver exposes a ADB protocol interface by implementing ADB WWAN Port. +The userspace end of the ADB channel pipe is a /dev/wwan0adb0 character device. +Application shall use this interface for ADB protocol communication. + +MIPC port userspace ABI +----------------------- + +/dev/wwan0mipc0 character device +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +The driver exposes a diagnostic interface by implementing MIPC (Modem +Information Process Center) WWAN Port. The userspace end of the MIPC channel +pipe is a /dev/wwan0mipc0 character device. +Application shall use this interface for MTK modem diagnostic communication. + The MediaTek's T700 modem supports the 3GPP TS 27.007 [4] specification. References @@ -164,3 +206,9 @@ speak the Mobile Interface Broadband Model (MBIM) protocol"* [5] *fastboot "a mechanism for communicating with bootloaders"* - https://android.googlesource.com/platform/system/core/+/refs/heads/main/fastboot/README.md + +[6] *ADB (Android Debug Bridge) "a mechanism to keep track of Android devices +and emulators instances connected to or running on a given host developer +machine with ADB protocol"* + +- https://android.googlesource.com/platform/packages/modules/adb/+/refs/heads/main/README.md diff --git a/Documentation/networking/devlink/octeontx2.rst b/Documentation/networking/devlink/octeontx2.rst index d33a90dd44bf..84206537aedb 100644 --- a/Documentation/networking/devlink/octeontx2.rst +++ b/Documentation/networking/devlink/octeontx2.rst @@ -40,6 +40,27 @@ The ``octeontx2 AF`` driver implements the following driver-specific parameters. - runtime - Use to set the quantum which hardware uses for scheduling among transmit queues. Hardware uses weighted DWRR algorithm to schedule among all transmit queues. + * - ``npc_mcam_high_zone_percent`` + - u8 + - runtime + - Use to set the number of high priority zone entries in NPC MCAM that can be allocated + by a user, out of the three priority zone categories high, mid and low. + * - ``npc_def_rule_cntr`` + - bool + - runtime + - Use to enable or disable hit counters for the default rules in NPC MCAM. + Its not guaranteed that counters gets enabled and mapped to all the default rules, + since the counters are scarce and driver follows a best effort approach. + The default rule serves as the primary packet steering rule for a specific PF or VF, + based on its DMAC address which is installed by AF driver as part of its initialization. + Sample command to read hit counters for default rule from debugfs is as follows, + cat /sys/kernel/debug/cn10k/npc/mcam_rules + * - ``nix_maxlf`` + - u16 + - runtime + - Use to set the maximum number of LFs in NIX hardware block. This would be useful + to increase the availability of default resources allocated to enabled LFs like + MCAM entries for example. The ``octeontx2 PF`` driver implements the following driver-specific parameters. diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst index e4bd7aa1f5aa..544bad175aae 100644 --- a/Documentation/networking/j1939.rst +++ b/Documentation/networking/j1939.rst @@ -121,7 +121,7 @@ format, the Group Extension is set in the PS-field. On the other hand, when using PDU1 format, the PS-field contains a so-called Destination Address, which is _not_ part of the PGN. When communicating a PGN -from user space to kernel (or vice versa) and PDU2 format is used, the PS-field +from user space to kernel (or vice versa) and PDU1 format is used, the PS-field of the PGN shall be set to zero. The Destination Address shall be set elsewhere. diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst index dfa5d549be9c..02720dd71a76 100644 --- a/Documentation/networking/napi.rst +++ b/Documentation/networking/napi.rst @@ -192,6 +192,33 @@ is reused to control the delay of the timer, while ``napi_defer_hard_irqs`` controls the number of consecutive empty polls before NAPI gives up and goes back to using hardware IRQs. +The above parameters can also be set on a per-NAPI basis using netlink via +netdev-genl. When used with netlink and configured on a per-NAPI basis, the +parameters mentioned above use hyphens instead of underscores: +``gro-flush-timeout`` and ``napi-defer-hard-irqs``. + +Per-NAPI configuration can be done programmatically in a user application +or by using a script included in the kernel source tree: +``tools/net/ynl/cli.py``. + +For example, using the script: + +.. code-block:: bash + + $ kernel-source/tools/net/ynl/cli.py \ + --spec Documentation/netlink/specs/netdev.yaml \ + --do napi-set \ + --json='{"id": 345, + "defer-hard-irqs": 111, + "gro-flush-timeout": 11111}' + +Similarly, the parameter ``irq-suspend-timeout`` can be set using netlink +via netdev-genl. There is no global sysfs parameter for this value. + +``irq-suspend-timeout`` is used to determine how long an application can +completely suspend IRQs. It is used in combination with SO_PREFER_BUSY_POLL, +which can be set on a per-epoll context basis with ``EPIOCSPARAMS`` ioctl. + .. _poll: Busy polling @@ -207,6 +234,46 @@ selected sockets or using the global ``net.core.busy_poll`` and ``net.core.busy_read`` sysctls. An io_uring API for NAPI busy polling also exists. +epoll-based busy polling +------------------------ + +It is possible to trigger packet processing directly from calls to +``epoll_wait``. In order to use this feature, a user application must ensure +all file descriptors which are added to an epoll context have the same NAPI ID. + +If the application uses a dedicated acceptor thread, the application can obtain +the NAPI ID of the incoming connection using SO_INCOMING_NAPI_ID and then +distribute that file descriptor to a worker thread. The worker thread would add +the file descriptor to its epoll context. This would ensure each worker thread +has an epoll context with FDs that have the same NAPI ID. + +Alternatively, if the application uses SO_REUSEPORT, a bpf or ebpf program can +be inserted to distribute incoming connections to threads such that each thread +is only given incoming connections with the same NAPI ID. Care must be taken to +carefully handle cases where a system may have multiple NICs. + +In order to enable busy polling, there are two choices: + +1. ``/proc/sys/net/core/busy_poll`` can be set with a time in useconds to busy + loop waiting for events. This is a system-wide setting and will cause all + epoll-based applications to busy poll when they call epoll_wait. This may + not be desirable as many applications may not have the need to busy poll. + +2. Applications using recent kernels can issue an ioctl on the epoll context + file descriptor to set (``EPIOCSPARAMS``) or get (``EPIOCGPARAMS``) ``struct + epoll_params``:, which user programs can define as follows: + +.. code-block:: c + + struct epoll_params { + uint32_t busy_poll_usecs; + uint16_t busy_poll_budget; + uint8_t prefer_busy_poll; + + /* pad the struct to a multiple of 64bits */ + uint8_t __pad; + }; + IRQ mitigation --------------- @@ -222,12 +289,111 @@ Such applications can pledge to the kernel that they will perform a busy polling operation periodically, and the driver should keep the device IRQs permanently masked. This mode is enabled by using the ``SO_PREFER_BUSY_POLL`` socket option. To avoid system misbehavior the pledge is revoked -if ``gro_flush_timeout`` passes without any busy poll call. +if ``gro_flush_timeout`` passes without any busy poll call. For epoll-based +busy polling applications, the ``prefer_busy_poll`` field of ``struct +epoll_params`` can be set to 1 and the ``EPIOCSPARAMS`` ioctl can be issued to +enable this mode. See the above section for more details. The NAPI budget for busy polling is lower than the default (which makes sense given the low latency intention of normal busy polling). This is not the case with IRQ mitigation, however, so the budget can be adjusted -with the ``SO_BUSY_POLL_BUDGET`` socket option. +with the ``SO_BUSY_POLL_BUDGET`` socket option. For epoll-based busy polling +applications, the ``busy_poll_budget`` field can be adjusted to the desired value +in ``struct epoll_params`` and set on a specific epoll context using the ``EPIOCSPARAMS`` +ioctl. See the above section for more details. + +It is important to note that choosing a large value for ``gro_flush_timeout`` +will defer IRQs to allow for better batch processing, but will induce latency +when the system is not fully loaded. Choosing a small value for +``gro_flush_timeout`` can cause interference of the user application which is +attempting to busy poll by device IRQs and softirq processing. This value +should be chosen carefully with these tradeoffs in mind. epoll-based busy +polling applications may be able to mitigate how much user processing happens +by choosing an appropriate value for ``maxevents``. + +Users may want to consider an alternate approach, IRQ suspension, to help deal +with these tradeoffs. + +IRQ suspension +-------------- + +IRQ suspension is a mechanism wherein device IRQs are masked while epoll +triggers NAPI packet processing. + +While application calls to epoll_wait successfully retrieve events, the kernel will +defer the IRQ suspension timer. If the kernel does not retrieve any events +while busy polling (for example, because network traffic levels subsided), IRQ +suspension is disabled and the IRQ mitigation strategies described above are +engaged. + +This allows users to balance CPU consumption with network processing +efficiency. + +To use this mechanism: + + 1. The per-NAPI config parameter ``irq-suspend-timeout`` should be set to the + maximum time (in nanoseconds) the application can have its IRQs + suspended. This is done using netlink, as described above. This timeout + serves as a safety mechanism to restart IRQ driver interrupt processing if + the application has stalled. This value should be chosen so that it covers + the amount of time the user application needs to process data from its + call to epoll_wait, noting that applications can control how much data + they retrieve by setting ``max_events`` when calling epoll_wait. + + 2. The sysfs parameter or per-NAPI config parameters ``gro_flush_timeout`` + and ``napi_defer_hard_irqs`` can be set to low values. They will be used + to defer IRQs after busy poll has found no data. + + 3. The ``prefer_busy_poll`` flag must be set to true. This can be done using + the ``EPIOCSPARAMS`` ioctl as described above. + + 4. The application uses epoll as described above to trigger NAPI packet + processing. + +As mentioned above, as long as subsequent calls to epoll_wait return events to +userland, the ``irq-suspend-timeout`` is deferred and IRQs are disabled. This +allows the application to process data without interference. + +Once a call to epoll_wait results in no events being found, IRQ suspension is +automatically disabled and the ``gro_flush_timeout`` and +``napi_defer_hard_irqs`` mitigation mechanisms take over. + +It is expected that ``irq-suspend-timeout`` will be set to a value much larger +than ``gro_flush_timeout`` as ``irq-suspend-timeout`` should suspend IRQs for +the duration of one userland processing cycle. + +While it is not stricly necessary to use ``napi_defer_hard_irqs`` and +``gro_flush_timeout`` to use IRQ suspension, their use is strongly +recommended. + +IRQ suspension causes the system to alternate between polling mode and +irq-driven packet delivery. During busy periods, ``irq-suspend-timeout`` +overrides ``gro_flush_timeout`` and keeps the system busy polling, but when +epoll finds no events, the setting of ``gro_flush_timeout`` and +``napi_defer_hard_irqs`` determine the next step. + +There are essentially three possible loops for network processing and +packet delivery: + +1) hardirq -> softirq -> napi poll; basic interrupt delivery +2) timer -> softirq -> napi poll; deferred irq processing +3) epoll -> busy-poll -> napi poll; busy looping + +Loop 2 can take control from Loop 1, if ``gro_flush_timeout`` and +``napi_defer_hard_irqs`` are set. + +If ``gro_flush_timeout`` and ``napi_defer_hard_irqs`` are set, Loops 2 +and 3 "wrestle" with each other for control. + +During busy periods, ``irq-suspend-timeout`` is used as timer in Loop 2, +which essentially tilts network processing in favour of Loop 3. + +If ``gro_flush_timeout`` and ``napi_defer_hard_irqs`` are not set, Loop 3 +cannot take control from Loop 1. + +Therefore, setting ``gro_flush_timeout`` and ``napi_defer_hard_irqs`` is +the recommended usage, because otherwise setting ``irq-suspend-timeout`` +might not have any discernible effect. .. _threaded: diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index ade50d4e67cf..15e31ece675f 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -188,4 +188,5 @@ u64 max_pacing_offload_horizon struct_napi_config* napi_config unsigned_long gro_flush_timeout u32 napi_defer_hard_irqs +struct hlist_head neighbours[2] =================================== =========================== =================== =================== =================================================================================== diff --git a/Documentation/networking/net_dim.rst b/Documentation/networking/net_dim.rst index 8908fd7b0a8d..4377998e6826 100644 --- a/Documentation/networking/net_dim.rst +++ b/Documentation/networking/net_dim.rst @@ -156,7 +156,7 @@ usage is not complete but it should make the outline of the usage clear. my_entity->bytes, &dim_sample); /* Call net DIM */ - net_dim(&my_entity->dim, dim_sample); + net_dim(&my_entity->dim, &dim_sample); ... } diff --git a/Documentation/networking/packet_mmap.rst b/Documentation/networking/packet_mmap.rst index dca15d15feaf..02370786e77b 100644 --- a/Documentation/networking/packet_mmap.rst +++ b/Documentation/networking/packet_mmap.rst @@ -16,7 +16,7 @@ ii) transmit network traffic, or any other that needs raw Howto can be found at: - https://sites.google.com/site/packetmmap/ + https://web.archive.org/web/20220404160947/https://sites.google.com/site/packetmmap/ Please send your comments to - Ulisses Alonso Camaró <[email protected]> @@ -166,7 +166,8 @@ As capture, each frame contains two parts:: /* bind socket to eth0 */ bind(this->socket, (struct sockaddr *)&my_addr, sizeof(struct sockaddr_ll)); - A complete tutorial is available at: https://sites.google.com/site/packetmmap/ + A complete tutorial is available at: + https://web.archive.org/web/20220404160947/https://sites.google.com/site/packetmmap/ By default, the user should put data at:: diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst index 750ff371570a..54be7ddf3e57 100644 --- a/Documentation/rust/arch-support.rst +++ b/Documentation/rust/arch-support.rst @@ -17,7 +17,7 @@ Architecture Level of support Constraints ============= ================ ============================================== ``arm64`` Maintained Little Endian only. ``loongarch`` Maintained \- -``riscv`` Maintained ``riscv64`` only. +``riscv`` Maintained ``riscv64`` and LLVM/Clang only. ``um`` Maintained \- ``x86`` Maintained ``x86_64`` only. ============= ================ ============================================== diff --git a/Documentation/userspace-api/mseal.rst b/Documentation/userspace-api/mseal.rst index 4132eec995a3..41102f74c5e2 100644 --- a/Documentation/userspace-api/mseal.rst +++ b/Documentation/userspace-api/mseal.rst @@ -23,177 +23,166 @@ applications can additionally seal security critical data at runtime. A similar feature already exists in the XNU kernel with the VM_FLAGS_PERMANENT flag [1] and on OpenBSD with the mimmutable syscall [2]. -User API -======== -mseal() ------------ -The mseal() syscall has the following signature: - -``int mseal(void addr, size_t len, unsigned long flags)`` - -**addr/len**: virtual memory address range. - -The address range set by ``addr``/``len`` must meet: - - The start address must be in an allocated VMA. - - The start address must be page aligned. - - The end address (``addr`` + ``len``) must be in an allocated VMA. - - no gap (unallocated memory) between start and end address. - -The ``len`` will be paged aligned implicitly by the kernel. - -**flags**: reserved for future use. - -**return values**: - -- ``0``: Success. - -- ``-EINVAL``: - - Invalid input ``flags``. - - The start address (``addr``) is not page aligned. - - Address range (``addr`` + ``len``) overflow. - -- ``-ENOMEM``: - - The start address (``addr``) is not allocated. - - The end address (``addr`` + ``len``) is not allocated. - - A gap (unallocated memory) between start and end address. - -- ``-EPERM``: - - sealing is supported only on 64-bit CPUs, 32-bit is not supported. - -- For above error cases, users can expect the given memory range is - unmodified, i.e. no partial update. - -- There might be other internal errors/cases not listed here, e.g. - error during merging/splitting VMAs, or the process reaching the max - number of supported VMAs. In those cases, partial updates to the given - memory range could happen. However, those cases should be rare. - -**Blocked operations after sealing**: - Unmapping, moving to another location, and shrinking the size, - via munmap() and mremap(), can leave an empty space, therefore - can be replaced with a VMA with a new set of attributes. - - Moving or expanding a different VMA into the current location, - via mremap(). - - Modifying a VMA via mmap(MAP_FIXED). - - Size expansion, via mremap(), does not appear to pose any - specific risks to sealed VMAs. It is included anyway because - the use case is unclear. In any case, users can rely on - merging to expand a sealed VMA. - - mprotect() and pkey_mprotect(). - - Some destructive madvice() behaviors (e.g. MADV_DONTNEED) - for anonymous memory, when users don't have write permission to the - memory. Those behaviors can alter region contents by discarding pages, - effectively a memset(0) for anonymous memory. - - Kernel will return -EPERM for blocked operations. - - For blocked operations, one can expect the given address is unmodified, - i.e. no partial update. Note, this is different from existing mm - system call behaviors, where partial updates are made till an error is - found and returned to userspace. To give an example: - - Assume following code sequence: - - - ptr = mmap(null, 8192, PROT_NONE); - - munmap(ptr + 4096, 4096); - - ret1 = mprotect(ptr, 8192, PROT_READ); - - mseal(ptr, 4096); - - ret2 = mprotect(ptr, 8192, PROT_NONE); - - ret1 will be -ENOMEM, the page from ptr is updated to PROT_READ. - - ret2 will be -EPERM, the page remains to be PROT_READ. - -**Note**: - -- mseal() only works on 64-bit CPUs, not 32-bit CPU. - -- users can call mseal() multiple times, mseal() on an already sealed memory - is a no-action (not error). - -- munseal() is not supported. - -Use cases: -========== +SYSCALL +======= +mseal syscall signature +----------------------- + ``int mseal(void \* addr, size_t len, unsigned long flags)`` + + **addr**/**len**: virtual memory address range. + The address range set by **addr**/**len** must meet: + - The start address must be in an allocated VMA. + - The start address must be page aligned. + - The end address (**addr** + **len**) must be in an allocated VMA. + - no gap (unallocated memory) between start and end address. + + The ``len`` will be paged aligned implicitly by the kernel. + + **flags**: reserved for future use. + + **Return values**: + - **0**: Success. + - **-EINVAL**: + * Invalid input ``flags``. + * The start address (``addr``) is not page aligned. + * Address range (``addr`` + ``len``) overflow. + - **-ENOMEM**: + * The start address (``addr``) is not allocated. + * The end address (``addr`` + ``len``) is not allocated. + * A gap (unallocated memory) between start and end address. + - **-EPERM**: + * sealing is supported only on 64-bit CPUs, 32-bit is not supported. + + **Note about error return**: + - For above error cases, users can expect the given memory range is + unmodified, i.e. no partial update. + - There might be other internal errors/cases not listed here, e.g. + error during merging/splitting VMAs, or the process reaching the maximum + number of supported VMAs. In those cases, partial updates to the given + memory range could happen. However, those cases should be rare. + + **Architecture support**: + mseal only works on 64-bit CPUs, not 32-bit CPUs. + + **Idempotent**: + users can call mseal multiple times. mseal on an already sealed memory + is a no-action (not error). + + **no munseal** + Once mapping is sealed, it can't be unsealed. The kernel should never + have munseal, this is consistent with other sealing feature, e.g. + F_SEAL_SEAL for file. + +Blocked mm syscall for sealed mapping +------------------------------------- + It might be important to note: **once the mapping is sealed, it will + stay in the process's memory until the process terminates**. + + Example:: + + *ptr = mmap(0, 4096, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + rc = mseal(ptr, 4096, 0); + /* munmap will fail */ + rc = munmap(ptr, 4096); + assert(rc < 0); + + Blocked mm syscall: + - munmap + - mmap + - mremap + - mprotect and pkey_mprotect + - some destructive madvise behaviors: MADV_DONTNEED, MADV_FREE, + MADV_DONTNEED_LOCKED, MADV_FREE, MADV_DONTFORK, MADV_WIPEONFORK + + The first set of syscalls to block is munmap, mremap, mmap. They can + either leave an empty space in the address space, therefore allowing + replacement with a new mapping with new set of attributes, or can + overwrite the existing mapping with another mapping. + + mprotect and pkey_mprotect are blocked because they changes the + protection bits (RWX) of the mapping. + + Certain destructive madvise behaviors, specifically MADV_DONTNEED, + MADV_FREE, MADV_DONTNEED_LOCKED, and MADV_WIPEONFORK, can introduce + risks when applied to anonymous memory by threads lacking write + permissions. Consequently, these operations are prohibited under such + conditions. The aforementioned behaviors have the potential to modify + region contents by discarding pages, effectively performing a memset(0) + operation on the anonymous memory. + + Kernel will return -EPERM for blocked syscalls. + + When blocked syscall return -EPERM due to sealing, the memory regions may + or may not be changed, depends on the syscall being blocked: + + - munmap: munmap is atomic. If one of VMAs in the given range is + sealed, none of VMAs are updated. + - mprotect, pkey_mprotect, madvise: partial update might happen, e.g. + when mprotect over multiple VMAs, mprotect might update the beginning + VMAs before reaching the sealed VMA and return -EPERM. + - mmap and mremap: undefined behavior. + +Use cases +========= - glibc: The dynamic linker, during loading ELF executables, can apply sealing to - non-writable memory segments. - -- Chrome browser: protect some security sensitive data-structures. + mapping segments. -Notes on which memory to seal: -============================== +- Chrome browser: protect some security sensitive data structures. -It might be important to note that sealing changes the lifetime of a mapping, -i.e. the sealed mapping won’t be unmapped till the process terminates or the -exec system call is invoked. Applications can apply sealing to any virtual -memory region from userspace, but it is crucial to thoroughly analyze the -mapping's lifetime prior to apply the sealing. +When not to use mseal +===================== +Applications can apply sealing to any virtual memory region from userspace, +but it is *crucial to thoroughly analyze the mapping's lifetime* prior to +apply the sealing. This is because the sealed mapping *won’t be unmapped* +until the process terminates or the exec system call is invoked. For example: + - aio/shm + aio/shm can call mmap and munmap on behalf of userspace, e.g. + ksys_shmdt() in shm.c. The lifetimes of those mapping are not tied to + the lifetime of the process. If those memories are sealed from userspace, + then munmap will fail, causing leaks in VMA address space during the + lifetime of the process. + + - ptr allocated by malloc (heap) + Don't use mseal on the memory ptr return from malloc(). + malloc() is implemented by allocator, e.g. by glibc. Heap manager might + allocate a ptr from brk or mapping created by mmap. + If an app calls mseal on a ptr returned from malloc(), this can affect + the heap manager's ability to manage the mappings; the outcome is + non-deterministic. + + Example:: + + ptr = malloc(size); + /* don't call mseal on ptr return from malloc. */ + mseal(ptr, size); + /* free will success, allocator can't shrink heap lower than ptr */ + free(ptr); + +mseal doesn't block +=================== +In a nutshell, mseal blocks certain mm syscall from modifying some of VMA's +attributes, such as protection bits (RWX). Sealed mappings doesn't mean the +memory is immutable. -- aio/shm - - aio/shm can call mmap()/munmap() on behalf of userspace, e.g. ksys_shmdt() in - shm.c. The lifetime of those mapping are not tied to the lifetime of the - process. If those memories are sealed from userspace, then munmap() will fail, - causing leaks in VMA address space during the lifetime of the process. - -- Brk (heap) - - Currently, userspace applications can seal parts of the heap by calling - malloc() and mseal(). - let's assume following calls from user space: - - - ptr = malloc(size); - - mprotect(ptr, size, RO); - - mseal(ptr, size); - - free(ptr); - - Technically, before mseal() is added, the user can change the protection of - the heap by calling mprotect(RO). As long as the user changes the protection - back to RW before free(), the memory range can be reused. - - Adding mseal() into the picture, however, the heap is then sealed partially, - the user can still free it, but the memory remains to be RO. If the address - is re-used by the heap manager for another malloc, the process might crash - soon after. Therefore, it is important not to apply sealing to any memory - that might get recycled. - - Furthermore, even if the application never calls the free() for the ptr, - the heap manager may invoke the brk system call to shrink the size of the - heap. In the kernel, the brk-shrink will call munmap(). Consequently, - depending on the location of the ptr, the outcome of brk-shrink is - nondeterministic. - - -Additional notes: -================= As Jann Horn pointed out in [3], there are still a few ways to write -to RO memory, which is, in a way, by design. Those cases are not covered -by mseal(). If applications want to block such cases, sandbox tools (such as -seccomp, LSM, etc) might be considered. +to RO memory, which is, in a way, by design. And those could be blocked +by different security measures. Those cases are: -- Write to read-only memory through /proc/self/mem interface. -- Write to read-only memory through ptrace (such as PTRACE_POKETEXT). -- userfaultfd. + - Write to read-only memory through /proc/self/mem interface (FOLL_FORCE). + - Write to read-only memory through ptrace (such as PTRACE_POKETEXT). + - userfaultfd. The idea that inspired this patch comes from Stephen Röttger’s work in V8 CFI [4]. Chrome browser in ChromeOS will be the first user of this API. -Reference: -========== -[1] https://github.com/apple-oss-distributions/xnu/blob/1031c584a5e37aff177559b9f69dbd3c8c3fd30a/osfmk/mach/vm_statistics.h#L274 - -[2] https://man.openbsd.org/mimmutable.2 - -[3] https://lore.kernel.org/lkml/CAG48ez3ShUYey+ZAFsU2i1RpQn0a5eOs2hzQ426FkcgnfUGLvA@mail.gmail.com - -[4] https://docs.google.com/document/d/1O2jwK4dxI3nRcOJuPYkonhTkNQfbmwdvxQMyXgeaRHo/edit#heading=h.bvaojj9fu6hc +Reference +========= +- [1] https://github.com/apple-oss-distributions/xnu/blob/1031c584a5e37aff177559b9f69dbd3c8c3fd30a/osfmk/mach/vm_statistics.h#L274 +- [2] https://man.openbsd.org/mimmutable.2 +- [3] https://lore.kernel.org/lkml/CAG48ez3ShUYey+ZAFsU2i1RpQn0a5eOs2hzQ426FkcgnfUGLvA@mail.gmail.com +- [4] https://docs.google.com/document/d/1O2jwK4dxI3nRcOJuPYkonhTkNQfbmwdvxQMyXgeaRHo/edit#heading=h.bvaojj9fu6hc diff --git a/MAINTAINERS b/MAINTAINERS index f39ab140710f..675bd38630b7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2852,7 +2852,7 @@ F: Documentation/devicetree/bindings/arm/qcom.yaml F: Documentation/devicetree/bindings/bus/qcom* F: Documentation/devicetree/bindings/cache/qcom,llcc.yaml F: Documentation/devicetree/bindings/firmware/qcom,scm.yaml -F: Documentation/devicetree/bindings/reserved-memory/qcom +F: Documentation/devicetree/bindings/reserved-memory/qcom* F: Documentation/devicetree/bindings/soc/qcom/ F: arch/arm/boot/dts/qcom/ F: arch/arm/configs/qcom_defconfig @@ -3745,6 +3745,7 @@ F: drivers/spi/spi-axi-spi-engine.c AXI PWM GENERATOR M: Michael Hennerich <[email protected]> M: Nuno Sá <[email protected]> +R: Trevor Gamblin <[email protected]> S: Supported W: https://ez.analog.com/linux-software-drivers @@ -8996,9 +8997,16 @@ F: drivers/dma/fsl-edma*.* FREESCALE ENETC ETHERNET DRIVERS M: Claudiu Manoil <[email protected]> M: Vladimir Oltean <[email protected]> +M: Wei Fang <[email protected]> +M: Clark Wang <[email protected]> S: Maintained +F: Documentation/devicetree/bindings/net/fsl,enetc*.yaml +F: Documentation/devicetree/bindings/net/nxp,netc-blk-ctrl.yaml F: drivers/net/ethernet/freescale/enetc/ +F: include/linux/fsl/enetc_mdio.h +F: include/linux/fsl/netc_global.h FREESCALE eTSEC ETHERNET DRIVER (GIANFAR) M: Claudiu Manoil <[email protected]> @@ -9723,6 +9731,7 @@ F: include/dt-bindings/gpio/ F: include/linux/gpio.h F: include/linux/gpio/ F: include/linux/of_gpio.h +K: (devm_)?gpio_(request|free|direction|get|set) GPIO UAPI M: Bartosz Golaszewski <[email protected]> @@ -14146,6 +14155,15 @@ S: Maintained T: git git://linuxtv.org/media_tree.git F: drivers/media/platform/nxp/imx-pxp.[ch] +MEDIA DRIVERS FOR ASCOT2E +M: Abylay Ospan <[email protected]> +S: Supported +W: https://linuxtv.org +W: http://netup.tv/ +T: git git://linuxtv.org/media_tree.git +F: drivers/media/dvb-frontends/ascot2e* + MEDIA DRIVERS FOR CXD2099AR CI CONTROLLERS M: Jasmin Jessich <[email protected]> @@ -14154,6 +14172,15 @@ W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git F: drivers/media/dvb-frontends/cxd2099* +MEDIA DRIVERS FOR CXD2841ER +M: Abylay Ospan <[email protected]> +S: Supported +W: https://linuxtv.org +W: http://netup.tv/ +T: git git://linuxtv.org/media_tree.git +F: drivers/media/dvb-frontends/cxd2841er* + MEDIA DRIVERS FOR CXD2880 M: Yasunari Takiguchi <[email protected]> @@ -14198,6 +14225,33 @@ F: drivers/media/platform/nxp/imx-mipi-csis.c F: drivers/media/platform/nxp/imx7-media-csi.c F: drivers/media/platform/nxp/imx8mq-mipi-csi2.c +MEDIA DRIVERS FOR HELENE +M: Abylay Ospan <[email protected]> +S: Supported +W: https://linuxtv.org +W: http://netup.tv/ +T: git git://linuxtv.org/media_tree.git +F: drivers/media/dvb-frontends/helene* + +MEDIA DRIVERS FOR HORUS3A +M: Abylay Ospan <[email protected]> +S: Supported +W: https://linuxtv.org +W: http://netup.tv/ +T: git git://linuxtv.org/media_tree.git +F: drivers/media/dvb-frontends/horus3a* + +MEDIA DRIVERS FOR LNBH25 +M: Abylay Ospan <[email protected]> +S: Supported +W: https://linuxtv.org +W: http://netup.tv/ +T: git git://linuxtv.org/media_tree.git +F: drivers/media/dvb-frontends/lnbh25* + MEDIA DRIVERS FOR MXL5XX TUNER DEMODULATORS S: Orphan @@ -14205,6 +14259,15 @@ W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git F: drivers/media/dvb-frontends/mxl5xx* +MEDIA DRIVERS FOR NETUP PCI UNIVERSAL DVB devices +M: Abylay Ospan <[email protected]> +S: Supported +W: https://linuxtv.org +W: http://netup.tv/ +T: git git://linuxtv.org/media_tree.git +F: drivers/media/pci/netup_unidvb/* + MEDIA DRIVERS FOR NVIDIA TEGRA - VDE M: Dmitry Osipenko <[email protected]> @@ -14376,8 +14439,10 @@ M: Qingfang Deng <[email protected]> M: SkyLake Huang <[email protected]> S: Maintained -F: drivers/net/phy/mediatek-ge-soc.c -F: drivers/net/phy/mediatek-ge.c +F: drivers/net/phy/mediatek/mtk-ge-soc.c +F: drivers/net/phy/mediatek/mtk-phy-lib.c +F: drivers/net/phy/mediatek/mtk-ge.c +F: drivers/net/phy/mediatek/mtk.h F: drivers/phy/mediatek/phy-mtk-xfi-tphy.c MEDIATEK I2C CONTROLLER DRIVER @@ -14992,6 +15057,7 @@ F: drivers/spi/spi-at91-usart.c MICROCHIP AUDIO ASOC DRIVERS M: Claudiu Beznea <[email protected]> +M: Andrei Simion <[email protected]> S: Supported F: Documentation/devicetree/bindings/sound/atmel* @@ -15091,6 +15157,13 @@ S: Maintained F: Documentation/devicetree/bindings/interrupt-controller/microchip,lan966x-oic.yaml F: drivers/irqchip/irq-lan966x-oic.c +MICROCHIP LAN969X ETHERNET DRIVER +M: Daniel Machon <[email protected]> +S: Maintained +F: drivers/net/ethernet/microchip/lan969x/* + MICROCHIP LCDFB DRIVER M: Nicolas Ferre <[email protected]> @@ -15100,6 +15173,7 @@ F: include/video/atmel_lcdc.h MICROCHIP MCP16502 PMIC DRIVER M: Claudiu Beznea <[email protected]> +M: Andrei Simion <[email protected]> L: [email protected] (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/regulator/microchip,mcp16502.yaml @@ -15230,6 +15304,7 @@ F: drivers/spi/spi-atmel.* MICROCHIP SSC DRIVER M: Claudiu Beznea <[email protected]> +M: Andrei Simion <[email protected]> L: [email protected] (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/misc/atmel-ssc.txt @@ -16031,7 +16106,6 @@ F: drivers/net/wireless/ NETWORKING [DSA] M: Andrew Lunn <[email protected]> -M: Florian Fainelli <[email protected]> M: Vladimir Oltean <[email protected]> S: Maintained F: Documentation/devicetree/bindings/net/dsa/ @@ -19803,12 +19877,10 @@ L: [email protected] S: Maintained Q: https://patchwork.kernel.org/project/linux-riscv/list/ T: git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/ -F: Documentation/devicetree/bindings/riscv/ -F: arch/riscv/boot/dts/ -X: arch/riscv/boot/dts/allwinner/ -X: arch/riscv/boot/dts/renesas/ -X: arch/riscv/boot/dts/sophgo/ -X: arch/riscv/boot/dts/thead/ +F: arch/riscv/boot/dts/canaan/ +F: arch/riscv/boot/dts/microchip/ +F: arch/riscv/boot/dts/sifive/ +F: arch/riscv/boot/dts/starfive/ RISC-V PMU DRIVERS M: Atish Patra <[email protected]> @@ -19827,8 +19899,10 @@ L: [email protected] S: Maintained T: git https://github.com/pdp7/linux.git F: Documentation/devicetree/bindings/clock/thead,th1520-clk-ap.yaml +F: Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml F: arch/riscv/boot/dts/thead/ F: drivers/clk/thead/clk-th1520-ap.c +F: drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c F: include/dt-bindings/clock/thead,th1520-clk-ap.h RNBD BLOCK DRIVERS @@ -20204,6 +20278,12 @@ F: Documentation/arch/s390/pci.rst F: arch/s390/pci/ F: drivers/pci/hotplug/s390_pci_hpc.c +S390 PTP DRIVER +M: Sven Schnelle <[email protected]> +S: Supported +F: drivers/ptp/ptp_s390.c + S390 SCM DRIVER M: Vineeth Vijayan <[email protected]> @@ -23154,7 +23234,7 @@ F: Documentation/devicetree/bindings/iio/adc/ti,lmp92064.yaml F: drivers/iio/adc/ti-lmp92064.c TI PCM3060 ASoC CODEC DRIVER -M: Kirill Marinushkin <[email protected]> +M: Kirill Marinushkin <[email protected]> S: Maintained F: Documentation/devicetree/bindings/sound/pcm3060.txt @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 12 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc6 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 00163e4a237c..bd9f095d69fa 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -855,14 +855,14 @@ config HAVE_CFI_ICALL_NORMALIZE_INTEGERS_CLANG def_bool y depends on $(cc-option,-fsanitize=kcfi -fsanitize-cfi-icall-experimental-normalize-integers) # With GCOV/KASAN we need this fix: https://github.com/llvm/llvm-project/pull/104826 - depends on CLANG_VERSION >= 190000 || (!GCOV_KERNEL && !KASAN_GENERIC && !KASAN_SW_TAGS) + depends on CLANG_VERSION >= 190103 || (!GCOV_KERNEL && !KASAN_GENERIC && !KASAN_SW_TAGS) config HAVE_CFI_ICALL_NORMALIZE_INTEGERS_RUSTC def_bool y depends on HAVE_CFI_ICALL_NORMALIZE_INTEGERS_CLANG depends on RUSTC_VERSION >= 107900 # With GCOV/KASAN we need this fix: https://github.com/rust-lang/rust/pull/129373 - depends on (RUSTC_LLVM_VERSION >= 190000 && RUSTC_VERSION >= 108200) || \ + depends on (RUSTC_LLVM_VERSION >= 190103 && RUSTC_VERSION >= 108200) || \ (!GCOV_KERNEL && !KASAN_GENERIC && !KASAN_SW_TAGS) config CFI_PERMISSIVE diff --git a/arch/arm/boot/dts/rockchip/rk3036-kylin.dts b/arch/arm/boot/dts/rockchip/rk3036-kylin.dts index e32c73d32f0a..2f84e2805712 100644 --- a/arch/arm/boot/dts/rockchip/rk3036-kylin.dts +++ b/arch/arm/boot/dts/rockchip/rk3036-kylin.dts @@ -325,8 +325,8 @@ &i2c2 { status = "okay"; - rt5616: rt5616@1b { - compatible = "rt5616"; + rt5616: audio-codec@1b { + compatible = "realtek,rt5616"; reg = <0x1b>; clocks = <&cru SCLK_I2S_OUT>; clock-names = "mclk"; diff --git a/arch/arm/boot/dts/rockchip/rk3036.dtsi b/arch/arm/boot/dts/rockchip/rk3036.dtsi index 96279d1e02fe..63b9912be06a 100644 --- a/arch/arm/boot/dts/rockchip/rk3036.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3036.dtsi @@ -384,12 +384,13 @@ }; }; - acodec: acodec-ana@20030000 { - compatible = "rk3036-codec"; + acodec: audio-codec@20030000 { + compatible = "rockchip,rk3036-codec"; reg = <0x20030000 0x4000>; - rockchip,grf = <&grf>; clock-names = "acodec_pclk"; clocks = <&cru PCLK_ACODEC>; + rockchip,grf = <&grf>; + #sound-dai-cells = <0>; status = "disabled"; }; @@ -399,7 +400,6 @@ interrupts = <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru PCLK_HDMI>; clock-names = "pclk"; - rockchip,grf = <&grf>; pinctrl-names = "default"; pinctrl-0 = <&hdmi_ctl>; #sound-dai-cells = <0>; @@ -553,11 +553,11 @@ }; spi: spi@20074000 { - compatible = "rockchip,rockchip-spi"; + compatible = "rockchip,rk3036-spi"; reg = <0x20074000 0x1000>; interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&cru PCLK_SPI>, <&cru SCLK_SPI>; - clock-names = "apb-pclk","spi_pclk"; + clocks = <&cru SCLK_SPI>, <&cru PCLK_SPI>; + clock-names = "spiclk", "apb_pclk"; dmas = <&pdma 8>, <&pdma 9>; dma-names = "tx", "rx"; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-lvds0.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-lvds0.dtsi index d00036204a8c..dad0dc8fb431 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-lvds0.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-lvds0.dtsi @@ -14,7 +14,7 @@ lvds0_subsys: bus@56240000 { compatible = "fsl,imx8qxp-lpcg"; reg = <0x56243000 0x4>; #clock-cells = <1>; - clock-output-names = "mipi1_lis_lpcg_ipg_clk"; + clock-output-names = "lvds0_lis_lpcg_ipg_clk"; power-domains = <&pd IMX_SC_R_MIPI_1>; }; @@ -22,9 +22,9 @@ lvds0_subsys: bus@56240000 { compatible = "fsl,imx8qxp-lpcg"; reg = <0x5624300c 0x4>; #clock-cells = <1>; - clock-output-names = "mipi1_pwm_lpcg_clk", - "mipi1_pwm_lpcg_ipg_clk", - "mipi1_pwm_lpcg_32k_clk"; + clock-output-names = "lvds0_pwm_lpcg_clk", + "lvds0_pwm_lpcg_ipg_clk", + "lvds0_pwm_lpcg_32k_clk"; power-domains = <&pd IMX_SC_R_MIPI_1_PWM_0>; }; @@ -32,8 +32,8 @@ lvds0_subsys: bus@56240000 { compatible = "fsl,imx8qxp-lpcg"; reg = <0x56243010 0x4>; #clock-cells = <1>; - clock-output-names = "mipi1_i2c0_lpcg_clk", - "mipi1_i2c0_lpcg_ipg_clk"; + clock-output-names = "lvds0_i2c0_lpcg_clk", + "lvds0_i2c0_lpcg_ipg_clk"; power-domains = <&pd IMX_SC_R_MIPI_1_I2C_0>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-vpu.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-vpu.dtsi index c6540768bdb9..87211c18d65a 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-vpu.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-vpu.dtsi @@ -15,7 +15,7 @@ vpu: vpu@2c000000 { mu_m0: mailbox@2d000000 { compatible = "fsl,imx6sx-mu"; reg = <0x2d000000 0x20000>; - interrupts = <GIC_SPI 469 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 472 IRQ_TYPE_LEVEL_HIGH>; #mbox-cells = <2>; power-domains = <&pd IMX_SC_R_VPU_MU_0>; status = "disabled"; @@ -24,7 +24,7 @@ vpu: vpu@2c000000 { mu1_m0: mailbox@2d020000 { compatible = "fsl,imx6sx-mu"; reg = <0x2d020000 0x20000>; - interrupts = <GIC_SPI 470 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 473 IRQ_TYPE_LEVEL_HIGH>; #mbox-cells = <2>; power-domains = <&pd IMX_SC_R_VPU_MU_1>; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts index 50debe821c42..9c102acb8052 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts @@ -218,6 +218,18 @@ }; }; +&media_blk_ctrl { + /* + * The LVDS panel on this device uses 72.4 MHz pixel clock, + * set IMX8MP_VIDEO_PLL1 to 72.4 * 7 = 506.8 MHz so the LDB + * serializer and LCDIFv3 scanout engine can reach accurate + * pixel clock of exactly 72.4 MHz. + */ + assigned-clock-rates = <500000000>, <200000000>, + <0>, <0>, <500000000>, + <506800000>; +}; + &snvs_pwrkey { status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts index 3c2efdc59bfa..30962922b361 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts @@ -71,6 +71,7 @@ assigned-clock-rates = <500000000>, <200000000>, <0>, /* IMX8MP_CLK_MEDIA_DISP2_PIX = pixelclk of lvds panel */ <68900000>, + <500000000>, /* IMX8MP_VIDEO_PLL1 = IMX8MP_CLK_MEDIA_LDB * 2 */ <964600000>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index f3531cfb0d79..40e847bc0b7f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -1261,7 +1261,7 @@ compatible = "fsl,imx8mp-usdhc", "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b40000 0x10000>; interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MP_CLK_DUMMY>, + clocks = <&clk IMX8MP_CLK_IPG_ROOT>, <&clk IMX8MP_CLK_NAND_USDHC_BUS>, <&clk IMX8MP_CLK_USDHC1_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -1275,7 +1275,7 @@ compatible = "fsl,imx8mp-usdhc", "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b50000 0x10000>; interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MP_CLK_DUMMY>, + clocks = <&clk IMX8MP_CLK_IPG_ROOT>, <&clk IMX8MP_CLK_NAND_USDHC_BUS>, <&clk IMX8MP_CLK_USDHC2_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -1289,7 +1289,7 @@ compatible = "fsl,imx8mp-usdhc", "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b60000 0x10000>; interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MP_CLK_DUMMY>, + clocks = <&clk IMX8MP_CLK_IPG_ROOT>, <&clk IMX8MP_CLK_NAND_USDHC_BUS>, <&clk IMX8MP_CLK_USDHC3_ROOT>; clock-names = "ipg", "ahb", "per"; diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi b/arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi index 7894a3ab26d6..f81937b5fb72 100644 --- a/arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi @@ -5,6 +5,14 @@ * Author: Alexander Stein */ +&mu_m0 { + interrupts = <GIC_SPI 469 IRQ_TYPE_LEVEL_HIGH>; +}; + +&mu1_m0 { + interrupts = <GIC_SPI 470 IRQ_TYPE_LEVEL_HIGH>; +}; + &vpu_core0 { reg = <0x2d040000 0x10000>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi index e32d5afcf4a9..43f543768444 100644 --- a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi @@ -384,7 +384,7 @@ }; flexspi2: spi@29810000 { - compatible = "nxp,imx8mm-fspi"; + compatible = "nxp,imx8ulp-fspi"; reg = <0x29810000 0x10000>, <0x60000000 0x10000000>; reg-names = "fspi_base", "fspi_mmap"; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/qcom/msm8939.dtsi b/arch/arm64/boot/dts/qcom/msm8939.dtsi index 28634789a8a9..7af210789879 100644 --- a/arch/arm64/boot/dts/qcom/msm8939.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8939.dtsi @@ -248,7 +248,7 @@ smd-edge { interrupts = <GIC_SPI 168 IRQ_TYPE_EDGE_RISING>; - mboxes = <&apcs1_mbox 0>; + qcom,ipc = <&apcs1_mbox 8 0>; qcom,smd-edge = <15>; rpm_requests: rpm-requests { diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi index 9bafb3b350ff..38cb524cc568 100644 --- a/arch/arm64/boot/dts/qcom/sm8450.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi @@ -1973,7 +1973,7 @@ clocks = <&gcc GCC_PCIE_1_PIPE_CLK>, <&gcc GCC_PCIE_1_PIPE_CLK_SRC>, - <&pcie1_phy>, + <&pcie1_phy QMP_PCIE_PIPE_CLK>, <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_PCIE_1_AUX_CLK>, <&gcc GCC_PCIE_1_CFG_AHB_CLK>, diff --git a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts index 941dfddd6713..fdde988ae01e 100644 --- a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts +++ b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts @@ -139,6 +139,8 @@ pinctrl-0 = <&nvme_reg_en>; pinctrl-names = "default"; + + regulator-boot-on; }; vph_pwr: regulator-vph-pwr { diff --git a/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts b/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts index 20616bd4aa6c..fb4a48a1e2a8 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts @@ -134,6 +134,8 @@ pinctrl-0 = <&nvme_reg_en>; pinctrl-names = "default"; + + regulator-boot-on; }; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts index 10b28d870f08..c6e0356ed9a2 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts @@ -177,9 +177,9 @@ compatible = "qcom,x1e80100-sndcard"; model = "X1E80100-CRD"; audio-routing = "WooferLeft IN", "WSA WSA_SPK1 OUT", - "TwitterLeft IN", "WSA WSA_SPK2 OUT", + "TweeterLeft IN", "WSA WSA_SPK2 OUT", "WooferRight IN", "WSA2 WSA_SPK2 OUT", - "TwitterRight IN", "WSA2 WSA_SPK2 OUT", + "TweeterRight IN", "WSA2 WSA_SPK2 OUT", "IN1_HPHL", "HPHL_OUT", "IN2_HPHR", "HPHR_OUT", "AMIC2", "MIC BIAS2", @@ -300,6 +300,8 @@ pinctrl-names = "default"; pinctrl-0 = <&nvme_reg_en>; + + regulator-boot-on; }; vreg_wwan: regulator-wwan { @@ -933,7 +935,7 @@ reg = <0 1>; reset-gpios = <&lpass_tlmm 12 GPIO_ACTIVE_LOW>; #sound-dai-cells = <0>; - sound-name-prefix = "TwitterLeft"; + sound-name-prefix = "TweeterLeft"; vdd-1p8-supply = <&vreg_l15b_1p8>; vdd-io-supply = <&vreg_l12b_1p2>; qcom,port-mapping = <4 5 6 7 11 13>; @@ -986,7 +988,7 @@ reg = <0 1>; reset-gpios = <&lpass_tlmm 13 GPIO_ACTIVE_LOW>; #sound-dai-cells = <0>; - sound-name-prefix = "TwitterRight"; + sound-name-prefix = "TweeterRight"; vdd-1p8-supply = <&vreg_l15b_1p8>; vdd-io-supply = <&vreg_l12b_1p2>; qcom,port-mapping = <4 5 6 7 11 13>; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts b/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts index 3c13331a9ef4..0cdaff9c8cf0 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts @@ -205,6 +205,8 @@ pinctrl-0 = <&nvme_reg_en>; pinctrl-names = "default"; + + regulator-boot-on; }; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi b/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi index 42e02ad6a9c3..cdb401767c42 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi @@ -164,6 +164,8 @@ pinctrl-0 = <&nvme_reg_en>; pinctrl-names = "default"; + + regulator-boot-on; }; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts index 1c3a6a7b3ed6..5ef030c60abe 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts @@ -253,6 +253,8 @@ pinctrl-names = "default"; pinctrl-0 = <&nvme_reg_en>; + + regulator-boot-on; }; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi index a36076e3c56b..0510abc0edf0 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi @@ -2924,14 +2924,14 @@ "mhi"; #address-cells = <3>; #size-cells = <2>; - ranges = <0x01000000 0 0x00000000 0 0x70200000 0 0x100000>, - <0x02000000 0 0x70300000 0 0x70300000 0 0x3d00000>; - bus-range = <0 0xff>; + ranges = <0x01000000 0x0 0x00000000 0x0 0x70200000 0x0 0x100000>, + <0x02000000 0x0 0x70300000 0x0 0x70300000 0x0 0x1d00000>; + bus-range = <0x00 0xff>; dma-coherent; linux,pci-domain = <6>; - num-lanes = <2>; + num-lanes = <4>; interrupts = <GIC_SPI 773 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 774 IRQ_TYPE_LEVEL_HIGH>, @@ -2997,19 +2997,22 @@ }; pcie6a_phy: phy@1bfc000 { - compatible = "qcom,x1e80100-qmp-gen4x2-pcie-phy"; - reg = <0 0x01bfc000 0 0x2000>; + compatible = "qcom,x1e80100-qmp-gen4x4-pcie-phy"; + reg = <0 0x01bfc000 0 0x2000>, + <0 0x01bfe000 0 0x2000>; clocks = <&gcc GCC_PCIE_6A_PHY_AUX_CLK>, <&gcc GCC_PCIE_6A_CFG_AHB_CLK>, - <&rpmhcc RPMH_CXO_CLK>, + <&tcsr TCSR_PCIE_4L_CLKREF_EN>, <&gcc GCC_PCIE_6A_PHY_RCHNG_CLK>, - <&gcc GCC_PCIE_6A_PIPE_CLK>; + <&gcc GCC_PCIE_6A_PIPE_CLK>, + <&gcc GCC_PCIE_6A_PIPEDIV2_CLK>; clock-names = "aux", "cfg_ahb", "ref", "rchng", - "pipe"; + "pipe", + "pipediv2"; resets = <&gcc GCC_PCIE_6A_PHY_BCR>, <&gcc GCC_PCIE_6A_NOCSR_COM_PHY_BCR>; @@ -3021,6 +3024,8 @@ power-domains = <&gcc GCC_PCIE_6_PHY_GDSC>; + qcom,4ln-config-sel = <&tcsr 0x1a000 0>; + #clock-cells = <0>; clock-output-names = "pcie6a_pipe_clk"; @@ -3097,7 +3102,7 @@ assigned-clocks = <&gcc GCC_PCIE_5_AUX_CLK>; assigned-clock-rates = <19200000>; - interconnects = <&pcie_south_anoc MASTER_PCIE_5 QCOM_ICC_TAG_ALWAYS + interconnects = <&pcie_north_anoc MASTER_PCIE_5 QCOM_ICC_TAG_ALWAYS &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS &cnoc_main SLAVE_PCIE_5 QCOM_ICC_TAG_ALWAYS>; @@ -3124,14 +3129,16 @@ clocks = <&gcc GCC_PCIE_5_AUX_CLK>, <&gcc GCC_PCIE_5_CFG_AHB_CLK>, - <&rpmhcc RPMH_CXO_CLK>, + <&tcsr TCSR_PCIE_2L_5_CLKREF_EN>, <&gcc GCC_PCIE_5_PHY_RCHNG_CLK>, - <&gcc GCC_PCIE_5_PIPE_CLK>; + <&gcc GCC_PCIE_5_PIPE_CLK>, + <&gcc GCC_PCIE_5_PIPEDIV2_CLK>; clock-names = "aux", "cfg_ahb", "ref", "rchng", - "pipe"; + "pipe", + "pipediv2"; resets = <&gcc GCC_PCIE_5_PHY_BCR>; reset-names = "phy"; @@ -3166,8 +3173,8 @@ "mhi"; #address-cells = <3>; #size-cells = <2>; - ranges = <0x01000000 0 0x00000000 0 0x7c200000 0 0x100000>, - <0x02000000 0 0x7c300000 0 0x7c300000 0 0x3d00000>; + ranges = <0x01000000 0x0 0x00000000 0x0 0x7c200000 0x0 0x100000>, + <0x02000000 0x0 0x7c300000 0x0 0x7c300000 0x0 0x1d00000>; bus-range = <0x00 0xff>; dma-coherent; @@ -3217,7 +3224,7 @@ assigned-clocks = <&gcc GCC_PCIE_4_AUX_CLK>; assigned-clock-rates = <19200000>; - interconnects = <&pcie_south_anoc MASTER_PCIE_4 QCOM_ICC_TAG_ALWAYS + interconnects = <&pcie_north_anoc MASTER_PCIE_4 QCOM_ICC_TAG_ALWAYS &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>, <&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS &cnoc_main SLAVE_PCIE_4 QCOM_ICC_TAG_ALWAYS>; @@ -3254,14 +3261,16 @@ clocks = <&gcc GCC_PCIE_4_AUX_CLK>, <&gcc GCC_PCIE_4_CFG_AHB_CLK>, - <&rpmhcc RPMH_CXO_CLK>, + <&tcsr TCSR_PCIE_2L_4_CLKREF_EN>, <&gcc GCC_PCIE_4_PHY_RCHNG_CLK>, - <&gcc GCC_PCIE_4_PIPE_CLK>; + <&gcc GCC_PCIE_4_PIPE_CLK>, + <&gcc GCC_PCIE_4_PIPEDIV2_CLK>; clock-names = "aux", "cfg_ahb", "ref", "rchng", - "pipe"; + "pipe", + "pipediv2"; resets = <&gcc GCC_PCIE_4_PHY_BCR>; reset-names = "phy"; @@ -6084,7 +6093,8 @@ <0 0x25a00000 0 0x200000>, <0 0x25c00000 0 0x200000>, <0 0x25e00000 0 0x200000>, - <0 0x26000000 0 0x200000>; + <0 0x26000000 0 0x200000>, + <0 0x26200000 0 0x200000>; reg-names = "llcc0_base", "llcc1_base", "llcc2_base", @@ -6093,7 +6103,8 @@ "llcc5_base", "llcc6_base", "llcc7_base", - "llcc_broadcast_base"; + "llcc_broadcast_base", + "llcc_broadcast_and_base"; interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>; }; diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi index bb1aea82e666..b7163ed74232 100644 --- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi @@ -66,7 +66,6 @@ bus-width = <8>; cap-mmc-highspeed; mmc-hs200-1_8v; - supports-emmc; mmc-pwrseq = <&emmc_pwrseq>; non-removable; vmmc-supply = <&vcc_3v3>; diff --git a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts index 9232357f4fec..d9e191ad1d77 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts @@ -36,14 +36,14 @@ power_led: led-0 { label = "firefly:red:power"; - linux,default-trigger = "ir-power-click"; + linux,default-trigger = "default-on"; default-state = "on"; gpios = <&gpio0 RK_PA6 GPIO_ACTIVE_HIGH>; }; user_led: led-1 { label = "firefly:blue:user"; - linux,default-trigger = "ir-user-click"; + linux,default-trigger = "rc-feedback"; default-state = "off"; gpios = <&gpio0 RK_PB2 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s-plus.dts b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s-plus.dts index cb81ba3f23ff..4b9ced67742d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s-plus.dts @@ -24,9 +24,7 @@ disable-wp; mmc-hs200-1_8v; non-removable; - num-slots = <1>; pinctrl-names = "default"; pinctrl-0 = <&emmc_clk &emmc_cmd &emmc_bus8>; - supports-emmc; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 16b4faa22e4f..c01a4cad48f3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -754,8 +754,7 @@ compatible = "rockchip,rk3328-dw-hdmi"; reg = <0x0 0xff3c0000 0x0 0x20000>; reg-io-width = <4>; - interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cru PCLK_HDMI>, <&cru SCLK_HDMI_SFC>, <&cru SCLK_RTC32K>; diff --git a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi index 8ac8acf4082d..ab3fda69a1fb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi @@ -61,7 +61,6 @@ fan: fan@18 { compatible = "ti,amc6821"; reg = <0x18>; - #cooling-cells = <2>; }; rtc_twi: rtc@6f { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts b/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts index 1489eb32e266..4feb78797982 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts @@ -541,7 +541,7 @@ status = "okay"; rt5651: audio-codec@1a { - compatible = "rockchip,rt5651"; + compatible = "realtek,rt5651"; reg = <0x1a>; clocks = <&cru SCLK_I2S_8CH_OUT>; clock-names = "mclk"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts index 1a44582a49fb..09a016ea8c76 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts @@ -166,7 +166,6 @@ regulator-max-microvolt = <1800000>; vin-supply = <&vcc3v3_sys>; gpio = <&gpio3 RK_PA5 GPIO_ACTIVE_HIGH>; - pinctrl-names = "default"; }; /* MIPI DSI panel 2.8v supply */ @@ -178,7 +177,6 @@ regulator-max-microvolt = <2800000>; vin-supply = <&vcc3v3_sys>; gpio = <&gpio3 RK_PA1 GPIO_ACTIVE_HIGH>; - pinctrl-names = "default"; }; vibrator { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts index 7ba1c28f70a9..2f06bfdd70bf 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts @@ -114,7 +114,6 @@ es8388: es8388@11 { compatible = "everest,es8388"; reg = <0x11>; - clock-names = "mclk"; clocks = <&cru SCLK_I2S_8CH_OUT>; #sound-dai-cells = <0>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi index 8146f870d2bd..ab890e7b6c59 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi @@ -576,7 +576,7 @@ bluetooth { compatible = "brcm,bcm43438-bt"; clocks = <&rk808 1>; - clock-names = "ext_clock"; + clock-names = "txco"; device-wakeup-gpios = <&gpio2 RK_PD3 GPIO_ACTIVE_HIGH>; host-wakeup-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_HIGH>; shutdown-gpios = <&gpio0 RK_PB1 GPIO_ACTIVE_HIGH>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts index dbec2b7173a0..31ea3d0182c0 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts @@ -163,7 +163,7 @@ status = "okay"; rt5651: rt5651@1a { - compatible = "rockchip,rt5651"; + compatible = "realtek,rt5651"; reg = <0x1a>; clocks = <&cru SCLK_I2S_8CH_OUT>; clock-names = "mclk"; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353p.dts b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353p.dts index a73cf30801ec..9816a4ed4599 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353p.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353p.dts @@ -92,7 +92,7 @@ }; &i2c2 { - pintctrl-names = "default"; + pinctrl-names = "default"; pinctrl-0 = <&i2c2m1_xfer>; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353v.dts b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353v.dts index e9954a33e8cd..a79a5614bcc8 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353v.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353v.dts @@ -79,7 +79,7 @@ }; &i2c2 { - pintctrl-names = "default"; + pinctrl-names = "default"; pinctrl-0 = <&i2c2m1_xfer>; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-box-demo.dts b/arch/arm64/boot/dts/rockchip/rk3566-box-demo.dts index 0c18406e4c59..7d4680933823 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-box-demo.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-box-demo.dts @@ -449,9 +449,9 @@ bluetooth { compatible = "brcm,bcm43438-bt"; clocks = <&pmucru CLK_RTC_32K>; - clock-names = "ext_clock"; - device-wake-gpios = <&gpio2 RK_PC1 GPIO_ACTIVE_HIGH>; - host-wake-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>; + clock-names = "txco"; + device-wakeup-gpios = <&gpio2 RK_PC1 GPIO_ACTIVE_HIGH>; + host-wakeup-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>; shutdown-gpios = <&gpio2 RK_PB7 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&bt_host_wake_l &bt_wake_l &bt_enable_h>; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts index c1194d1e438d..9a2f59a351de 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts @@ -507,7 +507,6 @@ non-removable; pinctrl-names = "default"; pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd>; - supports-emmc; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi index ae2536c65a83..0131f2cdd312 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi @@ -684,11 +684,11 @@ compatible = "brcm,bcm43438-bt"; clocks = <&rk817 1>; clock-names = "lpo"; - device-wake-gpios = <&gpio0 RK_PC2 GPIO_ACTIVE_HIGH>; - host-wake-gpios = <&gpio0 RK_PC3 GPIO_ACTIVE_HIGH>; - reset-gpios = <&gpio0 RK_PC4 GPIO_ACTIVE_LOW>; + device-wakeup-gpios = <&gpio0 RK_PC2 GPIO_ACTIVE_HIGH>; + host-wakeup-gpios = <&gpio0 RK_PC3 GPIO_ACTIVE_HIGH>; pinctrl-0 = <&bt_enable_h>, <&bt_host_wake_l>, <&bt_wake_h>; pinctrl-names = "default"; + shutdown-gpios = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>; vbat-supply = <&vcc_wl>; vddio-supply = <&vcca_1v8_pmu>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3.dtsi index 45de2630bb50..1e36f73840da 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3.dtsi @@ -402,9 +402,9 @@ clock-names = "lpo"; device-wakeup-gpios = <&gpio2 RK_PB2 GPIO_ACTIVE_HIGH>; host-wakeup-gpios = <&gpio2 RK_PB1 GPIO_ACTIVE_HIGH>; - reset-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_LOW>; pinctrl-names = "default"; pinctrl-0 = <&bt_host_wake_h &bt_reg_on_h &bt_wake_host_h>; + shutdown-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>; vbat-supply = <&vcc_3v3>; vddio-supply = <&vcc_1v8>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts b/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts index a3112d5df200..b505a4537ee8 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts @@ -589,7 +589,6 @@ non-removable; pinctrl-names = "default"; pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd>; - supports-emmc; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-roc-pc.dts b/arch/arm64/boot/dts/rockchip/rk3568-roc-pc.dts index e333449ead04..2fa89a0eeafc 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-roc-pc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-roc-pc.dts @@ -272,7 +272,6 @@ regulator-name = "vdd_logic"; regulator-always-on; regulator-boot-on; - regulator-init-microvolt = <900000>; regulator-initial-mode = <0x2>; regulator-min-microvolt = <500000>; regulator-max-microvolt = <1350000>; @@ -285,7 +284,6 @@ vdd_gpu: DCDC_REG2 { regulator-name = "vdd_gpu"; - regulator-init-microvolt = <900000>; regulator-initial-mode = <0x2>; regulator-min-microvolt = <500000>; regulator-max-microvolt = <1350000>; @@ -309,7 +307,6 @@ vdd_npu: DCDC_REG4 { regulator-name = "vdd_npu"; - regulator-init-microvolt = <900000>; regulator-initial-mode = <0x2>; regulator-min-microvolt = <500000>; regulator-max-microvolt = <1350000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi index d97d84b88837..fc67585b64b7 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi @@ -337,15 +337,19 @@ cache-unified; next-level-cache = <&l3_cache>; }; + }; - l3_cache: l3-cache { - compatible = "cache"; - cache-size = <3145728>; - cache-line-size = <64>; - cache-sets = <4096>; - cache-level = <3>; - cache-unified; - }; + /* + * The L3 cache belongs to the DynamIQ Shared Unit (DSU), + * so it's represented here, outside the "cpus" node + */ + l3_cache: l3-cache { + compatible = "cache"; + cache-size = <3145728>; + cache-line-size = <64>; + cache-sets = <4096>; + cache-level = <3>; + cache-unified; }; display_subsystem: display-subsystem { diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts index c3a6812cc93a..dd4c79bcad87 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts @@ -328,7 +328,6 @@ compatible = "everest,es8388"; reg = <0x11>; clocks = <&cru I2S0_8CH_MCLKOUT>; - clock-names = "mclk"; AVDD-supply = <&vcc_1v8_s0>; DVDD-supply = <&vcc_1v8_s0>; HPVDD-supply = <&vcc_3v3_s0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts index e4a20cda65ed..b38dab009ccc 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts @@ -316,7 +316,6 @@ assigned-clocks = <&cru I2S0_8CH_MCLKOUT>; assigned-clock-rates = <12288000>; clocks = <&cru I2S0_8CH_MCLKOUT>; - clock-names = "mclk"; AVDD-supply = <&avcc_1v8_codec_s0>; DVDD-supply = <&avcc_1v8_codec_s0>; HPVDD-supply = <&vcc_3v3_s0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts index 966bbc582d89..6bd06e46a101 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts @@ -304,12 +304,12 @@ }; cooling-maps { - map1 { + map0 { trip = <&package_fan0>; cooling-device = <&fan THERMAL_NO_LIMIT 1>; }; - map2 { + map1 { trip = <&package_fan1>; cooling-device = <&fan 2 THERMAL_NO_LIMIT>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts b/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts index d0021524e7f9..328dcb894ccb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts @@ -428,7 +428,6 @@ regulator-boot-on; regulator-min-microvolt = <550000>; regulator-max-microvolt = <950000>; - regulator-init-microvolt = <750000>; regulator-ramp-delay = <12500>; regulator-state-mem { diff --git a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi index dbaa94ca69f4..432133251e31 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi @@ -296,6 +296,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>, <&rk806_dvs2_null>, <&rk806_dvs3_null>; + system-power-controller; vcc1-supply = <&vcc5v0_sys>; vcc2-supply = <&vcc5v0_sys>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts index d8c50fdcca3b..8ba111d9283f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts @@ -377,7 +377,6 @@ assigned-clock-rates = <12288000>; assigned-clocks = <&cru I2S0_8CH_MCLKOUT>; AVDD-supply = <&vcc_3v3_s3>; - clock-names = "mclk"; clocks = <&cru I2S0_8CH_MCLKOUT>; DVDD-supply = <&vcc_1v8_s3>; HPVDD-supply = <&vcc_3v3_s3>; diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 561986947530..c7d311d8b92a 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -19,6 +19,7 @@ #include <linux/ratelimit.h> #include <linux/rseq.h> #include <linux/syscalls.h> +#include <linux/pkeys.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> @@ -66,10 +67,63 @@ struct rt_sigframe_user_layout { unsigned long end_offset; }; +/* + * Holds any EL0-controlled state that influences unprivileged memory accesses. + * This includes both accesses done in userspace and uaccess done in the kernel. + * + * This state needs to be carefully managed to ensure that it doesn't cause + * uaccess to fail when setting up the signal frame, and the signal handler + * itself also expects a well-defined state when entered. + */ +struct user_access_state { + u64 por_el0; +}; + #define BASE_SIGFRAME_SIZE round_up(sizeof(struct rt_sigframe), 16) #define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16) #define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16) +/* + * Save the user access state into ua_state and reset it to disable any + * restrictions. + */ +static void save_reset_user_access_state(struct user_access_state *ua_state) +{ + if (system_supports_poe()) { + u64 por_enable_all = 0; + + for (int pkey = 0; pkey < arch_max_pkey(); pkey++) + por_enable_all |= POE_RXW << (pkey * POR_BITS_PER_PKEY); + + ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0); + write_sysreg_s(por_enable_all, SYS_POR_EL0); + /* Ensure that any subsequent uaccess observes the updated value */ + isb(); + } +} + +/* + * Set the user access state for invoking the signal handler. + * + * No uaccess should be done after that function is called. + */ +static void set_handler_user_access_state(void) +{ + if (system_supports_poe()) + write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0); +} + +/* + * Restore the user access state to the values saved in ua_state. + * + * No uaccess should be done after that function is called. + */ +static void restore_user_access_state(const struct user_access_state *ua_state) +{ + if (system_supports_poe()) + write_sysreg_s(ua_state->por_el0, SYS_POR_EL0); +} + static void init_user_layout(struct rt_sigframe_user_layout *user) { const size_t reserved_size = @@ -261,18 +315,20 @@ static int restore_fpmr_context(struct user_ctxs *user) return err; } -static int preserve_poe_context(struct poe_context __user *ctx) +static int preserve_poe_context(struct poe_context __user *ctx, + const struct user_access_state *ua_state) { int err = 0; __put_user_error(POE_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(*ctx), &ctx->head.size, err); - __put_user_error(read_sysreg_s(SYS_POR_EL0), &ctx->por_el0, err); + __put_user_error(ua_state->por_el0, &ctx->por_el0, err); return err; } -static int restore_poe_context(struct user_ctxs *user) +static int restore_poe_context(struct user_ctxs *user, + struct user_access_state *ua_state) { u64 por_el0; int err = 0; @@ -282,7 +338,7 @@ static int restore_poe_context(struct user_ctxs *user) __get_user_error(por_el0, &(user->poe->por_el0), err); if (!err) - write_sysreg_s(por_el0, SYS_POR_EL0); + ua_state->por_el0 = por_el0; return err; } @@ -850,7 +906,8 @@ invalid: } static int restore_sigframe(struct pt_regs *regs, - struct rt_sigframe __user *sf) + struct rt_sigframe __user *sf, + struct user_access_state *ua_state) { sigset_t set; int i, err; @@ -899,7 +956,7 @@ static int restore_sigframe(struct pt_regs *regs, err = restore_zt_context(&user); if (err == 0 && system_supports_poe() && user.poe) - err = restore_poe_context(&user); + err = restore_poe_context(&user, ua_state); return err; } @@ -908,6 +965,7 @@ SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; + struct user_access_state ua_state; /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; @@ -924,12 +982,14 @@ SYSCALL_DEFINE0(rt_sigreturn) if (!access_ok(frame, sizeof (*frame))) goto badframe; - if (restore_sigframe(regs, frame)) + if (restore_sigframe(regs, frame, &ua_state)) goto badframe; if (restore_altstack(&frame->uc.uc_stack)) goto badframe; + restore_user_access_state(&ua_state); + return regs->regs[0]; badframe: @@ -1035,7 +1095,8 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, } static int setup_sigframe(struct rt_sigframe_user_layout *user, - struct pt_regs *regs, sigset_t *set) + struct pt_regs *regs, sigset_t *set, + const struct user_access_state *ua_state) { int i, err = 0; struct rt_sigframe __user *sf = user->sigframe; @@ -1097,10 +1158,9 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, struct poe_context __user *poe_ctx = apply_user_offset(user, user->poe_offset); - err |= preserve_poe_context(poe_ctx); + err |= preserve_poe_context(poe_ctx, ua_state); } - /* ZA state if present */ if (system_supports_sme() && err == 0 && user->za_offset) { struct za_context __user *za_ctx = @@ -1237,9 +1297,6 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, sme_smstop(); } - if (system_supports_poe()) - write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0); - if (ka->sa.sa_flags & SA_RESTORER) sigtramp = ka->sa.sa_restorer; else @@ -1253,6 +1310,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, { struct rt_sigframe_user_layout user; struct rt_sigframe __user *frame; + struct user_access_state ua_state; int err = 0; fpsimd_signal_preserve_current_state(); @@ -1260,13 +1318,14 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, if (get_sigframe(&user, ksig, regs)) return 1; + save_reset_user_access_state(&ua_state); frame = user.sigframe; __put_user_error(0, &frame->uc.uc_flags, err); __put_user_error(NULL, &frame->uc.uc_link, err); err |= __save_altstack(&frame->uc.uc_stack, regs->sp); - err |= setup_sigframe(&user, regs, set); + err |= setup_sigframe(&user, regs, set, &ua_state); if (err == 0) { setup_return(regs, &ksig->ka, &user, usig); if (ksig->ka.sa.sa_flags & SA_SIGINFO) { @@ -1276,6 +1335,11 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, } } + if (err == 0) + set_handler_user_access_state(); + else + restore_user_access_state(&ua_state); + return err; } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 8bbd0b20136a..5db82bfc9dc1 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -2220,7 +2220,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, emit(A64_STR64I(A64_R(20), A64_SP, regs_off + 8), ctx); if (flags & BPF_TRAMP_F_CALL_ORIG) { - emit_a64_mov_i64(A64_R(0), (const u64)im, ctx); + /* for the first pass, assume the worst case */ + if (!ctx->image) + ctx->idx += 4; + else + emit_a64_mov_i64(A64_R(0), (const u64)im, ctx); emit_call((const u64)__bpf_tramp_enter, ctx); } @@ -2264,7 +2268,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, if (flags & BPF_TRAMP_F_CALL_ORIG) { im->ip_epilogue = ctx->ro_image + ctx->idx; - emit_a64_mov_i64(A64_R(0), (const u64)im, ctx); + /* for the first pass, assume the worst case */ + if (!ctx->image) + ctx->idx += 4; + else + emit_a64_mov_i64(A64_R(0), (const u64)im, ctx); emit_call((const u64)__bpf_tramp_exit, ctx); } diff --git a/arch/mips/kernel/cmpxchg.c b/arch/mips/kernel/cmpxchg.c index e974a4954df8..c371def2302d 100644 --- a/arch/mips/kernel/cmpxchg.c +++ b/arch/mips/kernel/cmpxchg.c @@ -102,3 +102,4 @@ unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old, return old; } } +EXPORT_SYMBOL(__cmpxchg_small); diff --git a/arch/parisc/lib/checksum.c b/arch/parisc/lib/checksum.c index 4818f3db84a5..59d8c15d81bd 100644 --- a/arch/parisc/lib/checksum.c +++ b/arch/parisc/lib/checksum.c @@ -25,15 +25,6 @@ : "=r"(_t) \ : "r"(_r), "0"(_t)); -static inline unsigned short from32to16(unsigned int x) -{ - /* 32 bits --> 16 bits + carry */ - x = (x & 0xffff) + (x >> 16); - /* 16 bits + carry --> 16 bits including carry */ - x = (x & 0xffff) + (x >> 16); - return (unsigned short)x; -} - static inline unsigned int do_csum(const unsigned char * buff, int len) { int odd, count; @@ -85,7 +76,7 @@ static inline unsigned int do_csum(const unsigned char * buff, int len) } if (len & 1) result += le16_to_cpu(*buff); - result = from32to16(result); + result = csum_from32to16(result); if (odd) result = swab16(result); out: @@ -102,7 +93,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum) { unsigned int result = do_csum(buff, len); addc(result, sum); - return (__force __wsum)from32to16(result); + return (__force __wsum)csum_from32to16(result); } EXPORT_SYMBOL(csum_partial); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 62545946ecf4..f4c570538d55 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -177,7 +177,7 @@ config RISCV select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RETHOOK if !XIP_KERNEL select HAVE_RSEQ - select HAVE_RUST if RUSTC_SUPPORTS_RISCV + select HAVE_RUST if RUSTC_SUPPORTS_RISCV && CC_IS_CLANG select HAVE_SAMPLE_FTRACE_DIRECT select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_STACKPROTECTOR diff --git a/arch/riscv/boot/dts/sophgo/sg2042.dtsi b/arch/riscv/boot/dts/sophgo/sg2042.dtsi index 4e5fa6591623..e62ac51ac55a 100644 --- a/arch/riscv/boot/dts/sophgo/sg2042.dtsi +++ b/arch/riscv/boot/dts/sophgo/sg2042.dtsi @@ -112,7 +112,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -134,7 +134,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -156,7 +156,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi index c7771b3b6475..d6c55f1cc96a 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi @@ -128,7 +128,6 @@ assigned-clocks = <&ispcrg JH7110_ISPCLK_DOM4_APB_FUNC>, <&ispcrg JH7110_ISPCLK_MIPI_RX0_PXL>; assigned-clock-rates = <49500000>, <198000000>; - status = "okay"; ports { #address-cells = <1>; @@ -151,7 +150,6 @@ &csi2rx { assigned-clocks = <&ispcrg JH7110_ISPCLK_VIN_SYS>; assigned-clock-rates = <297000000>; - status = "okay"; ports { #address-cells = <1>; diff --git a/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts b/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts index b720cdd15ed6..8e39fdc73ecb 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts +++ b/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts @@ -44,8 +44,7 @@ }; &phy0 { - rx-internal-delay-ps = <1900>; - tx-internal-delay-ps = <1500>; + rx-internal-delay-ps = <1500>; motorcomm,rx-clk-drv-microamp = <2910>; motorcomm,rx-data-drv-microamp = <2910>; motorcomm,tx-clk-adj-enabled; diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile index 8a2739485123..f0da9d7b39c3 100644 --- a/arch/riscv/errata/Makefile +++ b/arch/riscv/errata/Makefile @@ -2,6 +2,12 @@ ifdef CONFIG_RELOCATABLE KBUILD_CFLAGS += -fno-pie endif +ifdef CONFIG_RISCV_ALTERNATIVE_EARLY +ifdef CONFIG_FORTIFY_SOURCE +KBUILD_CFLAGS += -D__NO_FORTIFY +endif +endif + obj-$(CONFIG_ERRATA_ANDES) += andes/ obj-$(CONFIG_ERRATA_SIFIVE) += sifive/ obj-$(CONFIG_ERRATA_THEAD) += thead/ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 7f88cc4931f5..69dc8aaab3fb 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -36,6 +36,11 @@ KASAN_SANITIZE_alternative.o := n KASAN_SANITIZE_cpufeature.o := n KASAN_SANITIZE_sbi_ecall.o := n endif +ifdef CONFIG_FORTIFY_SOURCE +CFLAGS_alternative.o += -D__NO_FORTIFY +CFLAGS_cpufeature.o += -D__NO_FORTIFY +CFLAGS_sbi_ecall.o += -D__NO_FORTIFY +endif endif extra-y += vmlinux.lds diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c index 6e0d333f57e5..2fd29695a788 100644 --- a/arch/riscv/kernel/acpi.c +++ b/arch/riscv/kernel/acpi.c @@ -210,7 +210,7 @@ void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size) if (!size) return NULL; - return early_ioremap(phys, size); + return early_memremap(phys, size); } void __init __acpi_unmap_table(void __iomem *map, unsigned long size) @@ -218,7 +218,7 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size) if (!map || !size) return; - early_iounmap(map, size); + early_memunmap(map, size); } void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index e94180ba432f..c2f3129a8e5c 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -4,8 +4,6 @@ * Copyright (C) 2017 SiFive */ -#define GENERATING_ASM_OFFSETS - #include <linux/kbuild.h> #include <linux/mm.h> #include <linux/sched.h> diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index b320b1d9aa01..2d40736fc37c 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -80,8 +80,7 @@ int populate_cache_leaves(unsigned int cpu) { struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); struct cacheinfo *this_leaf = this_cpu_ci->info_list; - struct device_node *np = of_cpu_device_node_get(cpu); - struct device_node *prev = NULL; + struct device_node *np, *prev; int levels = 1, level = 1; if (!acpi_disabled) { @@ -105,6 +104,10 @@ int populate_cache_leaves(unsigned int cpu) return 0; } + np = of_cpu_device_node_get(cpu); + if (!np) + return -ENOENT; + if (of_property_read_bool(np, "cache-size")) ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level); if (of_property_read_bool(np, "i-cache-size")) diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c index 28b58fc5ad19..a1e38ecfc8be 100644 --- a/arch/riscv/kernel/cpu-hotplug.c +++ b/arch/riscv/kernel/cpu-hotplug.c @@ -58,7 +58,7 @@ void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) if (cpu_ops->cpu_is_stopped) ret = cpu_ops->cpu_is_stopped(cpu); if (ret) - pr_warn("CPU%d may not have stopped: %d\n", cpu, ret); + pr_warn("CPU%u may not have stopped: %d\n", cpu, ret); } /* diff --git a/arch/riscv/kernel/efi-header.S b/arch/riscv/kernel/efi-header.S index 515b2dfbca75..c5f17c2710b5 100644 --- a/arch/riscv/kernel/efi-header.S +++ b/arch/riscv/kernel/efi-header.S @@ -64,7 +64,7 @@ extra_header_fields: .long efi_header_end - _start // SizeOfHeaders .long 0 // CheckSum .short IMAGE_SUBSYSTEM_EFI_APPLICATION // Subsystem - .short 0 // DllCharacteristics + .short IMAGE_DLL_CHARACTERISTICS_NX_COMPAT // DllCharacteristics .quad 0 // SizeOfStackReserve .quad 0 // SizeOfStackCommit .quad 0 // SizeOfHeapReserve diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile index d5bf1bc7de62..81d69d45c06c 100644 --- a/arch/riscv/kernel/pi/Makefile +++ b/arch/riscv/kernel/pi/Makefile @@ -16,8 +16,12 @@ KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO), $(KBUILD_CFLAGS)) KBUILD_CFLAGS += -mcmodel=medany CFLAGS_cmdline_early.o += -D__NO_FORTIFY -CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY CFLAGS_fdt_early.o += -D__NO_FORTIFY +# lib/string.c already defines __NO_FORTIFY +CFLAGS_ctype.o += -D__NO_FORTIFY +CFLAGS_lib-fdt.o += -D__NO_FORTIFY +CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY +CFLAGS_archrandom_early.o += -D__NO_FORTIFY $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \ --remove-section=.note.gnu.property \ diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index d4fd8af7aaf5..1b9867136b61 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -136,8 +136,6 @@ #define REG_PTR(insn, pos, regs) \ (ulong *)((ulong)(regs) + REG_OFFSET(insn, pos)) -#define GET_RM(insn) (((insn) >> 12) & 7) - #define GET_RS1(insn, regs) (*REG_PTR(insn, SH_RS1, regs)) #define GET_RS2(insn, regs) (*REG_PTR(insn, SH_RS2, regs)) #define GET_RS1S(insn, regs) (*REG_PTR(RVC_RS1S(insn), 0, regs)) diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 960feb1526ca..3f1c4b2d0b06 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -18,6 +18,7 @@ obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o ccflags-y := -fno-stack-protector ccflags-y += -DDISABLE_BRANCH_PROFILING +ccflags-y += -fno-builtin ifneq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y) diff --git a/arch/s390/include/asm/stp.h b/arch/s390/include/asm/stp.h index 4d74d7e33340..827cb208de86 100644 --- a/arch/s390/include/asm/stp.h +++ b/arch/s390/include/asm/stp.h @@ -94,5 +94,6 @@ struct stp_stzi { int stp_sync_check(void); int stp_island_check(void); void stp_queue_work(void); +bool stp_enabled(void); #endif /* __S390_STP_H */ diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 640901f2fbc3..642fd303ce01 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -93,6 +93,7 @@ extern unsigned char ptff_function_mask[16]; #define PTFF_QAF 0x00 /* query available functions */ #define PTFF_QTO 0x01 /* query tod offset */ #define PTFF_QSI 0x02 /* query steering information */ +#define PTFF_QPT 0x03 /* query physical clock */ #define PTFF_QUI 0x04 /* query UTC information */ #define PTFF_ATO 0x40 /* adjust tod offset */ #define PTFF_STO 0x41 /* set tod offset */ @@ -250,6 +251,11 @@ static __always_inline unsigned long tod_to_ns(unsigned long todval) return ((todval >> 9) * 125) + (((todval & 0x1ff) * 125) >> 9); } +static __always_inline u128 eitod_to_ns(u128 todval) +{ + return (todval * 125) >> 9; +} + /** * tod_after - compare two 64 bit TOD values * @a: first 64 bit TOD timestamp diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index b713effe0579..cc60b16a7dd0 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -255,6 +255,7 @@ static struct clocksource clocksource_tod = { .shift = 24, .flags = CLOCK_SOURCE_IS_CONTINUOUS, .vdso_clock_mode = VDSO_CLOCKMODE_TOD, + .id = CSID_S390_TOD, }; struct clocksource * __init clocksource_default_clock(void) @@ -468,6 +469,12 @@ static void __init stp_reset(void) } } +bool stp_enabled(void) +{ + return test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags) && stp_online; +} +EXPORT_SYMBOL(stp_enabled); + static void stp_timeout(struct timer_list *unused) { queue_work(time_sync_wq, &stp_work); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 2852fcd82cbd..16354dfa6d96 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2257,6 +2257,7 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING config ADDRESS_MASKING bool "Linear Address Masking support" depends on X86_64 + depends on COMPILE_TEST || !CPU_MITIGATIONS # wait for LASS help Linear Address Masking (LAM) modifies the checking that is applied to 64-bit linear addresses, allowing software to use of the diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 6f3b6aef47ba..d0caac26533f 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -116,7 +116,10 @@ static inline bool amd_gart_present(void) #define amd_nb_num(x) 0 #define amd_nb_has_feature(x) false -#define node_to_amd_nb(x) NULL +static inline struct amd_northbridge *node_to_amd_nb(int node) +{ + return NULL; +} #define amd_gart_present(x) false #endif diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h index 24e3a53ca255..6652ebddfd02 100644 --- a/arch/x86/include/asm/runtime-const.h +++ b/arch/x86/include/asm/runtime-const.h @@ -6,7 +6,7 @@ typeof(sym) __ret; \ asm_inline("mov %1,%0\n1:\n" \ ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ - ".long 1b - %c2 - .\n\t" \ + ".long 1b - %c2 - .\n" \ ".popsection" \ :"=r" (__ret) \ :"i" ((unsigned long)0x0123456789abcdefull), \ @@ -20,7 +20,7 @@ typeof(0u+(val)) __ret = (val); \ asm_inline("shrl $12,%k0\n1:\n" \ ".pushsection runtime_shift_" #sym ",\"a\"\n\t" \ - ".long 1b - 1 - .\n\t" \ + ".long 1b - 1 - .\n" \ ".popsection" \ :"+r" (__ret)); \ __ret; }) diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index afce8ee5d7b7..b0a887209400 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -12,6 +12,13 @@ #include <asm/cpufeatures.h> #include <asm/page.h> #include <asm/percpu.h> +#include <asm/runtime-const.h> + +/* + * Virtual variable: there's no actual backing store for this, + * it can purely be used as 'runtime_const_ptr(USER_PTR_MAX)' + */ +extern unsigned long USER_PTR_MAX; #ifdef CONFIG_ADDRESS_MASKING /* @@ -46,19 +53,24 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, #endif -/* - * The virtual address space space is logically divided into a kernel - * half and a user half. When cast to a signed type, user pointers - * are positive and kernel pointers are negative. - */ -#define valid_user_address(x) ((__force long)(x) >= 0) +#define valid_user_address(x) \ + ((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX)) /* * Masking the user address is an alternative to a conditional * user_access_begin that can avoid the fencing. This only works * for dense accesses starting at the address. */ -#define mask_user_address(x) ((typeof(x))((long)(x)|((long)(x)>>63))) +static inline void __user *mask_user_address(const void __user *ptr) +{ + unsigned long mask; + asm("cmp %1,%0\n\t" + "sbb %0,%0" + :"=r" (mask) + :"r" (ptr), + "0" (runtime_const_ptr(USER_PTR_MAX))); + return (__force void __user *)(mask | (__force unsigned long)ptr); +} #define masked_user_access_begin(x) ({ \ __auto_type __masked_ptr = (x); \ __masked_ptr = mask_user_address(__masked_ptr); \ @@ -69,23 +81,16 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, * arbitrary values in those bits rather then masking them off. * * Enforce two rules: - * 1. 'ptr' must be in the user half of the address space + * 1. 'ptr' must be in the user part of the address space * 2. 'ptr+size' must not overflow into kernel addresses * - * Note that addresses around the sign change are not valid addresses, - * and will GP-fault even with LAM enabled if the sign bit is set (see - * "CR3.LAM_SUP" that can narrow the canonicality check if we ever - * enable it, but not remove it entirely). - * - * So the "overflow into kernel addresses" does not imply some sudden - * exact boundary at the sign bit, and we can allow a lot of slop on the - * size check. + * Note that we always have at least one guard page between the + * max user address and the non-canonical gap, allowing us to + * ignore small sizes entirely. * * In fact, we could probably remove the size check entirely, since * any kernel accesses will be in increasing address order starting - * at 'ptr', and even if the end might be in kernel space, we'll - * hit the GP faults for non-canonical accesses before we ever get - * there. + * at 'ptr'. * * That's a separate optimization, for now just handle the small * constant case. diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f1040cb64841..a5f221ea5688 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -69,6 +69,7 @@ #include <asm/sev.h> #include <asm/tdx.h> #include <asm/posted_intr.h> +#include <asm/runtime-const.h> #include "cpu.h" @@ -2389,6 +2390,15 @@ void __init arch_cpu_finalize_init(void) alternative_instructions(); if (IS_ENABLED(CONFIG_X86_64)) { + unsigned long USER_PTR_MAX = TASK_SIZE_MAX-1; + + /* + * Enable this when LAM is gated on LASS support + if (cpu_feature_enabled(X86_FEATURE_LAM)) + USER_PTR_MAX = (1ul << 63) - PAGE_SIZE - 1; + */ + runtime_const_init(ptr, USER_PTR_MAX); + /* * Make sure the first 2MB area is not mapped by huge pages * There are typically fixed size MTRRs in there and overlapping diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index f63b051f25a0..31a73715d755 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -584,7 +584,7 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_ native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy); } -static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size); +static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size); static int __init save_microcode_in_initrd(void) { @@ -605,7 +605,7 @@ static int __init save_microcode_in_initrd(void) if (!desc.mc) return -EINVAL; - ret = load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size); + ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size); if (ret > UCODE_UPDATED) return -EINVAL; @@ -613,16 +613,19 @@ static int __init save_microcode_in_initrd(void) } early_initcall(save_microcode_in_initrd); -static inline bool patch_cpus_equivalent(struct ucode_patch *p, struct ucode_patch *n) +static inline bool patch_cpus_equivalent(struct ucode_patch *p, + struct ucode_patch *n, + bool ignore_stepping) { /* Zen and newer hardcode the f/m/s in the patch ID */ if (x86_family(bsp_cpuid_1_eax) >= 0x17) { union cpuid_1_eax p_cid = ucode_rev_to_cpuid(p->patch_id); union cpuid_1_eax n_cid = ucode_rev_to_cpuid(n->patch_id); - /* Zap stepping */ - p_cid.stepping = 0; - n_cid.stepping = 0; + if (ignore_stepping) { + p_cid.stepping = 0; + n_cid.stepping = 0; + } return p_cid.full == n_cid.full; } else { @@ -644,13 +647,13 @@ static struct ucode_patch *cache_find_patch(struct ucode_cpu_info *uci, u16 equi WARN_ON_ONCE(!n.patch_id); list_for_each_entry(p, µcode_cache, plist) - if (patch_cpus_equivalent(p, &n)) + if (patch_cpus_equivalent(p, &n, false)) return p; return NULL; } -static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n) +static inline int patch_newer(struct ucode_patch *p, struct ucode_patch *n) { /* Zen and newer hardcode the f/m/s in the patch ID */ if (x86_family(bsp_cpuid_1_eax) >= 0x17) { @@ -659,6 +662,9 @@ static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n) zp.ucode_rev = p->patch_id; zn.ucode_rev = n->patch_id; + if (zn.stepping != zp.stepping) + return -1; + return zn.rev > zp.rev; } else { return n->patch_id > p->patch_id; @@ -668,10 +674,14 @@ static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n) static void update_cache(struct ucode_patch *new_patch) { struct ucode_patch *p; + int ret; list_for_each_entry(p, µcode_cache, plist) { - if (patch_cpus_equivalent(p, new_patch)) { - if (!patch_newer(p, new_patch)) { + if (patch_cpus_equivalent(p, new_patch, true)) { + ret = patch_newer(p, new_patch); + if (ret < 0) + continue; + else if (!ret) { /* we already have the latest patch */ kfree(new_patch->data); kfree(new_patch); @@ -944,21 +954,30 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, return UCODE_OK; } -static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) +static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size) { - struct cpuinfo_x86 *c; - unsigned int nid, cpu; - struct ucode_patch *p; enum ucode_state ret; /* free old equiv table */ free_equiv_cpu_table(); ret = __load_microcode_amd(family, data, size); - if (ret != UCODE_OK) { + if (ret != UCODE_OK) cleanup(); + + return ret; +} + +static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) +{ + struct cpuinfo_x86 *c; + unsigned int nid, cpu; + struct ucode_patch *p; + enum ucode_state ret; + + ret = _load_microcode_amd(family, data, size); + if (ret != UCODE_OK) return ret; - } for_each_node(nid) { cpu = cpumask_first(cpumask_of_node(nid)); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d05392db5d0f..2dbadf347b5f 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -261,12 +261,6 @@ static noinstr bool handle_bug(struct pt_regs *regs) int ud_type; u32 imm; - /* - * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug() - * is a rare case that uses @regs without passing them to - * irqentry_enter(). - */ - kmsan_unpoison_entry_regs(regs); ud_type = decode_bug(regs->ip, &imm); if (ud_type == BUG_NONE) return handled; @@ -276,6 +270,12 @@ static noinstr bool handle_bug(struct pt_regs *regs) */ instrumentation_begin(); /* + * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug() + * is a rare case that uses @regs without passing them to + * irqentry_enter(). + */ + kmsan_unpoison_entry_regs(regs); + /* * Since we're emulating a CALL with exceptions, restore the interrupt * state to what it was at the exception site. */ diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 6726be89b7a6..b8c5741d2fb4 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -358,6 +358,7 @@ SECTIONS #endif RUNTIME_CONST_VARIABLES + RUNTIME_CONST(ptr, USER_PTR_MAX) . = ALIGN(PAGE_SIZE); diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index d066aecf8aeb..4357ec2a0bfc 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -39,8 +39,13 @@ .macro check_range size:req .if IS_ENABLED(CONFIG_X86_64) - mov %rax, %rdx - sar $63, %rdx + movq $0x0123456789abcdef,%rdx + 1: + .pushsection runtime_ptr_USER_PTR_MAX,"a" + .long 1b - 8 - . + .popsection + cmp %rax, %rdx + sbb %rdx, %rdx or %rdx, %rax .else cmp $TASK_SIZE_MAX-\size+1, %eax diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index 0ce17766c0e5..9a6a943d8e41 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -173,6 +173,8 @@ static void __init __snp_fixup_e820_tables(u64 pa) e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); e820__range_update_table(e820_table_kexec, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); e820__range_update_table(e820_table_firmware, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); + if (!memblock_is_region_reserved(pa, PMD_SIZE)) + memblock_reserve(pa, PMD_SIZE); } } diff --git a/arch/xtensa/include/asm/page.h b/arch/xtensa/include/asm/page.h index 4db56ef052d2..8665d57991dd 100644 --- a/arch/xtensa/include/asm/page.h +++ b/arch/xtensa/include/asm/page.h @@ -109,26 +109,8 @@ typedef struct page *pgtable_t; #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) -/* - * Pure 2^n version of get_order - * Use 'nsau' instructions if supported by the processor or the generic version. - */ - -#if XCHAL_HAVE_NSA - -static inline __attribute_const__ int get_order(unsigned long size) -{ - int lz; - asm ("nsau %0, %1" : "=r" (lz) : "r" ((size - 1) >> PAGE_SHIFT)); - return 32 - lz; -} - -#else - # include <asm-generic/getorder.h> -#endif - struct page; struct vm_area_struct; extern void clear_page(void *page); diff --git a/block/blk-map.c b/block/blk-map.c index 0e1167b23934..b5fd1d857461 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -561,57 +561,33 @@ EXPORT_SYMBOL(blk_rq_append_bio); /* Prepare bio for passthrough IO given ITER_BVEC iter */ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter) { - struct request_queue *q = rq->q; - size_t nr_iter = iov_iter_count(iter); - size_t nr_segs = iter->nr_segs; - struct bio_vec *bvecs, *bvprvp = NULL; - const struct queue_limits *lim = &q->limits; - unsigned int nsegs = 0, bytes = 0; + const struct queue_limits *lim = &rq->q->limits; + unsigned int max_bytes = lim->max_hw_sectors << SECTOR_SHIFT; + unsigned int nsegs; struct bio *bio; - size_t i; + int ret; - if (!nr_iter || (nr_iter >> SECTOR_SHIFT) > queue_max_hw_sectors(q)) - return -EINVAL; - if (nr_segs > queue_max_segments(q)) + if (!iov_iter_count(iter) || iov_iter_count(iter) > max_bytes) return -EINVAL; - /* no iovecs to alloc, as we already have a BVEC iterator */ + /* reuse the bvecs from the iterator instead of allocating new ones */ bio = blk_rq_map_bio_alloc(rq, 0, GFP_KERNEL); - if (bio == NULL) + if (!bio) return -ENOMEM; - bio_iov_bvec_set(bio, (struct iov_iter *)iter); - blk_rq_bio_prep(rq, bio, nr_segs); - - /* loop to perform a bunch of sanity checks */ - bvecs = (struct bio_vec *)iter->bvec; - for (i = 0; i < nr_segs; i++) { - struct bio_vec *bv = &bvecs[i]; - /* - * If the queue doesn't support SG gaps and adding this - * offset would create a gap, fallback to copy. - */ - if (bvprvp && bvec_gap_to_prev(lim, bvprvp, bv->bv_offset)) { - blk_mq_map_bio_put(bio); - return -EREMOTEIO; - } - /* check full condition */ - if (nsegs >= nr_segs || bytes > UINT_MAX - bv->bv_len) - goto put_bio; - if (bytes + bv->bv_len > nr_iter) - goto put_bio; - if (bv->bv_offset + bv->bv_len > PAGE_SIZE) - goto put_bio; - - nsegs++; - bytes += bv->bv_len; - bvprvp = bv; + /* check that the data layout matches the hardware restrictions */ + ret = bio_split_rw_at(bio, lim, &nsegs, max_bytes); + if (ret) { + /* if we would have to split the bio, copy instead */ + if (ret > 0) + ret = -EREMOTEIO; + blk_mq_map_bio_put(bio); + return ret; } + + blk_rq_bio_prep(rq, bio, nsegs); return 0; -put_bio: - blk_mq_map_bio_put(bio); - return -EINVAL; } /** diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c index 6f86f8df30db..8d50981594d1 100644 --- a/drivers/accel/ivpu/ivpu_debugfs.c +++ b/drivers/accel/ivpu/ivpu_debugfs.c @@ -108,6 +108,14 @@ static int reset_pending_show(struct seq_file *s, void *v) return 0; } +static int firewall_irq_counter_show(struct seq_file *s, void *v) +{ + struct ivpu_device *vdev = seq_to_ivpu(s); + + seq_printf(s, "%d\n", atomic_read(&vdev->hw->firewall_irq_counter)); + return 0; +} + static const struct drm_debugfs_info vdev_debugfs_list[] = { {"bo_list", bo_list_show, 0}, {"fw_name", fw_name_show, 0}, @@ -116,6 +124,7 @@ static const struct drm_debugfs_info vdev_debugfs_list[] = { {"last_bootmode", last_bootmode_show, 0}, {"reset_counter", reset_counter_show, 0}, {"reset_pending", reset_pending_show, 0}, + {"firewall_irq_counter", firewall_irq_counter_show, 0}, }; static ssize_t diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c index 27f0fe4d54e0..e69c0613513f 100644 --- a/drivers/accel/ivpu/ivpu_hw.c +++ b/drivers/accel/ivpu/ivpu_hw.c @@ -249,6 +249,7 @@ int ivpu_hw_init(struct ivpu_device *vdev) platform_init(vdev); wa_init(vdev); timeouts_init(vdev); + atomic_set(&vdev->hw->firewall_irq_counter, 0); return 0; } diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h index 1c0c98e3afb8..a96a05b2acda 100644 --- a/drivers/accel/ivpu/ivpu_hw.h +++ b/drivers/accel/ivpu/ivpu_hw.h @@ -52,6 +52,7 @@ struct ivpu_hw_info { int dma_bits; ktime_t d0i3_entry_host_ts; u64 d0i3_entry_vpu_ts; + atomic_t firewall_irq_counter; }; int ivpu_hw_init(struct ivpu_device *vdev); diff --git a/drivers/accel/ivpu/ivpu_hw_ip.c b/drivers/accel/ivpu/ivpu_hw_ip.c index dfd2f4a5b526..60b33fc59d96 100644 --- a/drivers/accel/ivpu/ivpu_hw_ip.c +++ b/drivers/accel/ivpu/ivpu_hw_ip.c @@ -1062,7 +1062,10 @@ static void irq_wdt_mss_handler(struct ivpu_device *vdev) static void irq_noc_firewall_handler(struct ivpu_device *vdev) { - ivpu_pm_trigger_recovery(vdev, "NOC Firewall IRQ"); + atomic_inc(&vdev->hw->firewall_irq_counter); + + ivpu_dbg(vdev, IRQ, "NOC Firewall interrupt detected, counter %d\n", + atomic_read(&vdev->hw->firewall_irq_counter)); } /* Handler for IRQs from NPU core */ diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 51470208e6da..7773e6b860e7 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -130,6 +130,17 @@ static const struct dmi_system_id dmi_lid_quirks[] = { }, .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, }, + { + /* + * Samsung galaxybook2 ,initial _LID device notification returns + * lid closed. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), + DMI_MATCH(DMI_PRODUCT_NAME, "750XED"), + }, + .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, + }, {} }; diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index b73b3aa92f3f..1a40f0514eaa 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -867,7 +867,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) /* Store CPU Logical ID */ cpc_ptr->cpu_id = pr->id; - spin_lock_init(&cpc_ptr->rmw_lock); + raw_spin_lock_init(&cpc_ptr->rmw_lock); /* Parse PSD data for this CPU */ ret = acpi_get_psd(cpc_ptr, handle); @@ -1087,6 +1087,7 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; struct cpc_desc *cpc_desc; + unsigned long flags; size = GET_BIT_WIDTH(reg); @@ -1126,7 +1127,7 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) return -ENODEV; } - spin_lock(&cpc_desc->rmw_lock); + raw_spin_lock_irqsave(&cpc_desc->rmw_lock, flags); switch (size) { case 8: prev_val = readb_relaxed(vaddr); @@ -1141,7 +1142,7 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) prev_val = readq_relaxed(vaddr); break; default: - spin_unlock(&cpc_desc->rmw_lock); + raw_spin_unlock_irqrestore(&cpc_desc->rmw_lock, flags); return -EFAULT; } val = MASK_VAL_WRITE(reg, prev_val, val); @@ -1174,7 +1175,7 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) } if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) - spin_unlock(&cpc_desc->rmw_lock); + raw_spin_unlock_irqrestore(&cpc_desc->rmw_lock, flags); return ret_val; } @@ -1916,9 +1917,15 @@ unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf) u64 mul, div; if (caps->lowest_freq && caps->nominal_freq) { - mul = caps->nominal_freq - caps->lowest_freq; + /* Avoid special case when nominal_freq is equal to lowest_freq */ + if (caps->lowest_freq == caps->nominal_freq) { + mul = caps->nominal_freq; + div = caps->nominal_perf; + } else { + mul = caps->nominal_freq - caps->lowest_freq; + div = caps->nominal_perf - caps->lowest_perf; + } mul *= KHZ_PER_MHZ; - div = caps->nominal_perf - caps->lowest_perf; offset = caps->nominal_freq * KHZ_PER_MHZ - div64_u64(caps->nominal_perf * mul, div); } else { @@ -1939,11 +1946,17 @@ unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq) { s64 retval, offset = 0; static u64 max_khz; - u64 mul, div; + u64 mul, div; if (caps->lowest_freq && caps->nominal_freq) { - mul = caps->nominal_perf - caps->lowest_perf; - div = caps->nominal_freq - caps->lowest_freq; + /* Avoid special case when nominal_freq is equal to lowest_freq */ + if (caps->lowest_freq == caps->nominal_freq) { + mul = caps->nominal_perf; + div = caps->nominal_freq; + } else { + mul = caps->nominal_perf - caps->lowest_perf; + div = caps->nominal_freq - caps->lowest_freq; + } /* * We don't need to convert to kHz for computing offset and can * directly use nominal_freq and lowest_freq as the div64_u64 diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c index 1cfaa5957ac4..747f83f7114d 100644 --- a/drivers/acpi/prmt.c +++ b/drivers/acpi/prmt.c @@ -52,7 +52,7 @@ struct prm_context_buffer { static LIST_HEAD(prm_module_list); struct prm_handler_info { - guid_t guid; + efi_guid_t guid; efi_status_t (__efiapi *handler_addr)(u64, void *); u64 static_data_buffer_addr; u64 acpi_param_buffer_addr; @@ -72,17 +72,21 @@ struct prm_module_info { struct prm_handler_info handlers[] __counted_by(handler_count); }; -static u64 efi_pa_va_lookup(u64 pa) +static u64 efi_pa_va_lookup(efi_guid_t *guid, u64 pa) { efi_memory_desc_t *md; u64 pa_offset = pa & ~PAGE_MASK; u64 page = pa & PAGE_MASK; for_each_efi_memory_desc(md) { - if (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages) + if ((md->attribute & EFI_MEMORY_RUNTIME) && + (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages)) { return pa_offset + md->virt_addr + page - md->phys_addr; + } } + pr_warn("Failed to find VA for GUID: %pUL, PA: 0x%llx", guid, pa); + return 0; } @@ -148,9 +152,15 @@ acpi_parse_prmt(union acpi_subtable_headers *header, const unsigned long end) th = &tm->handlers[cur_handler]; guid_copy(&th->guid, (guid_t *)handler_info->handler_guid); - th->handler_addr = (void *)efi_pa_va_lookup(handler_info->handler_address); - th->static_data_buffer_addr = efi_pa_va_lookup(handler_info->static_data_buffer_address); - th->acpi_param_buffer_addr = efi_pa_va_lookup(handler_info->acpi_param_buffer_address); + th->handler_addr = + (void *)efi_pa_va_lookup(&th->guid, handler_info->handler_address); + + th->static_data_buffer_addr = + efi_pa_va_lookup(&th->guid, handler_info->static_data_buffer_address); + + th->acpi_param_buffer_addr = + efi_pa_va_lookup(&th->guid, handler_info->acpi_param_buffer_address); + } while (++cur_handler < tm->handler_count && (handler_info = get_next_handler(handler_info))); return 0; @@ -277,6 +287,13 @@ static acpi_status acpi_platformrt_space_handler(u32 function, if (!handler || !module) goto invalid_guid; + if (!handler->handler_addr || + !handler->static_data_buffer_addr || + !handler->acpi_param_buffer_addr) { + buffer->prm_status = PRM_HANDLER_ERROR; + return AE_OK; + } + ACPI_COPY_NAMESEG(context.signature, "PRMC"); context.revision = 0x0; context.reserved = 0x0; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 129bceb1f4a2..7fe842dae1ec 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -503,6 +503,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = { DMI_MATCH(DMI_BOARD_NAME, "17U70P"), }, }, + { + /* LG Electronics 16T90SP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), + DMI_MATCH(DMI_BOARD_NAME, "16T90SP"), + }, + }, { } }; diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index fa41ea57a978..3b303d4ae37a 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -651,6 +651,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, /* the scmd has an associated qc */ if (!(qc->flags & ATA_QCFLAG_EH)) { /* which hasn't failed yet, timeout */ + set_host_byte(scmd, DID_TIME_OUT); qc->err_mask |= AC_ERR_TIMEOUT; qc->flags |= ATA_QCFLAG_EH; nr_timedout++; diff --git a/drivers/base/core.c b/drivers/base/core.c index a4c853411a6b..048ff98dbdfd 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -26,7 +26,6 @@ #include <linux/of.h> #include <linux/of_device.h> #include <linux/pm_runtime.h> -#include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> @@ -2634,7 +2633,6 @@ static const char *dev_uevent_name(const struct kobject *kobj) static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { const struct device *dev = kobj_to_dev(kobj); - struct device_driver *driver; int retval = 0; /* add device node properties if present */ @@ -2663,12 +2661,8 @@ static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) if (dev->type && dev->type->name) add_uevent_var(env, "DEVTYPE=%s", dev->type->name); - /* Synchronize with module_remove_driver() */ - rcu_read_lock(); - driver = READ_ONCE(dev->driver); - if (driver) - add_uevent_var(env, "DRIVER=%s", driver->name); - rcu_read_unlock(); + if (dev->driver) + add_uevent_var(env, "DRIVER=%s", dev->driver->name); /* Add common DT information about the device */ of_device_uevent(dev, env); @@ -2738,8 +2732,11 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, if (!env) return -ENOMEM; + /* Synchronize with really_probe() */ + device_lock(dev); /* let the kset specific function add its keys */ retval = kset->uevent_ops->uevent(&dev->kobj, env); + device_unlock(dev); if (retval) goto out; @@ -4038,6 +4035,41 @@ int device_for_each_child_reverse(struct device *parent, void *data, EXPORT_SYMBOL_GPL(device_for_each_child_reverse); /** + * device_for_each_child_reverse_from - device child iterator in reversed order. + * @parent: parent struct device. + * @from: optional starting point in child list + * @fn: function to be called for each device. + * @data: data for the callback. + * + * Iterate over @parent's child devices, starting at @from, and call @fn + * for each, passing it @data. This helper is identical to + * device_for_each_child_reverse() when @from is NULL. + * + * @fn is checked each iteration. If it returns anything other than 0, + * iteration stop and that value is returned to the caller of + * device_for_each_child_reverse_from(); + */ +int device_for_each_child_reverse_from(struct device *parent, + struct device *from, const void *data, + int (*fn)(struct device *, const void *)) +{ + struct klist_iter i; + struct device *child; + int error = 0; + + if (!parent->p) + return 0; + + klist_iter_init_node(&parent->p->klist_children, &i, + (from ? &from->p->knode_parent : NULL)); + while ((child = prev_device(&i)) && !error) + error = fn(child, data); + klist_iter_exit(&i); + return error; +} +EXPORT_SYMBOL_GPL(device_for_each_child_reverse_from); + +/** * device_find_child - device iterator for locating a particular device. * @parent: parent struct device * @match: Callback function to check device diff --git a/drivers/base/module.c b/drivers/base/module.c index c4eaa1158d54..5bc71bea883a 100644 --- a/drivers/base/module.c +++ b/drivers/base/module.c @@ -7,7 +7,6 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/string.h> -#include <linux/rcupdate.h> #include "base.h" static char *make_driver_name(const struct device_driver *drv) @@ -102,9 +101,6 @@ void module_remove_driver(const struct device_driver *drv) if (!drv) return; - /* Synchronize with dev_uevent() */ - synchronize_rcu(); - sysfs_remove_link(&drv->p->kobj, "module"); if (drv->owner) diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index 854546000c92..7df7abaf3e52 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -525,10 +525,6 @@ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) { struct tpm_chip *chip = container_of(rng, struct tpm_chip, hwrng); - /* Give back zero bytes, as TPM chip has not yet fully resumed: */ - if (chip->flags & TPM_CHIP_FLAG_SUSPENDED) - return 0; - return tpm_get_random(chip, data, max); } @@ -674,6 +670,16 @@ EXPORT_SYMBOL_GPL(tpm_chip_register); */ void tpm_chip_unregister(struct tpm_chip *chip) { +#ifdef CONFIG_TCG_TPM2_HMAC + int rc; + + rc = tpm_try_get_ops(chip); + if (!rc) { + tpm2_end_auth_session(chip); + tpm_put_ops(chip); + } +#endif + tpm_del_legacy_sysfs(chip); if (tpm_is_hwrng_enabled(chip)) hwrng_unregister(&chip->hwrng); diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c index c3fbbf4d3db7..48ff87444f85 100644 --- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -27,6 +27,9 @@ static ssize_t tpm_dev_transmit(struct tpm_chip *chip, struct tpm_space *space, struct tpm_header *header = (void *)buf; ssize_t ret, len; + if (chip->flags & TPM_CHIP_FLAG_TPM2) + tpm2_end_auth_session(chip); + ret = tpm2_prepare_space(chip, space, buf, bufsiz); /* If the command is not implemented by the TPM, synthesize a * response with a TPM2_RC_COMMAND_CODE return for user-space. diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 5da134f12c9a..b1daa0d7b341 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -370,6 +370,13 @@ int tpm_pm_suspend(struct device *dev) if (!chip) return -ENODEV; + rc = tpm_try_get_ops(chip); + if (rc) { + /* Can be safely set out of locks, as no action cannot race: */ + chip->flags |= TPM_CHIP_FLAG_SUSPENDED; + goto out; + } + if (chip->flags & TPM_CHIP_FLAG_ALWAYS_POWERED) goto suspended; @@ -377,19 +384,19 @@ int tpm_pm_suspend(struct device *dev) !pm_suspend_via_firmware()) goto suspended; - rc = tpm_try_get_ops(chip); - if (!rc) { - if (chip->flags & TPM_CHIP_FLAG_TPM2) - tpm2_shutdown(chip, TPM2_SU_STATE); - else - rc = tpm1_pm_suspend(chip, tpm_suspend_pcr); - - tpm_put_ops(chip); + if (chip->flags & TPM_CHIP_FLAG_TPM2) { + tpm2_end_auth_session(chip); + tpm2_shutdown(chip, TPM2_SU_STATE); + goto suspended; } + rc = tpm1_pm_suspend(chip, tpm_suspend_pcr); + suspended: chip->flags |= TPM_CHIP_FLAG_SUSPENDED; + tpm_put_ops(chip); +out: if (rc) dev_err(dev, "Ignoring error %d while suspending\n", rc); return 0; @@ -438,11 +445,18 @@ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max) if (!chip) return -ENODEV; + /* Give back zero bytes, as TPM chip has not yet fully resumed: */ + if (chip->flags & TPM_CHIP_FLAG_SUSPENDED) { + rc = 0; + goto out; + } + if (chip->flags & TPM_CHIP_FLAG_TPM2) rc = tpm2_get_random(chip, out, max); else rc = tpm1_get_random(chip, out, max); +out: tpm_put_ops(chip); return rc; } diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index 511c67061728..0739830904b2 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -333,6 +333,9 @@ void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf, } #ifdef CONFIG_TCG_TPM2_HMAC + /* The first write to /dev/tpm{rm0} will flush the session. */ + attributes |= TPM2_SA_CONTINUE_SESSION; + /* * The Architecture Guide requires us to strip trailing zeros * before computing the HMAC @@ -484,7 +487,8 @@ static void tpm2_KDFe(u8 z[EC_PT_SZ], const char *str, u8 *pt_u, u8 *pt_v, sha256_final(&sctx, out); } -static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip) +static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip, + struct tpm2_auth *auth) { struct crypto_kpp *kpp; struct kpp_request *req; @@ -543,7 +547,7 @@ static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip) sg_set_buf(&s[0], chip->null_ec_key_x, EC_PT_SZ); sg_set_buf(&s[1], chip->null_ec_key_y, EC_PT_SZ); kpp_request_set_input(req, s, EC_PT_SZ*2); - sg_init_one(d, chip->auth->salt, EC_PT_SZ); + sg_init_one(d, auth->salt, EC_PT_SZ); kpp_request_set_output(req, d, EC_PT_SZ); crypto_kpp_compute_shared_secret(req); kpp_request_free(req); @@ -554,8 +558,7 @@ static void tpm_buf_append_salt(struct tpm_buf *buf, struct tpm_chip *chip) * This works because KDFe fully consumes the secret before it * writes the salt */ - tpm2_KDFe(chip->auth->salt, "SECRET", x, chip->null_ec_key_x, - chip->auth->salt); + tpm2_KDFe(auth->salt, "SECRET", x, chip->null_ec_key_x, auth->salt); out: crypto_free_kpp(kpp); @@ -853,7 +856,9 @@ int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf, if (rc) /* manually close the session if it wasn't consumed */ tpm2_flush_context(chip, auth->handle); - memzero_explicit(auth, sizeof(*auth)); + + kfree_sensitive(auth); + chip->auth = NULL; } else { /* reset for next use */ auth->session = TPM_HEADER_SIZE; @@ -881,7 +886,8 @@ void tpm2_end_auth_session(struct tpm_chip *chip) return; tpm2_flush_context(chip, auth->handle); - memzero_explicit(auth, sizeof(*auth)); + kfree_sensitive(auth); + chip->auth = NULL; } EXPORT_SYMBOL(tpm2_end_auth_session); @@ -915,33 +921,37 @@ static int tpm2_parse_start_auth_session(struct tpm2_auth *auth, static int tpm2_load_null(struct tpm_chip *chip, u32 *null_key) { - int rc; unsigned int offset = 0; /* dummy offset for null seed context */ u8 name[SHA256_DIGEST_SIZE + 2]; + u32 tmp_null_key; + int rc; rc = tpm2_load_context(chip, chip->null_key_context, &offset, - null_key); - if (rc != -EINVAL) - return rc; + &tmp_null_key); + if (rc != -EINVAL) { + if (!rc) + *null_key = tmp_null_key; + goto err; + } - /* an integrity failure may mean the TPM has been reset */ - dev_err(&chip->dev, "NULL key integrity failure!\n"); - /* check the null name against what we know */ - tpm2_create_primary(chip, TPM2_RH_NULL, NULL, name); - if (memcmp(name, chip->null_key_name, sizeof(name)) == 0) - /* name unchanged, assume transient integrity failure */ - return rc; - /* - * Fatal TPM failure: the NULL seed has actually changed, so - * the TPM must have been illegally reset. All in-kernel TPM - * operations will fail because the NULL primary can't be - * loaded to salt the sessions, but disable the TPM anyway so - * userspace programmes can't be compromised by it. - */ - dev_err(&chip->dev, "NULL name has changed, disabling TPM due to interference\n"); + /* Try to re-create null key, given the integrity failure: */ + rc = tpm2_create_primary(chip, TPM2_RH_NULL, &tmp_null_key, name); + if (rc) + goto err; + + /* Return null key if the name has not been changed: */ + if (!memcmp(name, chip->null_key_name, sizeof(name))) { + *null_key = tmp_null_key; + return 0; + } + + /* Deduce from the name change TPM interference: */ + dev_err(&chip->dev, "null key integrity check failed\n"); + tpm2_flush_context(chip, tmp_null_key); chip->flags |= TPM_CHIP_FLAG_DISABLE; - return rc; +err: + return rc ? -ENODEV : 0; } /** @@ -958,16 +968,20 @@ static int tpm2_load_null(struct tpm_chip *chip, u32 *null_key) */ int tpm2_start_auth_session(struct tpm_chip *chip) { + struct tpm2_auth *auth; struct tpm_buf buf; - struct tpm2_auth *auth = chip->auth; - int rc; u32 null_key; + int rc; - if (!auth) { - dev_warn_once(&chip->dev, "auth session is not active\n"); + if (chip->auth) { + dev_warn_once(&chip->dev, "auth session is active\n"); return 0; } + auth = kzalloc(sizeof(*auth), GFP_KERNEL); + if (!auth) + return -ENOMEM; + rc = tpm2_load_null(chip, &null_key); if (rc) goto out; @@ -988,7 +1002,7 @@ int tpm2_start_auth_session(struct tpm_chip *chip) tpm_buf_append(&buf, auth->our_nonce, sizeof(auth->our_nonce)); /* append encrypted salt and squirrel away unencrypted in auth */ - tpm_buf_append_salt(&buf, chip); + tpm_buf_append_salt(&buf, chip, auth); /* session type (HMAC, audit or policy) */ tpm_buf_append_u8(&buf, TPM2_SE_HMAC); @@ -1010,10 +1024,13 @@ int tpm2_start_auth_session(struct tpm_chip *chip) tpm_buf_destroy(&buf); - if (rc) - goto out; + if (rc == TPM2_RC_SUCCESS) { + chip->auth = auth; + return 0; + } - out: +out: + kfree_sensitive(auth); return rc; } EXPORT_SYMBOL(tpm2_start_auth_session); @@ -1347,18 +1364,21 @@ static int tpm2_create_null_primary(struct tpm_chip *chip) * * Derive and context save the null primary and allocate memory in the * struct tpm_chip for the authorizations. + * + * Return: + * * 0 - OK + * * -errno - A system error + * * TPM_RC - A TPM error */ int tpm2_sessions_init(struct tpm_chip *chip) { int rc; rc = tpm2_create_null_primary(chip); - if (rc) - dev_err(&chip->dev, "TPM: security failed (NULL seed derivation): %d\n", rc); - - chip->auth = kmalloc(sizeof(*chip->auth), GFP_KERNEL); - if (!chip->auth) - return -ENOMEM; + if (rc) { + dev_err(&chip->dev, "null key creation failed with %d\n", rc); + return rc; + } return rc; } diff --git a/drivers/cxl/Kconfig b/drivers/cxl/Kconfig index 29c192f20082..876469e23f7a 100644 --- a/drivers/cxl/Kconfig +++ b/drivers/cxl/Kconfig @@ -60,6 +60,7 @@ config CXL_ACPI default CXL_BUS select ACPI_TABLE_LIB select ACPI_HMAT + select CXL_PORT help Enable support for host managed device memory (HDM) resources published by a platform's ACPI CXL memory layout description. See diff --git a/drivers/cxl/Makefile b/drivers/cxl/Makefile index db321f48ba52..2caa90fa4bf2 100644 --- a/drivers/cxl/Makefile +++ b/drivers/cxl/Makefile @@ -1,13 +1,21 @@ # SPDX-License-Identifier: GPL-2.0 + +# Order is important here for the built-in case: +# - 'core' first for fundamental init +# - 'port' before platform root drivers like 'acpi' so that CXL-root ports +# are immediately enabled +# - 'mem' and 'pmem' before endpoint drivers so that memdevs are +# immediately enabled +# - 'pci' last, also mirrors the hardware enumeration hierarchy obj-y += core/ -obj-$(CONFIG_CXL_PCI) += cxl_pci.o -obj-$(CONFIG_CXL_MEM) += cxl_mem.o +obj-$(CONFIG_CXL_PORT) += cxl_port.o obj-$(CONFIG_CXL_ACPI) += cxl_acpi.o obj-$(CONFIG_CXL_PMEM) += cxl_pmem.o -obj-$(CONFIG_CXL_PORT) += cxl_port.o +obj-$(CONFIG_CXL_MEM) += cxl_mem.o +obj-$(CONFIG_CXL_PCI) += cxl_pci.o -cxl_mem-y := mem.o -cxl_pci-y := pci.o +cxl_port-y := port.o cxl_acpi-y := acpi.o cxl_pmem-y := pmem.o security.o -cxl_port-y := port.o +cxl_mem-y := mem.o +cxl_pci-y := pci.o diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index 82b78e331d8e..432b7cfd12a8 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -924,6 +924,13 @@ static void __exit cxl_acpi_exit(void) /* load before dax_hmem sees 'Soft Reserved' CXL ranges */ subsys_initcall(cxl_acpi_init); + +/* + * Arrange for host-bridge ports to be active synchronous with + * cxl_acpi_probe() exit. + */ +MODULE_SOFTDEP("pre: cxl_port"); + module_exit(cxl_acpi_exit); MODULE_DESCRIPTION("CXL ACPI: Platform Support"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c index ef1621d40f05..e9cd7939c407 100644 --- a/drivers/cxl/core/cdat.c +++ b/drivers/cxl/core/cdat.c @@ -641,6 +641,9 @@ static int cxl_endpoint_gather_bandwidth(struct cxl_region *cxlr, void *ptr; int rc; + if (!dev_is_pci(cxlds->dev)) + return -ENODEV; + if (cxlds->rcd) return -ENODEV; diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 3df10517a327..223c273c0cd1 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -712,7 +712,44 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld) return 0; } -static int cxl_decoder_reset(struct cxl_decoder *cxld) +static int commit_reap(struct device *dev, const void *data) +{ + struct cxl_port *port = to_cxl_port(dev->parent); + struct cxl_decoder *cxld; + + if (!is_switch_decoder(dev) && !is_endpoint_decoder(dev)) + return 0; + + cxld = to_cxl_decoder(dev); + if (port->commit_end == cxld->id && + ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)) { + port->commit_end--; + dev_dbg(&port->dev, "reap: %s commit_end: %d\n", + dev_name(&cxld->dev), port->commit_end); + } + + return 0; +} + +void cxl_port_commit_reap(struct cxl_decoder *cxld) +{ + struct cxl_port *port = to_cxl_port(cxld->dev.parent); + + lockdep_assert_held_write(&cxl_region_rwsem); + + /* + * Once the highest committed decoder is disabled, free any other + * decoders that were pinned allocated by out-of-order release. + */ + port->commit_end--; + dev_dbg(&port->dev, "reap: %s commit_end: %d\n", dev_name(&cxld->dev), + port->commit_end); + device_for_each_child_reverse_from(&port->dev, &cxld->dev, NULL, + commit_reap); +} +EXPORT_SYMBOL_NS_GPL(cxl_port_commit_reap, CXL); + +static void cxl_decoder_reset(struct cxl_decoder *cxld) { struct cxl_port *port = to_cxl_port(cxld->dev.parent); struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev); @@ -721,14 +758,14 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld) u32 ctrl; if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0) - return 0; + return; - if (port->commit_end != id) { + if (port->commit_end == id) + cxl_port_commit_reap(cxld); + else dev_dbg(&port->dev, "%s: out of order reset, expected decoder%d.%d\n", dev_name(&cxld->dev), port->id, port->commit_end); - return -EBUSY; - } down_read(&cxl_dpa_rwsem); ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(id)); @@ -741,7 +778,6 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld) writel(0, hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(id)); up_read(&cxl_dpa_rwsem); - port->commit_end--; cxld->flags &= ~CXL_DECODER_F_ENABLE; /* Userspace is now responsible for reconfiguring this decoder */ @@ -751,8 +787,6 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld) cxled = to_cxl_endpoint_decoder(&cxld->dev); cxled->state = CXL_DECODER_STATE_MANUAL; } - - return 0; } static int cxl_setup_hdm_decoder_from_dvsec( diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index e666ec6a9085..af92c67bc954 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -2084,11 +2084,18 @@ static void cxl_bus_remove(struct device *dev) static struct workqueue_struct *cxl_bus_wq; -static void cxl_bus_rescan_queue(struct work_struct *w) +static int cxl_rescan_attach(struct device *dev, void *data) { - int rc = bus_rescan_devices(&cxl_bus_type); + int rc = device_attach(dev); + + dev_vdbg(dev, "rescan: %s\n", rc ? "attach" : "detached"); - pr_debug("CXL bus rescan result: %d\n", rc); + return 0; +} + +static void cxl_bus_rescan_queue(struct work_struct *w) +{ + bus_for_each_dev(&cxl_bus_type, NULL, NULL, cxl_rescan_attach); } void cxl_bus_rescan(void) diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index e701e4b04032..dff618c708dc 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -232,8 +232,8 @@ static int cxl_region_invalidate_memregion(struct cxl_region *cxlr) "Bypassing cpu_cache_invalidate_memregion() for testing!\n"); return 0; } else { - dev_err(&cxlr->dev, - "Failed to synchronize CPU cache state\n"); + dev_WARN(&cxlr->dev, + "Failed to synchronize CPU cache state\n"); return -ENXIO; } } @@ -242,19 +242,17 @@ static int cxl_region_invalidate_memregion(struct cxl_region *cxlr) return 0; } -static int cxl_region_decode_reset(struct cxl_region *cxlr, int count) +static void cxl_region_decode_reset(struct cxl_region *cxlr, int count) { struct cxl_region_params *p = &cxlr->params; - int i, rc = 0; + int i; /* - * Before region teardown attempt to flush, and if the flush - * fails cancel the region teardown for data consistency - * concerns + * Before region teardown attempt to flush, evict any data cached for + * this region, or scream loudly about missing arch / platform support + * for CXL teardown. */ - rc = cxl_region_invalidate_memregion(cxlr); - if (rc) - return rc; + cxl_region_invalidate_memregion(cxlr); for (i = count - 1; i >= 0; i--) { struct cxl_endpoint_decoder *cxled = p->targets[i]; @@ -277,23 +275,17 @@ static int cxl_region_decode_reset(struct cxl_region *cxlr, int count) cxl_rr = cxl_rr_load(iter, cxlr); cxld = cxl_rr->decoder; if (cxld->reset) - rc = cxld->reset(cxld); - if (rc) - return rc; + cxld->reset(cxld); set_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags); } endpoint_reset: - rc = cxled->cxld.reset(&cxled->cxld); - if (rc) - return rc; + cxled->cxld.reset(&cxled->cxld); set_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags); } /* all decoders associated with this region have been torn down */ clear_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags); - - return 0; } static int commit_decoder(struct cxl_decoder *cxld) @@ -409,16 +401,8 @@ static ssize_t commit_store(struct device *dev, struct device_attribute *attr, * still pending. */ if (p->state == CXL_CONFIG_RESET_PENDING) { - rc = cxl_region_decode_reset(cxlr, p->interleave_ways); - /* - * Revert to committed since there may still be active - * decoders associated with this region, or move forward - * to active to mark the reset successful - */ - if (rc) - p->state = CXL_CONFIG_COMMIT; - else - p->state = CXL_CONFIG_ACTIVE; + cxl_region_decode_reset(cxlr, p->interleave_ways); + p->state = CXL_CONFIG_ACTIVE; } } @@ -794,26 +778,50 @@ out: return rc; } +static int check_commit_order(struct device *dev, const void *data) +{ + struct cxl_decoder *cxld = to_cxl_decoder(dev); + + /* + * if port->commit_end is not the only free decoder, then out of + * order shutdown has occurred, block further allocations until + * that is resolved + */ + if (((cxld->flags & CXL_DECODER_F_ENABLE) == 0)) + return -EBUSY; + return 0; +} + static int match_free_decoder(struct device *dev, void *data) { + struct cxl_port *port = to_cxl_port(dev->parent); struct cxl_decoder *cxld; - int *id = data; + int rc; if (!is_switch_decoder(dev)) return 0; cxld = to_cxl_decoder(dev); - /* enforce ordered allocation */ - if (cxld->id != *id) + if (cxld->id != port->commit_end + 1) return 0; - if (!cxld->region) - return 1; - - (*id)++; + if (cxld->region) { + dev_dbg(dev->parent, + "next decoder to commit (%s) is already reserved (%s)\n", + dev_name(dev), dev_name(&cxld->region->dev)); + return 0; + } - return 0; + rc = device_for_each_child_reverse_from(dev->parent, dev, NULL, + check_commit_order); + if (rc) { + dev_dbg(dev->parent, + "unable to allocate %s due to out of order shutdown\n", + dev_name(dev)); + return 0; + } + return 1; } static int match_auto_decoder(struct device *dev, void *data) @@ -840,7 +848,6 @@ cxl_region_find_decoder(struct cxl_port *port, struct cxl_region *cxlr) { struct device *dev; - int id = 0; if (port == cxled_to_port(cxled)) return &cxled->cxld; @@ -849,7 +856,7 @@ cxl_region_find_decoder(struct cxl_port *port, dev = device_find_child(&port->dev, &cxlr->params, match_auto_decoder); else - dev = device_find_child(&port->dev, &id, match_free_decoder); + dev = device_find_child(&port->dev, NULL, match_free_decoder); if (!dev) return NULL; /* @@ -2054,13 +2061,7 @@ static int cxl_region_detach(struct cxl_endpoint_decoder *cxled) get_device(&cxlr->dev); if (p->state > CXL_CONFIG_ACTIVE) { - /* - * TODO: tear down all impacted regions if a device is - * removed out of order - */ - rc = cxl_region_decode_reset(cxlr, p->interleave_ways); - if (rc) - goto out; + cxl_region_decode_reset(cxlr, p->interleave_ways); p->state = CXL_CONFIG_ACTIVE; } diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index 8672b42ee4d1..8389a94adb1a 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -279,7 +279,7 @@ TRACE_EVENT(cxl_generic_event, #define CXL_GMER_MEM_EVT_TYPE_ECC_ERROR 0x00 #define CXL_GMER_MEM_EVT_TYPE_INV_ADDR 0x01 #define CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR 0x02 -#define show_mem_event_type(type) __print_symbolic(type, \ +#define show_gmer_mem_event_type(type) __print_symbolic(type, \ { CXL_GMER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \ { CXL_GMER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \ { CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" } \ @@ -373,7 +373,7 @@ TRACE_EVENT(cxl_general_media, "hpa=%llx region=%s region_uuid=%pUb", __entry->dpa, show_dpa_flags(__entry->dpa_flags), show_event_desc_flags(__entry->descriptor), - show_mem_event_type(__entry->type), + show_gmer_mem_event_type(__entry->type), show_trans_type(__entry->transaction_type), __entry->channel, __entry->rank, __entry->device, __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE), @@ -391,6 +391,17 @@ TRACE_EVENT(cxl_general_media, * DRAM Event Record defines many fields the same as the General Media Event * Record. Reuse those definitions as appropriate. */ +#define CXL_DER_MEM_EVT_TYPE_ECC_ERROR 0x00 +#define CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR 0x01 +#define CXL_DER_MEM_EVT_TYPE_INV_ADDR 0x02 +#define CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR 0x03 +#define show_dram_mem_event_type(type) __print_symbolic(type, \ + { CXL_DER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \ + { CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR, "Scrub Media ECC Error" }, \ + { CXL_DER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \ + { CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" } \ +) + #define CXL_DER_VALID_CHANNEL BIT(0) #define CXL_DER_VALID_RANK BIT(1) #define CXL_DER_VALID_NIBBLE BIT(2) @@ -477,7 +488,7 @@ TRACE_EVENT(cxl_dram, "hpa=%llx region=%s region_uuid=%pUb", __entry->dpa, show_dpa_flags(__entry->dpa_flags), show_event_desc_flags(__entry->descriptor), - show_mem_event_type(__entry->type), + show_dram_mem_event_type(__entry->type), show_trans_type(__entry->transaction_type), __entry->channel, __entry->rank, __entry->nibble_mask, __entry->bank_group, __entry->bank, diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 0d8b810a51f0..5406e3ab3d4a 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -359,7 +359,7 @@ struct cxl_decoder { struct cxl_region *region; unsigned long flags; int (*commit)(struct cxl_decoder *cxld); - int (*reset)(struct cxl_decoder *cxld); + void (*reset)(struct cxl_decoder *cxld); }; /* @@ -730,6 +730,7 @@ static inline bool is_cxl_root(struct cxl_port *port) int cxl_num_decoders_committed(struct cxl_port *port); bool is_cxl_port(const struct device *dev); struct cxl_port *to_cxl_port(const struct device *dev); +void cxl_port_commit_reap(struct cxl_decoder *cxld); struct pci_bus; int devm_cxl_register_pci_bus(struct device *host, struct device *uport_dev, struct pci_bus *bus); diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index 861dde65768f..9dc394295e1f 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -208,7 +208,22 @@ static struct cxl_driver cxl_port_driver = { }, }; -module_cxl_driver(cxl_port_driver); +static int __init cxl_port_init(void) +{ + return cxl_driver_register(&cxl_port_driver); +} +/* + * Be ready to immediately enable ports emitted by the platform CXL root + * (e.g. cxl_acpi) when CONFIG_CXL_PORT=y. + */ +subsys_initcall(cxl_port_init); + +static void __exit cxl_port_exit(void) +{ + cxl_driver_unregister(&cxl_port_driver); +} +module_exit(cxl_port_exit); + MODULE_DESCRIPTION("CXL: Port enumeration and services"); MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS(CXL); diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c index 65a27c5a7bce..811389fc9cb8 100644 --- a/drivers/dma/sh/rz-dmac.c +++ b/drivers/dma/sh/rz-dmac.c @@ -601,22 +601,25 @@ static int rz_dmac_config(struct dma_chan *chan, struct rz_dmac_chan *channel = to_rz_dmac_chan(chan); u32 val; - channel->src_per_address = config->src_addr; channel->dst_per_address = config->dst_addr; - - val = rz_dmac_ds_to_val_mapping(config->dst_addr_width); - if (val == CHCFG_DS_INVALID) - return -EINVAL; - channel->chcfg &= ~CHCFG_FILL_DDS_MASK; - channel->chcfg |= FIELD_PREP(CHCFG_FILL_DDS_MASK, val); + if (channel->dst_per_address) { + val = rz_dmac_ds_to_val_mapping(config->dst_addr_width); + if (val == CHCFG_DS_INVALID) + return -EINVAL; - val = rz_dmac_ds_to_val_mapping(config->src_addr_width); - if (val == CHCFG_DS_INVALID) - return -EINVAL; + channel->chcfg |= FIELD_PREP(CHCFG_FILL_DDS_MASK, val); + } + channel->src_per_address = config->src_addr; channel->chcfg &= ~CHCFG_FILL_SDS_MASK; - channel->chcfg |= FIELD_PREP(CHCFG_FILL_SDS_MASK, val); + if (channel->src_per_address) { + val = rz_dmac_ds_to_val_mapping(config->src_addr_width); + if (val == CHCFG_DS_INVALID) + return -EINVAL; + + channel->chcfg |= FIELD_PREP(CHCFG_FILL_SDS_MASK, val); + } return 0; } diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index 406ee199c2ac..b3f27b3f9209 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -3185,27 +3185,40 @@ static int udma_configure_statictr(struct udma_chan *uc, struct udma_desc *d, d->static_tr.elcnt = elcnt; - /* - * PDMA must to close the packet when the channel is in packet mode. - * For TR mode when the channel is not cyclic we also need PDMA to close - * the packet otherwise the transfer will stall because PDMA holds on - * the data it has received from the peripheral. - */ if (uc->config.pkt_mode || !uc->cyclic) { + /* + * PDMA must close the packet when the channel is in packet mode. + * For TR mode when the channel is not cyclic we also need PDMA + * to close the packet otherwise the transfer will stall because + * PDMA holds on the data it has received from the peripheral. + */ unsigned int div = dev_width * elcnt; if (uc->cyclic) d->static_tr.bstcnt = d->residue / d->sglen / div; else d->static_tr.bstcnt = d->residue / div; + } else if (uc->ud->match_data->type == DMA_TYPE_BCDMA && + uc->config.dir == DMA_DEV_TO_MEM && + uc->cyclic) { + /* + * For cyclic mode with BCDMA we have to set EOP in each TR to + * prevent short packet errors seen on channel teardown. So the + * PDMA must close the packet after every TR transfer by setting + * burst count equal to the number of bytes transferred. + */ + struct cppi5_tr_type1_t *tr_req = d->hwdesc[0].tr_req_base; - if (uc->config.dir == DMA_DEV_TO_MEM && - d->static_tr.bstcnt > uc->ud->match_data->statictr_z_mask) - return -EINVAL; + d->static_tr.bstcnt = + (tr_req->icnt0 * tr_req->icnt1) / dev_width; } else { d->static_tr.bstcnt = 0; } + if (uc->config.dir == DMA_DEV_TO_MEM && + d->static_tr.bstcnt > uc->ud->match_data->statictr_z_mask) + return -EINVAL; + return 0; } @@ -3450,8 +3463,9 @@ udma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, /* static TR for remote PDMA */ if (udma_configure_statictr(uc, d, dev_width, burst)) { dev_err(uc->ud->dev, - "%s: StaticTR Z is limited to maximum 4095 (%u)\n", - __func__, d->static_tr.bstcnt); + "%s: StaticTR Z is limited to maximum %u (%u)\n", + __func__, uc->ud->match_data->statictr_z_mask, + d->static_tr.bstcnt); udma_free_hwdesc(uc, d); kfree(d); @@ -3476,6 +3490,7 @@ udma_prep_dma_cyclic_tr(struct udma_chan *uc, dma_addr_t buf_addr, u16 tr0_cnt0, tr0_cnt1, tr1_cnt0; unsigned int i; int num_tr; + u32 period_csf = 0; num_tr = udma_get_tr_counters(period_len, __ffs(buf_addr), &tr0_cnt0, &tr0_cnt1, &tr1_cnt0); @@ -3498,6 +3513,20 @@ udma_prep_dma_cyclic_tr(struct udma_chan *uc, dma_addr_t buf_addr, period_addr = buf_addr | ((u64)uc->config.asel << K3_ADDRESS_ASEL_SHIFT); + /* + * For BCDMA <-> PDMA transfers, the EOP flag needs to be set on the + * last TR of a descriptor, to mark the packet as complete. + * This is required for getting the teardown completion message in case + * of TX, and to avoid short-packet error in case of RX. + * + * As we are in cyclic mode, we do not know which period might be the + * last one, so set the flag for each period. + */ + if (uc->config.ep_type == PSIL_EP_PDMA_XY && + uc->ud->match_data->type == DMA_TYPE_BCDMA) { + period_csf = CPPI5_TR_CSF_EOP; + } + for (i = 0; i < periods; i++) { int tr_idx = i * num_tr; @@ -3525,8 +3554,10 @@ udma_prep_dma_cyclic_tr(struct udma_chan *uc, dma_addr_t buf_addr, } if (!(flags & DMA_PREP_INTERRUPT)) - cppi5_tr_csf_set(&tr_req[tr_idx].flags, - CPPI5_TR_CSF_SUPR_EVT); + period_csf |= CPPI5_TR_CSF_SUPR_EVT; + + if (period_csf) + cppi5_tr_csf_set(&tr_req[tr_idx].flags, period_csf); period_addr += period_len; } @@ -3655,8 +3686,9 @@ udma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len, /* static TR for remote PDMA */ if (udma_configure_statictr(uc, d, dev_width, burst)) { dev_err(uc->ud->dev, - "%s: StaticTR Z is limited to maximum 4095 (%u)\n", - __func__, d->static_tr.bstcnt); + "%s: StaticTR Z is limited to maximum %u (%u)\n", + __func__, uc->ud->match_data->statictr_z_mask, + d->static_tr.bstcnt); udma_free_hwdesc(uc, d); kfree(d); diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index fc0280dcddd1..c130f87147fa 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -170,6 +170,27 @@ dpll_msg_add_temp(struct sk_buff *msg, struct dpll_device *dpll, } static int +dpll_msg_add_clock_quality_level(struct sk_buff *msg, struct dpll_device *dpll, + struct netlink_ext_ack *extack) +{ + const struct dpll_device_ops *ops = dpll_device_ops(dpll); + DECLARE_BITMAP(qls, DPLL_CLOCK_QUALITY_LEVEL_MAX) = { 0 }; + enum dpll_clock_quality_level ql; + int ret; + + if (!ops->clock_quality_level_get) + return 0; + ret = ops->clock_quality_level_get(dpll, dpll_priv(dpll), qls, extack); + if (ret) + return ret; + for_each_set_bit(ql, qls, DPLL_CLOCK_QUALITY_LEVEL_MAX) + if (nla_put_u32(msg, DPLL_A_CLOCK_QUALITY_LEVEL, ql)) + return -EMSGSIZE; + + return 0; +} + +static int dpll_msg_add_pin_prio(struct sk_buff *msg, struct dpll_pin *pin, struct dpll_pin_ref *ref, struct netlink_ext_ack *extack) @@ -559,6 +580,9 @@ dpll_device_get_one(struct dpll_device *dpll, struct sk_buff *msg, ret = dpll_msg_add_lock_status(msg, dpll, extack); if (ret) return ret; + ret = dpll_msg_add_clock_quality_level(msg, dpll, extack); + if (ret) + return ret; ret = dpll_msg_add_mode(msg, dpll, extack); if (ret) return ret; diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c index d3cd4cc54ace..a9a8ba067007 100644 --- a/drivers/edac/qcom_edac.c +++ b/drivers/edac/qcom_edac.c @@ -342,9 +342,11 @@ static int qcom_llcc_edac_probe(struct platform_device *pdev) int ecc_irq; int rc; - rc = qcom_llcc_core_setup(llcc_driv_data, llcc_driv_data->bcast_regmap); - if (rc) - return rc; + if (!llcc_driv_data->ecc_irq_configured) { + rc = qcom_llcc_core_setup(llcc_driv_data, llcc_driv_data->bcast_regmap); + if (rc) + return rc; + } /* Allocate edac control info */ edev_ctl = edac_device_alloc_ctl_info(0, "qcom-llcc", 1, "bank", diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c index 6adadb11962e..892b94cfd626 100644 --- a/drivers/firewire/core-topology.c +++ b/drivers/firewire/core-topology.c @@ -204,7 +204,7 @@ static struct fw_node *build_tree(struct fw_card *card, const u32 *sid, int self // the node->ports array where the parent node should be. Later, // when we handle the parent node, we fix up the reference. ++parent_count; - node->color = i; + node->color = port_index; break; case PHY_PACKET_SELF_ID_PORT_STATUS_CHILD: diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 96b2e5f9a8ef..157172a5f2b5 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -325,7 +325,10 @@ EXPORT_SYMBOL_GPL(scmi_driver_unregister); static void scmi_device_release(struct device *dev) { - kfree(to_scmi_dev(dev)); + struct scmi_device *scmi_dev = to_scmi_dev(dev); + + kfree_const(scmi_dev->name); + kfree(scmi_dev); } static void __scmi_device_destroy(struct scmi_device *scmi_dev) @@ -338,7 +341,6 @@ static void __scmi_device_destroy(struct scmi_device *scmi_dev) if (scmi_dev->protocol_id == SCMI_PROTOCOL_SYSTEM) atomic_set(&scmi_syspower_registered, 0); - kfree_const(scmi_dev->name); ida_free(&scmi_bus_id, scmi_dev->id); device_unregister(&scmi_dev->dev); } @@ -410,7 +412,6 @@ __scmi_device_create(struct device_node *np, struct device *parent, return scmi_dev; put_dev: - kfree_const(scmi_dev->name); put_device(&scmi_dev->dev); ida_free(&scmi_bus_id, id); return NULL; diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index c4b8e7ff88aa..cdec50a698a1 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -163,6 +163,7 @@ void scmi_protocol_release(const struct scmi_handle *handle, u8 protocol_id); * used to initialize this channel * @dev: Reference to device in the SCMI hierarchy corresponding to this * channel + * @is_p2a: A flag to identify a channel as P2A (RX) * @rx_timeout_ms: The configured RX timeout in milliseconds. * @handle: Pointer to SCMI entity handle * @no_completion_irq: Flag to indicate that this channel has no completion @@ -174,6 +175,7 @@ void scmi_protocol_release(const struct scmi_handle *handle, u8 protocol_id); struct scmi_chan_info { int id; struct device *dev; + bool is_p2a; unsigned int rx_timeout_ms; struct scmi_handle *handle; bool no_completion_irq; diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index a477b5ade38d..f8934d049d68 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -1048,6 +1048,11 @@ static inline void scmi_xfer_command_release(struct scmi_info *info, static inline void scmi_clear_channel(struct scmi_info *info, struct scmi_chan_info *cinfo) { + if (!cinfo->is_p2a) { + dev_warn(cinfo->dev, "Invalid clear on A2P channel !\n"); + return; + } + if (info->desc->ops->clear_channel) info->desc->ops->clear_channel(cinfo); } @@ -2638,6 +2643,7 @@ static int scmi_chan_setup(struct scmi_info *info, struct device_node *of_node, if (!cinfo) return -ENOMEM; + cinfo->is_p2a = !tx; cinfo->rx_timeout_ms = info->desc->max_rx_timeout_ms; /* Create a unique name for this transport device */ @@ -3042,10 +3048,10 @@ static const struct scmi_desc *scmi_transport_setup(struct device *dev) dev_info(dev, "Using %s\n", dev_driver_string(trans->supplier)); - ret = of_property_read_u32(dev->of_node, "max-rx-timeout-ms", + ret = of_property_read_u32(dev->of_node, "arm,max-rx-timeout-ms", &trans->desc->max_rx_timeout_ms); if (ret && ret != -EINVAL) - dev_err(dev, "Malformed max-rx-timeout-ms DT property.\n"); + dev_err(dev, "Malformed arm,max-rx-timeout-ms DT property.\n"); dev_info(dev, "SCMI max-rx-timeout: %dms\n", trans->desc->max_rx_timeout_ms); diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c index 285fe7ad490d..3e8051fe8296 100644 --- a/drivers/firmware/arm_sdei.c +++ b/drivers/firmware/arm_sdei.c @@ -763,7 +763,7 @@ static int sdei_device_freeze(struct device *dev) int err; /* unregister private events */ - cpuhp_remove_state(sdei_entry_point); + cpuhp_remove_state(sdei_hp_state); err = sdei_unregister_shared(); if (err) diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c index 9ca5ee58edbd..0f7ec8848202 100644 --- a/drivers/firmware/microchip/mpfs-auto-update.c +++ b/drivers/firmware/microchip/mpfs-auto-update.c @@ -76,14 +76,11 @@ #define AUTO_UPDATE_INFO_SIZE SZ_1M #define AUTO_UPDATE_BITSTREAM_BASE (AUTO_UPDATE_DIRECTORY_SIZE + AUTO_UPDATE_INFO_SIZE) -#define AUTO_UPDATE_TIMEOUT_MS 60000 - struct mpfs_auto_update_priv { struct mpfs_sys_controller *sys_controller; struct device *dev; struct mtd_info *flash; struct fw_upload *fw_uploader; - struct completion programming_complete; size_t size_per_bitstream; bool cancel_request; }; @@ -156,19 +153,6 @@ static void mpfs_auto_update_cancel(struct fw_upload *fw_uploader) static enum fw_upload_err mpfs_auto_update_poll_complete(struct fw_upload *fw_uploader) { - struct mpfs_auto_update_priv *priv = fw_uploader->dd_handle; - int ret; - - /* - * There is no meaningful way to get the status of the programming while - * it is in progress, so attempting anything other than waiting for it - * to complete would be misplaced. - */ - ret = wait_for_completion_timeout(&priv->programming_complete, - msecs_to_jiffies(AUTO_UPDATE_TIMEOUT_MS)); - if (!ret) - return FW_UPLOAD_ERR_TIMEOUT; - return FW_UPLOAD_ERR_NONE; } @@ -349,33 +333,23 @@ static enum fw_upload_err mpfs_auto_update_write(struct fw_upload *fw_uploader, u32 offset, u32 size, u32 *written) { struct mpfs_auto_update_priv *priv = fw_uploader->dd_handle; - enum fw_upload_err err = FW_UPLOAD_ERR_NONE; int ret; - reinit_completion(&priv->programming_complete); - ret = mpfs_auto_update_write_bitstream(fw_uploader, data, offset, size, written); - if (ret) { - err = FW_UPLOAD_ERR_RW_ERROR; - goto out; - } + if (ret) + return FW_UPLOAD_ERR_RW_ERROR; - if (priv->cancel_request) { - err = FW_UPLOAD_ERR_CANCELED; - goto out; - } + if (priv->cancel_request) + return FW_UPLOAD_ERR_CANCELED; if (mpfs_auto_update_is_bitstream_info(data, size)) - goto out; + return FW_UPLOAD_ERR_NONE; ret = mpfs_auto_update_verify_image(fw_uploader); if (ret) - err = FW_UPLOAD_ERR_FW_INVALID; + return FW_UPLOAD_ERR_FW_INVALID; -out: - complete(&priv->programming_complete); - - return err; + return FW_UPLOAD_ERR_NONE; } static const struct fw_upload_ops mpfs_auto_update_ops = { @@ -461,8 +435,6 @@ static int mpfs_auto_update_probe(struct platform_device *pdev) return dev_err_probe(dev, ret, "The current bitstream does not support auto-update\n"); - init_completion(&priv->programming_complete); - fw_uploader = firmware_upload_register(THIS_MODULE, dev, "mpfs-auto-update", &mpfs_auto_update_ops, priv); if (IS_ERR(fw_uploader)) diff --git a/drivers/firmware/qcom/qcom_scm.c b/drivers/firmware/qcom/qcom_scm.c index 10986cb11ec0..2e4260ba5f79 100644 --- a/drivers/firmware/qcom/qcom_scm.c +++ b/drivers/firmware/qcom/qcom_scm.c @@ -112,6 +112,7 @@ enum qcom_scm_qseecom_tz_cmd_info { }; #define QSEECOM_MAX_APP_NAME_SIZE 64 +#define SHMBRIDGE_RESULT_NOTSUPP 4 /* Each bit configures cold/warm boot address for one of the 4 CPUs */ static const u8 qcom_scm_cpu_cold_bits[QCOM_SCM_BOOT_MAX_CPUS] = { @@ -216,7 +217,7 @@ static DEFINE_SPINLOCK(scm_query_lock); struct qcom_tzmem_pool *qcom_scm_get_tzmem_pool(void) { - return __scm->mempool; + return __scm ? __scm->mempool : NULL; } static enum qcom_scm_convention __get_convention(void) @@ -545,7 +546,7 @@ static void qcom_scm_set_download_mode(u32 dload_mode) } else if (__qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_BOOT, QCOM_SCM_BOOT_SET_DLOAD_MODE)) { ret = __qcom_scm_set_dload_mode(__scm->dev, !!dload_mode); - } else { + } else if (dload_mode) { dev_err(__scm->dev, "No available mechanism for setting download mode\n"); } @@ -1361,6 +1362,8 @@ EXPORT_SYMBOL_GPL(qcom_scm_lmh_dcvsh_available); int qcom_scm_shm_bridge_enable(void) { + int ret; + struct qcom_scm_desc desc = { .svc = QCOM_SCM_SVC_MP, .cmd = QCOM_SCM_MP_SHM_BRIDGE_ENABLE, @@ -1373,7 +1376,15 @@ int qcom_scm_shm_bridge_enable(void) QCOM_SCM_MP_SHM_BRIDGE_ENABLE)) return -EOPNOTSUPP; - return qcom_scm_call(__scm->dev, &desc, &res) ?: res.result[0]; + ret = qcom_scm_call(__scm->dev, &desc, &res); + + if (ret) + return ret; + + if (res.result[0] == SHMBRIDGE_RESULT_NOTSUPP) + return -EOPNOTSUPP; + + return res.result[0]; } EXPORT_SYMBOL_GPL(qcom_scm_shm_bridge_enable); diff --git a/drivers/gpio/gpio-sloppy-logic-analyzer.c b/drivers/gpio/gpio-sloppy-logic-analyzer.c index 07e0d7180579..59a8f3a5c4e4 100644 --- a/drivers/gpio/gpio-sloppy-logic-analyzer.c +++ b/drivers/gpio/gpio-sloppy-logic-analyzer.c @@ -234,7 +234,9 @@ static int gpio_la_poll_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - devm_mutex_init(dev, &priv->blob_lock); + ret = devm_mutex_init(dev, &priv->blob_lock); + if (ret) + return ret; fops_buf_size_set(priv, GPIO_LA_DEFAULT_BUF_SIZE); diff --git a/drivers/gpio/gpiolib-swnode.c b/drivers/gpio/gpiolib-swnode.c index 2b2dd7e92211..51d2475c05c5 100644 --- a/drivers/gpio/gpiolib-swnode.c +++ b/drivers/gpio/gpiolib-swnode.c @@ -64,7 +64,7 @@ struct gpio_desc *swnode_find_gpio(struct fwnode_handle *fwnode, struct fwnode_reference_args args; struct gpio_desc *desc; char propname[32]; /* 32 is max size of property name */ - int ret; + int ret = 0; swnode = to_software_node(fwnode); if (!swnode) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index d5952ab7752c..2b02655abb56 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -4926,6 +4926,8 @@ static void *gpiolib_seq_start(struct seq_file *s, loff_t *pos) return NULL; s->private = priv; + if (*pos > 0) + priv->newline = true; priv->idx = srcu_read_lock(&gpio_devices_srcu); list_for_each_entry_srcu(gdev, &gpio_devices, list, @@ -4969,7 +4971,7 @@ static int gpiolib_seq_show(struct seq_file *s, void *v) gc = srcu_dereference(gdev->chip, &gdev->srcu); if (!gc) { - seq_printf(s, "%s%s: (dangling chip)", + seq_printf(s, "%s%s: (dangling chip)\n", priv->newline ? "\n" : "", dev_name(&gdev->dev)); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index f85ace0384d2..1f5a296f5ed2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -147,6 +147,7 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif, struct acpi_buffer *params) { acpi_status status; + union acpi_object *obj; union acpi_object atif_arg_elements[2]; struct acpi_object_list atif_arg; struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; @@ -169,16 +170,24 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif, status = acpi_evaluate_object(atif->handle, NULL, &atif_arg, &buffer); + obj = (union acpi_object *)buffer.pointer; - /* Fail only if calling the method fails and ATIF is supported */ + /* Fail if calling the method fails and ATIF is supported */ if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) { DRM_DEBUG_DRIVER("failed to evaluate ATIF got %s\n", acpi_format_exception(status)); - kfree(buffer.pointer); + kfree(obj); return NULL; } - return buffer.pointer; + if (obj->type != ACPI_TYPE_BUFFER) { + DRM_DEBUG_DRIVER("bad object returned from ATIF: %d\n", + obj->type); + kfree(obj); + return NULL; + } + + return obj; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index a8763496aed3..9288f37a3cc5 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -51,6 +51,12 @@ MODULE_FIRMWARE("amdgpu/sdma_7_0_1.bin"); #define SDMA0_HYP_DEC_REG_END 0x589a #define SDMA1_HYP_DEC_REG_OFFSET 0x20 +/*define for compression field for sdma7*/ +#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_offset 0 +#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_mask 0x00000001 +#define SDMA_PKT_CONSTANT_FILL_HEADER_compress_shift 16 +#define SDMA_PKT_CONSTANT_FILL_HEADER_COMPRESS(x) (((x) & SDMA_PKT_CONSTANT_FILL_HEADER_compress_mask) << SDMA_PKT_CONSTANT_FILL_HEADER_compress_shift) + static const struct amdgpu_hwip_reg_entry sdma_reg_list_7_0[] = { SOC15_REG_ENTRY_STR(GC, 0, regSDMA0_STATUS_REG), SOC15_REG_ENTRY_STR(GC, 0, regSDMA0_STATUS1_REG), @@ -1724,7 +1730,8 @@ static void sdma_v7_0_emit_fill_buffer(struct amdgpu_ib *ib, uint64_t dst_offset, uint32_t byte_count) { - ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_CONST_FILL); + ib->ptr[ib->length_dw++] = SDMA_PKT_CONSTANT_FILL_HEADER_OP(SDMA_OP_CONST_FILL) | + SDMA_PKT_CONSTANT_FILL_HEADER_COMPRESS(1); ib->ptr[ib->length_dw++] = lower_32_bits(dst_offset); ib->ptr[ib->length_dw++] = upper_32_bits(dst_offset); ib->ptr[ib->length_dw++] = src_data; 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 6b5e2206e687..13421a58210d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8374,7 +8374,8 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, if (amdgpu_ip_version(adev, DCE_HWIP, 0) < IP_VERSION(3, 5, 0) || acrtc_state->stream->link->psr_settings.psr_version < - DC_PSR_VERSION_UNSUPPORTED) { + DC_PSR_VERSION_UNSUPPORTED || + !(adev->flags & AMD_IS_APU)) { timing = &acrtc_state->stream->timing; /* at least 2 frames */ 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 069e0195e50a..eea317dcbe8c 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 @@ -44,6 +44,7 @@ #include "dm_helpers.h" #include "ddc_service_types.h" +#include "clk_mgr.h" static u32 edid_extract_panel_id(struct edid *edid) { @@ -1121,6 +1122,8 @@ bool dm_helpers_dp_handle_test_pattern_request( struct pipe_ctx *pipe_ctx = NULL; struct amdgpu_dm_connector *aconnector = link->priv; struct drm_device *dev = aconnector->base.dev; + struct dc_state *dc_state = ctx->dc->current_state; + struct clk_mgr *clk_mgr = ctx->dc->clk_mgr; int i; for (i = 0; i < MAX_PIPES; i++) { @@ -1221,6 +1224,16 @@ bool dm_helpers_dp_handle_test_pattern_request( pipe_ctx->stream->test_pattern.type = test_pattern; pipe_ctx->stream->test_pattern.color_space = test_pattern_color_space; + /* Temp W/A for compliance test failure */ + dc_state->bw_ctx.bw.dcn.clk.p_state_change_support = false; + dc_state->bw_ctx.bw.dcn.clk.dramclk_khz = clk_mgr->dc_mode_softmax_enabled ? + clk_mgr->bw_params->dc_mode_softmax_memclk : clk_mgr->bw_params->max_memclk_mhz; + dc_state->bw_ctx.bw.dcn.clk.idle_dramclk_khz = dc_state->bw_ctx.bw.dcn.clk.dramclk_khz; + ctx->dc->clk_mgr->funcs->update_clocks( + ctx->dc->clk_mgr, + dc_state, + false); + dc_link_dp_set_test_pattern( (struct dc_link *) link, test_pattern, diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c index 11c904ae2958..c4c52173ef22 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_policy.c @@ -303,6 +303,7 @@ void build_unoptimized_policy_settings(enum dml_project_id project, struct dml_m if (project == dml_project_dcn35 || project == dml_project_dcn351) { policy->DCCProgrammingAssumesScanDirectionUnknownFinal = false; + policy->EnhancedPrefetchScheduleAccelerationFinal = 0; policy->AllowForPStateChangeOrStutterInVBlankFinal = dml_prefetch_support_uclk_fclk_and_stutter_if_possible; /*new*/ policy->UseOnlyMaxPrefetchModes = 1; } diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 3cd52e7a9c77..95838c7ab054 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -841,6 +841,8 @@ bool is_psr_su_specific_panel(struct dc_link *link) isPSRSUSupported = false; else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03) isPSRSUSupported = false; + else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x01) + isPSRSUSupported = false; else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1) isPSRSUSupported = true; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 9ad9cf7a9c98..80e60ea2d11e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1234,6 +1234,14 @@ static void smu_init_xgmi_plpd_mode(struct smu_context *smu) } } +static bool smu_is_workload_profile_available(struct smu_context *smu, + u32 profile) +{ + if (profile >= PP_SMC_POWER_PROFILE_COUNT) + return false; + return smu->workload_map && smu->workload_map[profile].valid_mapping; +} + static int smu_sw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1265,7 +1273,8 @@ static int smu_sw_init(void *handle) smu->workload_prority[PP_SMC_POWER_PROFILE_COMPUTE] = 5; smu->workload_prority[PP_SMC_POWER_PROFILE_CUSTOM] = 6; - if (smu->is_apu) + if (smu->is_apu || + !smu_is_workload_profile_available(smu, PP_SMC_POWER_PROFILE_FULLSCREEN3D)) smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT]; else smu->workload_mask = 1 << smu->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D]; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h index ee457a6f0813..c2fd0a4a13e5 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0.h @@ -25,7 +25,7 @@ #define SMU14_DRIVER_IF_V14_0_H //Increment this version if SkuTable_t or BoardTable_t change -#define PPTABLE_VERSION 0x18 +#define PPTABLE_VERSION 0x1B #define NUM_GFXCLK_DPM_LEVELS 16 #define NUM_SOCCLK_DPM_LEVELS 8 @@ -145,7 +145,7 @@ typedef enum { } FEATURE_BTC_e; // Debug Overrides Bitmask -#define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_VCN_FCLK 0x00000001 +#define DEBUG_OVERRIDE_NOT_USE 0x00000001 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_DCN_FCLK 0x00000002 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_MP0_FCLK 0x00000004 #define DEBUG_OVERRIDE_DISABLE_VOLT_LINK_VCN_DCFCLK 0x00000008 @@ -161,6 +161,7 @@ typedef enum { #define DEBUG_OVERRIDE_ENABLE_SOC_VF_BRINGUP_MODE 0x00002000 #define DEBUG_OVERRIDE_ENABLE_PER_WGP_RESIENCY 0x00004000 #define DEBUG_OVERRIDE_DISABLE_MEMORY_VOLTAGE_SCALING 0x00008000 +#define DEBUG_OVERRIDE_DFLL_BTC_FCW_LOG 0x00010000 // VR Mapping Bit Defines #define VR_MAPPING_VR_SELECT_MASK 0x01 @@ -391,6 +392,21 @@ typedef struct { EccInfo_t EccInfo[24]; } EccInfoTable_t; +#define EPCS_HIGH_POWER 600 +#define EPCS_NORMAL_POWER 450 +#define EPCS_LOW_POWER 300 +#define EPCS_SHORTED_POWER 150 +#define EPCS_NO_BOOTUP 0 + +typedef enum{ + EPCS_SHORTED_LIMIT, + EPCS_LOW_POWER_LIMIT, + EPCS_NORMAL_POWER_LIMIT, + EPCS_HIGH_POWER_LIMIT, + EPCS_NOT_CONFIGURED, + EPCS_STATUS_COUNT, +} EPCS_STATUS_e; + //D3HOT sequences typedef enum { BACO_SEQUENCE, @@ -662,7 +678,7 @@ typedef enum { } PP_GRTAVFS_FW_SEP_FUSE_e; #define PP_NUM_RTAVFS_PWL_ZONES 5 - +#define PP_NUM_PSM_DIDT_PWL_ZONES 3 // VBIOS or PPLIB configures telemetry slope and offset. Only slope expected to be set for SVI3 // Slope Q1.7, Offset Q1.2 @@ -746,10 +762,10 @@ typedef struct { uint16_t Padding; //Frequency changes - int16_t GfxclkFmin; // MHz - int16_t GfxclkFmax; // MHz - uint16_t UclkFmin; // MHz - uint16_t UclkFmax; // MHz + int16_t GfxclkFoffset; + uint16_t Padding1; + uint16_t UclkFmin; + uint16_t UclkFmax; uint16_t FclkFmin; uint16_t FclkFmax; @@ -770,19 +786,23 @@ typedef struct { uint8_t MaxOpTemp; uint8_t AdvancedOdModeEnabled; - uint8_t Padding1[3]; + uint8_t Padding2[3]; uint16_t GfxVoltageFullCtrlMode; uint16_t SocVoltageFullCtrlMode; uint16_t GfxclkFullCtrlMode; uint16_t UclkFullCtrlMode; uint16_t FclkFullCtrlMode; - uint16_t Padding2; + uint16_t Padding3; int16_t GfxEdc; int16_t GfxPccLimitControl; - uint32_t Spare[10]; + uint16_t GfxclkFmaxVmax; + uint8_t GfxclkFmaxVmaxTemperature; + uint8_t Padding4[1]; + + uint32_t Spare[9]; uint32_t MmHubPadding[8]; // SMU internal use. Adding here instead of external as a workaround } OverDriveTable_t; @@ -802,8 +822,8 @@ typedef struct { uint16_t VddSocVmax; //gfxclk - int16_t GfxclkFmin; // MHz - int16_t GfxclkFmax; // MHz + int16_t GfxclkFoffset; + uint16_t Padding; //uclk uint16_t UclkFmin; // MHz uint16_t UclkFmax; // MHz @@ -828,7 +848,7 @@ typedef struct { uint8_t FanZeroRpmEnable; //temperature uint8_t MaxOpTemp; - uint8_t Padding[2]; + uint8_t Padding1[2]; //Full Ctrl uint16_t GfxVoltageFullCtrlMode; @@ -839,7 +859,7 @@ typedef struct { //EDC int16_t GfxEdc; int16_t GfxPccLimitControl; - int16_t Padding1; + int16_t Padding2; uint32_t Spare[5]; } OverDriveLimits_t; @@ -987,8 +1007,9 @@ typedef struct { uint16_t BaseClockDc; uint16_t GameClockDc; uint16_t BoostClockDc; - - uint32_t Reserved[4]; + uint16_t MaxReportedClock; + uint16_t Padding; + uint32_t Reserved[3]; } DriverReportedClocks_t; typedef struct { @@ -1132,7 +1153,7 @@ typedef struct { uint32_t DcModeMaxFreq [PPCLK_COUNT ]; // In MHz uint16_t GfxclkAibFmax; - uint16_t GfxclkFreqCap; + uint16_t GfxDpmPadding; //GFX Idle Power Settings uint16_t GfxclkFgfxoffEntry; // Entry in RLC stage (PLL), in Mhz @@ -1172,8 +1193,7 @@ typedef struct { uint32_t DvoFmaxLowScaler; //Unitless float // GFX DCS - uint16_t DcsGfxOffVoltage; //Voltage in mV(Q2) applied to VDDGFX when entering DCS GFXOFF phase - uint16_t PaddingDcs; + uint32_t PaddingDcs; uint16_t DcsMinGfxOffTime; //Minimum amount of time PMFW shuts GFX OFF as part of GFX DCS phase uint16_t DcsMaxGfxOffTime; //Maximum amount of time PMFW can shut GFX OFF as part of GFX DCS phase at a stretch. @@ -1205,8 +1225,7 @@ typedef struct { uint16_t DalDcModeMaxUclkFreq; uint8_t PaddingsMem[2]; //FCLK Section - uint16_t FclkDpmDisallowPstateFreq; //Frequency which FW will target when indicated that display config cannot support P-state. Set to 0 use FW calculated value - uint16_t PaddingFclk; + uint32_t PaddingFclk; // Link DPM Settings uint8_t PcieGenSpeed[NUM_LINK_LEVELS]; ///< 0:PciE-gen1 1:PciE-gen2 2:PciE-gen3 3:PciE-gen4 4:PciE-gen5 @@ -1215,12 +1234,19 @@ typedef struct { // SECTION: VDD_GFX AVFS uint8_t OverrideGfxAvfsFuses; - uint8_t GfxAvfsPadding[3]; + uint8_t GfxAvfsPadding[1]; + uint16_t DroopGBStDev; uint32_t SocHwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT]; //new added for Soc domain uint32_t GfxL2HwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT]; //see fusedoc for encoding //uint32_t GfxSeHwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT]; - uint32_t spare_HwRtAvfsFuses[PP_GRTAVFS_HW_FUSE_COUNT]; + + uint16_t PsmDidt_Vcross[PP_NUM_PSM_DIDT_PWL_ZONES-1]; + uint32_t PsmDidt_StaticDroop_A[PP_NUM_PSM_DIDT_PWL_ZONES]; + uint32_t PsmDidt_StaticDroop_B[PP_NUM_PSM_DIDT_PWL_ZONES]; + uint32_t PsmDidt_DynDroop_A[PP_NUM_PSM_DIDT_PWL_ZONES]; + uint32_t PsmDidt_DynDroop_B[PP_NUM_PSM_DIDT_PWL_ZONES]; + uint32_t spare_HwRtAvfsFuses[19]; uint32_t SocCommonRtAvfs[PP_GRTAVFS_FW_COMMON_FUSE_COUNT]; uint32_t GfxCommonRtAvfs[PP_GRTAVFS_FW_COMMON_FUSE_COUNT]; @@ -1246,11 +1272,7 @@ typedef struct { uint32_t dGbV_dT_vmin; uint32_t dGbV_dT_vmax; - //Unused: PMFW-9370 - uint32_t V2F_vmin_range_low; - uint32_t V2F_vmin_range_high; - uint32_t V2F_vmax_range_low; - uint32_t V2F_vmax_range_high; + uint32_t PaddingV2F[4]; AvfsDcBtcParams_t DcBtcGfxParams; QuadraticInt_t SSCurve_GFX; @@ -1327,18 +1349,18 @@ typedef struct { uint16_t PsmDidtReleaseTimer; uint32_t PsmDidtStallPattern; //Will be written to both pattern 1 and didt_static_level_prog // CAC EDC - uint32_t Leakage_C0; // in IEEE float - uint32_t Leakage_C1; // in IEEE float - uint32_t Leakage_C2; // in IEEE float - uint32_t Leakage_C3; // in IEEE float - uint32_t Leakage_C4; // in IEEE float - uint32_t Leakage_C5; // in IEEE float - uint32_t GFX_CLK_SCALAR; // in IEEE float - uint32_t GFX_CLK_INTERCEPT; // in IEEE float - uint32_t GFX_CAC_M; // in IEEE float - uint32_t GFX_CAC_B; // in IEEE float - uint32_t VDD_GFX_CurrentLimitGuardband; // in IEEE float - uint32_t DynToTotalCacScalar; // in IEEE + uint32_t CacEdcCacLeakageC0; + uint32_t CacEdcCacLeakageC1; + uint32_t CacEdcCacLeakageC2; + uint32_t CacEdcCacLeakageC3; + uint32_t CacEdcCacLeakageC4; + uint32_t CacEdcCacLeakageC5; + uint32_t CacEdcGfxClkScalar; + uint32_t CacEdcGfxClkIntercept; + uint32_t CacEdcCac_m; + uint32_t CacEdcCac_b; + uint32_t CacEdcCurrLimitGuardband; + uint32_t CacEdcDynToTotalCacRatio; // GFX EDC XVMIN uint32_t XVmin_Gfx_EdcThreshScalar; uint32_t XVmin_Gfx_EdcEnableFreq; @@ -1467,7 +1489,7 @@ typedef struct { uint8_t VddqOffEnabled; uint8_t PaddingUmcFlags[2]; - uint32_t PostVoltageSetBacoDelay; // in microseconds. Amount of time FW will wait after power good is established or PSI0 command is issued + uint32_t Paddign1; uint32_t BacoEntryDelay; // in milliseconds. Amount of time FW will wait to trigger BACO entry after receiving entry notification from OS uint8_t FuseWritePowerMuxPresent; @@ -1530,7 +1552,7 @@ typedef struct { int16_t FuzzyFan_ErrorSetDelta; int16_t FuzzyFan_ErrorRateSetDelta; int16_t FuzzyFan_PwmSetDelta; - uint16_t FuzzyFan_Reserved; + uint16_t FanPadding2; uint16_t FwCtfLimit[TEMP_COUNT]; @@ -1547,9 +1569,10 @@ typedef struct { uint16_t FanSpare[1]; uint8_t FanIntakeSensorSupport; uint8_t FanIntakePadding; - uint32_t FanAmbientPerfBoostThreshold; uint32_t FanSpare2[12]; + uint32_t ODFeatureCtrlMask; + uint16_t TemperatureLimit_Hynix; // In degrees Celsius. Memory temperature limit associated with Hynix uint16_t TemperatureLimit_Micron; // In degrees Celsius. Memory temperature limit associated with Micron uint16_t TemperatureFwCtfLimit_Hynix; @@ -1637,7 +1660,7 @@ typedef struct { uint16_t AverageDclk0Frequency ; uint16_t AverageVclk1Frequency ; uint16_t AverageDclk1Frequency ; - uint16_t PCIeBusy ; + uint16_t AveragePCIeBusy ; uint16_t dGPU_W_MAX ; uint16_t padding ; @@ -1665,12 +1688,12 @@ typedef struct { uint16_t AverageGfxActivity ; uint16_t AverageUclkActivity ; - uint16_t Vcn0ActivityPercentage ; + uint16_t AverageVcn0ActivityPercentage; uint16_t Vcn1ActivityPercentage ; uint32_t EnergyAccumulator; uint16_t AverageSocketPower; - uint16_t MovingAverageTotalBoardPower; + uint16_t AverageTotalBoardPower; uint16_t AvgTemperature[TEMP_COUNT]; uint16_t AvgTemperatureFanIntake; @@ -1684,7 +1707,8 @@ typedef struct { uint8_t ThrottlingPercentage[THROTTLER_COUNT]; - uint8_t padding1[3]; + uint8_t VmaxThrottlingPercentage; + uint8_t padding1[2]; //metrics for D3hot entry/exit and driver ARM msgs uint32_t D3HotEntryCountPerMode[D3HOT_SEQUENCE_COUNT]; @@ -1693,7 +1717,7 @@ typedef struct { uint16_t ApuSTAPMSmartShiftLimit; uint16_t ApuSTAPMLimit; - uint16_t MovingAvgApuSocketPower; + uint16_t AvgApuSocketPower; uint16_t AverageUclkActivity_MAX; @@ -1823,6 +1847,17 @@ typedef struct { #define TABLE_TRANSFER_FAILED 0xFF #define TABLE_TRANSFER_PENDING 0xAB +#define TABLE_PPT_FAILED 0x100 +#define TABLE_TDC_FAILED 0x200 +#define TABLE_TEMP_FAILED 0x400 +#define TABLE_FAN_TARGET_TEMP_FAILED 0x800 +#define TABLE_FAN_STOP_TEMP_FAILED 0x1000 +#define TABLE_FAN_START_TEMP_FAILED 0x2000 +#define TABLE_FAN_PWM_MIN_FAILED 0x4000 +#define TABLE_ACOUSTIC_TARGET_RPM_FAILED 0x8000 +#define TABLE_ACOUSTIC_LIMIT_RPM_FAILED 0x10000 +#define TABLE_MGPU_ACOUSTIC_TARGET_RPM_FAILED 0x20000 + // Table types #define TABLE_PPTABLE 0 #define TABLE_COMBO_PPTABLE 1 @@ -1849,5 +1884,6 @@ typedef struct { #define IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING 0x7 #define IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL 0x8 #define IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY 0x9 +#define IH_INTERRUPT_CONTEXT_ID_DYNAMIC_TABLE 0xA #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h index 46b456590a08..727d5b405435 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h @@ -28,7 +28,7 @@ #define SMU14_DRIVER_IF_VERSION_INV 0xFFFFFFFF #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_0 0x7 #define SMU14_DRIVER_IF_VERSION_SMU_V14_0_1 0x6 -#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x26 +#define SMU14_DRIVER_IF_VERSION_SMU_V14_0_2 0x2E #define FEATURE_MASK(feature) (1ULL << feature) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 22737b11b1bf..1fe020f1f4db 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -242,7 +242,9 @@ static int vangogh_tables_init(struct smu_context *smu) goto err0_out; smu_table->metrics_time = 0; - smu_table->gpu_metrics_table_size = max(sizeof(struct gpu_metrics_v2_3), sizeof(struct gpu_metrics_v2_2)); + smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_2); + smu_table->gpu_metrics_table_size = max(smu_table->gpu_metrics_table_size, sizeof(struct gpu_metrics_v2_3)); + smu_table->gpu_metrics_table_size = max(smu_table->gpu_metrics_table_size, sizeof(struct gpu_metrics_v2_4)); smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL); if (!smu_table->gpu_metrics_table) goto err1_out; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index cb923e33fd6f..d53e162dcd8d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2485,7 +2485,7 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, DpmActivityMonitorCoeffInt_t *activity_monitor = &(activity_monitor_external.DpmActivityMonitorCoeffInt); int workload_type, ret = 0; - u32 workload_mask; + u32 workload_mask, selected_workload_mask; smu->power_profile_mode = input[size]; @@ -2552,7 +2552,7 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, if (workload_type < 0) return -EINVAL; - workload_mask = 1 << workload_type; + selected_workload_mask = workload_mask = 1 << workload_type; /* Add optimizations for SMU13.0.0/10. Reuse the power saving profile */ if ((amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 0) && @@ -2572,7 +2572,7 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, workload_mask, NULL); if (!ret) - smu->workload_mask = workload_mask; + smu->workload_mask = selected_workload_mask; return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index 5899d01fa73d..e83ea2bc7f9c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -1077,12 +1077,9 @@ static void smu_v14_0_2_get_od_setting_limits(struct smu_context *smu, switch (od_feature_bit) { case PP_OD_FEATURE_GFXCLK_FMIN: - od_min_setting = overdrive_lowerlimits->GfxclkFmin; - od_max_setting = overdrive_upperlimits->GfxclkFmin; - break; case PP_OD_FEATURE_GFXCLK_FMAX: - od_min_setting = overdrive_lowerlimits->GfxclkFmax; - od_max_setting = overdrive_upperlimits->GfxclkFmax; + od_min_setting = overdrive_lowerlimits->GfxclkFoffset; + od_max_setting = overdrive_upperlimits->GfxclkFoffset; break; case PP_OD_FEATURE_UCLK_FMIN: od_min_setting = overdrive_lowerlimits->UclkFmin; @@ -1269,10 +1266,16 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu, PP_OD_FEATURE_GFXCLK_BIT)) break; - size += sysfs_emit_at(buf, size, "OD_SCLK:\n"); - size += sysfs_emit_at(buf, size, "0: %uMhz\n1: %uMhz\n", - od_table->OverDriveTable.GfxclkFmin, - od_table->OverDriveTable.GfxclkFmax); + PPTable_t *pptable = smu->smu_table.driver_pptable; + const OverDriveLimits_t * const overdrive_upperlimits = + &pptable->SkuTable.OverDriveLimitsBasicMax; + const OverDriveLimits_t * const overdrive_lowerlimits = + &pptable->SkuTable.OverDriveLimitsBasicMin; + + size += sysfs_emit_at(buf, size, "OD_SCLK_OFFSET:\n"); + size += sysfs_emit_at(buf, size, "0: %dMhz\n1: %uMhz\n", + overdrive_lowerlimits->GfxclkFoffset, + overdrive_upperlimits->GfxclkFoffset); break; case SMU_OD_MCLK: @@ -1414,7 +1417,7 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu, PP_OD_FEATURE_GFXCLK_FMAX, NULL, &max_value); - size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n", + size += sysfs_emit_at(buf, size, "SCLK_OFFSET: %7dMhz %10uMhz\n", min_value, max_value); } @@ -1796,7 +1799,7 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu, DpmActivityMonitorCoeffInt_t *activity_monitor = &(activity_monitor_external.DpmActivityMonitorCoeffInt); int workload_type, ret = 0; - + uint32_t current_profile_mode = smu->power_profile_mode; smu->power_profile_mode = input[size]; if (smu->power_profile_mode >= PP_SMC_POWER_PROFILE_COUNT) { @@ -1854,6 +1857,11 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu, } } + if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE) + smu_v14_0_deep_sleep_control(smu, false); + else if (current_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE) + smu_v14_0_deep_sleep_control(smu, true); + /* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */ workload_type = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_WORKLOAD, @@ -2158,7 +2166,7 @@ static ssize_t smu_v14_0_2_get_gpu_metrics(struct smu_context *smu, gpu_metrics->average_gfx_activity = metrics->AverageGfxActivity; gpu_metrics->average_umc_activity = metrics->AverageUclkActivity; - gpu_metrics->average_mm_activity = max(metrics->Vcn0ActivityPercentage, + gpu_metrics->average_mm_activity = max(metrics->AverageVcn0ActivityPercentage, metrics->Vcn1ActivityPercentage); gpu_metrics->average_socket_power = metrics->AverageSocketPower; @@ -2217,8 +2225,7 @@ static void smu_v14_0_2_dump_od_table(struct smu_context *smu, { struct amdgpu_device *adev = smu->adev; - dev_dbg(adev->dev, "OD: Gfxclk: (%d, %d)\n", od_table->OverDriveTable.GfxclkFmin, - od_table->OverDriveTable.GfxclkFmax); + dev_dbg(adev->dev, "OD: Gfxclk offset: (%d)\n", od_table->OverDriveTable.GfxclkFoffset); dev_dbg(adev->dev, "OD: Uclk: (%d, %d)\n", od_table->OverDriveTable.UclkFmin, od_table->OverDriveTable.UclkFmax); } @@ -2309,10 +2316,8 @@ static int smu_v14_0_2_set_default_od_settings(struct smu_context *smu) memcpy(user_od_table, boot_od_table, sizeof(OverDriveTableExternal_t)); - user_od_table->OverDriveTable.GfxclkFmin = - user_od_table_bak.OverDriveTable.GfxclkFmin; - user_od_table->OverDriveTable.GfxclkFmax = - user_od_table_bak.OverDriveTable.GfxclkFmax; + user_od_table->OverDriveTable.GfxclkFoffset = + user_od_table_bak.OverDriveTable.GfxclkFoffset; user_od_table->OverDriveTable.UclkFmin = user_od_table_bak.OverDriveTable.UclkFmin; user_od_table->OverDriveTable.UclkFmax = @@ -2441,22 +2446,6 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu, } switch (input[i]) { - case 0: - smu_v14_0_2_get_od_setting_limits(smu, - PP_OD_FEATURE_GFXCLK_FMIN, - &minimum, - &maximum); - if (input[i + 1] < minimum || - input[i + 1] > maximum) { - dev_info(adev->dev, "GfxclkFmin (%ld) must be within [%u, %u]!\n", - input[i + 1], minimum, maximum); - return -EINVAL; - } - - od_table->OverDriveTable.GfxclkFmin = input[i + 1]; - od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT; - break; - case 1: smu_v14_0_2_get_od_setting_limits(smu, PP_OD_FEATURE_GFXCLK_FMAX, @@ -2469,7 +2458,7 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu, return -EINVAL; } - od_table->OverDriveTable.GfxclkFmax = input[i + 1]; + od_table->OverDriveTable.GfxclkFoffset = input[i + 1]; od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT; break; @@ -2480,13 +2469,6 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu, } } - if (od_table->OverDriveTable.GfxclkFmin > od_table->OverDriveTable.GfxclkFmax) { - dev_err(adev->dev, - "Invalid setting: GfxclkFmin(%u) is bigger than GfxclkFmax(%u)\n", - (uint32_t)od_table->OverDriveTable.GfxclkFmin, - (uint32_t)od_table->OverDriveTable.GfxclkFmax); - return -EINVAL; - } break; case PP_OD_EDIT_MCLK_VDDC_TABLE: diff --git a/drivers/gpu/drm/bridge/aux-bridge.c b/drivers/gpu/drm/bridge/aux-bridge.c index b29980f95379..295e9d031e2d 100644 --- a/drivers/gpu/drm/bridge/aux-bridge.c +++ b/drivers/gpu/drm/bridge/aux-bridge.c @@ -58,9 +58,10 @@ int drm_aux_bridge_register(struct device *parent) adev->id = ret; adev->name = "aux_bridge"; adev->dev.parent = parent; - adev->dev.of_node = of_node_get(parent->of_node); adev->dev.release = drm_aux_bridge_release; + device_set_of_node_from_dev(&adev->dev, parent); + ret = auxiliary_device_init(adev); if (ret) { ida_free(&drm_aux_bridge_ida, adev->id); diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index 290e2532fab1..f3afdab55c11 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -2391,6 +2391,7 @@ static int tc_probe_bridge_endpoint(struct tc_data *tc) if (tc->pre_emphasis[0] < 0 || tc->pre_emphasis[0] > 2 || tc->pre_emphasis[1] < 0 || tc->pre_emphasis[1] > 2) { dev_err(dev, "Incorrect Pre-Emphasis setting, use either 0=0dB 1=3.5dB 2=6dB\n"); + of_node_put(node); return -EINVAL; } } diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index faa253b27664..14ac351fd76d 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -123,9 +123,8 @@ config DRM_I915_USERPTR config DRM_I915_GVT_KVMGT tristate "Enable KVM host support Intel GVT-g graphics virtualization" depends on DRM_I915 - depends on X86 + depends on KVM_X86 depends on 64BIT - depends on KVM depends on VFIO select DRM_I915_GVT select KVM_EXTERNAL_WRITE_TRACKING diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c index 175b00e5a253..eb0e1233ad04 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c @@ -127,9 +127,8 @@ static void mtk_crtc_destroy(struct drm_crtc *crtc) mtk_mutex_put(mtk_crtc->mutex); #if IS_REACHABLE(CONFIG_MTK_CMDQ) - cmdq_pkt_destroy(&mtk_crtc->cmdq_client, &mtk_crtc->cmdq_handle); - if (mtk_crtc->cmdq_client.chan) { + cmdq_pkt_destroy(&mtk_crtc->cmdq_client, &mtk_crtc->cmdq_handle); mbox_free_channel(mtk_crtc->cmdq_client.chan); mtk_crtc->cmdq_client.chan = NULL; } @@ -913,6 +912,7 @@ static int mtk_crtc_init_comp_planes(struct drm_device *drm_dev, BIT(pipe), mtk_crtc_plane_type(mtk_crtc->layer_nr, num_planes), mtk_ddp_comp_supported_rotations(comp), + mtk_ddp_comp_get_blend_modes(comp), mtk_ddp_comp_get_formats(comp), mtk_ddp_comp_get_num_formats(comp), i); if (ret) diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c index be66d94be361..edc6417639e6 100644 --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c @@ -363,6 +363,7 @@ static const struct mtk_ddp_comp_funcs ddp_ovl = { .layer_config = mtk_ovl_layer_config, .bgclr_in_on = mtk_ovl_bgclr_in_on, .bgclr_in_off = mtk_ovl_bgclr_in_off, + .get_blend_modes = mtk_ovl_get_blend_modes, .get_formats = mtk_ovl_get_formats, .get_num_formats = mtk_ovl_get_num_formats, }; @@ -416,6 +417,7 @@ static const struct mtk_ddp_comp_funcs ddp_ovl_adaptor = { .disconnect = mtk_ovl_adaptor_disconnect, .add = mtk_ovl_adaptor_add_comp, .remove = mtk_ovl_adaptor_remove_comp, + .get_blend_modes = mtk_ovl_adaptor_get_blend_modes, .get_formats = mtk_ovl_adaptor_get_formats, .get_num_formats = mtk_ovl_adaptor_get_num_formats, .mode_valid = mtk_ovl_adaptor_mode_valid, diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h index ecf6dc283cd7..39720b27f4e9 100644 --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h @@ -80,6 +80,7 @@ struct mtk_ddp_comp_funcs { void (*ctm_set)(struct device *dev, struct drm_crtc_state *state); struct device * (*dma_dev_get)(struct device *dev); + u32 (*get_blend_modes)(struct device *dev); const u32 *(*get_formats)(struct device *dev); size_t (*get_num_formats)(struct device *dev); void (*connect)(struct device *dev, struct device *mmsys_dev, unsigned int next); @@ -267,6 +268,15 @@ static inline struct device *mtk_ddp_comp_dma_dev_get(struct mtk_ddp_comp *comp) } static inline +u32 mtk_ddp_comp_get_blend_modes(struct mtk_ddp_comp *comp) +{ + if (comp->funcs && comp->funcs->get_blend_modes) + return comp->funcs->get_blend_modes(comp->dev); + + return 0; +} + +static inline const u32 *mtk_ddp_comp_get_formats(struct mtk_ddp_comp *comp) { if (comp->funcs && comp->funcs->get_formats) diff --git a/drivers/gpu/drm/mediatek/mtk_disp_drv.h b/drivers/gpu/drm/mediatek/mtk_disp_drv.h index 082ac18fe04a..04154db9085c 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_drv.h +++ b/drivers/gpu/drm/mediatek/mtk_disp_drv.h @@ -103,6 +103,7 @@ void mtk_ovl_register_vblank_cb(struct device *dev, void mtk_ovl_unregister_vblank_cb(struct device *dev); void mtk_ovl_enable_vblank(struct device *dev); void mtk_ovl_disable_vblank(struct device *dev); +u32 mtk_ovl_get_blend_modes(struct device *dev); const u32 *mtk_ovl_get_formats(struct device *dev); size_t mtk_ovl_get_num_formats(struct device *dev); @@ -131,6 +132,7 @@ void mtk_ovl_adaptor_start(struct device *dev); void mtk_ovl_adaptor_stop(struct device *dev); unsigned int mtk_ovl_adaptor_layer_nr(struct device *dev); struct device *mtk_ovl_adaptor_dma_dev_get(struct device *dev); +u32 mtk_ovl_adaptor_get_blend_modes(struct device *dev); const u32 *mtk_ovl_adaptor_get_formats(struct device *dev); size_t mtk_ovl_adaptor_get_num_formats(struct device *dev); enum drm_mode_status mtk_ovl_adaptor_mode_valid(struct device *dev, diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index 89b439dcf3a6..e0c0bb01f65a 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -65,8 +65,8 @@ #define OVL_CON_CLRFMT_RGB (1 << 12) #define OVL_CON_CLRFMT_ARGB8888 (2 << 12) #define OVL_CON_CLRFMT_RGBA8888 (3 << 12) -#define OVL_CON_CLRFMT_ABGR8888 (OVL_CON_CLRFMT_RGBA8888 | OVL_CON_BYTE_SWAP) -#define OVL_CON_CLRFMT_BGRA8888 (OVL_CON_CLRFMT_ARGB8888 | OVL_CON_BYTE_SWAP) +#define OVL_CON_CLRFMT_ABGR8888 (OVL_CON_CLRFMT_ARGB8888 | OVL_CON_BYTE_SWAP) +#define OVL_CON_CLRFMT_BGRA8888 (OVL_CON_CLRFMT_RGBA8888 | OVL_CON_BYTE_SWAP) #define OVL_CON_CLRFMT_UYVY (4 << 12) #define OVL_CON_CLRFMT_YUYV (5 << 12) #define OVL_CON_MTX_YUV_TO_RGB (6 << 16) @@ -146,6 +146,7 @@ struct mtk_disp_ovl_data { bool fmt_rgb565_is_0; bool smi_id_en; bool supports_afbc; + const u32 blend_modes; const u32 *formats; size_t num_formats; bool supports_clrfmt_ext; @@ -214,6 +215,13 @@ void mtk_ovl_disable_vblank(struct device *dev) writel_relaxed(0x0, ovl->regs + DISP_REG_OVL_INTEN); } +u32 mtk_ovl_get_blend_modes(struct device *dev) +{ + struct mtk_disp_ovl *ovl = dev_get_drvdata(dev); + + return ovl->data->blend_modes; +} + const u32 *mtk_ovl_get_formats(struct device *dev) { struct mtk_disp_ovl *ovl = dev_get_drvdata(dev); @@ -386,14 +394,27 @@ void mtk_ovl_layer_off(struct device *dev, unsigned int idx, DISP_REG_OVL_RDMA_CTRL(idx)); } -static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt, - unsigned int blend_mode) +static unsigned int mtk_ovl_fmt_convert(struct mtk_disp_ovl *ovl, + struct mtk_plane_state *state) { - /* The return value in switch "MEM_MODE_INPUT_FORMAT_XXX" - * is defined in mediatek HW data sheet. - * The alphabet order in XXX is no relation to data - * arrangement in memory. + unsigned int fmt = state->pending.format; + unsigned int blend_mode = DRM_MODE_BLEND_COVERAGE; + + /* + * For the platforms where OVL_CON_CLRFMT_MAN is defined in the hardware data sheet + * and supports premultiplied color formats, such as OVL_CON_CLRFMT_PARGB8888. + * + * Check blend_modes in the driver data to see if premultiplied mode is supported. + * If not, use coverage mode instead to set it to the supported color formats. + * + * Current DRM assumption is that alpha is default premultiplied, so the bitmask of + * blend_modes must include BIT(DRM_MODE_BLEND_PREMULTI). Otherwise, mtk_plane_init() + * will get an error return from drm_plane_create_blend_mode_property() and + * state->base.pixel_blend_mode should not be used. */ + if (ovl->data->blend_modes & BIT(DRM_MODE_BLEND_PREMULTI)) + blend_mode = state->base.pixel_blend_mode; + switch (fmt) { default: case DRM_FORMAT_RGB565: @@ -471,20 +492,26 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, return; } - con = ovl_fmt_convert(ovl, fmt, blend_mode); + con = mtk_ovl_fmt_convert(ovl, state); if (state->base.fb) { - con |= OVL_CON_AEN; con |= state->base.alpha & OVL_CON_ALPHA; - } - /* CONST_BLD must be enabled for XRGB formats although the alpha channel - * can be ignored, or OVL will still read the value from memory. - * For RGB888 related formats, whether CONST_BLD is enabled or not won't - * affect the result. Therefore we use !has_alpha as the condition. - */ - if ((state->base.fb && !state->base.fb->format->has_alpha) || - blend_mode == DRM_MODE_BLEND_PIXEL_NONE) - ignore_pixel_alpha = OVL_CONST_BLEND; + /* + * For blend_modes supported SoCs, always enable alpha blending. + * For blend_modes unsupported SoCs, enable alpha blending when has_alpha is set. + */ + if (blend_mode || state->base.fb->format->has_alpha) + con |= OVL_CON_AEN; + + /* + * Although the alpha channel can be ignored, CONST_BLD must be enabled + * for XRGB format, otherwise OVL will still read the value from memory. + * For RGB888 related formats, whether CONST_BLD is enabled or not won't + * affect the result. Therefore we use !has_alpha as the condition. + */ + if (blend_mode == DRM_MODE_BLEND_PIXEL_NONE || !state->base.fb->format->has_alpha) + ignore_pixel_alpha = OVL_CONST_BLEND; + } if (pending->rotation & DRM_MODE_REFLECT_Y) { con |= OVL_CON_VIRT_FLIP; @@ -663,6 +690,9 @@ static const struct mtk_disp_ovl_data mt8192_ovl_driver_data = { .layer_nr = 4, .fmt_rgb565_is_0 = true, .smi_id_en = true, + .blend_modes = BIT(DRM_MODE_BLEND_PREMULTI) | + BIT(DRM_MODE_BLEND_COVERAGE) | + BIT(DRM_MODE_BLEND_PIXEL_NONE), .formats = mt8173_formats, .num_formats = ARRAY_SIZE(mt8173_formats), }; @@ -673,6 +703,9 @@ static const struct mtk_disp_ovl_data mt8192_ovl_2l_driver_data = { .layer_nr = 2, .fmt_rgb565_is_0 = true, .smi_id_en = true, + .blend_modes = BIT(DRM_MODE_BLEND_PREMULTI) | + BIT(DRM_MODE_BLEND_COVERAGE) | + BIT(DRM_MODE_BLEND_PIXEL_NONE), .formats = mt8173_formats, .num_formats = ARRAY_SIZE(mt8173_formats), }; @@ -684,6 +717,9 @@ static const struct mtk_disp_ovl_data mt8195_ovl_driver_data = { .fmt_rgb565_is_0 = true, .smi_id_en = true, .supports_afbc = true, + .blend_modes = BIT(DRM_MODE_BLEND_PREMULTI) | + BIT(DRM_MODE_BLEND_COVERAGE) | + BIT(DRM_MODE_BLEND_PIXEL_NONE), .formats = mt8195_formats, .num_formats = ARRAY_SIZE(mt8195_formats), .supports_clrfmt_ext = true, diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c index c6768210b08b..bf2546c4681a 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c @@ -400,6 +400,13 @@ void mtk_ovl_adaptor_disable_vblank(struct device *dev) mtk_ethdr_disable_vblank(ovl_adaptor->ovl_adaptor_comp[OVL_ADAPTOR_ETHDR0]); } +u32 mtk_ovl_adaptor_get_blend_modes(struct device *dev) +{ + struct mtk_disp_ovl_adaptor *ovl_adaptor = dev_get_drvdata(dev); + + return mtk_ethdr_get_blend_modes(ovl_adaptor->ovl_adaptor_comp[OVL_ADAPTOR_ETHDR0]); +} + const u32 *mtk_ovl_adaptor_get_formats(struct device *dev) { struct mtk_disp_ovl_adaptor *ovl_adaptor = dev_get_drvdata(dev); diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index d8796a904eca..f2bee617f063 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -145,6 +145,89 @@ struct mtk_dp_data { u16 audio_m_div2_bit; }; +static const struct mtk_dp_efuse_fmt mt8188_dp_efuse_fmt[MTK_DP_CAL_MAX] = { + [MTK_DP_CAL_GLB_BIAS_TRIM] = { + .idx = 0, + .shift = 10, + .mask = 0x1f, + .min_val = 1, + .max_val = 0x1e, + .default_val = 0xf, + }, + [MTK_DP_CAL_CLKTX_IMPSE] = { + .idx = 0, + .shift = 15, + .mask = 0xf, + .min_val = 1, + .max_val = 0xe, + .default_val = 0x8, + }, + [MTK_DP_CAL_LN_TX_IMPSEL_PMOS_0] = { + .idx = 1, + .shift = 0, + .mask = 0xf, + .min_val = 1, + .max_val = 0xe, + .default_val = 0x8, + }, + [MTK_DP_CAL_LN_TX_IMPSEL_PMOS_1] = { + .idx = 1, + .shift = 8, + .mask = 0xf, + .min_val = 1, + .max_val = 0xe, + .default_val = 0x8, + }, + [MTK_DP_CAL_LN_TX_IMPSEL_PMOS_2] = { + .idx = 1, + .shift = 16, + .mask = 0xf, + .min_val = 1, + .max_val = 0xe, + .default_val = 0x8, + }, + [MTK_DP_CAL_LN_TX_IMPSEL_PMOS_3] = { + .idx = 1, + .shift = 24, + .mask = 0xf, + .min_val = 1, + .max_val = 0xe, + .default_val = 0x8, + }, + [MTK_DP_CAL_LN_TX_IMPSEL_NMOS_0] = { + .idx = 1, + .shift = 4, + .mask = 0xf, + .min_val = 1, + .max_val = 0xe, + .default_val = 0x8, + }, + [MTK_DP_CAL_LN_TX_IMPSEL_NMOS_1] = { + .idx = 1, + .shift = 12, + .mask = 0xf, + .min_val = 1, + .max_val = 0xe, + .default_val = 0x8, + }, + [MTK_DP_CAL_LN_TX_IMPSEL_NMOS_2] = { + .idx = 1, + .shift = 20, + .mask = 0xf, + .min_val = 1, + .max_val = 0xe, + .default_val = 0x8, + }, + [MTK_DP_CAL_LN_TX_IMPSEL_NMOS_3] = { + .idx = 1, + .shift = 28, + .mask = 0xf, + .min_val = 1, + .max_val = 0xe, + .default_val = 0x8, + }, +}; + static const struct mtk_dp_efuse_fmt mt8195_edp_efuse_fmt[MTK_DP_CAL_MAX] = { [MTK_DP_CAL_GLB_BIAS_TRIM] = { .idx = 3, @@ -2771,7 +2854,7 @@ static SIMPLE_DEV_PM_OPS(mtk_dp_pm_ops, mtk_dp_suspend, mtk_dp_resume); static const struct mtk_dp_data mt8188_dp_data = { .bridge_type = DRM_MODE_CONNECTOR_DisplayPort, .smc_cmd = MTK_DP_SIP_ATF_VIDEO_UNMUTE, - .efuse_fmt = mt8195_dp_efuse_fmt, + .efuse_fmt = mt8188_dp_efuse_fmt, .audio_supported = true, .audio_pkt_in_hblank_area = true, .audio_m_div2_bit = MT8188_AUDIO_M_CODE_MULT_DIV_SEL_DP_ENC0_P0_DIV_2, diff --git a/drivers/gpu/drm/mediatek/mtk_ethdr.c b/drivers/gpu/drm/mediatek/mtk_ethdr.c index d1d9cf8b10e1..0f22e7d337cb 100644 --- a/drivers/gpu/drm/mediatek/mtk_ethdr.c +++ b/drivers/gpu/drm/mediatek/mtk_ethdr.c @@ -145,6 +145,13 @@ static irqreturn_t mtk_ethdr_irq_handler(int irq, void *dev_id) return IRQ_HANDLED; } +u32 mtk_ethdr_get_blend_modes(struct device *dev) +{ + return BIT(DRM_MODE_BLEND_PREMULTI) | + BIT(DRM_MODE_BLEND_COVERAGE) | + BIT(DRM_MODE_BLEND_PIXEL_NONE); +} + void mtk_ethdr_layer_config(struct device *dev, unsigned int idx, struct mtk_plane_state *state, struct cmdq_pkt *cmdq_pkt) diff --git a/drivers/gpu/drm/mediatek/mtk_ethdr.h b/drivers/gpu/drm/mediatek/mtk_ethdr.h index 81af9edea3f7..a72aeee46829 100644 --- a/drivers/gpu/drm/mediatek/mtk_ethdr.h +++ b/drivers/gpu/drm/mediatek/mtk_ethdr.h @@ -13,6 +13,7 @@ void mtk_ethdr_clk_disable(struct device *dev); void mtk_ethdr_config(struct device *dev, unsigned int w, unsigned int h, unsigned int vrefresh, unsigned int bpc, struct cmdq_pkt *cmdq_pkt); +u32 mtk_ethdr_get_blend_modes(struct device *dev); void mtk_ethdr_layer_config(struct device *dev, unsigned int idx, struct mtk_plane_state *state, struct cmdq_pkt *cmdq_pkt); diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c index 7d2cb4e0fafa..8a48b3b0a956 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_plane.c @@ -320,8 +320,8 @@ static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = { int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane, unsigned long possible_crtcs, enum drm_plane_type type, - unsigned int supported_rotations, const u32 *formats, - size_t num_formats, unsigned int plane_idx) + unsigned int supported_rotations, const u32 blend_modes, + const u32 *formats, size_t num_formats, unsigned int plane_idx) { int err; @@ -366,12 +366,11 @@ int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane, if (err) DRM_ERROR("failed to create property: alpha\n"); - err = drm_plane_create_blend_mode_property(plane, - BIT(DRM_MODE_BLEND_PREMULTI) | - BIT(DRM_MODE_BLEND_COVERAGE) | - BIT(DRM_MODE_BLEND_PIXEL_NONE)); - if (err) - DRM_ERROR("failed to create property: blend_mode\n"); + if (blend_modes) { + err = drm_plane_create_blend_mode_property(plane, blend_modes); + if (err) + DRM_ERROR("failed to create property: blend_mode\n"); + } drm_plane_helper_add(plane, &mtk_plane_helper_funcs); diff --git a/drivers/gpu/drm/mediatek/mtk_plane.h b/drivers/gpu/drm/mediatek/mtk_plane.h index 5b177eac67b7..3b13b89989c7 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.h +++ b/drivers/gpu/drm/mediatek/mtk_plane.h @@ -48,6 +48,6 @@ to_mtk_plane_state(struct drm_plane_state *state) int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane, unsigned long possible_crtcs, enum drm_plane_type type, - unsigned int supported_rotations, const u32 *formats, - size_t num_formats, unsigned int plane_idx); + unsigned int supported_rotations, const u32 blend_modes, + const u32 *formats, size_t num_formats, unsigned int plane_idx); #endif diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c index ef232c0c2049..4e2d3a02ea06 100644 --- a/drivers/gpu/drm/panthor/panthor_fw.c +++ b/drivers/gpu/drm/panthor/panthor_fw.c @@ -487,6 +487,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev, struct panthor_fw_binary_iter *iter, u32 ehdr) { + ssize_t vm_pgsz = panthor_vm_page_size(ptdev->fw->vm); struct panthor_fw_binary_section_entry_hdr hdr; struct panthor_fw_section *section; u32 section_size; @@ -515,8 +516,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev, return -EINVAL; } - if ((hdr.va.start & ~PAGE_MASK) != 0 || - (hdr.va.end & ~PAGE_MASK) != 0) { + if (!IS_ALIGNED(hdr.va.start, vm_pgsz) || !IS_ALIGNED(hdr.va.end, vm_pgsz)) { drm_err(&ptdev->base, "Firmware corrupted, virtual addresses not page aligned: 0x%x-0x%x\n", hdr.va.start, hdr.va.end); return -EINVAL; diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c index 38f560864879..be97d56bc011 100644 --- a/drivers/gpu/drm/panthor/panthor_gem.c +++ b/drivers/gpu/drm/panthor/panthor_gem.c @@ -44,8 +44,7 @@ void panthor_kernel_bo_destroy(struct panthor_kernel_bo *bo) to_panthor_bo(bo->obj)->exclusive_vm_root_gem != panthor_vm_root_gem(vm))) goto out_free_bo; - ret = panthor_vm_unmap_range(vm, bo->va_node.start, - panthor_kernel_bo_size(bo)); + ret = panthor_vm_unmap_range(vm, bo->va_node.start, bo->va_node.size); if (ret) goto out_free_bo; @@ -95,10 +94,16 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm, } bo = to_panthor_bo(&obj->base); - size = obj->base.size; kbo->obj = &obj->base; bo->flags = bo_flags; + /* The system and GPU MMU page size might differ, which becomes a + * problem for FW sections that need to be mapped at explicit address + * since our PAGE_SIZE alignment might cover a VA range that's + * expected to be used for another section. + * Make sure we never map more than we need. + */ + size = ALIGN(size, panthor_vm_page_size(vm)); ret = panthor_vm_alloc_va(vm, gpu_va, size, &kbo->va_node); if (ret) goto err_put_obj; diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c index 3cd2bce59edc..5d5e25b1be95 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -826,6 +826,14 @@ void panthor_vm_idle(struct panthor_vm *vm) mutex_unlock(&ptdev->mmu->as.slots_lock); } +u32 panthor_vm_page_size(struct panthor_vm *vm) +{ + const struct io_pgtable *pgt = io_pgtable_ops_to_pgtable(vm->pgtbl_ops); + u32 pg_shift = ffs(pgt->cfg.pgsize_bitmap) - 1; + + return 1u << pg_shift; +} + static void panthor_vm_stop(struct panthor_vm *vm) { drm_sched_stop(&vm->sched, NULL); @@ -1025,12 +1033,13 @@ int panthor_vm_alloc_va(struct panthor_vm *vm, u64 va, u64 size, struct drm_mm_node *va_node) { + ssize_t vm_pgsz = panthor_vm_page_size(vm); int ret; - if (!size || (size & ~PAGE_MASK)) + if (!size || !IS_ALIGNED(size, vm_pgsz)) return -EINVAL; - if (va != PANTHOR_VM_KERNEL_AUTO_VA && (va & ~PAGE_MASK)) + if (va != PANTHOR_VM_KERNEL_AUTO_VA && !IS_ALIGNED(va, vm_pgsz)) return -EINVAL; mutex_lock(&vm->mm_lock); @@ -2366,11 +2375,12 @@ panthor_vm_bind_prepare_op_ctx(struct drm_file *file, const struct drm_panthor_vm_bind_op *op, struct panthor_vm_op_ctx *op_ctx) { + ssize_t vm_pgsz = panthor_vm_page_size(vm); struct drm_gem_object *gem; int ret; /* Aligned on page size. */ - if ((op->va | op->size) & ~PAGE_MASK) + if (!IS_ALIGNED(op->va | op->size, vm_pgsz)) return -EINVAL; switch (op->flags & DRM_PANTHOR_VM_BIND_OP_TYPE_MASK) { diff --git a/drivers/gpu/drm/panthor/panthor_mmu.h b/drivers/gpu/drm/panthor/panthor_mmu.h index 6788771071e3..8d21e83d8aba 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.h +++ b/drivers/gpu/drm/panthor/panthor_mmu.h @@ -30,6 +30,7 @@ panthor_vm_get_bo_for_va(struct panthor_vm *vm, u64 va, u64 *bo_offset); int panthor_vm_active(struct panthor_vm *vm); void panthor_vm_idle(struct panthor_vm *vm); +u32 panthor_vm_page_size(struct panthor_vm *vm); int panthor_vm_as(struct panthor_vm *vm); int panthor_vm_flush_all(struct panthor_vm *vm); diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c index aee362abb710..9929e22f4d8d 100644 --- a/drivers/gpu/drm/panthor/panthor_sched.c +++ b/drivers/gpu/drm/panthor/panthor_sched.c @@ -589,10 +589,11 @@ struct panthor_group { * @timedout: True when a timeout occurred on any of the queues owned by * this group. * - * Timeouts can be reported by drm_sched or by the FW. In any case, any - * timeout situation is unrecoverable, and the group becomes useless. - * We simply wait for all references to be dropped so we can release the - * group object. + * Timeouts can be reported by drm_sched or by the FW. If a reset is required, + * and the group can't be suspended, this also leads to a timeout. In any case, + * any timeout situation is unrecoverable, and the group becomes useless. We + * simply wait for all references to be dropped so we can release the group + * object. */ bool timedout; @@ -2640,6 +2641,12 @@ void panthor_sched_suspend(struct panthor_device *ptdev) csgs_upd_ctx_init(&upd_ctx); while (slot_mask) { u32 csg_id = ffs(slot_mask) - 1; + struct panthor_csg_slot *csg_slot = &sched->csg_slots[csg_id]; + + /* We consider group suspension failures as fatal and flag the + * group as unusable by setting timedout=true. + */ + csg_slot->group->timedout = true; csgs_upd_ctx_queue_reqs(ptdev, &upd_ctx, csg_id, CSG_STATE_TERMINATE, @@ -3409,6 +3416,11 @@ panthor_job_create(struct panthor_file *pfile, goto err_put_job; } + if (!group_can_run(job->group)) { + ret = -EINVAL; + goto err_put_job; + } + if (job->queue_idx >= job->group->queue_count || !job->group->queues[job->queue_idx]) { ret = -EINVAL; diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index eaef20f41786..e97c6c60bc96 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1276,10 +1276,11 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, sched->own_submit_wq = false; } else { #ifdef CONFIG_LOCKDEP - sched->submit_wq = alloc_ordered_workqueue_lockdep_map(name, 0, + sched->submit_wq = alloc_ordered_workqueue_lockdep_map(name, + WQ_MEM_RECLAIM, &drm_sched_lockdep_map); #else - sched->submit_wq = alloc_ordered_workqueue(name, 0); + sched->submit_wq = alloc_ordered_workqueue(name, WQ_MEM_RECLAIM); #endif if (!sched->submit_wq) return -ENOMEM; diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index c9eb329665ec..34d22ba210b0 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1153,8 +1153,8 @@ static int host1x_drm_probe(struct host1x_device *dev) if (host1x_drm_wants_iommu(dev) && device_iommu_mapped(dma_dev)) { tegra->domain = iommu_paging_domain_alloc(dma_dev); - if (!tegra->domain) { - err = -ENOMEM; + if (IS_ERR(tegra->domain)) { + err = PTR_ERR(tegra->domain); goto free; } diff --git a/drivers/gpu/drm/tests/drm_connector_test.c b/drivers/gpu/drm/tests/drm_connector_test.c index 15e36a8db685..6bba97d0be88 100644 --- a/drivers/gpu/drm/tests/drm_connector_test.c +++ b/drivers/gpu/drm/tests/drm_connector_test.c @@ -996,7 +996,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb(struct kunit *test) unsigned long long rate; struct drm_device *drm = &priv->drm; - mode = drm_display_mode_from_cea_vic(drm, 16); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16); KUNIT_ASSERT_NOT_NULL(test, mode); KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK); @@ -1017,7 +1017,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_10bpc(struct kunit *test) unsigned long long rate; struct drm_device *drm = &priv->drm; - mode = drm_display_mode_from_cea_vic(drm, 16); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16); KUNIT_ASSERT_NOT_NULL(test, mode); KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK); @@ -1038,7 +1038,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_10bpc_vic_1(struct kunit *t unsigned long long rate; struct drm_device *drm = &priv->drm; - mode = drm_display_mode_from_cea_vic(drm, 1); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); rate = drm_hdmi_compute_mode_clock(mode, 10, HDMI_COLORSPACE_RGB); @@ -1056,7 +1056,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_12bpc(struct kunit *test) unsigned long long rate; struct drm_device *drm = &priv->drm; - mode = drm_display_mode_from_cea_vic(drm, 16); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16); KUNIT_ASSERT_NOT_NULL(test, mode); KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK); @@ -1077,7 +1077,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_12bpc_vic_1(struct kunit *t unsigned long long rate; struct drm_device *drm = &priv->drm; - mode = drm_display_mode_from_cea_vic(drm, 1); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); rate = drm_hdmi_compute_mode_clock(mode, 12, HDMI_COLORSPACE_RGB); @@ -1095,7 +1095,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_double(struct kunit *test) unsigned long long rate; struct drm_device *drm = &priv->drm; - mode = drm_display_mode_from_cea_vic(drm, 6); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 6); KUNIT_ASSERT_NOT_NULL(test, mode); KUNIT_ASSERT_TRUE(test, mode->flags & DRM_MODE_FLAG_DBLCLK); @@ -1118,7 +1118,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv420_valid(struct kunit unsigned long long rate; unsigned int vic = *(unsigned int *)test->param_value; - mode = drm_display_mode_from_cea_vic(drm, vic); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, vic); KUNIT_ASSERT_NOT_NULL(test, mode); KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK); @@ -1155,7 +1155,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv420_10_bpc(struct kuni drm_hdmi_compute_mode_clock_yuv420_vic_valid_tests[0]; unsigned long long rate; - mode = drm_display_mode_from_cea_vic(drm, vic); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, vic); KUNIT_ASSERT_NOT_NULL(test, mode); KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK); @@ -1180,7 +1180,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv420_12_bpc(struct kuni drm_hdmi_compute_mode_clock_yuv420_vic_valid_tests[0]; unsigned long long rate; - mode = drm_display_mode_from_cea_vic(drm, vic); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, vic); KUNIT_ASSERT_NOT_NULL(test, mode); KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK); @@ -1203,7 +1203,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv422_8_bpc(struct kunit struct drm_device *drm = &priv->drm; unsigned long long rate; - mode = drm_display_mode_from_cea_vic(drm, 16); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16); KUNIT_ASSERT_NOT_NULL(test, mode); KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK); @@ -1225,7 +1225,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv422_10_bpc(struct kuni struct drm_device *drm = &priv->drm; unsigned long long rate; - mode = drm_display_mode_from_cea_vic(drm, 16); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16); KUNIT_ASSERT_NOT_NULL(test, mode); KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK); @@ -1247,7 +1247,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv422_12_bpc(struct kuni struct drm_device *drm = &priv->drm; unsigned long long rate; - mode = drm_display_mode_from_cea_vic(drm, 16); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16); KUNIT_ASSERT_NOT_NULL(test, mode); KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK); diff --git a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c index 34ee95d41f29..294773342e71 100644 --- a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c +++ b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c @@ -441,7 +441,7 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode_vic_1(struct kunit *test) ctx = drm_kunit_helper_acquire_ctx_alloc(test); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - mode = drm_display_mode_from_cea_vic(drm, 1); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); drm = &priv->drm; @@ -555,7 +555,7 @@ static void drm_test_check_broadcast_rgb_full_cea_mode_vic_1(struct kunit *test) ctx = drm_kunit_helper_acquire_ctx_alloc(test); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - mode = drm_display_mode_from_cea_vic(drm, 1); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); drm = &priv->drm; @@ -671,7 +671,7 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode_vic_1(struct kunit *te ctx = drm_kunit_helper_acquire_ctx_alloc(test); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - mode = drm_display_mode_from_cea_vic(drm, 1); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); drm = &priv->drm; @@ -1263,7 +1263,7 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test) ctx = drm_kunit_helper_acquire_ctx_alloc(test); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - mode = drm_display_mode_from_cea_vic(drm, 1); + mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); /* diff --git a/drivers/gpu/drm/tests/drm_kunit_helpers.c b/drivers/gpu/drm/tests/drm_kunit_helpers.c index aa62719dab0e..04a6b8cc62ac 100644 --- a/drivers/gpu/drm/tests/drm_kunit_helpers.c +++ b/drivers/gpu/drm/tests/drm_kunit_helpers.c @@ -3,6 +3,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_drv.h> +#include <drm/drm_edid.h> #include <drm/drm_fourcc.h> #include <drm/drm_kunit_helpers.h> #include <drm/drm_managed.h> @@ -311,6 +312,47 @@ drm_kunit_helper_create_crtc(struct kunit *test, } EXPORT_SYMBOL_GPL(drm_kunit_helper_create_crtc); +static void kunit_action_drm_mode_destroy(void *ptr) +{ + struct drm_display_mode *mode = ptr; + + drm_mode_destroy(NULL, mode); +} + +/** + * drm_kunit_display_mode_from_cea_vic() - return a mode for CEA VIC + for a KUnit test + * @test: The test context object + * @dev: DRM device + * @video_code: CEA VIC of the mode + * + * Creates a new mode matching the specified CEA VIC for a KUnit test. + * + * Resources will be cleaned up automatically. + * + * Returns: A new drm_display_mode on success or NULL on failure + */ +struct drm_display_mode * +drm_kunit_display_mode_from_cea_vic(struct kunit *test, struct drm_device *dev, + u8 video_code) +{ + struct drm_display_mode *mode; + int ret; + + mode = drm_display_mode_from_cea_vic(dev, video_code); + if (!mode) + return NULL; + + ret = kunit_add_action_or_reset(test, + kunit_action_drm_mode_destroy, + mode); + if (ret) + return NULL; + + return mode; +} +EXPORT_SYMBOL_GPL(drm_kunit_display_mode_from_cea_vic); + MODULE_AUTHOR("Maxime Ripard <[email protected]>"); MODULE_DESCRIPTION("KUnit test suite helper functions"); MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c index 75736faf2a80..c6e0c8d77a70 100644 --- a/drivers/gpu/drm/xe/display/xe_display.c +++ b/drivers/gpu/drm/xe/display/xe_display.c @@ -309,18 +309,7 @@ static void xe_display_flush_cleanup_work(struct xe_device *xe) } /* TODO: System and runtime suspend/resume sequences will be sanitized as a follow-up. */ -void xe_display_pm_runtime_suspend(struct xe_device *xe) -{ - if (!xe->info.probe_display) - return; - - if (xe->d3cold.allowed) - xe_display_pm_suspend(xe, true); - - intel_hpd_poll_enable(xe); -} - -void xe_display_pm_suspend(struct xe_device *xe, bool runtime) +static void __xe_display_pm_suspend(struct xe_device *xe, bool runtime) { struct intel_display *display = &xe->display; bool s2idle = suspend_to_idle(); @@ -353,28 +342,38 @@ void xe_display_pm_suspend(struct xe_device *xe, bool runtime) intel_opregion_suspend(display, s2idle ? PCI_D1 : PCI_D3cold); intel_dmc_suspend(xe); + + if (runtime && has_display(xe)) + intel_hpd_poll_enable(xe); } -void xe_display_pm_suspend_late(struct xe_device *xe) +void xe_display_pm_suspend(struct xe_device *xe) +{ + __xe_display_pm_suspend(xe, false); +} + +void xe_display_pm_runtime_suspend(struct xe_device *xe) { - bool s2idle = suspend_to_idle(); if (!xe->info.probe_display) return; - intel_power_domains_suspend(xe, s2idle); + if (xe->d3cold.allowed) { + __xe_display_pm_suspend(xe, true); + return; + } - intel_display_power_suspend_late(xe); + intel_hpd_poll_enable(xe); } -void xe_display_pm_runtime_resume(struct xe_device *xe) +void xe_display_pm_suspend_late(struct xe_device *xe) { + bool s2idle = suspend_to_idle(); if (!xe->info.probe_display) return; - intel_hpd_poll_disable(xe); + intel_power_domains_suspend(xe, s2idle); - if (xe->d3cold.allowed) - xe_display_pm_resume(xe, true); + intel_display_power_suspend_late(xe); } void xe_display_pm_resume_early(struct xe_device *xe) @@ -387,7 +386,7 @@ void xe_display_pm_resume_early(struct xe_device *xe) intel_power_domains_resume(xe); } -void xe_display_pm_resume(struct xe_device *xe, bool runtime) +static void __xe_display_pm_resume(struct xe_device *xe, bool runtime) { struct intel_display *display = &xe->display; @@ -411,9 +410,11 @@ void xe_display_pm_resume(struct xe_device *xe, bool runtime) intel_display_driver_resume(xe); drm_kms_helper_poll_enable(&xe->drm); intel_display_driver_enable_user_access(xe); - intel_hpd_poll_disable(xe); } + if (has_display(xe)) + intel_hpd_poll_disable(xe); + intel_opregion_resume(display); intel_fbdev_set_suspend(&xe->drm, FBINFO_STATE_RUNNING, false); @@ -421,6 +422,26 @@ void xe_display_pm_resume(struct xe_device *xe, bool runtime) intel_power_domains_enable(xe); } +void xe_display_pm_resume(struct xe_device *xe) +{ + __xe_display_pm_resume(xe, false); +} + +void xe_display_pm_runtime_resume(struct xe_device *xe) +{ + if (!xe->info.probe_display) + return; + + if (xe->d3cold.allowed) { + __xe_display_pm_resume(xe, true); + return; + } + + intel_hpd_init(xe); + intel_hpd_poll_disable(xe); +} + + static void display_device_remove(struct drm_device *dev, void *arg) { struct xe_device *xe = arg; diff --git a/drivers/gpu/drm/xe/display/xe_display.h b/drivers/gpu/drm/xe/display/xe_display.h index 53d727fd792b..bed55fd26f30 100644 --- a/drivers/gpu/drm/xe/display/xe_display.h +++ b/drivers/gpu/drm/xe/display/xe_display.h @@ -34,10 +34,10 @@ void xe_display_irq_enable(struct xe_device *xe, u32 gu_misc_iir); void xe_display_irq_reset(struct xe_device *xe); void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt); -void xe_display_pm_suspend(struct xe_device *xe, bool runtime); +void xe_display_pm_suspend(struct xe_device *xe); void xe_display_pm_suspend_late(struct xe_device *xe); void xe_display_pm_resume_early(struct xe_device *xe); -void xe_display_pm_resume(struct xe_device *xe, bool runtime); +void xe_display_pm_resume(struct xe_device *xe); void xe_display_pm_runtime_suspend(struct xe_device *xe); void xe_display_pm_runtime_resume(struct xe_device *xe); @@ -65,10 +65,10 @@ static inline void xe_display_irq_enable(struct xe_device *xe, u32 gu_misc_iir) static inline void xe_display_irq_reset(struct xe_device *xe) {} static inline void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt) {} -static inline void xe_display_pm_suspend(struct xe_device *xe, bool runtime) {} +static inline void xe_display_pm_suspend(struct xe_device *xe) {} static inline void xe_display_pm_suspend_late(struct xe_device *xe) {} static inline void xe_display_pm_resume_early(struct xe_device *xe) {} -static inline void xe_display_pm_resume(struct xe_device *xe, bool runtime) {} +static inline void xe_display_pm_resume(struct xe_device *xe) {} static inline void xe_display_pm_runtime_suspend(struct xe_device *xe) {} static inline void xe_display_pm_runtime_resume(struct xe_device *xe) {} diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 0a9ffc19e92f..10fd4601b9f2 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -890,7 +890,7 @@ void xe_device_l2_flush(struct xe_device *xe) spin_lock(>->global_invl_lock); xe_mmio_write32(gt, XE2_GLOBAL_INVAL, 0x1); - if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 150, NULL, true)) + if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 500, NULL, true)) xe_gt_err_once(gt, "Global invalidation timeout\n"); spin_unlock(>->global_invl_lock); diff --git a/drivers/gpu/drm/xe/xe_force_wake.c b/drivers/gpu/drm/xe/xe_force_wake.c index b263fff15273..7d9fc489dcb8 100644 --- a/drivers/gpu/drm/xe/xe_force_wake.c +++ b/drivers/gpu/drm/xe/xe_force_wake.c @@ -115,9 +115,15 @@ static int __domain_wait(struct xe_gt *gt, struct xe_force_wake_domain *domain, XE_FORCE_WAKE_ACK_TIMEOUT_MS * USEC_PER_MSEC, &value, true); if (ret) - xe_gt_notice(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n", - domain->id, str_wake_sleep(wake), ERR_PTR(ret), - domain->reg_ack.addr, value); + xe_gt_err(gt, "Force wake domain %d failed to ack %s (%pe) reg[%#x] = %#x\n", + domain->id, str_wake_sleep(wake), ERR_PTR(ret), + domain->reg_ack.addr, value); + if (value == ~0) { + xe_gt_err(gt, + "Force wake domain %d: %s. MMIO unreliable (forcewake register returns 0xFFFFFFFF)!\n", + domain->id, str_wake_sleep(wake)); + ret = -EIO; + } return ret; } diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c index 2895f154654c..ff19eca5d358 100644 --- a/drivers/gpu/drm/xe/xe_ggtt.c +++ b/drivers/gpu/drm/xe/xe_ggtt.c @@ -397,6 +397,16 @@ static void ggtt_invalidate_gt_tlb(struct xe_gt *gt) static void xe_ggtt_invalidate(struct xe_ggtt *ggtt) { + struct xe_device *xe = tile_to_xe(ggtt->tile); + + /* + * XXX: Barrier for GGTT pages. Unsure exactly why this required but + * without this LNL is having issues with the GuC reading scratch page + * vs. correct GGTT page. Not particularly a hot code path so blindly + * do a mmio read here which results in GuC reading correct GGTT page. + */ + xe_mmio_read32(xe_root_mmio_gt(xe), VF_CAP_REG); + /* Each GT in a tile has its own TLB to cache GGTT lookups */ ggtt_invalidate_gt_tlb(ggtt->tile->primary_gt); ggtt_invalidate_gt_tlb(ggtt->tile->media_gt); diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index d16eb9ab49fb..17986bfd8818 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -898,6 +898,24 @@ retry_same_fence: ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ); /* + * Occasionally it is seen that the G2H worker starts running after a delay of more than + * a second even after being queued and activated by the Linux workqueue subsystem. This + * leads to G2H timeout error. The root cause of issue lies with scheduling latency of + * Lunarlake Hybrid CPU. Issue dissappears if we disable Lunarlake atom cores from BIOS + * and this is beyond xe kmd. + * + * TODO: Drop this change once workqueue scheduling delay issue is fixed on LNL Hybrid CPU. + */ + if (!ret) { + flush_work(&ct->g2h_worker); + if (g2h_fence.done) { + xe_gt_warn(gt, "G2H fence %u, action %04x, done\n", + g2h_fence.seqno, action[0]); + ret = 1; + } + } + + /* * Ensure we serialize with completion side to prevent UAF with fence going out of scope on * the stack, since we have no clue if it will fire after the timeout before we can erase * from the xa. Also we have some dependent loads and stores below for which we need the diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 8a9254e5af6e..f903b0772722 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -916,12 +916,22 @@ static void xe_guc_exec_queue_lr_cleanup(struct work_struct *w) static bool check_timeout(struct xe_exec_queue *q, struct xe_sched_job *job) { struct xe_gt *gt = guc_to_gt(exec_queue_to_guc(q)); - u32 ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]); - u32 ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]); + u32 ctx_timestamp, ctx_job_timestamp; u32 timeout_ms = q->sched_props.job_timeout_ms; u32 diff; u64 running_time_ms; + if (!xe_sched_job_started(job)) { + xe_gt_warn(gt, "Check job timeout: seqno=%u, lrc_seqno=%u, guc_id=%d, not started", + xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job), + q->guc->id); + + return xe_sched_invalidate_job(job, 2); + } + + ctx_timestamp = xe_lrc_ctx_timestamp(q->lrc[0]); + ctx_job_timestamp = xe_lrc_ctx_job_timestamp(q->lrc[0]); + /* * Counter wraps at ~223s at the usual 19.2MHz, be paranoid catch * possible overflows with a high timeout. @@ -1049,10 +1059,6 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job) exec_queue_killed_or_banned_or_wedged(q) || exec_queue_destroyed(q); - /* Job hasn't started, can't be timed out */ - if (!skip_timeout_check && !xe_sched_job_started(job)) - goto rearm; - /* * XXX: Sampling timeout doesn't work in wedged mode as we have to * modify scheduling state to read timestamp. We could read the @@ -1726,8 +1732,13 @@ void xe_guc_submit_stop(struct xe_guc *guc) mutex_lock(&guc->submission_state.lock); - xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) + xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) { + /* Prevent redundant attempts to stop parallel queues */ + if (q->guc->id != index) + continue; + guc_exec_queue_stop(guc, q); + } mutex_unlock(&guc->submission_state.lock); @@ -1765,8 +1776,13 @@ int xe_guc_submit_start(struct xe_guc *guc) mutex_lock(&guc->submission_state.lock); atomic_dec(&guc->submission_state.stopped); - xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) + xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) { + /* Prevent redundant attempts to start parallel queues */ + if (q->guc->id != index) + continue; + guc_exec_queue_start(q); + } mutex_unlock(&guc->submission_state.lock); wake_up_all(&guc->ct.wq); diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index 7cf2160fe040..33eb039053e4 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -123,7 +123,7 @@ int xe_pm_suspend(struct xe_device *xe) for_each_gt(gt, xe, id) xe_gt_suspend_prepare(gt); - xe_display_pm_suspend(xe, false); + xe_display_pm_suspend(xe); /* FIXME: Super racey... */ err = xe_bo_evict_all(xe); @@ -133,7 +133,7 @@ int xe_pm_suspend(struct xe_device *xe) for_each_gt(gt, xe, id) { err = xe_gt_suspend(gt); if (err) { - xe_display_pm_resume(xe, false); + xe_display_pm_resume(xe); goto err; } } @@ -187,7 +187,7 @@ int xe_pm_resume(struct xe_device *xe) for_each_gt(gt, xe, id) xe_gt_resume(gt); - xe_display_pm_resume(xe, false); + xe_display_pm_resume(xe); err = xe_bo_restore_user(xe); if (err) diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c index c6cf227ead40..2e72c06fd40d 100644 --- a/drivers/gpu/drm/xe/xe_sync.c +++ b/drivers/gpu/drm/xe/xe_sync.c @@ -54,8 +54,9 @@ static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr, { struct xe_user_fence *ufence; u64 __user *ptr = u64_to_user_ptr(addr); + u64 __maybe_unused prefetch_val; - if (!access_ok(ptr, sizeof(*ptr))) + if (get_user(prefetch_val, ptr)) return ERR_PTR(-EFAULT); ufence = kzalloc(sizeof(*ufence), GFP_KERNEL); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 612ee6ddfc8d..582fd234eec7 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1875,7 +1875,7 @@ u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags) u32 len = hid_report_len(report) + 7; - return kmalloc(len, flags); + return kzalloc(len, flags); } EXPORT_SYMBOL_GPL(hid_alloc_report_buf); diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c index a5d91933f505..b79c48d46ccc 100644 --- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -637,7 +637,7 @@ static int ad7124_write_raw(struct iio_dev *indio_dev, switch (info) { case IIO_CHAN_INFO_SAMP_FREQ: - if (val2 != 0) { + if (val2 != 0 || val == 0) { ret = -EINVAL; break; } diff --git a/drivers/iio/adc/ad7380.c b/drivers/iio/adc/ad7380.c index e8bddfb0d07d..fb728570debe 100644 --- a/drivers/iio/adc/ad7380.c +++ b/drivers/iio/adc/ad7380.c @@ -75,6 +75,7 @@ #define T_CONVERT_NS 190 /* conversion time */ #define T_CONVERT_0_NS 10 /* 1st conversion start time (oversampling) */ #define T_CONVERT_X_NS 500 /* xth conversion start time (oversampling) */ +#define T_POWERUP_US 5000 /* Power up */ struct ad7380_timing_specs { const unsigned int t_csh_ns; /* CS minimum high time */ @@ -86,6 +87,9 @@ struct ad7380_chip_info { unsigned int num_channels; unsigned int num_simult_channels; bool has_mux; + const char * const *supplies; + unsigned int num_supplies; + bool external_ref_only; const char * const *vcm_supplies; unsigned int num_vcm_supplies; const unsigned long *available_scan_masks; @@ -243,6 +247,10 @@ DEFINE_AD7380_8_CHANNEL(ad7386_4_channels, 16, 0, u); DEFINE_AD7380_8_CHANNEL(ad7387_4_channels, 14, 0, u); DEFINE_AD7380_8_CHANNEL(ad7388_4_channels, 12, 0, u); +static const char * const ad7380_supplies[] = { + "vcc", "vlogic", +}; + static const char * const ad7380_2_channel_vcm_supplies[] = { "aina", "ainb", }; @@ -338,6 +346,8 @@ static const struct ad7380_chip_info ad7380_chip_info = { .channels = ad7380_channels, .num_channels = ARRAY_SIZE(ad7380_channels), .num_simult_channels = 2, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .available_scan_masks = ad7380_2_channel_scan_masks, .timing_specs = &ad7380_timing, }; @@ -347,6 +357,8 @@ static const struct ad7380_chip_info ad7381_chip_info = { .channels = ad7381_channels, .num_channels = ARRAY_SIZE(ad7381_channels), .num_simult_channels = 2, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .available_scan_masks = ad7380_2_channel_scan_masks, .timing_specs = &ad7380_timing, }; @@ -356,6 +368,8 @@ static const struct ad7380_chip_info ad7383_chip_info = { .channels = ad7383_channels, .num_channels = ARRAY_SIZE(ad7383_channels), .num_simult_channels = 2, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .vcm_supplies = ad7380_2_channel_vcm_supplies, .num_vcm_supplies = ARRAY_SIZE(ad7380_2_channel_vcm_supplies), .available_scan_masks = ad7380_2_channel_scan_masks, @@ -367,6 +381,8 @@ static const struct ad7380_chip_info ad7384_chip_info = { .channels = ad7384_channels, .num_channels = ARRAY_SIZE(ad7384_channels), .num_simult_channels = 2, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .vcm_supplies = ad7380_2_channel_vcm_supplies, .num_vcm_supplies = ARRAY_SIZE(ad7380_2_channel_vcm_supplies), .available_scan_masks = ad7380_2_channel_scan_masks, @@ -378,6 +394,8 @@ static const struct ad7380_chip_info ad7386_chip_info = { .channels = ad7386_channels, .num_channels = ARRAY_SIZE(ad7386_channels), .num_simult_channels = 2, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .has_mux = true, .available_scan_masks = ad7380_2x2_channel_scan_masks, .timing_specs = &ad7380_timing, @@ -388,6 +406,8 @@ static const struct ad7380_chip_info ad7387_chip_info = { .channels = ad7387_channels, .num_channels = ARRAY_SIZE(ad7387_channels), .num_simult_channels = 2, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .has_mux = true, .available_scan_masks = ad7380_2x2_channel_scan_masks, .timing_specs = &ad7380_timing, @@ -398,6 +418,8 @@ static const struct ad7380_chip_info ad7388_chip_info = { .channels = ad7388_channels, .num_channels = ARRAY_SIZE(ad7388_channels), .num_simult_channels = 2, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .has_mux = true, .available_scan_masks = ad7380_2x2_channel_scan_masks, .timing_specs = &ad7380_timing, @@ -408,6 +430,9 @@ static const struct ad7380_chip_info ad7380_4_chip_info = { .channels = ad7380_4_channels, .num_channels = ARRAY_SIZE(ad7380_4_channels), .num_simult_channels = 4, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), + .external_ref_only = true, .available_scan_masks = ad7380_4_channel_scan_masks, .timing_specs = &ad7380_4_timing, }; @@ -417,6 +442,8 @@ static const struct ad7380_chip_info ad7381_4_chip_info = { .channels = ad7381_4_channels, .num_channels = ARRAY_SIZE(ad7381_4_channels), .num_simult_channels = 4, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .available_scan_masks = ad7380_4_channel_scan_masks, .timing_specs = &ad7380_4_timing, }; @@ -426,6 +453,8 @@ static const struct ad7380_chip_info ad7383_4_chip_info = { .channels = ad7383_4_channels, .num_channels = ARRAY_SIZE(ad7383_4_channels), .num_simult_channels = 4, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .vcm_supplies = ad7380_4_channel_vcm_supplies, .num_vcm_supplies = ARRAY_SIZE(ad7380_4_channel_vcm_supplies), .available_scan_masks = ad7380_4_channel_scan_masks, @@ -437,6 +466,8 @@ static const struct ad7380_chip_info ad7384_4_chip_info = { .channels = ad7384_4_channels, .num_channels = ARRAY_SIZE(ad7384_4_channels), .num_simult_channels = 4, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .vcm_supplies = ad7380_4_channel_vcm_supplies, .num_vcm_supplies = ARRAY_SIZE(ad7380_4_channel_vcm_supplies), .available_scan_masks = ad7380_4_channel_scan_masks, @@ -448,6 +479,8 @@ static const struct ad7380_chip_info ad7386_4_chip_info = { .channels = ad7386_4_channels, .num_channels = ARRAY_SIZE(ad7386_4_channels), .num_simult_channels = 4, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .has_mux = true, .available_scan_masks = ad7380_2x4_channel_scan_masks, .timing_specs = &ad7380_4_timing, @@ -458,6 +491,8 @@ static const struct ad7380_chip_info ad7387_4_chip_info = { .channels = ad7387_4_channels, .num_channels = ARRAY_SIZE(ad7387_4_channels), .num_simult_channels = 4, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .has_mux = true, .available_scan_masks = ad7380_2x4_channel_scan_masks, .timing_specs = &ad7380_4_timing, @@ -468,6 +503,8 @@ static const struct ad7380_chip_info ad7388_4_chip_info = { .channels = ad7388_4_channels, .num_channels = ARRAY_SIZE(ad7388_4_channels), .num_simult_channels = 4, + .supplies = ad7380_supplies, + .num_supplies = ARRAY_SIZE(ad7380_supplies), .has_mux = true, .available_scan_masks = ad7380_2x4_channel_scan_masks, .timing_specs = &ad7380_4_timing, @@ -956,7 +993,7 @@ static const struct iio_info ad7380_info = { .debugfs_reg_access = &ad7380_debugfs_reg_access, }; -static int ad7380_init(struct ad7380_state *st, struct regulator *vref) +static int ad7380_init(struct ad7380_state *st, bool external_ref_en) { int ret; @@ -968,13 +1005,13 @@ static int ad7380_init(struct ad7380_state *st, struct regulator *vref) if (ret < 0) return ret; - /* select internal or external reference voltage */ - ret = regmap_update_bits(st->regmap, AD7380_REG_ADDR_CONFIG1, - AD7380_CONFIG1_REFSEL, - FIELD_PREP(AD7380_CONFIG1_REFSEL, - vref ? 1 : 0)); - if (ret < 0) - return ret; + if (external_ref_en) { + /* select external reference voltage */ + ret = regmap_set_bits(st->regmap, AD7380_REG_ADDR_CONFIG1, + AD7380_CONFIG1_REFSEL); + if (ret < 0) + return ret; + } /* This is the default value after reset. */ st->oversampling_ratio = 1; @@ -987,16 +1024,11 @@ static int ad7380_init(struct ad7380_state *st, struct regulator *vref) FIELD_PREP(AD7380_CONFIG2_SDO, 1)); } -static void ad7380_regulator_disable(void *p) -{ - regulator_disable(p); -} - static int ad7380_probe(struct spi_device *spi) { struct iio_dev *indio_dev; struct ad7380_state *st; - struct regulator *vref; + bool external_ref_en; int ret, i; indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*st)); @@ -1009,36 +1041,38 @@ static int ad7380_probe(struct spi_device *spi) if (!st->chip_info) return dev_err_probe(&spi->dev, -EINVAL, "missing match data\n"); - vref = devm_regulator_get_optional(&spi->dev, "refio"); - if (IS_ERR(vref)) { - if (PTR_ERR(vref) != -ENODEV) - return dev_err_probe(&spi->dev, PTR_ERR(vref), - "Failed to get refio regulator\n"); - - vref = NULL; - } + ret = devm_regulator_bulk_get_enable(&spi->dev, st->chip_info->num_supplies, + st->chip_info->supplies); - /* - * If there is no REFIO supply, then it means that we are using - * the internal 2.5V reference, otherwise REFIO is reference voltage. - */ - if (vref) { - ret = regulator_enable(vref); - if (ret) - return ret; - - ret = devm_add_action_or_reset(&spi->dev, - ad7380_regulator_disable, vref); - if (ret) - return ret; + if (ret) + return dev_err_probe(&spi->dev, ret, + "Failed to enable power supplies\n"); + fsleep(T_POWERUP_US); - ret = regulator_get_voltage(vref); + if (st->chip_info->external_ref_only) { + ret = devm_regulator_get_enable_read_voltage(&spi->dev, + "refin"); if (ret < 0) - return ret; + return dev_err_probe(&spi->dev, ret, + "Failed to get refin regulator\n"); st->vref_mv = ret / 1000; + + /* these chips don't have a register bit for this */ + external_ref_en = false; } else { - st->vref_mv = AD7380_INTERNAL_REF_MV; + /* + * If there is no REFIO supply, then it means that we are using + * the internal reference, otherwise REFIO is reference voltage. + */ + ret = devm_regulator_get_enable_read_voltage(&spi->dev, + "refio"); + if (ret < 0 && ret != -ENODEV) + return dev_err_probe(&spi->dev, ret, + "Failed to get refio regulator\n"); + + external_ref_en = ret != -ENODEV; + st->vref_mv = external_ref_en ? ret / 1000 : AD7380_INTERNAL_REF_MV; } if (st->chip_info->num_vcm_supplies > ARRAY_SIZE(st->vcm_mv)) @@ -1050,27 +1084,13 @@ static int ad7380_probe(struct spi_device *spi) * input pin. */ for (i = 0; i < st->chip_info->num_vcm_supplies; i++) { - struct regulator *vcm; - - vcm = devm_regulator_get(&spi->dev, - st->chip_info->vcm_supplies[i]); - if (IS_ERR(vcm)) - return dev_err_probe(&spi->dev, PTR_ERR(vcm), - "Failed to get %s regulator\n", - st->chip_info->vcm_supplies[i]); + const char *vcm = st->chip_info->vcm_supplies[i]; - ret = regulator_enable(vcm); - if (ret) - return ret; - - ret = devm_add_action_or_reset(&spi->dev, - ad7380_regulator_disable, vcm); - if (ret) - return ret; - - ret = regulator_get_voltage(vcm); + ret = devm_regulator_get_enable_read_voltage(&spi->dev, vcm); if (ret < 0) - return ret; + return dev_err_probe(&spi->dev, ret, + "Failed to get %s regulator\n", + vcm); st->vcm_mv[i] = ret / 1000; } @@ -1135,7 +1155,7 @@ static int ad7380_probe(struct spi_device *spi) if (ret) return ret; - ret = ad7380_init(st, vref); + ret = ad7380_init(st, external_ref_en); if (ret) return ret; diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig index 45e337c6d256..9f5d5ebb8653 100644 --- a/drivers/iio/dac/Kconfig +++ b/drivers/iio/dac/Kconfig @@ -380,7 +380,7 @@ config LTC2632 config LTC2664 tristate "Analog Devices LTC2664 and LTC2672 DAC SPI driver" depends on SPI - select REGMAP + select REGMAP_SPI help Say yes here to build support for Analog Devices LTC2664 and LTC2672 converters (DAC). diff --git a/drivers/iio/industrialio-gts-helper.c b/drivers/iio/industrialio-gts-helper.c index 59d7615c0f56..5f131bc1a01e 100644 --- a/drivers/iio/industrialio-gts-helper.c +++ b/drivers/iio/industrialio-gts-helper.c @@ -307,13 +307,15 @@ static int iio_gts_build_avail_scale_table(struct iio_gts *gts) if (ret) goto err_free_out; + for (i = 0; i < gts->num_itime; i++) + kfree(per_time_gains[i]); kfree(per_time_gains); gts->per_time_avail_scale_tables = per_time_scales; return 0; err_free_out: - for (i--; i; i--) { + for (i--; i >= 0; i--) { kfree(per_time_scales[i]); kfree(per_time_gains[i]); } diff --git a/drivers/iio/light/veml6030.c b/drivers/iio/light/veml6030.c index 9630de1c578e..621428885455 100644 --- a/drivers/iio/light/veml6030.c +++ b/drivers/iio/light/veml6030.c @@ -522,7 +522,7 @@ static int veml6030_read_raw(struct iio_dev *indio_dev, } if (mask == IIO_CHAN_INFO_PROCESSED) { *val = (reg * data->cur_resolution) / 10000; - *val2 = (reg * data->cur_resolution) % 10000; + *val2 = (reg * data->cur_resolution) % 10000 * 100; return IIO_VAL_INT_PLUS_MICRO; } *val = reg; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 2ebcb2de962b..7ad83566ab0f 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -1532,9 +1532,11 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, u32 tbl_indx; int rc; + spin_lock_bh(&rcfw->tbl_lock); tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw); rcfw->qp_tbl[tbl_indx].qp_id = BNXT_QPLIB_QP_ID_INVALID; rcfw->qp_tbl[tbl_indx].qp_handle = NULL; + spin_unlock_bh(&rcfw->tbl_lock); bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, CMDQ_BASE_OPCODE_DESTROY_QP, @@ -1545,8 +1547,10 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, sizeof(resp), 0); rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) { + spin_lock_bh(&rcfw->tbl_lock); rcfw->qp_tbl[tbl_indx].qp_id = qp->id; rcfw->qp_tbl[tbl_indx].qp_handle = qp; + spin_unlock_bh(&rcfw->tbl_lock); return rc; } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 7294221b3316..e82bd37158ad 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -290,7 +290,6 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_hwq *hwq; u32 sw_prod, cmdq_prod; struct pci_dev *pdev; - unsigned long flags; u16 cookie; u8 *preq; @@ -301,7 +300,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, /* Cmdq are in 16-byte units, each request can consume 1 or more * cmdqe */ - spin_lock_irqsave(&hwq->lock, flags); + spin_lock_bh(&hwq->lock); required_slots = bnxt_qplib_get_cmd_slots(msg->req); free_slots = HWQ_FREE_SLOTS(hwq); cookie = cmdq->seq_num & RCFW_MAX_COOKIE_VALUE; @@ -311,7 +310,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, dev_info_ratelimited(&pdev->dev, "CMDQ is full req/free %d/%d!", required_slots, free_slots); - spin_unlock_irqrestore(&hwq->lock, flags); + spin_unlock_bh(&hwq->lock); return -EAGAIN; } if (msg->block) @@ -367,7 +366,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, wmb(); writel(cmdq_prod, cmdq->cmdq_mbox.prod); writel(RCFW_CMDQ_TRIG_VAL, cmdq->cmdq_mbox.db); - spin_unlock_irqrestore(&hwq->lock, flags); + spin_unlock_bh(&hwq->lock); /* Return the CREQ response pointer */ return 0; } @@ -486,7 +485,6 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, { struct creq_qp_event *evnt = (struct creq_qp_event *)msg->resp; struct bnxt_qplib_crsqe *crsqe; - unsigned long flags; u16 cookie; int rc; u8 opcode; @@ -512,12 +510,12 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, rc = __poll_for_resp(rcfw, cookie); if (rc) { - spin_lock_irqsave(&rcfw->cmdq.hwq.lock, flags); + spin_lock_bh(&rcfw->cmdq.hwq.lock); crsqe = &rcfw->crsqe_tbl[cookie]; crsqe->is_waiter_alive = false; if (rc == -ENODEV) set_bit(FIRMWARE_STALL_DETECTED, &rcfw->cmdq.flags); - spin_unlock_irqrestore(&rcfw->cmdq.hwq.lock, flags); + spin_unlock_bh(&rcfw->cmdq.hwq.lock); return -ETIMEDOUT; } @@ -628,7 +626,6 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, u16 cookie, blocked = 0; bool is_waiter_alive; struct pci_dev *pdev; - unsigned long flags; u32 wait_cmds = 0; int rc = 0; @@ -637,17 +634,21 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, case CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION: err_event = (struct creq_qp_error_notification *)qp_event; qp_id = le32_to_cpu(err_event->xid); + spin_lock(&rcfw->tbl_lock); tbl_indx = map_qp_id_to_tbl_indx(qp_id, rcfw); qp = rcfw->qp_tbl[tbl_indx].qp_handle; + if (!qp) { + spin_unlock(&rcfw->tbl_lock); + break; + } + bnxt_qplib_mark_qp_error(qp); + rc = rcfw->creq.aeq_handler(rcfw, qp_event, qp); + spin_unlock(&rcfw->tbl_lock); dev_dbg(&pdev->dev, "Received QP error notification\n"); dev_dbg(&pdev->dev, "qpid 0x%x, req_err=0x%x, resp_err=0x%x\n", qp_id, err_event->req_err_state_reason, err_event->res_err_state_reason); - if (!qp) - break; - bnxt_qplib_mark_qp_error(qp); - rc = rcfw->creq.aeq_handler(rcfw, qp_event, qp); break; default: /* @@ -659,8 +660,7 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, * */ - spin_lock_irqsave_nested(&hwq->lock, flags, - SINGLE_DEPTH_NESTING); + spin_lock_nested(&hwq->lock, SINGLE_DEPTH_NESTING); cookie = le16_to_cpu(qp_event->cookie); blocked = cookie & RCFW_CMD_IS_BLOCKING; cookie &= RCFW_MAX_COOKIE_VALUE; @@ -672,7 +672,7 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, dev_info(&pdev->dev, "rcfw timedout: cookie = %#x, free_slots = %d", cookie, crsqe->free_slots); - spin_unlock_irqrestore(&hwq->lock, flags); + spin_unlock(&hwq->lock); return rc; } @@ -720,7 +720,7 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, __destroy_timedout_ah(rcfw, (struct creq_create_ah_resp *) qp_event); - spin_unlock_irqrestore(&hwq->lock, flags); + spin_unlock(&hwq->lock); } *num_wait += wait_cmds; return rc; @@ -734,12 +734,11 @@ static void bnxt_qplib_service_creq(struct tasklet_struct *t) u32 type, budget = CREQ_ENTRY_POLL_BUDGET; struct bnxt_qplib_hwq *hwq = &creq->hwq; struct creq_base *creqe; - unsigned long flags; u32 num_wakeup = 0; u32 hw_polled = 0; /* Service the CREQ until budget is over */ - spin_lock_irqsave(&hwq->lock, flags); + spin_lock_bh(&hwq->lock); while (budget > 0) { creqe = bnxt_qplib_get_qe(hwq, hwq->cons, NULL); if (!CREQ_CMP_VALID(creqe, creq->creq_db.dbinfo.flags)) @@ -782,7 +781,7 @@ static void bnxt_qplib_service_creq(struct tasklet_struct *t) if (hw_polled) bnxt_qplib_ring_nq_db(&creq->creq_db.dbinfo, rcfw->res->cctx, true); - spin_unlock_irqrestore(&hwq->lock, flags); + spin_unlock_bh(&hwq->lock); if (num_wakeup) wake_up_nr(&rcfw->cmdq.waitq, num_wakeup); } @@ -978,6 +977,7 @@ int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res, GFP_KERNEL); if (!rcfw->qp_tbl) goto fail; + spin_lock_init(&rcfw->tbl_lock); rcfw->max_timeout = res->cctx->hwrm_cmd_max_timeout; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index 45996e60a0d0..07779aeb7575 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -224,6 +224,8 @@ struct bnxt_qplib_rcfw { struct bnxt_qplib_crsqe *crsqe_tbl; int qp_tbl_size; struct bnxt_qplib_qp_node *qp_tbl; + /* To synchronize the qp-handle hash table */ + spinlock_t tbl_lock; u64 oos_prev; u32 init_oos_stats; u32 cmdq_depth; diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index 10a4c738b59f..e059f92d90fd 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -473,6 +473,7 @@ static const struct ib_device_ops c4iw_dev_ops = { .fill_res_cq_entry = c4iw_fill_res_cq_entry, .fill_res_cm_id_entry = c4iw_fill_res_cm_id_entry, .fill_res_mr_entry = c4iw_fill_res_mr_entry, + .fill_res_qp_entry = c4iw_fill_res_qp_entry, .get_dev_fw_str = get_dev_fw_str, .get_dma_mr = c4iw_get_dma_mr, .get_hw_stats = c4iw_get_mib, diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index e39b1a101e97..10ce3b44f645 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -4268,14 +4268,14 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp, MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt); if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC && attr->max_rd_atomic) - MLX5_SET(qpc, qpc, log_sra_max, ilog2(attr->max_rd_atomic)); + MLX5_SET(qpc, qpc, log_sra_max, fls(attr->max_rd_atomic - 1)); if (attr_mask & IB_QP_SQ_PSN) MLX5_SET(qpc, qpc, next_send_psn, attr->sq_psn); if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC && attr->max_dest_rd_atomic) MLX5_SET(qpc, qpc, log_rra_max, - ilog2(attr->max_dest_rd_atomic)); + fls(attr->max_dest_rd_atomic - 1)); if (attr_mask & (IB_QP_ACCESS_FLAGS | IB_QP_MAX_DEST_RD_ATOMIC)) { err = set_qpc_atomic_flags(qp, attr, attr_mask, qpc); diff --git a/drivers/input/input.c b/drivers/input/input.c index 47fac29cf7c3..c51858f1cdc5 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -119,12 +119,12 @@ static void input_pass_values(struct input_dev *dev, handle = rcu_dereference(dev->grab); if (handle) { - count = handle->handler->events(handle, vals, count); + count = handle->handle_events(handle, vals, count); } else { list_for_each_entry_rcu(handle, &dev->h_list, d_node) if (handle->open) { - count = handle->handler->events(handle, vals, - count); + count = handle->handle_events(handle, vals, + count); if (!count) break; } @@ -2534,57 +2534,6 @@ static int input_handler_check_methods(const struct input_handler *handler) return 0; } -/* - * An implementation of input_handler's events() method that simply - * invokes handler->event() method for each event one by one. - */ -static unsigned int input_handler_events_default(struct input_handle *handle, - struct input_value *vals, - unsigned int count) -{ - struct input_handler *handler = handle->handler; - struct input_value *v; - - for (v = vals; v != vals + count; v++) - handler->event(handle, v->type, v->code, v->value); - - return count; -} - -/* - * An implementation of input_handler's events() method that invokes - * handler->filter() method for each event one by one and removes events - * that were filtered out from the "vals" array. - */ -static unsigned int input_handler_events_filter(struct input_handle *handle, - struct input_value *vals, - unsigned int count) -{ - struct input_handler *handler = handle->handler; - struct input_value *end = vals; - struct input_value *v; - - for (v = vals; v != vals + count; v++) { - if (handler->filter(handle, v->type, v->code, v->value)) - continue; - if (end != v) - *end = *v; - end++; - } - - return end - vals; -} - -/* - * An implementation of input_handler's events() method that does nothing. - */ -static unsigned int input_handler_events_null(struct input_handle *handle, - struct input_value *vals, - unsigned int count) -{ - return count; -} - /** * input_register_handler - register a new input handler * @handler: handler to be registered @@ -2604,13 +2553,6 @@ int input_register_handler(struct input_handler *handler) INIT_LIST_HEAD(&handler->h_list); - if (handler->filter) - handler->events = input_handler_events_filter; - else if (handler->event) - handler->events = input_handler_events_default; - else if (!handler->events) - handler->events = input_handler_events_null; - error = mutex_lock_interruptible(&input_mutex); if (error) return error; @@ -2684,6 +2626,75 @@ int input_handler_for_each_handle(struct input_handler *handler, void *data, } EXPORT_SYMBOL(input_handler_for_each_handle); +/* + * An implementation of input_handle's handle_events() method that simply + * invokes handler->event() method for each event one by one. + */ +static unsigned int input_handle_events_default(struct input_handle *handle, + struct input_value *vals, + unsigned int count) +{ + struct input_handler *handler = handle->handler; + struct input_value *v; + + for (v = vals; v != vals + count; v++) + handler->event(handle, v->type, v->code, v->value); + + return count; +} + +/* + * An implementation of input_handle's handle_events() method that invokes + * handler->filter() method for each event one by one and removes events + * that were filtered out from the "vals" array. + */ +static unsigned int input_handle_events_filter(struct input_handle *handle, + struct input_value *vals, + unsigned int count) +{ + struct input_handler *handler = handle->handler; + struct input_value *end = vals; + struct input_value *v; + + for (v = vals; v != vals + count; v++) { + if (handler->filter(handle, v->type, v->code, v->value)) + continue; + if (end != v) + *end = *v; + end++; + } + + return end - vals; +} + +/* + * An implementation of input_handle's handle_events() method that does nothing. + */ +static unsigned int input_handle_events_null(struct input_handle *handle, + struct input_value *vals, + unsigned int count) +{ + return count; +} + +/* + * Sets up appropriate handle->event_handler based on the input_handler + * associated with the handle. + */ +static void input_handle_setup_event_handler(struct input_handle *handle) +{ + struct input_handler *handler = handle->handler; + + if (handler->filter) + handle->handle_events = input_handle_events_filter; + else if (handler->event) + handle->handle_events = input_handle_events_default; + else if (handler->events) + handle->handle_events = handler->events; + else + handle->handle_events = input_handle_events_null; +} + /** * input_register_handle - register a new input handle * @handle: handle to register @@ -2701,6 +2712,7 @@ int input_register_handle(struct input_handle *handle) struct input_dev *dev = handle->dev; int error; + input_handle_setup_event_handler(handle); /* * We take dev->mutex here to prevent race with * input_release_device(). diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c index d25d63a807f2..dc734974ce06 100644 --- a/drivers/input/keyboard/adp5588-keys.c +++ b/drivers/input/keyboard/adp5588-keys.c @@ -822,7 +822,8 @@ static int adp5588_suspend(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); - disable_irq(client->irq); + if (client->irq) + disable_irq(client->irq); return 0; } @@ -831,7 +832,8 @@ static int adp5588_resume(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); - enable_irq(client->irq); + if (client->irq) + enable_irq(client->irq); return 0; } diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index fda49b2fe088..85c6d8ce003f 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -1121,6 +1121,14 @@ static void edt_ft5x06_ts_set_regs(struct edt_ft5x06_ts_data *tsdata) } } +static void edt_ft5x06_exit_regmap(void *arg) +{ + struct edt_ft5x06_ts_data *data = arg; + + if (!IS_ERR_OR_NULL(data->regmap)) + regmap_exit(data->regmap); +} + static void edt_ft5x06_disable_regulators(void *arg) { struct edt_ft5x06_ts_data *data = arg; @@ -1154,6 +1162,16 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client) return PTR_ERR(tsdata->regmap); } + /* + * We are not using devm_regmap_init_i2c() and instead install a + * custom action because we may replace regmap with M06-specific one + * and we need to make sure that it will not be released too early. + */ + error = devm_add_action_or_reset(&client->dev, edt_ft5x06_exit_regmap, + tsdata); + if (error) + return error; + chip_data = device_get_match_data(&client->dev); if (!chip_data) chip_data = (const struct edt_i2c_chip_data *)id->driver_data; @@ -1347,7 +1365,6 @@ static void edt_ft5x06_ts_remove(struct i2c_client *client) struct edt_ft5x06_ts_data *tsdata = i2c_get_clientdata(client); edt_ft5x06_ts_teardown_debugfs(tsdata); - regmap_exit(tsdata->regmap); } static int edt_ft5x06_ts_suspend(struct device *dev) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index ab597e74ba08..52f625e07658 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3810,8 +3810,18 @@ static int its_vpe_set_affinity(struct irq_data *d, * Check if we're racing against a VPE being destroyed, for * which we don't want to allow a VMOVP. */ - if (!atomic_read(&vpe->vmapp_count)) - return -EINVAL; + if (!atomic_read(&vpe->vmapp_count)) { + if (gic_requires_eager_mapping()) + return -EINVAL; + + /* + * If we lazily map the VPEs, this isn't an error and + * we can exit cleanly. + */ + cpu = cpumask_first(mask_val); + irq_data_update_effective_affinity(d, cpumask_of(cpu)); + return IRQ_SET_MASK_OK_DONE; + } /* * Changing affinity is mega expensive, so let's be as lazy as diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c index e5a483fd9ad8..45ff0e198f8f 100644 --- a/drivers/isdn/hardware/mISDN/hfcmulti.c +++ b/drivers/isdn/hardware/mISDN/hfcmulti.c @@ -25,8 +25,8 @@ * Bit 8 = 0x00100 = uLaw (instead of aLaw) * Bit 9 = 0x00200 = Disable DTMF detect on all B-channels via hardware * Bit 10 = spare - * Bit 11 = 0x00800 = Force PCM bus into slave mode. (otherwhise auto) - * or Bit 12 = 0x01000 = Force PCM bus into master mode. (otherwhise auto) + * Bit 11 = 0x00800 = Force PCM bus into slave mode. (otherwise auto) + * or Bit 12 = 0x01000 = Force PCM bus into master mode. (otherwise auto) * Bit 13 = spare * Bit 14 = 0x04000 = Use external ram (128K) * Bit 15 = 0x08000 = Use external ram (512K) @@ -41,7 +41,7 @@ * port: (optional or required for all ports on all installed cards) * HFC-4S/HFC-8S only bits: * Bit 0 = 0x001 = Use master clock for this S/T interface - * (ony once per chip). + * (only once per chip). * Bit 1 = 0x002 = transmitter line setup (non capacitive mode) * Don't use this unless you know what you are doing! * Bit 2 = 0x004 = Disable E-channel. (No E-channel processing) @@ -82,7 +82,7 @@ * By default (0), the PCM bus id is 100 for the card that is PCM master. * If multiple cards are PCM master (because they are not interconnected), * each card with PCM master will have increasing PCM id. - * All PCM busses with the same ID are expected to be connected and have + * All PCM buses with the same ID are expected to be connected and have * common time slots slots. * Only one chip of the PCM bus must be master, the others slave. * -1 means no support of PCM bus not even. @@ -930,7 +930,7 @@ hfcmulti_resync(struct hfc_multi *locked, struct hfc_multi *newmaster, int rm) if (newmaster) { hc = newmaster; if (debug & DEBUG_HFCMULTI_PLXSD) - printk(KERN_DEBUG "id=%d (0x%p) = syncronized with " + printk(KERN_DEBUG "id=%d (0x%p) = synchronized with " "interface.\n", hc->id, hc); /* Enable new sync master */ plx_acc_32 = hc->plx_membase + PLX_GPIOC; @@ -949,7 +949,7 @@ hfcmulti_resync(struct hfc_multi *locked, struct hfc_multi *newmaster, int rm) hc = pcmmaster; if (debug & DEBUG_HFCMULTI_PLXSD) printk(KERN_DEBUG - "id=%d (0x%p) = PCM master syncronized " + "id=%d (0x%p) = PCM master synchronized " "with QUARTZ\n", hc->id, hc); if (hc->ctype == HFC_TYPE_E1) { /* Use the crystal clock for the PCM @@ -2001,7 +2001,7 @@ next_frame: if (Zspace <= 0) Zspace += hc->Zlen; Zspace -= 4; /* keep not too full, so pointers will not overrun */ - /* fill transparent data only to maxinum transparent load (minus 4) */ + /* fill transparent data only to maximum transparent load (minus 4) */ if (bch && test_bit(FLG_TRANSPARENT, &bch->Flags)) Zspace = Zspace - hc->Zlen + hc->max_trans; if (Zspace <= 0) /* no space of 4 bytes */ @@ -4672,7 +4672,7 @@ init_e1_port_hw(struct hfc_multi *hc, struct hm_map *m) if (debug & DEBUG_HFCMULTI_INIT) printk(KERN_DEBUG "%s: PORT set optical " - "interfacs: card(%d) " + "interface: card(%d) " "port(%d)\n", __func__, HFC_cnt + 1, 1); diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index aaeeabfab09b..40709310e327 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1905,16 +1905,13 @@ static void check_migrations(struct work_struct *ws) * This function gets called on the error paths of the constructor, so we * have to cope with a partially initialised struct. */ -static void destroy(struct cache *cache) +static void __destroy(struct cache *cache) { - unsigned int i; - mempool_exit(&cache->migration_pool); if (cache->prison) dm_bio_prison_destroy_v2(cache->prison); - cancel_delayed_work_sync(&cache->waker); if (cache->wq) destroy_workqueue(cache->wq); @@ -1942,13 +1939,22 @@ static void destroy(struct cache *cache) if (cache->policy) dm_cache_policy_destroy(cache->policy); + bioset_exit(&cache->bs); + + kfree(cache); +} + +static void destroy(struct cache *cache) +{ + unsigned int i; + + cancel_delayed_work_sync(&cache->waker); + for (i = 0; i < cache->nr_ctr_args ; i++) kfree(cache->ctr_args[i]); kfree(cache->ctr_args); - bioset_exit(&cache->bs); - - kfree(cache); + __destroy(cache); } static void cache_dtr(struct dm_target *ti) @@ -2003,7 +2009,6 @@ struct cache_args { sector_t cache_sectors; struct dm_dev *origin_dev; - sector_t origin_sectors; uint32_t block_size; @@ -2084,6 +2089,7 @@ static int parse_cache_dev(struct cache_args *ca, struct dm_arg_set *as, static int parse_origin_dev(struct cache_args *ca, struct dm_arg_set *as, char **error) { + sector_t origin_sectors; int r; if (!at_least_one_arg(as, error)) @@ -2096,8 +2102,8 @@ static int parse_origin_dev(struct cache_args *ca, struct dm_arg_set *as, return r; } - ca->origin_sectors = get_dev_size(ca->origin_dev); - if (ca->ti->len > ca->origin_sectors) { + origin_sectors = get_dev_size(ca->origin_dev); + if (ca->ti->len > origin_sectors) { *error = "Device size larger than cached device"; return -EINVAL; } @@ -2407,7 +2413,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) ca->metadata_dev = ca->origin_dev = ca->cache_dev = NULL; - origin_blocks = cache->origin_sectors = ca->origin_sectors; + origin_blocks = cache->origin_sectors = ti->len; origin_blocks = block_div(origin_blocks, ca->block_size); cache->origin_blocks = to_oblock(origin_blocks); @@ -2561,7 +2567,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) *result = cache; return 0; bad: - destroy(cache); + __destroy(cache); return r; } @@ -2612,7 +2618,7 @@ static int cache_ctr(struct dm_target *ti, unsigned int argc, char **argv) r = copy_ctr_args(cache, argc - 3, (const char **)argv + 3); if (r) { - destroy(cache); + __destroy(cache); goto out; } @@ -2895,19 +2901,19 @@ static dm_cblock_t get_cache_dev_size(struct cache *cache) static bool can_resize(struct cache *cache, dm_cblock_t new_size) { if (from_cblock(new_size) > from_cblock(cache->cache_size)) { - if (cache->sized) { - DMERR("%s: unable to extend cache due to missing cache table reload", - cache_device_name(cache)); - return false; - } + DMERR("%s: unable to extend cache due to missing cache table reload", + cache_device_name(cache)); + return false; } /* * We can't drop a dirty block when shrinking the cache. */ - while (from_cblock(new_size) < from_cblock(cache->cache_size)) { - new_size = to_cblock(from_cblock(new_size) + 1); - if (is_dirty(cache, new_size)) { + if (cache->loaded_mappings) { + new_size = to_cblock(find_next_bit(cache->dirty_bitset, + from_cblock(cache->cache_size), + from_cblock(new_size))); + if (new_size != cache->cache_size) { DMERR("%s: unable to shrink cache; cache block %llu is dirty", cache_device_name(cache), (unsigned long long) from_cblock(new_size)); @@ -2943,20 +2949,15 @@ static int cache_preresume(struct dm_target *ti) /* * Check to see if the cache has resized. */ - if (!cache->sized) { - r = resize_cache_dev(cache, csize); - if (r) - return r; - - cache->sized = true; - - } else if (csize != cache->cache_size) { + if (!cache->sized || csize != cache->cache_size) { if (!can_resize(cache, csize)) return -EINVAL; r = resize_cache_dev(cache, csize); if (r) return r; + + cache->sized = true; } if (!cache->loaded_mappings) { diff --git a/drivers/md/dm-unstripe.c b/drivers/md/dm-unstripe.c index 48587c16c445..e8a9432057dc 100644 --- a/drivers/md/dm-unstripe.c +++ b/drivers/md/dm-unstripe.c @@ -85,8 +85,8 @@ static int unstripe_ctr(struct dm_target *ti, unsigned int argc, char **argv) } uc->physical_start = start; - uc->unstripe_offset = uc->unstripe * uc->chunk_size; - uc->unstripe_width = (uc->stripes - 1) * uc->chunk_size; + uc->unstripe_offset = (sector_t)uc->unstripe * uc->chunk_size; + uc->unstripe_width = (sector_t)(uc->stripes - 1) * uc->chunk_size; uc->chunk_shift = is_power_of_2(uc->chunk_size) ? fls(uc->chunk_size) - 1 : 0; tmp_len = ti->len; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 7d4d90b4395a..c142ec5458b7 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -356,9 +356,9 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_METADATA, hash_block)) { - struct bio *bio = - dm_bio_from_per_bio_data(io, - v->ti->per_io_data_size); + struct bio *bio; + io->had_mismatch = true; + bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size); dm_audit_log_bio(DM_MSG_PREFIX, "verify-metadata", bio, block, 0); r = -EIO; @@ -482,6 +482,7 @@ static int verity_handle_data_hash_mismatch(struct dm_verity *v, return -EIO; /* Error correction failed; Just return error */ if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, blkno)) { + io->had_mismatch = true; dm_audit_log_bio(DM_MSG_PREFIX, "verify-data", bio, blkno, 0); return -EIO; } @@ -606,6 +607,7 @@ static void verity_finish_io(struct dm_verity_io *io, blk_status_t status) if (unlikely(status != BLK_STS_OK) && unlikely(!(bio->bi_opf & REQ_RAHEAD)) && + !io->had_mismatch && !verity_is_system_shutting_down()) { if (v->error_mode == DM_VERITY_MODE_PANIC) { panic("dm-verity device has I/O error"); @@ -779,6 +781,7 @@ static int verity_map(struct dm_target *ti, struct bio *bio) io->orig_bi_end_io = bio->bi_end_io; io->block = bio->bi_iter.bi_sector >> (v->data_dev_block_bits - SECTOR_SHIFT); io->n_blocks = bio->bi_iter.bi_size >> v->data_dev_block_bits; + io->had_mismatch = false; bio->bi_end_io = verity_end_io; bio->bi_private = io; diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index 6b75159bf835..c996140bda94 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -92,6 +92,7 @@ struct dm_verity_io { sector_t block; unsigned int n_blocks; bool in_bh; + bool had_mismatch; struct work_struct work; struct work_struct bh_work; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index ff4a6b570b76..19230404d8c2 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2290,8 +2290,10 @@ static struct mapped_device *alloc_dev(int minor) * override accordingly. */ md->disk = blk_alloc_disk(NULL, md->numa_node_id); - if (IS_ERR(md->disk)) + if (IS_ERR(md->disk)) { + md->disk = NULL; goto bad; + } md->queue = md->disk->queue; init_waitqueue_head(&md->wait); diff --git a/drivers/md/md.c b/drivers/md/md.c index 179ee4afe937..67108c397c5a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -546,6 +546,26 @@ static int mddev_set_closing_and_sync_blockdev(struct mddev *mddev, int opener_n return 0; } +/* + * The only difference from bio_chain_endio() is that the current + * bi_status of bio does not affect the bi_status of parent. + */ +static void md_end_flush(struct bio *bio) +{ + struct bio *parent = bio->bi_private; + + /* + * If any flush io error before the power failure, + * disk data may be lost. + */ + if (bio->bi_status) + pr_err("md: %pg flush io error %d\n", bio->bi_bdev, + blk_status_to_errno(bio->bi_status)); + + bio_put(bio); + bio_endio(parent); +} + bool md_flush_request(struct mddev *mddev, struct bio *bio) { struct md_rdev *rdev; @@ -565,7 +585,9 @@ bool md_flush_request(struct mddev *mddev, struct bio *bio) new = bio_alloc_bioset(rdev->bdev, 0, REQ_OP_WRITE | REQ_PREFLUSH, GFP_NOIO, &mddev->bio_set); - bio_chain(new, bio); + new->bi_private = bio; + new->bi_end_io = md_end_flush; + bio_inc_remaining(bio); submit_bio(new); } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index f3bf1116794a..862b1fb71d86 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -4061,9 +4061,12 @@ static int raid10_run(struct mddev *mddev) } if (!mddev_is_dm(conf->mddev)) { - ret = raid10_set_queue_limits(mddev); - if (ret) + int err = raid10_set_queue_limits(mddev); + + if (err) { + ret = err; goto out_free_conf; + } } /* need to check that every block has at least one working mirror */ diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 9d090fa07516..be011cef12e5 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -321,7 +321,7 @@ void mei_io_cb_free(struct mei_cl_cb *cb) return; list_del(&cb->list); - kfree(cb->buf.data); + kvfree(cb->buf.data); kfree(cb->ext_hdr); kfree(cb); } @@ -497,7 +497,7 @@ struct mei_cl_cb *mei_cl_alloc_cb(struct mei_cl *cl, size_t length, if (length == 0) return cb; - cb->buf.data = kmalloc(roundup(length, MEI_SLOT_SIZE), GFP_KERNEL); + cb->buf.data = kvmalloc(roundup(length, MEI_SLOT_SIZE), GFP_KERNEL); if (!cb->buf.data) { mei_io_cb_free(cb); return NULL; diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index 0f81586a19df..68ce4920e01e 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -892,28 +892,40 @@ static void gl9767_disable_ssc_pll(struct pci_dev *pdev) gl9767_vhs_read(pdev); } +static void gl9767_set_low_power_negotiation(struct pci_dev *pdev, bool enable) +{ + u32 value; + + gl9767_vhs_write(pdev); + + pci_read_config_dword(pdev, PCIE_GLI_9767_CFG, &value); + if (enable) + value &= ~PCIE_GLI_9767_CFG_LOW_PWR_OFF; + else + value |= PCIE_GLI_9767_CFG_LOW_PWR_OFF; + pci_write_config_dword(pdev, PCIE_GLI_9767_CFG, value); + + gl9767_vhs_read(pdev); +} + static void sdhci_gl9767_set_clock(struct sdhci_host *host, unsigned int clock) { struct sdhci_pci_slot *slot = sdhci_priv(host); struct mmc_ios *ios = &host->mmc->ios; struct pci_dev *pdev; - u32 value; u16 clk; pdev = slot->chip->pdev; host->mmc->actual_clock = 0; - gl9767_vhs_write(pdev); - - pci_read_config_dword(pdev, PCIE_GLI_9767_CFG, &value); - value |= PCIE_GLI_9767_CFG_LOW_PWR_OFF; - pci_write_config_dword(pdev, PCIE_GLI_9767_CFG, value); - + gl9767_set_low_power_negotiation(pdev, false); gl9767_disable_ssc_pll(pdev); sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL); - if (clock == 0) + if (clock == 0) { + gl9767_set_low_power_negotiation(pdev, true); return; + } clk = sdhci_calc_clk(host, clock, &host->mmc->actual_clock); if (clock == 200000000 && ios->timing == MMC_TIMING_UHS_SDR104) { @@ -922,12 +934,7 @@ static void sdhci_gl9767_set_clock(struct sdhci_host *host, unsigned int clock) } sdhci_enable_clk(host, clk); - - pci_read_config_dword(pdev, PCIE_GLI_9767_CFG, &value); - value &= ~PCIE_GLI_9767_CFG_LOW_PWR_OFF; - pci_write_config_dword(pdev, PCIE_GLI_9767_CFG, value); - - gl9767_vhs_read(pdev); + gl9767_set_low_power_negotiation(pdev, true); } static void gli_set_9767(struct sdhci_host *host) @@ -1061,6 +1068,9 @@ static int gl9767_init_sd_express(struct mmc_host *mmc, struct mmc_ios *ios) sdhci_writew(host, value, SDHCI_CLOCK_CONTROL); } + pci_read_config_dword(pdev, PCIE_GLI_9767_CFG, &value); + value &= ~PCIE_GLI_9767_CFG_LOW_PWR_OFF; + pci_write_config_dword(pdev, PCIE_GLI_9767_CFG, value); gl9767_vhs_read(pdev); return 0; diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 0433a0f36d1b..98c6205ed19f 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -3206,15 +3206,11 @@ static int amt_newlink(struct net *net, struct net_device *dev, goto err; } - if (data[IFLA_AMT_RELAY_PORT]) - amt->relay_port = nla_get_be16(data[IFLA_AMT_RELAY_PORT]); - else - amt->relay_port = htons(IANA_AMT_UDP_PORT); + amt->relay_port = nla_get_be16_default(data[IFLA_AMT_RELAY_PORT], + htons(IANA_AMT_UDP_PORT)); - if (data[IFLA_AMT_GATEWAY_PORT]) - amt->gw_port = nla_get_be16(data[IFLA_AMT_GATEWAY_PORT]); - else - amt->gw_port = htons(IANA_AMT_UDP_PORT); + amt->gw_port = nla_get_be16_default(data[IFLA_AMT_GATEWAY_PORT], + htons(IANA_AMT_UDP_PORT)); if (!amt->relay_port) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_DISCOVERY_IP], diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5812e8eaccf1..9e8bdd0d0922 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1545,6 +1545,7 @@ static void bond_compute_features(struct bonding *bond) { unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; + netdev_features_t gso_partial_features = NETIF_F_GSO_ESP; netdev_features_t vlan_features = BOND_VLAN_FEATURES; netdev_features_t enc_features = BOND_ENC_FEATURES; #ifdef CONFIG_XFRM_OFFLOAD @@ -1577,6 +1578,9 @@ static void bond_compute_features(struct bonding *bond) BOND_XFRM_FEATURES); #endif /* CONFIG_XFRM_OFFLOAD */ + if (slave->dev->hw_enc_features & NETIF_F_GSO_PARTIAL) + gso_partial_features &= slave->dev->gso_partial_features; + mpls_features = netdev_increment_features(mpls_features, slave->dev->mpls_features, BOND_MPLS_FEATURES); @@ -1590,6 +1594,11 @@ static void bond_compute_features(struct bonding *bond) } bond_dev->hard_header_len = max_hard_header_len; + if (gso_partial_features & NETIF_F_GSO_ESP) + bond_dev->gso_partial_features |= NETIF_F_GSO_ESP; + else + bond_dev->gso_partial_features &= ~NETIF_F_GSO_ESP; + done: bond_dev->vlan_features = vlan_features; bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | diff --git a/drivers/net/can/c_can/c_can_main.c b/drivers/net/can/c_can/c_can_main.c index c63f7fc1e691..511615dc3341 100644 --- a/drivers/net/can/c_can/c_can_main.c +++ b/drivers/net/can/c_can/c_can_main.c @@ -1011,7 +1011,6 @@ static int c_can_handle_bus_err(struct net_device *dev, /* common for all type of bus errors */ priv->can.can_stats.bus_error++; - stats->rx_errors++; /* propagate the error condition to the CAN stack */ skb = alloc_can_err_skb(dev, &cf); @@ -1027,26 +1026,32 @@ static int c_can_handle_bus_err(struct net_device *dev, case LEC_STUFF_ERROR: netdev_dbg(dev, "stuff error\n"); cf->data[2] |= CAN_ERR_PROT_STUFF; + stats->rx_errors++; break; case LEC_FORM_ERROR: netdev_dbg(dev, "form error\n"); cf->data[2] |= CAN_ERR_PROT_FORM; + stats->rx_errors++; break; case LEC_ACK_ERROR: netdev_dbg(dev, "ack error\n"); cf->data[3] = CAN_ERR_PROT_LOC_ACK; + stats->tx_errors++; break; case LEC_BIT1_ERROR: netdev_dbg(dev, "bit1 error\n"); cf->data[2] |= CAN_ERR_PROT_BIT1; + stats->tx_errors++; break; case LEC_BIT0_ERROR: netdev_dbg(dev, "bit0 error\n"); cf->data[2] |= CAN_ERR_PROT_BIT0; + stats->tx_errors++; break; case LEC_CRC_ERROR: netdev_dbg(dev, "CRC error\n"); cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ; + stats->rx_errors++; break; default: break; diff --git a/drivers/net/can/cc770/Kconfig b/drivers/net/can/cc770/Kconfig index 467ef19de1c1..aae25c2f849e 100644 --- a/drivers/net/can/cc770/Kconfig +++ b/drivers/net/can/cc770/Kconfig @@ -7,7 +7,7 @@ if CAN_CC770 config CAN_CC770_ISA tristate "ISA Bus based legacy CC770 driver" - depends on ISA + depends on HAS_IOPORT help This driver adds legacy support for CC770 and AN82527 chips connected to the ISA bus using I/O port, memory mapped or diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index a978b960f1f1..16e9e7d7527d 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1765,7 +1765,8 @@ static int m_can_close(struct net_device *dev) netif_stop_queue(dev); m_can_stop(dev); - free_irq(dev->irq, dev); + if (dev->irq) + free_irq(dev->irq, dev); m_can_clean(dev); diff --git a/drivers/net/can/rockchip/Kconfig b/drivers/net/can/rockchip/Kconfig index e029e2a3ca4b..d203c530551f 100644 --- a/drivers/net/can/rockchip/Kconfig +++ b/drivers/net/can/rockchip/Kconfig @@ -2,7 +2,8 @@ config CAN_ROCKCHIP_CANFD tristate "Rockchip CAN-FD controller" - depends on OF || COMPILE_TEST + depends on OF + depends on ARCH_ROCKCHIP || COMPILE_TEST select CAN_RX_OFFLOAD help Say Y here if you want to use CAN-FD controller found on diff --git a/drivers/net/can/sja1000/Kconfig b/drivers/net/can/sja1000/Kconfig index 01168db4c106..2f516cc6d22c 100644 --- a/drivers/net/can/sja1000/Kconfig +++ b/drivers/net/can/sja1000/Kconfig @@ -87,7 +87,7 @@ config CAN_PLX_PCI config CAN_SJA1000_ISA tristate "ISA Bus based legacy SJA1000 driver" - depends on ISA + depends on HAS_IOPORT help This driver adds legacy support for SJA1000 chips connected to the ISA bus using I/O port, memory mapped or indirect access. diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c index e684991fa391..7209a831f0f2 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c @@ -2,7 +2,7 @@ // // mcp251xfd - Microchip MCP251xFD Family CAN controller driver // -// Copyright (c) 2019, 2020, 2021 Pengutronix, +// Copyright (c) 2019, 2020, 2021, 2024 Pengutronix, // Marc Kleine-Budde <[email protected]> // // Based on: @@ -483,9 +483,11 @@ int mcp251xfd_ring_alloc(struct mcp251xfd_priv *priv) }; const struct ethtool_coalesce ec = { .rx_coalesce_usecs_irq = priv->rx_coalesce_usecs_irq, - .rx_max_coalesced_frames_irq = priv->rx_obj_num_coalesce_irq, + .rx_max_coalesced_frames_irq = priv->rx_obj_num_coalesce_irq == 0 ? + 1 : priv->rx_obj_num_coalesce_irq, .tx_coalesce_usecs_irq = priv->tx_coalesce_usecs_irq, - .tx_max_coalesced_frames_irq = priv->tx_obj_num_coalesce_irq, + .tx_max_coalesced_frames_irq = priv->tx_obj_num_coalesce_irq == 0 ? + 1 : priv->tx_obj_num_coalesce_irq, }; struct can_ram_layout layout; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c index f732556d233a..d3ac865933fd 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c @@ -16,9 +16,9 @@ #include "mcp251xfd.h" -static inline bool mcp251xfd_tx_fifo_sta_full(u32 fifo_sta) +static inline bool mcp251xfd_tx_fifo_sta_empty(u32 fifo_sta) { - return !(fifo_sta & MCP251XFD_REG_FIFOSTA_TFNRFNIF); + return fifo_sta & MCP251XFD_REG_FIFOSTA_TFERFFIF; } static inline int @@ -122,7 +122,11 @@ mcp251xfd_get_tef_len(struct mcp251xfd_priv *priv, u8 *len_p) if (err) return err; - if (mcp251xfd_tx_fifo_sta_full(fifo_sta)) { + /* If the chip says the TX-FIFO is empty, but there are no TX + * buffers free in the ring, we assume all have been sent. + */ + if (mcp251xfd_tx_fifo_sta_empty(fifo_sta) && + mcp251xfd_get_tx_free(tx_ring) == 0) { *len_p = tx_ring->obj_num; return 0; } diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index 9e1b7d41005f..da7c72105fb6 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -188,14 +188,10 @@ static int vxcan_newlink(struct net *net, struct net_device *dev, /* register peer device */ if (data && data[VXCAN_INFO_PEER]) { - struct nlattr *nla_peer; + struct nlattr *nla_peer = data[VXCAN_INFO_PEER]; - nla_peer = data[VXCAN_INFO_PEER]; ifmp = nla_data(nla_peer); - err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); - if (err < 0) - return err; - + rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); tbp = peer_tb; } @@ -208,9 +204,6 @@ static int vxcan_newlink(struct net *net, struct net_device *dev, } peer_net = rtnl_link_get_net(net, tbp); - if (IS_ERR(peer_net)) - return PTR_ERR(peer_net); - peer = rtnl_create_link(peer_net, ifname, name_assign_type, &vxcan_link_ops, tbp, extack); if (IS_ERR(peer)) { @@ -302,6 +295,7 @@ static struct rtnl_link_ops vxcan_link_ops = { .newlink = vxcan_newlink, .dellink = vxcan_dellink, .policy = vxcan_policy, + .peer_type = VXCAN_INFO_PEER, .maxtype = VXCAN_INFO_MAX, .get_link_net = vxcan_get_link_net, }; diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index c39cb119e760..285785c942b0 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -989,8 +989,7 @@ void b53_get_strings(struct dsa_switch *ds, int port, u32 stringset, if (stringset == ETH_SS_STATS) { for (i = 0; i < mib_size; i++) - strscpy(data + i * ETH_GSTRING_LEN, - mibs[i].name, ETH_GSTRING_LEN); + ethtool_puts(&data, mibs[i].name); } else if (stringset == ETH_SS_PHY_STATS) { phydev = b53_get_phy_device(ds, port); if (!phydev) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 9201f07839ad..43bde1f583ff 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1183,8 +1183,8 @@ static void bcm_sf2_sw_get_strings(struct dsa_switch *ds, int port, int cnt = b53_get_sset_count(ds, port, stringset); b53_get_strings(ds, port, stringset, data); - bcm_sf2_cfp_get_strings(ds, port, stringset, - data + cnt * ETH_GSTRING_LEN); + data += cnt * ETH_GSTRING_LEN; + bcm_sf2_cfp_get_strings(ds, port, stringset, &data); } static void bcm_sf2_sw_get_ethtool_stats(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h index 4fda075a3449..be9f3b29019f 100644 --- a/drivers/net/dsa/bcm_sf2.h +++ b/drivers/net/dsa/bcm_sf2.h @@ -228,8 +228,8 @@ int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port, int bcm_sf2_cfp_rst(struct bcm_sf2_priv *priv); void bcm_sf2_cfp_exit(struct dsa_switch *ds); int bcm_sf2_cfp_resume(struct dsa_switch *ds); -void bcm_sf2_cfp_get_strings(struct dsa_switch *ds, int port, - u32 stringset, uint8_t *data); +void bcm_sf2_cfp_get_strings(struct dsa_switch *ds, int port, u32 stringset, + uint8_t **data); void bcm_sf2_cfp_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data); int bcm_sf2_cfp_get_sset_count(struct dsa_switch *ds, int port, int sset); diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index c88ee3dd4299..e22362e6f0cd 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -1279,27 +1279,19 @@ static const struct bcm_sf2_cfp_stat { }, }; -void bcm_sf2_cfp_get_strings(struct dsa_switch *ds, int port, - u32 stringset, uint8_t *data) +void bcm_sf2_cfp_get_strings(struct dsa_switch *ds, int port, u32 stringset, + uint8_t **data) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - unsigned int s = ARRAY_SIZE(bcm_sf2_cfp_stats); - char buf[ETH_GSTRING_LEN]; - unsigned int i, j, iter; + unsigned int i, j; if (stringset != ETH_SS_STATS) return; - for (i = 1; i < priv->num_cfp_rules; i++) { - for (j = 0; j < s; j++) { - snprintf(buf, sizeof(buf), - "CFP%03d_%sCntr", - i, bcm_sf2_cfp_stats[j].name); - iter = (i - 1) * s + j; - strscpy(data + iter * ETH_GSTRING_LEN, - buf, ETH_GSTRING_LEN); - } - } + for (i = 1; i < priv->num_cfp_rules; i++) + for (j = 0; j < ARRAY_SIZE(bcm_sf2_cfp_stats); j++) + ethtool_sprintf(data, "CFP%03d_%sCntr", i, + bcm_sf2_cfp_stats[j].name); } void bcm_sf2_cfp_get_ethtool_stats(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index c70ed67cc188..adbab544c60f 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -121,8 +121,7 @@ static void dsa_loop_get_strings(struct dsa_switch *ds, int port, return; for (i = 0; i < __DSA_LOOP_CNT_MAX; i++) - memcpy(data + i * ETH_GSTRING_LEN, - ps->ports[port].mib[i].name, ETH_GSTRING_LEN); + ethtool_puts(&data, ps->ports[port].mib[i].name); } static void dsa_loop_get_ethtool_stats(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index d798f17cf7ea..283ec5a6e23c 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -294,12 +294,8 @@ static void hellcreek_get_strings(struct dsa_switch *ds, int port, { int i; - for (i = 0; i < ARRAY_SIZE(hellcreek_counter); ++i) { - const struct hellcreek_counter *counter = &hellcreek_counter[i]; - - strscpy(data + i * ETH_GSTRING_LEN, - counter->name, ETH_GSTRING_LEN); - } + for (i = 0; i < ARRAY_SIZE(hellcreek_counter); ++i) + ethtool_puts(&data, hellcreek_counter[i].name); } static int hellcreek_get_sset_count(struct dsa_switch *ds, int port, int sset) diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 5290f5ad98f3..d57782cdda59 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -411,6 +411,8 @@ static const struct ksz_dev_ops lan937x_dev_ops = { .flush_dyn_mac_table = ksz9477_flush_dyn_mac_table, .port_setup = lan937x_port_setup, .set_ageing_time = lan937x_set_ageing_time, + .mdio_bus_preinit = lan937x_mdio_bus_preinit, + .create_phy_addr_map = lan937x_create_phy_addr_map, .r_phy = lan937x_r_phy, .w_phy = lan937x_w_phy, .r_mib_cnt = ksz9477_r_mib_cnt, @@ -1762,6 +1764,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .num_tx_queues = 8, .num_ipms = 8, .tc_cbs_supported = true, + .phy_side_mdio_supported = true, .ops = &lan937x_dev_ops, .phylink_mac_ops = &lan937x_phylink_mac_ops, .mib_names = ksz9477_mib_names, @@ -1790,6 +1793,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .num_tx_queues = 8, .num_ipms = 8, .tc_cbs_supported = true, + .phy_side_mdio_supported = true, .ops = &lan937x_dev_ops, .phylink_mac_ops = &lan937x_phylink_mac_ops, .mib_names = ksz9477_mib_names, @@ -1818,6 +1822,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .num_tx_queues = 8, .num_ipms = 8, .tc_cbs_supported = true, + .phy_side_mdio_supported = true, .ops = &lan937x_dev_ops, .phylink_mac_ops = &lan937x_phylink_mac_ops, .mib_names = ksz9477_mib_names, @@ -1850,6 +1855,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .num_tx_queues = 8, .num_ipms = 8, .tc_cbs_supported = true, + .phy_side_mdio_supported = true, .ops = &lan937x_dev_ops, .phylink_mac_ops = &lan937x_phylink_mac_ops, .mib_names = ksz9477_mib_names, @@ -1882,6 +1888,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .num_tx_queues = 8, .num_ipms = 8, .tc_cbs_supported = true, + .phy_side_mdio_supported = true, .ops = &lan937x_dev_ops, .phylink_mac_ops = &lan937x_phylink_mac_ops, .mib_names = ksz9477_mib_names, @@ -2112,10 +2119,8 @@ static void ksz_get_strings(struct dsa_switch *ds, int port, if (stringset != ETH_SS_STATS) return; - for (i = 0; i < dev->info->mib_cnt; i++) { - memcpy(buf + i * ETH_GSTRING_LEN, - dev->info->mib_names[i].string, ETH_GSTRING_LEN); - } + for (i = 0; i < dev->info->mib_cnt; i++) + ethtool_puts(&buf, dev->info->mib_names[i].string); } /** @@ -2238,16 +2243,100 @@ static int ksz_sw_mdio_write(struct mii_bus *bus, int addr, int regnum, return dev->dev_ops->w_phy(dev, addr, regnum, val); } +/** + * ksz_parent_mdio_read - Read data from a PHY register on the parent MDIO bus. + * @bus: MDIO bus structure. + * @addr: PHY address on the parent MDIO bus. + * @regnum: Register number to read. + * + * This function provides a direct read operation on the parent MDIO bus for + * accessing PHY registers. By bypassing SPI or I2C, it uses the parent MDIO bus + * to retrieve data from the PHY registers at the specified address and register + * number. + * + * Return: Value of the PHY register, or a negative error code on failure. + */ +static int ksz_parent_mdio_read(struct mii_bus *bus, int addr, int regnum) +{ + struct ksz_device *dev = bus->priv; + + return mdiobus_read_nested(dev->parent_mdio_bus, addr, regnum); +} + +/** + * ksz_parent_mdio_write - Write data to a PHY register on the parent MDIO bus. + * @bus: MDIO bus structure. + * @addr: PHY address on the parent MDIO bus. + * @regnum: Register number to write to. + * @val: Value to write to the PHY register. + * + * This function provides a direct write operation on the parent MDIO bus for + * accessing PHY registers. Bypassing SPI or I2C, it uses the parent MDIO bus + * to modify the PHY register values at the specified address. + * + * Return: 0 on success, or a negative error code on failure. + */ +static int ksz_parent_mdio_write(struct mii_bus *bus, int addr, int regnum, + u16 val) +{ + struct ksz_device *dev = bus->priv; + + return mdiobus_write_nested(dev->parent_mdio_bus, addr, regnum, val); +} + +/** + * ksz_phy_addr_to_port - Map a PHY address to the corresponding switch port. + * @dev: Pointer to device structure. + * @addr: PHY address to map to a port. + * + * This function finds the corresponding switch port for a given PHY address by + * iterating over all user ports on the device. It checks if a port's PHY + * address in `phy_addr_map` matches the specified address and if the port + * contains an internal PHY. If a match is found, the index of the port is + * returned. + * + * Return: Port index on success, or -EINVAL if no matching port is found. + */ +static int ksz_phy_addr_to_port(struct ksz_device *dev, int addr) +{ + struct dsa_switch *ds = dev->ds; + struct dsa_port *dp; + + dsa_switch_for_each_user_port(dp, ds) { + if (dev->info->internal_phy[dp->index] && + dev->phy_addr_map[dp->index] == addr) + return dp->index; + } + + return -EINVAL; +} + +/** + * ksz_irq_phy_setup - Configure IRQs for PHYs in the KSZ device. + * @dev: Pointer to the KSZ device structure. + * + * Sets up IRQs for each active PHY connected to the KSZ switch by mapping the + * appropriate IRQs for each PHY and assigning them to the `user_mii_bus` in + * the DSA switch structure. Each IRQ is mapped based on the port's IRQ domain. + * + * Return: 0 on success, or a negative error code on failure. + */ static int ksz_irq_phy_setup(struct ksz_device *dev) { struct dsa_switch *ds = dev->ds; - int phy; + int phy, port; int irq; int ret; - for (phy = 0; phy < KSZ_MAX_NUM_PORTS; phy++) { + for (phy = 0; phy < PHY_MAX_ADDR; phy++) { if (BIT(phy) & ds->phys_mii_mask) { - irq = irq_find_mapping(dev->ports[phy].pirq.domain, + port = ksz_phy_addr_to_port(dev, phy); + if (port < 0) { + ret = port; + goto out; + } + + irq = irq_find_mapping(dev->ports[port].pirq.domain, PORT_SRC_PHY_INT); if (irq < 0) { ret = irq; @@ -2265,49 +2354,183 @@ out: return ret; } +/** + * ksz_irq_phy_free - Release IRQ mappings for PHYs in the KSZ device. + * @dev: Pointer to the KSZ device structure. + * + * Releases any IRQ mappings previously assigned to active PHYs in the KSZ + * switch by disposing of each mapped IRQ in the `user_mii_bus` structure. + */ static void ksz_irq_phy_free(struct ksz_device *dev) { struct dsa_switch *ds = dev->ds; int phy; - for (phy = 0; phy < KSZ_MAX_NUM_PORTS; phy++) + for (phy = 0; phy < PHY_MAX_ADDR; phy++) if (BIT(phy) & ds->phys_mii_mask) irq_dispose_mapping(ds->user_mii_bus->irq[phy]); } +/** + * ksz_parse_dt_phy_config - Parse and validate PHY configuration from DT + * @dev: pointer to the KSZ device structure + * @bus: pointer to the MII bus structure + * @mdio_np: pointer to the MDIO node in the device tree + * + * This function parses and validates PHY configurations for each user port + * defined in the device tree for a KSZ switch device. It verifies that the + * `phy-handle` properties are correctly set and that the internal PHYs match + * expected addresses and parent nodes. Sets up the PHY mask in the MII bus if + * all validations pass. Logs error messages for any mismatches or missing data. + * + * Return: 0 on success, or a negative error code on failure. + */ +static int ksz_parse_dt_phy_config(struct ksz_device *dev, struct mii_bus *bus, + struct device_node *mdio_np) +{ + struct device_node *phy_node, *phy_parent_node; + bool phys_are_valid = true; + struct dsa_port *dp; + u32 phy_addr; + int ret; + + dsa_switch_for_each_user_port(dp, dev->ds) { + if (!dev->info->internal_phy[dp->index]) + continue; + + phy_node = of_parse_phandle(dp->dn, "phy-handle", 0); + if (!phy_node) { + dev_err(dev->dev, "failed to parse phy-handle for port %d.\n", + dp->index); + phys_are_valid = false; + continue; + } + + phy_parent_node = of_get_parent(phy_node); + if (!phy_parent_node) { + dev_err(dev->dev, "failed to get PHY-parent node for port %d\n", + dp->index); + phys_are_valid = false; + } else if (phy_parent_node != mdio_np) { + dev_err(dev->dev, "PHY-parent node mismatch for port %d, expected %pOF, got %pOF\n", + dp->index, mdio_np, phy_parent_node); + phys_are_valid = false; + } else { + ret = of_property_read_u32(phy_node, "reg", &phy_addr); + if (ret < 0) { + dev_err(dev->dev, "failed to read PHY address for port %d. Error %d\n", + dp->index, ret); + phys_are_valid = false; + } else if (phy_addr != dev->phy_addr_map[dp->index]) { + dev_err(dev->dev, "PHY address mismatch for port %d, expected 0x%x, got 0x%x\n", + dp->index, dev->phy_addr_map[dp->index], + phy_addr); + phys_are_valid = false; + } else { + bus->phy_mask |= BIT(phy_addr); + } + } + + of_node_put(phy_node); + of_node_put(phy_parent_node); + } + + if (!phys_are_valid) + return -EINVAL; + + return 0; +} + +/** + * ksz_mdio_register - Register and configure the MDIO bus for the KSZ device. + * @dev: Pointer to the KSZ device structure. + * + * This function sets up and registers an MDIO bus for the KSZ switch device, + * allowing access to its internal PHYs. If the device supports side MDIO, + * the function will configure the external MDIO controller specified by the + * "mdio-parent-bus" device tree property to directly manage internal PHYs. + * Otherwise, SPI or I2C access is set up for PHY access. + * + * Return: 0 on success, or a negative error code on failure. + */ static int ksz_mdio_register(struct ksz_device *dev) { + struct device_node *parent_bus_node; + struct mii_bus *parent_bus = NULL; struct dsa_switch *ds = dev->ds; struct device_node *mdio_np; struct mii_bus *bus; - int ret; + int ret, i; mdio_np = of_get_child_by_name(dev->dev->of_node, "mdio"); if (!mdio_np) return 0; + parent_bus_node = of_parse_phandle(mdio_np, "mdio-parent-bus", 0); + if (parent_bus_node && !dev->info->phy_side_mdio_supported) { + dev_err(dev->dev, "Side MDIO bus is not supported for this HW, ignoring 'mdio-parent-bus' property.\n"); + ret = -EINVAL; + + goto put_mdio_node; + } else if (parent_bus_node) { + parent_bus = of_mdio_find_bus(parent_bus_node); + if (!parent_bus) { + ret = -EPROBE_DEFER; + + goto put_mdio_node; + } + + dev->parent_mdio_bus = parent_bus; + } + bus = devm_mdiobus_alloc(ds->dev); if (!bus) { - of_node_put(mdio_np); - return -ENOMEM; + ret = -ENOMEM; + goto put_mdio_node; + } + + if (dev->dev_ops->mdio_bus_preinit) { + ret = dev->dev_ops->mdio_bus_preinit(dev, !!parent_bus); + if (ret) + goto put_mdio_node; + } + + if (dev->dev_ops->create_phy_addr_map) { + ret = dev->dev_ops->create_phy_addr_map(dev, !!parent_bus); + if (ret) + goto put_mdio_node; + } else { + for (i = 0; i < dev->info->port_cnt; i++) + dev->phy_addr_map[i] = i; } bus->priv = dev; - bus->read = ksz_sw_mdio_read; - bus->write = ksz_sw_mdio_write; - bus->name = "ksz user smi"; - snprintf(bus->id, MII_BUS_ID_SIZE, "SMI-%d", ds->index); + if (parent_bus) { + bus->read = ksz_parent_mdio_read; + bus->write = ksz_parent_mdio_write; + bus->name = "KSZ side MDIO"; + snprintf(bus->id, MII_BUS_ID_SIZE, "ksz-side-mdio-%d", + ds->index); + } else { + bus->read = ksz_sw_mdio_read; + bus->write = ksz_sw_mdio_write; + bus->name = "ksz user smi"; + snprintf(bus->id, MII_BUS_ID_SIZE, "SMI-%d", ds->index); + } + + ret = ksz_parse_dt_phy_config(dev, bus, mdio_np); + if (ret) + goto put_mdio_node; + + ds->phys_mii_mask = bus->phy_mask; bus->parent = ds->dev; - bus->phy_mask = ~ds->phys_mii_mask; ds->user_mii_bus = bus; if (dev->irq > 0) { ret = ksz_irq_phy_setup(dev); - if (ret) { - of_node_put(mdio_np); - return ret; - } + if (ret) + goto put_mdio_node; } ret = devm_of_mdiobus_register(ds->dev, bus, mdio_np); @@ -2318,7 +2541,9 @@ static int ksz_mdio_register(struct ksz_device *dev) ksz_irq_phy_free(dev); } +put_mdio_node: of_node_put(mdio_np); + of_node_put(parent_bus_node); return ret; } diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index bec846e20682..bbb548af201e 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -65,6 +65,12 @@ struct ksz_chip_data { u8 num_tx_queues; u8 num_ipms; /* number of Internal Priority Maps */ bool tc_cbs_supported; + + /** + * @phy_side_mdio_supported: Indicates if the chip supports an additional + * side MDIO channel for accessing integrated PHYs. + */ + bool phy_side_mdio_supported; const struct ksz_dev_ops *ops; const struct phylink_mac_ops *phylink_mac_ops; bool phy_errata_9477; @@ -191,6 +197,22 @@ struct ksz_device { struct ksz_switch_macaddr *switch_macaddr; struct net_device *hsr_dev; /* HSR */ u8 hsr_ports; + + /** + * @phy_addr_map: Array mapping switch ports to their corresponding PHY + * addresses. + */ + u8 phy_addr_map[KSZ_MAX_NUM_PORTS]; + + /** + * @parent_mdio_bus: Pointer to the external MDIO bus controller. + * + * This points to an external MDIO bus controller that is used to access + * the PHYs integrated within the switch. Unlike an integrated MDIO + * bus, this external controller provides a direct path for managing + * the switch’s internal PHYs, bypassing the main SPI interface. + */ + struct mii_bus *parent_mdio_bus; }; /* List of supported models */ @@ -326,6 +348,43 @@ struct ksz_dev_ops { void (*port_cleanup)(struct ksz_device *dev, int port); void (*port_setup)(struct ksz_device *dev, int port, bool cpu_port); int (*set_ageing_time)(struct ksz_device *dev, unsigned int msecs); + + /** + * @mdio_bus_preinit: Function pointer to pre-initialize the MDIO bus + * for accessing PHYs. + * @dev: Pointer to device structure. + * @side_mdio: Boolean indicating if the PHYs are accessed over a side + * MDIO bus. + * + * This function pointer is used to configure the MDIO bus for PHY + * access before initiating regular PHY operations. It enables either + * SPI/I2C or side MDIO access modes by unlocking necessary registers + * and setting up access permissions for the selected mode. + * + * Return: + * - 0 on success. + * - Negative error code on failure. + */ + int (*mdio_bus_preinit)(struct ksz_device *dev, bool side_mdio); + + /** + * @create_phy_addr_map: Function pointer to create a port-to-PHY + * address map. + * @dev: Pointer to device structure. + * @side_mdio: Boolean indicating if the PHYs are accessed over a side + * MDIO bus. + * + * This function pointer is responsible for mapping switch ports to PHY + * addresses according to the configured access mode (SPI or side MDIO) + * and the device’s strap configuration. The mapping setup may vary + * depending on the chip variant and configuration. Ensures the correct + * address mapping for PHY communication. + * + * Return: + * - 0 on success. + * - Negative error code on failure (e.g., invalid configuration). + */ + int (*create_phy_addr_map)(struct ksz_device *dev, bool side_mdio); int (*r_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 *val); int (*w_phy)(struct ksz_device *dev, u16 phy, u16 reg, u16 val); void (*r_mib_cnt)(struct ksz_device *dev, int port, u16 addr, diff --git a/drivers/net/dsa/microchip/lan937x.h b/drivers/net/dsa/microchip/lan937x.h index 3388d91dbc44..df13ebbd356f 100644 --- a/drivers/net/dsa/microchip/lan937x.h +++ b/drivers/net/dsa/microchip/lan937x.h @@ -13,6 +13,8 @@ void lan937x_port_setup(struct ksz_device *dev, int port, bool cpu_port); void lan937x_config_cpu_port(struct dsa_switch *ds); int lan937x_switch_init(struct ksz_device *dev); void lan937x_switch_exit(struct ksz_device *dev); +int lan937x_mdio_bus_preinit(struct ksz_device *dev, bool side_mdio); +int lan937x_create_phy_addr_map(struct ksz_device *dev, bool side_mdio); int lan937x_r_phy(struct ksz_device *dev, u16 addr, u16 reg, u16 *data); int lan937x_w_phy(struct ksz_device *dev, u16 addr, u16 reg, u16 val); int lan937x_change_mtu(struct ksz_device *dev, int port, int new_mtu); diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c index 824d9309a3d3..b7652efd632e 100644 --- a/drivers/net/dsa/microchip/lan937x_main.c +++ b/drivers/net/dsa/microchip/lan937x_main.c @@ -18,6 +18,87 @@ #include "ksz9477.h" #include "lan937x.h" +/* marker for ports without built-in PHY */ +#define LAN937X_NO_PHY U8_MAX + +/* + * lan9370_phy_addr - Mapping of LAN9370 switch ports to PHY addresses. + * + * Each entry corresponds to a specific port on the LAN9370 switch, + * where ports 1-4 are connected to integrated 100BASE-T1 PHYs, and + * Port 5 is connected to an RGMII interface without a PHY. The values + * are based on the documentation (DS00003108E, section 3.3). + */ +static const u8 lan9370_phy_addr[] = { + [0] = 2, /* Port 1, T1 AFE0 */ + [1] = 3, /* Port 2, T1 AFE1 */ + [2] = 5, /* Port 3, T1 AFE3 */ + [3] = 6, /* Port 4, T1 AFE4 */ + [4] = LAN937X_NO_PHY, /* Port 5, RGMII 2 */ +}; + +/* + * lan9371_phy_addr - Mapping of LAN9371 switch ports to PHY addresses. + * + * The values are based on the documentation (DS00003109E, section 3.3). + */ +static const u8 lan9371_phy_addr[] = { + [0] = 2, /* Port 1, T1 AFE0 */ + [1] = 3, /* Port 2, T1 AFE1 */ + [2] = 5, /* Port 3, T1 AFE3 */ + [3] = 8, /* Port 4, TX PHY */ + [4] = LAN937X_NO_PHY, /* Port 5, RGMII 2 */ + [5] = LAN937X_NO_PHY, /* Port 6, RGMII 1 */ +}; + +/* + * lan9372_phy_addr - Mapping of LAN9372 switch ports to PHY addresses. + * + * The values are based on the documentation (DS00003110F, section 3.3). + */ +static const u8 lan9372_phy_addr[] = { + [0] = 2, /* Port 1, T1 AFE0 */ + [1] = 3, /* Port 2, T1 AFE1 */ + [2] = 5, /* Port 3, T1 AFE3 */ + [3] = 8, /* Port 4, TX PHY */ + [4] = LAN937X_NO_PHY, /* Port 5, RGMII 2 */ + [5] = LAN937X_NO_PHY, /* Port 6, RGMII 1 */ + [6] = 6, /* Port 7, T1 AFE4 */ + [7] = 4, /* Port 8, T1 AFE2 */ +}; + +/* + * lan9373_phy_addr - Mapping of LAN9373 switch ports to PHY addresses. + * + * The values are based on the documentation (DS00003110F, section 3.3). + */ +static const u8 lan9373_phy_addr[] = { + [0] = 2, /* Port 1, T1 AFE0 */ + [1] = 3, /* Port 2, T1 AFE1 */ + [2] = 5, /* Port 3, T1 AFE3 */ + [3] = LAN937X_NO_PHY, /* Port 4, SGMII */ + [4] = LAN937X_NO_PHY, /* Port 5, RGMII 2 */ + [5] = LAN937X_NO_PHY, /* Port 6, RGMII 1 */ + [6] = 6, /* Port 7, T1 AFE4 */ + [7] = 4, /* Port 8, T1 AFE2 */ +}; + +/* + * lan9374_phy_addr - Mapping of LAN9374 switch ports to PHY addresses. + * + * The values are based on the documentation (DS00003110F, section 3.3). + */ +static const u8 lan9374_phy_addr[] = { + [0] = 2, /* Port 1, T1 AFE0 */ + [1] = 3, /* Port 2, T1 AFE1 */ + [2] = 5, /* Port 3, T1 AFE3 */ + [3] = 7, /* Port 4, T1 AFE5 */ + [4] = LAN937X_NO_PHY, /* Port 5, RGMII 2 */ + [5] = LAN937X_NO_PHY, /* Port 6, RGMII 1 */ + [6] = 6, /* Port 7, T1 AFE4 */ + [7] = 4, /* Port 8, T1 AFE2 */ +}; + static int lan937x_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set) { return regmap_update_bits(ksz_regmap_8(dev), addr, bits, set ? bits : 0); @@ -30,24 +111,144 @@ static int lan937x_port_cfg(struct ksz_device *dev, int port, int offset, bits, set ? bits : 0); } -static int lan937x_enable_spi_indirect_access(struct ksz_device *dev) +/** + * lan937x_create_phy_addr_map - Create port-to-PHY address map for MDIO bus. + * @dev: Pointer to device structure. + * @side_mdio: Boolean indicating if the PHYs are accessed over a side MDIO bus. + * + * This function sets up the PHY address mapping for the LAN937x switches, + * which support two access modes for internal PHYs: + * 1. **SPI Access**: A straightforward one-to-one port-to-PHY address + * mapping is applied. + * 2. **MDIO Access**: The PHY address mapping varies based on chip variant + * and strap configuration. An offset is calculated based on strap settings + * to ensure correct PHY addresses are assigned. The offset calculation logic + * is based on Microchip's Article Number 000015828, available at: + * https://microchip.my.site.com/s/article/LAN9374-Virtual-PHY-PHY-Address-Mapping + * + * The function first checks if side MDIO access is disabled, in which case a + * simple direct mapping (port number = PHY address) is applied. If side MDIO + * access is enabled, it reads the strap configuration to determine the correct + * offset for PHY addresses. + * + * The appropriate mapping table is selected based on the chip ID, and the + * `phy_addr_map` is populated with the correct addresses for each port. Any + * port with no PHY is assigned a `LAN937X_NO_PHY` marker. + * + * Return: 0 on success, error code on failure. + */ +int lan937x_create_phy_addr_map(struct ksz_device *dev, bool side_mdio) +{ + static const u8 *phy_addr_map; + u32 strap_val; + u8 offset = 0; + size_t size; + int ret, i; + + if (!side_mdio) { + /* simple direct mapping */ + for (i = 0; i < dev->info->port_cnt; i++) + dev->phy_addr_map[i] = i; + + return 0; + } + + ret = ksz_read32(dev, REG_SW_CFG_STRAP_VAL, &strap_val); + if (ret < 0) + return ret; + + if (!(strap_val & SW_CASCADE_ID_CFG) && !(strap_val & SW_VPHY_ADD_CFG)) + offset = 0; + else if (!(strap_val & SW_CASCADE_ID_CFG) && (strap_val & SW_VPHY_ADD_CFG)) + offset = 7; + else if ((strap_val & SW_CASCADE_ID_CFG) && !(strap_val & SW_VPHY_ADD_CFG)) + offset = 15; + else + offset = 22; + + switch (dev->info->chip_id) { + case LAN9370_CHIP_ID: + phy_addr_map = lan9370_phy_addr; + size = ARRAY_SIZE(lan9370_phy_addr); + break; + case LAN9371_CHIP_ID: + phy_addr_map = lan9371_phy_addr; + size = ARRAY_SIZE(lan9371_phy_addr); + break; + case LAN9372_CHIP_ID: + phy_addr_map = lan9372_phy_addr; + size = ARRAY_SIZE(lan9372_phy_addr); + break; + case LAN9373_CHIP_ID: + phy_addr_map = lan9373_phy_addr; + size = ARRAY_SIZE(lan9373_phy_addr); + break; + case LAN9374_CHIP_ID: + phy_addr_map = lan9374_phy_addr; + size = ARRAY_SIZE(lan9374_phy_addr); + break; + default: + return -EINVAL; + } + + if (size < dev->info->port_cnt) + return -EINVAL; + + for (i = 0; i < dev->info->port_cnt; i++) { + if (phy_addr_map[i] == LAN937X_NO_PHY) + dev->phy_addr_map[i] = phy_addr_map[i]; + else + dev->phy_addr_map[i] = phy_addr_map[i] + offset; + } + + return 0; +} + +/** + * lan937x_mdio_bus_preinit - Pre-initialize MDIO bus for accessing PHYs. + * @dev: Pointer to device structure. + * @side_mdio: Boolean indicating if the PHYs are accessed over a side MDIO bus. + * + * This function configures the LAN937x switch for PHY access either through + * SPI or the side MDIO bus, unlocking the necessary registers for each access + * mode. + * + * Operation Modes: + * 1. **SPI Access**: Enables SPI indirect access to address clock domain + * crossing issues when SPI is used for PHY access. + * 2. **MDIO Access**: Grants access to internal PHYs over the side MDIO bus, + * required when using the MDIO bus for PHY management. + * + * Return: 0 on success, error code on failure. + */ +int lan937x_mdio_bus_preinit(struct ksz_device *dev, bool side_mdio) { u16 data16; int ret; - /* Enable Phy access through SPI */ + /* Unlock access to the PHYs, needed for SPI and side MDIO access */ ret = lan937x_cfg(dev, REG_GLOBAL_CTRL_0, SW_PHY_REG_BLOCK, false); if (ret < 0) - return ret; + goto print_error; - ret = ksz_read16(dev, REG_VPHY_SPECIAL_CTRL__2, &data16); - if (ret < 0) - return ret; + if (side_mdio) + /* Allow access to internal PHYs over MDIO bus */ + data16 = VPHY_MDIO_INTERNAL_ENABLE; + else + /* Enable SPI indirect access to address clock domain crossing + * issue + */ + data16 = VPHY_SPI_INDIRECT_ENABLE; - /* Allow SPI access */ - data16 |= VPHY_SPI_INDIRECT_ENABLE; + ret = ksz_rmw16(dev, REG_VPHY_SPECIAL_CTRL__2, + VPHY_SPI_INDIRECT_ENABLE | VPHY_MDIO_INTERNAL_ENABLE, + data16); + +print_error: + if (ret < 0) + dev_err(dev->dev, "failed to preinit the MDIO bus\n"); - return ksz_write16(dev, REG_VPHY_SPECIAL_CTRL__2, data16); + return ret; } static int lan937x_vphy_ind_addr_wr(struct ksz_device *dev, int addr, int reg) @@ -363,13 +564,6 @@ int lan937x_setup(struct dsa_switch *ds) struct ksz_device *dev = ds->priv; int ret; - /* enable Indirect Access from SPI to the VPHY registers */ - ret = lan937x_enable_spi_indirect_access(dev); - if (ret < 0) { - dev_err(dev->dev, "failed to enable spi indirect access"); - return ret; - } - /* The VLAN aware is a global setting. Mixed vlan * filterings are not supported. */ diff --git a/drivers/net/dsa/microchip/lan937x_reg.h b/drivers/net/dsa/microchip/lan937x_reg.h index 2f22a9d01de3..4ec93e421da4 100644 --- a/drivers/net/dsa/microchip/lan937x_reg.h +++ b/drivers/net/dsa/microchip/lan937x_reg.h @@ -37,6 +37,10 @@ #define SW_CLK125_ENB BIT(1) #define SW_CLK25_ENB BIT(0) +#define REG_SW_CFG_STRAP_VAL 0x0200 +#define SW_CASCADE_ID_CFG BIT(15) +#define SW_VPHY_ADD_CFG BIT(0) + /* 2 - PHY Control */ #define REG_SW_CFG_STRAP_OVR 0x0214 #define SW_VPHY_DISABLE BIT(31) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index d84ee1b419a6..086b8b3d5b40 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -21,6 +21,7 @@ #include <linux/gpio/consumer.h> #include <linux/gpio/driver.h> #include <net/dsa.h> +#include <net/pkt_cls.h> #include "mt7530.h" @@ -3146,6 +3147,53 @@ mt753x_conduit_state_change(struct dsa_switch *ds, mt7530_rmw(priv, MT753X_MFC, MT7530_CPU_EN | MT7530_CPU_PORT_MASK, val); } +static int mt753x_tc_setup_qdisc_tbf(struct dsa_switch *ds, int port, + struct tc_tbf_qopt_offload *qopt) +{ + struct tc_tbf_qopt_offload_replace_params *p = &qopt->replace_params; + struct mt7530_priv *priv = ds->priv; + u32 rate = 0; + + switch (qopt->command) { + case TC_TBF_REPLACE: + rate = div_u64(p->rate.rate_bytes_ps, 1000) << 3; /* kbps */ + fallthrough; + case TC_TBF_DESTROY: { + u32 val, tick; + + mt7530_rmw(priv, MT753X_GERLCR, EGR_BC_MASK, + EGR_BC_CRC_IPG_PREAMBLE); + + /* if rate is greater than 10Mbps tick is 1/32 ms, + * 1ms otherwise + */ + tick = rate > 10000 ? 2 : 7; + val = FIELD_PREP(ERLCR_CIR_MASK, (rate >> 5)) | + FIELD_PREP(ERLCR_EN_MASK, !!rate) | + FIELD_PREP(ERLCR_EXP_MASK, tick) | + ERLCR_TBF_MODE_MASK | + FIELD_PREP(ERLCR_MANT_MASK, 0xf); + mt7530_write(priv, MT753X_ERLCR_P(port), val); + break; + } + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int mt753x_setup_tc(struct dsa_switch *ds, int port, + enum tc_setup_type type, void *type_data) +{ + switch (type) { + case TC_SETUP_QDISC_TBF: + return mt753x_tc_setup_qdisc_tbf(ds, port, type_data); + default: + return -EOPNOTSUPP; + } +} + static int mt7988_setup(struct dsa_switch *ds) { struct mt7530_priv *priv = ds->priv; @@ -3193,6 +3241,7 @@ const struct dsa_switch_ops mt7530_switch_ops = { .get_mac_eee = mt753x_get_mac_eee, .set_mac_eee = mt753x_set_mac_eee, .conduit_state_change = mt753x_conduit_state_change, + .port_setup_tc = mt753x_setup_tc, }; EXPORT_SYMBOL_GPL(mt7530_switch_ops); diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 6ad33a9f6b1d..448200689f49 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -248,6 +248,18 @@ enum mt7530_vlan_egress_attr { #define AGE_UNIT_MAX 0xfff #define AGE_UNIT(x) (AGE_UNIT_MASK & (x)) +#define MT753X_ERLCR_P(x) (0x1040 + ((x) * 0x100)) +#define ERLCR_CIR_MASK GENMASK(31, 16) +#define ERLCR_EN_MASK BIT(15) +#define ERLCR_EXP_MASK GENMASK(11, 8) +#define ERLCR_TBF_MODE_MASK BIT(7) +#define ERLCR_MANT_MASK GENMASK(6, 0) + +#define MT753X_GERLCR 0x10e0 +#define EGR_BC_MASK GENMASK(7, 0) +#define EGR_BC_CRC 0x4 /* crc */ +#define EGR_BC_CRC_IPG_PREAMBLE 0x18 /* crc + ipg + preamble */ + /* Register for port STP state control */ #define MT7530_SSP_P(x) (0x2000 + ((x) * 0x100)) #define FID_PST(fid, state) (((state) & 0x3) << ((fid) * 2)) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index c75005b4d86e..3a792f79270d 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1153,42 +1153,37 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip, return value; } -static int mv88e6xxx_stats_get_strings(struct mv88e6xxx_chip *chip, - uint8_t *data, int types) +static void mv88e6xxx_stats_get_strings(struct mv88e6xxx_chip *chip, + uint8_t **data, int types) { const struct mv88e6xxx_hw_stat *stat; - int i, j; + int i; - for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) { + for (i = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) { stat = &mv88e6xxx_hw_stats[i]; - if (stat->type & types) { - memcpy(data + j * ETH_GSTRING_LEN, stat->string, - ETH_GSTRING_LEN); - j++; - } + if (stat->type & types) + ethtool_puts(data, stat->string); } - - return j; } -static int mv88e6095_stats_get_strings(struct mv88e6xxx_chip *chip, - uint8_t *data) +static void mv88e6095_stats_get_strings(struct mv88e6xxx_chip *chip, + uint8_t **data) { - return mv88e6xxx_stats_get_strings(chip, data, - STATS_TYPE_BANK0 | STATS_TYPE_PORT); + mv88e6xxx_stats_get_strings(chip, data, + STATS_TYPE_BANK0 | STATS_TYPE_PORT); } -static int mv88e6250_stats_get_strings(struct mv88e6xxx_chip *chip, - uint8_t *data) +static void mv88e6250_stats_get_strings(struct mv88e6xxx_chip *chip, + uint8_t **data) { - return mv88e6xxx_stats_get_strings(chip, data, STATS_TYPE_BANK0); + mv88e6xxx_stats_get_strings(chip, data, STATS_TYPE_BANK0); } -static int mv88e6320_stats_get_strings(struct mv88e6xxx_chip *chip, - uint8_t *data) +static void mv88e6320_stats_get_strings(struct mv88e6xxx_chip *chip, + uint8_t **data) { - return mv88e6xxx_stats_get_strings(chip, data, - STATS_TYPE_BANK0 | STATS_TYPE_BANK1); + mv88e6xxx_stats_get_strings(chip, data, + STATS_TYPE_BANK0 | STATS_TYPE_BANK1); } static const uint8_t *mv88e6xxx_atu_vtu_stats_strings[] = { @@ -1199,21 +1194,18 @@ static const uint8_t *mv88e6xxx_atu_vtu_stats_strings[] = { "vtu_miss_violation", }; -static void mv88e6xxx_atu_vtu_get_strings(uint8_t *data) +static void mv88e6xxx_atu_vtu_get_strings(uint8_t **data) { unsigned int i; for (i = 0; i < ARRAY_SIZE(mv88e6xxx_atu_vtu_stats_strings); i++) - strscpy(data + i * ETH_GSTRING_LEN, - mv88e6xxx_atu_vtu_stats_strings[i], - ETH_GSTRING_LEN); + ethtool_puts(data, mv88e6xxx_atu_vtu_stats_strings[i]); } static void mv88e6xxx_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data) { struct mv88e6xxx_chip *chip = ds->priv; - int count = 0; if (stringset != ETH_SS_STATS) return; @@ -1221,15 +1213,12 @@ static void mv88e6xxx_get_strings(struct dsa_switch *ds, int port, mv88e6xxx_reg_lock(chip); if (chip->info->ops->stats_get_strings) - count = chip->info->ops->stats_get_strings(chip, data); + chip->info->ops->stats_get_strings(chip, &data); - if (chip->info->ops->serdes_get_strings) { - data += count * ETH_GSTRING_LEN; - count = chip->info->ops->serdes_get_strings(chip, port, data); - } + if (chip->info->ops->serdes_get_strings) + chip->info->ops->serdes_get_strings(chip, port, &data); - data += count * ETH_GSTRING_LEN; - mv88e6xxx_atu_vtu_get_strings(data); + mv88e6xxx_atu_vtu_get_strings(&data); mv88e6xxx_reg_unlock(chip); } diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 48399ab5355a..9fe8e8a7856b 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -606,7 +606,7 @@ struct mv88e6xxx_ops { /* Return the number of strings describing statistics */ int (*stats_get_sset_count)(struct mv88e6xxx_chip *chip); - int (*stats_get_strings)(struct mv88e6xxx_chip *chip, uint8_t *data); + void (*stats_get_strings)(struct mv88e6xxx_chip *chip, uint8_t **data); size_t (*stats_get_stat)(struct mv88e6xxx_chip *chip, int port, const struct mv88e6xxx_hw_stat *stat, uint64_t *data); @@ -633,8 +633,8 @@ struct mv88e6xxx_ops { /* Statistics from the SERDES interface */ int (*serdes_get_sset_count)(struct mv88e6xxx_chip *chip, int port); - int (*serdes_get_strings)(struct mv88e6xxx_chip *chip, int port, - uint8_t *data); + int (*serdes_get_strings)(struct mv88e6xxx_chip *chip, int port, + uint8_t **data); size_t (*serdes_get_stats)(struct mv88e6xxx_chip *chip, int port, uint64_t *data); diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index 01ea53940786..b3330211edbc 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -132,8 +132,8 @@ int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port) return ARRAY_SIZE(mv88e6352_serdes_hw_stats); } -int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip, - int port, uint8_t *data) +int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip, int port, + uint8_t **data) { struct mv88e6352_serdes_hw_stat *stat; int err, i; @@ -144,8 +144,7 @@ int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip, for (i = 0; i < ARRAY_SIZE(mv88e6352_serdes_hw_stats); i++) { stat = &mv88e6352_serdes_hw_stats[i]; - memcpy(data + i * ETH_GSTRING_LEN, stat->string, - ETH_GSTRING_LEN); + ethtool_puts(data, stat->string); } return ARRAY_SIZE(mv88e6352_serdes_hw_stats); } @@ -394,8 +393,8 @@ int mv88e6390_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port) return ARRAY_SIZE(mv88e6390_serdes_hw_stats); } -int mv88e6390_serdes_get_strings(struct mv88e6xxx_chip *chip, - int port, uint8_t *data) +int mv88e6390_serdes_get_strings(struct mv88e6xxx_chip *chip, int port, + uint8_t **data) { struct mv88e6390_serdes_hw_stat *stat; int i; @@ -405,8 +404,7 @@ int mv88e6390_serdes_get_strings(struct mv88e6xxx_chip *chip, for (i = 0; i < ARRAY_SIZE(mv88e6390_serdes_hw_stats); i++) { stat = &mv88e6390_serdes_hw_stats[i]; - memcpy(data + i * ETH_GSTRING_LEN, stat->string, - ETH_GSTRING_LEN); + ethtool_puts(data, stat->string); } return ARRAY_SIZE(mv88e6390_serdes_hw_stats); } diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index ff5c3ab31e15..ad887d8601bc 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -125,13 +125,13 @@ unsigned int mv88e6352_serdes_irq_mapping(struct mv88e6xxx_chip *chip, unsigned int mv88e6390_serdes_irq_mapping(struct mv88e6xxx_chip *chip, int port); int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port); -int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip, - int port, uint8_t *data); +int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip, int port, + uint8_t **data); size_t mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, uint64_t *data); int mv88e6390_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port); -int mv88e6390_serdes_get_strings(struct mv88e6xxx_chip *chip, - int port, uint8_t *data); +int mv88e6390_serdes_get_strings(struct mv88e6xxx_chip *chip, int port, + uint8_t **data); size_t mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, uint64_t *data); diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index f8d8c70642c4..59b4a7240b58 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -673,7 +673,7 @@ qca8k_phy_eth_command(struct qca8k_priv *priv, bool read, int phy, * We therefore need to lock the MDIO bus onto which the switch is * connected. */ - mutex_lock(&priv->bus->mdio_lock); + mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED); /* Actually start the request: * 1. Send mdio master packet diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c index 1135a32e4b7e..66974379334a 100644 --- a/drivers/net/dsa/rzn1_a5psw.c +++ b/drivers/net/dsa/rzn1_a5psw.c @@ -802,10 +802,8 @@ static void a5psw_get_strings(struct dsa_switch *ds, int port, u32 stringset, if (stringset != ETH_SS_STATS) return; - for (u = 0; u < ARRAY_SIZE(a5psw_stats); u++) { - memcpy(data + u * ETH_GSTRING_LEN, a5psw_stats[u].name, - ETH_GSTRING_LEN); - } + for (u = 0; u < ARRAY_SIZE(a5psw_stats); u++) + ethtool_puts(&data, a5psw_stats[u].name); } static void a5psw_get_ethtool_stats(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/sja1105/sja1105_ethtool.c b/drivers/net/dsa/sja1105/sja1105_ethtool.c index decc6c931dc1..2ea64b1d026d 100644 --- a/drivers/net/dsa/sja1105/sja1105_ethtool.c +++ b/drivers/net/dsa/sja1105/sja1105_ethtool.c @@ -586,7 +586,6 @@ void sja1105_get_strings(struct dsa_switch *ds, int port, { struct sja1105_private *priv = ds->priv; enum sja1105_counter_index max_ctr, i; - char *p = data; if (stringset != ETH_SS_STATS) return; @@ -597,10 +596,8 @@ void sja1105_get_strings(struct dsa_switch *ds, int port, else max_ctr = __MAX_SJA1105PQRS_PORT_COUNTER; - for (i = 0; i < max_ctr; i++) { - strscpy(p, sja1105_port_counters[i].name, ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < max_ctr; i++) + ethtool_puts(&data, sja1105_port_counters[i].name); } int sja1105_get_sset_count(struct dsa_switch *ds, int port, int sset) diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c index de3b768f2ff9..4dbcc49a9e52 100644 --- a/drivers/net/dsa/xrs700x/xrs700x.c +++ b/drivers/net/dsa/xrs700x/xrs700x.c @@ -91,10 +91,8 @@ static void xrs700x_get_strings(struct dsa_switch *ds, int port, if (stringset != ETH_SS_STATS) return; - for (i = 0; i < ARRAY_SIZE(xrs700x_mibs); i++) { - strscpy(data, xrs700x_mibs[i].name, ETH_GSTRING_LEN); - data += ETH_GSTRING_LEN; - } + for (i = 0; i < ARRAY_SIZE(xrs700x_mibs); i++) + ethtool_puts(&data, xrs700x_mibs[i].name); } static int xrs700x_get_sset_count(struct dsa_switch *ds, int port, int sset) diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index e9c5e1e11fa0..005d79975f3b 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -168,22 +168,21 @@ static int __init dummy_init_module(void) { int i, err = 0; - down_write(&pernet_ops_rwsem); - rtnl_lock(); - err = __rtnl_link_register(&dummy_link_ops); + err = rtnl_link_register(&dummy_link_ops); if (err < 0) - goto out; + return err; + + rtnl_net_lock(&init_net); for (i = 0; i < numdummies && !err; i++) { err = dummy_init_one(); cond_resched(); } - if (err < 0) - __rtnl_link_unregister(&dummy_link_ops); -out: - rtnl_unlock(); - up_write(&pernet_ops_rwsem); + rtnl_net_unlock(&init_net); + + if (err < 0) + rtnl_link_unregister(&dummy_link_ops); return err; } diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index d958cda9e58b..66445617fbfb 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -763,25 +763,16 @@ static int ena_com_wait_and_process_admin_cq_interrupts(struct ena_comp_ctx *com if (comp_ctx->status == ENA_CMD_COMPLETED) { netdev_err(admin_queue->ena_dev->net_device, - "The ena device sent a completion but the driver didn't receive a MSI-X interrupt (cmd %d), autopolling mode is %s\n", - comp_ctx->cmd_opcode, admin_queue->auto_polling ? "ON" : "OFF"); - /* Check if fallback to polling is enabled */ - if (admin_queue->auto_polling) - admin_queue->polling = true; + "The ena device sent a completion but the driver didn't receive a MSI-X interrupt (cmd %d)\n", + comp_ctx->cmd_opcode); } else { netdev_err(admin_queue->ena_dev->net_device, "The ena device didn't send a completion for the admin cmd %d status %d\n", comp_ctx->cmd_opcode, comp_ctx->status); } - /* Check if shifted to polling mode. - * This will happen if there is a completion without an interrupt - * and autopolling mode is enabled. Continuing normal execution in such case - */ - if (!admin_queue->polling) { - admin_queue->running_state = false; - ret = -ETIME; - goto err; - } + admin_queue->running_state = false; + ret = -ETIME; + goto err; } ret = ena_com_comp_status_to_errno(admin_queue, comp_ctx->comp_status); @@ -1650,12 +1641,6 @@ void ena_com_set_admin_polling_mode(struct ena_com_dev *ena_dev, bool polling) ena_dev->admin_queue.polling = polling; } -void ena_com_set_admin_auto_polling_mode(struct ena_com_dev *ena_dev, - bool polling) -{ - ena_dev->admin_queue.auto_polling = polling; -} - int ena_com_mmio_reg_read_request_init(struct ena_com_dev *ena_dev) { struct ena_com_mmio_read *mmio_read = &ena_dev->mmio_read; @@ -2198,21 +2183,6 @@ int ena_com_get_ena_srd_info(struct ena_com_dev *ena_dev, return ret; } -int ena_com_get_dev_basic_stats(struct ena_com_dev *ena_dev, - struct ena_admin_basic_stats *stats) -{ - struct ena_com_stats_ctx ctx; - int ret; - - memset(&ctx, 0x0, sizeof(ctx)); - ret = ena_get_dev_stats(ena_dev, &ctx, ENA_ADMIN_GET_STATS_TYPE_BASIC); - if (likely(ret == 0)) - memcpy(stats, &ctx.get_resp.u.basic_stats, - sizeof(ctx.get_resp.u.basic_stats)); - - return ret; -} - int ena_com_get_customer_metrics(struct ena_com_dev *ena_dev, char *buffer, u32 len) { struct ena_admin_aq_get_stats_cmd *get_cmd; @@ -2289,24 +2259,6 @@ int ena_com_set_dev_mtu(struct ena_com_dev *ena_dev, u32 mtu) return ret; } -int ena_com_get_offload_settings(struct ena_com_dev *ena_dev, - struct ena_admin_feature_offload_desc *offload) -{ - int ret; - struct ena_admin_get_feat_resp resp; - - ret = ena_com_get_feature(ena_dev, &resp, - ENA_ADMIN_STATELESS_OFFLOAD_CONFIG, 0); - if (unlikely(ret)) { - netdev_err(ena_dev->net_device, "Failed to get offload capabilities %d\n", ret); - return ret; - } - - memcpy(offload, &resp.u.offload, sizeof(resp.u.offload)); - - return 0; -} - int ena_com_set_hash_function(struct ena_com_dev *ena_dev) { struct ena_com_admin_queue *admin_queue = &ena_dev->admin_queue; diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h index a372c5e768a7..9414e93d107b 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_com.h @@ -224,9 +224,6 @@ struct ena_com_admin_queue { /* Indicate if the admin queue should poll for completion */ bool polling; - /* Define if fallback to polling mode should occur */ - bool auto_polling; - u16 curr_cmd_id; /* Indicate that the ena was initialized and can @@ -493,17 +490,6 @@ bool ena_com_get_admin_running_state(struct ena_com_dev *ena_dev); */ void ena_com_set_admin_polling_mode(struct ena_com_dev *ena_dev, bool polling); -/* ena_com_set_admin_auto_polling_mode - Enable autoswitch to polling mode - * @ena_dev: ENA communication layer struct - * @polling: Enable/Disable polling mode - * - * Set the autopolling mode. - * If autopolling is on: - * In case of missing interrupt when data is available switch to polling. - */ -void ena_com_set_admin_auto_polling_mode(struct ena_com_dev *ena_dev, - bool polling); - /* ena_com_admin_q_comp_intr_handler - admin queue interrupt handler * @ena_dev: ENA communication layer struct * @@ -591,15 +577,6 @@ int ena_com_set_aenq_config(struct ena_com_dev *ena_dev, u32 groups_flag); int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev, struct ena_com_dev_get_features_ctx *get_feat_ctx); -/* ena_com_get_dev_basic_stats - Get device basic statistics - * @ena_dev: ENA communication layer struct - * @stats: stats return value - * - * @return: 0 on Success and negative value otherwise. - */ -int ena_com_get_dev_basic_stats(struct ena_com_dev *ena_dev, - struct ena_admin_basic_stats *stats); - /* ena_com_get_eni_stats - Get extended network interface statistics * @ena_dev: ENA communication layer struct * @stats: stats return value @@ -635,15 +612,6 @@ int ena_com_get_customer_metrics(struct ena_com_dev *ena_dev, char *buffer, u32 */ int ena_com_set_dev_mtu(struct ena_com_dev *ena_dev, u32 mtu); -/* ena_com_get_offload_settings - Retrieve the device offloads capabilities - * @ena_dev: ENA communication layer struct - * @offlad: offload return value - * - * @return: 0 on Success and negative value otherwise. - */ -int ena_com_get_offload_settings(struct ena_com_dev *ena_dev, - struct ena_admin_feature_offload_desc *offload); - /* ena_com_rss_init - Init RSS * @ena_dev: ENA communication layer struct * @log_size: indirection log size diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index 60fb35ec4b15..a3c934c3de71 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -1129,22 +1129,18 @@ static void ena_dump_stats_ex(struct ena_adapter *adapter, u8 *buf) return; } - strings_buf = devm_kcalloc(&adapter->pdev->dev, - ETH_GSTRING_LEN, strings_num, - GFP_ATOMIC); + strings_buf = kcalloc(strings_num, ETH_GSTRING_LEN, GFP_ATOMIC); if (!strings_buf) { netif_err(adapter, drv, netdev, "Failed to allocate strings_buf\n"); return; } - data_buf = devm_kcalloc(&adapter->pdev->dev, - strings_num, sizeof(u64), - GFP_ATOMIC); + data_buf = kcalloc(strings_num, sizeof(u64), GFP_ATOMIC); if (!data_buf) { netif_err(adapter, drv, netdev, "Failed to allocate data buf\n"); - devm_kfree(&adapter->pdev->dev, strings_buf); + kfree(strings_buf); return; } @@ -1166,8 +1162,8 @@ static void ena_dump_stats_ex(struct ena_adapter *adapter, u8 *buf) strings_buf + i * ETH_GSTRING_LEN, data_buf[i]); - devm_kfree(&adapter->pdev->dev, strings_buf); - devm_kfree(&adapter->pdev->dev, data_buf); + kfree(strings_buf); + kfree(data_buf); } void ena_dump_stats_to_buf(struct ena_adapter *adapter, u8 *buf) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 96df20854eb9..63c8a2328142 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1383,7 +1383,7 @@ static void ena_adjust_adaptive_rx_intr_moderation(struct ena_napi *ena_napi) rx_ring->rx_stats.bytes, &dim_sample); - net_dim(&ena_napi->dim, dim_sample); + net_dim(&ena_napi->dim, &dim_sample); rx_ring->per_napi_packets = 0; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 43c71f6b314f..08630ee94251 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -162,8 +162,8 @@ int aq_pci_func_alloc_irq(struct aq_nic_s *self, unsigned int i, self->msix_entry_mask |= (1 << i); if (pdev->msix_enabled && affinity_mask) - irq_set_affinity_hint(pci_irq_vector(pdev, i), - affinity_mask); + irq_update_affinity_hint(pci_irq_vector(pdev, i), + affinity_mask); } return err; @@ -187,7 +187,7 @@ void aq_pci_func_free_irqs(struct aq_nic_s *self) continue; if (pdev->msix_enabled) - irq_set_affinity_hint(pci_irq_vector(pdev, i), NULL); + irq_update_affinity_hint(pci_irq_vector(pdev, i), NULL); free_irq(pci_irq_vector(pdev, i), irq_data); self->msix_entry_mask &= ~(1U << i); } diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 31ee477dd131..8283aeee35fb 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -111,6 +111,7 @@ static void arc_emac_tx_clean(struct net_device *ndev) { struct arc_emac_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; + struct device *dev = ndev->dev.parent; unsigned int i; for (i = 0; i < TX_BD_NUM; i++) { @@ -140,7 +141,7 @@ static void arc_emac_tx_clean(struct net_device *ndev) stats->tx_bytes += skb->len; } - dma_unmap_single(&ndev->dev, dma_unmap_addr(tx_buff, addr), + dma_unmap_single(dev, dma_unmap_addr(tx_buff, addr), dma_unmap_len(tx_buff, len), DMA_TO_DEVICE); /* return the sk_buff to system */ @@ -174,6 +175,7 @@ static void arc_emac_tx_clean(struct net_device *ndev) static int arc_emac_rx(struct net_device *ndev, int budget) { struct arc_emac_priv *priv = netdev_priv(ndev); + struct device *dev = ndev->dev.parent; unsigned int work_done; for (work_done = 0; work_done < budget; work_done++) { @@ -223,9 +225,9 @@ static int arc_emac_rx(struct net_device *ndev, int budget) continue; } - addr = dma_map_single(&ndev->dev, (void *)skb->data, + addr = dma_map_single(dev, (void *)skb->data, EMAC_BUFFER_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(&ndev->dev, addr)) { + if (dma_mapping_error(dev, addr)) { if (net_ratelimit()) netdev_err(ndev, "cannot map dma buffer\n"); dev_kfree_skb(skb); @@ -237,7 +239,7 @@ static int arc_emac_rx(struct net_device *ndev, int budget) } /* unmap previosly mapped skb */ - dma_unmap_single(&ndev->dev, dma_unmap_addr(rx_buff, addr), + dma_unmap_single(dev, dma_unmap_addr(rx_buff, addr), dma_unmap_len(rx_buff, len), DMA_FROM_DEVICE); pktlen = info & LEN_MASK; @@ -423,6 +425,7 @@ static int arc_emac_open(struct net_device *ndev) { struct arc_emac_priv *priv = netdev_priv(ndev); struct phy_device *phy_dev = ndev->phydev; + struct device *dev = ndev->dev.parent; int i; phy_dev->autoneg = AUTONEG_ENABLE; @@ -445,9 +448,9 @@ static int arc_emac_open(struct net_device *ndev) if (unlikely(!rx_buff->skb)) return -ENOMEM; - addr = dma_map_single(&ndev->dev, (void *)rx_buff->skb->data, + addr = dma_map_single(dev, (void *)rx_buff->skb->data, EMAC_BUFFER_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(&ndev->dev, addr)) { + if (dma_mapping_error(dev, addr)) { netdev_err(ndev, "cannot dma map\n"); dev_kfree_skb(rx_buff->skb); return -ENOMEM; @@ -548,6 +551,7 @@ static void arc_emac_set_rx_mode(struct net_device *ndev) static void arc_free_tx_queue(struct net_device *ndev) { struct arc_emac_priv *priv = netdev_priv(ndev); + struct device *dev = ndev->dev.parent; unsigned int i; for (i = 0; i < TX_BD_NUM; i++) { @@ -555,7 +559,7 @@ static void arc_free_tx_queue(struct net_device *ndev) struct buffer_state *tx_buff = &priv->tx_buff[i]; if (tx_buff->skb) { - dma_unmap_single(&ndev->dev, + dma_unmap_single(dev, dma_unmap_addr(tx_buff, addr), dma_unmap_len(tx_buff, len), DMA_TO_DEVICE); @@ -579,6 +583,7 @@ static void arc_free_tx_queue(struct net_device *ndev) static void arc_free_rx_queue(struct net_device *ndev) { struct arc_emac_priv *priv = netdev_priv(ndev); + struct device *dev = ndev->dev.parent; unsigned int i; for (i = 0; i < RX_BD_NUM; i++) { @@ -586,7 +591,7 @@ static void arc_free_rx_queue(struct net_device *ndev) struct buffer_state *rx_buff = &priv->rx_buff[i]; if (rx_buff->skb) { - dma_unmap_single(&ndev->dev, + dma_unmap_single(dev, dma_unmap_addr(rx_buff, addr), dma_unmap_len(rx_buff, len), DMA_FROM_DEVICE); @@ -679,6 +684,7 @@ static netdev_tx_t arc_emac_tx(struct sk_buff *skb, struct net_device *ndev) unsigned int len, *txbd_curr = &priv->txbd_curr; struct net_device_stats *stats = &ndev->stats; __le32 *info = &priv->txbd[*txbd_curr].info; + struct device *dev = ndev->dev.parent; dma_addr_t addr; if (skb_padto(skb, ETH_ZLEN)) @@ -692,10 +698,9 @@ static netdev_tx_t arc_emac_tx(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_BUSY; } - addr = dma_map_single(&ndev->dev, (void *)skb->data, len, - DMA_TO_DEVICE); + addr = dma_map_single(dev, (void *)skb->data, len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(&ndev->dev, addr))) { + if (unlikely(dma_mapping_error(dev, addr))) { stats->tx_dropped++; stats->tx_errors++; dev_kfree_skb_any(skb); diff --git a/drivers/net/ethernet/arc/emac_mdio.c b/drivers/net/ethernet/arc/emac_mdio.c index 87f40c2ba904..078b1a72c161 100644 --- a/drivers/net/ethernet/arc/emac_mdio.c +++ b/drivers/net/ethernet/arc/emac_mdio.c @@ -133,6 +133,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv) struct arc_emac_mdio_bus_data *data = &priv->bus_data; struct device_node *np = priv->dev->of_node; const char *name = "Synopsys MII Bus"; + struct device_node *mdio_node; struct mii_bus *bus; int error; @@ -164,7 +165,13 @@ int arc_mdio_probe(struct arc_emac_priv *priv) snprintf(bus->id, MII_BUS_ID_SIZE, "%s", bus->name); - error = of_mdiobus_register(bus, priv->dev->of_node); + /* Backwards compatibility for EMAC nodes without MDIO subnode. */ + mdio_node = of_get_child_by_name(np, "mdio"); + if (!mdio_node) + mdio_node = of_node_get(np); + + error = of_mdiobus_register(bus, mdio_node); + of_node_put(mdio_node); if (error) { mdiobus_free(bus); return dev_err_probe(priv->dev, error, diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c index 67928b5d8a26..9da5ae29a105 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c @@ -101,14 +101,14 @@ static int bcmasp_get_sset_count(struct net_device *dev, int string_set) static void bcmasp_get_strings(struct net_device *dev, u32 stringset, u8 *data) { + const char *str; unsigned int i; switch (stringset) { case ETH_SS_STATS: for (i = 0; i < BCMASP_STATS_LEN; i++) { - memcpy(data + i * ETH_GSTRING_LEN, - bcmasp_gstrings_stats[i].stat_string, - ETH_GSTRING_LEN); + str = bcmasp_gstrings_stats[i].stat_string; + ethtool_puts(&data, str); } break; default: diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index e5e03aaa49f9..65e3a0656a4c 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1339,14 +1339,14 @@ static int bcm_enet_get_sset_count(struct net_device *netdev, static void bcm_enet_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { + const char *str; int i; switch (stringset) { case ETH_SS_STATS: for (i = 0; i < BCM_ENET_STATS_LEN; i++) { - memcpy(data + i * ETH_GSTRING_LEN, - bcm_enet_gstrings_stats[i].stat_string, - ETH_GSTRING_LEN); + str = bcm_enet_gstrings_stats[i].stat_string; + ethtool_puts(&data, str); } break; } @@ -2503,14 +2503,14 @@ static const struct bcm_enet_stats bcm_enetsw_gstrings_stats[] = { static void bcm_enetsw_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { + const char *str; int i; switch (stringset) { case ETH_SS_STATS: for (i = 0; i < BCM_ENETSW_STATS_LEN; i++) { - memcpy(data + i * ETH_GSTRING_LEN, - bcm_enetsw_gstrings_stats[i].stat_string, - ETH_GSTRING_LEN); + str = bcm_enetsw_gstrings_stats[i].stat_string; + ethtool_puts(&data, str); } break; } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index caff6e87a488..42672c63f108 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -346,32 +346,22 @@ static void bcm_sysport_get_strings(struct net_device *dev, { struct bcm_sysport_priv *priv = netdev_priv(dev); const struct bcm_sysport_stats *s; - char buf[128]; - int i, j; + int i; switch (stringset) { case ETH_SS_STATS: - for (i = 0, j = 0; i < BCM_SYSPORT_STATS_LEN; i++) { + for (i = 0; i < BCM_SYSPORT_STATS_LEN; i++) { s = &bcm_sysport_gstrings_stats[i]; if (priv->is_lite && !bcm_sysport_lite_stat_valid(s->type)) continue; - memcpy(data + j * ETH_GSTRING_LEN, s->stat_string, - ETH_GSTRING_LEN); - j++; + ethtool_puts(&data, s->stat_string); } for (i = 0; i < dev->num_tx_queues; i++) { - snprintf(buf, sizeof(buf), "txq%d_packets", i); - memcpy(data + j * ETH_GSTRING_LEN, buf, - ETH_GSTRING_LEN); - j++; - - snprintf(buf, sizeof(buf), "txq%d_bytes", i); - memcpy(data + j * ETH_GSTRING_LEN, buf, - ETH_GSTRING_LEN); - j++; + ethtool_sprintf(&data, "txq%d_packets", i); + ethtool_sprintf(&data, "txq%d_bytes", i); } break; default: @@ -1029,7 +1019,7 @@ static int bcm_sysport_poll(struct napi_struct *napi, int budget) if (priv->dim.use_dim) { dim_update_sample(priv->dim.event_ctr, priv->dim.packets, priv->dim.bytes, &dim_sample); - net_dim(&priv->dim.dim, dim_sample); + net_dim(&priv->dim.dim, &dim_sample); } return work_done; diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 6ffdc4229407..a461ec612e95 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1367,8 +1367,7 @@ static void bgmac_get_strings(struct net_device *dev, u32 stringset, return; for (i = 0; i < BGMAC_STATS_LEN; i++) - strscpy(data + i * ETH_GSTRING_LEN, - bgmac_get_strings_stats[i].name, ETH_GSTRING_LEN); + ethtool_puts(&data, bgmac_get_strings_stats[i].name); } static void bgmac_get_ethtool_stats(struct net_device *dev, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index adf7b6b94941..44199855ebfb 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -39,34 +39,34 @@ static const struct { int size; char string[ETH_GSTRING_LEN]; } bnx2x_q_stats_arr[] = { -/* 1 */ { Q_STATS_OFFSET32(total_bytes_received_hi), 8, "[%s]: rx_bytes" }, +/* 1 */ { Q_STATS_OFFSET32(total_bytes_received_hi), 8, "[%d]: rx_bytes" }, { Q_STATS_OFFSET32(total_unicast_packets_received_hi), - 8, "[%s]: rx_ucast_packets" }, + 8, "[%d]: rx_ucast_packets" }, { Q_STATS_OFFSET32(total_multicast_packets_received_hi), - 8, "[%s]: rx_mcast_packets" }, + 8, "[%d]: rx_mcast_packets" }, { Q_STATS_OFFSET32(total_broadcast_packets_received_hi), - 8, "[%s]: rx_bcast_packets" }, - { Q_STATS_OFFSET32(no_buff_discard_hi), 8, "[%s]: rx_discards" }, + 8, "[%d]: rx_bcast_packets" }, + { Q_STATS_OFFSET32(no_buff_discard_hi), 8, "[%d]: rx_discards" }, { Q_STATS_OFFSET32(rx_err_discard_pkt), - 4, "[%s]: rx_phy_ip_err_discards"}, + 4, "[%d]: rx_phy_ip_err_discards"}, { Q_STATS_OFFSET32(rx_skb_alloc_failed), - 4, "[%s]: rx_skb_alloc_discard" }, - { Q_STATS_OFFSET32(hw_csum_err), 4, "[%s]: rx_csum_offload_errors" }, - { Q_STATS_OFFSET32(driver_xoff), 4, "[%s]: tx_exhaustion_events" }, - { Q_STATS_OFFSET32(total_bytes_transmitted_hi), 8, "[%s]: tx_bytes" }, + 4, "[%d]: rx_skb_alloc_discard" }, + { Q_STATS_OFFSET32(hw_csum_err), 4, "[%d]: rx_csum_offload_errors" }, + { Q_STATS_OFFSET32(driver_xoff), 4, "[%d]: tx_exhaustion_events" }, + { Q_STATS_OFFSET32(total_bytes_transmitted_hi), 8, "[%d]: tx_bytes" }, /* 10 */{ Q_STATS_OFFSET32(total_unicast_packets_transmitted_hi), - 8, "[%s]: tx_ucast_packets" }, + 8, "[%d]: tx_ucast_packets" }, { Q_STATS_OFFSET32(total_multicast_packets_transmitted_hi), - 8, "[%s]: tx_mcast_packets" }, + 8, "[%d]: tx_mcast_packets" }, { Q_STATS_OFFSET32(total_broadcast_packets_transmitted_hi), - 8, "[%s]: tx_bcast_packets" }, + 8, "[%d]: tx_bcast_packets" }, { Q_STATS_OFFSET32(total_tpa_aggregations_hi), - 8, "[%s]: tpa_aggregations" }, + 8, "[%d]: tpa_aggregations" }, { Q_STATS_OFFSET32(total_tpa_aggregated_frames_hi), - 8, "[%s]: tpa_aggregated_frames"}, - { Q_STATS_OFFSET32(total_tpa_bytes_hi), 8, "[%s]: tpa_bytes"}, + 8, "[%d]: tpa_aggregated_frames"}, + { Q_STATS_OFFSET32(total_tpa_bytes_hi), 8, "[%d]: tpa_bytes"}, { Q_STATS_OFFSET32(driver_filtered_tx_pkt), - 4, "[%s]: driver_filtered_tx_pkt" } + 4, "[%d]: driver_filtered_tx_pkt" } }; #define BNX2X_NUM_Q_STATS ARRAY_SIZE(bnx2x_q_stats_arr) @@ -3184,49 +3184,43 @@ static u32 bnx2x_get_private_flags(struct net_device *dev) static void bnx2x_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { struct bnx2x *bp = netdev_priv(dev); - int i, j, k, start; - char queue_name[MAX_QUEUE_NAME_LEN+1]; + const char *str; + int i, j, start; switch (stringset) { case ETH_SS_STATS: - k = 0; if (is_multi(bp)) { for_each_eth_queue(bp, i) { - memset(queue_name, 0, sizeof(queue_name)); - snprintf(queue_name, sizeof(queue_name), - "%d", i); - for (j = 0; j < BNX2X_NUM_Q_STATS; j++) - snprintf(buf + (k + j)*ETH_GSTRING_LEN, - ETH_GSTRING_LEN, - bnx2x_q_stats_arr[j].string, - queue_name); - k += BNX2X_NUM_Q_STATS; + for (j = 0; j < BNX2X_NUM_Q_STATS; j++) { + str = bnx2x_q_stats_arr[j].string; + ethtool_sprintf(&buf, str, i); + } } } - for (i = 0, j = 0; i < BNX2X_NUM_STATS; i++) { + for (i = 0; i < BNX2X_NUM_STATS; i++) { if (HIDE_PORT_STAT(bp) && IS_PORT_STAT(i)) continue; - strcpy(buf + (k + j)*ETH_GSTRING_LEN, - bnx2x_stats_arr[i].string); - j++; + ethtool_puts(&buf, bnx2x_stats_arr[i].string); } break; case ETH_SS_TEST: + if (IS_VF(bp)) + break; /* First 4 tests cannot be done in MF mode */ if (!IS_MF(bp)) start = 0; else start = 4; - memcpy(buf, bnx2x_tests_str_arr + start, - ETH_GSTRING_LEN * BNX2X_NUM_TESTS(bp)); + for (i = start; i < BNX2X_NUM_TESTS_SF; i++) + ethtool_puts(&buf, bnx2x_tests_str_arr[i]); break; case ETH_SS_PRIV_FLAGS: - memcpy(buf, bnx2x_private_arr, - ETH_GSTRING_LEN * BNX2X_PRI_FLAG_LEN); + for (i = 0; i < BNX2X_PRI_FLAG_LEN; i++) + ethtool_puts(&buf, bnx2x_private_arr[i]); break; } } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6dd6541d8619..4c1302a8f72d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -864,6 +864,11 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) bnapi->events &= ~BNXT_TX_CMP_EVENT; } +static bool bnxt_separate_head_pool(void) +{ + return PAGE_SIZE > BNXT_RX_PAGE_SIZE; +} + static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping, struct bnxt_rx_ring_info *rxr, unsigned int *offset, @@ -886,27 +891,19 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping, } static inline u8 *__bnxt_alloc_rx_frag(struct bnxt *bp, dma_addr_t *mapping, + struct bnxt_rx_ring_info *rxr, gfp_t gfp) { - u8 *data; - struct pci_dev *pdev = bp->pdev; + unsigned int offset; + struct page *page; - if (gfp == GFP_ATOMIC) - data = napi_alloc_frag(bp->rx_buf_size); - else - data = netdev_alloc_frag(bp->rx_buf_size); - if (!data) + page = page_pool_alloc_frag(rxr->head_pool, &offset, + bp->rx_buf_size, gfp); + if (!page) return NULL; - *mapping = dma_map_single_attrs(&pdev->dev, data + bp->rx_dma_offset, - bp->rx_buf_use_size, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); - - if (dma_mapping_error(&pdev->dev, *mapping)) { - skb_free_frag(data); - data = NULL; - } - return data; + *mapping = page_pool_get_dma_addr(page) + bp->rx_dma_offset + offset; + return page_address(page) + offset; } int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, @@ -928,7 +925,7 @@ int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, rx_buf->data = page; rx_buf->data_ptr = page_address(page) + offset + bp->rx_offset; } else { - u8 *data = __bnxt_alloc_rx_frag(bp, &mapping, gfp); + u8 *data = __bnxt_alloc_rx_frag(bp, &mapping, rxr, gfp); if (!data) return -ENOMEM; @@ -1179,13 +1176,14 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp, } skb = napi_build_skb(data, bp->rx_buf_size); - dma_unmap_single_attrs(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size, - bp->rx_dir, DMA_ATTR_WEAK_ORDERING); + dma_sync_single_for_cpu(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size, + bp->rx_dir); if (!skb) { - skb_free_frag(data); + page_pool_free_va(rxr->head_pool, data, true); return NULL; } + skb_mark_for_recycle(skb); skb_reserve(skb, bp->rx_offset); skb_put(skb, offset_and_len & 0xffff); return skb; @@ -1840,7 +1838,8 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, u8 *new_data; dma_addr_t new_mapping; - new_data = __bnxt_alloc_rx_frag(bp, &new_mapping, GFP_ATOMIC); + new_data = __bnxt_alloc_rx_frag(bp, &new_mapping, rxr, + GFP_ATOMIC); if (!new_data) { bnxt_abort_tpa(cpr, idx, agg_bufs); cpr->sw_stats->rx.rx_oom_discards += 1; @@ -1852,16 +1851,16 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, tpa_info->mapping = new_mapping; skb = napi_build_skb(data, bp->rx_buf_size); - dma_unmap_single_attrs(&bp->pdev->dev, mapping, - bp->rx_buf_use_size, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); + dma_sync_single_for_cpu(&bp->pdev->dev, mapping, + bp->rx_buf_use_size, bp->rx_dir); if (!skb) { - skb_free_frag(data); + page_pool_free_va(rxr->head_pool, data, true); bnxt_abort_tpa(cpr, idx, agg_bufs); cpr->sw_stats->rx.rx_oom_discards += 1; return NULL; } + skb_mark_for_recycle(skb); skb_reserve(skb, bp->rx_offset); skb_put(skb, len); } @@ -2254,11 +2253,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) { struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; - unsigned long flags; - spin_lock_irqsave(&ptp->ptp_lock, flags); - ns = timecounter_cyc2time(&ptp->tc, ts); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + ns = bnxt_timecounter_cyc2time(ptp, ts); memset(skb_hwtstamps(skb), 0, sizeof(*skb_hwtstamps(skb))); skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ns); @@ -2764,12 +2760,12 @@ static int bnxt_async_event_process(struct bnxt *bp, if (!ptp) goto async_event_process_exit; - spin_lock_irqsave(&ptp->ptp_lock, flags); bnxt_ptp_update_current_time(bp); ns = (((u64)BNXT_EVENT_PHC_RTC_UPDATE(data1) << BNXT_PHC_BITS) | ptp->current_time); + write_seqlock_irqsave(&ptp->ptp_lock, flags); bnxt_ptp_rtc_timecounter_init(ptp, ns); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + write_sequnlock_irqrestore(&ptp->ptp_lock, flags); } break; } @@ -3102,7 +3098,7 @@ static int bnxt_poll(struct napi_struct *napi, int budget) cpr->rx_packets, cpr->rx_bytes, &dim_sample); - net_dim(&cpr->dim, dim_sample); + net_dim(&cpr->dim, &dim_sample); } return work_done; } @@ -3233,7 +3229,7 @@ poll_done: cpr_rx->rx_packets, cpr_rx->rx_bytes, &dim_sample); - net_dim(&cpr->dim, dim_sample); + net_dim(&cpr->dim, &dim_sample); } return work_done; } @@ -3311,28 +3307,22 @@ static void bnxt_free_tx_skbs(struct bnxt *bp) static void bnxt_free_one_rx_ring(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) { - struct pci_dev *pdev = bp->pdev; int i, max_idx; max_idx = bp->rx_nr_pages * RX_DESC_CNT; for (i = 0; i < max_idx; i++) { struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[i]; - dma_addr_t mapping = rx_buf->mapping; void *data = rx_buf->data; if (!data) continue; rx_buf->data = NULL; - if (BNXT_RX_PAGE_MODE(bp)) { + if (BNXT_RX_PAGE_MODE(bp)) page_pool_recycle_direct(rxr->page_pool, data); - } else { - dma_unmap_single_attrs(&pdev->dev, mapping, - bp->rx_buf_use_size, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); - skb_free_frag(data); - } + else + page_pool_free_va(rxr->head_pool, data, true); } } @@ -3359,7 +3349,6 @@ static void bnxt_free_one_rx_agg_ring(struct bnxt *bp, struct bnxt_rx_ring_info static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr]; - struct pci_dev *pdev = bp->pdev; struct bnxt_tpa_idx_map *map; int i; @@ -3373,13 +3362,8 @@ static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr) if (!data) continue; - dma_unmap_single_attrs(&pdev->dev, tpa_info->mapping, - bp->rx_buf_use_size, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); - tpa_info->data = NULL; - - skb_free_frag(data); + page_pool_free_va(rxr->head_pool, data, false); } skip_rx_tpa_free: @@ -3595,7 +3579,9 @@ static void bnxt_free_rx_rings(struct bnxt *bp) xdp_rxq_info_unreg(&rxr->xdp_rxq); page_pool_destroy(rxr->page_pool); - rxr->page_pool = NULL; + if (rxr->page_pool != rxr->head_pool) + page_pool_destroy(rxr->head_pool); + rxr->page_pool = rxr->head_pool = NULL; kfree(rxr->rx_agg_bmap); rxr->rx_agg_bmap = NULL; @@ -3613,6 +3599,7 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, int numa_node) { struct page_pool_params pp = { 0 }; + struct page_pool *pool; pp.pool_size = bp->rx_agg_ring_size; if (BNXT_RX_PAGE_MODE(bp)) @@ -3625,14 +3612,25 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, pp.max_len = PAGE_SIZE; pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; - rxr->page_pool = page_pool_create(&pp); - if (IS_ERR(rxr->page_pool)) { - int err = PTR_ERR(rxr->page_pool); + pool = page_pool_create(&pp); + if (IS_ERR(pool)) + return PTR_ERR(pool); + rxr->page_pool = pool; - rxr->page_pool = NULL; - return err; + if (bnxt_separate_head_pool()) { + pp.pool_size = max(bp->rx_ring_size, 1024); + pool = page_pool_create(&pp); + if (IS_ERR(pool)) + goto err_destroy_pp; } + rxr->head_pool = pool; + return 0; + +err_destroy_pp: + page_pool_destroy(rxr->page_pool); + rxr->page_pool = NULL; + return PTR_ERR(pool); } static int bnxt_alloc_rx_rings(struct bnxt *bp) @@ -4183,7 +4181,8 @@ static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr) u8 *data; for (i = 0; i < bp->max_tpa; i++) { - data = __bnxt_alloc_rx_frag(bp, &mapping, GFP_KERNEL); + data = __bnxt_alloc_rx_frag(bp, &mapping, rxr, + GFP_KERNEL); if (!data) return -ENOMEM; @@ -10885,7 +10884,7 @@ static void bnxt_free_irq(struct bnxt *bp) irq = &bp->irq_tbl[map_idx]; if (irq->requested) { if (irq->have_cpumask) { - irq_set_affinity_hint(irq->vector, NULL); + irq_update_affinity_hint(irq->vector, NULL); free_cpumask_var(irq->cpu_mask); irq->have_cpumask = 0; } @@ -10940,10 +10939,10 @@ static int bnxt_request_irq(struct bnxt *bp) irq->have_cpumask = 1; cpumask_set_cpu(cpumask_local_spread(i, numa_node), irq->cpu_mask); - rc = irq_set_affinity_hint(irq->vector, irq->cpu_mask); + rc = irq_update_affinity_hint(irq->vector, irq->cpu_mask); if (rc) { netdev_warn(bp->dev, - "Set affinity failed, IRQ = %d\n", + "Update affinity hint failed, IRQ = %d\n", irq->vector); break; } @@ -13496,12 +13495,13 @@ static void bnxt_force_fw_reset(struct bnxt *bp) test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) return; + /* we have to serialize with bnxt_refclk_read()*/ if (ptp) { unsigned long flags; - spin_lock_irqsave(&ptp->ptp_lock, flags); + write_seqlock_irqsave(&ptp->ptp_lock, flags); set_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + write_sequnlock_irqrestore(&ptp->ptp_lock, flags); } else { set_bit(BNXT_STATE_IN_FW_RESET, &bp->state); } @@ -13565,12 +13565,13 @@ void bnxt_fw_reset(struct bnxt *bp) struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; int n = 0, tmo; + /* we have to serialize with bnxt_refclk_read()*/ if (ptp) { unsigned long flags; - spin_lock_irqsave(&ptp->ptp_lock, flags); + write_seqlock_irqsave(&ptp->ptp_lock, flags); set_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + write_sequnlock_irqrestore(&ptp->ptp_lock, flags); } else { set_bit(BNXT_STATE_IN_FW_RESET, &bp->state); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 69231e85140b..649955fa3e37 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1105,6 +1105,7 @@ struct bnxt_rx_ring_info { struct bnxt_ring_struct rx_agg_ring_struct; struct xdp_rxq_info xdp_rxq; struct page_pool *page_pool; + struct page_pool *head_pool; }; struct bnxt_rx_sw_stats { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index f71cc8188b4e..cfd2c65b1c90 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -705,112 +705,105 @@ skip_ring_stats: static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { struct bnxt *bp = netdev_priv(dev); - static const char * const *str; u32 i, j, num_str; + const char *str; switch (stringset) { case ETH_SS_STATS: for (i = 0; i < bp->cp_nr_rings; i++) { - if (is_rx_ring(bp, i)) { - num_str = NUM_RING_RX_HW_STATS; - for (j = 0; j < num_str; j++) { - sprintf(buf, "[%d]: %s", i, - bnxt_ring_rx_stats_str[j]); - buf += ETH_GSTRING_LEN; + if (is_rx_ring(bp, i)) + for (j = 0; j < NUM_RING_RX_HW_STATS; j++) { + str = bnxt_ring_rx_stats_str[j]; + ethtool_sprintf(&buf, "[%d]: %s", i, + str); } - } - if (is_tx_ring(bp, i)) { - num_str = NUM_RING_TX_HW_STATS; - for (j = 0; j < num_str; j++) { - sprintf(buf, "[%d]: %s", i, - bnxt_ring_tx_stats_str[j]); - buf += ETH_GSTRING_LEN; + if (is_tx_ring(bp, i)) + for (j = 0; j < NUM_RING_TX_HW_STATS; j++) { + str = bnxt_ring_tx_stats_str[j]; + ethtool_sprintf(&buf, "[%d]: %s", i, + str); } - } num_str = bnxt_get_num_tpa_ring_stats(bp); if (!num_str || !is_rx_ring(bp, i)) goto skip_tpa_stats; if (bp->max_tpa_v2) - str = bnxt_ring_tpa2_stats_str; + for (j = 0; j < num_str; j++) { + str = bnxt_ring_tpa2_stats_str[j]; + ethtool_sprintf(&buf, "[%d]: %s", i, + str); + } else - str = bnxt_ring_tpa_stats_str; - - for (j = 0; j < num_str; j++) { - sprintf(buf, "[%d]: %s", i, str[j]); - buf += ETH_GSTRING_LEN; - } -skip_tpa_stats: - if (is_rx_ring(bp, i)) { - num_str = NUM_RING_RX_SW_STATS; for (j = 0; j < num_str; j++) { - sprintf(buf, "[%d]: %s", i, - bnxt_rx_sw_stats_str[j]); - buf += ETH_GSTRING_LEN; + str = bnxt_ring_tpa_stats_str[j]; + ethtool_sprintf(&buf, "[%d]: %s", i, + str); } +skip_tpa_stats: + if (is_rx_ring(bp, i)) + for (j = 0; j < NUM_RING_RX_SW_STATS; j++) { + str = bnxt_rx_sw_stats_str[j]; + ethtool_sprintf(&buf, "[%d]: %s", i, + str); + } + for (j = 0; j < NUM_RING_CMN_SW_STATS; j++) { + str = bnxt_cmn_sw_stats_str[j]; + ethtool_sprintf(&buf, "[%d]: %s", i, str); } - num_str = NUM_RING_CMN_SW_STATS; - for (j = 0; j < num_str; j++) { - sprintf(buf, "[%d]: %s", i, - bnxt_cmn_sw_stats_str[j]); - buf += ETH_GSTRING_LEN; - } - } - for (i = 0; i < BNXT_NUM_RING_ERR_STATS; i++) { - strscpy(buf, bnxt_ring_err_stats_arr[i], ETH_GSTRING_LEN); - buf += ETH_GSTRING_LEN; } + for (i = 0; i < BNXT_NUM_RING_ERR_STATS; i++) + ethtool_puts(&buf, bnxt_ring_err_stats_arr[i]); - if (bp->flags & BNXT_FLAG_PORT_STATS) { + if (bp->flags & BNXT_FLAG_PORT_STATS) for (i = 0; i < BNXT_NUM_PORT_STATS; i++) { - strcpy(buf, bnxt_port_stats_arr[i].string); - buf += ETH_GSTRING_LEN; + str = bnxt_port_stats_arr[i].string; + ethtool_puts(&buf, str); } - } + if (bp->flags & BNXT_FLAG_PORT_STATS_EXT) { u32 len; len = min_t(u32, bp->fw_rx_stats_ext_size, ARRAY_SIZE(bnxt_port_stats_ext_arr)); for (i = 0; i < len; i++) { - strcpy(buf, bnxt_port_stats_ext_arr[i].string); - buf += ETH_GSTRING_LEN; + str = bnxt_port_stats_ext_arr[i].string; + ethtool_puts(&buf, str); } + len = min_t(u32, bp->fw_tx_stats_ext_size, ARRAY_SIZE(bnxt_tx_port_stats_ext_arr)); for (i = 0; i < len; i++) { - strcpy(buf, - bnxt_tx_port_stats_ext_arr[i].string); - buf += ETH_GSTRING_LEN; + str = bnxt_tx_port_stats_ext_arr[i].string; + ethtool_puts(&buf, str); } + if (bp->pri2cos_valid) { for (i = 0; i < 8; i++) { - strcpy(buf, - bnxt_rx_bytes_pri_arr[i].string); - buf += ETH_GSTRING_LEN; + str = bnxt_rx_bytes_pri_arr[i].string; + ethtool_puts(&buf, str); } + for (i = 0; i < 8; i++) { - strcpy(buf, - bnxt_rx_pkts_pri_arr[i].string); - buf += ETH_GSTRING_LEN; + str = bnxt_rx_pkts_pri_arr[i].string; + ethtool_puts(&buf, str); } + for (i = 0; i < 8; i++) { - strcpy(buf, - bnxt_tx_bytes_pri_arr[i].string); - buf += ETH_GSTRING_LEN; + str = bnxt_tx_bytes_pri_arr[i].string; + ethtool_puts(&buf, str); } + for (i = 0; i < 8; i++) { - strcpy(buf, - bnxt_tx_pkts_pri_arr[i].string); - buf += ETH_GSTRING_LEN; + str = bnxt_tx_pkts_pri_arr[i].string; + ethtool_puts(&buf, str); } } } break; case ETH_SS_TEST: if (bp->num_tests) - memcpy(buf, bp->test_info->string, - bp->num_tests * ETH_GSTRING_LEN); + for (i = 0; i < bp->num_tests; i++) + ethtool_puts(&buf, bp->test_info->string[i]); break; default: netdev_err(bp->dev, "bnxt_get_strings invalid request %x\n", @@ -1131,14 +1124,15 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd) fkeys = &fltr->fkeys; fmasks = &fltr->fmasks; if (fkeys->basic.n_proto == htons(ETH_P_IP)) { - if (fkeys->basic.ip_proto == IPPROTO_ICMP || - fkeys->basic.ip_proto == IPPROTO_RAW) { + if (fkeys->basic.ip_proto == BNXT_IP_PROTO_WILDCARD) { fs->flow_type = IP_USER_FLOW; fs->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4; - if (fkeys->basic.ip_proto == IPPROTO_ICMP) - fs->h_u.usr_ip4_spec.proto = IPPROTO_ICMP; - else - fs->h_u.usr_ip4_spec.proto = IPPROTO_RAW; + fs->h_u.usr_ip4_spec.proto = BNXT_IP_PROTO_WILDCARD; + fs->m_u.usr_ip4_spec.proto = 0; + } else if (fkeys->basic.ip_proto == IPPROTO_ICMP) { + fs->flow_type = IP_USER_FLOW; + fs->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4; + fs->h_u.usr_ip4_spec.proto = IPPROTO_ICMP; fs->m_u.usr_ip4_spec.proto = BNXT_IP_PROTO_FULL_MASK; } else if (fkeys->basic.ip_proto == IPPROTO_TCP) { fs->flow_type = TCP_V4_FLOW; @@ -1160,13 +1154,13 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd) fs->m_u.tcp_ip4_spec.pdst = fmasks->ports.dst; } } else { - if (fkeys->basic.ip_proto == IPPROTO_ICMPV6 || - fkeys->basic.ip_proto == IPPROTO_RAW) { + if (fkeys->basic.ip_proto == BNXT_IP_PROTO_WILDCARD) { fs->flow_type = IPV6_USER_FLOW; - if (fkeys->basic.ip_proto == IPPROTO_ICMPV6) - fs->h_u.usr_ip6_spec.l4_proto = IPPROTO_ICMPV6; - else - fs->h_u.usr_ip6_spec.l4_proto = IPPROTO_RAW; + fs->h_u.usr_ip6_spec.l4_proto = BNXT_IP_PROTO_WILDCARD; + fs->m_u.usr_ip6_spec.l4_proto = 0; + } else if (fkeys->basic.ip_proto == IPPROTO_ICMPV6) { + fs->flow_type = IPV6_USER_FLOW; + fs->h_u.usr_ip6_spec.l4_proto = IPPROTO_ICMPV6; fs->m_u.usr_ip6_spec.l4_proto = BNXT_IP_PROTO_FULL_MASK; } else if (fkeys->basic.ip_proto == IPPROTO_TCP) { fs->flow_type = TCP_V6_FLOW; @@ -1289,10 +1283,12 @@ static int bnxt_add_l2_cls_rule(struct bnxt *bp, static bool bnxt_verify_ntuple_ip4_flow(struct ethtool_usrip4_spec *ip_spec, struct ethtool_usrip4_spec *ip_mask) { + u8 mproto = ip_mask->proto; + u8 sproto = ip_spec->proto; + if (ip_mask->l4_4_bytes || ip_mask->tos || ip_spec->ip_ver != ETH_RX_NFC_IP4 || - ip_mask->proto != BNXT_IP_PROTO_FULL_MASK || - (ip_spec->proto != IPPROTO_RAW && ip_spec->proto != IPPROTO_ICMP)) + (mproto && (mproto != BNXT_IP_PROTO_FULL_MASK || sproto != IPPROTO_ICMP))) return false; return true; } @@ -1300,10 +1296,11 @@ static bool bnxt_verify_ntuple_ip4_flow(struct ethtool_usrip4_spec *ip_spec, static bool bnxt_verify_ntuple_ip6_flow(struct ethtool_usrip6_spec *ip_spec, struct ethtool_usrip6_spec *ip_mask) { + u8 mproto = ip_mask->l4_proto; + u8 sproto = ip_spec->l4_proto; + if (ip_mask->l4_4_bytes || ip_mask->tclass || - ip_mask->l4_proto != BNXT_IP_PROTO_FULL_MASK || - (ip_spec->l4_proto != IPPROTO_RAW && - ip_spec->l4_proto != IPPROTO_ICMPV6)) + (mproto && (mproto != BNXT_IP_PROTO_FULL_MASK || sproto != IPPROTO_ICMPV6))) return false; return true; } @@ -1357,7 +1354,8 @@ static int bnxt_add_ntuple_cls_rule(struct bnxt *bp, struct ethtool_usrip4_spec *ip_spec = &fs->h_u.usr_ip4_spec; struct ethtool_usrip4_spec *ip_mask = &fs->m_u.usr_ip4_spec; - fkeys->basic.ip_proto = ip_spec->proto; + fkeys->basic.ip_proto = ip_mask->proto ? ip_spec->proto + : BNXT_IP_PROTO_WILDCARD; fkeys->basic.n_proto = htons(ETH_P_IP); fkeys->addrs.v4addrs.src = ip_spec->ip4src; fmasks->addrs.v4addrs.src = ip_mask->ip4src; @@ -1388,7 +1386,8 @@ static int bnxt_add_ntuple_cls_rule(struct bnxt *bp, struct ethtool_usrip6_spec *ip_spec = &fs->h_u.usr_ip6_spec; struct ethtool_usrip6_spec *ip_mask = &fs->m_u.usr_ip6_spec; - fkeys->basic.ip_proto = ip_spec->l4_proto; + fkeys->basic.ip_proto = ip_mask->l4_proto ? ip_spec->l4_proto + : BNXT_IP_PROTO_WILDCARD; fkeys->basic.n_proto = htons(ETH_P_IPV6); fkeys->addrs.v6addrs.src = *(struct in6_addr *)&ip_spec->ip6src; fmasks->addrs.v6addrs.src = *(struct in6_addr *)&ip_mask->ip6src; @@ -2781,7 +2780,7 @@ u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed) static void bnxt_get_default_speeds(struct ethtool_link_ksettings *lk_ksettings, struct bnxt_link_info *link_info) { - struct ethtool_link_settings *base = &lk_ksettings->base; + struct ethtool_link_settings_hdr *base = &lk_ksettings->base; if (link_info->link_state == BNXT_LINK_STATE_UP) { base->speed = bnxt_fw_to_ethtool_speed(link_info->link_speed); @@ -2800,7 +2799,7 @@ static void bnxt_get_default_speeds(struct ethtool_link_ksettings *lk_ksettings, static int bnxt_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *lk_ksettings) { - struct ethtool_link_settings *base = &lk_ksettings->base; + struct ethtool_link_settings_hdr *base = &lk_ksettings->base; enum ethtool_link_mode_bit_indices link_mode; struct bnxt *bp = netdev_priv(dev); struct bnxt_link_info *link_info; @@ -3023,9 +3022,9 @@ u16 bnxt_get_fw_auto_link_speeds(const unsigned long *mode) static int bnxt_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *lk_ksettings) { + const struct ethtool_link_settings_hdr *base = &lk_ksettings->base; struct bnxt *bp = netdev_priv(dev); struct bnxt_link_info *link_info = &bp->link_info; - const struct ethtool_link_settings *base = &lk_ksettings->base; bool set_pause = false; u32 speed, lanes = 0; int rc = 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h index e2ee030237d4..33b86ede1ce5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h @@ -44,6 +44,7 @@ struct bnxt_led_cfg { #define BNXT_PXP_REG_LEN 0x3110 #define BNXT_IP_PROTO_FULL_MASK 0xFF +#define BNXT_IP_PROTO_WILDCARD 0x0 extern const struct ethtool_ops bnxt_ethtool_ops; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index fa514be87650..91e7e08fabb1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -67,15 +67,15 @@ static int bnxt_ptp_settime(struct ptp_clock_info *ptp_info, if (BNXT_PTP_USE_RTC(ptp->bp)) return bnxt_ptp_cfg_settime(ptp->bp, ns); - spin_lock_irqsave(&ptp->ptp_lock, flags); + write_seqlock_irqsave(&ptp->ptp_lock, flags); timecounter_init(&ptp->tc, &ptp->cc, ns); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + write_sequnlock_irqrestore(&ptp->ptp_lock, flags); return 0; } /* Caller holds ptp_lock */ -static int bnxt_refclk_read(struct bnxt *bp, struct ptp_system_timestamp *sts, - u64 *ns) +static int __bnxt_refclk_read(struct bnxt *bp, struct ptp_system_timestamp *sts, + u64 *ns) { struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; u32 high_before, high_now, low; @@ -98,17 +98,28 @@ static int bnxt_refclk_read(struct bnxt *bp, struct ptp_system_timestamp *sts, return 0; } -static void bnxt_ptp_get_current_time(struct bnxt *bp) +static int bnxt_refclk_read(struct bnxt *bp, struct ptp_system_timestamp *sts, + u64 *ns) { struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; unsigned long flags; + int rc; + + /* We have to serialize reg access and FW reset */ + read_seqlock_excl_irqsave(&ptp->ptp_lock, flags); + rc = __bnxt_refclk_read(bp, sts, ns); + read_sequnlock_excl_irqrestore(&ptp->ptp_lock, flags); + return rc; +} + +static void bnxt_ptp_get_current_time(struct bnxt *bp) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; if (!ptp) return; - spin_lock_irqsave(&ptp->ptp_lock, flags); - WRITE_ONCE(ptp->old_time, ptp->current_time); + WRITE_ONCE(ptp->old_time, ptp->current_time >> BNXT_HI_TIMER_SHIFT); bnxt_refclk_read(bp, NULL, &ptp->current_time); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); } static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts, @@ -151,36 +162,30 @@ static int bnxt_ptp_gettimex(struct ptp_clock_info *ptp_info, { struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg, ptp_info); - unsigned long flags; u64 ns, cycles; int rc; - spin_lock_irqsave(&ptp->ptp_lock, flags); rc = bnxt_refclk_read(ptp->bp, sts, &cycles); - if (rc) { - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + if (rc) return rc; - } - ns = timecounter_cyc2time(&ptp->tc, cycles); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + + ns = bnxt_timecounter_cyc2time(ptp, cycles); *ts = ns_to_timespec64(ns); return 0; } -/* Caller holds ptp_lock */ void bnxt_ptp_update_current_time(struct bnxt *bp) { struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; bnxt_refclk_read(ptp->bp, NULL, &ptp->current_time); - WRITE_ONCE(ptp->old_time, ptp->current_time); + WRITE_ONCE(ptp->old_time, ptp->current_time >> BNXT_HI_TIMER_SHIFT); } static int bnxt_ptp_adjphc(struct bnxt_ptp_cfg *ptp, s64 delta) { struct hwrm_port_mac_cfg_input *req; - unsigned long flags; int rc; rc = hwrm_req_init(ptp->bp, req, HWRM_PORT_MAC_CFG); @@ -194,9 +199,7 @@ static int bnxt_ptp_adjphc(struct bnxt_ptp_cfg *ptp, s64 delta) if (rc) { netdev_err(ptp->bp->dev, "ptp adjphc failed. rc = %x\n", rc); } else { - spin_lock_irqsave(&ptp->ptp_lock, flags); bnxt_ptp_update_current_time(ptp->bp); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); } return rc; @@ -211,9 +214,9 @@ static int bnxt_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta) if (BNXT_PTP_USE_RTC(ptp->bp)) return bnxt_ptp_adjphc(ptp, delta); - spin_lock_irqsave(&ptp->ptp_lock, flags); + write_seqlock_irqsave(&ptp->ptp_lock, flags); timecounter_adjtime(&ptp->tc, delta); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + write_sequnlock_irqrestore(&ptp->ptp_lock, flags); return 0; } @@ -246,10 +249,10 @@ static int bnxt_ptp_adjfine(struct ptp_clock_info *ptp_info, long scaled_ppm) if (!BNXT_MH(bp)) return bnxt_ptp_adjfine_rtc(bp, scaled_ppm); - spin_lock_irqsave(&ptp->ptp_lock, flags); + write_seqlock_irqsave(&ptp->ptp_lock, flags); timecounter_read(&ptp->tc); ptp->cc.mult = adjust_by_scaled_ppm(ptp->cmult, scaled_ppm); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + write_sequnlock_irqrestore(&ptp->ptp_lock, flags); return 0; } @@ -257,13 +260,10 @@ void bnxt_ptp_pps_event(struct bnxt *bp, u32 data1, u32 data2) { struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; struct ptp_clock_event event; - unsigned long flags; u64 ns, pps_ts; pps_ts = EVENT_PPS_TS(data2, data1); - spin_lock_irqsave(&ptp->ptp_lock, flags); - ns = timecounter_cyc2time(&ptp->tc, pps_ts); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + ns = bnxt_timecounter_cyc2time(ptp, pps_ts); switch (EVENT_DATA2_PPS_EVENT_TYPE(data2)) { case ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_INTERNAL: @@ -400,17 +400,13 @@ static int bnxt_get_target_cycles(struct bnxt_ptp_cfg *ptp, u64 target_ns, { u64 cycles_now; u64 nsec_now, nsec_delta; - unsigned long flags; int rc; - spin_lock_irqsave(&ptp->ptp_lock, flags); rc = bnxt_refclk_read(ptp->bp, NULL, &cycles_now); - if (rc) { - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + if (rc) return rc; - } - nsec_now = timecounter_cyc2time(&ptp->tc, cycles_now); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + + nsec_now = bnxt_timecounter_cyc2time(ptp, cycles_now); nsec_delta = target_ns - nsec_now; *cycles_delta = div64_u64(nsec_delta << ptp->cc.shift, ptp->cc.mult); @@ -687,7 +683,7 @@ static u64 bnxt_cc_read(const struct cyclecounter *cc) struct bnxt_ptp_cfg *ptp = container_of(cc, struct bnxt_ptp_cfg, cc); u64 ns = 0; - bnxt_refclk_read(ptp->bp, NULL, &ns); + __bnxt_refclk_read(ptp->bp, NULL, &ns); return ns; } @@ -697,7 +693,6 @@ static int bnxt_stamp_tx_skb(struct bnxt *bp, int slot) struct skb_shared_hwtstamps timestamp; struct bnxt_ptp_tx_req *txts_req; unsigned long now = jiffies; - unsigned long flags; u64 ts = 0, ns = 0; u32 tmo = 0; int rc; @@ -711,9 +706,7 @@ static int bnxt_stamp_tx_skb(struct bnxt *bp, int slot) tmo, slot); if (!rc) { memset(×tamp, 0, sizeof(timestamp)); - spin_lock_irqsave(&ptp->ptp_lock, flags); - ns = timecounter_cyc2time(&ptp->tc, ts); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + ns = bnxt_timecounter_cyc2time(ptp, ts); timestamp.hwtstamp = ns_to_ktime(ns); skb_tstamp_tx(txts_req->tx_skb, ×tamp); ptp->stats.ts_pkts++; @@ -767,9 +760,9 @@ next_slot: bnxt_ptp_get_current_time(bp); ptp->next_period = now + HZ; if (time_after_eq(now, ptp->next_overflow_check)) { - spin_lock_irqsave(&ptp->ptp_lock, flags); + write_seqlock_irqsave(&ptp->ptp_lock, flags); timecounter_read(&ptp->tc); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + write_sequnlock_irqrestore(&ptp->ptp_lock, flags); ptp->next_overflow_check = now + BNXT_PHC_OVERFLOW_PERIOD; } if (rc == -EAGAIN) @@ -813,7 +806,7 @@ int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts) if (!ptp) return -ENODEV; - BNXT_READ_TIME64(ptp, time, ptp->old_time); + time = (u64)READ_ONCE(ptp->old_time) << BNXT_HI_TIMER_SHIFT; *ts = (time & BNXT_HI_TIMER_MASK) | pkt_ts; if (pkt_ts < (time & BNXT_LO_TIMER_MASK)) *ts += BNXT_LO_TIMER_MASK + 1; @@ -829,7 +822,6 @@ void bnxt_tx_ts_cmp(struct bnxt *bp, struct bnxt_napi *bnapi, u32 opaque = tscmp->tx_ts_cmp_opaque; struct bnxt_tx_ring_info *txr; struct bnxt_sw_tx_bd *tx_buf; - unsigned long flags; u64 ts, ns; u16 cons; @@ -844,9 +836,7 @@ void bnxt_tx_ts_cmp(struct bnxt *bp, struct bnxt_napi *bnapi, le32_to_cpu(tscmp->tx_ts_cmp_flags_type), le32_to_cpu(tscmp->tx_ts_cmp_errors_v)); } else { - spin_lock_irqsave(&ptp->ptp_lock, flags); - ns = timecounter_cyc2time(&ptp->tc, ts); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + ns = bnxt_timecounter_cyc2time(ptp, ts); timestamp.hwtstamp = ns_to_ktime(ns); skb_tstamp_tx(tx_buf->skb, ×tamp); } @@ -955,6 +945,7 @@ static bool bnxt_pps_config_ok(struct bnxt *bp) static void bnxt_ptp_timecounter_init(struct bnxt *bp, bool init_tc) { struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + unsigned long flags; if (!ptp->ptp_clock) { memset(&ptp->cc, 0, sizeof(ptp->cc)); @@ -971,8 +962,11 @@ static void bnxt_ptp_timecounter_init(struct bnxt *bp, bool init_tc) } ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD; } - if (init_tc) + if (init_tc) { + write_seqlock_irqsave(&ptp->ptp_lock, flags); timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real())); + write_sequnlock_irqrestore(&ptp->ptp_lock, flags); + } } /* Caller holds ptp_lock */ @@ -1005,9 +999,9 @@ int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg) if (rc) return rc; } - spin_lock_irqsave(&bp->ptp_cfg->ptp_lock, flags); + write_seqlock_irqsave(&bp->ptp_cfg->ptp_lock, flags); bnxt_ptp_rtc_timecounter_init(bp->ptp_cfg, ns); - spin_unlock_irqrestore(&bp->ptp_cfg->ptp_lock, flags); + write_sequnlock_irqrestore(&bp->ptp_cfg->ptp_lock, flags); return 0; } @@ -1042,7 +1036,7 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg) bnxt_ptp_free(bp); WRITE_ONCE(ptp->tx_avail, BNXT_MAX_TX_TS); - spin_lock_init(&ptp->ptp_lock); + seqlock_init(&ptp->ptp_lock); spin_lock_init(&ptp->ptp_tx_lock); if (BNXT_PTP_USE_RTC(bp)) { @@ -1075,12 +1069,8 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg) atomic64_set(&ptp->stats.ts_err, 0); if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { - unsigned long flags; - - spin_lock_irqsave(&ptp->ptp_lock, flags); bnxt_refclk_read(bp, NULL, &ptp->current_time); - WRITE_ONCE(ptp->old_time, ptp->current_time); - spin_unlock_irqrestore(&ptp->ptp_lock, flags); + WRITE_ONCE(ptp->old_time, ptp->current_time >> BNXT_HI_TIMER_SHIFT); ptp_schedule_worker(ptp->ptp_clock, 0); } ptp->txts_tmo = BNXT_PTP_DFLT_TX_TMO; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index f322466ecad3..4df4c2f373e0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -21,6 +21,7 @@ #define BNXT_DEVCLK_FREQ 1000000 #define BNXT_LO_TIMER_MASK 0x0000ffffffffUL #define BNXT_HI_TIMER_MASK 0xffff00000000UL +#define BNXT_HI_TIMER_SHIFT 24 #define BNXT_PTP_DFLT_TX_TMO 1000 /* ms */ #define BNXT_PTP_QTS_TIMEOUT 1000 @@ -102,14 +103,15 @@ struct bnxt_ptp_cfg { struct timecounter tc; struct bnxt_pps pps_info; /* serialize timecounter access */ - spinlock_t ptp_lock; + seqlock_t ptp_lock; /* serialize ts tx request queuing */ spinlock_t ptp_tx_lock; u64 current_time; - u64 old_time; unsigned long next_period; unsigned long next_overflow_check; u32 cmult; + /* cache of upper 24 bits of cyclecoutner. 8 bits are used to check for roll-over */ + u32 old_time; /* a 23b shift cyclecounter will overflow in ~36 mins. Check overflow every 18 mins. */ #define BNXT_PHC_OVERFLOW_PERIOD (18 * 60 * HZ) @@ -145,20 +147,6 @@ struct bnxt_ptp_cfg { struct bnxt_ptp_stats stats; }; -#if BITS_PER_LONG == 32 -#define BNXT_READ_TIME64(ptp, dst, src) \ -do { \ - unsigned long flags; \ - \ - spin_lock_irqsave(&(ptp)->ptp_lock, flags); \ - (dst) = (src); \ - spin_unlock_irqrestore(&(ptp)->ptp_lock, flags); \ -} while (0) -#else -#define BNXT_READ_TIME64(ptp, dst, src) \ - ((dst) = READ_ONCE(src)) -#endif - #define BNXT_PTP_INC_TX_AVAIL(ptp) \ do { \ spin_lock_bh(&(ptp)->ptp_tx_lock); \ @@ -182,4 +170,16 @@ void bnxt_ptp_rtc_timecounter_init(struct bnxt_ptp_cfg *ptp, u64 ns); int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg); int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg); void bnxt_ptp_clear(struct bnxt *bp); +static inline u64 bnxt_timecounter_cyc2time(struct bnxt_ptp_cfg *ptp, u64 ts) +{ + unsigned int seq; + u64 ns; + + do { + seq = read_seqbegin(&ptp->ptp_lock); + ns = timecounter_cyc2time(&ptp->tc, ts); + } while (read_seqretry(&ptp->ptp_lock, seq)); + + return ns; +} #endif diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 10966ab15373..3e93f957430b 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1144,14 +1144,14 @@ static int bcmgenet_get_sset_count(struct net_device *dev, int string_set) static void bcmgenet_get_strings(struct net_device *dev, u32 stringset, u8 *data) { + const char *str; int i; switch (stringset) { case ETH_SS_STATS: for (i = 0; i < BCMGENET_STATS_LEN; i++) { - memcpy(data + i * ETH_GSTRING_LEN, - bcmgenet_gstrings_stats[i].stat_string, - ETH_GSTRING_LEN); + str = bcmgenet_gstrings_stats[i].stat_string; + ethtool_puts(&data, str); } break; } @@ -2405,7 +2405,7 @@ static int bcmgenet_rx_poll(struct napi_struct *napi, int budget) if (ring->dim.use_dim) { dim_update_sample(ring->dim.event_ctr, ring->dim.packets, ring->dim.bytes, &dim_sample); - net_dim(&ring->dim.dim, dim_sample); + net_dim(&ring->dim.dim, &dim_sample); } return work_done; diff --git a/drivers/net/ethernet/brocade/bna/bnad.h b/drivers/net/ethernet/brocade/bna/bnad.h index 10b1e534030e..4396997c59d0 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.h +++ b/drivers/net/ethernet/brocade/bna/bnad.h @@ -351,7 +351,6 @@ struct bnad { /* debugfs specific data */ char *regdata; u32 reglen; - struct dentry *bnad_dentry_files[5]; struct dentry *port_debugfs_root; }; diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c index 97291bfbeea5..8f0972e6737c 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c +++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c @@ -500,11 +500,6 @@ bnad_debugfs_init(struct bnad *bnad) if (!bna_debugfs_root) { bna_debugfs_root = debugfs_create_dir("bna", NULL); atomic_set(&bna_debugfs_port_count, 0); - if (!bna_debugfs_root) { - netdev_warn(bnad->netdev, - "debugfs root dir creation failed\n"); - return; - } } /* Setup the pci_dev debugfs directory for the port */ @@ -517,18 +512,11 @@ bnad_debugfs_init(struct bnad *bnad) for (i = 0; i < ARRAY_SIZE(bnad_debugfs_files); i++) { file = &bnad_debugfs_files[i]; - bnad->bnad_dentry_files[i] = - debugfs_create_file(file->name, - file->mode, - bnad->port_debugfs_root, - bnad, - file->fops); - if (!bnad->bnad_dentry_files[i]) { - netdev_warn(bnad->netdev, - "create %s entry failed\n", - file->name); - return; - } + debugfs_create_file(file->name, + file->mode, + bnad->port_debugfs_root, + bnad, + file->fops); } } } @@ -537,15 +525,6 @@ bnad_debugfs_init(struct bnad *bnad) void bnad_debugfs_uninit(struct bnad *bnad) { - int i; - - for (i = 0; i < ARRAY_SIZE(bnad_debugfs_files); i++) { - if (bnad->bnad_dentry_files[i]) { - debugfs_remove(bnad->bnad_dentry_files[i]); - bnad->bnad_dentry_files[i] = NULL; - } - } - /* Remove the pci_dev debugfs directory for the port */ if (bnad->port_debugfs_root) { debugfs_remove(bnad->port_debugfs_root); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index ebe886b98891..daa416fb1724 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -915,20 +915,15 @@ static int macb_mii_probe(struct net_device *dev) return 0; } -static int macb_mdiobus_register(struct macb *bp) +static int macb_mdiobus_register(struct macb *bp, struct device_node *mdio_np) { struct device_node *child, *np = bp->pdev->dev.of_node; /* If we have a child named mdio, probe it instead of looking for PHYs * directly under the MAC node */ - child = of_get_child_by_name(np, "mdio"); - if (child) { - int ret = of_mdiobus_register(bp->mii_bus, child); - - of_node_put(child); - return ret; - } + if (mdio_np) + return of_mdiobus_register(bp->mii_bus, mdio_np); /* Only create the PHY from the device tree if at least one PHY is * described. Otherwise scan the entire MDIO bus. We do this to support @@ -950,17 +945,15 @@ static int macb_mdiobus_register(struct macb *bp) static int macb_mii_init(struct macb *bp) { - struct device_node *child, *np = bp->pdev->dev.of_node; + struct device_node *mdio_np, *np = bp->pdev->dev.of_node; int err = -ENXIO; /* With fixed-link, we don't need to register the MDIO bus, * except if we have a child named "mdio" in the device tree. * In that case, some devices may be attached to the MACB's MDIO bus. */ - child = of_get_child_by_name(np, "mdio"); - if (child) - of_node_put(child); - else if (of_phy_is_fixed_link(np)) + mdio_np = of_get_child_by_name(np, "mdio"); + if (!mdio_np && of_phy_is_fixed_link(np)) return macb_mii_probe(bp->dev); /* Enable management port */ @@ -984,7 +977,7 @@ static int macb_mii_init(struct macb *bp) dev_set_drvdata(&bp->dev->dev, bp->mii_bus); - err = macb_mdiobus_register(bp); + err = macb_mdiobus_register(bp, mdio_np); if (err) goto err_out_free_mdiobus; @@ -999,6 +992,8 @@ err_out_unregister_bus: err_out_free_mdiobus: mdiobus_free(bp->mii_bus); err_out: + of_node_put(mdio_np); + return err; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 7f3f5afa864f..45d28a65347e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -662,8 +662,8 @@ static unsigned int lmm_to_fw_caps(const unsigned long *link_mode_mask) static int get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings) { + struct ethtool_link_settings_hdr *base = &link_ksettings->base; struct port_info *pi = netdev_priv(dev); - struct ethtool_link_settings *base = &link_ksettings->base; /* For the nonce, the Firmware doesn't send up Port State changes * when the Virtual Interface attached to the Port is down. So @@ -717,9 +717,9 @@ static int get_link_ksettings(struct net_device *dev, static int set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *link_ksettings) { + const struct ethtool_link_settings_hdr *base = &link_ksettings->base; struct port_info *pi = netdev_priv(dev); struct link_config *lc = &pi->link_cfg; - const struct ethtool_link_settings *base = &link_ksettings->base; struct link_config old_lc; unsigned int fw_caps; int ret = 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 2fbe0f059a0b..61d08547e3f9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -1436,8 +1436,8 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, static int cxgb4vf_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings) { + struct ethtool_link_settings_hdr *base = &link_ksettings->base; struct port_info *pi = netdev_priv(dev); - struct ethtool_link_settings *base = &link_ksettings->base; /* For the nonce, the Firmware doesn't send up Port State changes * when the Virtual Interface attached to the Port is down. So diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c index f7986f2b6a17..4fe85780a950 100644 --- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c +++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c @@ -129,8 +129,8 @@ static void enic_intr_coal_set_rx(struct enic *enic, u32 timer) static int enic_get_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *ecmd) { + struct ethtool_link_settings_hdr *base = &ecmd->base; struct enic *enic = netdev_priv(netdev); - struct ethtool_link_settings *base = &ecmd->base; ethtool_link_ksettings_add_link_mode(ecmd, supported, 10000baseT_Full); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index ac06b01fe934..bf5baef5c3e0 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1820,7 +1820,6 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, struct page *page, *head_page; struct dpaa_bp *dpaa_bp; void *vaddr, *sg_vaddr; - int frag_off, frag_len; struct sk_buff *skb; dma_addr_t sg_addr; int page_offset; @@ -1863,6 +1862,11 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, * on Tx, if extra headers are added. */ WARN_ON(fd_off != priv->rx_headroom); + /* The offset to data start within the buffer holding + * the SGT should always be equal to the offset to data + * start within the first buffer holding the frame. + */ + WARN_ON_ONCE(fd_off != qm_sg_entry_get_off(&sgt[i])); skb_reserve(skb, fd_off); skb_put(skb, qm_sg_entry_get_len(&sgt[i])); } else { @@ -1876,21 +1880,23 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, page = virt_to_page(sg_vaddr); head_page = virt_to_head_page(sg_vaddr); - /* Compute offset in (possibly tail) page */ + /* Compute offset of sg_vaddr in (possibly tail) page */ page_offset = ((unsigned long)sg_vaddr & (PAGE_SIZE - 1)) + (page_address(page) - page_address(head_page)); - /* page_offset only refers to the beginning of sgt[i]; - * but the buffer itself may have an internal offset. + + /* Non-initial SGT entries should not have a buffer + * offset. */ - frag_off = qm_sg_entry_get_off(&sgt[i]) + page_offset; - frag_len = qm_sg_entry_get_len(&sgt[i]); + WARN_ON_ONCE(qm_sg_entry_get_off(&sgt[i])); + /* skb_add_rx_frag() does no checking on the page; if * we pass it a tail page, we'll end up with - * bad page accounting and eventually with segafults. + * bad page accounting and eventually with segfaults. */ - skb_add_rx_frag(skb, i - 1, head_page, frag_off, - frag_len, dpaa_bp->size); + skb_add_rx_frag(skb, i - 1, head_page, page_offset, + qm_sg_entry_get_len(&sgt[i]), + dpaa_bp->size); } /* Update the pool count for the current {cpu x bpool} */ @@ -2766,7 +2772,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, if (net_dev->features & NETIF_F_RXHASH && priv->keygen_in_use && !fman_port_get_hash_result_offset(priv->mac_dev->port[RX], &hash_offset)) { - hash = be32_to_cpu(*(u32 *)(vaddr + hash_offset)); + hash = be32_to_cpu(*(__be32 *)(vaddr + hash_offset)); hash_valid = true; } diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_trace.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_trace.h index 6f0e58a2a58a..9e1d44ae92cc 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_trace.h +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_trace.h @@ -56,7 +56,7 @@ DECLARE_EVENT_CLASS(dpaa_eth_fd, __entry->fd_format = qm_fd_get_format(fd); __entry->fd_offset = qm_fd_get_offset(fd); __entry->fd_length = qm_fd_get_length(fd); - __entry->fd_status = fd->status; + __entry->fd_status = __be32_to_cpu(fd->status); __assign_str(name); ), diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index b0060cf96090..9986f6e1f587 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -243,38 +243,24 @@ static void dpaa_get_ethtool_stats(struct net_device *net_dev, static void dpaa_get_strings(struct net_device *net_dev, u32 stringset, u8 *data) { - unsigned int i, j, num_cpus, size; - char string_cpu[ETH_GSTRING_LEN]; - u8 *strings; + unsigned int i, j, num_cpus; - memset(string_cpu, 0, sizeof(string_cpu)); - strings = data; - num_cpus = num_online_cpus(); - size = DPAA_STATS_GLOBAL_LEN * ETH_GSTRING_LEN; + num_cpus = num_online_cpus(); for (i = 0; i < DPAA_STATS_PERCPU_LEN; i++) { - for (j = 0; j < num_cpus; j++) { - snprintf(string_cpu, ETH_GSTRING_LEN, "%s [CPU %d]", - dpaa_stats_percpu[i], j); - memcpy(strings, string_cpu, ETH_GSTRING_LEN); - strings += ETH_GSTRING_LEN; - } - snprintf(string_cpu, ETH_GSTRING_LEN, "%s [TOTAL]", - dpaa_stats_percpu[i]); - memcpy(strings, string_cpu, ETH_GSTRING_LEN); - strings += ETH_GSTRING_LEN; - } - for (j = 0; j < num_cpus; j++) { - snprintf(string_cpu, ETH_GSTRING_LEN, - "bpool [CPU %d]", j); - memcpy(strings, string_cpu, ETH_GSTRING_LEN); - strings += ETH_GSTRING_LEN; + for (j = 0; j < num_cpus; j++) + ethtool_sprintf(&data, "%s [CPU %d]", + dpaa_stats_percpu[i], j); + + ethtool_sprintf(&data, "%s [TOTAL]", dpaa_stats_percpu[i]); } - snprintf(string_cpu, ETH_GSTRING_LEN, "bpool [TOTAL]"); - memcpy(strings, string_cpu, ETH_GSTRING_LEN); - strings += ETH_GSTRING_LEN; + for (i = 0; i < num_cpus; i++) + ethtool_sprintf(&data, "bpool [CPU %d]", i); + + ethtool_puts(&data, "bpool [TOTAL]"); - memcpy(strings, dpaa_stats_global, size); + for (i = 0; i < DPAA_STATS_GLOBAL_LEN; i++) + ethtool_puts(&data, dpaa_stats_global[i]); } static int dpaa_get_hash_opts(struct net_device *dev, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 7f476519b7ad..74ef77cb7078 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -217,20 +217,15 @@ static int dpaa2_eth_set_pauseparam(struct net_device *net_dev, static void dpaa2_eth_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { - u8 *p = data; int i; switch (stringset) { case ETH_SS_STATS: - for (i = 0; i < DPAA2_ETH_NUM_STATS; i++) { - strscpy(p, dpaa2_ethtool_stats[i], ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - for (i = 0; i < DPAA2_ETH_NUM_EXTRA_STATS; i++) { - strscpy(p, dpaa2_ethtool_extras[i], ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - dpaa2_mac_get_strings(p); + for (i = 0; i < DPAA2_ETH_NUM_STATS; i++) + ethtool_puts(&data, dpaa2_ethtool_stats[i]); + for (i = 0; i < DPAA2_ETH_NUM_EXTRA_STATS; i++) + ethtool_puts(&data, dpaa2_ethtool_extras[i]); + dpaa2_mac_get_strings(&data); break; } } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index a69bb22c37ea..422ce13a7c94 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -558,15 +558,12 @@ int dpaa2_mac_get_sset_count(void) return DPAA2_MAC_NUM_STATS; } -void dpaa2_mac_get_strings(u8 *data) +void dpaa2_mac_get_strings(u8 **data) { - u8 *p = data; int i; - for (i = 0; i < DPAA2_MAC_NUM_STATS; i++) { - strscpy(p, dpaa2_mac_ethtool_stats[i], ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < DPAA2_MAC_NUM_STATS; i++) + ethtool_puts(data, dpaa2_mac_ethtool_stats[i]); } void dpaa2_mac_get_ethtool_stats(struct dpaa2_mac *mac, u64 *data) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h index c1ec9efd413a..53f8d106d11e 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h @@ -49,7 +49,7 @@ void dpaa2_mac_disconnect(struct dpaa2_mac *mac); int dpaa2_mac_get_sset_count(void); -void dpaa2_mac_get_strings(u8 *data); +void dpaa2_mac_get_strings(u8 **data); void dpaa2_mac_get_ethtool_stats(struct dpaa2_mac *mac, u64 *data); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c index 6bc1988be311..a888f6e6e9b0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-ethtool.c @@ -170,17 +170,16 @@ dpaa2_switch_ethtool_get_sset_count(struct net_device *netdev, int sset) static void dpaa2_switch_ethtool_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { - u8 *p = data; + const char *str; int i; switch (stringset) { case ETH_SS_STATS: for (i = 0; i < DPAA2_SWITCH_NUM_COUNTERS; i++) { - memcpy(p, dpaa2_switch_ethtool_counters[i].name, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; + str = dpaa2_switch_ethtool_counters[i].name; + ethtool_puts(&data, str); } - dpaa2_mac_get_strings(p); + dpaa2_mac_get_strings(&data); break; } } diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index 4d75e6807e92..6c2779047dcd 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -7,6 +7,14 @@ config FSL_ENETC_CORE If compiled as module (M), the module name is fsl-enetc-core. +config NXP_ENETC_PF_COMMON + tristate + help + This module supports common functionality between drivers of + different versions of NXP ENETC PF controllers. + + If compiled as module (M), the module name is nxp-enetc-pf-common. + config FSL_ENETC tristate "ENETC PF driver" depends on PCI_MSI @@ -14,6 +22,7 @@ config FSL_ENETC select FSL_ENETC_CORE select FSL_ENETC_IERB select FSL_ENETC_MDIO + select NXP_ENETC_PF_COMMON select PHYLINK select PCS_LYNX select DIMLIB @@ -24,6 +33,23 @@ config FSL_ENETC If compiled as module (M), the module name is fsl-enetc. +config NXP_ENETC4 + tristate "ENETC4 PF driver" + depends on PCI_MSI + select MDIO_DEVRES + select FSL_ENETC_CORE + select FSL_ENETC_MDIO + select NXP_ENETC_PF_COMMON + select PHYLINK + select DIMLIB + help + This driver supports NXP ENETC devices with major revision 4. ENETC is + as the NIC functionality in NETC, it supports virtualization/isolation + based on PCIe Single Root IO Virtualization (SR-IOV) and a full range + of TSN standards and NIC offload capabilities. + + If compiled as module (M), the module name is nxp-enetc4. + config FSL_ENETC_VF tristate "ENETC VF driver" depends on PCI_MSI @@ -75,3 +101,17 @@ config FSL_ENETC_QOS enable/disable from user space via Qos commands(tc). In the kernel side, it can be loaded by Qos driver. Currently, it is only support taprio(802.1Qbv) and Credit Based Shaper(802.1Qbu). + +config NXP_NETC_BLK_CTRL + tristate "NETC blocks control driver" + help + This driver configures Integrated Endpoint Register Block (IERB) and + Privileged Register Block (PRB) of NETC. For i.MX platforms, it also + includes the configuration of NETCMIX block. + The IERB contains registers that are used for pre-boot initialization, + debug, and non-customer configuration. The PRB controls global reset + and global error handling for NETC. The NETCMIX block is mainly used + to set MII protocol and PCS protocol of the links, it also contains + settings for some other functions. + + If compiled as module (M), the module name is nxp-netc-blk-ctrl. diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile index b13cbbabb2ea..6fd27ee4fcd1 100644 --- a/drivers/net/ethernet/freescale/enetc/Makefile +++ b/drivers/net/ethernet/freescale/enetc/Makefile @@ -3,11 +3,17 @@ obj-$(CONFIG_FSL_ENETC_CORE) += fsl-enetc-core.o fsl-enetc-core-y := enetc.o enetc_cbdr.o enetc_ethtool.o +obj-$(CONFIG_NXP_ENETC_PF_COMMON) += nxp-enetc-pf-common.o +nxp-enetc-pf-common-y := enetc_pf_common.o + obj-$(CONFIG_FSL_ENETC) += fsl-enetc.o fsl-enetc-y := enetc_pf.o fsl-enetc-$(CONFIG_PCI_IOV) += enetc_msg.o fsl-enetc-$(CONFIG_FSL_ENETC_QOS) += enetc_qos.o +obj-$(CONFIG_NXP_ENETC4) += nxp-enetc4.o +nxp-enetc4-y := enetc4_pf.o + obj-$(CONFIG_FSL_ENETC_VF) += fsl-enetc-vf.o fsl-enetc-vf-y := enetc_vf.o @@ -19,3 +25,6 @@ fsl-enetc-mdio-y := enetc_pci_mdio.o enetc_mdio.o obj-$(CONFIG_FSL_ENETC_PTP_CLOCK) += fsl-enetc-ptp.o fsl-enetc-ptp-y := enetc_ptp.o + +obj-$(CONFIG_NXP_NETC_BLK_CTRL) += nxp-netc-blk-ctrl.o +nxp-netc-blk-ctrl-y := netc_blk_ctrl.o diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index c09370eab319..35634c516e26 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -3,6 +3,7 @@ #include "enetc.h" #include <linux/bpf_trace.h> +#include <linux/clk.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/vmalloc.h> @@ -21,7 +22,7 @@ void enetc_port_mac_wr(struct enetc_si *si, u32 reg, u32 val) { enetc_port_wr(&si->hw, reg, val); if (si->hw_features & ENETC_SI_F_QBU) - enetc_port_wr(&si->hw, reg + ENETC_PMAC_OFFSET, val); + enetc_port_wr(&si->hw, reg + si->drvdata->pmac_offset, val); } EXPORT_SYMBOL_GPL(enetc_port_mac_wr); @@ -700,8 +701,9 @@ static void enetc_rx_dim_work(struct work_struct *w) net_dim_get_rx_moderation(dim->mode, dim->profile_ix); struct enetc_int_vector *v = container_of(dim, struct enetc_int_vector, rx_dim); + struct enetc_ndev_priv *priv = netdev_priv(v->rx_ring.ndev); - v->rx_ictt = enetc_usecs_to_cycles(moder.usec); + v->rx_ictt = enetc_usecs_to_cycles(moder.usec, priv->sysclk_freq); dim->state = DIM_START_MEASURE; } @@ -718,7 +720,7 @@ static void enetc_rx_net_dim(struct enetc_int_vector *v) v->rx_ring.stats.packets, v->rx_ring.stats.bytes, &dim_sample); - net_dim(&v->rx_dim, dim_sample); + net_dim(&v->rx_dim, &dim_sample); } static int enetc_bd_ready_count(struct enetc_bdr *tx_ring, int ci) @@ -1736,9 +1738,15 @@ void enetc_get_si_caps(struct enetc_si *si) si->num_rx_rings = (val >> 16) & 0xff; si->num_tx_rings = val & 0xff; - val = enetc_rd(hw, ENETC_SIRFSCAPR); - si->num_fs_entries = ENETC_SIRFSCAPR_GET_NUM_RFS(val); - si->num_fs_entries = min(si->num_fs_entries, ENETC_MAX_RFS_SIZE); + val = enetc_rd(hw, ENETC_SIPCAPR0); + if (val & ENETC_SIPCAPR0_RFS) { + val = enetc_rd(hw, ENETC_SIRFSCAPR); + si->num_fs_entries = ENETC_SIRFSCAPR_GET_NUM_RFS(val); + si->num_fs_entries = min(si->num_fs_entries, ENETC_MAX_RFS_SIZE); + } else { + /* ENETC which not supports RFS */ + si->num_fs_entries = 0; + } si->num_rss = 0; val = enetc_rd(hw, ENETC_SIPCAPR0); @@ -2066,7 +2074,10 @@ int enetc_configure_si(struct enetc_ndev_priv *priv) /* enable SI */ enetc_wr(hw, ENETC_SIMR, ENETC_SIMR_EN); - if (si->num_rss) { + /* TODO: RSS support for i.MX95 will be supported later, and the + * is_enetc_rev1() condition will be removed + */ + if (si->num_rss && is_enetc_rev1(si)) { err = enetc_setup_default_rss_table(si, priv->num_rx_rings); if (err) return err; @@ -2090,9 +2101,9 @@ void enetc_init_si_rings_params(struct enetc_ndev_priv *priv) */ priv->num_rx_rings = min_t(int, cpus, si->num_rx_rings); priv->num_tx_rings = si->num_tx_rings; - priv->bdr_int_num = cpus; + priv->bdr_int_num = priv->num_rx_rings; priv->ic_mode = ENETC_IC_RX_ADAPTIVE | ENETC_IC_TX_MANUAL; - priv->tx_ictt = ENETC_TXIC_TIMETHR; + priv->tx_ictt = enetc_usecs_to_cycles(600, priv->sysclk_freq); } EXPORT_SYMBOL_GPL(enetc_init_si_rings_params); @@ -2501,10 +2512,14 @@ int enetc_open(struct net_device *ndev) extended = !!(priv->active_offloads & ENETC_F_RX_TSTAMP); - err = enetc_setup_irqs(priv); + err = clk_prepare_enable(priv->ref_clk); if (err) return err; + err = enetc_setup_irqs(priv); + if (err) + goto err_setup_irqs; + err = enetc_phylink_connect(ndev); if (err) goto err_phy_connect; @@ -2536,6 +2551,8 @@ err_alloc_tx: phylink_disconnect_phy(priv->phylink); err_phy_connect: enetc_free_irqs(priv); +err_setup_irqs: + clk_disable_unprepare(priv->ref_clk); return err; } @@ -2589,6 +2606,7 @@ int enetc_close(struct net_device *ndev) enetc_assign_tx_resources(priv, NULL); enetc_free_irqs(priv); + clk_disable_unprepare(priv->ref_clk); return 0; } @@ -2995,13 +3013,99 @@ int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd) } EXPORT_SYMBOL_GPL(enetc_ioctl); +static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i, + int v_tx_rings) +{ + struct enetc_int_vector *v; + struct enetc_bdr *bdr; + int j, err; + + v = kzalloc(struct_size(v, tx_ring, v_tx_rings), GFP_KERNEL); + if (!v) + return -ENOMEM; + + priv->int_vector[i] = v; + bdr = &v->rx_ring; + bdr->index = i; + bdr->ndev = priv->ndev; + bdr->dev = priv->dev; + bdr->bd_count = priv->rx_bd_count; + bdr->buffer_offset = ENETC_RXB_PAD; + priv->rx_ring[i] = bdr; + + err = xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0); + if (err) + goto free_vector; + + err = xdp_rxq_info_reg_mem_model(&bdr->xdp.rxq, MEM_TYPE_PAGE_SHARED, + NULL); + if (err) { + xdp_rxq_info_unreg(&bdr->xdp.rxq); + goto free_vector; + } + + /* init defaults for adaptive IC */ + if (priv->ic_mode & ENETC_IC_RX_ADAPTIVE) { + v->rx_ictt = 0x1; + v->rx_dim_en = true; + } + + INIT_WORK(&v->rx_dim.work, enetc_rx_dim_work); + netif_napi_add(priv->ndev, &v->napi, enetc_poll); + v->count_tx_rings = v_tx_rings; + + for (j = 0; j < v_tx_rings; j++) { + int idx; + + /* default tx ring mapping policy */ + idx = priv->bdr_int_num * j + i; + __set_bit(idx, &v->tx_rings_map); + bdr = &v->tx_ring[j]; + bdr->index = idx; + bdr->ndev = priv->ndev; + bdr->dev = priv->dev; + bdr->bd_count = priv->tx_bd_count; + priv->tx_ring[idx] = bdr; + } + + return 0; + +free_vector: + priv->rx_ring[i] = NULL; + priv->int_vector[i] = NULL; + kfree(v); + + return err; +} + +static void enetc_int_vector_destroy(struct enetc_ndev_priv *priv, int i) +{ + struct enetc_int_vector *v = priv->int_vector[i]; + struct enetc_bdr *rx_ring = &v->rx_ring; + int j, tx_ring_index; + + xdp_rxq_info_unreg_mem_model(&rx_ring->xdp.rxq); + xdp_rxq_info_unreg(&rx_ring->xdp.rxq); + netif_napi_del(&v->napi); + cancel_work_sync(&v->rx_dim.work); + + for (j = 0; j < v->count_tx_rings; j++) { + tx_ring_index = priv->bdr_int_num * j + i; + priv->tx_ring[tx_ring_index] = NULL; + } + + priv->rx_ring[i] = NULL; + priv->int_vector[i] = NULL; + kfree(v); +} + int enetc_alloc_msix(struct enetc_ndev_priv *priv) { struct pci_dev *pdev = priv->si->pdev; + int v_tx_rings, v_remainder; int num_stack_tx_queues; int first_xdp_tx_ring; int i, n, err, nvec; - int v_tx_rings; nvec = ENETC_BDR_INT_BASE_IDX + priv->bdr_int_num; /* allocate MSIX for both messaging and Rx/Tx interrupts */ @@ -3015,64 +3119,17 @@ int enetc_alloc_msix(struct enetc_ndev_priv *priv) /* # of tx rings per int vector */ v_tx_rings = priv->num_tx_rings / priv->bdr_int_num; + v_remainder = priv->num_tx_rings % priv->bdr_int_num; for (i = 0; i < priv->bdr_int_num; i++) { - struct enetc_int_vector *v; - struct enetc_bdr *bdr; - int j; - - v = kzalloc(struct_size(v, tx_ring, v_tx_rings), GFP_KERNEL); - if (!v) { - err = -ENOMEM; - goto fail; - } - - priv->int_vector[i] = v; - - bdr = &v->rx_ring; - bdr->index = i; - bdr->ndev = priv->ndev; - bdr->dev = priv->dev; - bdr->bd_count = priv->rx_bd_count; - bdr->buffer_offset = ENETC_RXB_PAD; - priv->rx_ring[i] = bdr; - - err = xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0); - if (err) { - kfree(v); - goto fail; - } + /* Distribute the remaining TX rings to the first v_remainder + * interrupt vectors + */ + int num_tx_rings = i < v_remainder ? v_tx_rings + 1 : v_tx_rings; - err = xdp_rxq_info_reg_mem_model(&bdr->xdp.rxq, - MEM_TYPE_PAGE_SHARED, NULL); - if (err) { - xdp_rxq_info_unreg(&bdr->xdp.rxq); - kfree(v); + err = enetc_int_vector_init(priv, i, num_tx_rings); + if (err) goto fail; - } - - /* init defaults for adaptive IC */ - if (priv->ic_mode & ENETC_IC_RX_ADAPTIVE) { - v->rx_ictt = 0x1; - v->rx_dim_en = true; - } - INIT_WORK(&v->rx_dim.work, enetc_rx_dim_work); - netif_napi_add(priv->ndev, &v->napi, enetc_poll); - v->count_tx_rings = v_tx_rings; - - for (j = 0; j < v_tx_rings; j++) { - int idx; - - /* default tx ring mapping policy */ - idx = priv->bdr_int_num * j + i; - __set_bit(idx, &v->tx_rings_map); - bdr = &v->tx_ring[j]; - bdr->index = idx; - bdr->ndev = priv->ndev; - bdr->dev = priv->dev; - bdr->bd_count = priv->tx_bd_count; - priv->tx_ring[idx] = bdr; - } } num_stack_tx_queues = enetc_num_stack_tx_queues(priv); @@ -3092,16 +3149,8 @@ int enetc_alloc_msix(struct enetc_ndev_priv *priv) return 0; fail: - while (i--) { - struct enetc_int_vector *v = priv->int_vector[i]; - struct enetc_bdr *rx_ring = &v->rx_ring; - - xdp_rxq_info_unreg_mem_model(&rx_ring->xdp.rxq); - xdp_rxq_info_unreg(&rx_ring->xdp.rxq); - netif_napi_del(&v->napi); - cancel_work_sync(&v->rx_dim.work); - kfree(v); - } + while (i--) + enetc_int_vector_destroy(priv, i); pci_free_irq_vectors(pdev); @@ -3113,26 +3162,8 @@ void enetc_free_msix(struct enetc_ndev_priv *priv) { int i; - for (i = 0; i < priv->bdr_int_num; i++) { - struct enetc_int_vector *v = priv->int_vector[i]; - struct enetc_bdr *rx_ring = &v->rx_ring; - - xdp_rxq_info_unreg_mem_model(&rx_ring->xdp.rxq); - xdp_rxq_info_unreg(&rx_ring->xdp.rxq); - netif_napi_del(&v->napi); - cancel_work_sync(&v->rx_dim.work); - } - - for (i = 0; i < priv->num_rx_rings; i++) - priv->rx_ring[i] = NULL; - - for (i = 0; i < priv->num_tx_rings; i++) - priv->tx_ring[i] = NULL; - - for (i = 0; i < priv->bdr_int_num; i++) { - kfree(priv->int_vector[i]); - priv->int_vector[i] = NULL; - } + for (i = 0; i < priv->bdr_int_num; i++) + enetc_int_vector_destroy(priv, i); /* disable all MSIX for this device */ pci_free_irq_vectors(priv->si->pdev); @@ -3241,5 +3272,55 @@ void enetc_pci_remove(struct pci_dev *pdev) } EXPORT_SYMBOL_GPL(enetc_pci_remove); +static const struct enetc_drvdata enetc_pf_data = { + .sysclk_freq = ENETC_CLK_400M, + .pmac_offset = ENETC_PMAC_OFFSET, + .eth_ops = &enetc_pf_ethtool_ops, +}; + +static const struct enetc_drvdata enetc4_pf_data = { + .sysclk_freq = ENETC_CLK_333M, + .pmac_offset = ENETC4_PMAC_OFFSET, + .eth_ops = &enetc4_pf_ethtool_ops, +}; + +static const struct enetc_drvdata enetc_vf_data = { + .sysclk_freq = ENETC_CLK_400M, + .eth_ops = &enetc_vf_ethtool_ops, +}; + +static const struct enetc_platform_info enetc_info[] = { + { .revision = ENETC_REV_1_0, + .dev_id = ENETC_DEV_ID_PF, + .data = &enetc_pf_data, + }, + { .revision = ENETC_REV_4_1, + .dev_id = NXP_ENETC_PF_DEV_ID, + .data = &enetc4_pf_data, + }, + { .revision = ENETC_REV_1_0, + .dev_id = ENETC_DEV_ID_VF, + .data = &enetc_vf_data, + }, +}; + +int enetc_get_driver_data(struct enetc_si *si) +{ + u16 dev_id = si->pdev->device; + int i; + + for (i = 0; i < ARRAY_SIZE(enetc_info); i++) { + if (si->revision == enetc_info[i].revision && + dev_id == enetc_info[i].dev_id) { + si->drvdata = enetc_info[i].data; + + return 0; + } + } + + return -ERANGE; +} +EXPORT_SYMBOL_GPL(enetc_get_driver_data); + MODULE_DESCRIPTION("NXP ENETC Ethernet driver"); MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index fb7d98d57783..72fa03dbc2dd 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -14,6 +14,7 @@ #include <net/xdp.h> #include "enetc_hw.h" +#include "enetc4_hw.h" #define ENETC_MAC_MAXFRM_SIZE 9600 #define ENETC_MAX_MTU (ENETC_MAC_MAXFRM_SIZE - \ @@ -231,6 +232,18 @@ enum enetc_errata { #define ENETC_SI_F_QBV BIT(1) #define ENETC_SI_F_QBU BIT(2) +struct enetc_drvdata { + u32 pmac_offset; /* Only valid for PSI which supports 802.1Qbu */ + u64 sysclk_freq; + const struct ethtool_ops *eth_ops; +}; + +struct enetc_platform_info { + u16 revision; + u16 dev_id; + const struct enetc_drvdata *data; +}; + /* PCI IEP device data */ struct enetc_si { struct pci_dev *pdev; @@ -246,11 +259,18 @@ struct enetc_si { int num_fs_entries; int num_rss; /* number of RSS buckets */ unsigned short pad; + u16 revision; int hw_features; + const struct enetc_drvdata *drvdata; }; #define ENETC_SI_ALIGN 32 +static inline bool is_enetc_rev1(struct enetc_si *si) +{ + return si->pdev->revision == ENETC_REV1; +} + static inline void *enetc_si_priv(const struct enetc_si *si) { return (char *)si + ALIGN(sizeof(struct enetc_si), ENETC_SI_ALIGN); @@ -302,7 +322,7 @@ struct enetc_cls_rule { int used; }; -#define ENETC_MAX_BDR_INT 2 /* fixed to max # of available cpus */ +#define ENETC_MAX_BDR_INT 6 /* fixed to max # of available cpus */ struct psfp_cap { u32 max_streamid; u32 max_psfp_filter; @@ -341,7 +361,6 @@ enum enetc_ic_mode { #define ENETC_RXIC_PKTTHR min_t(u32, 256, ENETC_RX_RING_DEFAULT_SIZE / 2) #define ENETC_TXIC_PKTTHR min_t(u32, 128, ENETC_TX_RING_DEFAULT_SIZE / 2) -#define ENETC_TXIC_TIMETHR enetc_usecs_to_cycles(600) struct enetc_ndev_priv { struct net_device *ndev; @@ -389,6 +408,9 @@ struct enetc_ndev_priv { * and link state updates */ struct mutex mm_lock; + + struct clk *ref_clk; /* RGMII/RMII reference clock */ + u64 sysclk_freq; /* NETC system clock frequency */ }; /* Messaging */ @@ -418,6 +440,7 @@ void enetc_init_si_rings_params(struct enetc_ndev_priv *priv); int enetc_alloc_si_resources(struct enetc_ndev_priv *priv); void enetc_free_si_resources(struct enetc_ndev_priv *priv); int enetc_configure_si(struct enetc_ndev_priv *priv); +int enetc_get_driver_data(struct enetc_si *si); int enetc_open(struct net_device *ndev); int enetc_close(struct net_device *ndev); @@ -434,6 +457,9 @@ int enetc_xdp_xmit(struct net_device *ndev, int num_frames, struct xdp_frame **frames, u32 flags); /* ethtool */ +extern const struct ethtool_ops enetc_pf_ethtool_ops; +extern const struct ethtool_ops enetc4_pf_ethtool_ops; +extern const struct ethtool_ops enetc_vf_ethtool_ops; void enetc_set_ethtool_ops(struct net_device *ndev); void enetc_mm_link_state_update(struct enetc_ndev_priv *priv, bool link); void enetc_mm_commit_preemptible_tcs(struct enetc_ndev_priv *priv); diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h new file mode 100644 index 000000000000..26b220677448 --- /dev/null +++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* + * This header file defines the register offsets and bit fields + * of ENETC4 PF and VFs. Note that the same registers as ENETC + * version 1.0 are defined in the enetc_hw.h file. + * + * Copyright 2024 NXP + */ +#ifndef __ENETC4_HW_H_ +#define __ENETC4_HW_H_ + +#define NXP_ENETC_VENDOR_ID 0x1131 +#define NXP_ENETC_PF_DEV_ID 0xe101 + +/***************************ENETC port registers**************************/ +#define ENETC4_ECAPR0 0x0 +#define ECAPR0_RFS BIT(2) +#define ECAPR0_TSD BIT(5) +#define ECAPR0_RSS BIT(8) +#define ECAPR0_RSC BIT(9) +#define ECAPR0_LSO BIT(10) +#define ECAPR0_WO BIT(13) + +#define ENETC4_ECAPR1 0x4 +#define ECAPR1_NUM_TCS GENMASK(6, 4) +#define ECAPR1_NUM_MCH GENMASK(9, 8) +#define ECAPR1_NUM_UCH GENMASK(11, 10) +#define ECAPR1_NUM_MSIX GENMASK(22, 12) +#define ECAPR1_NUM_VSI GENMASK(27, 24) +#define ECAPR1_NUM_IPV BIT(31) + +#define ENETC4_ECAPR2 0x8 +#define ECAPR2_NUM_TX_BDR GENMASK(9, 0) +#define ECAPR2_NUM_RX_BDR GENMASK(25, 16) + +#define ENETC4_PMR 0x10 +#define PMR_SI_EN(a) BIT((16 + (a))) + +/* Port Pause ON/OFF threshold register */ +#define ENETC4_PPAUONTR 0x108 +#define ENETC4_PPAUOFFTR 0x10c + +/* Port Station interface promiscuous MAC mode register */ +#define ENETC4_PSIPMMR 0x200 +#define PSIPMMR_SI_MAC_UP(a) BIT(a) /* a = SI index */ +#define PSIPMMR_SI_MAC_MP(a) BIT((a) + 16) + +/* Port Station interface promiscuous VLAN mode register */ +#define ENETC4_PSIPVMR 0x204 + +/* Port RSS key register n. n = 0,1,2,...,9 */ +#define ENETC4_PRSSKR(n) ((n) * 0x4 + 0x250) + +/* Port station interface MAC address filtering capability register */ +#define ENETC4_PSIMAFCAPR 0x280 +#define PSIMAFCAPR_NUM_MAC_AFTE GENMASK(11, 0) + +/* Port station interface VLAN filtering capability register */ +#define ENETC4_PSIVLANFCAPR 0x2c0 +#define PSIVLANFCAPR_NUM_VLAN_FTE GENMASK(11, 0) + +/* Port station interface VLAN filtering mode register */ +#define ENETC4_PSIVLANFMR 0x2c4 +#define PSIVLANFMR_VS BIT(0) + +/* Port Station interface a primary MAC address registers */ +#define ENETC4_PSIPMAR0(a) ((a) * 0x80 + 0x2000) +#define ENETC4_PSIPMAR1(a) ((a) * 0x80 + 0x2004) + +/* Port station interface a configuration register 0/2 */ +#define ENETC4_PSICFGR0(a) ((a) * 0x80 + 0x2010) +#define PSICFGR0_VASE BIT(13) +#define PSICFGR0_ASE BIT(15) +#define PSICFGR0_ANTI_SPOOFING (PSICFGR0_VASE | PSICFGR0_ASE) + +#define ENETC4_PSICFGR2(a) ((a) * 0x80 + 0x2018) +#define PSICFGR2_NUM_MSIX GENMASK(5, 0) + +#define ENETC4_PMCAPR 0x4004 +#define PMCAPR_HD BIT(8) +#define PMCAPR_FP GENMASK(10, 9) + +/* Port configuration register */ +#define ENETC4_PCR 0x4010 +#define PCR_HDR_FMT BIT(0) +#define PCR_L2DOSE BIT(4) +#define PCR_TIMER_CS BIT(8) +#define PCR_PSPEED GENMASK(29, 16) +#define PCR_PSPEED_VAL(speed) (((speed) / 10 - 1) << 16) + +/* Port MAC address register 0/1 */ +#define ENETC4_PMAR0 0x4020 +#define ENETC4_PMAR1 0x4024 + +/* Port operational register */ +#define ENETC4_POR 0x4100 + +/* Port traffic class a transmit maximum SDU register */ +#define ENETC4_PTCTMSDUR(a) ((a) * 0x20 + 0x4208) +#define PTCTMSDUR_MAXSDU GENMASK(15, 0) +#define PTCTMSDUR_SDU_TYPE GENMASK(17, 16) +#define SDU_TYPE_PPDU 0 +#define SDU_TYPE_MPDU 1 +#define SDU_TYPE_MSDU 2 + +#define ENETC4_PMAC_OFFSET 0x400 +#define ENETC4_PM_CMD_CFG(mac) (0x5008 + (mac) * 0x400) +#define PM_CMD_CFG_TX_EN BIT(0) +#define PM_CMD_CFG_RX_EN BIT(1) +#define PM_CMD_CFG_PAUSE_FWD BIT(7) +#define PM_CMD_CFG_PAUSE_IGN BIT(8) +#define PM_CMD_CFG_TX_ADDR_INS BIT(9) +#define PM_CMD_CFG_LOOP_EN BIT(10) +#define PM_CMD_CFG_LPBK_MODE GENMASK(12, 11) +#define LPBCK_MODE_EXT_TX_CLK 0 +#define LPBCK_MODE_MAC_LEVEL 1 +#define LPBCK_MODE_INT_TX_CLK 2 +#define PM_CMD_CFG_CNT_FRM_EN BIT(13) +#define PM_CMD_CFG_TXP BIT(15) +#define PM_CMD_CFG_SEND_IDLE BIT(16) +#define PM_CMD_CFG_HD_FCEN BIT(18) +#define PM_CMD_CFG_SFD BIT(21) +#define PM_CMD_CFG_TX_FLUSH BIT(22) +#define PM_CMD_CFG_TX_LOWP_EN BIT(23) +#define PM_CMD_CFG_RX_LOWP_EMPTY BIT(24) +#define PM_CMD_CFG_SWR BIT(26) +#define PM_CMD_CFG_TS_MODE BIT(30) +#define PM_CMD_CFG_MG BIT(31) + +/* Port MAC 0/1 Maximum Frame Length Register */ +#define ENETC4_PM_MAXFRM(mac) (0x5014 + (mac) * 0x400) + +/* Port MAC 0/1 Pause Quanta Register */ +#define ENETC4_PM_PAUSE_QUANTA(mac) (0x5054 + (mac) * 0x400) + +/* Port MAC 0/1 Pause Quanta Threshold Register */ +#define ENETC4_PM_PAUSE_THRESH(mac) (0x5064 + (mac) * 0x400) + +/* Port MAC 0 Interface Mode Control Register */ +#define ENETC4_PM_IF_MODE(mac) (0x5300 + (mac) * 0x400) +#define PM_IF_MODE_IFMODE GENMASK(2, 0) +#define IFMODE_XGMII 0 +#define IFMODE_RMII 3 +#define IFMODE_RGMII 4 +#define IFMODE_SGMII 5 +#define PM_IF_MODE_REVMII BIT(3) +#define PM_IF_MODE_M10 BIT(4) +#define PM_IF_MODE_HD BIT(6) +#define PM_IF_MODE_SSP GENMASK(14, 13) +#define SSP_100M 0 +#define SSP_10M 1 +#define SSP_1G 2 +#define PM_IF_MODE_ENA BIT(15) + +#endif diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c new file mode 100644 index 000000000000..fc41078c4f5d --- /dev/null +++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c @@ -0,0 +1,756 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* Copyright 2024 NXP */ + +#include <linux/clk.h> +#include <linux/module.h> +#include <linux/of_net.h> +#include <linux/of_platform.h> +#include <linux/unaligned.h> + +#include "enetc_pf_common.h" + +#define ENETC_SI_MAX_RING_NUM 8 + +static void enetc4_get_port_caps(struct enetc_pf *pf) +{ + struct enetc_hw *hw = &pf->si->hw; + u32 val; + + val = enetc_port_rd(hw, ENETC4_ECAPR1); + pf->caps.num_vsi = (val & ECAPR1_NUM_VSI) >> 24; + pf->caps.num_msix = ((val & ECAPR1_NUM_MSIX) >> 12) + 1; + + val = enetc_port_rd(hw, ENETC4_ECAPR2); + pf->caps.num_rx_bdr = (val & ECAPR2_NUM_RX_BDR) >> 16; + pf->caps.num_tx_bdr = val & ECAPR2_NUM_TX_BDR; + + val = enetc_port_rd(hw, ENETC4_PMCAPR); + pf->caps.half_duplex = (val & PMCAPR_HD) ? 1 : 0; +} + +static void enetc4_pf_set_si_primary_mac(struct enetc_hw *hw, int si, + const u8 *addr) +{ + u16 lower = get_unaligned_le16(addr + 4); + u32 upper = get_unaligned_le32(addr); + + if (si != 0) { + __raw_writel(upper, hw->port + ENETC4_PSIPMAR0(si)); + __raw_writew(lower, hw->port + ENETC4_PSIPMAR1(si)); + } else { + __raw_writel(upper, hw->port + ENETC4_PMAR0); + __raw_writew(lower, hw->port + ENETC4_PMAR1); + } +} + +static void enetc4_pf_get_si_primary_mac(struct enetc_hw *hw, int si, + u8 *addr) +{ + u32 upper; + u16 lower; + + upper = __raw_readl(hw->port + ENETC4_PSIPMAR0(si)); + lower = __raw_readw(hw->port + ENETC4_PSIPMAR1(si)); + + put_unaligned_le32(upper, addr); + put_unaligned_le16(lower, addr + 4); +} + +static const struct enetc_pf_ops enetc4_pf_ops = { + .set_si_primary_mac = enetc4_pf_set_si_primary_mac, + .get_si_primary_mac = enetc4_pf_get_si_primary_mac, +}; + +static int enetc4_pf_struct_init(struct enetc_si *si) +{ + struct enetc_pf *pf = enetc_si_priv(si); + + pf->si = si; + pf->total_vfs = pci_sriov_get_totalvfs(si->pdev); + pf->ops = &enetc4_pf_ops; + + enetc4_get_port_caps(pf); + + return 0; +} + +static u32 enetc4_psicfgr0_val_construct(bool is_vf, u32 num_tx_bdr, u32 num_rx_bdr) +{ + u32 val; + + val = ENETC_PSICFGR0_SET_TXBDR(num_tx_bdr); + val |= ENETC_PSICFGR0_SET_RXBDR(num_rx_bdr); + val |= ENETC_PSICFGR0_SIVC(ENETC_VLAN_TYPE_C | ENETC_VLAN_TYPE_S); + + if (is_vf) + val |= ENETC_PSICFGR0_VTE | ENETC_PSICFGR0_SIVIE; + + return val; +} + +static void enetc4_default_rings_allocation(struct enetc_pf *pf) +{ + struct enetc_hw *hw = &pf->si->hw; + u32 num_rx_bdr, num_tx_bdr, val; + u32 vf_tx_bdr, vf_rx_bdr; + int i, rx_rem, tx_rem; + + if (pf->caps.num_rx_bdr < ENETC_SI_MAX_RING_NUM + pf->caps.num_vsi) + num_rx_bdr = pf->caps.num_rx_bdr - pf->caps.num_vsi; + else + num_rx_bdr = ENETC_SI_MAX_RING_NUM; + + if (pf->caps.num_tx_bdr < ENETC_SI_MAX_RING_NUM + pf->caps.num_vsi) + num_tx_bdr = pf->caps.num_tx_bdr - pf->caps.num_vsi; + else + num_tx_bdr = ENETC_SI_MAX_RING_NUM; + + val = enetc4_psicfgr0_val_construct(false, num_tx_bdr, num_rx_bdr); + enetc_port_wr(hw, ENETC4_PSICFGR0(0), val); + + num_rx_bdr = pf->caps.num_rx_bdr - num_rx_bdr; + rx_rem = num_rx_bdr % pf->caps.num_vsi; + num_rx_bdr = num_rx_bdr / pf->caps.num_vsi; + + num_tx_bdr = pf->caps.num_tx_bdr - num_tx_bdr; + tx_rem = num_tx_bdr % pf->caps.num_vsi; + num_tx_bdr = num_tx_bdr / pf->caps.num_vsi; + + for (i = 0; i < pf->caps.num_vsi; i++) { + vf_tx_bdr = (i < tx_rem) ? num_tx_bdr + 1 : num_tx_bdr; + vf_rx_bdr = (i < rx_rem) ? num_rx_bdr + 1 : num_rx_bdr; + val = enetc4_psicfgr0_val_construct(true, vf_tx_bdr, vf_rx_bdr); + enetc_port_wr(hw, ENETC4_PSICFGR0(i + 1), val); + } +} + +static void enetc4_allocate_si_rings(struct enetc_pf *pf) +{ + enetc4_default_rings_allocation(pf); +} + +static void enetc4_pf_set_si_vlan_promisc(struct enetc_hw *hw, int si, bool en) +{ + u32 val = enetc_port_rd(hw, ENETC4_PSIPVMR); + + if (en) + val |= BIT(si); + else + val &= ~BIT(si); + + enetc_port_wr(hw, ENETC4_PSIPVMR, val); +} + +static void enetc4_set_default_si_vlan_promisc(struct enetc_pf *pf) +{ + struct enetc_hw *hw = &pf->si->hw; + int num_si = pf->caps.num_vsi + 1; + int i; + + /* enforce VLAN promiscuous mode for all SIs */ + for (i = 0; i < num_si; i++) + enetc4_pf_set_si_vlan_promisc(hw, i, true); +} + +/* Allocate the number of MSI-X vectors for per SI. */ +static void enetc4_set_si_msix_num(struct enetc_pf *pf) +{ + struct enetc_hw *hw = &pf->si->hw; + int i, num_msix, total_si; + u32 val; + + total_si = pf->caps.num_vsi + 1; + + num_msix = pf->caps.num_msix / total_si + + pf->caps.num_msix % total_si - 1; + val = num_msix & PSICFGR2_NUM_MSIX; + enetc_port_wr(hw, ENETC4_PSICFGR2(0), val); + + num_msix = pf->caps.num_msix / total_si - 1; + val = num_msix & PSICFGR2_NUM_MSIX; + for (i = 0; i < pf->caps.num_vsi; i++) + enetc_port_wr(hw, ENETC4_PSICFGR2(i + 1), val); +} + +static void enetc4_enable_all_si(struct enetc_pf *pf) +{ + struct enetc_hw *hw = &pf->si->hw; + int num_si = pf->caps.num_vsi + 1; + u32 si_bitmap = 0; + int i; + + /* Master enable for all SIs */ + for (i = 0; i < num_si; i++) + si_bitmap |= PMR_SI_EN(i); + + enetc_port_wr(hw, ENETC4_PMR, si_bitmap); +} + +static void enetc4_configure_port_si(struct enetc_pf *pf) +{ + struct enetc_hw *hw = &pf->si->hw; + + enetc4_allocate_si_rings(pf); + + /* Outer VLAN tag will be used for VLAN filtering */ + enetc_port_wr(hw, ENETC4_PSIVLANFMR, PSIVLANFMR_VS); + + enetc4_set_default_si_vlan_promisc(pf); + + /* Disable SI MAC multicast & unicast promiscuous */ + enetc_port_wr(hw, ENETC4_PSIPMMR, 0); + + enetc4_set_si_msix_num(pf); + + enetc4_enable_all_si(pf); +} + +static void enetc4_pf_reset_tc_msdu(struct enetc_hw *hw) +{ + u32 val = ENETC_MAC_MAXFRM_SIZE; + int tc; + + val = u32_replace_bits(val, SDU_TYPE_MPDU, PTCTMSDUR_SDU_TYPE); + + for (tc = 0; tc < ENETC_NUM_TC; tc++) + enetc_port_wr(hw, ENETC4_PTCTMSDUR(tc), val); +} + +static void enetc4_set_trx_frame_size(struct enetc_pf *pf) +{ + struct enetc_si *si = pf->si; + + enetc_port_mac_wr(si, ENETC4_PM_MAXFRM(0), + ENETC_SET_MAXFRM(ENETC_MAC_MAXFRM_SIZE)); + + enetc4_pf_reset_tc_msdu(&si->hw); +} + +static void enetc4_set_rss_key(struct enetc_hw *hw, const u8 *bytes) +{ + int i; + + for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++) + enetc_port_wr(hw, ENETC4_PRSSKR(i), ((u32 *)bytes)[i]); +} + +static void enetc4_set_default_rss_key(struct enetc_pf *pf) +{ + u8 hash_key[ENETC_RSSHASH_KEY_SIZE] = {0}; + struct enetc_hw *hw = &pf->si->hw; + + /* set up hash key */ + get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE); + enetc4_set_rss_key(hw, hash_key); +} + +static void enetc4_enable_trx(struct enetc_pf *pf) +{ + struct enetc_hw *hw = &pf->si->hw; + + /* Enable port transmit/receive */ + enetc_port_wr(hw, ENETC4_POR, 0); +} + +static void enetc4_configure_port(struct enetc_pf *pf) +{ + enetc4_configure_port_si(pf); + enetc4_set_trx_frame_size(pf); + enetc4_set_default_rss_key(pf); + enetc4_enable_trx(pf); +} + +static int enetc4_pf_init(struct enetc_pf *pf) +{ + struct device *dev = &pf->si->pdev->dev; + int err; + + /* Initialize the MAC address for PF and VFs */ + err = enetc_setup_mac_addresses(dev->of_node, pf); + if (err) { + dev_err(dev, "Failed to set MAC addresses\n"); + return err; + } + + enetc4_configure_port(pf); + + return 0; +} + +static const struct net_device_ops enetc4_ndev_ops = { + .ndo_open = enetc_open, + .ndo_stop = enetc_close, + .ndo_start_xmit = enetc_xmit, + .ndo_get_stats = enetc_get_stats, + .ndo_set_mac_address = enetc_pf_set_mac_addr, +}; + +static struct phylink_pcs * +enetc4_pl_mac_select_pcs(struct phylink_config *config, phy_interface_t iface) +{ + struct enetc_pf *pf = phylink_to_enetc_pf(config); + + return pf->pcs; +} + +static void enetc4_mac_config(struct enetc_pf *pf, unsigned int mode, + phy_interface_t phy_mode) +{ + struct enetc_ndev_priv *priv = netdev_priv(pf->si->ndev); + struct enetc_si *si = pf->si; + u32 val; + + val = enetc_port_mac_rd(si, ENETC4_PM_IF_MODE(0)); + val &= ~(PM_IF_MODE_IFMODE | PM_IF_MODE_ENA); + + switch (phy_mode) { + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + val |= IFMODE_RGMII; + /* We need to enable auto-negotiation for the MAC + * if its RGMII interface support In-Band status. + */ + if (phylink_autoneg_inband(mode)) + val |= PM_IF_MODE_ENA; + break; + case PHY_INTERFACE_MODE_RMII: + val |= IFMODE_RMII; + break; + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_2500BASEX: + val |= IFMODE_SGMII; + break; + case PHY_INTERFACE_MODE_10GBASER: + case PHY_INTERFACE_MODE_XGMII: + case PHY_INTERFACE_MODE_USXGMII: + val |= IFMODE_XGMII; + break; + default: + dev_err(priv->dev, + "Unsupported PHY mode:%d\n", phy_mode); + return; + } + + enetc_port_mac_wr(si, ENETC4_PM_IF_MODE(0), val); +} + +static void enetc4_pl_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) +{ + struct enetc_pf *pf = phylink_to_enetc_pf(config); + + enetc4_mac_config(pf, mode, state->interface); +} + +static void enetc4_set_port_speed(struct enetc_ndev_priv *priv, int speed) +{ + u32 old_speed = priv->speed; + u32 val; + + if (speed == old_speed) + return; + + val = enetc_port_rd(&priv->si->hw, ENETC4_PCR); + val &= ~PCR_PSPEED; + + switch (speed) { + case SPEED_100: + case SPEED_1000: + case SPEED_2500: + case SPEED_10000: + val |= (PCR_PSPEED & PCR_PSPEED_VAL(speed)); + break; + case SPEED_10: + default: + val |= (PCR_PSPEED & PCR_PSPEED_VAL(SPEED_10)); + } + + priv->speed = speed; + enetc_port_wr(&priv->si->hw, ENETC4_PCR, val); +} + +static void enetc4_set_rgmii_mac(struct enetc_pf *pf, int speed, int duplex) +{ + struct enetc_si *si = pf->si; + u32 old_val, val; + + old_val = enetc_port_mac_rd(si, ENETC4_PM_IF_MODE(0)); + val = old_val & ~(PM_IF_MODE_ENA | PM_IF_MODE_M10 | PM_IF_MODE_REVMII); + + switch (speed) { + case SPEED_1000: + val = u32_replace_bits(val, SSP_1G, PM_IF_MODE_SSP); + break; + case SPEED_100: + val = u32_replace_bits(val, SSP_100M, PM_IF_MODE_SSP); + break; + case SPEED_10: + val = u32_replace_bits(val, SSP_10M, PM_IF_MODE_SSP); + } + + val = u32_replace_bits(val, duplex == DUPLEX_FULL ? 0 : 1, + PM_IF_MODE_HD); + + if (val == old_val) + return; + + enetc_port_mac_wr(si, ENETC4_PM_IF_MODE(0), val); +} + +static void enetc4_set_rmii_mac(struct enetc_pf *pf, int speed, int duplex) +{ + struct enetc_si *si = pf->si; + u32 old_val, val; + + old_val = enetc_port_mac_rd(si, ENETC4_PM_IF_MODE(0)); + val = old_val & ~(PM_IF_MODE_ENA | PM_IF_MODE_SSP); + + switch (speed) { + case SPEED_100: + val &= ~PM_IF_MODE_M10; + break; + case SPEED_10: + val |= PM_IF_MODE_M10; + } + + val = u32_replace_bits(val, duplex == DUPLEX_FULL ? 0 : 1, + PM_IF_MODE_HD); + + if (val == old_val) + return; + + enetc_port_mac_wr(si, ENETC4_PM_IF_MODE(0), val); +} + +static void enetc4_set_hd_flow_control(struct enetc_pf *pf, bool enable) +{ + struct enetc_si *si = pf->si; + u32 old_val, val; + + if (!pf->caps.half_duplex) + return; + + old_val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0)); + val = u32_replace_bits(old_val, enable ? 1 : 0, PM_CMD_CFG_HD_FCEN); + if (val == old_val) + return; + + enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val); +} + +static void enetc4_set_rx_pause(struct enetc_pf *pf, bool rx_pause) +{ + struct enetc_si *si = pf->si; + u32 old_val, val; + + old_val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0)); + val = u32_replace_bits(old_val, rx_pause ? 0 : 1, PM_CMD_CFG_PAUSE_IGN); + if (val == old_val) + return; + + enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val); +} + +static void enetc4_set_tx_pause(struct enetc_pf *pf, int num_rxbdr, bool tx_pause) +{ + u32 pause_off_thresh = 0, pause_on_thresh = 0; + u32 init_quanta = 0, refresh_quanta = 0; + struct enetc_hw *hw = &pf->si->hw; + u32 rbmr, old_rbmr; + int i; + + for (i = 0; i < num_rxbdr; i++) { + old_rbmr = enetc_rxbdr_rd(hw, i, ENETC_RBMR); + rbmr = u32_replace_bits(old_rbmr, tx_pause ? 1 : 0, ENETC_RBMR_CM); + if (rbmr == old_rbmr) + continue; + + enetc_rxbdr_wr(hw, i, ENETC_RBMR, rbmr); + } + + if (tx_pause) { + /* When the port first enters congestion, send a PAUSE request + * with the maximum number of quanta. When the port exits + * congestion, it will automatically send a PAUSE frame with + * zero quanta. + */ + init_quanta = 0xffff; + + /* Also, set up the refresh timer to send follow-up PAUSE + * frames at half the quanta value, in case the congestion + * condition persists. + */ + refresh_quanta = 0xffff / 2; + + /* Start emitting PAUSE frames when 3 large frames (or more + * smaller frames) have accumulated in the FIFO waiting to be + * DMAed to the RX ring. + */ + pause_on_thresh = 3 * ENETC_MAC_MAXFRM_SIZE; + pause_off_thresh = 1 * ENETC_MAC_MAXFRM_SIZE; + } + + enetc_port_mac_wr(pf->si, ENETC4_PM_PAUSE_QUANTA(0), init_quanta); + enetc_port_mac_wr(pf->si, ENETC4_PM_PAUSE_THRESH(0), refresh_quanta); + enetc_port_wr(hw, ENETC4_PPAUONTR, pause_on_thresh); + enetc_port_wr(hw, ENETC4_PPAUOFFTR, pause_off_thresh); +} + +static void enetc4_enable_mac(struct enetc_pf *pf, bool en) +{ + struct enetc_si *si = pf->si; + u32 val; + + val = enetc_port_mac_rd(si, ENETC4_PM_CMD_CFG(0)); + val &= ~(PM_CMD_CFG_TX_EN | PM_CMD_CFG_RX_EN); + val |= en ? (PM_CMD_CFG_TX_EN | PM_CMD_CFG_RX_EN) : 0; + + enetc_port_mac_wr(si, ENETC4_PM_CMD_CFG(0), val); +} + +static void enetc4_pl_mac_link_up(struct phylink_config *config, + struct phy_device *phy, unsigned int mode, + phy_interface_t interface, int speed, + int duplex, bool tx_pause, bool rx_pause) +{ + struct enetc_pf *pf = phylink_to_enetc_pf(config); + struct enetc_si *si = pf->si; + struct enetc_ndev_priv *priv; + bool hd_fc = false; + + priv = netdev_priv(si->ndev); + enetc4_set_port_speed(priv, speed); + + if (!phylink_autoneg_inband(mode) && + phy_interface_mode_is_rgmii(interface)) + enetc4_set_rgmii_mac(pf, speed, duplex); + + if (interface == PHY_INTERFACE_MODE_RMII) + enetc4_set_rmii_mac(pf, speed, duplex); + + if (duplex == DUPLEX_FULL) { + /* When preemption is enabled, generation of PAUSE frames + * must be disabled, as stated in the IEEE 802.3 standard. + */ + if (priv->active_offloads & ENETC_F_QBU) + tx_pause = false; + } else { /* DUPLEX_HALF */ + if (tx_pause || rx_pause) + hd_fc = true; + + /* As per 802.3 annex 31B, PAUSE frames are only supported + * when the link is configured for full duplex operation. + */ + tx_pause = false; + rx_pause = false; + } + + enetc4_set_hd_flow_control(pf, hd_fc); + enetc4_set_tx_pause(pf, priv->num_rx_rings, tx_pause); + enetc4_set_rx_pause(pf, rx_pause); + enetc4_enable_mac(pf, true); +} + +static void enetc4_pl_mac_link_down(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ + struct enetc_pf *pf = phylink_to_enetc_pf(config); + + enetc4_enable_mac(pf, false); +} + +static const struct phylink_mac_ops enetc_pl_mac_ops = { + .mac_select_pcs = enetc4_pl_mac_select_pcs, + .mac_config = enetc4_pl_mac_config, + .mac_link_up = enetc4_pl_mac_link_up, + .mac_link_down = enetc4_pl_mac_link_down, +}; + +static void enetc4_pci_remove(void *data) +{ + struct pci_dev *pdev = data; + + enetc_pci_remove(pdev); +} + +static int enetc4_link_init(struct enetc_ndev_priv *priv, + struct device_node *node) +{ + struct enetc_pf *pf = enetc_si_priv(priv->si); + struct device *dev = priv->dev; + int err; + + err = of_get_phy_mode(node, &pf->if_mode); + if (err) { + dev_err(dev, "Failed to get PHY mode\n"); + return err; + } + + err = enetc_mdiobus_create(pf, node); + if (err) { + dev_err(dev, "Failed to create MDIO bus\n"); + return err; + } + + err = enetc_phylink_create(priv, node, &enetc_pl_mac_ops); + if (err) { + dev_err(dev, "Failed to create phylink\n"); + goto err_phylink_create; + } + + return 0; + +err_phylink_create: + enetc_mdiobus_destroy(pf); + + return err; +} + +static void enetc4_link_deinit(struct enetc_ndev_priv *priv) +{ + struct enetc_pf *pf = enetc_si_priv(priv->si); + + enetc_phylink_destroy(priv); + enetc_mdiobus_destroy(pf); +} + +static int enetc4_pf_netdev_create(struct enetc_si *si) +{ + struct device *dev = &si->pdev->dev; + struct enetc_ndev_priv *priv; + struct net_device *ndev; + int err; + + ndev = alloc_etherdev_mqs(sizeof(struct enetc_ndev_priv), + si->num_tx_rings, si->num_rx_rings); + if (!ndev) + return -ENOMEM; + + priv = netdev_priv(ndev); + priv->ref_clk = devm_clk_get_optional(dev, "ref"); + if (IS_ERR(priv->ref_clk)) { + dev_err(dev, "Get reference clock failed\n"); + err = PTR_ERR(priv->ref_clk); + goto err_clk_get; + } + + enetc_pf_netdev_setup(si, ndev, &enetc4_ndev_ops); + + enetc_init_si_rings_params(priv); + + err = enetc_configure_si(priv); + if (err) { + dev_err(dev, "Failed to configure SI\n"); + goto err_config_si; + } + + err = enetc_alloc_msix(priv); + if (err) { + dev_err(dev, "Failed to alloc MSI-X\n"); + goto err_alloc_msix; + } + + err = enetc4_link_init(priv, dev->of_node); + if (err) + goto err_link_init; + + err = register_netdev(ndev); + if (err) { + dev_err(dev, "Failed to register netdev\n"); + goto err_reg_netdev; + } + + return 0; + +err_reg_netdev: + enetc4_link_deinit(priv); +err_link_init: + enetc_free_msix(priv); +err_alloc_msix: +err_config_si: +err_clk_get: + mutex_destroy(&priv->mm_lock); + free_netdev(ndev); + + return err; +} + +static void enetc4_pf_netdev_destroy(struct enetc_si *si) +{ + struct enetc_ndev_priv *priv = netdev_priv(si->ndev); + struct net_device *ndev = si->ndev; + + unregister_netdev(ndev); + enetc_free_msix(priv); + free_netdev(ndev); +} + +static int enetc4_pf_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct device *dev = &pdev->dev; + struct enetc_si *si; + struct enetc_pf *pf; + int err; + + err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(*pf)); + if (err) + return dev_err_probe(dev, err, "PCIe probing failed\n"); + + err = devm_add_action_or_reset(dev, enetc4_pci_remove, pdev); + if (err) + return dev_err_probe(dev, err, + "Add enetc4_pci_remove() action failed\n"); + + /* si is the private data. */ + si = pci_get_drvdata(pdev); + if (!si->hw.port || !si->hw.global) + return dev_err_probe(dev, -ENODEV, + "Couldn't map PF only space\n"); + + si->revision = enetc_get_ip_revision(&si->hw); + err = enetc_get_driver_data(si); + if (err) + return dev_err_probe(dev, err, + "Could not get VF driver data\n"); + + err = enetc4_pf_struct_init(si); + if (err) + return err; + + pf = enetc_si_priv(si); + err = enetc4_pf_init(pf); + if (err) + return err; + + enetc_get_si_caps(si); + + return enetc4_pf_netdev_create(si); +} + +static void enetc4_pf_remove(struct pci_dev *pdev) +{ + struct enetc_si *si = pci_get_drvdata(pdev); + + enetc4_pf_netdev_destroy(si); +} + +static const struct pci_device_id enetc4_pf_id_table[] = { + { PCI_DEVICE(NXP_ENETC_VENDOR_ID, NXP_ENETC_PF_DEV_ID) }, + { 0, } /* End of table. */ +}; +MODULE_DEVICE_TABLE(pci, enetc4_pf_id_table); + +static struct pci_driver enetc4_pf_driver = { + .name = KBUILD_MODNAME, + .id_table = enetc4_pf_id_table, + .probe = enetc4_pf_probe, + .remove = enetc4_pf_remove, +}; +module_pci_driver(enetc4_pf_driver); + +MODULE_DESCRIPTION("ENETC4 PF Driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index 2563eb8ac7b6..bf34b5bb1e35 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -247,38 +247,25 @@ static int enetc_get_sset_count(struct net_device *ndev, int sset) static void enetc_get_strings(struct net_device *ndev, u32 stringset, u8 *data) { struct enetc_ndev_priv *priv = netdev_priv(ndev); - u8 *p = data; int i, j; switch (stringset) { case ETH_SS_STATS: - for (i = 0; i < ARRAY_SIZE(enetc_si_counters); i++) { - strscpy(p, enetc_si_counters[i].name, ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - for (i = 0; i < priv->num_tx_rings; i++) { - for (j = 0; j < ARRAY_SIZE(tx_ring_stats); j++) { - snprintf(p, ETH_GSTRING_LEN, tx_ring_stats[j], - i); - p += ETH_GSTRING_LEN; - } - } - for (i = 0; i < priv->num_rx_rings; i++) { - for (j = 0; j < ARRAY_SIZE(rx_ring_stats); j++) { - snprintf(p, ETH_GSTRING_LEN, rx_ring_stats[j], - i); - p += ETH_GSTRING_LEN; - } - } + for (i = 0; i < ARRAY_SIZE(enetc_si_counters); i++) + ethtool_puts(&data, enetc_si_counters[i].name); + for (i = 0; i < priv->num_tx_rings; i++) + for (j = 0; j < ARRAY_SIZE(tx_ring_stats); j++) + ethtool_sprintf(&data, tx_ring_stats[j], i); + for (i = 0; i < priv->num_rx_rings; i++) + for (j = 0; j < ARRAY_SIZE(rx_ring_stats); j++) + ethtool_sprintf(&data, rx_ring_stats[j], i); if (!enetc_si_is_pf(priv->si)) break; - for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++) { - strscpy(p, enetc_port_counters[i].name, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++) + ethtool_puts(&data, enetc_port_counters[i].name); + break; } } @@ -775,9 +762,10 @@ static int enetc_get_coalesce(struct net_device *ndev, { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_int_vector *v = priv->int_vector[0]; + u64 clk_freq = priv->sysclk_freq; - ic->tx_coalesce_usecs = enetc_cycles_to_usecs(priv->tx_ictt); - ic->rx_coalesce_usecs = enetc_cycles_to_usecs(v->rx_ictt); + ic->tx_coalesce_usecs = enetc_cycles_to_usecs(priv->tx_ictt, clk_freq); + ic->rx_coalesce_usecs = enetc_cycles_to_usecs(v->rx_ictt, clk_freq); ic->tx_max_coalesced_frames = ENETC_TXIC_PKTTHR; ic->rx_max_coalesced_frames = ENETC_RXIC_PKTTHR; @@ -793,12 +781,13 @@ static int enetc_set_coalesce(struct net_device *ndev, struct netlink_ext_ack *extack) { struct enetc_ndev_priv *priv = netdev_priv(ndev); + u64 clk_freq = priv->sysclk_freq; u32 rx_ictt, tx_ictt; int i, ic_mode; bool changed; - tx_ictt = enetc_usecs_to_cycles(ic->tx_coalesce_usecs); - rx_ictt = enetc_usecs_to_cycles(ic->rx_coalesce_usecs); + tx_ictt = enetc_usecs_to_cycles(ic->tx_coalesce_usecs, clk_freq); + rx_ictt = enetc_usecs_to_cycles(ic->rx_coalesce_usecs, clk_freq); if (ic->rx_max_coalesced_frames != ENETC_RXIC_PKTTHR) return -EOPNOTSUPP; @@ -1178,7 +1167,7 @@ void enetc_mm_link_state_update(struct enetc_ndev_priv *priv, bool link) } EXPORT_SYMBOL_GPL(enetc_mm_link_state_update); -static const struct ethtool_ops enetc_pf_ethtool_ops = { +const struct ethtool_ops enetc_pf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USE_ADAPTIVE_RX, @@ -1213,7 +1202,7 @@ static const struct ethtool_ops enetc_pf_ethtool_ops = { .get_mm_stats = enetc_get_mm_stats, }; -static const struct ethtool_ops enetc_vf_ethtool_ops = { +const struct ethtool_ops enetc_vf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USE_ADAPTIVE_RX, @@ -1234,13 +1223,26 @@ static const struct ethtool_ops enetc_vf_ethtool_ops = { .get_ts_info = enetc_get_ts_info, }; +const struct ethtool_ops enetc4_pf_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_MAX_FRAMES | + ETHTOOL_COALESCE_USE_ADAPTIVE_RX, + .get_ringparam = enetc_get_ringparam, + .get_coalesce = enetc_get_coalesce, + .set_coalesce = enetc_set_coalesce, + .get_link_ksettings = enetc_get_link_ksettings, + .set_link_ksettings = enetc_set_link_ksettings, + .get_link = ethtool_op_get_link, + .get_wol = enetc_get_wol, + .set_wol = enetc_set_wol, + .get_pauseparam = enetc_get_pauseparam, + .set_pauseparam = enetc_set_pauseparam, +}; + void enetc_set_ethtool_ops(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); - if (enetc_si_is_pf(priv->si)) - ndev->ethtool_ops = &enetc_pf_ethtool_ops; - else - ndev->ethtool_ops = &enetc_vf_ethtool_ops; + ndev->ethtool_ops = priv->si->drvdata->eth_ops; } EXPORT_SYMBOL_GPL(enetc_set_ethtool_ops); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 1619943fb263..7c3285584f8a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -6,6 +6,8 @@ #define ENETC_MM_VERIFY_SLEEP_US USEC_PER_MSEC #define ENETC_MM_VERIFY_RETRIES 3 +#define ENETC_NUM_TC 8 + /* ENETC device IDs */ #define ENETC_DEV_ID_PF 0xe100 #define ENETC_DEV_ID_VF 0xef00 @@ -25,6 +27,7 @@ #define ENETC_SIPCAPR0_RSS BIT(8) #define ENETC_SIPCAPR0_QBV BIT(4) #define ENETC_SIPCAPR0_QBU BIT(3) +#define ENETC_SIPCAPR0_RFS BIT(2) #define ENETC_SIPCAPR1 0x24 #define ENETC_SITGTGR 0x30 #define ENETC_SIRBGCR 0x38 @@ -368,6 +371,10 @@ enum enetc_bdr_type {TX, RX}; /** Global regs, offset: 2_0000h */ #define ENETC_GLOBAL_BASE 0x20000 #define ENETC_G_EIPBRR0 0x0bf8 +#define EIPBRR0_REVISION GENMASK(15, 0) +#define ENETC_REV_1_0 0x0100 +#define ENETC_REV_4_1 0X0401 + #define ENETC_G_EIPBRR1 0x0bfc #define ENETC_G_EPFBLPR(n) (0xd00 + 4 * (n)) #define ENETC_G_EPFBLPR1_XGMII 0x80000000 @@ -396,18 +403,22 @@ struct enetc_hw { */ extern rwlock_t enetc_mdio_lock; +DECLARE_STATIC_KEY_FALSE(enetc_has_err050089); + /* use this locking primitive only on the fast datapath to * group together multiple non-MDIO register accesses to * minimize the overhead of the lock */ static inline void enetc_lock_mdio(void) { - read_lock(&enetc_mdio_lock); + if (static_branch_unlikely(&enetc_has_err050089)) + read_lock(&enetc_mdio_lock); } static inline void enetc_unlock_mdio(void) { - read_unlock(&enetc_mdio_lock); + if (static_branch_unlikely(&enetc_has_err050089)) + read_unlock(&enetc_mdio_lock); } /* use these accessors only on the fast datapath under @@ -416,14 +427,16 @@ static inline void enetc_unlock_mdio(void) */ static inline u32 enetc_rd_reg_hot(void __iomem *reg) { - lockdep_assert_held(&enetc_mdio_lock); + if (static_branch_unlikely(&enetc_has_err050089)) + lockdep_assert_held(&enetc_mdio_lock); return ioread32(reg); } static inline void enetc_wr_reg_hot(void __iomem *reg, u32 val) { - lockdep_assert_held(&enetc_mdio_lock); + if (static_branch_unlikely(&enetc_has_err050089)) + lockdep_assert_held(&enetc_mdio_lock); iowrite32(val, reg); } @@ -452,9 +465,13 @@ static inline u32 _enetc_rd_mdio_reg_wa(void __iomem *reg) unsigned long flags; u32 val; - write_lock_irqsave(&enetc_mdio_lock, flags); - val = ioread32(reg); - write_unlock_irqrestore(&enetc_mdio_lock, flags); + if (static_branch_unlikely(&enetc_has_err050089)) { + write_lock_irqsave(&enetc_mdio_lock, flags); + val = ioread32(reg); + write_unlock_irqrestore(&enetc_mdio_lock, flags); + } else { + val = ioread32(reg); + } return val; } @@ -463,9 +480,13 @@ static inline void _enetc_wr_mdio_reg_wa(void __iomem *reg, u32 val) { unsigned long flags; - write_lock_irqsave(&enetc_mdio_lock, flags); - iowrite32(val, reg); - write_unlock_irqrestore(&enetc_mdio_lock, flags); + if (static_branch_unlikely(&enetc_has_err050089)) { + write_lock_irqsave(&enetc_mdio_lock, flags); + iowrite32(val, reg); + write_unlock_irqrestore(&enetc_mdio_lock, flags); + } else { + iowrite32(val, reg); + } } #ifdef ioread64 @@ -957,15 +978,17 @@ struct enetc_cbd { u8 status_flags; }; -#define ENETC_CLK 400000000ULL -static inline u32 enetc_cycles_to_usecs(u32 cycles) +#define ENETC_CLK_400M 400000000ULL +#define ENETC_CLK_333M 333000000ULL + +static inline u32 enetc_cycles_to_usecs(u32 cycles, u64 clk_freq) { - return (u32)div_u64(cycles * 1000000ULL, ENETC_CLK); + return (u32)div_u64(cycles * 1000000ULL, clk_freq); } -static inline u32 enetc_usecs_to_cycles(u32 usecs) +static inline u32 enetc_usecs_to_cycles(u32 usecs, u64 clk_freq) { - return (u32)div_u64(usecs * ENETC_CLK, 1000000ULL); + return (u32)div_u64(usecs * clk_freq, 1000000ULL); } /* Port traffic class frame preemption register */ diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c index a1b595bd7993..e108cac8288d 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c @@ -4,11 +4,35 @@ #include <linux/of_mdio.h> #include "enetc_pf.h" +#define NETC_EMDIO_VEN_ID 0x1131 +#define NETC_EMDIO_DEV_ID 0xee00 #define ENETC_MDIO_DEV_ID 0xee01 #define ENETC_MDIO_DEV_NAME "FSL PCIe IE Central MDIO" #define ENETC_MDIO_BUS_NAME ENETC_MDIO_DEV_NAME " Bus" #define ENETC_MDIO_DRV_NAME ENETC_MDIO_DEV_NAME " driver" +DEFINE_STATIC_KEY_FALSE(enetc_has_err050089); +EXPORT_SYMBOL_GPL(enetc_has_err050089); + +static void enetc_emdio_enable_err050089(struct pci_dev *pdev) +{ + if (pdev->vendor == PCI_VENDOR_ID_FREESCALE && + pdev->device == ENETC_MDIO_DEV_ID) { + static_branch_inc(&enetc_has_err050089); + dev_info(&pdev->dev, "Enabled ERR050089 workaround\n"); + } +} + +static void enetc_emdio_disable_err050089(struct pci_dev *pdev) +{ + if (pdev->vendor == PCI_VENDOR_ID_FREESCALE && + pdev->device == ENETC_MDIO_DEV_ID) { + static_branch_dec(&enetc_has_err050089); + if (!static_key_enabled(&enetc_has_err050089.key)) + dev_info(&pdev->dev, "Disabled ERR050089 workaround\n"); + } +} + static int enetc_pci_mdio_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -62,6 +86,8 @@ static int enetc_pci_mdio_probe(struct pci_dev *pdev, goto err_pci_mem_reg; } + enetc_emdio_enable_err050089(pdev); + err = of_mdiobus_register(bus, dev->of_node); if (err) goto err_mdiobus_reg; @@ -71,6 +97,7 @@ static int enetc_pci_mdio_probe(struct pci_dev *pdev, return 0; err_mdiobus_reg: + enetc_emdio_disable_err050089(pdev); pci_release_region(pdev, 0); err_pci_mem_reg: pci_disable_device(pdev); @@ -88,6 +115,9 @@ static void enetc_pci_mdio_remove(struct pci_dev *pdev) struct enetc_mdio_priv *mdio_priv; mdiobus_unregister(bus); + + enetc_emdio_disable_err050089(pdev); + mdio_priv = bus->priv; iounmap(mdio_priv->hw->port); pci_release_region(pdev, 0); @@ -96,6 +126,7 @@ static void enetc_pci_mdio_remove(struct pci_dev *pdev) static const struct pci_device_id enetc_pci_mdio_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_MDIO_DEV_ID) }, + { PCI_DEVICE(NETC_EMDIO_VEN_ID, NETC_EMDIO_DEV_ID) }, { 0, } /* End of table. */ }; MODULE_DEVICE_TABLE(pci, enetc_pci_mdio_id_table); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 8f6b0bf48139..c47b4a743d93 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -2,15 +2,13 @@ /* Copyright 2017-2019 NXP */ #include <linux/unaligned.h> -#include <linux/mdio.h> #include <linux/module.h> -#include <linux/fsl/enetc_mdio.h> +#include <linux/of.h> #include <linux/of_platform.h> -#include <linux/of_mdio.h> #include <linux/of_net.h> #include <linux/pcs-lynx.h> #include "enetc_ierb.h" -#include "enetc_pf.h" +#include "enetc_pf_common.h" #define ENETC_DRV_NAME_STR "ENETC PF driver" @@ -33,18 +31,15 @@ static void enetc_pf_set_primary_mac_addr(struct enetc_hw *hw, int si, __raw_writew(lower, hw->port + ENETC_PSIPMAR1(si)); } -static int enetc_pf_set_mac_addr(struct net_device *ndev, void *addr) +static struct phylink_pcs *enetc_pf_create_pcs(struct enetc_pf *pf, + struct mii_bus *bus) { - struct enetc_ndev_priv *priv = netdev_priv(ndev); - struct sockaddr *saddr = addr; - - if (!is_valid_ether_addr(saddr->sa_data)) - return -EADDRNOTAVAIL; - - eth_hw_addr_set(ndev, saddr->sa_data); - enetc_pf_set_primary_mac_addr(&priv->si->hw, 0, saddr->sa_data); + return lynx_pcs_create_mdiodev(bus, 0); +} - return 0; +static void enetc_pf_destroy_pcs(struct phylink_pcs *pcs) +{ + lynx_pcs_destroy(pcs); } static void enetc_set_vlan_promisc(struct enetc_hw *hw, char si_map) @@ -393,56 +388,6 @@ static int enetc_pf_set_vf_spoofchk(struct net_device *ndev, int vf, bool en) return 0; } -static int enetc_setup_mac_address(struct device_node *np, struct enetc_pf *pf, - int si) -{ - struct device *dev = &pf->si->pdev->dev; - struct enetc_hw *hw = &pf->si->hw; - u8 mac_addr[ETH_ALEN] = { 0 }; - int err; - - /* (1) try to get the MAC address from the device tree */ - if (np) { - err = of_get_mac_address(np, mac_addr); - if (err == -EPROBE_DEFER) - return err; - } - - /* (2) bootloader supplied MAC address */ - if (is_zero_ether_addr(mac_addr)) - enetc_pf_get_primary_mac_addr(hw, si, mac_addr); - - /* (3) choose a random one */ - if (is_zero_ether_addr(mac_addr)) { - eth_random_addr(mac_addr); - dev_info(dev, "no MAC address specified for SI%d, using %pM\n", - si, mac_addr); - } - - enetc_pf_set_primary_mac_addr(hw, si, mac_addr); - - return 0; -} - -static int enetc_setup_mac_addresses(struct device_node *np, - struct enetc_pf *pf) -{ - int err, i; - - /* The PF might take its MAC from the device tree */ - err = enetc_setup_mac_address(np, pf, 0); - if (err) - return err; - - for (i = 0; i < pf->total_vfs; i++) { - err = enetc_setup_mac_address(NULL, pf, i + 1); - if (err) - return err; - } - - return 0; -} - static void enetc_port_assign_rfs_entries(struct enetc_si *si) { struct enetc_pf *pf = enetc_si_priv(si); @@ -665,19 +610,11 @@ static int enetc_sriov_configure(struct pci_dev *pdev, int num_vfs) if (!num_vfs) { enetc_msg_psi_free(pf); - kfree(pf->vf_state); pf->num_vfs = 0; pci_disable_sriov(pdev); } else { pf->num_vfs = num_vfs; - pf->vf_state = kcalloc(num_vfs, sizeof(struct enetc_vf_state), - GFP_KERNEL); - if (!pf->vf_state) { - pf->num_vfs = 0; - return -ENOMEM; - } - err = enetc_msg_psi_init(pf); if (err) { dev_err(&pdev->dev, "enetc_msg_psi_init (%d)\n", err); @@ -696,7 +633,6 @@ static int enetc_sriov_configure(struct pci_dev *pdev, int num_vfs) err_en_sriov: enetc_msg_psi_free(pf); err_msg_psi: - kfree(pf->vf_state); pf->num_vfs = 0; return err; @@ -775,187 +711,6 @@ static const struct net_device_ops enetc_ndev_ops = { .ndo_xdp_xmit = enetc_xdp_xmit, }; -static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, - const struct net_device_ops *ndev_ops) -{ - struct enetc_ndev_priv *priv = netdev_priv(ndev); - - SET_NETDEV_DEV(ndev, &si->pdev->dev); - priv->ndev = ndev; - priv->si = si; - priv->dev = &si->pdev->dev; - si->ndev = ndev; - - priv->msg_enable = (NETIF_MSG_WOL << 1) - 1; - ndev->netdev_ops = ndev_ops; - enetc_set_ethtool_ops(ndev); - ndev->watchdog_timeo = 5 * HZ; - ndev->max_mtu = ENETC_MAX_MTU; - - ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | - NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK | - NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; - ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; - ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM | - NETIF_F_TSO | NETIF_F_TSO6; - - if (si->num_rss) - ndev->hw_features |= NETIF_F_RXHASH; - - ndev->priv_flags |= IFF_UNICAST_FLT; - ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | - NETDEV_XDP_ACT_NDO_XMIT_SG; - - if (si->hw_features & ENETC_SI_F_PSFP && !enetc_psfp_enable(priv)) { - priv->active_offloads |= ENETC_F_QCI; - ndev->features |= NETIF_F_HW_TC; - ndev->hw_features |= NETIF_F_HW_TC; - } - - /* pick up primary MAC address from SI */ - enetc_load_primary_mac_addr(&si->hw, ndev); -} - -static int enetc_mdio_probe(struct enetc_pf *pf, struct device_node *np) -{ - struct device *dev = &pf->si->pdev->dev; - struct enetc_mdio_priv *mdio_priv; - struct mii_bus *bus; - int err; - - bus = devm_mdiobus_alloc_size(dev, sizeof(*mdio_priv)); - if (!bus) - return -ENOMEM; - - bus->name = "Freescale ENETC MDIO Bus"; - bus->read = enetc_mdio_read_c22; - bus->write = enetc_mdio_write_c22; - bus->read_c45 = enetc_mdio_read_c45; - bus->write_c45 = enetc_mdio_write_c45; - bus->parent = dev; - mdio_priv = bus->priv; - mdio_priv->hw = &pf->si->hw; - mdio_priv->mdio_base = ENETC_EMDIO_BASE; - snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev)); - - err = of_mdiobus_register(bus, np); - if (err) - return dev_err_probe(dev, err, "cannot register MDIO bus\n"); - - pf->mdio = bus; - - return 0; -} - -static void enetc_mdio_remove(struct enetc_pf *pf) -{ - if (pf->mdio) - mdiobus_unregister(pf->mdio); -} - -static int enetc_imdio_create(struct enetc_pf *pf) -{ - struct device *dev = &pf->si->pdev->dev; - struct enetc_mdio_priv *mdio_priv; - struct phylink_pcs *phylink_pcs; - struct mii_bus *bus; - int err; - - bus = mdiobus_alloc_size(sizeof(*mdio_priv)); - if (!bus) - return -ENOMEM; - - bus->name = "Freescale ENETC internal MDIO Bus"; - bus->read = enetc_mdio_read_c22; - bus->write = enetc_mdio_write_c22; - bus->read_c45 = enetc_mdio_read_c45; - bus->write_c45 = enetc_mdio_write_c45; - bus->parent = dev; - bus->phy_mask = ~0; - mdio_priv = bus->priv; - mdio_priv->hw = &pf->si->hw; - mdio_priv->mdio_base = ENETC_PM_IMDIO_BASE; - snprintf(bus->id, MII_BUS_ID_SIZE, "%s-imdio", dev_name(dev)); - - err = mdiobus_register(bus); - if (err) { - dev_err(dev, "cannot register internal MDIO bus (%d)\n", err); - goto free_mdio_bus; - } - - phylink_pcs = lynx_pcs_create_mdiodev(bus, 0); - if (IS_ERR(phylink_pcs)) { - err = PTR_ERR(phylink_pcs); - dev_err(dev, "cannot create lynx pcs (%d)\n", err); - goto unregister_mdiobus; - } - - pf->imdio = bus; - pf->pcs = phylink_pcs; - - return 0; - -unregister_mdiobus: - mdiobus_unregister(bus); -free_mdio_bus: - mdiobus_free(bus); - return err; -} - -static void enetc_imdio_remove(struct enetc_pf *pf) -{ - if (pf->pcs) - lynx_pcs_destroy(pf->pcs); - if (pf->imdio) { - mdiobus_unregister(pf->imdio); - mdiobus_free(pf->imdio); - } -} - -static bool enetc_port_has_pcs(struct enetc_pf *pf) -{ - return (pf->if_mode == PHY_INTERFACE_MODE_SGMII || - pf->if_mode == PHY_INTERFACE_MODE_1000BASEX || - pf->if_mode == PHY_INTERFACE_MODE_2500BASEX || - pf->if_mode == PHY_INTERFACE_MODE_USXGMII); -} - -static int enetc_mdiobus_create(struct enetc_pf *pf, struct device_node *node) -{ - struct device_node *mdio_np; - int err; - - mdio_np = of_get_child_by_name(node, "mdio"); - if (mdio_np) { - err = enetc_mdio_probe(pf, mdio_np); - - of_node_put(mdio_np); - if (err) - return err; - } - - if (enetc_port_has_pcs(pf)) { - err = enetc_imdio_create(pf); - if (err) { - enetc_mdio_remove(pf); - return err; - } - } - - return 0; -} - -static void enetc_mdiobus_destroy(struct enetc_pf *pf) -{ - enetc_mdio_remove(pf); - enetc_imdio_remove(pf); -} - static struct phylink_pcs * enetc_pl_mac_select_pcs(struct phylink_config *config, phy_interface_t iface) { @@ -1101,47 +856,6 @@ static const struct phylink_mac_ops enetc_mac_phylink_ops = { .mac_link_down = enetc_pl_mac_link_down, }; -static int enetc_phylink_create(struct enetc_ndev_priv *priv, - struct device_node *node) -{ - struct enetc_pf *pf = enetc_si_priv(priv->si); - struct phylink *phylink; - int err; - - pf->phylink_config.dev = &priv->ndev->dev; - pf->phylink_config.type = PHYLINK_NETDEV; - pf->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | - MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD; - - __set_bit(PHY_INTERFACE_MODE_INTERNAL, - pf->phylink_config.supported_interfaces); - __set_bit(PHY_INTERFACE_MODE_SGMII, - pf->phylink_config.supported_interfaces); - __set_bit(PHY_INTERFACE_MODE_1000BASEX, - pf->phylink_config.supported_interfaces); - __set_bit(PHY_INTERFACE_MODE_2500BASEX, - pf->phylink_config.supported_interfaces); - __set_bit(PHY_INTERFACE_MODE_USXGMII, - pf->phylink_config.supported_interfaces); - phy_interface_set_rgmii(pf->phylink_config.supported_interfaces); - - phylink = phylink_create(&pf->phylink_config, of_fwnode_handle(node), - pf->if_mode, &enetc_mac_phylink_ops); - if (IS_ERR(phylink)) { - err = PTR_ERR(phylink); - return err; - } - - priv->phylink = phylink; - - return 0; -} - -static void enetc_phylink_destroy(struct enetc_ndev_priv *priv) -{ - phylink_destroy(priv->phylink); -} - /* Initialize the entire shared memory for the flow steering entries * of this port (PF + VFs) */ @@ -1224,6 +938,13 @@ static struct enetc_si *enetc_psi_create(struct pci_dev *pdev) goto out_pci_remove; } + si->revision = enetc_get_ip_revision(&si->hw); + err = enetc_get_driver_data(si); + if (err) { + dev_err(&pdev->dev, "Could not get PF driver data\n"); + goto out_pci_remove; + } + err = enetc_setup_cbdr(&pdev->dev, &si->hw, ENETC_CBDR_DEFAULT_SIZE, &si->cbd_ring); if (err) @@ -1259,6 +980,14 @@ static void enetc_psi_destroy(struct pci_dev *pdev) enetc_pci_remove(pdev); } +static const struct enetc_pf_ops enetc_pf_ops = { + .set_si_primary_mac = enetc_pf_set_primary_mac_addr, + .get_si_primary_mac = enetc_pf_get_primary_mac_addr, + .create_pcs = enetc_pf_create_pcs, + .destroy_pcs = enetc_pf_destroy_pcs, + .enable_psfp = enetc_psfp_enable, +}; + static int enetc_pf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -1285,7 +1014,15 @@ static int enetc_pf_probe(struct pci_dev *pdev, pf = enetc_si_priv(si); pf->si = si; + pf->ops = &enetc_pf_ops; + pf->total_vfs = pci_sriov_get_totalvfs(pdev); + if (pf->total_vfs) { + pf->vf_state = kcalloc(pf->total_vfs, sizeof(struct enetc_vf_state), + GFP_KERNEL); + if (!pf->vf_state) + goto err_alloc_vf_state; + } err = enetc_setup_mac_addresses(node, pf); if (err) @@ -1338,7 +1075,7 @@ static int enetc_pf_probe(struct pci_dev *pdev, if (err) goto err_mdiobus_create; - err = enetc_phylink_create(priv, node); + err = enetc_phylink_create(priv, node, &enetc_mac_phylink_ops); if (err) goto err_phylink_create; @@ -1363,6 +1100,8 @@ err_alloc_si_res: free_netdev(ndev); err_alloc_netdev: err_setup_mac_addresses: + kfree(pf->vf_state); +err_alloc_vf_state: enetc_psi_destroy(pdev); err_psi_create: return err; @@ -1389,6 +1128,7 @@ static void enetc_pf_remove(struct pci_dev *pdev) enetc_free_si_resources(priv); free_netdev(si->ndev); + kfree(pf->vf_state); enetc_psi_destroy(pdev); } diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h index c26bd66e4597..a26a12863855 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h @@ -28,6 +28,24 @@ struct enetc_vf_state { enum enetc_vf_flags flags; }; +struct enetc_port_caps { + u32 half_duplex:1; + int num_vsi; + int num_msix; + int num_rx_bdr; + int num_tx_bdr; +}; + +struct enetc_pf; + +struct enetc_pf_ops { + void (*set_si_primary_mac)(struct enetc_hw *hw, int si, const u8 *addr); + void (*get_si_primary_mac)(struct enetc_hw *hw, int si, u8 *addr); + struct phylink_pcs *(*create_pcs)(struct enetc_pf *pf, struct mii_bus *bus); + void (*destroy_pcs)(struct phylink_pcs *pcs); + int (*enable_psfp)(struct enetc_ndev_priv *priv); +}; + struct enetc_pf { struct enetc_si *si; int num_vfs; /* number of active VFs, after sriov_init */ @@ -50,6 +68,9 @@ struct enetc_pf { phy_interface_t if_mode; struct phylink_config phylink_config; + + struct enetc_port_caps caps; + const struct enetc_pf_ops *ops; }; #define phylink_to_enetc_pf(config) \ diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c new file mode 100644 index 000000000000..0eecfc833164 --- /dev/null +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* Copyright 2024 NXP */ + +#include <linux/fsl/enetc_mdio.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> + +#include "enetc_pf_common.h" + +static void enetc_set_si_hw_addr(struct enetc_pf *pf, int si, + const u8 *mac_addr) +{ + struct enetc_hw *hw = &pf->si->hw; + + pf->ops->set_si_primary_mac(hw, si, mac_addr); +} + +static void enetc_get_si_hw_addr(struct enetc_pf *pf, int si, u8 *mac_addr) +{ + struct enetc_hw *hw = &pf->si->hw; + + pf->ops->get_si_primary_mac(hw, si, mac_addr); +} + +int enetc_pf_set_mac_addr(struct net_device *ndev, void *addr) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_pf *pf = enetc_si_priv(priv->si); + struct sockaddr *saddr = addr; + + if (!is_valid_ether_addr(saddr->sa_data)) + return -EADDRNOTAVAIL; + + eth_hw_addr_set(ndev, saddr->sa_data); + enetc_set_si_hw_addr(pf, 0, saddr->sa_data); + + return 0; +} +EXPORT_SYMBOL_GPL(enetc_pf_set_mac_addr); + +static int enetc_setup_mac_address(struct device_node *np, struct enetc_pf *pf, + int si) +{ + struct device *dev = &pf->si->pdev->dev; + u8 mac_addr[ETH_ALEN] = { 0 }; + int err; + + /* (1) try to get the MAC address from the device tree */ + if (np) { + err = of_get_mac_address(np, mac_addr); + if (err == -EPROBE_DEFER) + return err; + } + + /* (2) bootloader supplied MAC address */ + if (is_zero_ether_addr(mac_addr)) + enetc_get_si_hw_addr(pf, si, mac_addr); + + /* (3) choose a random one */ + if (is_zero_ether_addr(mac_addr)) { + eth_random_addr(mac_addr); + dev_info(dev, "no MAC address specified for SI%d, using %pM\n", + si, mac_addr); + } + + enetc_set_si_hw_addr(pf, si, mac_addr); + + return 0; +} + +int enetc_setup_mac_addresses(struct device_node *np, struct enetc_pf *pf) +{ + int err, i; + + /* The PF might take its MAC from the device tree */ + err = enetc_setup_mac_address(np, pf, 0); + if (err) + return err; + + for (i = 0; i < pf->total_vfs; i++) { + err = enetc_setup_mac_address(NULL, pf, i + 1); + if (err) + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(enetc_setup_mac_addresses); + +void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, + const struct net_device_ops *ndev_ops) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_pf *pf = enetc_si_priv(si); + + SET_NETDEV_DEV(ndev, &si->pdev->dev); + priv->ndev = ndev; + priv->si = si; + priv->dev = &si->pdev->dev; + si->ndev = ndev; + + priv->msg_enable = (NETIF_MSG_WOL << 1) - 1; + priv->sysclk_freq = si->drvdata->sysclk_freq; + ndev->netdev_ops = ndev_ops; + enetc_set_ethtool_ops(ndev); + ndev->watchdog_timeo = 5 * HZ; + ndev->max_mtu = ENETC_MAX_MTU; + + ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | + NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK | + NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; + ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6; + ndev->vlan_features = NETIF_F_SG | NETIF_F_HW_CSUM | + NETIF_F_TSO | NETIF_F_TSO6; + + ndev->priv_flags |= IFF_UNICAST_FLT; + + /* TODO: currently, i.MX95 ENETC driver does not support advanced features */ + if (!is_enetc_rev1(si)) { + ndev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK); + goto end; + } + + if (si->num_rss) + ndev->hw_features |= NETIF_F_RXHASH; + + ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG; + + if (si->hw_features & ENETC_SI_F_PSFP && pf->ops->enable_psfp && + !pf->ops->enable_psfp(priv)) { + priv->active_offloads |= ENETC_F_QCI; + ndev->features |= NETIF_F_HW_TC; + ndev->hw_features |= NETIF_F_HW_TC; + } + +end: + /* pick up primary MAC address from SI */ + enetc_load_primary_mac_addr(&si->hw, ndev); +} +EXPORT_SYMBOL_GPL(enetc_pf_netdev_setup); + +static int enetc_mdio_probe(struct enetc_pf *pf, struct device_node *np) +{ + struct device *dev = &pf->si->pdev->dev; + struct enetc_mdio_priv *mdio_priv; + struct mii_bus *bus; + int err; + + bus = devm_mdiobus_alloc_size(dev, sizeof(*mdio_priv)); + if (!bus) + return -ENOMEM; + + bus->name = "Freescale ENETC MDIO Bus"; + bus->read = enetc_mdio_read_c22; + bus->write = enetc_mdio_write_c22; + bus->read_c45 = enetc_mdio_read_c45; + bus->write_c45 = enetc_mdio_write_c45; + bus->parent = dev; + mdio_priv = bus->priv; + mdio_priv->hw = &pf->si->hw; + mdio_priv->mdio_base = ENETC_EMDIO_BASE; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev)); + + err = of_mdiobus_register(bus, np); + if (err) + return dev_err_probe(dev, err, "cannot register MDIO bus\n"); + + pf->mdio = bus; + + return 0; +} + +static void enetc_mdio_remove(struct enetc_pf *pf) +{ + if (pf->mdio) + mdiobus_unregister(pf->mdio); +} + +static int enetc_imdio_create(struct enetc_pf *pf) +{ + struct device *dev = &pf->si->pdev->dev; + struct enetc_mdio_priv *mdio_priv; + struct phylink_pcs *phylink_pcs; + struct mii_bus *bus; + int err; + + if (!pf->ops->create_pcs) { + dev_err(dev, "Creating PCS is not supported\n"); + + return -EOPNOTSUPP; + } + + bus = mdiobus_alloc_size(sizeof(*mdio_priv)); + if (!bus) + return -ENOMEM; + + bus->name = "Freescale ENETC internal MDIO Bus"; + bus->read = enetc_mdio_read_c22; + bus->write = enetc_mdio_write_c22; + bus->read_c45 = enetc_mdio_read_c45; + bus->write_c45 = enetc_mdio_write_c45; + bus->parent = dev; + bus->phy_mask = ~0; + mdio_priv = bus->priv; + mdio_priv->hw = &pf->si->hw; + mdio_priv->mdio_base = ENETC_PM_IMDIO_BASE; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-imdio", dev_name(dev)); + + err = mdiobus_register(bus); + if (err) { + dev_err(dev, "cannot register internal MDIO bus (%d)\n", err); + goto free_mdio_bus; + } + + phylink_pcs = pf->ops->create_pcs(pf, bus); + if (IS_ERR(phylink_pcs)) { + err = PTR_ERR(phylink_pcs); + dev_err(dev, "cannot create lynx pcs (%d)\n", err); + goto unregister_mdiobus; + } + + pf->imdio = bus; + pf->pcs = phylink_pcs; + + return 0; + +unregister_mdiobus: + mdiobus_unregister(bus); +free_mdio_bus: + mdiobus_free(bus); + return err; +} + +static void enetc_imdio_remove(struct enetc_pf *pf) +{ + if (pf->pcs && pf->ops->destroy_pcs) + pf->ops->destroy_pcs(pf->pcs); + + if (pf->imdio) { + mdiobus_unregister(pf->imdio); + mdiobus_free(pf->imdio); + } +} + +static bool enetc_port_has_pcs(struct enetc_pf *pf) +{ + return (pf->if_mode == PHY_INTERFACE_MODE_SGMII || + pf->if_mode == PHY_INTERFACE_MODE_1000BASEX || + pf->if_mode == PHY_INTERFACE_MODE_2500BASEX || + pf->if_mode == PHY_INTERFACE_MODE_USXGMII); +} + +int enetc_mdiobus_create(struct enetc_pf *pf, struct device_node *node) +{ + struct device_node *mdio_np; + int err; + + mdio_np = of_get_child_by_name(node, "mdio"); + if (mdio_np) { + err = enetc_mdio_probe(pf, mdio_np); + + of_node_put(mdio_np); + if (err) + return err; + } + + if (enetc_port_has_pcs(pf)) { + err = enetc_imdio_create(pf); + if (err) { + enetc_mdio_remove(pf); + return err; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(enetc_mdiobus_create); + +void enetc_mdiobus_destroy(struct enetc_pf *pf) +{ + enetc_mdio_remove(pf); + enetc_imdio_remove(pf); +} +EXPORT_SYMBOL_GPL(enetc_mdiobus_destroy); + +int enetc_phylink_create(struct enetc_ndev_priv *priv, struct device_node *node, + const struct phylink_mac_ops *ops) +{ + struct enetc_pf *pf = enetc_si_priv(priv->si); + struct phylink *phylink; + int err; + + pf->phylink_config.dev = &priv->ndev->dev; + pf->phylink_config.type = PHYLINK_NETDEV; + pf->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD; + + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + pf->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_SGMII, + pf->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, + pf->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_2500BASEX, + pf->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_USXGMII, + pf->phylink_config.supported_interfaces); + phy_interface_set_rgmii(pf->phylink_config.supported_interfaces); + + phylink = phylink_create(&pf->phylink_config, of_fwnode_handle(node), + pf->if_mode, ops); + if (IS_ERR(phylink)) { + err = PTR_ERR(phylink); + return err; + } + + priv->phylink = phylink; + + return 0; +} +EXPORT_SYMBOL_GPL(enetc_phylink_create); + +void enetc_phylink_destroy(struct enetc_ndev_priv *priv) +{ + phylink_destroy(priv->phylink); +} +EXPORT_SYMBOL_GPL(enetc_phylink_destroy); + +MODULE_DESCRIPTION("NXP ENETC PF common functionality driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h new file mode 100644 index 000000000000..48f55ee743ad --- /dev/null +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* Copyright 2024 NXP */ + +#include "enetc_pf.h" + +int enetc_pf_set_mac_addr(struct net_device *ndev, void *addr); +int enetc_setup_mac_addresses(struct device_node *np, struct enetc_pf *pf); +void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, + const struct net_device_ops *ndev_ops); +int enetc_mdiobus_create(struct enetc_pf *pf, struct device_node *node); +void enetc_mdiobus_destroy(struct enetc_pf *pf); +int enetc_phylink_create(struct enetc_ndev_priv *priv, struct device_node *node, + const struct phylink_mac_ops *ops); +void enetc_phylink_destroy(struct enetc_ndev_priv *priv); + +static inline u16 enetc_get_ip_revision(struct enetc_hw *hw) +{ + return enetc_global_rd(hw, ENETC_G_EIPBRR0) & EIPBRR0_REVISION; +} diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index b65da49dd926..ccf86651455c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -336,7 +336,7 @@ int enetc_setup_tc_cbs(struct net_device *ndev, void *type_data) * * (enetClockFrequency / portTransmitRate) * 100 */ - hi_credit_reg = (u32)div_u64((ENETC_CLK * 100ULL) * hi_credit_bit, + hi_credit_reg = (u32)div_u64((priv->sysclk_freq * 100ULL) * hi_credit_bit, port_transmit_rate * 1000000ULL); enetc_port_wr(hw, ENETC_PTCCBSR1(tc), hi_credit_reg); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c index dfcaac302e24..d18c11e406fc 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c @@ -78,11 +78,18 @@ static int enetc_vf_set_mac_addr(struct net_device *ndev, void *addr) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct sockaddr *saddr = addr; + int err; if (!is_valid_ether_addr(saddr->sa_data)) return -EADDRNOTAVAIL; - return enetc_msg_vsi_set_primary_mac_addr(priv, saddr); + err = enetc_msg_vsi_set_primary_mac_addr(priv, saddr); + if (err) + return err; + + eth_hw_addr_set(ndev, saddr->sa_data); + + return 0; } static int enetc_vf_set_features(struct net_device *ndev, @@ -128,6 +135,7 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev, si->ndev = ndev; priv->msg_enable = (NETIF_MSG_IFUP << 1) - 1; + priv->sysclk_freq = si->drvdata->sysclk_freq; ndev->netdev_ops = ndev_ops; enetc_set_ethtool_ops(ndev); ndev->watchdog_timeo = 5 * HZ; @@ -164,6 +172,11 @@ static int enetc_vf_probe(struct pci_dev *pdev, return dev_err_probe(&pdev->dev, err, "PCI probing failed\n"); si = pci_get_drvdata(pdev); + si->revision = ENETC_REV_1_0; + err = enetc_get_driver_data(si); + if (err) + return dev_err_probe(&pdev->dev, err, + "Could not get VF driver data\n"); enetc_get_si_caps(si); diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c new file mode 100644 index 000000000000..bcb8eefeb93c --- /dev/null +++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c @@ -0,0 +1,445 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* + * NXP NETC Blocks Control Driver + * + * Copyright 2024 NXP + * + * This driver is used for pre-initialization of NETC, such as PCS and MII + * protocols, LDID, warm reset, etc. Therefore, all NETC device drivers can + * only be probed after the netc-blk-crtl driver has completed initialization. + * In addition, when the system enters suspend mode, IERB, PRB, and NETCMIX + * will be powered off, except for WOL. Therefore, when the system resumes, + * these blocks need to be reinitialized. + */ + +#include <linux/bits.h> +#include <linux/clk.h> +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/fsl/netc_global.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_net.h> +#include <linux/of_platform.h> +#include <linux/phy.h> +#include <linux/platform_device.h> +#include <linux/seq_file.h> + +/* NETCMIX registers */ +#define IMX95_CFG_LINK_IO_VAR 0x0 +#define IO_VAR_16FF_16G_SERDES 0x1 +#define IO_VAR(port, var) (((var) & 0xf) << ((port) << 2)) + +#define IMX95_CFG_LINK_MII_PROT 0x4 +#define CFG_LINK_MII_PORT_0 GENMASK(3, 0) +#define CFG_LINK_MII_PORT_1 GENMASK(7, 4) +#define MII_PROT_MII 0x0 +#define MII_PROT_RMII 0x1 +#define MII_PROT_RGMII 0x2 +#define MII_PROT_SERIAL 0x3 +#define MII_PROT(port, prot) (((prot) & 0xf) << ((port) << 2)) + +#define IMX95_CFG_LINK_PCS_PROT(a) (0x8 + (a) * 4) +#define PCS_PROT_1G_SGMII BIT(0) +#define PCS_PROT_2500M_SGMII BIT(1) +#define PCS_PROT_XFI BIT(3) +#define PCS_PROT_SFI BIT(4) +#define PCS_PROT_10G_SXGMII BIT(6) + +/* NETC privileged register block register */ +#define PRB_NETCRR 0x100 +#define NETCRR_SR BIT(0) +#define NETCRR_LOCK BIT(1) + +#define PRB_NETCSR 0x104 +#define NETCSR_ERROR BIT(0) +#define NETCSR_STATE BIT(1) + +/* NETC integrated endpoint register block register */ +#define IERB_EMDIOFAUXR 0x344 +#define IERB_T0FAUXR 0x444 +#define IERB_EFAUXR(a) (0x3044 + 0x100 * (a)) +#define IERB_VFAUXR(a) (0x4004 + 0x40 * (a)) +#define FAUXR_LDID GENMASK(3, 0) + +/* Platform information */ +#define IMX95_ENETC0_BUS_DEVFN 0x0 +#define IMX95_ENETC1_BUS_DEVFN 0x40 +#define IMX95_ENETC2_BUS_DEVFN 0x80 + +/* Flags for different platforms */ +#define NETC_HAS_NETCMIX BIT(0) + +struct netc_devinfo { + u32 flags; + int (*netcmix_init)(struct platform_device *pdev); + int (*ierb_init)(struct platform_device *pdev); +}; + +struct netc_blk_ctrl { + void __iomem *prb; + void __iomem *ierb; + void __iomem *netcmix; + + const struct netc_devinfo *devinfo; + struct platform_device *pdev; + struct dentry *debugfs_root; +}; + +static void netc_reg_write(void __iomem *base, u32 offset, u32 val) +{ + netc_write(base + offset, val); +} + +static u32 netc_reg_read(void __iomem *base, u32 offset) +{ + return netc_read(base + offset); +} + +static int netc_of_pci_get_bus_devfn(struct device_node *np) +{ + u32 reg[5]; + int error; + + error = of_property_read_u32_array(np, "reg", reg, ARRAY_SIZE(reg)); + if (error) + return error; + + return (reg[0] >> 8) & 0xffff; +} + +static int netc_get_link_mii_protocol(phy_interface_t interface) +{ + switch (interface) { + case PHY_INTERFACE_MODE_MII: + return MII_PROT_MII; + case PHY_INTERFACE_MODE_RMII: + return MII_PROT_RMII; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + return MII_PROT_RGMII; + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_2500BASEX: + case PHY_INTERFACE_MODE_10GBASER: + case PHY_INTERFACE_MODE_XGMII: + case PHY_INTERFACE_MODE_USXGMII: + return MII_PROT_SERIAL; + default: + return -EINVAL; + } +} + +static int imx95_netcmix_init(struct platform_device *pdev) +{ + struct netc_blk_ctrl *priv = platform_get_drvdata(pdev); + struct device_node *np = pdev->dev.of_node; + phy_interface_t interface; + int bus_devfn, mii_proto; + u32 val; + int err; + + /* Default setting of MII protocol */ + val = MII_PROT(0, MII_PROT_RGMII) | MII_PROT(1, MII_PROT_RGMII) | + MII_PROT(2, MII_PROT_SERIAL); + + /* Update the link MII protocol through parsing phy-mode */ + for_each_available_child_of_node_scoped(np, child) { + for_each_available_child_of_node_scoped(child, gchild) { + if (!of_device_is_compatible(gchild, "pci1131,e101")) + continue; + + bus_devfn = netc_of_pci_get_bus_devfn(gchild); + if (bus_devfn < 0) + return -EINVAL; + + if (bus_devfn == IMX95_ENETC2_BUS_DEVFN) + continue; + + err = of_get_phy_mode(gchild, &interface); + if (err) + continue; + + mii_proto = netc_get_link_mii_protocol(interface); + if (mii_proto < 0) + return -EINVAL; + + switch (bus_devfn) { + case IMX95_ENETC0_BUS_DEVFN: + val = u32_replace_bits(val, mii_proto, + CFG_LINK_MII_PORT_0); + break; + case IMX95_ENETC1_BUS_DEVFN: + val = u32_replace_bits(val, mii_proto, + CFG_LINK_MII_PORT_1); + break; + default: + return -EINVAL; + } + } + } + + /* Configure Link I/O variant */ + netc_reg_write(priv->netcmix, IMX95_CFG_LINK_IO_VAR, + IO_VAR(2, IO_VAR_16FF_16G_SERDES)); + /* Configure Link 2 PCS protocol */ + netc_reg_write(priv->netcmix, IMX95_CFG_LINK_PCS_PROT(2), + PCS_PROT_10G_SXGMII); + netc_reg_write(priv->netcmix, IMX95_CFG_LINK_MII_PROT, val); + + return 0; +} + +static bool netc_ierb_is_locked(struct netc_blk_ctrl *priv) +{ + return !!(netc_reg_read(priv->prb, PRB_NETCRR) & NETCRR_LOCK); +} + +static int netc_lock_ierb(struct netc_blk_ctrl *priv) +{ + u32 val; + + netc_reg_write(priv->prb, PRB_NETCRR, NETCRR_LOCK); + + return read_poll_timeout(netc_reg_read, val, !(val & NETCSR_STATE), + 100, 2000, false, priv->prb, PRB_NETCSR); +} + +static int netc_unlock_ierb_with_warm_reset(struct netc_blk_ctrl *priv) +{ + u32 val; + + netc_reg_write(priv->prb, PRB_NETCRR, 0); + + return read_poll_timeout(netc_reg_read, val, !(val & NETCRR_LOCK), + 1000, 100000, true, priv->prb, PRB_NETCRR); +} + +static int imx95_ierb_init(struct platform_device *pdev) +{ + struct netc_blk_ctrl *priv = platform_get_drvdata(pdev); + + /* EMDIO : No MSI-X intterupt */ + netc_reg_write(priv->ierb, IERB_EMDIOFAUXR, 0); + /* ENETC0 PF */ + netc_reg_write(priv->ierb, IERB_EFAUXR(0), 0); + /* ENETC0 VF0 */ + netc_reg_write(priv->ierb, IERB_VFAUXR(0), 1); + /* ENETC0 VF1 */ + netc_reg_write(priv->ierb, IERB_VFAUXR(1), 2); + /* ENETC1 PF */ + netc_reg_write(priv->ierb, IERB_EFAUXR(1), 3); + /* ENETC1 VF0 */ + netc_reg_write(priv->ierb, IERB_VFAUXR(2), 5); + /* ENETC1 VF1 */ + netc_reg_write(priv->ierb, IERB_VFAUXR(3), 6); + /* ENETC2 PF */ + netc_reg_write(priv->ierb, IERB_EFAUXR(2), 4); + /* ENETC2 VF0 */ + netc_reg_write(priv->ierb, IERB_VFAUXR(4), 5); + /* ENETC2 VF1 */ + netc_reg_write(priv->ierb, IERB_VFAUXR(5), 6); + /* NETC TIMER */ + netc_reg_write(priv->ierb, IERB_T0FAUXR, 7); + + return 0; +} + +static int netc_ierb_init(struct platform_device *pdev) +{ + struct netc_blk_ctrl *priv = platform_get_drvdata(pdev); + const struct netc_devinfo *devinfo = priv->devinfo; + int err; + + if (netc_ierb_is_locked(priv)) { + err = netc_unlock_ierb_with_warm_reset(priv); + if (err) { + dev_err(&pdev->dev, "Unlock IERB failed.\n"); + return err; + } + } + + if (devinfo->ierb_init) { + err = devinfo->ierb_init(pdev); + if (err) + return err; + } + + err = netc_lock_ierb(priv); + if (err) { + dev_err(&pdev->dev, "Lock IERB failed.\n"); + return err; + } + + return 0; +} + +#if IS_ENABLED(CONFIG_DEBUG_FS) +static int netc_prb_show(struct seq_file *s, void *data) +{ + struct netc_blk_ctrl *priv = s->private; + u32 val; + + val = netc_reg_read(priv->prb, PRB_NETCRR); + seq_printf(s, "[PRB NETCRR] Lock:%d SR:%d\n", + (val & NETCRR_LOCK) ? 1 : 0, + (val & NETCRR_SR) ? 1 : 0); + + val = netc_reg_read(priv->prb, PRB_NETCSR); + seq_printf(s, "[PRB NETCSR] State:%d Error:%d\n", + (val & NETCSR_STATE) ? 1 : 0, + (val & NETCSR_ERROR) ? 1 : 0); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(netc_prb); + +static void netc_blk_ctrl_create_debugfs(struct netc_blk_ctrl *priv) +{ + struct dentry *root; + + root = debugfs_create_dir("netc_blk_ctrl", NULL); + if (IS_ERR(root)) + return; + + priv->debugfs_root = root; + + debugfs_create_file("prb", 0444, root, priv, &netc_prb_fops); +} + +static void netc_blk_ctrl_remove_debugfs(struct netc_blk_ctrl *priv) +{ + debugfs_remove_recursive(priv->debugfs_root); + priv->debugfs_root = NULL; +} + +#else + +static void netc_blk_ctrl_create_debugfs(struct netc_blk_ctrl *priv) +{ +} + +static void netc_blk_ctrl_remove_debugfs(struct netc_blk_ctrl *priv) +{ +} +#endif + +static int netc_prb_check_error(struct netc_blk_ctrl *priv) +{ + if (netc_reg_read(priv->prb, PRB_NETCSR) & NETCSR_ERROR) + return -1; + + return 0; +} + +static const struct netc_devinfo imx95_devinfo = { + .flags = NETC_HAS_NETCMIX, + .netcmix_init = imx95_netcmix_init, + .ierb_init = imx95_ierb_init, +}; + +static const struct of_device_id netc_blk_ctrl_match[] = { + { .compatible = "nxp,imx95-netc-blk-ctrl", .data = &imx95_devinfo }, + {}, +}; +MODULE_DEVICE_TABLE(of, netc_blk_ctrl_match); + +static int netc_blk_ctrl_probe(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + const struct netc_devinfo *devinfo; + struct device *dev = &pdev->dev; + const struct of_device_id *id; + struct netc_blk_ctrl *priv; + struct clk *ipg_clk; + void __iomem *regs; + int err; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->pdev = pdev; + ipg_clk = devm_clk_get_optional_enabled(dev, "ipg"); + if (IS_ERR(ipg_clk)) + return dev_err_probe(dev, PTR_ERR(ipg_clk), + "Set ipg clock failed\n"); + + id = of_match_device(netc_blk_ctrl_match, dev); + if (!id) + return dev_err_probe(dev, -EINVAL, "Cannot match device\n"); + + devinfo = (struct netc_devinfo *)id->data; + if (!devinfo) + return dev_err_probe(dev, -EINVAL, "No device information\n"); + + priv->devinfo = devinfo; + regs = devm_platform_ioremap_resource_byname(pdev, "ierb"); + if (IS_ERR(regs)) + return dev_err_probe(dev, PTR_ERR(regs), + "Missing IERB resource\n"); + + priv->ierb = regs; + regs = devm_platform_ioremap_resource_byname(pdev, "prb"); + if (IS_ERR(regs)) + return dev_err_probe(dev, PTR_ERR(regs), + "Missing PRB resource\n"); + + priv->prb = regs; + if (devinfo->flags & NETC_HAS_NETCMIX) { + regs = devm_platform_ioremap_resource_byname(pdev, "netcmix"); + if (IS_ERR(regs)) + return dev_err_probe(dev, PTR_ERR(regs), + "Missing NETCMIX resource\n"); + priv->netcmix = regs; + } + + platform_set_drvdata(pdev, priv); + if (devinfo->netcmix_init) { + err = devinfo->netcmix_init(pdev); + if (err) + return dev_err_probe(dev, err, + "Initializing NETCMIX failed\n"); + } + + err = netc_ierb_init(pdev); + if (err) + return dev_err_probe(dev, err, "Initializing IERB failed\n"); + + if (netc_prb_check_error(priv) < 0) + dev_warn(dev, "The current IERB configuration is invalid\n"); + + netc_blk_ctrl_create_debugfs(priv); + + err = of_platform_populate(node, NULL, NULL, dev); + if (err) { + netc_blk_ctrl_remove_debugfs(priv); + return dev_err_probe(dev, err, "of_platform_populate failed\n"); + } + + return 0; +} + +static void netc_blk_ctrl_remove(struct platform_device *pdev) +{ + struct netc_blk_ctrl *priv = platform_get_drvdata(pdev); + + of_platform_depopulate(&pdev->dev); + netc_blk_ctrl_remove_debugfs(priv); +} + +static struct platform_driver netc_blk_ctrl_driver = { + .driver = { + .name = "nxp-netc-blk-ctrl", + .of_match_table = netc_blk_ctrl_match, + }, + .probe = netc_blk_ctrl_probe, + .remove = netc_blk_ctrl_remove, +}; + +module_platform_driver(netc_blk_ctrl_driver); + +MODULE_DESCRIPTION("NXP NETC Blocks Control Driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index d96028f01770..fb416d60dcd7 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -24,7 +24,6 @@ /* General defines */ #define FMAN_LIODN_TBL 64 /* size of LIODN table */ -#define MAX_NUM_OF_MACS 10 #define FM_NUM_OF_FMAN_CTRL_EVENT_REGS 4 #define BASE_RX_PORTID 0x08 #define BASE_TX_PORTID 0x28 diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h index 2ea575a46675..74eb62eba0d7 100644 --- a/drivers/net/ethernet/freescale/fman/fman.h +++ b/drivers/net/ethernet/freescale/fman/fman.h @@ -74,6 +74,9 @@ #define BM_MAX_NUM_OF_POOLS 64 /* Buffers pools */ #define FMAN_PORT_MAX_EXT_POOLS_NUM 8 /* External BM pools per Rx port */ +/* General defines */ +#define MAX_NUM_OF_MACS 10 + struct fman; /* FMan data */ /* Enum for defining port types */ diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index c7bff9490ce0..a39fcea6a77a 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -217,6 +217,11 @@ static int mac_probe(struct platform_device *_of_dev) err = -EINVAL; goto _return_dev_put; } + if (val >= MAX_NUM_OF_MACS) { + dev_err(dev, "cell-index value is too big for %pOF\n", mac_node); + err = -EINVAL; + goto _return_dev_put; + } priv->cell_index = (u8)val; /* Get the MAC address */ diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index a99b95c4bcfb..781d92e703cb 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -115,12 +115,14 @@ static const char stat_gstrings[][ETH_GSTRING_LEN] = { static void gfar_gstrings(struct net_device *dev, u32 stringset, u8 * buf) { struct gfar_private *priv = netdev_priv(dev); + int i; if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) - memcpy(buf, stat_gstrings, GFAR_STATS_LEN * ETH_GSTRING_LEN); + for (i = 0; i < GFAR_STATS_LEN; i++) + ethtool_puts(&buf, stat_gstrings[i]); else - memcpy(buf, stat_gstrings, - GFAR_EXTRA_STATS_LEN * ETH_GSTRING_LEN); + for (i = 0; i < GFAR_EXTRA_STATS_LEN; i++) + ethtool_puts(&buf, stat_gstrings[i]); } /* Fill in an array of 64-bit statistics from various sources. diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index d3ddca22d6b0..6663c1768089 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3591,22 +3591,23 @@ static int ucc_geth_probe(struct platform_device* ofdev) if ((ucc_num < 0) || (ucc_num > 7)) return -ENODEV; - ug_info = kmemdup(&ugeth_primary_info, sizeof(*ug_info), GFP_KERNEL); - if (ug_info == NULL) + ug_info = devm_kmemdup(&ofdev->dev, &ugeth_primary_info, + sizeof(*ug_info), GFP_KERNEL); + if (!ug_info) return -ENOMEM; ug_info->uf_info.ucc_num = ucc_num; err = ucc_geth_parse_clock(np, "rx", &ug_info->uf_info.rx_clock); if (err) - goto err_free_info; + return err; err = ucc_geth_parse_clock(np, "tx", &ug_info->uf_info.tx_clock); if (err) - goto err_free_info; + return err; err = of_address_to_resource(np, 0, &res); if (err) - goto err_free_info; + return err; ug_info->uf_info.regs = res.start; ug_info->uf_info.irq = irq_of_parse_and_map(np, 0); @@ -3619,7 +3620,7 @@ static int ucc_geth_probe(struct platform_device* ofdev) */ err = of_phy_register_fixed_link(np); if (err) - goto err_free_info; + return err; ug_info->phy_node = of_node_get(np); } @@ -3687,9 +3688,8 @@ static int ucc_geth_probe(struct platform_device* ofdev) ug_info->uf_info.irq); /* Create an ethernet device instance */ - dev = alloc_etherdev(sizeof(*ugeth)); - - if (dev == NULL) { + dev = devm_alloc_etherdev(&ofdev->dev, sizeof(*ugeth)); + if (!dev) { err = -ENOMEM; goto err_deregister_fixed_link; } @@ -3724,15 +3724,17 @@ static int ucc_geth_probe(struct platform_device* ofdev) /* Carrier starts down, phylib will bring it up */ netif_carrier_off(dev); - err = register_netdev(dev); + err = devm_register_netdev(&ofdev->dev, dev); if (err) { if (netif_msg_probe(ugeth)) pr_err("%s: Cannot register net device, aborting\n", dev->name); - goto err_free_netdev; + goto err_deregister_fixed_link; } - of_get_ethdev_address(np, dev); + err = of_get_ethdev_address(np, dev); + if (err == -EPROBE_DEFER) + goto err_deregister_fixed_link; ugeth->ug_info = ug_info; ugeth->dev = device; @@ -3741,16 +3743,11 @@ static int ucc_geth_probe(struct platform_device* ofdev) return 0; -err_free_netdev: - free_netdev(dev); err_deregister_fixed_link: if (of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); of_node_put(ug_info->tbi_node); of_node_put(ug_info->phy_node); -err_free_info: - kfree(ug_info); - return err; } @@ -3760,14 +3757,11 @@ static void ucc_geth_remove(struct platform_device* ofdev) struct ucc_geth_private *ugeth = netdev_priv(dev); struct device_node *np = ofdev->dev.of_node; - unregister_netdev(dev); ucc_geth_memclean(ugeth); if (of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); of_node_put(ugeth->ug_info->tbi_node); of_node_put(ugeth->ug_info->phy_node); - kfree(ugeth->ug_info); - free_netdev(dev); } static const struct of_device_id ucc_geth_match[] = { diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c index 601beb93d3b3..699f346faf5c 100644 --- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c +++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c @@ -287,20 +287,17 @@ static void uec_get_strings(struct net_device *netdev, u32 stringset, u8 *buf) { struct ucc_geth_private *ugeth = netdev_priv(netdev); u32 stats_mode = ugeth->ug_info->statisticsMode; + int i; - if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_HARDWARE) { - memcpy(buf, hw_stat_gstrings, UEC_HW_STATS_LEN * - ETH_GSTRING_LEN); - buf += UEC_HW_STATS_LEN * ETH_GSTRING_LEN; - } - if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_FIRMWARE_TX) { - memcpy(buf, tx_fw_stat_gstrings, UEC_TX_FW_STATS_LEN * - ETH_GSTRING_LEN); - buf += UEC_TX_FW_STATS_LEN * ETH_GSTRING_LEN; - } + if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_HARDWARE) + for (i = 0; i < UEC_HW_STATS_LEN; i++) + ethtool_puts(&buf, hw_stat_gstrings[i]); + if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_FIRMWARE_TX) + for (i = 0; i < UEC_TX_FW_STATS_LEN; i++) + ethtool_puts(&buf, tx_fw_stat_gstrings[i]); if (stats_mode & UCC_GETH_STATISTICS_GATHERING_MODE_FIRMWARE_RX) - memcpy(buf, rx_fw_stat_gstrings, UEC_RX_FW_STATS_LEN * - ETH_GSTRING_LEN); + for (i = 0; i < UEC_RX_FW_STATS_LEN; i++) + ethtool_puts(&buf, rx_fw_stat_gstrings[i]); } static void uec_get_ethtool_stats(struct net_device *netdev, diff --git a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c index 05bf1f80a79c..403f0f335ba6 100644 --- a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c @@ -210,8 +210,7 @@ void gve_free_to_page_pool(struct gve_rx_ring *rx, if (!page) return; - page_pool_put_page(page->pp, page, buf_state->page_info.buf_size, - allow_direct); + page_pool_put_full_page(page->pp, page, allow_direct); buf_state->page_info.page = NULL; } diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index d72657444ef3..2ae34d01fd36 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -512,7 +512,7 @@ struct hnae_ae_ops { struct net_device_stats *net_stats); void (*get_stats)(struct hnae_handle *handle, u64 *data); void (*get_strings)(struct hnae_handle *handle, - u32 stringset, u8 *data); + u32 stringset, u8 **data); int (*get_sset_count)(struct hnae_handle *handle, int stringset); void (*update_led_status)(struct hnae_handle *handle); int (*set_led_id)(struct hnae_handle *handle, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index bc3e406f0139..8ce910f8d0cc 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -730,15 +730,14 @@ static void hns_ae_get_stats(struct hnae_handle *handle, u64 *data) hns_dsaf_get_stats(vf_cb->dsaf_dev, p, vf_cb->port_index); } -static void hns_ae_get_strings(struct hnae_handle *handle, - u32 stringset, u8 *data) +static void hns_ae_get_strings(struct hnae_handle *handle, u32 stringset, + u8 **data) { int port; int idx; struct hns_mac_cb *mac_cb; struct hns_ppe_cb *ppe_cb; struct dsaf_device *dsaf_dev = hns_ae_get_dsaf_dev(handle->dev); - u8 *p = data; struct hnae_vf_cb *vf_cb; assert(handle); @@ -748,19 +747,14 @@ static void hns_ae_get_strings(struct hnae_handle *handle, mac_cb = hns_get_mac_cb(handle); ppe_cb = hns_get_ppe_cb(handle); - for (idx = 0; idx < handle->q_num; idx++) { - hns_rcb_get_strings(stringset, p, idx); - p += ETH_GSTRING_LEN * hns_rcb_get_ring_sset_count(stringset); - } - - hns_ppe_get_strings(ppe_cb, stringset, p); - p += ETH_GSTRING_LEN * hns_ppe_get_sset_count(stringset); + for (idx = 0; idx < handle->q_num; idx++) + hns_rcb_get_strings(stringset, data, idx); - hns_mac_get_strings(mac_cb, stringset, p); - p += ETH_GSTRING_LEN * hns_mac_get_sset_count(mac_cb, stringset); + hns_ppe_get_strings(ppe_cb, stringset, data); + hns_mac_get_strings(mac_cb, stringset, data); if (mac_cb->mac_type == HNAE_PORT_SERVICE) - hns_dsaf_get_strings(stringset, p, port, dsaf_dev); + hns_dsaf_get_strings(stringset, data, port, dsaf_dev); } static int hns_ae_get_sset_count(struct hnae_handle *handle, int stringset) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index bdb7afaabdd0..400933ca1a29 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -669,16 +669,15 @@ static void hns_gmac_get_stats(void *mac_drv, u64 *data) } } -static void hns_gmac_get_strings(u32 stringset, u8 *data) +static void hns_gmac_get_strings(u32 stringset, u8 **data) { - u8 *buff = data; u32 i; if (stringset != ETH_SS_STATS) return; for (i = 0; i < ARRAY_SIZE(g_gmac_stats_string); i++) - ethtool_puts(&buff, g_gmac_stats_string[i].desc); + ethtool_puts(data, g_gmac_stats_string[i].desc); } static int hns_gmac_get_sset_count(int stringset) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 5fa9b2eeb929..bc6b269be299 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -1190,8 +1190,7 @@ void hns_mac_get_stats(struct hns_mac_cb *mac_cb, u64 *data) mac_ctrl_drv->get_ethtool_stats(mac_ctrl_drv, data); } -void hns_mac_get_strings(struct hns_mac_cb *mac_cb, - int stringset, u8 *data) +void hns_mac_get_strings(struct hns_mac_cb *mac_cb, int stringset, u8 **data) { struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h index edf0bcf76ac9..630f01cf7a71 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h @@ -378,7 +378,7 @@ struct mac_driver { void (*get_regs)(void *mac_drv, void *data); int (*get_regs_count)(void); /* get strings name for ethtool statistic */ - void (*get_strings)(u32 stringset, u8 *data); + void (*get_strings)(u32 stringset, u8 **data); /* get the number of strings*/ int (*get_sset_count)(int stringset); @@ -445,7 +445,7 @@ int hns_mac_config_mac_loopback(struct hns_mac_cb *mac_cb, enum hnae_loop loop, int en); void hns_mac_update_stats(struct hns_mac_cb *mac_cb); void hns_mac_get_stats(struct hns_mac_cb *mac_cb, u64 *data); -void hns_mac_get_strings(struct hns_mac_cb *mac_cb, int stringset, u8 *data); +void hns_mac_get_strings(struct hns_mac_cb *mac_cb, int stringset, u8 **data); int hns_mac_get_sset_count(struct hns_mac_cb *mac_cb, int stringset); void hns_mac_get_regs(struct hns_mac_cb *mac_cb, void *data); int hns_mac_get_regs_count(struct hns_mac_cb *mac_cb); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index eb60f45a3460..851490346261 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -2590,55 +2590,34 @@ void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data) p[i] = 0xdddddddd; } -static char *hns_dsaf_get_node_stats_strings(char *data, int node, - struct dsaf_device *dsaf_dev) +static void hns_dsaf_get_node_stats_strings(u8 **data, int node, + struct dsaf_device *dsaf_dev) { - char *buff = data; - int i; bool is_ver1 = AE_IS_VER1(dsaf_dev->dsaf_ver); + int i; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_pad_drop_pkts", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_manage_pkts", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_rx_pkts", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_rx_pkt_id", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_rx_pause_frame", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_release_buf_num", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_sbm_drop_pkts", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_crc_false_pkts", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_bp_drop_pkts", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_lookup_rslt_drop_pkts", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_local_rslt_fail_pkts", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_vlan_drop_pkts", node); - buff += ETH_GSTRING_LEN; - snprintf(buff, ETH_GSTRING_LEN, "innod%d_stp_drop_pkts", node); - buff += ETH_GSTRING_LEN; + ethtool_sprintf(data, "innod%d_pad_drop_pkts", node); + ethtool_sprintf(data, "innod%d_manage_pkts", node); + ethtool_sprintf(data, "innod%d_rx_pkts", node); + ethtool_sprintf(data, "innod%d_rx_pkt_id", node); + ethtool_sprintf(data, "innod%d_rx_pause_frame", node); + ethtool_sprintf(data, "innod%d_release_buf_num", node); + ethtool_sprintf(data, "innod%d_sbm_drop_pkts", node); + ethtool_sprintf(data, "innod%d_crc_false_pkts", node); + ethtool_sprintf(data, "innod%d_bp_drop_pkts", node); + ethtool_sprintf(data, "innod%d_lookup_rslt_drop_pkts", node); + ethtool_sprintf(data, "innod%d_local_rslt_fail_pkts", node); + ethtool_sprintf(data, "innod%d_vlan_drop_pkts", node); + ethtool_sprintf(data, "innod%d_stp_drop_pkts", node); if (node < DSAF_SERVICE_NW_NUM && !is_ver1) { for (i = 0; i < DSAF_PRIO_NR; i++) { - snprintf(buff + 0 * ETH_GSTRING_LEN * DSAF_PRIO_NR, - ETH_GSTRING_LEN, "inod%d_pfc_prio%d_pkts", - node, i); - snprintf(buff + 1 * ETH_GSTRING_LEN * DSAF_PRIO_NR, - ETH_GSTRING_LEN, "onod%d_pfc_prio%d_pkts", - node, i); - buff += ETH_GSTRING_LEN; + ethtool_sprintf(data, "inod%d_pfc_prio%d_pkts", node, + i); + ethtool_sprintf(data, "onod%d_pfc_prio%d_pkts", node, + i); } - buff += 1 * DSAF_PRIO_NR * ETH_GSTRING_LEN; } - snprintf(buff, ETH_GSTRING_LEN, "onnod%d_tx_pkts", node); - buff += ETH_GSTRING_LEN; - - return buff; + ethtool_sprintf(data, "onnod%d_tx_pkts", node); } static u64 *hns_dsaf_get_node_stats(struct dsaf_device *ddev, u64 *data, @@ -2720,21 +2699,20 @@ int hns_dsaf_get_sset_count(struct dsaf_device *dsaf_dev, int stringset) *@port:port index *@dsaf_dev: dsaf device */ -void hns_dsaf_get_strings(int stringset, u8 *data, int port, +void hns_dsaf_get_strings(int stringset, u8 **data, int port, struct dsaf_device *dsaf_dev) { - char *buff = (char *)data; int node = port; if (stringset != ETH_SS_STATS) return; /* for ge/xge node info */ - buff = hns_dsaf_get_node_stats_strings(buff, node, dsaf_dev); + hns_dsaf_get_node_stats_strings(data, node, dsaf_dev); /* for ppe node info */ node = port + DSAF_PPE_INODE_BASE; - (void)hns_dsaf_get_node_stats_strings(buff, node, dsaf_dev); + hns_dsaf_get_node_stats_strings(data, node, dsaf_dev); } /** diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 5526a10caac5..0eb03dff1a8b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -442,7 +442,7 @@ void hns_dsaf_update_stats(struct dsaf_device *dsaf_dev, u32 inode_num); int hns_dsaf_get_sset_count(struct dsaf_device *dsaf_dev, int stringset); void hns_dsaf_get_stats(struct dsaf_device *ddev, u64 *data, int port); -void hns_dsaf_get_strings(int stringset, u8 *data, int port, +void hns_dsaf_get_strings(int stringset, u8 **data, int port, struct dsaf_device *dsaf_dev); void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c index a08d1f0a5a16..5013beb4d282 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c @@ -457,24 +457,23 @@ int hns_ppe_get_regs_count(void) * @stringset: string set type * @data: output string */ -void hns_ppe_get_strings(struct hns_ppe_cb *ppe_cb, int stringset, u8 *data) +void hns_ppe_get_strings(struct hns_ppe_cb *ppe_cb, int stringset, u8 **data) { int index = ppe_cb->index; - u8 *buff = data; - - ethtool_sprintf(&buff, "ppe%d_rx_sw_pkt", index); - ethtool_sprintf(&buff, "ppe%d_rx_pkt_ok", index); - ethtool_sprintf(&buff, "ppe%d_rx_drop_pkt_no_bd", index); - ethtool_sprintf(&buff, "ppe%d_rx_alloc_buf_fail", index); - ethtool_sprintf(&buff, "ppe%d_rx_alloc_buf_wait", index); - ethtool_sprintf(&buff, "ppe%d_rx_pkt_drop_no_buf", index); - ethtool_sprintf(&buff, "ppe%d_rx_pkt_err_fifo_full", index); - - ethtool_sprintf(&buff, "ppe%d_tx_bd", index); - ethtool_sprintf(&buff, "ppe%d_tx_pkt", index); - ethtool_sprintf(&buff, "ppe%d_tx_pkt_ok", index); - ethtool_sprintf(&buff, "ppe%d_tx_pkt_err_fifo_empty", index); - ethtool_sprintf(&buff, "ppe%d_tx_pkt_err_csum_fail", index); + + ethtool_sprintf(data, "ppe%d_rx_sw_pkt", index); + ethtool_sprintf(data, "ppe%d_rx_pkt_ok", index); + ethtool_sprintf(data, "ppe%d_rx_drop_pkt_no_bd", index); + ethtool_sprintf(data, "ppe%d_rx_alloc_buf_fail", index); + ethtool_sprintf(data, "ppe%d_rx_alloc_buf_wait", index); + ethtool_sprintf(data, "ppe%d_rx_pkt_drop_no_buf", index); + ethtool_sprintf(data, "ppe%d_rx_pkt_err_fifo_full", index); + + ethtool_sprintf(data, "ppe%d_tx_bd", index); + ethtool_sprintf(data, "ppe%d_tx_pkt", index); + ethtool_sprintf(data, "ppe%d_tx_pkt_ok", index); + ethtool_sprintf(data, "ppe%d_tx_pkt_err_fifo_empty", index); + ethtool_sprintf(data, "ppe%d_tx_pkt_err_csum_fail", index); } void hns_ppe_get_stats(struct hns_ppe_cb *ppe_cb, u64 *data) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h index 7e00231c1acf..602c8e971fe4 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h @@ -109,7 +109,7 @@ int hns_ppe_get_sset_count(int stringset); int hns_ppe_get_regs_count(void); void hns_ppe_get_regs(struct hns_ppe_cb *ppe_cb, void *data); -void hns_ppe_get_strings(struct hns_ppe_cb *ppe_cb, int stringset, u8 *data); +void hns_ppe_get_strings(struct hns_ppe_cb *ppe_cb, int stringset, u8 **data); void hns_ppe_get_stats(struct hns_ppe_cb *ppe_cb, u64 *data); void hns_ppe_set_tso_enable(struct hns_ppe_cb *ppe_cb, u32 value); void hns_ppe_set_rss_key(struct hns_ppe_cb *ppe_cb, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index 93344563a259..46af467aa596 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -923,44 +923,42 @@ int hns_rcb_get_ring_regs_count(void) *@data:strings name value *@index:queue index */ -void hns_rcb_get_strings(int stringset, u8 *data, int index) +void hns_rcb_get_strings(int stringset, u8 **data, int index) { - u8 *buff = data; - if (stringset != ETH_SS_STATS) return; - ethtool_sprintf(&buff, "tx_ring%d_rcb_pkt_num", index); - ethtool_sprintf(&buff, "tx_ring%d_ppe_tx_pkt_num", index); - ethtool_sprintf(&buff, "tx_ring%d_ppe_drop_pkt_num", index); - ethtool_sprintf(&buff, "tx_ring%d_fbd_num", index); - - ethtool_sprintf(&buff, "tx_ring%d_pkt_num", index); - ethtool_sprintf(&buff, "tx_ring%d_bytes", index); - ethtool_sprintf(&buff, "tx_ring%d_err_cnt", index); - ethtool_sprintf(&buff, "tx_ring%d_io_err", index); - ethtool_sprintf(&buff, "tx_ring%d_sw_err", index); - ethtool_sprintf(&buff, "tx_ring%d_seg_pkt", index); - ethtool_sprintf(&buff, "tx_ring%d_restart_queue", index); - ethtool_sprintf(&buff, "tx_ring%d_tx_busy", index); - - ethtool_sprintf(&buff, "rx_ring%d_rcb_pkt_num", index); - ethtool_sprintf(&buff, "rx_ring%d_ppe_pkt_num", index); - ethtool_sprintf(&buff, "rx_ring%d_ppe_drop_pkt_num", index); - ethtool_sprintf(&buff, "rx_ring%d_fbd_num", index); - - ethtool_sprintf(&buff, "rx_ring%d_pkt_num", index); - ethtool_sprintf(&buff, "rx_ring%d_bytes", index); - ethtool_sprintf(&buff, "rx_ring%d_err_cnt", index); - ethtool_sprintf(&buff, "rx_ring%d_io_err", index); - ethtool_sprintf(&buff, "rx_ring%d_sw_err", index); - ethtool_sprintf(&buff, "rx_ring%d_seg_pkt", index); - ethtool_sprintf(&buff, "rx_ring%d_reuse_pg", index); - ethtool_sprintf(&buff, "rx_ring%d_len_err", index); - ethtool_sprintf(&buff, "rx_ring%d_non_vld_desc_err", index); - ethtool_sprintf(&buff, "rx_ring%d_bd_num_err", index); - ethtool_sprintf(&buff, "rx_ring%d_l2_err", index); - ethtool_sprintf(&buff, "rx_ring%d_l3l4csum_err", index); + ethtool_sprintf(data, "tx_ring%d_rcb_pkt_num", index); + ethtool_sprintf(data, "tx_ring%d_ppe_tx_pkt_num", index); + ethtool_sprintf(data, "tx_ring%d_ppe_drop_pkt_num", index); + ethtool_sprintf(data, "tx_ring%d_fbd_num", index); + + ethtool_sprintf(data, "tx_ring%d_pkt_num", index); + ethtool_sprintf(data, "tx_ring%d_bytes", index); + ethtool_sprintf(data, "tx_ring%d_err_cnt", index); + ethtool_sprintf(data, "tx_ring%d_io_err", index); + ethtool_sprintf(data, "tx_ring%d_sw_err", index); + ethtool_sprintf(data, "tx_ring%d_seg_pkt", index); + ethtool_sprintf(data, "tx_ring%d_restart_queue", index); + ethtool_sprintf(data, "tx_ring%d_tx_busy", index); + + ethtool_sprintf(data, "rx_ring%d_rcb_pkt_num", index); + ethtool_sprintf(data, "rx_ring%d_ppe_pkt_num", index); + ethtool_sprintf(data, "rx_ring%d_ppe_drop_pkt_num", index); + ethtool_sprintf(data, "rx_ring%d_fbd_num", index); + + ethtool_sprintf(data, "rx_ring%d_pkt_num", index); + ethtool_sprintf(data, "rx_ring%d_bytes", index); + ethtool_sprintf(data, "rx_ring%d_err_cnt", index); + ethtool_sprintf(data, "rx_ring%d_io_err", index); + ethtool_sprintf(data, "rx_ring%d_sw_err", index); + ethtool_sprintf(data, "rx_ring%d_seg_pkt", index); + ethtool_sprintf(data, "rx_ring%d_reuse_pg", index); + ethtool_sprintf(data, "rx_ring%d_len_err", index); + ethtool_sprintf(data, "rx_ring%d_non_vld_desc_err", index); + ethtool_sprintf(data, "rx_ring%d_bd_num_err", index); + ethtool_sprintf(data, "rx_ring%d_l2_err", index); + ethtool_sprintf(data, "rx_ring%d_l3l4csum_err", index); } void hns_rcb_get_common_regs(struct rcb_common_cb *rcb_com, void *data) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h index c1e9b6997853..0f4cc184ef39 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h @@ -157,7 +157,7 @@ int hns_rcb_get_ring_regs_count(void); void hns_rcb_get_ring_regs(struct hnae_queue *queue, void *data); -void hns_rcb_get_strings(int stringset, u8 *data, int index); +void hns_rcb_get_strings(int stringset, u8 **data, int index); void hns_rcb_set_rx_ring_bs(struct hnae_queue *q, u32 buf_size); void hns_rcb_set_tx_ring_bs(struct hnae_queue *q, u32 buf_size); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c index c58833eb4830..dbc44c2c26c2 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c @@ -743,16 +743,15 @@ static void hns_xgmac_get_stats(void *mac_drv, u64 *data) *@stringset: type of values in data *@data:data for value of string name */ -static void hns_xgmac_get_strings(u32 stringset, u8 *data) +static void hns_xgmac_get_strings(u32 stringset, u8 **data) { - u8 *buff = data; u32 i; if (stringset != ETH_SS_STATS) return; for (i = 0; i < ARRAY_SIZE(g_xgmac_stats_string); i++) - ethtool_puts(&buff, g_xgmac_stats_string[i].desc); + ethtool_puts(data, g_xgmac_stats_string[i].desc); } /** diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index a5bb306b2cf1..6c458f037262 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -903,7 +903,6 @@ static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { struct hns_nic_priv *priv = netdev_priv(netdev); struct hnae_handle *h = priv->ae_handle; - u8 *buff = data; if (!h->dev->ops->get_strings) { netdev_err(netdev, "h->dev->ops->get_strings is null!\n"); @@ -912,43 +911,43 @@ static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data) if (stringset == ETH_SS_TEST) { if (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII) - ethtool_puts(&buff, + ethtool_puts(&data, hns_nic_test_strs[MAC_INTERNALLOOP_MAC]); - ethtool_puts(&buff, hns_nic_test_strs[MAC_INTERNALLOOP_SERDES]); + ethtool_puts(&data, hns_nic_test_strs[MAC_INTERNALLOOP_SERDES]); if ((netdev->phydev) && (!netdev->phydev->is_c45)) - ethtool_puts(&buff, + ethtool_puts(&data, hns_nic_test_strs[MAC_INTERNALLOOP_PHY]); } else { - ethtool_puts(&buff, "rx_packets"); - ethtool_puts(&buff, "tx_packets"); - ethtool_puts(&buff, "rx_bytes"); - ethtool_puts(&buff, "tx_bytes"); - ethtool_puts(&buff, "rx_errors"); - ethtool_puts(&buff, "tx_errors"); - ethtool_puts(&buff, "rx_dropped"); - ethtool_puts(&buff, "tx_dropped"); - ethtool_puts(&buff, "multicast"); - ethtool_puts(&buff, "collisions"); - ethtool_puts(&buff, "rx_over_errors"); - ethtool_puts(&buff, "rx_crc_errors"); - ethtool_puts(&buff, "rx_frame_errors"); - ethtool_puts(&buff, "rx_fifo_errors"); - ethtool_puts(&buff, "rx_missed_errors"); - ethtool_puts(&buff, "tx_aborted_errors"); - ethtool_puts(&buff, "tx_carrier_errors"); - ethtool_puts(&buff, "tx_fifo_errors"); - ethtool_puts(&buff, "tx_heartbeat_errors"); - ethtool_puts(&buff, "rx_length_errors"); - ethtool_puts(&buff, "tx_window_errors"); - ethtool_puts(&buff, "rx_compressed"); - ethtool_puts(&buff, "tx_compressed"); - ethtool_puts(&buff, "netdev_rx_dropped"); - ethtool_puts(&buff, "netdev_tx_dropped"); - - ethtool_puts(&buff, "netdev_tx_timeout"); - - h->dev->ops->get_strings(h, stringset, buff); + ethtool_puts(&data, "rx_packets"); + ethtool_puts(&data, "tx_packets"); + ethtool_puts(&data, "rx_bytes"); + ethtool_puts(&data, "tx_bytes"); + ethtool_puts(&data, "rx_errors"); + ethtool_puts(&data, "tx_errors"); + ethtool_puts(&data, "rx_dropped"); + ethtool_puts(&data, "tx_dropped"); + ethtool_puts(&data, "multicast"); + ethtool_puts(&data, "collisions"); + ethtool_puts(&data, "rx_over_errors"); + ethtool_puts(&data, "rx_crc_errors"); + ethtool_puts(&data, "rx_frame_errors"); + ethtool_puts(&data, "rx_fifo_errors"); + ethtool_puts(&data, "rx_missed_errors"); + ethtool_puts(&data, "tx_aborted_errors"); + ethtool_puts(&data, "tx_carrier_errors"); + ethtool_puts(&data, "tx_fifo_errors"); + ethtool_puts(&data, "tx_heartbeat_errors"); + ethtool_puts(&data, "rx_length_errors"); + ethtool_puts(&data, "tx_window_errors"); + ethtool_puts(&data, "rx_compressed"); + ethtool_puts(&data, "tx_compressed"); + ethtool_puts(&data, "netdev_rx_dropped"); + ethtool_puts(&data, "netdev_tx_dropped"); + + ethtool_puts(&data, "netdev_tx_timeout"); + + h->dev->ops->get_strings(h, stringset, &data); } } @@ -970,7 +969,7 @@ static int hns_get_sset_count(struct net_device *netdev, int stringset) return -EOPNOTSUPP; } if (stringset == ETH_SS_TEST) { - u32 cnt = (sizeof(hns_nic_test_strs) / ETH_GSTRING_LEN); + u32 cnt = ARRAY_SIZE(hns_nic_test_strs); if (priv->ae_handle->phy_if == PHY_INTERFACE_MODE_XGMII) cnt--; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c index 67b0bf310daa..9a63fbc69408 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -25,8 +25,11 @@ void hnae3_unregister_ae_algo_prepare(struct hnae3_ae_algo *ae_algo) pci_id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev); if (!pci_id) continue; - if (IS_ENABLED(CONFIG_PCI_IOV)) + if (IS_ENABLED(CONFIG_PCI_IOV)) { + device_lock(&ae_dev->pdev->dev); pci_disable_sriov(ae_dev->pdev); + device_unlock(&ae_dev->pdev->dev); + } } } EXPORT_SYMBOL(hnae3_unregister_ae_algo_prepare); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 27dbe367f3d3..710a8f9f2248 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -677,7 +677,7 @@ struct hnae3_ae_ops { void (*get_mac_stats)(struct hnae3_handle *handle, struct hns3_mac_stats *mac_stats); void (*get_strings)(struct hnae3_handle *handle, - u32 stringset, u8 *data); + u32 stringset, u8 **data); int (*get_sset_count)(struct hnae3_handle *handle, int stringset); void (*get_regs)(struct hnae3_handle *handle, u32 *version, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c index 2b31188ff555..f9a3d6fc4416 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c @@ -36,27 +36,22 @@ int hclge_comm_tqps_get_sset_count(struct hnae3_handle *handle) } EXPORT_SYMBOL_GPL(hclge_comm_tqps_get_sset_count); -u8 *hclge_comm_tqps_get_strings(struct hnae3_handle *handle, u8 *data) +void hclge_comm_tqps_get_strings(struct hnae3_handle *handle, u8 **data) { struct hnae3_knic_private_info *kinfo = &handle->kinfo; - u8 *buff = data; u16 i; for (i = 0; i < kinfo->num_tqps; i++) { struct hclge_comm_tqp *tqp = container_of(kinfo->tqp[i], struct hclge_comm_tqp, q); - snprintf(buff, ETH_GSTRING_LEN, "txq%u_pktnum_rcd", tqp->index); - buff += ETH_GSTRING_LEN; + ethtool_sprintf(data, "txq%u_pktnum_rcd", tqp->index); } for (i = 0; i < kinfo->num_tqps; i++) { struct hclge_comm_tqp *tqp = container_of(kinfo->tqp[i], struct hclge_comm_tqp, q); - snprintf(buff, ETH_GSTRING_LEN, "rxq%u_pktnum_rcd", tqp->index); - buff += ETH_GSTRING_LEN; + ethtool_sprintf(data, "rxq%u_pktnum_rcd", tqp->index); } - - return buff; } EXPORT_SYMBOL_GPL(hclge_comm_tqps_get_strings); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.h b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.h index a46350162ee8..b9ff424c0bc2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.h @@ -32,7 +32,7 @@ struct hclge_comm_tqp { u64 *hclge_comm_tqps_get_stats(struct hnae3_handle *handle, u64 *data); int hclge_comm_tqps_get_sset_count(struct hnae3_handle *handle); -u8 *hclge_comm_tqps_get_strings(struct hnae3_handle *handle, u8 *data); +void hclge_comm_tqps_get_strings(struct hnae3_handle *handle, u8 **data); void hclge_comm_reset_tqp_stats(struct hnae3_handle *handle); int hclge_comm_tqps_update_stats(struct hnae3_handle *handle, struct hclge_comm_hw *hw); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 4cbc4d069a1f..43377a7b2426 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -4448,7 +4448,7 @@ static void hns3_update_rx_int_coalesce(struct hns3_enet_tqp_vector *tqp_vector) dim_update_sample(tqp_vector->event_cnt, rx_group->total_packets, rx_group->total_bytes, &sample); - net_dim(&rx_group->dim, sample); + net_dim(&rx_group->dim, &sample); } static void hns3_update_tx_int_coalesce(struct hns3_enet_tqp_vector *tqp_vector) @@ -4461,7 +4461,7 @@ static void hns3_update_tx_int_coalesce(struct hns3_enet_tqp_vector *tqp_vector) dim_update_sample(tqp_vector->event_cnt, tx_group->total_packets, tx_group->total_bytes, &sample); - net_dim(&tx_group->dim, sample); + net_dim(&tx_group->dim, &sample); } static int hns3_nic_common_poll(struct napi_struct *napi, int budget) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index b1e988347347..b771a2daba43 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -509,54 +509,37 @@ static int hns3_get_sset_count(struct net_device *netdev, int stringset) } } -static void *hns3_update_strings(u8 *data, const struct hns3_stats *stats, - u32 stat_count, u32 num_tqps, const char *prefix) +static void hns3_update_strings(u8 **data, const struct hns3_stats *stats, + u32 stat_count, u32 num_tqps, + const char *prefix) { -#define MAX_PREFIX_SIZE (6 + 4) - u32 size_left; u32 i, j; - u32 n1; - for (i = 0; i < num_tqps; i++) { - for (j = 0; j < stat_count; j++) { - data[ETH_GSTRING_LEN - 1] = '\0'; - - /* first, prepend the prefix string */ - n1 = scnprintf(data, MAX_PREFIX_SIZE, "%s%u_", - prefix, i); - size_left = (ETH_GSTRING_LEN - 1) - n1; - - /* now, concatenate the stats string to it */ - strncat(data, stats[j].stats_string, size_left); - data += ETH_GSTRING_LEN; - } - } - - return data; + for (i = 0; i < num_tqps; i++) + for (j = 0; j < stat_count; j++) + ethtool_sprintf(data, "%s%u_%s", prefix, i, + stats[j].stats_string); } -static u8 *hns3_get_strings_tqps(struct hnae3_handle *handle, u8 *data) +static void hns3_get_strings_tqps(struct hnae3_handle *handle, u8 **data) { struct hnae3_knic_private_info *kinfo = &handle->kinfo; const char tx_prefix[] = "txq"; const char rx_prefix[] = "rxq"; /* get strings for Tx */ - data = hns3_update_strings(data, hns3_txq_stats, HNS3_TXQ_STATS_COUNT, - kinfo->num_tqps, tx_prefix); + hns3_update_strings(data, hns3_txq_stats, HNS3_TXQ_STATS_COUNT, + kinfo->num_tqps, tx_prefix); /* get strings for Rx */ - data = hns3_update_strings(data, hns3_rxq_stats, HNS3_RXQ_STATS_COUNT, - kinfo->num_tqps, rx_prefix); - - return data; + hns3_update_strings(data, hns3_rxq_stats, HNS3_RXQ_STATS_COUNT, + kinfo->num_tqps, rx_prefix); } static void hns3_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { struct hnae3_handle *h = hns3_get_handle(netdev); const struct hnae3_ae_ops *ops = h->ae_algo->ops; - char *buff = (char *)data; int i; if (!ops->get_strings) @@ -564,18 +547,15 @@ static void hns3_get_strings(struct net_device *netdev, u32 stringset, u8 *data) switch (stringset) { case ETH_SS_STATS: - buff = hns3_get_strings_tqps(h, buff); - ops->get_strings(h, stringset, (u8 *)buff); + hns3_get_strings_tqps(h, &data); + ops->get_strings(h, stringset, &data); break; case ETH_SS_TEST: - ops->get_strings(h, stringset, data); + ops->get_strings(h, stringset, &data); break; case ETH_SS_PRIV_FLAGS: - for (i = 0; i < HNS3_PRIV_FLAGS_LEN; i++) { - snprintf(buff, ETH_GSTRING_LEN, "%s", - hns3_priv_flags[i].name); - buff += ETH_GSTRING_LEN; - } + for (i = 0; i < HNS3_PRIV_FLAGS_LEN; i++) + ethtool_puts(&data, hns3_priv_flags[i].name); break; default: break; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index bd86efd92a5a..05942fa78b11 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -594,25 +594,21 @@ static u64 *hclge_comm_get_stats(struct hclge_dev *hdev, return buf; } -static u8 *hclge_comm_get_strings(struct hclge_dev *hdev, u32 stringset, - const struct hclge_comm_stats_str strs[], - int size, u8 *data) +static void hclge_comm_get_strings(struct hclge_dev *hdev, u32 stringset, + const struct hclge_comm_stats_str strs[], + int size, u8 **data) { - char *buff = (char *)data; u32 i; if (stringset != ETH_SS_STATS) - return buff; + return; for (i = 0; i < size; i++) { if (strs[i].stats_num > hdev->ae_dev->dev_specs.mac_stats_num) continue; - snprintf(buff, ETH_GSTRING_LEN, "%s", strs[i].desc); - buff = buff + ETH_GSTRING_LEN; + ethtool_puts(data, strs[i].desc); } - - return (u8 *)buff; } static void hclge_update_stats_for_all(struct hclge_dev *hdev) @@ -717,44 +713,38 @@ static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset) } static void hclge_get_strings(struct hnae3_handle *handle, u32 stringset, - u8 *data) + u8 **data) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - u8 *p = (char *)data; + const char *str; int size; if (stringset == ETH_SS_STATS) { size = ARRAY_SIZE(g_mac_stats_string); - p = hclge_comm_get_strings(hdev, stringset, g_mac_stats_string, - size, p); - p = hclge_comm_tqps_get_strings(handle, p); + hclge_comm_get_strings(hdev, stringset, g_mac_stats_string, + size, data); + hclge_comm_tqps_get_strings(handle, data); } else if (stringset == ETH_SS_TEST) { if (handle->flags & HNAE3_SUPPORT_EXTERNAL_LOOPBACK) { - memcpy(p, hns3_nic_test_strs[HNAE3_LOOP_EXTERNAL], - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; + str = hns3_nic_test_strs[HNAE3_LOOP_EXTERNAL]; + ethtool_puts(data, str); } if (handle->flags & HNAE3_SUPPORT_APP_LOOPBACK) { - memcpy(p, hns3_nic_test_strs[HNAE3_LOOP_APP], - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; + str = hns3_nic_test_strs[HNAE3_LOOP_APP]; + ethtool_puts(data, str); } if (handle->flags & HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK) { - memcpy(p, hns3_nic_test_strs[HNAE3_LOOP_SERIAL_SERDES], - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; + str = hns3_nic_test_strs[HNAE3_LOOP_SERIAL_SERDES]; + ethtool_puts(data, str); } if (handle->flags & HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK) { - memcpy(p, - hns3_nic_test_strs[HNAE3_LOOP_PARALLEL_SERDES], - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; + str = hns3_nic_test_strs[HNAE3_LOOP_PARALLEL_SERDES]; + ethtool_puts(data, str); } if (handle->flags & HNAE3_SUPPORT_PHY_LOOPBACK) { - memcpy(p, hns3_nic_test_strs[HNAE3_LOOP_PHY], - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; + str = hns3_nic_test_strs[HNAE3_LOOP_PHY]; + ethtool_puts(data, str); } } } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 094a7c7b5592..2f6ffb88e700 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -130,12 +130,10 @@ static int hclgevf_get_sset_count(struct hnae3_handle *handle, int strset) } static void hclgevf_get_strings(struct hnae3_handle *handle, u32 strset, - u8 *data) + u8 **data) { - u8 *p = (char *)data; - if (strset == ETH_SS_STATS) - p = hclge_comm_tqps_get_strings(handle, p); + hclge_comm_tqps_get_strings(handle, data); } static void hclgevf_get_stats(struct hnae3_handle *handle, u64 *data) diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c index c634534710d9..7d70056e9008 100644 --- a/drivers/net/ethernet/ibm/emac/mal.c +++ b/drivers/net/ethernet/ibm/emac/mal.c @@ -524,7 +524,8 @@ static int mal_probe(struct platform_device *ofdev) unsigned long irqflags; irq_handler_t hdlr_serr, hdlr_txde, hdlr_rxde; - mal = kzalloc(sizeof(struct mal_instance), GFP_KERNEL); + mal = devm_kzalloc(&ofdev->dev, sizeof(struct mal_instance), + GFP_KERNEL); if (!mal) return -ENOMEM; @@ -539,8 +540,7 @@ static int mal_probe(struct platform_device *ofdev) printk(KERN_ERR "mal%d: can't find MAL num-tx-chans property!\n", index); - err = -ENODEV; - goto fail; + return -ENODEV; } mal->num_tx_chans = prop[0]; @@ -549,8 +549,7 @@ static int mal_probe(struct platform_device *ofdev) printk(KERN_ERR "mal%d: can't find MAL num-rx-chans property!\n", index); - err = -ENODEV; - goto fail; + return -ENODEV; } mal->num_rx_chans = prop[0]; @@ -558,15 +557,13 @@ static int mal_probe(struct platform_device *ofdev) if (dcr_base == 0) { printk(KERN_ERR "mal%d: can't find DCR resource!\n", index); - err = -ENODEV; - goto fail; + return -ENODEV; } mal->dcr_host = dcr_map(ofdev->dev.of_node, dcr_base, 0x100); if (!DCR_MAP_OK(mal->dcr_host)) { printk(KERN_ERR "mal%d: failed to map DCRs !\n", index); - err = -ENODEV; - goto fail; + return -ENODEV; } if (of_device_is_compatible(ofdev->dev.of_node, "ibm,mcmal-405ez")) { @@ -582,25 +579,6 @@ static int mal_probe(struct platform_device *ofdev) #endif } - mal->txeob_irq = irq_of_parse_and_map(ofdev->dev.of_node, 0); - mal->rxeob_irq = irq_of_parse_and_map(ofdev->dev.of_node, 1); - mal->serr_irq = irq_of_parse_and_map(ofdev->dev.of_node, 2); - - if (mal_has_feature(mal, MAL_FTR_COMMON_ERR_INT)) { - mal->txde_irq = mal->rxde_irq = mal->serr_irq; - } else { - mal->txde_irq = irq_of_parse_and_map(ofdev->dev.of_node, 3); - mal->rxde_irq = irq_of_parse_and_map(ofdev->dev.of_node, 4); - } - - if (!mal->txeob_irq || !mal->rxeob_irq || !mal->serr_irq || - !mal->txde_irq || !mal->rxde_irq) { - printk(KERN_ERR - "mal%d: failed to map interrupts !\n", index); - err = -ENODEV; - goto fail_unmap; - } - INIT_LIST_HEAD(&mal->poll_list); INIT_LIST_HEAD(&mal->list); spin_lock_init(&mal->lock); @@ -654,31 +632,43 @@ static int mal_probe(struct platform_device *ofdev) sizeof(struct mal_descriptor) * mal_rx_bd_offset(mal, i)); + mal->txeob_irq = platform_get_irq(ofdev, 0); + mal->rxeob_irq = platform_get_irq(ofdev, 1); + mal->serr_irq = platform_get_irq(ofdev, 2); + if (mal_has_feature(mal, MAL_FTR_COMMON_ERR_INT)) { + mal->txde_irq = mal->rxde_irq = mal->serr_irq; irqflags = IRQF_SHARED; hdlr_serr = hdlr_txde = hdlr_rxde = mal_int; } else { + mal->txde_irq = platform_get_irq(ofdev, 3); + mal->rxde_irq = platform_get_irq(ofdev, 4); irqflags = 0; hdlr_serr = mal_serr; hdlr_txde = mal_txde; hdlr_rxde = mal_rxde; } - err = request_irq(mal->serr_irq, hdlr_serr, irqflags, "MAL SERR", mal); + err = devm_request_irq(&ofdev->dev, mal->serr_irq, hdlr_serr, irqflags, + "MAL SERR", mal); if (err) goto fail2; - err = request_irq(mal->txde_irq, hdlr_txde, irqflags, "MAL TX DE", mal); + err = devm_request_irq(&ofdev->dev, mal->txde_irq, hdlr_txde, irqflags, + "MAL TX DE", mal); if (err) - goto fail3; - err = request_irq(mal->txeob_irq, mal_txeob, 0, "MAL TX EOB", mal); + goto fail2; + err = devm_request_irq(&ofdev->dev, mal->txeob_irq, mal_txeob, 0, + "MAL TX EOB", mal); if (err) - goto fail4; - err = request_irq(mal->rxde_irq, hdlr_rxde, irqflags, "MAL RX DE", mal); + goto fail2; + err = devm_request_irq(&ofdev->dev, mal->rxde_irq, hdlr_rxde, irqflags, + "MAL RX DE", mal); if (err) - goto fail5; - err = request_irq(mal->rxeob_irq, mal_rxeob, 0, "MAL RX EOB", mal); + goto fail2; + err = devm_request_irq(&ofdev->dev, mal->rxeob_irq, mal_rxeob, 0, + "MAL RX EOB", mal); if (err) - goto fail6; + goto fail2; /* Enable all MAL SERR interrupt sources */ set_mal_dcrn(mal, MAL_IER, MAL_IER_EVENTS); @@ -697,23 +687,12 @@ static int mal_probe(struct platform_device *ofdev) return 0; - fail6: - free_irq(mal->rxde_irq, mal); - fail5: - free_irq(mal->txeob_irq, mal); - fail4: - free_irq(mal->txde_irq, mal); - fail3: - free_irq(mal->serr_irq, mal); fail2: dma_free_coherent(&ofdev->dev, bd_size, mal->bd_virt, mal->bd_dma); fail_dummy: free_netdev(mal->dummy_dev); fail_unmap: dcr_unmap(mal->dcr_host, 0x100); - fail: - kfree(mal); - return err; } @@ -732,12 +711,6 @@ static void mal_remove(struct platform_device *ofdev) "mal%d: commac list is not empty on remove!\n", mal->index); - free_irq(mal->serr_irq, mal); - free_irq(mal->txde_irq, mal); - free_irq(mal->txeob_irq, mal); - free_irq(mal->rxde_irq, mal); - free_irq(mal->rxeob_irq, mal); - mal_reset(mal); free_netdev(mal->dummy_dev); @@ -746,10 +719,9 @@ static void mal_remove(struct platform_device *ofdev) dma_free_coherent(&ofdev->dev, sizeof(struct mal_descriptor) * - (NUM_TX_BUFF * mal->num_tx_chans + - NUM_RX_BUFF * mal->num_rx_chans), mal->bd_virt, - mal->bd_dma); - kfree(mal); + (NUM_TX_BUFF * mal->num_tx_chans + + NUM_RX_BUFF * mal->num_rx_chans), + mal->bd_virt, mal->bd_dma); } static const struct of_device_id mal_platform_match[] = diff --git a/drivers/net/ethernet/ibm/emac/rgmii.c b/drivers/net/ethernet/ibm/emac/rgmii.c index 317c22d09172..b544dd8633b7 100644 --- a/drivers/net/ethernet/ibm/emac/rgmii.c +++ b/drivers/net/ethernet/ibm/emac/rgmii.c @@ -216,31 +216,24 @@ void *rgmii_dump_regs(struct platform_device *ofdev, void *buf) static int rgmii_probe(struct platform_device *ofdev) { - struct device_node *np = ofdev->dev.of_node; struct rgmii_instance *dev; - struct resource regs; - int rc; + int err; - rc = -ENOMEM; - dev = kzalloc(sizeof(struct rgmii_instance), GFP_KERNEL); - if (dev == NULL) - goto err_gone; + dev = devm_kzalloc(&ofdev->dev, sizeof(struct rgmii_instance), + GFP_KERNEL); + if (!dev) + return -ENOMEM; - mutex_init(&dev->lock); - dev->ofdev = ofdev; + err = devm_mutex_init(&ofdev->dev, &dev->lock); + if (err) + return err; - rc = -ENXIO; - if (of_address_to_resource(np, 0, ®s)) { - printk(KERN_ERR "%pOF: Can't get registers address\n", np); - goto err_free; - } + dev->ofdev = ofdev; - rc = -ENOMEM; - dev->base = (struct rgmii_regs __iomem *)ioremap(regs.start, - sizeof(struct rgmii_regs)); - if (dev->base == NULL) { - printk(KERN_ERR "%pOF: Can't map device registers!\n", np); - goto err_free; + dev->base = devm_platform_ioremap_resource(ofdev, 0); + if (IS_ERR(dev->base)) { + dev_err(&ofdev->dev, "can't map device registers"); + return PTR_ERR(dev->base); } /* Check for RGMII flags */ @@ -266,21 +259,6 @@ static int rgmii_probe(struct platform_device *ofdev) platform_set_drvdata(ofdev, dev); return 0; - - err_free: - kfree(dev); - err_gone: - return rc; -} - -static void rgmii_remove(struct platform_device *ofdev) -{ - struct rgmii_instance *dev = platform_get_drvdata(ofdev); - - WARN_ON(dev->users != 0); - - iounmap(dev->base); - kfree(dev); } static const struct of_device_id rgmii_match[] = @@ -300,7 +278,6 @@ static struct platform_driver rgmii_driver = { .of_match_table = rgmii_match, }, .probe = rgmii_probe, - .remove = rgmii_remove, }; int __init rgmii_init(void) diff --git a/drivers/net/ethernet/ibm/emac/tah.c b/drivers/net/ethernet/ibm/emac/tah.c index c605c8ff933e..09f6373ed2f9 100644 --- a/drivers/net/ethernet/ibm/emac/tah.c +++ b/drivers/net/ethernet/ibm/emac/tah.c @@ -87,31 +87,24 @@ void *tah_dump_regs(struct platform_device *ofdev, void *buf) static int tah_probe(struct platform_device *ofdev) { - struct device_node *np = ofdev->dev.of_node; struct tah_instance *dev; - struct resource regs; - int rc; + int err; - rc = -ENOMEM; - dev = kzalloc(sizeof(struct tah_instance), GFP_KERNEL); - if (dev == NULL) - goto err_gone; + dev = devm_kzalloc(&ofdev->dev, sizeof(struct tah_instance), + GFP_KERNEL); + if (!dev) + return -ENOMEM; - mutex_init(&dev->lock); - dev->ofdev = ofdev; + err = devm_mutex_init(&ofdev->dev, &dev->lock); + if (err) + return err; - rc = -ENXIO; - if (of_address_to_resource(np, 0, ®s)) { - printk(KERN_ERR "%pOF: Can't get registers address\n", np); - goto err_free; - } + dev->ofdev = ofdev; - rc = -ENOMEM; - dev->base = (struct tah_regs __iomem *)ioremap(regs.start, - sizeof(struct tah_regs)); - if (dev->base == NULL) { - printk(KERN_ERR "%pOF: Can't map device registers!\n", np); - goto err_free; + dev->base = devm_platform_ioremap_resource(ofdev, 0); + if (IS_ERR(dev->base)) { + dev_err(&ofdev->dev, "can't map device registers"); + return PTR_ERR(dev->base); } platform_set_drvdata(ofdev, dev); @@ -123,21 +116,6 @@ static int tah_probe(struct platform_device *ofdev) wmb(); return 0; - - err_free: - kfree(dev); - err_gone: - return rc; -} - -static void tah_remove(struct platform_device *ofdev) -{ - struct tah_instance *dev = platform_get_drvdata(ofdev); - - WARN_ON(dev->users != 0); - - iounmap(dev->base); - kfree(dev); } static const struct of_device_id tah_match[] = @@ -158,7 +136,6 @@ static struct platform_driver tah_driver = { .of_match_table = tah_match, }, .probe = tah_probe, - .remove = tah_remove, }; int __init tah_init(void) diff --git a/drivers/net/ethernet/ibm/emac/zmii.c b/drivers/net/ethernet/ibm/emac/zmii.c index 03bab3f95fe4..69ca6065de1c 100644 --- a/drivers/net/ethernet/ibm/emac/zmii.c +++ b/drivers/net/ethernet/ibm/emac/zmii.c @@ -232,32 +232,25 @@ void *zmii_dump_regs(struct platform_device *ofdev, void *buf) static int zmii_probe(struct platform_device *ofdev) { - struct device_node *np = ofdev->dev.of_node; struct zmii_instance *dev; - struct resource regs; - int rc; + int err; - rc = -ENOMEM; - dev = kzalloc(sizeof(struct zmii_instance), GFP_KERNEL); - if (dev == NULL) - goto err_gone; + dev = devm_kzalloc(&ofdev->dev, sizeof(struct zmii_instance), + GFP_KERNEL); + if (!dev) + return -ENOMEM; + + err = devm_mutex_init(&ofdev->dev, &dev->lock); + if (err) + return err; - mutex_init(&dev->lock); dev->ofdev = ofdev; dev->mode = PHY_INTERFACE_MODE_NA; - rc = -ENXIO; - if (of_address_to_resource(np, 0, ®s)) { - printk(KERN_ERR "%pOF: Can't get registers address\n", np); - goto err_free; - } - - rc = -ENOMEM; - dev->base = (struct zmii_regs __iomem *)ioremap(regs.start, - sizeof(struct zmii_regs)); - if (dev->base == NULL) { - printk(KERN_ERR "%pOF: Can't map device registers!\n", np); - goto err_free; + dev->base = devm_platform_ioremap_resource(ofdev, 0); + if (IS_ERR(dev->base)) { + dev_err(&ofdev->dev, "can't map device registers"); + return PTR_ERR(dev->base); } /* We may need FER value for autodetection later */ @@ -271,21 +264,6 @@ static int zmii_probe(struct platform_device *ofdev) platform_set_drvdata(ofdev, dev); return 0; - - err_free: - kfree(dev); - err_gone: - return rc; -} - -static void zmii_remove(struct platform_device *ofdev) -{ - struct zmii_instance *dev = platform_get_drvdata(ofdev); - - WARN_ON(dev->users != 0); - - iounmap(dev->base); - kfree(dev); } static const struct of_device_id zmii_match[] = @@ -306,7 +284,6 @@ static struct platform_driver zmii_driver = { .of_match_table = zmii_match, }, .probe = zmii_probe, - .remove = zmii_remove, }; int __init zmii_init(void) diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index ce227b56cf72..2f9655cf5dd9 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1205,12 +1205,10 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx) if (ret_val) goto out; - if (hw->mac.type != e1000_pch_mtp) { - ret_val = e1000e_force_smbus(hw); - if (ret_val) { - e_dbg("Failed to force SMBUS: %d\n", ret_val); - goto release; - } + ret_val = e1000e_force_smbus(hw); + if (ret_val) { + e_dbg("Failed to force SMBUS: %d\n", ret_val); + goto release; } /* Si workaround for ULP entry flow on i127/rev6 h/w. Enable @@ -1273,13 +1271,6 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx) } release: - if (hw->mac.type == e1000_pch_mtp) { - ret_val = e1000e_force_smbus(hw); - if (ret_val) - e_dbg("Failed to force SMBUS over MTL system: %d\n", - ret_val); - } - hw->phy.ops.release(hw); out: if (ret_val) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 2089a0e172bf..d4255c2706fa 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -755,6 +755,7 @@ enum i40e_filter_state { I40E_FILTER_ACTIVE, /* Added to switch by FW */ I40E_FILTER_FAILED, /* Rejected by FW */ I40E_FILTER_REMOVE, /* To be removed */ + I40E_FILTER_NEW_SYNC, /* New, not sent yet, is in i40e_sync_vsi_filters() */ /* There is no 'removed' state; the filter struct is freed */ }; struct i40e_mac_filter { diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index abf624d770e6..208c2f0857b6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -89,6 +89,7 @@ static char *i40e_filter_state_string[] = { "ACTIVE", "FAILED", "REMOVE", + "NEW_SYNC", }; /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 25295ae370b2..55fb362eb508 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1255,6 +1255,7 @@ int i40e_count_filters(struct i40e_vsi *vsi) hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { if (f->state == I40E_FILTER_NEW || + f->state == I40E_FILTER_NEW_SYNC || f->state == I40E_FILTER_ACTIVE) ++cnt; } @@ -1441,6 +1442,8 @@ static int i40e_correct_mac_vlan_filters(struct i40e_vsi *vsi, new->f = add_head; new->state = add_head->state; + if (add_head->state == I40E_FILTER_NEW) + add_head->state = I40E_FILTER_NEW_SYNC; /* Add the new filter to the tmp list */ hlist_add_head(&new->hlist, tmp_add_list); @@ -1550,6 +1553,8 @@ static int i40e_correct_vf_mac_vlan_filters(struct i40e_vsi *vsi, return -ENOMEM; new_mac->f = add_head; new_mac->state = add_head->state; + if (add_head->state == I40E_FILTER_NEW) + add_head->state = I40E_FILTER_NEW_SYNC; /* Add the new filter to the tmp list */ hlist_add_head(&new_mac->hlist, tmp_add_list); @@ -2437,7 +2442,8 @@ static int i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name, struct i40e_mac_filter *f) { - bool enable = f->state == I40E_FILTER_NEW; + bool enable = f->state == I40E_FILTER_NEW || + f->state == I40E_FILTER_NEW_SYNC; struct i40e_hw *hw = &vsi->back->hw; int aq_ret; @@ -2611,6 +2617,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) /* Add it to the hash list */ hlist_add_head(&new->hlist, &tmp_add_list); + f->state = I40E_FILTER_NEW_SYNC; } /* Count the number of active (current and new) VLAN @@ -2762,7 +2769,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) spin_lock_bh(&vsi->mac_filter_hash_lock); hlist_for_each_entry_safe(new, h, &tmp_add_list, hlist) { /* Only update the state if we're still NEW */ - if (new->f->state == I40E_FILTER_NEW) + if (new->f->state == I40E_FILTER_NEW || + new->f->state == I40E_FILTER_NEW_SYNC) new->f->state = new->state; hlist_del(&new->hlist); netdev_hw_addr_refcnt(new->f, vsi->netdev, -1); diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c index 928c8bdb6649..c6779d9dffff 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c @@ -989,5 +989,11 @@ ice_devlink_port_new(struct devlink *devlink, if (err) return err; + if (!ice_is_eswitch_mode_switchdev(pf)) { + NL_SET_ERR_MSG_MOD(extack, + "SF ports are only supported in eswitch switchdev mode"); + return -EOPNOTSUPP; + } + return ice_alloc_dynamic_port(pf, new_attr, extack, devlink_port); } diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 74c0e7319a4c..d5ad6d84007c 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -10,6 +10,7 @@ #define ICE_DPLL_PIN_IDX_INVALID 0xff #define ICE_DPLL_RCLK_NUM_PER_PF 1 #define ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT 25 +#define ICE_DPLL_PIN_GEN_RCLK_FREQ 1953125 /** * enum ice_dpll_pin_type - enumerate ice pin types: @@ -2064,6 +2065,73 @@ static int ice_dpll_init_worker(struct ice_pf *pf) } /** + * ice_dpll_init_info_pins_generic - initializes generic pins info + * @pf: board private structure + * @input: if input pins initialized + * + * Init information for generic pins, cache them in PF's pins structures. + * + * Return: + * * 0 - success + * * negative - init failure reason + */ +static int ice_dpll_init_info_pins_generic(struct ice_pf *pf, bool input) +{ + struct ice_dpll *de = &pf->dplls.eec, *dp = &pf->dplls.pps; + static const char labels[][sizeof("99")] = { + "0", "1", "2", "3", "4", "5", "6", "7", "8", + "9", "10", "11", "12", "13", "14", "15" }; + u32 cap = DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; + enum ice_dpll_pin_type pin_type; + int i, pin_num, ret = -EINVAL; + struct ice_dpll_pin *pins; + u32 phase_adj_max; + + if (input) { + pin_num = pf->dplls.num_inputs; + pins = pf->dplls.inputs; + phase_adj_max = pf->dplls.input_phase_adj_max; + pin_type = ICE_DPLL_PIN_TYPE_INPUT; + cap |= DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE; + } else { + pin_num = pf->dplls.num_outputs; + pins = pf->dplls.outputs; + phase_adj_max = pf->dplls.output_phase_adj_max; + pin_type = ICE_DPLL_PIN_TYPE_OUTPUT; + } + if (pin_num > ARRAY_SIZE(labels)) + return ret; + + for (i = 0; i < pin_num; i++) { + pins[i].idx = i; + pins[i].prop.board_label = labels[i]; + pins[i].prop.phase_range.min = phase_adj_max; + pins[i].prop.phase_range.max = -phase_adj_max; + pins[i].prop.capabilities = cap; + pins[i].pf = pf; + ret = ice_dpll_pin_state_update(pf, &pins[i], pin_type, NULL); + if (ret) + break; + if (input && pins[i].freq == ICE_DPLL_PIN_GEN_RCLK_FREQ) + pins[i].prop.type = DPLL_PIN_TYPE_MUX; + else + pins[i].prop.type = DPLL_PIN_TYPE_EXT; + if (!input) + continue; + ret = ice_aq_get_cgu_ref_prio(&pf->hw, de->dpll_idx, i, + &de->input_prio[i]); + if (ret) + break; + ret = ice_aq_get_cgu_ref_prio(&pf->hw, dp->dpll_idx, i, + &dp->input_prio[i]); + if (ret) + break; + } + + return ret; +} + +/** * ice_dpll_init_info_direct_pins - initializes direct pins info * @pf: board private structure * @pin_type: type of pins being initialized @@ -2101,6 +2169,8 @@ ice_dpll_init_info_direct_pins(struct ice_pf *pf, default: return -EINVAL; } + if (num_pins != ice_cgu_get_num_pins(hw, input)) + return ice_dpll_init_info_pins_generic(pf, input); for (i = 0; i < num_pins; i++) { caps = 0; diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index c0b3e70a7ea3..fb527434b58b 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -552,13 +552,14 @@ int ice_eswitch_attach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf) static void ice_eswitch_detach(struct ice_pf *pf, struct ice_repr *repr) { ice_eswitch_stop_reprs(pf); + repr->ops.rem(repr); + xa_erase(&pf->eswitch.reprs, repr->id); if (xa_empty(&pf->eswitch.reprs)) ice_eswitch_disable_switchdev(pf); ice_eswitch_release_repr(pf, repr); - repr->ops.rem(repr); ice_repr_destroy(repr); if (xa_empty(&pf->eswitch.reprs)) { diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 5412eff8ef23..ee9862ddfe15 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -1830,11 +1830,12 @@ static int ice_set_fdir_input_set(struct ice_vsi *vsi, struct ethtool_rx_flow_spec *fsp, struct ice_fdir_fltr *input) { - u16 dest_vsi, q_index = 0; + s16 q_index = ICE_FDIR_NO_QUEUE_IDX; u16 orig_q_index = 0; struct ice_pf *pf; struct ice_hw *hw; int flow_type; + u16 dest_vsi; u8 dest_ctl; if (!vsi || !fsp || !input) diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h index ab5b118daa2d..820023c0271f 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.h +++ b/drivers/net/ethernet/intel/ice/ice_fdir.h @@ -53,6 +53,8 @@ */ #define ICE_FDIR_IPV4_PKT_FLAG_MF 0x20 +#define ICE_FDIR_NO_QUEUE_IDX -1 + enum ice_fltr_prgm_desc_dest { ICE_FLTR_PRGM_DESC_DEST_DROP_PKT, ICE_FLTR_PRGM_DESC_DEST_DIRECT_PKT_QINDEX, @@ -186,7 +188,7 @@ struct ice_fdir_fltr { u16 flex_fltr; /* filter control */ - u16 q_index; + s16 q_index; u16 orig_q_index; u16 dest_vsi; u8 dest_ctl; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index da88c6ccfaeb..dfd49732bd5b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -34,7 +34,6 @@ static const struct ice_cgu_pin_desc ice_e810t_sfp_cgu_inputs[] = { ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, { "GNSS-1PPS", ZL_REF4P, DPLL_PIN_TYPE_GNSS, ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, - { "OCXO", ZL_REF4N, DPLL_PIN_TYPE_INT_OSCILLATOR, 0, }, }; static const struct ice_cgu_pin_desc ice_e810t_qsfp_cgu_inputs[] = { @@ -52,7 +51,6 @@ static const struct ice_cgu_pin_desc ice_e810t_qsfp_cgu_inputs[] = { ARRAY_SIZE(ice_cgu_pin_freq_common), ice_cgu_pin_freq_common }, { "GNSS-1PPS", ZL_REF4P, DPLL_PIN_TYPE_GNSS, ARRAY_SIZE(ice_cgu_pin_freq_1_hz), ice_cgu_pin_freq_1_hz }, - { "OCXO", ZL_REF4N, DPLL_PIN_TYPE_INT_OSCILLATOR, }, }; static const struct ice_cgu_pin_desc ice_e810t_sfp_cgu_outputs[] = { @@ -6048,6 +6046,25 @@ ice_cgu_get_pin_desc(struct ice_hw *hw, bool input, int *size) } /** + * ice_cgu_get_num_pins - get pin description array size + * @hw: pointer to the hw struct + * @input: if request is done against input or output pins + * + * Return: size of pin description array for given hw. + */ +int ice_cgu_get_num_pins(struct ice_hw *hw, bool input) +{ + const struct ice_cgu_pin_desc *t; + int size; + + t = ice_cgu_get_pin_desc(hw, input, &size); + if (t) + return size; + + return 0; +} + +/** * ice_cgu_get_pin_type - get pin's type * @hw: pointer to the hw struct * @pin: pin index diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 656daff3447e..47af7c5c79b8 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -406,6 +406,7 @@ int ice_read_sma_ctrl(struct ice_hw *hw, u8 *data); int ice_write_sma_ctrl(struct ice_hw *hw, u8 data); int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data); int ice_ptp_read_sdp_ac(struct ice_hw *hw, __le16 *entries, uint *num_entries); +int ice_cgu_get_num_pins(struct ice_hw *hw, bool input); enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input); struct dpll_pin_frequency * ice_cgu_get_pin_freq_supp(struct ice_hw *hw, u8 pin, bool input, u8 *num); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 8208055d6e7f..5d2d7736fd5f 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1352,14 +1352,14 @@ static void ice_net_dim(struct ice_q_vector *q_vector) struct dim_sample dim_sample; __ice_update_sample(q_vector, tx, &dim_sample, true); - net_dim(&tx->dim, dim_sample); + net_dim(&tx->dim, &dim_sample); } if (ITR_IS_DYNAMIC(rx)) { struct dim_sample dim_sample; __ice_update_sample(q_vector, rx, &dim_sample, false); - net_dim(&rx->dim, dim_sample); + net_dim(&rx->dim, &dim_sample); } } diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index 2c31ad87587a..66544faab710 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -141,6 +141,7 @@ enum idpf_vport_state { * @adapter: Adapter back pointer * @vport: Vport back pointer * @vport_id: Vport identifier + * @link_speed_mbps: Link speed in mbps * @vport_idx: Relative vport index * @state: See enum idpf_vport_state * @netstats: Packet and byte stats @@ -150,6 +151,7 @@ struct idpf_netdev_priv { struct idpf_adapter *adapter; struct idpf_vport *vport; u32 vport_id; + u32 link_speed_mbps; u16 vport_idx; enum idpf_vport_state state; struct rtnl_link_stats64 netstats; @@ -287,7 +289,6 @@ struct idpf_port_stats { * @tx_itr_profile: TX profiles for Dynamic Interrupt Moderation * @port_stats: per port csum, header split, and other offload stats * @link_up: True if link is up - * @link_speed_mbps: Link speed in mbps * @sw_marker_wq: workqueue for marker packets */ struct idpf_vport { @@ -331,7 +332,6 @@ struct idpf_vport { struct idpf_port_stats port_stats; bool link_up; - u32 link_speed_mbps; wait_queue_head_t sw_marker_wq; }; diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c index 3806ddd3ce4a..59b1a1a09996 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -1296,24 +1296,19 @@ static void idpf_set_msglevel(struct net_device *netdev, u32 data) static int idpf_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { - struct idpf_vport *vport; - - idpf_vport_ctrl_lock(netdev); - vport = idpf_netdev_to_vport(netdev); + struct idpf_netdev_priv *np = netdev_priv(netdev); ethtool_link_ksettings_zero_link_mode(cmd, supported); cmd->base.autoneg = AUTONEG_DISABLE; cmd->base.port = PORT_NONE; - if (vport->link_up) { + if (netif_carrier_ok(netdev)) { cmd->base.duplex = DUPLEX_FULL; - cmd->base.speed = vport->link_speed_mbps; + cmd->base.speed = np->link_speed_mbps; } else { cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.speed = SPEED_UNKNOWN; } - idpf_vport_ctrl_unlock(netdev); - return 0; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 4f20343e49a9..b4fbb99bfad2 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -1786,6 +1786,7 @@ static int idpf_init_hard_reset(struct idpf_adapter *adapter) */ err = idpf_vc_core_init(adapter); if (err) { + cancel_delayed_work_sync(&adapter->mbx_task); idpf_deinit_dflt_mbx(adapter); goto unlock_mutex; } @@ -1860,7 +1861,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, * mess with. Nothing below should use those variables from new_vport * and should instead always refer to them in vport if they need to. */ - memcpy(new_vport, vport, offsetof(struct idpf_vport, link_speed_mbps)); + memcpy(new_vport, vport, offsetof(struct idpf_vport, link_up)); /* Adjust resource parameters prior to reallocating resources */ switch (reset_cause) { @@ -1906,7 +1907,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, /* Same comment as above regarding avoiding copying the wait_queues and * mutexes applies here. We do not want to mess with those if possible. */ - memcpy(vport, new_vport, offsetof(struct idpf_vport, link_speed_mbps)); + memcpy(vport, new_vport, offsetof(struct idpf_vport, link_up)); if (reset_cause == IDPF_SR_Q_CHANGE) idpf_vport_alloc_vec_indexes(vport); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index d4e6f0e10487..da2a5becf62f 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3679,7 +3679,7 @@ static void idpf_net_dim(struct idpf_q_vector *q_vector) idpf_update_dim_sample(q_vector, &dim_sample, &q_vector->tx_dim, packets, bytes); - net_dim(&q_vector->tx_dim, dim_sample); + net_dim(&q_vector->tx_dim, &dim_sample); check_rx_itr: if (!IDPF_ITR_IS_DYNAMIC(q_vector->rx_intr_mode)) @@ -3698,7 +3698,7 @@ check_rx_itr: idpf_update_dim_sample(q_vector, &dim_sample, &q_vector->rx_dim, packets, bytes); - net_dim(&q_vector->rx_dim, dim_sample); + net_dim(&q_vector->rx_dim, &dim_sample); } /** diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index 15c00a01f1c0..d46c95f91b0d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -141,7 +141,7 @@ static void idpf_handle_event_link(struct idpf_adapter *adapter, } np = netdev_priv(vport->netdev); - vport->link_speed_mbps = le32_to_cpu(v2e->link_speed); + np->link_speed_mbps = le32_to_cpu(v2e->link_speed); if (vport->link_up == v2e->link_status) return; @@ -3063,7 +3063,6 @@ init_failed: adapter->state = __IDPF_VER_CHECK; if (adapter->vcxn_mngr) idpf_vc_xn_shutdown(adapter->vcxn_mngr); - idpf_deinit_dflt_mbx(adapter); set_bit(IDPF_HR_DRV_LOAD, adapter->flags); queue_delayed_work(adapter->vc_event_wq, &adapter->vc_event_task, msecs_to_jiffies(task_delay)); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index f1d088168723..b83df5f94b1f 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -907,7 +907,7 @@ static int igb_request_msix(struct igb_adapter *adapter) int i, err = 0, vector = 0, free_vector = 0; err = request_irq(adapter->msix_entries[vector].vector, - igb_msix_other, 0, netdev->name, adapter); + igb_msix_other, IRQF_NO_THREAD, netdev->name, adapter); if (err) goto err_out; diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig index a32d85d6f599..35c4f5f64f58 100644 --- a/drivers/net/ethernet/marvell/octeontx2/Kconfig +++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig @@ -46,3 +46,11 @@ config OCTEONTX2_VF depends on OCTEONTX2_PF help This driver supports Marvell's OcteonTX2 NIC virtual function. + +config RVU_ESWITCH + tristate "Marvell RVU E-Switch support" + depends on OCTEONTX2_PF + default m + help + This driver supports Marvell's RVU E-Switch that + provides internal SRIOV packet steering and switching. diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile index 3cf4c8285c90..ccea37847df8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile @@ -11,4 +11,5 @@ rvu_mbox-y := mbox.o rvu_trace.o rvu_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \ rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o \ rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o rvu_switch.o \ - rvu_sdp.o rvu_npc_hash.o mcs.o mcs_rvu_if.o mcs_cnf10kb.o + rvu_sdp.o rvu_npc_hash.o mcs.o mcs_rvu_if.o mcs_cnf10kb.o \ + rvu_rep.o diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h index 2436c1ff9ba4..5d84386ed22d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h @@ -156,6 +156,7 @@ enum nix_scheduler { #define NIC_HW_MIN_FRS 40 #define NIC_HW_MAX_FRS 9212 #define SDP_HW_MAX_FRS 65535 +#define SDP_HW_MIN_FRS 16 #define CN10K_LMAC_LINK_MAX_FRS 16380 /* 16k - FCS */ #define CN10K_LBK_LINK_MAX_FRS 65535 /* 64k */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 6ea2f3071fe8..62c07407eb94 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -144,6 +144,9 @@ M(LMTST_TBL_SETUP, 0x00a, lmtst_tbl_setup, lmtst_tbl_setup_req, \ msg_rsp) \ M(SET_VF_PERM, 0x00b, set_vf_perm, set_vf_perm, msg_rsp) \ M(PTP_GET_CAP, 0x00c, ptp_get_cap, msg_req, ptp_get_cap_rsp) \ +M(GET_REP_CNT, 0x00d, get_rep_cnt, msg_req, get_rep_cnt_rsp) \ +M(ESW_CFG, 0x00e, esw_cfg, esw_cfg_req, msg_rsp) \ +M(REP_EVENT_NOTIFY, 0x00f, rep_event_notify, rep_event, msg_rsp) \ /* CGX mbox IDs (range 0x200 - 0x3FF) */ \ M(CGX_START_RXTX, 0x200, cgx_start_rxtx, msg_req, msg_rsp) \ M(CGX_STOP_RXTX, 0x201, cgx_stop_rxtx, msg_req, msg_rsp) \ @@ -319,6 +322,7 @@ M(NIX_MCAST_GRP_DESTROY, 0x802c, nix_mcast_grp_destroy, nix_mcast_grp_destroy_re M(NIX_MCAST_GRP_UPDATE, 0x802d, nix_mcast_grp_update, \ nix_mcast_grp_update_req, \ nix_mcast_grp_update_rsp) \ +M(NIX_LF_STATS, 0x802e, nix_lf_stats, nix_stats_req, nix_stats_rsp) \ /* MCS mbox IDs (range 0xA000 - 0xBFFF) */ \ M(MCS_ALLOC_RESOURCES, 0xa000, mcs_alloc_resources, mcs_alloc_rsrc_req, \ mcs_alloc_rsrc_rsp) \ @@ -380,12 +384,16 @@ M(CPT_INST_LMTST, 0xD00, cpt_inst_lmtst, cpt_inst_lmtst_req, msg_rsp) #define MBOX_UP_MCS_MESSAGES \ M(MCS_INTR_NOTIFY, 0xE00, mcs_intr_notify, mcs_intr_info, msg_rsp) +#define MBOX_UP_REP_MESSAGES \ +M(REP_EVENT_UP_NOTIFY, 0xEF0, rep_event_up_notify, rep_event, msg_rsp) \ + enum { #define M(_name, _id, _1, _2, _3) MBOX_MSG_ ## _name = _id, MBOX_MESSAGES MBOX_UP_CGX_MESSAGES MBOX_UP_CPT_MESSAGES MBOX_UP_MCS_MESSAGES +MBOX_UP_REP_MESSAGES #undef M }; @@ -1364,6 +1372,37 @@ struct nix_bandprof_get_hwinfo_rsp { u32 policer_timeunit; }; +struct nix_stats_req { + struct mbox_msghdr hdr; + u8 reset; + u16 pcifunc; + u64 rsvd; +}; + +struct nix_stats_rsp { + struct mbox_msghdr hdr; + u16 pcifunc; + struct { + u64 octs; + u64 ucast; + u64 bcast; + u64 mcast; + u64 drop; + u64 drop_octs; + u64 drop_mcast; + u64 drop_bcast; + u64 err; + u64 rsvd[5]; + } rx; + struct { + u64 ucast; + u64 bcast; + u64 mcast; + u64 drop; + u64 octs; + } tx; +}; + /* NPC mbox message structs */ #define NPC_MCAM_ENTRY_INVALID 0xFFFF @@ -1525,6 +1564,41 @@ struct ptp_get_cap_rsp { u64 cap; }; +struct get_rep_cnt_rsp { + struct mbox_msghdr hdr; + u16 rep_cnt; + u16 rep_pf_map[64]; + u64 rsvd; +}; + +struct esw_cfg_req { + struct mbox_msghdr hdr; + u8 ena; + u64 rsvd; +}; + +struct rep_evt_data { + u8 port_state; + u8 vf_state; + u16 rx_mode; + u16 rx_flags; + u16 mtu; + u8 mac[ETH_ALEN]; + u64 rsvd[5]; +}; + +struct rep_event { + struct mbox_msghdr hdr; + u16 pcifunc; +#define RVU_EVENT_PORT_STATE BIT_ULL(0) +#define RVU_EVENT_PFVF_STATE BIT_ULL(1) +#define RVU_EVENT_MTU_CHANGE BIT_ULL(2) +#define RVU_EVENT_RX_MODE_CHANGE BIT_ULL(3) +#define RVU_EVENT_MAC_ADDR_CHANGE BIT_ULL(4) + u16 event; + struct rep_evt_data evt_data; +}; + struct flow_msg { unsigned char dmac[6]; unsigned char smac[6]; @@ -1563,6 +1637,7 @@ struct flow_msg { u8 icmp_type; u8 icmp_code; __be16 tcp_flags; + u16 sq_id; }; struct npc_install_flow_req { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 5016ba82e142..b897845e25fd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -513,6 +513,11 @@ struct rvu_switch { u16 start_entry; }; +struct rep_evtq_ent { + struct list_head node; + struct rep_event event; +}; + struct rvu { void __iomem *afreg_base; void __iomem *pfreg_base; @@ -525,6 +530,7 @@ struct rvu { struct mutex alias_lock; /* Serialize bar2 alias access */ int vfs; /* Number of VFs attached to RVU */ u16 vf_devid; /* VF devices id */ + bool def_rule_cntr_en; int nix_blkaddr[MAX_NIX_BLKS]; /* Mbox */ @@ -594,6 +600,15 @@ struct rvu { spinlock_t cpt_intr_lock; struct mutex mbox_lock; /* Serialize mbox up and down msgs */ + u16 rep_pcifunc; + int rep_cnt; + u16 *rep2pfvf_map; + u8 rep_mode; + struct work_struct rep_evt_work; + struct workqueue_struct *rep_evt_wq; + struct list_head rep_evtq_head; + /* Representor event lock */ + spinlock_t rep_evtq_lock; }; static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val) @@ -852,6 +867,14 @@ bool is_sdp_pfvf(u16 pcifunc); bool is_sdp_pf(u16 pcifunc); bool is_sdp_vf(struct rvu *rvu, u16 pcifunc); +static inline bool is_rep_dev(struct rvu *rvu, u16 pcifunc) +{ + if (rvu->rep_pcifunc && rvu->rep_pcifunc == pcifunc) + return true; + + return false; +} + /* CGX APIs */ static inline bool is_pf_cgxmapped(struct rvu *rvu, u8 pf) { @@ -960,7 +983,11 @@ void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, int group, int alg_idx, int mcam_index); - +void __rvu_mcam_remove_counter_from_rule(struct rvu *rvu, u16 pcifunc, + struct rvu_npc_mcam_rule *rule); +void __rvu_mcam_add_counter_to_rule(struct rvu *rvu, u16 pcifunc, + struct rvu_npc_mcam_rule *rule, + struct npc_install_flow_rsp *rsp); void rvu_npc_get_mcam_entry_alloc_info(struct rvu *rvu, u16 pcifunc, int blkaddr, int *alloc_cnt, int *enable_cnt); @@ -985,6 +1012,7 @@ void npc_set_mcam_action(struct rvu *rvu, struct npc_mcam *mcam, void npc_read_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, int blkaddr, u16 src, struct mcam_entry *entry, u8 *intf, u8 *ena); +int npc_config_cntr_default_entries(struct rvu *rvu, bool enable); bool is_cgx_config_permitted(struct rvu *rvu, u16 pcifunc); bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature); u32 rvu_cgx_get_fifolen(struct rvu *rvu); @@ -1045,7 +1073,8 @@ int rvu_ndc_fix_locked_cacheline(struct rvu *rvu, int blkaddr); /* RVU Switch */ void rvu_switch_enable(struct rvu *rvu); void rvu_switch_disable(struct rvu *rvu); -void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc); +void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc, bool ena); +void rvu_switch_enable_lbk_link(struct rvu *rvu, u16 pcifunc, bool ena); int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir, u64 pkind, u8 var_len_off, u8 var_len_off_mask, @@ -1058,4 +1087,9 @@ int rvu_mcs_flr_handler(struct rvu *rvu, u16 pcifunc); void rvu_mcs_ptp_cfg(struct rvu *rvu, u8 rpm_id, u8 lmac_id, bool ena); void rvu_mcs_exit(struct rvu *rvu); +/* Representor APIs */ +int rvu_rep_pf_init(struct rvu *rvu); +int rvu_rep_install_mcam_rules(struct rvu *rvu); +void rvu_rep_update_rules(struct rvu *rvu, u16 pcifunc, bool ena); +int rvu_rep_notify_pfvf_state(struct rvu *rvu, u16 pcifunc, bool enable); #endif /* RVU_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 8c700ee4a82b..148144f5b61d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -45,33 +45,6 @@ enum { CGX_STAT18, }; -/* NIX TX stats */ -enum nix_stat_lf_tx { - TX_UCAST = 0x0, - TX_BCAST = 0x1, - TX_MCAST = 0x2, - TX_DROP = 0x3, - TX_OCTS = 0x4, - TX_STATS_ENUM_LAST, -}; - -/* NIX RX stats */ -enum nix_stat_lf_rx { - RX_OCTS = 0x0, - RX_UCAST = 0x1, - RX_BCAST = 0x2, - RX_MCAST = 0x3, - RX_DROP = 0x4, - RX_DROP_OCTS = 0x5, - RX_FCS = 0x6, - RX_ERR = 0x7, - RX_DRP_BCAST = 0x8, - RX_DRP_MCAST = 0x9, - RX_DRP_L3BCAST = 0xa, - RX_DRP_L3MCAST = 0xb, - RX_STATS_ENUM_LAST, -}; - static char *cgx_rx_stats_fields[] = { [CGX_STAT0] = "Received packets", [CGX_STAT1] = "Octets of received packets", diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 7498ab429963..dab4deca893f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -1238,6 +1238,7 @@ enum rvu_af_dl_param_id { RVU_AF_DEVLINK_PARAM_ID_DWRR_MTU, RVU_AF_DEVLINK_PARAM_ID_NPC_MCAM_ZONE_PERCENT, RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE, + RVU_AF_DEVLINK_PARAM_ID_NPC_DEF_RULE_CNTR_ENABLE, RVU_AF_DEVLINK_PARAM_ID_NIX_MAXLF, }; @@ -1358,6 +1359,32 @@ static int rvu_af_dl_npc_mcam_high_zone_percent_validate(struct devlink *devlink return 0; } +static int rvu_af_dl_npc_def_rule_cntr_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct rvu_devlink *rvu_dl = devlink_priv(devlink); + struct rvu *rvu = rvu_dl->rvu; + + ctx->val.vbool = rvu->def_rule_cntr_en; + + return 0; +} + +static int rvu_af_dl_npc_def_rule_cntr_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + struct rvu_devlink *rvu_dl = devlink_priv(devlink); + struct rvu *rvu = rvu_dl->rvu; + int err; + + err = npc_config_cntr_default_entries(rvu, ctx->val.vbool); + if (!err) + rvu->def_rule_cntr_en = ctx->val.vbool; + + return err; +} + static int rvu_af_dl_nix_maxlf_get(struct devlink *devlink, u32 id, struct devlink_param_gset_ctx *ctx) { @@ -1444,6 +1471,11 @@ static const struct devlink_param rvu_af_dl_params[] = { rvu_af_dl_npc_mcam_high_zone_percent_get, rvu_af_dl_npc_mcam_high_zone_percent_set, rvu_af_dl_npc_mcam_high_zone_percent_validate), + DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_DEF_RULE_CNTR_ENABLE, + "npc_def_rule_cntr", DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + rvu_af_dl_npc_def_rule_cntr_get, + rvu_af_dl_npc_def_rule_cntr_set, NULL), DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NIX_MAXLF, "nix_maxlf", DEVLINK_PARAM_TYPE_U16, BIT(DEVLINK_PARAM_CMODE_RUNTIME), @@ -1468,6 +1500,9 @@ static int rvu_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) struct rvu *rvu = rvu_dl->rvu; struct rvu_switch *rswitch; + if (rvu->rep_mode) + return -EOPNOTSUPP; + rswitch = &rvu->rswitch; *mode = rswitch->mode; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index da69350c6f76..5d5a01dbbca1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -31,6 +31,7 @@ static int nix_free_all_bandprof(struct rvu *rvu, u16 pcifunc); static void nix_clear_ratelimit_aggr(struct rvu *rvu, struct nix_hw *nix_hw, u32 leaf_prof); static const char *nix_get_ctx_name(int ctype); +static int nix_get_tx_link(struct rvu *rvu, u16 pcifunc); enum mc_tbl_sz { MC_TBL_SZ_256, @@ -312,7 +313,9 @@ static bool is_valid_txschq(struct rvu *rvu, int blkaddr, /* TLs aggegating traffic are shared across PF and VFs */ if (lvl >= hw->cap.nix_tx_aggr_lvl) { - if (rvu_get_pf(map_func) != rvu_get_pf(pcifunc)) + if ((nix_get_tx_link(rvu, map_func) != + nix_get_tx_link(rvu, pcifunc)) && + (rvu_get_pf(map_func) != rvu_get_pf(pcifunc))) return false; else return true; @@ -360,7 +363,6 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf, cgx_set_pkind(rvu_cgx_pdata(cgx_id, rvu), lmac_id, pkind); rvu_npc_set_pkind(rvu, pkind, pfvf); - break; case NIX_INTF_TYPE_LBK: vf = (pcifunc & RVU_PFVF_FUNC_MASK) - 1; @@ -584,6 +586,9 @@ int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu, if (!is_pf_cgxmapped(rvu, pf) && type != NIX_INTF_TYPE_LBK) return 0; + if (is_sdp_pfvf(pcifunc)) + type = NIX_INTF_TYPE_SDP; + pfvf = rvu_get_pfvf(rvu, pcifunc); err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr); if (err) @@ -1614,6 +1619,12 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu, cfg = NPC_TX_DEF_PKIND; rvu_write64(rvu, blkaddr, NIX_AF_LFX_TX_PARSE_CFG(nixlf), cfg); + if (is_rep_dev(rvu, pcifunc)) { + pfvf->tx_chan_base = RVU_SWITCH_LBK_CHAN; + pfvf->tx_chan_cnt = 1; + goto exit; + } + intf = is_lbk_vf(rvu, pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX; if (is_sdp_pfvf(pcifunc)) intf = NIX_INTF_TYPE_SDP; @@ -1684,6 +1695,9 @@ int rvu_mbox_handler_nix_lf_free(struct rvu *rvu, struct nix_lf_free_req *req, if (nixlf < 0) return NIX_AF_ERR_AF_LF_INVALID; + if (is_rep_dev(rvu, pcifunc)) + goto free_lf; + if (req->flags & NIX_LF_DISABLE_FLOWS) rvu_npc_disable_mcam_entries(rvu, pcifunc, nixlf); else @@ -1695,6 +1709,7 @@ int rvu_mbox_handler_nix_lf_free(struct rvu *rvu, struct nix_lf_free_req *req, nix_interface_deinit(rvu, pcifunc, nixlf); +free_lf: /* Reset this NIX LF */ err = rvu_lf_reset(rvu, block, nixlf); if (err) { @@ -2007,7 +2022,8 @@ static void nix_get_txschq_range(struct rvu *rvu, u16 pcifunc, struct rvu_hwinfo *hw = rvu->hw; int pf = rvu_get_pf(pcifunc); - if (is_lbk_vf(rvu, pcifunc)) { /* LBK links */ + /* LBK links */ + if (is_lbk_vf(rvu, pcifunc) || is_rep_dev(rvu, pcifunc)) { *start = hw->cap.nix_txsch_per_cgx_lmac * link; *end = *start + hw->cap.nix_txsch_per_lbk_lmac; } else if (is_pf_cgxmapped(rvu, pf)) { /* CGX links */ @@ -2760,7 +2776,7 @@ void rvu_nix_tx_tl2_cfg(struct rvu *rvu, int blkaddr, u16 pcifunc, int schq; u64 cfg; - if (!is_pf_cgxmapped(rvu, pf)) + if (!is_pf_cgxmapped(rvu, pf) && !is_rep_dev(rvu, pcifunc)) return; cfg = enable ? (BIT_ULL(12) | RVU_SWITCH_LBK_CHAN) : 0; @@ -4393,8 +4409,6 @@ int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu, if (test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && from_vf) ether_addr_copy(pfvf->default_mac, req->mac_addr); - rvu_switch_update_rules(rvu, pcifunc); - return 0; } @@ -4555,7 +4569,7 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, if (!nix_hw) return NIX_AF_ERR_INVALID_NIXBLK; - if (is_lbk_vf(rvu, pcifunc)) + if (is_lbk_vf(rvu, pcifunc) || is_rep_dev(rvu, pcifunc)) rvu_get_lbk_link_max_frs(rvu, &max_mtu); else rvu_get_lmac_link_max_frs(rvu, &max_mtu); @@ -4583,6 +4597,8 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, /* For VFs of PF0 ingress is LBK port, so config LBK link */ pfvf = rvu_get_pfvf(rvu, pcifunc); link = hw->cgx_links + pfvf->lbkid; + } else if (is_rep_dev(rvu, pcifunc)) { + link = hw->cgx_links + 0; } if (link < 0) @@ -4674,7 +4690,7 @@ static void nix_link_config(struct rvu *rvu, int blkaddr, if (hw->sdp_links) { link = hw->cgx_links + hw->lbk_links; rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link), - SDP_HW_MAX_FRS << 16 | NIC_HW_MIN_FRS); + SDP_HW_MAX_FRS << 16 | SDP_HW_MIN_FRS); } /* Get MCS external bypass status for CN10K-B */ @@ -5166,7 +5182,7 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req, { u16 pcifunc = req->hdr.pcifunc; struct rvu_pfvf *pfvf; - int nixlf, err; + int nixlf, err, pf; err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL); if (err) @@ -5182,7 +5198,11 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req, pfvf = rvu_get_pfvf(rvu, pcifunc); set_bit(NIXLF_INITIALIZED, &pfvf->flags); - rvu_switch_update_rules(rvu, pcifunc); + rvu_switch_update_rules(rvu, pcifunc, true); + + pf = rvu_get_pf(pcifunc); + if (is_pf_cgxmapped(rvu, pf) && rvu->rep_mode) + rvu_rep_notify_pfvf_state(rvu, pcifunc, true); return rvu_cgx_start_stop_io(rvu, pcifunc, true); } @@ -5192,7 +5212,7 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, { u16 pcifunc = req->hdr.pcifunc; struct rvu_pfvf *pfvf; - int nixlf, err; + int nixlf, err, pf; err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL); if (err) @@ -5210,8 +5230,12 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, if (err) return err; + rvu_switch_update_rules(rvu, pcifunc, false); rvu_cgx_tx_enable(rvu, pcifunc, true); + pf = rvu_get_pf(pcifunc); + if (is_pf_cgxmapped(rvu, pf) && rvu->rep_mode) + rvu_rep_notify_pfvf_state(rvu, pcifunc, false); return 0; } @@ -5239,6 +5263,9 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) clear_bit(NIXLF_INITIALIZED, &pfvf->flags); + if (is_pf_cgxmapped(rvu, pf) && rvu->rep_mode) + rvu_rep_notify_pfvf_state(rvu, pcifunc, false); + rvu_cgx_start_stop_io(rvu, pcifunc, false); if (pfvf->sq_ctx) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 97722ce8c4cb..821fe242f821 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -2691,6 +2691,49 @@ void npc_mcam_rsrcs_reserve(struct rvu *rvu, int blkaddr, int entry_idx) npc_mcam_set_bit(mcam, entry_idx); } +int npc_config_cntr_default_entries(struct rvu *rvu, bool enable) +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + struct npc_install_flow_rsp rsp; + struct rvu_npc_mcam_rule *rule; + int blkaddr; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + if (blkaddr < 0) + return -EINVAL; + + mutex_lock(&mcam->lock); + list_for_each_entry(rule, &mcam->mcam_rules, list) { + if (!is_mcam_entry_enabled(rvu, mcam, blkaddr, rule->entry)) + continue; + if (!rule->default_rule) + continue; + if (enable && !rule->has_cntr) { /* Alloc and map new counter */ + __rvu_mcam_add_counter_to_rule(rvu, rule->owner, + rule, &rsp); + if (rsp.counter < 0) { + dev_err(rvu->dev, + "%s: Failed to allocate cntr for default rule (err=%d)\n", + __func__, rsp.counter); + break; + } + npc_map_mcam_entry_and_cntr(rvu, mcam, blkaddr, + rule->entry, rsp.counter); + /* Reset counter before use */ + rvu_write64(rvu, blkaddr, + NPC_AF_MATCH_STATX(rule->cntr), 0x0); + } + + /* Free and unmap counter */ + if (!enable && rule->has_cntr) + __rvu_mcam_remove_counter_from_rule(rvu, rule->owner, + rule); + } + mutex_unlock(&mcam->lock); + + return 0; +} + int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu, struct npc_mcam_alloc_entry_req *req, struct npc_mcam_alloc_entry_rsp *rsp) @@ -2975,9 +3018,9 @@ int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu, return rc; } -int rvu_mbox_handler_npc_mcam_alloc_counter(struct rvu *rvu, - struct npc_mcam_alloc_counter_req *req, - struct npc_mcam_alloc_counter_rsp *rsp) +static int __npc_mcam_alloc_counter(struct rvu *rvu, + struct npc_mcam_alloc_counter_req *req, + struct npc_mcam_alloc_counter_rsp *rsp) { struct npc_mcam *mcam = &rvu->hw->mcam; u16 pcifunc = req->hdr.pcifunc; @@ -2998,11 +3041,9 @@ int rvu_mbox_handler_npc_mcam_alloc_counter(struct rvu *rvu, if (!req->contig && req->count > NPC_MAX_NONCONTIG_COUNTERS) return NPC_MCAM_INVALID_REQ; - mutex_lock(&mcam->lock); /* Check if unused counters are available or not */ if (!rvu_rsrc_free_count(&mcam->counters)) { - mutex_unlock(&mcam->lock); return NPC_MCAM_ALLOC_FAILED; } @@ -3035,12 +3076,27 @@ int rvu_mbox_handler_npc_mcam_alloc_counter(struct rvu *rvu, } } - mutex_unlock(&mcam->lock); return 0; } -int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu, - struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp) +int rvu_mbox_handler_npc_mcam_alloc_counter(struct rvu *rvu, + struct npc_mcam_alloc_counter_req *req, + struct npc_mcam_alloc_counter_rsp *rsp) +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + int err; + + mutex_lock(&mcam->lock); + + err = __npc_mcam_alloc_counter(rvu, req, rsp); + + mutex_unlock(&mcam->lock); + return err; +} + +static int __npc_mcam_free_counter(struct rvu *rvu, + struct npc_mcam_oper_counter_req *req, + struct msg_rsp *rsp) { struct npc_mcam *mcam = &rvu->hw->mcam; u16 index, entry = 0; @@ -3050,10 +3106,8 @@ int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu, if (blkaddr < 0) return NPC_MCAM_INVALID_REQ; - mutex_lock(&mcam->lock); err = npc_mcam_verify_counter(mcam, req->hdr.pcifunc, req->cntr); if (err) { - mutex_unlock(&mcam->lock); return err; } @@ -3077,10 +3131,66 @@ int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu, index, req->cntr); } - mutex_unlock(&mcam->lock); return 0; } +int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu, + struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp) +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + int err; + + mutex_lock(&mcam->lock); + + err = __npc_mcam_free_counter(rvu, req, rsp); + + mutex_unlock(&mcam->lock); + + return err; +} + +void __rvu_mcam_remove_counter_from_rule(struct rvu *rvu, u16 pcifunc, + struct rvu_npc_mcam_rule *rule) +{ + struct npc_mcam_oper_counter_req free_req = { 0 }; + struct msg_rsp free_rsp; + + if (!rule->has_cntr) + return; + + free_req.hdr.pcifunc = pcifunc; + free_req.cntr = rule->cntr; + + __npc_mcam_free_counter(rvu, &free_req, &free_rsp); + rule->has_cntr = false; +} + +void __rvu_mcam_add_counter_to_rule(struct rvu *rvu, u16 pcifunc, + struct rvu_npc_mcam_rule *rule, + struct npc_install_flow_rsp *rsp) +{ + struct npc_mcam_alloc_counter_req cntr_req = { 0 }; + struct npc_mcam_alloc_counter_rsp cntr_rsp = { 0 }; + int err; + + cntr_req.hdr.pcifunc = pcifunc; + cntr_req.contig = true; + cntr_req.count = 1; + + /* we try to allocate a counter to track the stats of this + * rule. If counter could not be allocated then proceed + * without counter because counters are limited than entries. + */ + err = __npc_mcam_alloc_counter(rvu, &cntr_req, &cntr_rsp); + if (!err && cntr_rsp.count) { + rule->cntr = cntr_rsp.cntr; + rule->has_cntr = true; + rsp->counter = rule->cntr; + } else { + rsp->counter = err; + } +} + int rvu_mbox_handler_npc_mcam_unmap_counter(struct rvu *rvu, struct npc_mcam_unmap_counter_req *req, struct msg_rsp *rsp) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index 150635de2bd5..da69e454662a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -1081,44 +1081,26 @@ static void rvu_mcam_add_rule(struct npc_mcam *mcam, static void rvu_mcam_remove_counter_from_rule(struct rvu *rvu, u16 pcifunc, struct rvu_npc_mcam_rule *rule) { - struct npc_mcam_oper_counter_req free_req = { 0 }; - struct msg_rsp free_rsp; + struct npc_mcam *mcam = &rvu->hw->mcam; - if (!rule->has_cntr) - return; + mutex_lock(&mcam->lock); - free_req.hdr.pcifunc = pcifunc; - free_req.cntr = rule->cntr; + __rvu_mcam_remove_counter_from_rule(rvu, pcifunc, rule); - rvu_mbox_handler_npc_mcam_free_counter(rvu, &free_req, &free_rsp); - rule->has_cntr = false; + mutex_unlock(&mcam->lock); } static void rvu_mcam_add_counter_to_rule(struct rvu *rvu, u16 pcifunc, struct rvu_npc_mcam_rule *rule, struct npc_install_flow_rsp *rsp) { - struct npc_mcam_alloc_counter_req cntr_req = { 0 }; - struct npc_mcam_alloc_counter_rsp cntr_rsp = { 0 }; - int err; + struct npc_mcam *mcam = &rvu->hw->mcam; - cntr_req.hdr.pcifunc = pcifunc; - cntr_req.contig = true; - cntr_req.count = 1; + mutex_lock(&mcam->lock); - /* we try to allocate a counter to track the stats of this - * rule. If counter could not be allocated then proceed - * without counter because counters are limited than entries. - */ - err = rvu_mbox_handler_npc_mcam_alloc_counter(rvu, &cntr_req, - &cntr_rsp); - if (!err && cntr_rsp.count) { - rule->cntr = cntr_rsp.cntr; - rule->has_cntr = true; - rsp->counter = rule->cntr; - } else { - rsp->counter = err; - } + __rvu_mcam_add_counter_to_rule(rvu, pcifunc, rule, rsp); + + mutex_unlock(&mcam->lock); } static int npc_mcast_update_action_index(struct rvu *rvu, struct npc_install_flow_req *req, @@ -1416,6 +1398,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu, struct npc_install_flow_rsp *rsp) { bool from_vf = !!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK); + bool from_rep_dev = !!is_rep_dev(rvu, req->hdr.pcifunc); struct rvu_switch *rswitch = &rvu->rswitch; int blkaddr, nixlf, err; struct rvu_pfvf *pfvf; @@ -1472,14 +1455,19 @@ process_flow: /* AF installing for a PF/VF */ if (!req->hdr.pcifunc) target = req->vf; + /* PF installing for its VF */ - else if (!from_vf && req->vf) { + if (!from_vf && req->vf && !from_rep_dev) { target = (req->hdr.pcifunc & ~RVU_PFVF_FUNC_MASK) | req->vf; pf_set_vfs_mac = req->default_rule && (req->features & BIT_ULL(NPC_DMAC)); } - /* msg received from PF/VF */ + + /* Representor device installing for a representee */ + if (from_rep_dev && req->vf) + target = req->vf; else + /* msg received from PF/VF */ target = req->hdr.pcifunc; /* ignore chan_mask in case pf func is not AF, revisit later */ @@ -1492,8 +1480,10 @@ process_flow: pfvf = rvu_get_pfvf(rvu, target); + if (from_rep_dev) + req->channel = pfvf->rx_chan_base; /* PF installing for its VF */ - if (req->hdr.pcifunc && !from_vf && req->vf) + if (req->hdr.pcifunc && !from_vf && req->vf && !from_rep_dev) set_bit(PF_SET_VF_CFG, &pfvf->flags); /* update req destination mac addr */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index 2b299fa85159..62cdc714ba57 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -445,6 +445,7 @@ #define NIX_CONST_MAX_BPIDS GENMASK_ULL(23, 12) #define NIX_CONST_SDP_CHANS GENMASK_ULL(11, 0) +#define NIX_VLAN_ETYPE_MASK GENMASK_ULL(63, 48) #define NIX_AF_MDQ_PARENT_MASK GENMASK_ULL(24, 16) #define NIX_AF_TL4_PARENT_MASK GENMASK_ULL(23, 16) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c new file mode 100644 index 000000000000..052ae5923e3a --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c @@ -0,0 +1,468 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell RVU Admin Function driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#include <linux/bitfield.h> +#include <linux/types.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/pci.h> + +#include "rvu.h" +#include "rvu_reg.h" + +#define M(_name, _id, _fn_name, _req_type, _rsp_type) \ +static struct _req_type __maybe_unused \ +*otx2_mbox_alloc_msg_ ## _fn_name(struct rvu *rvu, int devid) \ +{ \ + struct _req_type *req; \ + \ + req = (struct _req_type *)otx2_mbox_alloc_msg_rsp( \ + &rvu->afpf_wq_info.mbox_up, devid, sizeof(struct _req_type), \ + sizeof(struct _rsp_type)); \ + if (!req) \ + return NULL; \ + req->hdr.sig = OTX2_MBOX_REQ_SIG; \ + req->hdr.id = _id; \ + return req; \ +} + +MBOX_UP_REP_MESSAGES +#undef M + +static int rvu_rep_up_notify(struct rvu *rvu, struct rep_event *event) +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, event->pcifunc); + struct rep_event *msg; + int pf; + + pf = rvu_get_pf(event->pcifunc); + + if (event->event & RVU_EVENT_MAC_ADDR_CHANGE) + ether_addr_copy(pfvf->mac_addr, event->evt_data.mac); + + mutex_lock(&rvu->mbox_lock); + msg = otx2_mbox_alloc_msg_rep_event_up_notify(rvu, pf); + if (!msg) { + mutex_unlock(&rvu->mbox_lock); + return -ENOMEM; + } + + msg->hdr.pcifunc = event->pcifunc; + msg->event = event->event; + + memcpy(&msg->evt_data, &event->evt_data, sizeof(struct rep_evt_data)); + + otx2_mbox_wait_for_zero(&rvu->afpf_wq_info.mbox_up, pf); + + otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pf); + + mutex_unlock(&rvu->mbox_lock); + return 0; +} + +static void rvu_rep_wq_handler(struct work_struct *work) +{ + struct rvu *rvu = container_of(work, struct rvu, rep_evt_work); + struct rep_evtq_ent *qentry; + struct rep_event *event; + unsigned long flags; + + do { + spin_lock_irqsave(&rvu->rep_evtq_lock, flags); + qentry = list_first_entry_or_null(&rvu->rep_evtq_head, + struct rep_evtq_ent, + node); + if (qentry) + list_del(&qentry->node); + + spin_unlock_irqrestore(&rvu->rep_evtq_lock, flags); + if (!qentry) + break; /* nothing more to process */ + + event = &qentry->event; + + rvu_rep_up_notify(rvu, event); + kfree(qentry); + } while (1); +} + +int rvu_mbox_handler_rep_event_notify(struct rvu *rvu, struct rep_event *req, + struct msg_rsp *rsp) +{ + struct rep_evtq_ent *qentry; + + qentry = kmalloc(sizeof(*qentry), GFP_ATOMIC); + if (!qentry) + return -ENOMEM; + + qentry->event = *req; + spin_lock(&rvu->rep_evtq_lock); + list_add_tail(&qentry->node, &rvu->rep_evtq_head); + spin_unlock(&rvu->rep_evtq_lock); + queue_work(rvu->rep_evt_wq, &rvu->rep_evt_work); + return 0; +} + +int rvu_rep_notify_pfvf_state(struct rvu *rvu, u16 pcifunc, bool enable) +{ + struct rep_event *req; + int pf; + + if (!is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) + return 0; + + pf = rvu_get_pf(rvu->rep_pcifunc); + + mutex_lock(&rvu->mbox_lock); + req = otx2_mbox_alloc_msg_rep_event_up_notify(rvu, pf); + if (!req) { + mutex_unlock(&rvu->mbox_lock); + return -ENOMEM; + } + + req->hdr.pcifunc = rvu->rep_pcifunc; + req->event |= RVU_EVENT_PFVF_STATE; + req->pcifunc = pcifunc; + req->evt_data.vf_state = enable; + + otx2_mbox_wait_for_zero(&rvu->afpf_wq_info.mbox_up, pf); + otx2_mbox_msg_send_up(&rvu->afpf_wq_info.mbox_up, pf); + + mutex_unlock(&rvu->mbox_lock); + return 0; +} + +#define RVU_LF_RX_STATS(reg) \ + rvu_read64(rvu, blkaddr, NIX_AF_LFX_RX_STATX(nixlf, reg)) + +#define RVU_LF_TX_STATS(reg) \ + rvu_read64(rvu, blkaddr, NIX_AF_LFX_TX_STATX(nixlf, reg)) + +int rvu_mbox_handler_nix_lf_stats(struct rvu *rvu, + struct nix_stats_req *req, + struct nix_stats_rsp *rsp) +{ + u16 pcifunc = req->pcifunc; + int nixlf, blkaddr, err; + struct msg_req rst_req; + struct msg_rsp rst_rsp; + + err = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr); + if (err) + return 0; + + if (req->reset) { + rst_req.hdr.pcifunc = pcifunc; + return rvu_mbox_handler_nix_stats_rst(rvu, &rst_req, &rst_rsp); + } + rsp->rx.octs = RVU_LF_RX_STATS(RX_OCTS); + rsp->rx.ucast = RVU_LF_RX_STATS(RX_UCAST); + rsp->rx.bcast = RVU_LF_RX_STATS(RX_BCAST); + rsp->rx.mcast = RVU_LF_RX_STATS(RX_MCAST); + rsp->rx.drop = RVU_LF_RX_STATS(RX_DROP); + rsp->rx.err = RVU_LF_RX_STATS(RX_ERR); + rsp->rx.drop_octs = RVU_LF_RX_STATS(RX_DROP_OCTS); + rsp->rx.drop_mcast = RVU_LF_RX_STATS(RX_DRP_MCAST); + rsp->rx.drop_bcast = RVU_LF_RX_STATS(RX_DRP_BCAST); + + rsp->tx.octs = RVU_LF_TX_STATS(TX_OCTS); + rsp->tx.ucast = RVU_LF_TX_STATS(TX_UCAST); + rsp->tx.bcast = RVU_LF_TX_STATS(TX_BCAST); + rsp->tx.mcast = RVU_LF_TX_STATS(TX_MCAST); + rsp->tx.drop = RVU_LF_TX_STATS(TX_DROP); + + rsp->pcifunc = req->pcifunc; + return 0; +} + +static u16 rvu_rep_get_vlan_id(struct rvu *rvu, u16 pcifunc) +{ + int id; + + for (id = 0; id < rvu->rep_cnt; id++) + if (rvu->rep2pfvf_map[id] == pcifunc) + return id; + return 0; +} + +static int rvu_rep_tx_vlan_cfg(struct rvu *rvu, u16 pcifunc, + u16 vlan_tci, int *vidx) +{ + struct nix_vtag_config_rsp rsp = {}; + struct nix_vtag_config req = {}; + u64 etype = ETH_P_8021Q; + int err; + + /* Insert vlan tag */ + req.hdr.pcifunc = pcifunc; + req.vtag_size = VTAGSIZE_T4; + req.cfg_type = 0; /* tx vlan cfg */ + req.tx.cfg_vtag0 = true; + req.tx.vtag0 = FIELD_PREP(NIX_VLAN_ETYPE_MASK, etype) | vlan_tci; + + err = rvu_mbox_handler_nix_vtag_cfg(rvu, &req, &rsp); + if (err) { + dev_err(rvu->dev, "Tx vlan config failed\n"); + return err; + } + *vidx = rsp.vtag0_idx; + return 0; +} + +static int rvu_rep_rx_vlan_cfg(struct rvu *rvu, u16 pcifunc) +{ + struct nix_vtag_config req = {}; + struct nix_vtag_config_rsp rsp; + + /* config strip, capture and size */ + req.hdr.pcifunc = pcifunc; + req.vtag_size = VTAGSIZE_T4; + req.cfg_type = 1; /* rx vlan cfg */ + req.rx.vtag_type = NIX_AF_LFX_RX_VTAG_TYPE0; + req.rx.strip_vtag = true; + req.rx.capture_vtag = false; + + return rvu_mbox_handler_nix_vtag_cfg(rvu, &req, &rsp); +} + +static int rvu_rep_install_rx_rule(struct rvu *rvu, u16 pcifunc, + u16 entry, bool rte) +{ + struct npc_install_flow_req req = {}; + struct npc_install_flow_rsp rsp = {}; + struct rvu_pfvf *pfvf; + u16 vlan_tci, rep_id; + + pfvf = rvu_get_pfvf(rvu, pcifunc); + + /* To steer the traffic from Representee to Representor */ + rep_id = rvu_rep_get_vlan_id(rvu, pcifunc); + if (rte) { + vlan_tci = rep_id | BIT_ULL(8); + req.vf = rvu->rep_pcifunc; + req.op = NIX_RX_ACTIONOP_UCAST; + req.index = rep_id; + } else { + vlan_tci = rep_id; + req.vf = pcifunc; + req.op = NIX_RX_ACTION_DEFAULT; + } + + rvu_rep_rx_vlan_cfg(rvu, req.vf); + req.entry = entry; + req.hdr.pcifunc = 0; /* AF is requester */ + req.features = BIT_ULL(NPC_OUTER_VID) | BIT_ULL(NPC_VLAN_ETYPE_CTAG); + req.vtag0_valid = true; + req.vtag0_type = NIX_AF_LFX_RX_VTAG_TYPE0; + req.packet.vlan_etype = cpu_to_be16(ETH_P_8021Q); + req.mask.vlan_etype = cpu_to_be16(ETH_P_8021Q); + req.packet.vlan_tci = cpu_to_be16(vlan_tci); + req.mask.vlan_tci = cpu_to_be16(0xffff); + + req.channel = RVU_SWITCH_LBK_CHAN; + req.chan_mask = 0xffff; + req.intf = pfvf->nix_rx_intf; + + return rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); +} + +static int rvu_rep_install_tx_rule(struct rvu *rvu, u16 pcifunc, u16 entry, + bool rte) +{ + struct npc_install_flow_req req = {}; + struct npc_install_flow_rsp rsp = {}; + struct rvu_pfvf *pfvf; + int vidx, err; + u16 vlan_tci; + u8 lbkid; + + pfvf = rvu_get_pfvf(rvu, pcifunc); + vlan_tci = rvu_rep_get_vlan_id(rvu, pcifunc); + if (rte) + vlan_tci |= BIT_ULL(8); + + err = rvu_rep_tx_vlan_cfg(rvu, pcifunc, vlan_tci, &vidx); + if (err) + return err; + + lbkid = pfvf->nix_blkaddr == BLKADDR_NIX0 ? 0 : 1; + req.hdr.pcifunc = 0; /* AF is requester */ + if (rte) { + req.vf = pcifunc; + } else { + req.vf = rvu->rep_pcifunc; + req.packet.sq_id = vlan_tci; + req.mask.sq_id = 0xffff; + } + + req.entry = entry; + req.intf = pfvf->nix_tx_intf; + req.op = NIX_TX_ACTIONOP_UCAST_CHAN; + req.index = (lbkid << 8) | RVU_SWITCH_LBK_CHAN; + req.set_cntr = 1; + req.vtag0_def = vidx; + req.vtag0_op = 1; + return rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); +} + +int rvu_rep_install_mcam_rules(struct rvu *rvu) +{ + struct rvu_switch *rswitch = &rvu->rswitch; + u16 start = rswitch->start_entry; + struct rvu_hwinfo *hw = rvu->hw; + u16 pcifunc, entry = 0; + int pf, vf, numvfs; + int err, nixlf, i; + u8 rep; + + for (pf = 1; pf < hw->total_pfs; pf++) { + if (!is_pf_cgxmapped(rvu, pf)) + continue; + + pcifunc = pf << RVU_PFVF_PF_SHIFT; + rvu_get_nix_blkaddr(rvu, pcifunc); + rep = true; + for (i = 0; i < 2; i++) { + err = rvu_rep_install_rx_rule(rvu, pcifunc, + start + entry, rep); + if (err) + return err; + rswitch->entry2pcifunc[entry++] = pcifunc; + + err = rvu_rep_install_tx_rule(rvu, pcifunc, + start + entry, rep); + if (err) + return err; + rswitch->entry2pcifunc[entry++] = pcifunc; + rep = false; + } + + rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL); + for (vf = 0; vf < numvfs; vf++) { + pcifunc = pf << RVU_PFVF_PF_SHIFT | + ((vf + 1) & RVU_PFVF_FUNC_MASK); + rvu_get_nix_blkaddr(rvu, pcifunc); + + /* Skip installimg rules if nixlf is not attached */ + err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL); + if (err) + continue; + rep = true; + for (i = 0; i < 2; i++) { + err = rvu_rep_install_rx_rule(rvu, pcifunc, + start + entry, + rep); + if (err) + return err; + rswitch->entry2pcifunc[entry++] = pcifunc; + + err = rvu_rep_install_tx_rule(rvu, pcifunc, + start + entry, + rep); + if (err) + return err; + rswitch->entry2pcifunc[entry++] = pcifunc; + rep = false; + } + } + } + + /* Initialize the wq for handling REP events */ + spin_lock_init(&rvu->rep_evtq_lock); + INIT_LIST_HEAD(&rvu->rep_evtq_head); + INIT_WORK(&rvu->rep_evt_work, rvu_rep_wq_handler); + rvu->rep_evt_wq = alloc_workqueue("rep_evt_wq", 0, 0); + if (!rvu->rep_evt_wq) { + dev_err(rvu->dev, "REP workqueue allocation failed\n"); + return -ENOMEM; + } + return 0; +} + +void rvu_rep_update_rules(struct rvu *rvu, u16 pcifunc, bool ena) +{ + struct rvu_switch *rswitch = &rvu->rswitch; + struct npc_mcam *mcam = &rvu->hw->mcam; + u32 max = rswitch->used_entries; + int blkaddr; + u16 entry; + + if (!rswitch->used_entries) + return; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + + if (blkaddr < 0) + return; + + rvu_switch_enable_lbk_link(rvu, pcifunc, ena); + mutex_lock(&mcam->lock); + for (entry = 0; entry < max; entry++) { + if (rswitch->entry2pcifunc[entry] == pcifunc) + npc_enable_mcam_entry(rvu, mcam, blkaddr, entry, ena); + } + mutex_unlock(&mcam->lock); +} + +int rvu_rep_pf_init(struct rvu *rvu) +{ + u16 pcifunc = rvu->rep_pcifunc; + struct rvu_pfvf *pfvf; + + pfvf = rvu_get_pfvf(rvu, pcifunc); + set_bit(NIXLF_INITIALIZED, &pfvf->flags); + rvu_switch_enable_lbk_link(rvu, pcifunc, true); + rvu_rep_rx_vlan_cfg(rvu, pcifunc); + return 0; +} + +int rvu_mbox_handler_esw_cfg(struct rvu *rvu, struct esw_cfg_req *req, + struct msg_rsp *rsp) +{ + if (req->hdr.pcifunc != rvu->rep_pcifunc) + return 0; + + rvu->rep_mode = req->ena; + + if (!rvu->rep_mode) + rvu_npc_free_mcam_entries(rvu, req->hdr.pcifunc, -1); + + return 0; +} + +int rvu_mbox_handler_get_rep_cnt(struct rvu *rvu, struct msg_req *req, + struct get_rep_cnt_rsp *rsp) +{ + int pf, vf, numvfs, hwvf, rep = 0; + u16 pcifunc; + + rvu->rep_pcifunc = req->hdr.pcifunc; + rsp->rep_cnt = rvu->cgx_mapped_pfs + rvu->cgx_mapped_vfs; + rvu->rep_cnt = rsp->rep_cnt; + + rvu->rep2pfvf_map = devm_kzalloc(rvu->dev, rvu->rep_cnt * + sizeof(u16), GFP_KERNEL); + if (!rvu->rep2pfvf_map) + return -ENOMEM; + + for (pf = 0; pf < rvu->hw->total_pfs; pf++) { + if (!is_pf_cgxmapped(rvu, pf)) + continue; + pcifunc = pf << RVU_PFVF_PF_SHIFT; + rvu->rep2pfvf_map[rep] = pcifunc; + rsp->rep_pf_map[rep] = pcifunc; + rep++; + rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvf); + for (vf = 0; vf < numvfs; vf++) { + rvu->rep2pfvf_map[rep] = pcifunc | + ((vf + 1) & RVU_PFVF_FUNC_MASK); + rsp->rep_pf_map[rep] = rvu->rep2pfvf_map[rep]; + rep++; + } + } + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h index fc8da2090657..77ac94cb2ec4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h @@ -823,4 +823,30 @@ enum nix_tx_vtag_op { #define VTAG_STRIP BIT_ULL(4) #define VTAG_CAPTURE BIT_ULL(5) +/* NIX TX stats */ +enum nix_stat_lf_tx { + TX_UCAST = 0x0, + TX_BCAST = 0x1, + TX_MCAST = 0x2, + TX_DROP = 0x3, + TX_OCTS = 0x4, + TX_STATS_ENUM_LAST, +}; + +/* NIX RX stats */ +enum nix_stat_lf_rx { + RX_OCTS = 0x0, + RX_UCAST = 0x1, + RX_BCAST = 0x2, + RX_MCAST = 0x3, + RX_DROP = 0x4, + RX_DROP_OCTS = 0x5, + RX_FCS = 0x6, + RX_ERR = 0x7, + RX_DRP_BCAST = 0x8, + RX_DRP_MCAST = 0x9, + RX_DRP_L3BCAST = 0xa, + RX_DRP_L3MCAST = 0xb, + RX_STATS_ENUM_LAST, +}; #endif /* RVU_STRUCT_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c index 854045ed3b06..268efb7c1c15 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c @@ -8,7 +8,7 @@ #include <linux/bitfield.h> #include "rvu.h" -static void rvu_switch_enable_lbk_link(struct rvu *rvu, u16 pcifunc, bool enable) +void rvu_switch_enable_lbk_link(struct rvu *rvu, u16 pcifunc, bool enable) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); struct nix_hw *nix_hw; @@ -166,6 +166,8 @@ void rvu_switch_enable(struct rvu *rvu) alloc_req.contig = true; alloc_req.count = rvu->cgx_mapped_pfs + rvu->cgx_mapped_vfs; + if (rvu->rep_mode) + alloc_req.count = alloc_req.count * 4; ret = rvu_mbox_handler_npc_mcam_alloc_entry(rvu, &alloc_req, &alloc_rsp); if (ret) { @@ -189,7 +191,12 @@ void rvu_switch_enable(struct rvu *rvu) rswitch->used_entries = alloc_rsp.count; rswitch->start_entry = alloc_rsp.entry; - ret = rvu_switch_install_rules(rvu); + if (rvu->rep_mode) { + rvu_rep_pf_init(rvu); + ret = rvu_rep_install_mcam_rules(rvu); + } else { + ret = rvu_switch_install_rules(rvu); + } if (ret) goto uninstall_rules; @@ -222,6 +229,9 @@ void rvu_switch_disable(struct rvu *rvu) if (!rswitch->used_entries) return; + if (rvu->rep_mode) + goto free_ents; + for (pf = 1; pf < hw->total_pfs; pf++) { if (!is_pf_cgxmapped(rvu, pf)) continue; @@ -249,6 +259,7 @@ void rvu_switch_disable(struct rvu *rvu) } } +free_ents: uninstall_req.start = rswitch->start_entry; uninstall_req.end = rswitch->start_entry + rswitch->used_entries - 1; free_req.all = 1; @@ -258,12 +269,15 @@ void rvu_switch_disable(struct rvu *rvu) kfree(rswitch->entry2pcifunc); } -void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc) +void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc, bool ena) { struct rvu_switch *rswitch = &rvu->rswitch; u32 max = rswitch->used_entries; u16 entry; + if (rvu->rep_mode) + return rvu_rep_update_rules(rvu, pcifunc, ena); + if (!rswitch->used_entries) return; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 64a97a0a10ed..dbc971266865 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -5,11 +5,13 @@ obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o otx2_ptp.o obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o +obj-$(CONFIG_RVU_ESWITCH) += rvu_rep.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ otx2_devlink.o qos_sq.o qos.o rvu_nicvf-y := otx2_vf.o +rvu_rep-y := rep.o rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o rvu_nicpf-$(CONFIG_MACSEC) += cn10k_macsec.o diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index 7417087b6db5..a15cc86635d6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -72,7 +72,7 @@ int cn10k_lmtst_init(struct otx2_nic *pfvf) } EXPORT_SYMBOL(cn10k_lmtst_init); -int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) +int cn10k_sq_aq_init(void *dev, u16 qidx, u8 chan_offset, u16 sqb_aura) { struct nix_cn10k_aq_enq_req *aq; struct otx2_nic *pfvf = dev; @@ -88,7 +88,7 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) aq->sq.ena = 1; aq->sq.smq = otx2_get_smq_idx(pfvf, qidx); aq->sq.smq_rr_weight = mtu_to_dwrr_weight(pfvf, pfvf->tx_max_pktlen); - aq->sq.default_chan = pfvf->hw.tx_chan_base; + aq->sq.default_chan = pfvf->hw.tx_chan_base + chan_offset; aq->sq.sqe_stype = NIX_STYPE_STF; /* Cache SQB */ aq->sq.sqb_aura = sqb_aura; aq->sq.sq_int_ena = NIX_SQINT_BITS; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h index c1861f7de254..e3f0bce9908f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h @@ -26,7 +26,7 @@ static inline int mtu_to_dwrr_weight(struct otx2_nic *pfvf, int mtu) int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq); void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx); -int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura); +int cn10k_sq_aq_init(void *dev, u16 qidx, u8 chan_offset, u16 sqb_aura); int cn10k_lmtst_init(struct otx2_nic *pfvf); int cn10k_free_all_ipolicers(struct otx2_nic *pfvf); int cn10k_alloc_matchall_ipolicer(struct otx2_nic *pfvf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 7510a918d942..523ecb798a7a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -83,6 +83,7 @@ int otx2_update_rq_stats(struct otx2_nic *pfvf, int qidx) otx2_nix_rq_op_stats(&rq->stats, pfvf, qidx); return 1; } +EXPORT_SYMBOL(otx2_update_rq_stats); int otx2_update_sq_stats(struct otx2_nic *pfvf, int qidx) { @@ -99,6 +100,7 @@ int otx2_update_sq_stats(struct otx2_nic *pfvf, int qidx) otx2_nix_sq_op_stats(&sq->stats, pfvf, qidx); return 1; } +EXPORT_SYMBOL(otx2_update_sq_stats); void otx2_get_dev_stats(struct otx2_nic *pfvf) { @@ -227,7 +229,7 @@ int otx2_hw_set_mtu(struct otx2_nic *pfvf, int mtu) u16 maxlen; int err; - maxlen = otx2_get_max_mtu(pfvf) + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; + maxlen = pfvf->hw.max_mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; mutex_lock(&pfvf->mbox.lock); req = otx2_mbox_alloc_msg_nix_set_hw_frs(&pfvf->mbox); @@ -236,7 +238,7 @@ int otx2_hw_set_mtu(struct otx2_nic *pfvf, int mtu) return -ENOMEM; } - req->maxlen = pfvf->netdev->mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; + req->maxlen = mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; /* Use max receive length supported by hardware for loopback devices */ if (is_otx2_lbkvf(pfvf->pdev)) @@ -246,13 +248,14 @@ int otx2_hw_set_mtu(struct otx2_nic *pfvf, int mtu) mutex_unlock(&pfvf->mbox.lock); return err; } +EXPORT_SYMBOL(otx2_hw_set_mtu); int otx2_config_pause_frm(struct otx2_nic *pfvf) { struct cgx_pause_frm_cfg *req; int err; - if (is_otx2_lbkvf(pfvf->pdev)) + if (is_otx2_lbkvf(pfvf->pdev) || is_otx2_sdp_rep(pfvf->pdev)) return 0; mutex_lock(&pfvf->mbox.lock); @@ -646,12 +649,22 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool txschq_for req->reg[2] = NIX_AF_MDQX_SCHEDULE(schq); req->regval[2] = dwrr_val; } else if (lvl == NIX_TXSCH_LVL_TL4) { + int sdp_chan = hw->tx_chan_base + prio; + + if (is_otx2_sdp_rep(pfvf->pdev)) + prio = 0; parent = schq_list[NIX_TXSCH_LVL_TL3][prio]; req->reg[0] = NIX_AF_TL4X_PARENT(schq); req->regval[0] = (u64)parent << 16; req->num_regs++; req->reg[1] = NIX_AF_TL4X_SCHEDULE(schq); req->regval[1] = dwrr_val; + if (is_otx2_sdp_rep(pfvf->pdev)) { + req->num_regs++; + req->reg[2] = NIX_AF_TL4X_SDP_LINK_CFG(schq); + req->regval[2] = BIT_ULL(12) | BIT_ULL(13) | + (sdp_chan & 0xff); + } } else if (lvl == NIX_TXSCH_LVL_TL3) { parent = schq_list[NIX_TXSCH_LVL_TL2][prio]; req->reg[0] = NIX_AF_TL3X_PARENT(schq); @@ -659,7 +672,8 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool txschq_for req->num_regs++; req->reg[1] = NIX_AF_TL3X_SCHEDULE(schq); req->regval[1] = dwrr_val; - if (lvl == hw->txschq_link_cfg_lvl) { + if (lvl == hw->txschq_link_cfg_lvl && + !is_otx2_sdp_rep(pfvf->pdev)) { req->num_regs++; req->reg[2] = NIX_AF_TL3_TL2X_LINKX_CFG(schq, hw->tx_link); /* Enable this queue and backpressure @@ -676,7 +690,8 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool txschq_for req->reg[1] = NIX_AF_TL2X_SCHEDULE(schq); req->regval[1] = (u64)hw->txschq_aggr_lvl_rr_prio << 24 | dwrr_val; - if (lvl == hw->txschq_link_cfg_lvl) { + if (lvl == hw->txschq_link_cfg_lvl && + !is_otx2_sdp_rep(pfvf->pdev)) { req->num_regs++; req->reg[2] = NIX_AF_TL3_TL2X_LINKX_CFG(schq, hw->tx_link); /* Enable this queue and backpressure @@ -735,6 +750,7 @@ EXPORT_SYMBOL(otx2_smq_flush); int otx2_txsch_alloc(struct otx2_nic *pfvf) { + int chan_cnt = pfvf->hw.tx_chan_cnt; struct nix_txsch_alloc_req *req; struct nix_txsch_alloc_rsp *rsp; int lvl, schq, rc; @@ -747,6 +763,12 @@ int otx2_txsch_alloc(struct otx2_nic *pfvf) /* Request one schq per level */ for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) req->schq[lvl] = 1; + + if (is_otx2_sdp_rep(pfvf->pdev) && chan_cnt > 1) { + req->schq[NIX_TXSCH_LVL_SMQ] = chan_cnt; + req->schq[NIX_TXSCH_LVL_TL4] = chan_cnt; + } + rc = otx2_sync_mbox_msg(&pfvf->mbox); if (rc) return rc; @@ -757,10 +779,12 @@ int otx2_txsch_alloc(struct otx2_nic *pfvf) return PTR_ERR(rsp); /* Setup transmit scheduler list */ - for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) + for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { + pfvf->hw.txschq_cnt[lvl] = rsp->schq[lvl]; for (schq = 0; schq < rsp->schq[lvl]; schq++) pfvf->hw.txschq_list[lvl][schq] = rsp->schq_list[lvl][schq]; + } pfvf->hw.txschq_link_cfg_lvl = rsp->link_cfg_lvl; pfvf->hw.txschq_aggr_lvl_rr_prio = rsp->aggr_lvl_rr_prio; @@ -798,12 +822,15 @@ EXPORT_SYMBOL(otx2_txschq_free_one); void otx2_txschq_stop(struct otx2_nic *pfvf) { - int lvl, schq; + int lvl, schq, idx; /* free non QOS TLx nodes */ - for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) - otx2_txschq_free_one(pfvf, lvl, - pfvf->hw.txschq_list[lvl][0]); + for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { + for (idx = 0; idx < pfvf->hw.txschq_cnt[lvl]; idx++) { + otx2_txschq_free_one(pfvf, lvl, + pfvf->hw.txschq_list[lvl][idx]); + } + } /* Clear the txschq list */ for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { @@ -883,7 +910,7 @@ static int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura) return otx2_sync_mbox_msg(&pfvf->mbox); } -int otx2_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) +int otx2_sq_aq_init(void *dev, u16 qidx, u8 chan_offset, u16 sqb_aura) { struct otx2_nic *pfvf = dev; struct otx2_snd_queue *sq; @@ -902,7 +929,7 @@ int otx2_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) aq->sq.ena = 1; aq->sq.smq = otx2_get_smq_idx(pfvf, qidx); aq->sq.smq_rr_quantum = mtu_to_dwrr_weight(pfvf, pfvf->tx_max_pktlen); - aq->sq.default_chan = pfvf->hw.tx_chan_base; + aq->sq.default_chan = pfvf->hw.tx_chan_base + chan_offset; aq->sq.sqe_stype = NIX_STYPE_STF; /* Cache SQB */ aq->sq.sqb_aura = sqb_aura; aq->sq.sq_int_ena = NIX_SQINT_BITS; @@ -925,6 +952,7 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) struct otx2_qset *qset = &pfvf->qset; struct otx2_snd_queue *sq; struct otx2_pool *pool; + u8 chan_offset; int err; pool = &pfvf->qset.pool[sqb_aura]; @@ -971,7 +999,8 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) sq->stats.bytes = 0; sq->stats.pkts = 0; - err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, sqb_aura); + chan_offset = qidx % pfvf->hw.tx_chan_cnt; + err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, chan_offset, sqb_aura); if (err) { kfree(sq->sg); sq->sg = NULL; @@ -1738,6 +1767,8 @@ void mbox_handler_nix_lf_alloc(struct otx2_nic *pfvf, pfvf->hw.sqb_size = rsp->sqb_size; pfvf->hw.rx_chan_base = rsp->rx_chan_base; pfvf->hw.tx_chan_base = rsp->tx_chan_base; + pfvf->hw.rx_chan_cnt = rsp->rx_chan_cnt; + pfvf->hw.tx_chan_cnt = rsp->tx_chan_cnt; pfvf->hw.lso_tsov4_idx = rsp->lso_tsov4_idx; pfvf->hw.lso_tsov6_idx = rsp->lso_tsov6_idx; pfvf->hw.cgx_links = rsp->cgx_links; @@ -1782,6 +1813,7 @@ void otx2_free_cints(struct otx2_nic *pfvf, int n) free_irq(vector, &qset->napi[qidx]); } } +EXPORT_SYMBOL(otx2_free_cints); void otx2_set_cints_affinity(struct otx2_nic *pfvf) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index f27a3456ae64..566848663fea 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -29,6 +29,7 @@ #include "otx2_devlink.h" #include <rvu_trace.h> #include "qos.h" +#include "rep.h" /* IPv4 flag more fragment bit */ #define IPV4_FLAG_MORE 0x20 @@ -41,6 +42,8 @@ #define PCI_SUBSYS_DEVID_96XX_RVU_PFVF 0xB200 #define PCI_SUBSYS_DEVID_CN10K_B_RVU_PFVF 0xBD00 +#define PCI_DEVID_OCTEONTX2_SDP_REP 0xA0F7 + /* PCI BAR nos */ #define PCI_CFG_REG_BAR_NUM 2 #define PCI_MBOX_BAR_NUM 4 @@ -120,33 +123,6 @@ enum otx2_errcodes_re { ERRCODE_IL4_CSUM = 0x22, }; -/* NIX TX stats */ -enum nix_stat_lf_tx { - TX_UCAST = 0x0, - TX_BCAST = 0x1, - TX_MCAST = 0x2, - TX_DROP = 0x3, - TX_OCTS = 0x4, - TX_STATS_ENUM_LAST, -}; - -/* NIX RX stats */ -enum nix_stat_lf_rx { - RX_OCTS = 0x0, - RX_UCAST = 0x1, - RX_BCAST = 0x2, - RX_MCAST = 0x3, - RX_DROP = 0x4, - RX_DROP_OCTS = 0x5, - RX_FCS = 0x6, - RX_ERR = 0x7, - RX_DRP_BCAST = 0x8, - RX_DRP_MCAST = 0x9, - RX_DRP_L3BCAST = 0xa, - RX_DRP_L3MCAST = 0xb, - RX_STATS_ENUM_LAST, -}; - struct otx2_dev_stats { u64 rx_bytes; u64 rx_frames; @@ -224,15 +200,19 @@ struct otx2_hw { /* NIX */ u8 txschq_link_cfg_lvl; + u8 txschq_cnt[NIX_TXSCH_LVL_CNT]; u8 txschq_aggr_lvl_rr_prio; u16 txschq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC]; u16 matchall_ipolicer; u32 dwrr_mtu; + u32 max_mtu; u8 smq_link_type; /* HW settings, coalescing etc */ u16 rx_chan_base; u16 tx_chan_base; + u8 rx_chan_cnt; + u8 tx_chan_cnt; u16 cq_qcount_wait; u16 cq_ecount_wait; u16 rq_skid; @@ -367,7 +347,8 @@ struct otx2_flow_config { }; struct dev_hw_ops { - int (*sq_aq_init)(void *dev, u16 qidx, u16 sqb_aura); + int (*sq_aq_init)(void *dev, u16 qidx, u8 chan_offset, + u16 sqb_aura); void (*sqe_flush)(void *dev, struct otx2_snd_queue *sq, int size, int qidx); int (*refill_pool_ptrs)(void *dev, struct otx2_cq_queue *cq); @@ -465,6 +446,8 @@ struct otx2_nic { #define OTX2_FLAG_PTP_ONESTEP_SYNC BIT_ULL(15) #define OTX2_FLAG_ADPTV_INT_COAL_ENABLED BIT_ULL(16) #define OTX2_FLAG_TC_MARK_ENABLED BIT_ULL(17) +#define OTX2_FLAG_REP_MODE_ENABLED BIT_ULL(18) +#define OTX2_FLAG_PORT_UP BIT_ULL(19) u64 flags; u64 *cq_op_addr; @@ -532,11 +515,19 @@ struct otx2_nic { #if IS_ENABLED(CONFIG_MACSEC) struct cn10k_mcs_cfg *macsec_cfg; #endif + +#if IS_ENABLED(CONFIG_RVU_ESWITCH) + struct rep_dev **reps; + int rep_cnt; + u16 rep_pf_map[RVU_MAX_REP]; + u16 esw_mode; +#endif }; static inline bool is_otx2_lbkvf(struct pci_dev *pdev) { - return pdev->device == PCI_DEVID_OCTEONTX2_RVU_AFVF; + return (pdev->device == PCI_DEVID_OCTEONTX2_RVU_AFVF) || + (pdev->device == PCI_DEVID_RVU_REP); } static inline bool is_96xx_A0(struct pci_dev *pdev) @@ -551,6 +542,11 @@ static inline bool is_96xx_B0(struct pci_dev *pdev) (pdev->subsystem_device == PCI_SUBSYS_DEVID_96XX_RVU_PFVF); } +static inline bool is_otx2_sdp_rep(struct pci_dev *pdev) +{ + return pdev->device == PCI_DEVID_OCTEONTX2_SDP_REP; +} + /* REVID for PCIe devices. * Bits 0..1: minor pass, bit 3..2: major pass * bits 7..4: midr id @@ -913,15 +909,19 @@ static inline void otx2_dma_unmap_page(struct otx2_nic *pfvf, static inline u16 otx2_get_smq_idx(struct otx2_nic *pfvf, u16 qidx) { u16 smq; + int idx; + #ifdef CONFIG_DCB if (qidx < NIX_PF_PFC_PRIO_MAX && pfvf->pfc_alloc_status[qidx]) return pfvf->pfc_schq_list[NIX_TXSCH_LVL_SMQ][qidx]; #endif /* check if qidx falls under QOS queues */ - if (qidx >= pfvf->hw.non_qos_queues) + if (qidx >= pfvf->hw.non_qos_queues) { smq = pfvf->qos.qid_to_sqmap[qidx - pfvf->hw.non_qos_queues]; - else - smq = pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][0]; + } else { + idx = qidx % pfvf->hw.txschq_cnt[NIX_TXSCH_LVL_SMQ]; + smq = pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][idx]; + } return smq; } @@ -988,14 +988,28 @@ int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable); void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int qidx); void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq); int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura); -int otx2_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura); -int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura); +int otx2_sq_aq_init(void *dev, u16 qidx, u8 chan_offset, u16 sqb_aura); +int cn10k_sq_aq_init(void *dev, u16 qidx, u8 chan_offset, u16 sqb_aura); int otx2_alloc_buffer(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, dma_addr_t *dma); int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, int stack_pages, int numptrs, int buf_size, int type); int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, int pool_id, int numptrs); +int otx2_init_rsrc(struct pci_dev *pdev, struct otx2_nic *pf); +void otx2_free_queue_mem(struct otx2_qset *qset); +int otx2_alloc_queue_mem(struct otx2_nic *pf); +int otx2_init_hw_resources(struct otx2_nic *pfvf); +void otx2_free_hw_resources(struct otx2_nic *pf); +int otx2_wq_init(struct otx2_nic *pf); +int otx2_check_pf_usable(struct otx2_nic *pf); +int otx2_pfaf_mbox_init(struct otx2_nic *pf); +int otx2_register_mbox_intr(struct otx2_nic *pf, bool probe_af); +int otx2_realloc_msix_vectors(struct otx2_nic *pf); +void otx2_pfaf_mbox_destroy(struct otx2_nic *pf); +void otx2_disable_mbox_intr(struct otx2_nic *pf); +void otx2_disable_napi(struct otx2_nic *pf); +irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq); /* RSS configuration APIs*/ int otx2_rss_init(struct otx2_nic *pfvf); @@ -1127,4 +1141,12 @@ u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb, int otx2_get_txq_by_classid(struct otx2_nic *pfvf, u16 classid); void otx2_qos_config_txschq(struct otx2_nic *pfvf); void otx2_clean_qos_queues(struct otx2_nic *pfvf); +int rvu_event_up_notify(struct otx2_nic *pf, struct rep_event *info); +int otx2_setup_tc_cls_flower(struct otx2_nic *nic, + struct flow_cls_offload *cls_flower); + +static inline int mcam_entry_cmp(const void *a, const void *b) +{ + return *(u16 *)a - *(u16 *)b; +} #endif /* OTX2_COMMON_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c index 53f14aa944bd..33ec9a7f7c03 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c @@ -141,7 +141,56 @@ static const struct devlink_param otx2_dl_params[] = { otx2_dl_ucast_flt_cnt_validate), }; +#ifdef CONFIG_RVU_ESWITCH +static int otx2_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) +{ + struct otx2_devlink *otx2_dl = devlink_priv(devlink); + struct otx2_nic *pfvf = otx2_dl->pfvf; + + if (!otx2_rep_dev(pfvf->pdev)) + return -EOPNOTSUPP; + + *mode = pfvf->esw_mode; + + return 0; +} + +static int otx2_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) +{ + struct otx2_devlink *otx2_dl = devlink_priv(devlink); + struct otx2_nic *pfvf = otx2_dl->pfvf; + int ret = 0; + + if (!otx2_rep_dev(pfvf->pdev)) + return -EOPNOTSUPP; + + if (pfvf->esw_mode == mode) + return 0; + + switch (mode) { + case DEVLINK_ESWITCH_MODE_LEGACY: + rvu_rep_destroy(pfvf); + break; + case DEVLINK_ESWITCH_MODE_SWITCHDEV: + ret = rvu_rep_create(pfvf, extack); + break; + default: + return -EINVAL; + } + + if (!ret) + pfvf->esw_mode = mode; + + return ret; +} +#endif + static const struct devlink_ops otx2_devlink_ops = { +#ifdef CONFIG_RVU_ESWITCH + .eswitch_mode_get = otx2_devlink_eswitch_mode_get, + .eswitch_mode_set = otx2_devlink_eswitch_mode_set, +#endif }; int otx2_register_dl(struct otx2_nic *pfvf) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 58720a161ee2..47bfd1fb37d4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -64,11 +64,6 @@ static int otx2_free_ntuple_mcam_entries(struct otx2_nic *pfvf) return 0; } -static int mcam_entry_cmp(const void *a, const void *b) -{ - return *(u16 *)a - *(u16 *)b; -} - int otx2_alloc_mcam_entries(struct otx2_nic *pfvf, u16 count) { struct otx2_flow_config *flow_cfg = pfvf->flow_cfg; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 5492dea547a1..e310f99b1736 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -519,6 +519,7 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work) switch (msg->id) { case MBOX_MSG_CGX_LINK_EVENT: + case MBOX_MSG_REP_EVENT_UP_NOTIFY: break; default: if (msg->rc) @@ -832,6 +833,9 @@ static void otx2_handle_link_event(struct otx2_nic *pf) struct cgx_link_user_info *linfo = &pf->linfo; struct net_device *netdev = pf->netdev; + if (pf->flags & OTX2_FLAG_PORT_UP) + return; + pr_info("%s NIC Link is %s %d Mbps %s duplex\n", netdev->name, linfo->link_up ? "UP" : "DOWN", linfo->speed, linfo->full_duplex ? "Full" : "Half"); @@ -844,6 +848,35 @@ static void otx2_handle_link_event(struct otx2_nic *pf) } } +static int otx2_mbox_up_handler_rep_event_up_notify(struct otx2_nic *pf, + struct rep_event *info, + struct msg_rsp *rsp) +{ + struct net_device *netdev = pf->netdev; + + if (info->event == RVU_EVENT_MTU_CHANGE) { + netdev->mtu = info->evt_data.mtu; + return 0; + } + + if (info->event == RVU_EVENT_PORT_STATE) { + if (info->evt_data.port_state) { + pf->flags |= OTX2_FLAG_PORT_UP; + netif_carrier_on(netdev); + netif_tx_start_all_queues(netdev); + } else { + pf->flags &= ~OTX2_FLAG_PORT_UP; + netif_tx_stop_all_queues(netdev); + netif_carrier_off(netdev); + } + return 0; + } +#ifdef CONFIG_RVU_ESWITCH + rvu_event_up_notify(pf, info); +#endif + return 0; +} + int otx2_mbox_up_handler_mcs_intr_notify(struct otx2_nic *pf, struct mcs_intr_info *event, struct msg_rsp *rsp) @@ -913,6 +946,7 @@ static int otx2_process_mbox_msg_up(struct otx2_nic *pf, } MBOX_UP_CGX_MESSAGES MBOX_UP_MCS_MESSAGES +MBOX_UP_REP_MESSAGES #undef M break; default: @@ -1008,7 +1042,7 @@ static irqreturn_t otx2_pfaf_mbox_intr_handler(int irq, void *pf_irq) return IRQ_HANDLED; } -static void otx2_disable_mbox_intr(struct otx2_nic *pf) +void otx2_disable_mbox_intr(struct otx2_nic *pf) { int vector = pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_AFPF_MBOX); @@ -1016,8 +1050,9 @@ static void otx2_disable_mbox_intr(struct otx2_nic *pf) otx2_write64(pf, RVU_PF_INT_ENA_W1C, BIT_ULL(0)); free_irq(vector, pf); } +EXPORT_SYMBOL(otx2_disable_mbox_intr); -static int otx2_register_mbox_intr(struct otx2_nic *pf, bool probe_af) +int otx2_register_mbox_intr(struct otx2_nic *pf, bool probe_af) { struct otx2_hw *hw = &pf->hw; struct msg_req *req; @@ -1061,7 +1096,7 @@ static int otx2_register_mbox_intr(struct otx2_nic *pf, bool probe_af) return 0; } -static void otx2_pfaf_mbox_destroy(struct otx2_nic *pf) +void otx2_pfaf_mbox_destroy(struct otx2_nic *pf) { struct mbox *mbox = &pf->mbox; @@ -1076,8 +1111,9 @@ static void otx2_pfaf_mbox_destroy(struct otx2_nic *pf) otx2_mbox_destroy(&mbox->mbox); otx2_mbox_destroy(&mbox->mbox_up); } +EXPORT_SYMBOL(otx2_pfaf_mbox_destroy); -static int otx2_pfaf_mbox_init(struct otx2_nic *pf) +int otx2_pfaf_mbox_init(struct otx2_nic *pf) { struct mbox *mbox = &pf->mbox; void __iomem *hwbase; @@ -1379,7 +1415,7 @@ done: return IRQ_HANDLED; } -static irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq) +irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq) { struct otx2_cq_poll *cq_poll = (struct otx2_cq_poll *)cq_irq; struct otx2_nic *pf = (struct otx2_nic *)cq_poll->dev; @@ -1398,20 +1434,25 @@ static irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq) return IRQ_HANDLED; } +EXPORT_SYMBOL(otx2_cq_intr_handler); -static void otx2_disable_napi(struct otx2_nic *pf) +void otx2_disable_napi(struct otx2_nic *pf) { struct otx2_qset *qset = &pf->qset; struct otx2_cq_poll *cq_poll; + struct work_struct *work; int qidx; for (qidx = 0; qidx < pf->hw.cint_cnt; qidx++) { cq_poll = &qset->napi[qidx]; - cancel_work_sync(&cq_poll->dim.work); + work = &cq_poll->dim.work; + if (work->func) + cancel_work_sync(work); napi_disable(&cq_poll->napi); netif_napi_del(&cq_poll->napi); } } +EXPORT_SYMBOL(otx2_disable_napi); static void otx2_free_cq_res(struct otx2_nic *pf) { @@ -1477,7 +1518,7 @@ static int otx2_get_rbuf_size(struct otx2_nic *pf, int mtu) return ALIGN(rbuf_size, 2048); } -static int otx2_init_hw_resources(struct otx2_nic *pf) +int otx2_init_hw_resources(struct otx2_nic *pf) { struct nix_lf_free_req *free_req; struct mbox *mbox = &pf->mbox; @@ -1493,10 +1534,11 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) hw->sqpool_cnt = otx2_get_total_tx_queues(pf); hw->pool_cnt = hw->rqpool_cnt + hw->sqpool_cnt; - /* Maximum hardware supported transmit length */ - pf->tx_max_pktlen = pf->netdev->max_mtu + OTX2_ETH_HLEN; - - pf->rbsize = otx2_get_rbuf_size(pf, pf->netdev->mtu); + if (!otx2_rep_dev(pf->pdev)) { + /* Maximum hardware supported transmit length */ + pf->tx_max_pktlen = pf->netdev->max_mtu + OTX2_ETH_HLEN; + pf->rbsize = otx2_get_rbuf_size(pf, pf->netdev->mtu); + } mutex_lock(&mbox->lock); /* NPA init */ @@ -1549,10 +1591,15 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) } for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { - err = otx2_txschq_config(pf, lvl, 0, false); - if (err) { - mutex_unlock(&mbox->lock); - goto err_free_nix_queues; + int idx; + + for (idx = 0; idx < pf->hw.txschq_cnt[lvl]; idx++) { + err = otx2_txschq_config(pf, lvl, idx, false); + if (err) { + dev_err(pf->dev, "Failed to config TXSCH\n"); + mutex_unlock(&mbox->lock); + goto err_free_nix_queues; + } } } @@ -1601,8 +1648,9 @@ exit: mutex_unlock(&mbox->lock); return err; } +EXPORT_SYMBOL(otx2_init_hw_resources); -static void otx2_free_hw_resources(struct otx2_nic *pf) +void otx2_free_hw_resources(struct otx2_nic *pf) { struct otx2_qset *qset = &pf->qset; struct nix_lf_free_req *free_req; @@ -1624,11 +1672,12 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) otx2_pfc_txschq_stop(pf); #endif - otx2_clean_qos_queues(pf); + if (!otx2_rep_dev(pf->pdev)) + otx2_clean_qos_queues(pf); mutex_lock(&mbox->lock); /* Disable backpressure */ - if (!(pf->pcifunc & RVU_PFVF_FUNC_MASK)) + if (!is_otx2_lbkvf(pf->pdev)) otx2_nix_config_bp(pf, false); mutex_unlock(&mbox->lock); @@ -1660,7 +1709,8 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) otx2_free_cq_res(pf); /* Free all ingress bandwidth profiles allocated */ - cn10k_free_all_ipolicers(pf); + if (!otx2_rep_dev(pf->pdev)) + cn10k_free_all_ipolicers(pf); mutex_lock(&mbox->lock); /* Reset NIX LF */ @@ -1688,6 +1738,7 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) } mutex_unlock(&mbox->lock); } +EXPORT_SYMBOL(otx2_free_hw_resources); static bool otx2_promisc_use_mce_list(struct otx2_nic *pfvf) { @@ -1770,15 +1821,24 @@ static void otx2_dim_work(struct work_struct *w) dim->state = DIM_START_MEASURE; } -int otx2_open(struct net_device *netdev) +void otx2_free_queue_mem(struct otx2_qset *qset) +{ + kfree(qset->sq); + qset->sq = NULL; + kfree(qset->cq); + qset->cq = NULL; + kfree(qset->rq); + qset->rq = NULL; + kfree(qset->napi); + qset->napi = NULL; +} +EXPORT_SYMBOL(otx2_free_queue_mem); + +int otx2_alloc_queue_mem(struct otx2_nic *pf) { - struct otx2_nic *pf = netdev_priv(netdev); - struct otx2_cq_poll *cq_poll = NULL; struct otx2_qset *qset = &pf->qset; - int err = 0, qidx, vec; - char *irq_name; + struct otx2_cq_poll *cq_poll; - netif_carrier_off(netdev); /* RQ and SQs are mapped to different CQs, * so find out max CQ IRQs (i.e CINTs) needed. @@ -1798,7 +1858,6 @@ int otx2_open(struct net_device *netdev) /* CQ size of SQ */ qset->sqe_cnt = qset->sqe_cnt ? qset->sqe_cnt : Q_COUNT(Q_SIZE_4K); - err = -ENOMEM; qset->cq = kcalloc(pf->qset.cq_cnt, sizeof(struct otx2_cq_queue), GFP_KERNEL); if (!qset->cq) @@ -1814,6 +1873,28 @@ int otx2_open(struct net_device *netdev) if (!qset->rq) goto err_free_mem; + return 0; + +err_free_mem: + otx2_free_queue_mem(qset); + return -ENOMEM; +} +EXPORT_SYMBOL(otx2_alloc_queue_mem); + +int otx2_open(struct net_device *netdev) +{ + struct otx2_nic *pf = netdev_priv(netdev); + struct otx2_cq_poll *cq_poll = NULL; + struct otx2_qset *qset = &pf->qset; + int err = 0, qidx, vec; + char *irq_name; + + netif_carrier_off(netdev); + + err = otx2_alloc_queue_mem(pf); + if (err) + return err; + err = otx2_init_hw_resources(pf); if (err) goto err_free_mem; @@ -1932,6 +2013,7 @@ int otx2_open(struct net_device *netdev) } pf->flags &= ~OTX2_FLAG_INTF_DOWN; + pf->flags &= ~OTX2_FLAG_PORT_UP; /* 'intf_down' may be checked on any cpu */ smp_wmb(); @@ -1979,10 +2061,7 @@ err_disable_napi: otx2_disable_napi(pf); otx2_free_hw_resources(pf); err_free_mem: - kfree(qset->sq); - kfree(qset->cq); - kfree(qset->rq); - kfree(qset->napi); + otx2_free_queue_mem(qset); return err; } EXPORT_SYMBOL(otx2_open); @@ -2047,11 +2126,7 @@ int otx2_stop(struct net_device *netdev) for (qidx = 0; qidx < netdev->num_tx_queues; qidx++) netdev_tx_reset_queue(netdev_get_tx_queue(netdev, qidx)); - - kfree(qset->sq); - kfree(qset->cq); - kfree(qset->rq); - kfree(qset->napi); + otx2_free_queue_mem(qset); /* Do not clear RQ/SQ ringsize settings */ memset_startat(qset, 0, sqe_cnt); return 0; @@ -2081,7 +2156,7 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev) sq = &pf->qset.sq[sq_idx]; txq = netdev_get_tx_queue(netdev, qidx); - if (!otx2_sq_append_skb(netdev, sq, skb, qidx)) { + if (!otx2_sq_append_skb(pf, txq, sq, skb, qidx)) { netif_tx_stop_queue(txq); /* Check again, incase SQBs got freed up */ @@ -2786,7 +2861,7 @@ static const struct net_device_ops otx2_netdev_ops = { .ndo_set_vf_trust = otx2_ndo_set_vf_trust, }; -static int otx2_wq_init(struct otx2_nic *pf) +int otx2_wq_init(struct otx2_nic *pf) { pf->otx2_wq = create_singlethread_workqueue("otx2_wq"); if (!pf->otx2_wq) @@ -2797,7 +2872,7 @@ static int otx2_wq_init(struct otx2_nic *pf) return 0; } -static int otx2_check_pf_usable(struct otx2_nic *nic) +int otx2_check_pf_usable(struct otx2_nic *nic) { u64 rev; @@ -2815,7 +2890,7 @@ static int otx2_check_pf_usable(struct otx2_nic *nic) return 0; } -static int otx2_realloc_msix_vectors(struct otx2_nic *pf) +int otx2_realloc_msix_vectors(struct otx2_nic *pf) { struct otx2_hw *hw = &pf->hw; int num_vec, err; @@ -2837,6 +2912,7 @@ static int otx2_realloc_msix_vectors(struct otx2_nic *pf) return otx2_register_mbox_intr(pf, false); } +EXPORT_SYMBOL(otx2_realloc_msix_vectors); static int otx2_sriov_vfcfg_init(struct otx2_nic *pf) { @@ -2872,6 +2948,88 @@ static void otx2_sriov_vfcfg_cleanup(struct otx2_nic *pf) } } +int otx2_init_rsrc(struct pci_dev *pdev, struct otx2_nic *pf) +{ + struct device *dev = &pdev->dev; + struct otx2_hw *hw = &pf->hw; + int num_vec, err; + + num_vec = pci_msix_vec_count(pdev); + hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE, + GFP_KERNEL); + if (!hw->irq_name) + return -ENOMEM; + + hw->affinity_mask = devm_kcalloc(&hw->pdev->dev, num_vec, + sizeof(cpumask_var_t), GFP_KERNEL); + if (!hw->affinity_mask) + return -ENOMEM; + + /* Map CSRs */ + pf->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0); + if (!pf->reg_base) { + dev_err(dev, "Unable to map physical function CSRs, aborting\n"); + return -ENOMEM; + } + + err = otx2_check_pf_usable(pf); + if (err) + return err; + + err = pci_alloc_irq_vectors(hw->pdev, RVU_PF_INT_VEC_CNT, + RVU_PF_INT_VEC_CNT, PCI_IRQ_MSIX); + if (err < 0) { + dev_err(dev, "%s: Failed to alloc %d IRQ vectors\n", + __func__, num_vec); + return err; + } + + otx2_setup_dev_hw_settings(pf); + + /* Init PF <=> AF mailbox stuff */ + err = otx2_pfaf_mbox_init(pf); + if (err) + goto err_free_irq_vectors; + + /* Register mailbox interrupt */ + err = otx2_register_mbox_intr(pf, true); + if (err) + goto err_mbox_destroy; + + /* Request AF to attach NPA and NIX LFs to this PF. + * NIX and NPA LFs are needed for this PF to function as a NIC. + */ + err = otx2_attach_npa_nix(pf); + if (err) + goto err_disable_mbox_intr; + + err = otx2_realloc_msix_vectors(pf); + if (err) + goto err_detach_rsrc; + + err = cn10k_lmtst_init(pf); + if (err) + goto err_detach_rsrc; + + return 0; + +err_detach_rsrc: + if (pf->hw.lmt_info) + free_percpu(pf->hw.lmt_info); + if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) + qmem_free(pf->dev, pf->dync_lmt); + otx2_detach_resources(&pf->mbox); +err_disable_mbox_intr: + otx2_disable_mbox_intr(pf); +err_mbox_destroy: + otx2_pfaf_mbox_destroy(pf); +err_free_irq_vectors: + pci_free_irq_vectors(hw->pdev); + + return err; +} +EXPORT_SYMBOL(otx2_init_rsrc); + static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct device *dev = &pdev->dev; @@ -2879,7 +3037,6 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct net_device *netdev; struct otx2_nic *pf; struct otx2_hw *hw; - int num_vec; err = pcim_enable_device(pdev); if (err) { @@ -2930,72 +3087,14 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* Use CQE of 128 byte descriptor size by default */ hw->xqe_size = 128; - num_vec = pci_msix_vec_count(pdev); - hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE, - GFP_KERNEL); - if (!hw->irq_name) { - err = -ENOMEM; - goto err_free_netdev; - } - - hw->affinity_mask = devm_kcalloc(&hw->pdev->dev, num_vec, - sizeof(cpumask_var_t), GFP_KERNEL); - if (!hw->affinity_mask) { - err = -ENOMEM; - goto err_free_netdev; - } - - /* Map CSRs */ - pf->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0); - if (!pf->reg_base) { - dev_err(dev, "Unable to map physical function CSRs, aborting\n"); - err = -ENOMEM; - goto err_free_netdev; - } - - err = otx2_check_pf_usable(pf); + err = otx2_init_rsrc(pdev, pf); if (err) goto err_free_netdev; - err = pci_alloc_irq_vectors(hw->pdev, RVU_PF_INT_VEC_CNT, - RVU_PF_INT_VEC_CNT, PCI_IRQ_MSIX); - if (err < 0) { - dev_err(dev, "%s: Failed to alloc %d IRQ vectors\n", - __func__, num_vec); - goto err_free_netdev; - } - - otx2_setup_dev_hw_settings(pf); - - /* Init PF <=> AF mailbox stuff */ - err = otx2_pfaf_mbox_init(pf); - if (err) - goto err_free_irq_vectors; - - /* Register mailbox interrupt */ - err = otx2_register_mbox_intr(pf, true); - if (err) - goto err_mbox_destroy; - - /* Request AF to attach NPA and NIX LFs to this PF. - * NIX and NPA LFs are needed for this PF to function as a NIC. - */ - err = otx2_attach_npa_nix(pf); - if (err) - goto err_disable_mbox_intr; - - err = otx2_realloc_msix_vectors(pf); - if (err) - goto err_detach_rsrc; - err = otx2_set_real_num_queues(netdev, hw->tx_queues, hw->rx_queues); if (err) goto err_detach_rsrc; - err = cn10k_lmtst_init(pf); - if (err) - goto err_detach_rsrc; - /* Assign default mac address */ otx2_get_mac_from_af(netdev); @@ -3058,6 +3157,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->min_mtu = OTX2_MIN_MTU; netdev->max_mtu = otx2_get_max_mtu(pf); + hw->max_mtu = netdev->max_mtu; /* reset CGX/RPM MAC stats */ otx2_reset_mac_stats(pf); @@ -3118,11 +3218,8 @@ err_detach_rsrc: if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) qmem_free(pf->dev, pf->dync_lmt); otx2_detach_resources(&pf->mbox); -err_disable_mbox_intr: otx2_disable_mbox_intr(pf); -err_mbox_destroy: otx2_pfaf_mbox_destroy(pf); -err_free_irq_vectors: pci_free_irq_vectors(hw->pdev); err_free_netdev: pci_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index e63cc1eb6d89..9a226ca74425 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -443,6 +443,7 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic, struct flow_action_entry *act; struct net_device *target; struct otx2_nic *priv; + struct rep_dev *rdev; u32 burst, mark = 0; u8 nr_police = 0; u8 num_intf = 1; @@ -464,14 +465,18 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic, return 0; case FLOW_ACTION_REDIRECT_INGRESS: target = act->dev; - priv = netdev_priv(target); - /* npc_install_flow_req doesn't support passing a target pcifunc */ - if (rvu_get_pf(nic->pcifunc) != rvu_get_pf(priv->pcifunc)) { - NL_SET_ERR_MSG_MOD(extack, - "can't redirect to other pf/vf"); - return -EOPNOTSUPP; + if (target->dev.parent) { + priv = netdev_priv(target); + if (rvu_get_pf(nic->pcifunc) != rvu_get_pf(priv->pcifunc)) { + NL_SET_ERR_MSG_MOD(extack, + "can't redirect to other pf/vf"); + return -EOPNOTSUPP; + } + req->vf = priv->pcifunc & RVU_PFVF_FUNC_MASK; + } else { + rdev = netdev_priv(target); + req->vf = rdev->pcifunc & RVU_PFVF_FUNC_MASK; } - req->vf = priv->pcifunc & RVU_PFVF_FUNC_MASK; /* if op is already set; avoid overwriting the same */ if (!req->op) @@ -1300,6 +1305,7 @@ static int otx2_tc_add_flow(struct otx2_nic *nic, req->channel = nic->hw.rx_chan_base; req->entry = flow_cfg->flow_ent[mcam_idx]; req->intf = NIX_INTF_RX; + req->vf = nic->pcifunc; req->set_cntr = 1; new_node->entry = req->entry; @@ -1400,8 +1406,8 @@ static int otx2_tc_get_flow_stats(struct otx2_nic *nic, return 0; } -static int otx2_setup_tc_cls_flower(struct otx2_nic *nic, - struct flow_cls_offload *cls_flower) +int otx2_setup_tc_cls_flower(struct otx2_nic *nic, + struct flow_cls_offload *cls_flower) { switch (cls_flower->command) { case FLOW_CLS_REPLACE: @@ -1414,6 +1420,7 @@ static int otx2_setup_tc_cls_flower(struct otx2_nic *nic, return -EOPNOTSUPP; } } +EXPORT_SYMBOL(otx2_setup_tc_cls_flower); static int otx2_tc_ingress_matchall_install(struct otx2_nic *nic, struct tc_cls_matchall_offload *cls) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 933e18ba2fb2..04bc06a80e23 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -376,9 +376,11 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf, } otx2_set_rxhash(pfvf, cqe, skb); - skb_record_rx_queue(skb, cq->cq_idx); - if (pfvf->netdev->features & NETIF_F_RXCSUM) - skb->ip_summed = CHECKSUM_UNNECESSARY; + if (!(pfvf->flags & OTX2_FLAG_REP_MODE_ENABLED)) { + skb_record_rx_queue(skb, cq->cq_idx); + if (pfvf->netdev->features & NETIF_F_RXCSUM) + skb->ip_summed = CHECKSUM_UNNECESSARY; + } if (pfvf->flags & OTX2_FLAG_TC_MARK_ENABLED) skb->mark = parse->match_id; @@ -453,6 +455,7 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf, int tx_pkts = 0, tx_bytes = 0, qidx; struct otx2_snd_queue *sq; struct nix_cqe_tx_s *cqe; + struct net_device *ndev; int processed_cqe = 0; if (cq->pend_cqe >= budget) @@ -493,6 +496,13 @@ process_cqe: otx2_write64(pfvf, NIX_LF_CQ_OP_DOOR, ((u64)cq->cq_idx << 32) | processed_cqe); +#if IS_ENABLED(CONFIG_RVU_ESWITCH) + if (pfvf->flags & OTX2_FLAG_REP_MODE_ENABLED) + ndev = pfvf->reps[qidx]->netdev; + else +#endif + ndev = pfvf->netdev; + if (likely(tx_pkts)) { struct netdev_queue *txq; @@ -500,12 +510,14 @@ process_cqe: if (qidx >= pfvf->hw.tx_queues) qidx -= pfvf->hw.xdp_queues; - txq = netdev_get_tx_queue(pfvf->netdev, qidx); + if (pfvf->flags & OTX2_FLAG_REP_MODE_ENABLED) + qidx = 0; + txq = netdev_get_tx_queue(ndev, qidx); netdev_tx_completed_queue(txq, tx_pkts, tx_bytes); /* Check if queue was stopped earlier due to ring full */ smp_mb(); if (netif_tx_queue_stopped(txq) && - netif_carrier_ok(pfvf->netdev)) + netif_carrier_ok(ndev)) netif_tx_wake_queue(txq); } return 0; @@ -527,7 +539,7 @@ static void otx2_adjust_adaptive_coalese(struct otx2_nic *pfvf, struct otx2_cq_p rx_frames + tx_frames, rx_bytes + tx_bytes, &dim_sample); - net_dim(&cq_poll->dim, dim_sample); + net_dim(&cq_poll->dim, &dim_sample); } int otx2_napi_handler(struct napi_struct *napi, int budget) @@ -594,6 +606,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget) } return workdone; } +EXPORT_SYMBOL(otx2_napi_handler); void otx2_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx) @@ -1141,13 +1154,13 @@ static void otx2_set_txtstamp(struct otx2_nic *pfvf, struct sk_buff *skb, } } -bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, +bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq, + struct otx2_snd_queue *sq, struct sk_buff *skb, u16 qidx) { - struct netdev_queue *txq = netdev_get_tx_queue(netdev, qidx); - struct otx2_nic *pfvf = netdev_priv(netdev); int offset, num_segs, free_desc; struct nix_sqe_hdr_s *sqe_hdr; + struct otx2_nic *pfvf = dev; /* Check if there is enough room between producer * and consumer index. diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index 3f1d2655ff77..e1db5f961877 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -167,7 +167,8 @@ static inline u64 otx2_iova_to_phys(void *iommu_domain, dma_addr_t dma_addr) } int otx2_napi_handler(struct napi_struct *napi, int budget); -bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, +bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq, + struct otx2_snd_queue *sq, struct sk_buff *skb, u16 qidx); void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 99fcc5661674..839fc77c11b2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -21,6 +21,7 @@ static const struct pci_device_id otx2_vf_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_RVU_AFVF) }, { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_RVU_VF) }, + { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_SDP_REP) }, { } }; @@ -371,7 +372,7 @@ static int otx2vf_open(struct net_device *netdev) /* LBKs do not receive link events so tell everyone we are up here */ vf = netdev_priv(netdev); - if (is_otx2_lbkvf(vf->pdev)) { + if (is_otx2_lbkvf(vf->pdev) || is_otx2_sdp_rep(vf->pdev)) { pr_info("%s NIC Link is UP\n", netdev->name); netif_carrier_on(netdev); netif_tx_start_all_queues(netdev); @@ -395,7 +396,7 @@ static netdev_tx_t otx2vf_xmit(struct sk_buff *skb, struct net_device *netdev) sq = &vf->qset.sq[qidx]; txq = netdev_get_tx_queue(netdev, qidx); - if (!otx2_sq_append_skb(netdev, sq, skb, qidx)) { + if (!otx2_sq_append_skb(vf, txq, sq, skb, qidx)) { netif_tx_stop_queue(txq); /* Check again, incase SQBs got freed up */ @@ -500,7 +501,7 @@ static const struct net_device_ops otx2vf_netdev_ops = { .ndo_setup_tc = otx2_setup_tc, }; -static int otx2_wq_init(struct otx2_nic *vf) +static int otx2_vf_wq_init(struct otx2_nic *vf) { vf->otx2_wq = create_singlethread_workqueue("otx2vf_wq"); if (!vf->otx2_wq) @@ -671,6 +672,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->min_mtu = OTX2_MIN_MTU; netdev->max_mtu = otx2_get_max_mtu(vf); + hw->max_mtu = netdev->max_mtu; /* To distinguish, for LBK VFs set netdev name explicitly */ if (is_otx2_lbkvf(vf->pdev)) { @@ -682,13 +684,22 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) snprintf(netdev->name, sizeof(netdev->name), "lbk%d", n); } + if (is_otx2_sdp_rep(vf->pdev)) { + int n; + + n = vf->pcifunc & RVU_PFVF_FUNC_MASK; + n -= 1; + snprintf(netdev->name, sizeof(netdev->name), "sdp%d-%d", + pdev->bus->number, n); + } + err = register_netdev(netdev); if (err) { dev_err(dev, "Failed to register netdevice\n"); goto err_ptp_destroy; } - err = otx2_wq_init(vf); + err = otx2_vf_wq_init(vf); if (err) goto err_unreg_netdev; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c new file mode 100644 index 000000000000..ae58d0601b45 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c @@ -0,0 +1,864 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell RVU representor driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#include <linux/etherdevice.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/net_tstamp.h> +#include <linux/sort.h> + +#include "otx2_common.h" +#include "cn10k.h" +#include "otx2_reg.h" +#include "rep.h" + +#define DRV_NAME "rvu_rep" +#define DRV_STRING "Marvell RVU Representor Driver" + +static const struct pci_device_id rvu_rep_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_RVU_REP) }, + { } +}; + +MODULE_AUTHOR("Marvell International Ltd."); +MODULE_DESCRIPTION(DRV_STRING); +MODULE_LICENSE("GPL"); +MODULE_DEVICE_TABLE(pci, rvu_rep_id_table); + +static int rvu_rep_notify_pfvf(struct otx2_nic *priv, u16 event, + struct rep_event *data); + +static int rvu_rep_mcam_flow_init(struct rep_dev *rep) +{ + struct npc_mcam_alloc_entry_req *req; + struct npc_mcam_alloc_entry_rsp *rsp; + struct otx2_nic *priv = rep->mdev; + int ent, allocated = 0; + int count; + + rep->flow_cfg = kcalloc(1, sizeof(struct otx2_flow_config), GFP_KERNEL); + + if (!rep->flow_cfg) + return -ENOMEM; + + count = OTX2_DEFAULT_FLOWCOUNT; + + rep->flow_cfg->flow_ent = kcalloc(count, sizeof(u16), GFP_KERNEL); + if (!rep->flow_cfg->flow_ent) + return -ENOMEM; + + while (allocated < count) { + req = otx2_mbox_alloc_msg_npc_mcam_alloc_entry(&priv->mbox); + if (!req) + goto exit; + + req->hdr.pcifunc = rep->pcifunc; + req->contig = false; + req->ref_entry = 0; + req->count = (count - allocated) > NPC_MAX_NONCONTIG_ENTRIES ? + NPC_MAX_NONCONTIG_ENTRIES : count - allocated; + + if (otx2_sync_mbox_msg(&priv->mbox)) + goto exit; + + rsp = (struct npc_mcam_alloc_entry_rsp *)otx2_mbox_get_rsp + (&priv->mbox.mbox, 0, &req->hdr); + + for (ent = 0; ent < rsp->count; ent++) + rep->flow_cfg->flow_ent[ent + allocated] = rsp->entry_list[ent]; + + allocated += rsp->count; + + if (rsp->count != req->count) + break; + } +exit: + /* Multiple MCAM entry alloc requests could result in non-sequential + * MCAM entries in the flow_ent[] array. Sort them in an ascending + * order, otherwise user installed ntuple filter index and MCAM entry + * index will not be in sync. + */ + if (allocated) + sort(&rep->flow_cfg->flow_ent[0], allocated, + sizeof(rep->flow_cfg->flow_ent[0]), mcam_entry_cmp, NULL); + + mutex_unlock(&priv->mbox.lock); + + rep->flow_cfg->max_flows = allocated; + + if (allocated) { + rep->flags |= OTX2_FLAG_MCAM_ENTRIES_ALLOC; + rep->flags |= OTX2_FLAG_NTUPLE_SUPPORT; + rep->flags |= OTX2_FLAG_TC_FLOWER_SUPPORT; + } + + INIT_LIST_HEAD(&rep->flow_cfg->flow_list); + INIT_LIST_HEAD(&rep->flow_cfg->flow_list_tc); + return 0; +} + +static int rvu_rep_setup_tc_cb(enum tc_setup_type type, + void *type_data, void *cb_priv) +{ + struct rep_dev *rep = cb_priv; + struct otx2_nic *priv = rep->mdev; + + if (!(rep->flags & RVU_REP_VF_INITIALIZED)) + return -EINVAL; + + if (!(rep->flags & OTX2_FLAG_TC_FLOWER_SUPPORT)) + rvu_rep_mcam_flow_init(rep); + + priv->netdev = rep->netdev; + priv->flags = rep->flags; + priv->pcifunc = rep->pcifunc; + priv->flow_cfg = rep->flow_cfg; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return otx2_setup_tc_cls_flower(priv, type_data); + default: + return -EOPNOTSUPP; + } +} + +static LIST_HEAD(rvu_rep_block_cb_list); +static int rvu_rep_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) +{ + struct rvu_rep *rep = netdev_priv(netdev); + + switch (type) { + case TC_SETUP_BLOCK: + return flow_block_cb_setup_simple(type_data, + &rvu_rep_block_cb_list, + rvu_rep_setup_tc_cb, + rep, rep, true); + default: + return -EOPNOTSUPP; + } +} + +static int +rvu_rep_sp_stats64(const struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct rep_dev *rep = netdev_priv(dev); + struct otx2_nic *priv = rep->mdev; + struct otx2_rcv_queue *rq; + struct otx2_snd_queue *sq; + u16 qidx = rep->rep_id; + + otx2_update_rq_stats(priv, qidx); + rq = &priv->qset.rq[qidx]; + + otx2_update_sq_stats(priv, qidx); + sq = &priv->qset.sq[qidx]; + + stats->tx_bytes = sq->stats.bytes; + stats->tx_packets = sq->stats.pkts; + stats->rx_bytes = rq->stats.bytes; + stats->rx_packets = rq->stats.pkts; + return 0; +} + +static bool +rvu_rep_has_offload_stats(const struct net_device *dev, int attr_id) +{ + return attr_id == IFLA_OFFLOAD_XSTATS_CPU_HIT; +} + +static int +rvu_rep_get_offload_stats(int attr_id, const struct net_device *dev, + void *sp) +{ + if (attr_id == IFLA_OFFLOAD_XSTATS_CPU_HIT) + return rvu_rep_sp_stats64(dev, (struct rtnl_link_stats64 *)sp); + + return -EINVAL; +} + +static int rvu_rep_dl_port_fn_hw_addr_get(struct devlink_port *port, + u8 *hw_addr, int *hw_addr_len, + struct netlink_ext_ack *extack) +{ + struct rep_dev *rep = container_of(port, struct rep_dev, dl_port); + + ether_addr_copy(hw_addr, rep->mac); + *hw_addr_len = ETH_ALEN; + return 0; +} + +static int rvu_rep_dl_port_fn_hw_addr_set(struct devlink_port *port, + const u8 *hw_addr, int hw_addr_len, + struct netlink_ext_ack *extack) +{ + struct rep_dev *rep = container_of(port, struct rep_dev, dl_port); + struct otx2_nic *priv = rep->mdev; + struct rep_event evt = {0}; + + eth_hw_addr_set(rep->netdev, hw_addr); + ether_addr_copy(rep->mac, hw_addr); + + ether_addr_copy(evt.evt_data.mac, hw_addr); + evt.pcifunc = rep->pcifunc; + rvu_rep_notify_pfvf(priv, RVU_EVENT_MAC_ADDR_CHANGE, &evt); + return 0; +} + +static const struct devlink_port_ops rvu_rep_dl_port_ops = { + .port_fn_hw_addr_get = rvu_rep_dl_port_fn_hw_addr_get, + .port_fn_hw_addr_set = rvu_rep_dl_port_fn_hw_addr_set, +}; + +static void +rvu_rep_devlink_set_switch_id(struct otx2_nic *priv, + struct netdev_phys_item_id *ppid) +{ + struct pci_dev *pdev = priv->pdev; + u64 id; + + id = pci_get_dsn(pdev); + + ppid->id_len = sizeof(id); + put_unaligned_be64(id, &ppid->id); +} + +static void rvu_rep_devlink_port_unregister(struct rep_dev *rep) +{ + devlink_port_unregister(&rep->dl_port); +} + +static int rvu_rep_devlink_port_register(struct rep_dev *rep) +{ + struct devlink_port_attrs attrs = {}; + struct otx2_nic *priv = rep->mdev; + struct devlink *dl = priv->dl->dl; + int err; + + if (!(rep->pcifunc & RVU_PFVF_FUNC_MASK)) { + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = rvu_get_pf(rep->pcifunc); + } else { + attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; + attrs.pci_vf.pf = rvu_get_pf(rep->pcifunc); + attrs.pci_vf.vf = rep->pcifunc & RVU_PFVF_FUNC_MASK; + } + + rvu_rep_devlink_set_switch_id(priv, &attrs.switch_id); + devlink_port_attrs_set(&rep->dl_port, &attrs); + + err = devl_port_register_with_ops(dl, &rep->dl_port, rep->rep_id, + &rvu_rep_dl_port_ops); + if (err) { + dev_err(rep->mdev->dev, "devlink_port_register failed: %d\n", + err); + return err; + } + return 0; +} + +static int rvu_rep_get_repid(struct otx2_nic *priv, u16 pcifunc) +{ + int rep_id; + + for (rep_id = 0; rep_id < priv->rep_cnt; rep_id++) + if (priv->rep_pf_map[rep_id] == pcifunc) + return rep_id; + return -EINVAL; +} + +static int rvu_rep_notify_pfvf(struct otx2_nic *priv, u16 event, + struct rep_event *data) +{ + struct rep_event *req; + + mutex_lock(&priv->mbox.lock); + req = otx2_mbox_alloc_msg_rep_event_notify(&priv->mbox); + if (!req) { + mutex_unlock(&priv->mbox.lock); + return -ENOMEM; + } + req->event = event; + req->pcifunc = data->pcifunc; + + memcpy(&req->evt_data, &data->evt_data, sizeof(struct rep_evt_data)); + otx2_sync_mbox_msg(&priv->mbox); + mutex_unlock(&priv->mbox.lock); + return 0; +} + +static void rvu_rep_state_evt_handler(struct otx2_nic *priv, + struct rep_event *info) +{ + struct rep_dev *rep; + int rep_id; + + rep_id = rvu_rep_get_repid(priv, info->pcifunc); + rep = priv->reps[rep_id]; + if (info->evt_data.vf_state) + rep->flags |= RVU_REP_VF_INITIALIZED; + else + rep->flags &= ~RVU_REP_VF_INITIALIZED; +} + +int rvu_event_up_notify(struct otx2_nic *pf, struct rep_event *info) +{ + if (info->event & RVU_EVENT_PFVF_STATE) + rvu_rep_state_evt_handler(pf, info); + return 0; +} + +static int rvu_rep_change_mtu(struct net_device *dev, int new_mtu) +{ + struct rep_dev *rep = netdev_priv(dev); + struct otx2_nic *priv = rep->mdev; + struct rep_event evt = {0}; + + netdev_info(dev, "Changing MTU from %d to %d\n", + dev->mtu, new_mtu); + dev->mtu = new_mtu; + + evt.evt_data.mtu = new_mtu; + evt.pcifunc = rep->pcifunc; + rvu_rep_notify_pfvf(priv, RVU_EVENT_MTU_CHANGE, &evt); + return 0; +} + +static void rvu_rep_get_stats(struct work_struct *work) +{ + struct delayed_work *del_work = to_delayed_work(work); + struct nix_stats_req *req; + struct nix_stats_rsp *rsp; + struct rep_stats *stats; + struct otx2_nic *priv; + struct rep_dev *rep; + int err; + + rep = container_of(del_work, struct rep_dev, stats_wrk); + priv = rep->mdev; + + mutex_lock(&priv->mbox.lock); + req = otx2_mbox_alloc_msg_nix_lf_stats(&priv->mbox); + if (!req) { + mutex_unlock(&priv->mbox.lock); + return; + } + req->pcifunc = rep->pcifunc; + err = otx2_sync_mbox_msg_busy_poll(&priv->mbox); + if (err) + goto exit; + + rsp = (struct nix_stats_rsp *) + otx2_mbox_get_rsp(&priv->mbox.mbox, 0, &req->hdr); + + if (IS_ERR(rsp)) { + err = PTR_ERR(rsp); + goto exit; + } + + stats = &rep->stats; + stats->rx_bytes = rsp->rx.octs; + stats->rx_frames = rsp->rx.ucast + rsp->rx.bcast + + rsp->rx.mcast; + stats->rx_drops = rsp->rx.drop; + stats->rx_mcast_frames = rsp->rx.mcast; + stats->tx_bytes = rsp->tx.octs; + stats->tx_frames = rsp->tx.ucast + rsp->tx.bcast + rsp->tx.mcast; + stats->tx_drops = rsp->tx.drop; +exit: + mutex_unlock(&priv->mbox.lock); +} + +static void rvu_rep_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct rep_dev *rep = netdev_priv(dev); + + if (!(rep->flags & RVU_REP_VF_INITIALIZED)) + return; + + stats->rx_packets = rep->stats.rx_frames; + stats->rx_bytes = rep->stats.rx_bytes; + stats->rx_dropped = rep->stats.rx_drops; + stats->multicast = rep->stats.rx_mcast_frames; + + stats->tx_packets = rep->stats.tx_frames; + stats->tx_bytes = rep->stats.tx_bytes; + stats->tx_dropped = rep->stats.tx_drops; + + schedule_delayed_work(&rep->stats_wrk, msecs_to_jiffies(100)); +} + +static int rvu_eswitch_config(struct otx2_nic *priv, u8 ena) +{ + struct esw_cfg_req *req; + + mutex_lock(&priv->mbox.lock); + req = otx2_mbox_alloc_msg_esw_cfg(&priv->mbox); + if (!req) { + mutex_unlock(&priv->mbox.lock); + return -ENOMEM; + } + req->ena = ena; + otx2_sync_mbox_msg(&priv->mbox); + mutex_unlock(&priv->mbox.lock); + return 0; +} + +static netdev_tx_t rvu_rep_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct rep_dev *rep = netdev_priv(dev); + struct otx2_nic *pf = rep->mdev; + struct otx2_snd_queue *sq; + struct netdev_queue *txq; + + sq = &pf->qset.sq[rep->rep_id]; + txq = netdev_get_tx_queue(dev, 0); + + if (!otx2_sq_append_skb(pf, txq, sq, skb, rep->rep_id)) { + netif_tx_stop_queue(txq); + + /* Check again, in case SQBs got freed up */ + smp_mb(); + if (((sq->num_sqbs - *sq->aura_fc_addr) * sq->sqe_per_sqb) + > sq->sqe_thresh) + netif_tx_wake_queue(txq); + + return NETDEV_TX_BUSY; + } + return NETDEV_TX_OK; +} + +static int rvu_rep_open(struct net_device *dev) +{ + struct rep_dev *rep = netdev_priv(dev); + struct otx2_nic *priv = rep->mdev; + struct rep_event evt = {0}; + + if (!(rep->flags & RVU_REP_VF_INITIALIZED)) + return 0; + + netif_carrier_on(dev); + netif_tx_start_all_queues(dev); + + evt.event = RVU_EVENT_PORT_STATE; + evt.evt_data.port_state = 1; + evt.pcifunc = rep->pcifunc; + rvu_rep_notify_pfvf(priv, RVU_EVENT_PORT_STATE, &evt); + return 0; +} + +static int rvu_rep_stop(struct net_device *dev) +{ + struct rep_dev *rep = netdev_priv(dev); + struct otx2_nic *priv = rep->mdev; + struct rep_event evt = {0}; + + if (!(rep->flags & RVU_REP_VF_INITIALIZED)) + return 0; + + netif_carrier_off(dev); + netif_tx_disable(dev); + + evt.event = RVU_EVENT_PORT_STATE; + evt.pcifunc = rep->pcifunc; + rvu_rep_notify_pfvf(priv, RVU_EVENT_PORT_STATE, &evt); + return 0; +} + +static const struct net_device_ops rvu_rep_netdev_ops = { + .ndo_open = rvu_rep_open, + .ndo_stop = rvu_rep_stop, + .ndo_start_xmit = rvu_rep_xmit, + .ndo_get_stats64 = rvu_rep_get_stats64, + .ndo_change_mtu = rvu_rep_change_mtu, + .ndo_has_offload_stats = rvu_rep_has_offload_stats, + .ndo_get_offload_stats = rvu_rep_get_offload_stats, + .ndo_setup_tc = rvu_rep_setup_tc, +}; + +static int rvu_rep_napi_init(struct otx2_nic *priv, + struct netlink_ext_ack *extack) +{ + struct otx2_qset *qset = &priv->qset; + struct otx2_cq_poll *cq_poll = NULL; + struct otx2_hw *hw = &priv->hw; + int err = 0, qidx, vec; + char *irq_name; + + qset->napi = kcalloc(hw->cint_cnt, sizeof(*cq_poll), GFP_KERNEL); + if (!qset->napi) + return -ENOMEM; + + /* Register NAPI handler */ + for (qidx = 0; qidx < hw->cint_cnt; qidx++) { + cq_poll = &qset->napi[qidx]; + cq_poll->cint_idx = qidx; + cq_poll->cq_ids[CQ_RX] = + (qidx < hw->rx_queues) ? qidx : CINT_INVALID_CQ; + cq_poll->cq_ids[CQ_TX] = (qidx < hw->tx_queues) ? + qidx + hw->rx_queues : + CINT_INVALID_CQ; + cq_poll->cq_ids[CQ_XDP] = CINT_INVALID_CQ; + cq_poll->cq_ids[CQ_QOS] = CINT_INVALID_CQ; + + cq_poll->dev = (void *)priv; + netif_napi_add(priv->reps[qidx]->netdev, &cq_poll->napi, + otx2_napi_handler); + napi_enable(&cq_poll->napi); + } + /* Register CQ IRQ handlers */ + vec = hw->nix_msixoff + NIX_LF_CINT_VEC_START; + for (qidx = 0; qidx < hw->cint_cnt; qidx++) { + irq_name = &hw->irq_name[vec * NAME_SIZE]; + + snprintf(irq_name, NAME_SIZE, "rep%d-rxtx-%d", qidx, qidx); + + err = request_irq(pci_irq_vector(priv->pdev, vec), + otx2_cq_intr_handler, 0, irq_name, + &qset->napi[qidx]); + if (err) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "RVU REP IRQ registration failed for CQ%d", + qidx); + goto err_free_cints; + } + vec++; + + /* Enable CQ IRQ */ + otx2_write64(priv, NIX_LF_CINTX_INT(qidx), BIT_ULL(0)); + otx2_write64(priv, NIX_LF_CINTX_ENA_W1S(qidx), BIT_ULL(0)); + } + priv->flags &= ~OTX2_FLAG_INTF_DOWN; + return 0; + +err_free_cints: + otx2_free_cints(priv, qidx); + otx2_disable_napi(priv); + return err; +} + +static void rvu_rep_free_cq_rsrc(struct otx2_nic *priv) +{ + struct otx2_qset *qset = &priv->qset; + struct otx2_cq_poll *cq_poll = NULL; + int qidx, vec; + + /* Cleanup CQ NAPI and IRQ */ + vec = priv->hw.nix_msixoff + NIX_LF_CINT_VEC_START; + for (qidx = 0; qidx < priv->hw.cint_cnt; qidx++) { + /* Disable interrupt */ + otx2_write64(priv, NIX_LF_CINTX_ENA_W1C(qidx), BIT_ULL(0)); + + synchronize_irq(pci_irq_vector(priv->pdev, vec)); + + cq_poll = &qset->napi[qidx]; + napi_synchronize(&cq_poll->napi); + vec++; + } + otx2_free_cints(priv, priv->hw.cint_cnt); + otx2_disable_napi(priv); +} + +static void rvu_rep_rsrc_free(struct otx2_nic *priv) +{ + struct otx2_qset *qset = &priv->qset; + struct delayed_work *work; + int wrk; + + for (wrk = 0; wrk < priv->qset.cq_cnt; wrk++) { + work = &priv->refill_wrk[wrk].pool_refill_work; + cancel_delayed_work_sync(work); + } + devm_kfree(priv->dev, priv->refill_wrk); + + otx2_free_hw_resources(priv); + otx2_free_queue_mem(qset); +} + +static int rvu_rep_rsrc_init(struct otx2_nic *priv) +{ + struct otx2_qset *qset = &priv->qset; + int err; + + err = otx2_alloc_queue_mem(priv); + if (err) + return err; + + priv->hw.max_mtu = otx2_get_max_mtu(priv); + priv->tx_max_pktlen = priv->hw.max_mtu + OTX2_ETH_HLEN; + priv->rbsize = ALIGN(priv->hw.rbuf_len, OTX2_ALIGN) + OTX2_HEAD_ROOM; + + err = otx2_init_hw_resources(priv); + if (err) + goto err_free_rsrc; + + /* Set maximum frame size allowed in HW */ + err = otx2_hw_set_mtu(priv, priv->hw.max_mtu); + if (err) { + dev_err(priv->dev, "Failed to set HW MTU\n"); + goto err_free_rsrc; + } + return 0; + +err_free_rsrc: + otx2_free_hw_resources(priv); + otx2_free_queue_mem(qset); + return err; +} + +void rvu_rep_destroy(struct otx2_nic *priv) +{ + struct rep_dev *rep; + int rep_id; + + rvu_eswitch_config(priv, false); + priv->flags |= OTX2_FLAG_INTF_DOWN; + rvu_rep_free_cq_rsrc(priv); + for (rep_id = 0; rep_id < priv->rep_cnt; rep_id++) { + rep = priv->reps[rep_id]; + unregister_netdev(rep->netdev); + rvu_rep_devlink_port_unregister(rep); + free_netdev(rep->netdev); + kfree(rep->flow_cfg); + } + kfree(priv->reps); + rvu_rep_rsrc_free(priv); +} + +int rvu_rep_create(struct otx2_nic *priv, struct netlink_ext_ack *extack) +{ + int rep_cnt = priv->rep_cnt; + struct net_device *ndev; + struct rep_dev *rep; + int rep_id, err; + u16 pcifunc; + + err = rvu_rep_rsrc_init(priv); + if (err) + return -ENOMEM; + + priv->reps = kcalloc(rep_cnt, sizeof(struct rep_dev *), GFP_KERNEL); + if (!priv->reps) + return -ENOMEM; + + for (rep_id = 0; rep_id < rep_cnt; rep_id++) { + ndev = alloc_etherdev(sizeof(*rep)); + if (!ndev) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "PFVF representor:%d creation failed", + rep_id); + err = -ENOMEM; + goto exit; + } + + rep = netdev_priv(ndev); + priv->reps[rep_id] = rep; + rep->mdev = priv; + rep->netdev = ndev; + rep->rep_id = rep_id; + + ndev->min_mtu = OTX2_MIN_MTU; + ndev->max_mtu = priv->hw.max_mtu; + ndev->netdev_ops = &rvu_rep_netdev_ops; + pcifunc = priv->rep_pf_map[rep_id]; + rep->pcifunc = pcifunc; + + snprintf(ndev->name, sizeof(ndev->name), "Rpf%dvf%d", + rvu_get_pf(pcifunc), (pcifunc & RVU_PFVF_FUNC_MASK)); + + ndev->hw_features = (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | NETIF_F_RXHASH | + NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6); + + ndev->hw_features |= NETIF_F_HW_TC; + ndev->features |= ndev->hw_features; + eth_hw_addr_random(ndev); + err = rvu_rep_devlink_port_register(rep); + if (err) + goto exit; + + SET_NETDEV_DEVLINK_PORT(ndev, &rep->dl_port); + err = register_netdev(ndev); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "PFVF reprentator registration failed"); + free_netdev(ndev); + goto exit; + } + + INIT_DELAYED_WORK(&rep->stats_wrk, rvu_rep_get_stats); + } + err = rvu_rep_napi_init(priv, extack); + if (err) + goto exit; + + rvu_eswitch_config(priv, true); + return 0; +exit: + while (--rep_id >= 0) { + rep = priv->reps[rep_id]; + unregister_netdev(rep->netdev); + rvu_rep_devlink_port_unregister(rep); + free_netdev(rep->netdev); + } + kfree(priv->reps); + rvu_rep_rsrc_free(priv); + return err; +} + +static int rvu_get_rep_cnt(struct otx2_nic *priv) +{ + struct get_rep_cnt_rsp *rsp; + struct mbox_msghdr *msghdr; + struct msg_req *req; + int err, rep; + + mutex_lock(&priv->mbox.lock); + req = otx2_mbox_alloc_msg_get_rep_cnt(&priv->mbox); + if (!req) { + mutex_unlock(&priv->mbox.lock); + return -ENOMEM; + } + err = otx2_sync_mbox_msg(&priv->mbox); + if (err) + goto exit; + + msghdr = otx2_mbox_get_rsp(&priv->mbox.mbox, 0, &req->hdr); + if (IS_ERR(msghdr)) { + err = PTR_ERR(msghdr); + goto exit; + } + + rsp = (struct get_rep_cnt_rsp *)msghdr; + priv->hw.tx_queues = rsp->rep_cnt; + priv->hw.rx_queues = rsp->rep_cnt; + priv->rep_cnt = rsp->rep_cnt; + for (rep = 0; rep < priv->rep_cnt; rep++) + priv->rep_pf_map[rep] = rsp->rep_pf_map[rep]; + +exit: + mutex_unlock(&priv->mbox.lock); + return err; +} + +static int rvu_rep_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct device *dev = &pdev->dev; + struct otx2_nic *priv; + struct otx2_hw *hw; + int err; + + err = pcim_enable_device(pdev); + if (err) { + dev_err(dev, "Failed to enable PCI device\n"); + return err; + } + + err = pci_request_regions(pdev, DRV_NAME); + if (err) { + dev_err(dev, "PCI request regions failed 0x%x\n", err); + return err; + } + + err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48)); + if (err) { + dev_err(dev, "DMA mask config failed, abort\n"); + goto err_release_regions; + } + + pci_set_master(pdev); + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) { + err = -ENOMEM; + goto err_release_regions; + } + + pci_set_drvdata(pdev, priv); + priv->pdev = pdev; + priv->dev = dev; + priv->flags |= OTX2_FLAG_INTF_DOWN; + priv->flags |= OTX2_FLAG_REP_MODE_ENABLED; + + hw = &priv->hw; + hw->pdev = pdev; + hw->max_queues = OTX2_MAX_CQ_CNT; + hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN; + hw->xqe_size = 128; + + err = otx2_init_rsrc(pdev, priv); + if (err) + goto err_release_regions; + + priv->iommu_domain = iommu_get_domain_for_dev(dev); + + err = rvu_get_rep_cnt(priv); + if (err) + goto err_detach_rsrc; + + err = otx2_register_dl(priv); + if (err) + goto err_detach_rsrc; + + return 0; + +err_detach_rsrc: + if (priv->hw.lmt_info) + free_percpu(priv->hw.lmt_info); + if (test_bit(CN10K_LMTST, &priv->hw.cap_flag)) + qmem_free(priv->dev, priv->dync_lmt); + otx2_detach_resources(&priv->mbox); + otx2_disable_mbox_intr(priv); + otx2_pfaf_mbox_destroy(priv); + pci_free_irq_vectors(pdev); +err_release_regions: + pci_set_drvdata(pdev, NULL); + pci_release_regions(pdev); + return err; +} + +static void rvu_rep_remove(struct pci_dev *pdev) +{ + struct otx2_nic *priv = pci_get_drvdata(pdev); + + otx2_unregister_dl(priv); + if (!(priv->flags & OTX2_FLAG_INTF_DOWN)) + rvu_rep_destroy(priv); + otx2_detach_resources(&priv->mbox); + if (priv->hw.lmt_info) + free_percpu(priv->hw.lmt_info); + if (test_bit(CN10K_LMTST, &priv->hw.cap_flag)) + qmem_free(priv->dev, priv->dync_lmt); + otx2_disable_mbox_intr(priv); + otx2_pfaf_mbox_destroy(priv); + pci_free_irq_vectors(priv->pdev); + pci_set_drvdata(pdev, NULL); + pci_release_regions(pdev); +} + +static struct pci_driver rvu_rep_driver = { + .name = DRV_NAME, + .id_table = rvu_rep_id_table, + .probe = rvu_rep_probe, + .remove = rvu_rep_remove, + .shutdown = rvu_rep_remove, +}; + +static int __init rvu_rep_init_module(void) +{ + return pci_register_driver(&rvu_rep_driver); +} + +static void __exit rvu_rep_cleanup_module(void) +{ + pci_unregister_driver(&rvu_rep_driver); +} + +module_init(rvu_rep_init_module); +module_exit(rvu_rep_cleanup_module); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.h b/drivers/net/ethernet/marvell/octeontx2/nic/rep.h new file mode 100644 index 000000000000..38446b3e4f13 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell RVU REPRESENTOR driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#ifndef REP_H +#define REP_H + +#include <linux/pci.h> + +#include "otx2_reg.h" +#include "otx2_txrx.h" +#include "otx2_common.h" + +#define PCI_DEVID_RVU_REP 0xA0E0 + +#define RVU_MAX_REP OTX2_MAX_CQ_CNT + +struct rep_stats { + u64 rx_bytes; + u64 rx_frames; + u64 rx_drops; + u64 rx_mcast_frames; + + u64 tx_bytes; + u64 tx_frames; + u64 tx_drops; +}; + +struct rep_dev { + struct otx2_nic *mdev; + struct net_device *netdev; + struct rep_stats stats; + struct delayed_work stats_wrk; + struct devlink_port dl_port; + struct otx2_flow_config *flow_cfg; +#define RVU_REP_VF_INITIALIZED BIT_ULL(0) + u64 flags; + u16 rep_id; + u16 pcifunc; + u8 mac[ETH_ALEN]; +}; + +static inline bool otx2_rep_dev(struct pci_dev *pdev) +{ + return pdev->device == PCI_DEVID_RVU_REP; +} + +int rvu_rep_create(struct otx2_nic *priv, struct netlink_ext_ack *extack); +void rvu_rep_destroy(struct otx2_nic *priv); +int rvu_event_up_notify(struct otx2_nic *pf, struct rep_event *info); +#endif /* REP_H */ diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c index f463a505f5ba..6c683a12d5aa 100644 --- a/drivers/net/ethernet/mediatek/airoha_eth.c +++ b/drivers/net/ethernet/mediatek/airoha_eth.c @@ -752,11 +752,9 @@ struct airoha_tx_irq_queue { struct airoha_qdma *qdma; struct napi_struct napi; - u32 *q; int size; - int queued; - u16 head; + u32 *q; }; struct airoha_hw_stats { @@ -1656,30 +1654,38 @@ static int airoha_qdma_init_rx(struct airoha_qdma *qdma) static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) { struct airoha_tx_irq_queue *irq_q; + int id, done = 0, irq_queued; struct airoha_qdma *qdma; struct airoha_eth *eth; - int id, done = 0; + u32 status, head; irq_q = container_of(napi, struct airoha_tx_irq_queue, napi); qdma = irq_q->qdma; id = irq_q - &qdma->q_tx_irq[0]; eth = qdma->eth; - while (irq_q->queued > 0 && done < budget) { - u32 qid, last, val = irq_q->q[irq_q->head]; + status = airoha_qdma_rr(qdma, REG_IRQ_STATUS(id)); + head = FIELD_GET(IRQ_HEAD_IDX_MASK, status); + head = head % irq_q->size; + irq_queued = FIELD_GET(IRQ_ENTRY_LEN_MASK, status); + + while (irq_queued > 0 && done < budget) { + u32 qid, val = irq_q->q[head]; + struct airoha_qdma_desc *desc; + struct airoha_queue_entry *e; struct airoha_queue *q; + u32 index, desc_ctrl; + struct sk_buff *skb; if (val == 0xff) break; - irq_q->q[irq_q->head] = 0xff; /* mark as done */ - irq_q->head = (irq_q->head + 1) % irq_q->size; - irq_q->queued--; + irq_q->q[head] = 0xff; /* mark as done */ + head = (head + 1) % irq_q->size; + irq_queued--; done++; - last = FIELD_GET(IRQ_DESC_IDX_MASK, val); qid = FIELD_GET(IRQ_RING_IDX_MASK, val); - if (qid >= ARRAY_SIZE(qdma->q_tx)) continue; @@ -1687,46 +1693,53 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) if (!q->ndesc) continue; + index = FIELD_GET(IRQ_DESC_IDX_MASK, val); + if (index >= q->ndesc) + continue; + spin_lock_bh(&q->lock); - while (q->queued > 0) { - struct airoha_qdma_desc *desc = &q->desc[q->tail]; - struct airoha_queue_entry *e = &q->entry[q->tail]; - u32 desc_ctrl = le32_to_cpu(desc->ctrl); - struct sk_buff *skb = e->skb; - u16 index = q->tail; + if (!q->queued) + goto unlock; - if (!(desc_ctrl & QDMA_DESC_DONE_MASK) && - !(desc_ctrl & QDMA_DESC_DROP_MASK)) - break; + desc = &q->desc[index]; + desc_ctrl = le32_to_cpu(desc->ctrl); - q->tail = (q->tail + 1) % q->ndesc; - q->queued--; + if (!(desc_ctrl & QDMA_DESC_DONE_MASK) && + !(desc_ctrl & QDMA_DESC_DROP_MASK)) + goto unlock; - dma_unmap_single(eth->dev, e->dma_addr, e->dma_len, - DMA_TO_DEVICE); + e = &q->entry[index]; + skb = e->skb; - WRITE_ONCE(desc->msg0, 0); - WRITE_ONCE(desc->msg1, 0); + dma_unmap_single(eth->dev, e->dma_addr, e->dma_len, + DMA_TO_DEVICE); + memset(e, 0, sizeof(*e)); + WRITE_ONCE(desc->msg0, 0); + WRITE_ONCE(desc->msg1, 0); + q->queued--; - if (skb) { - u16 queue = skb_get_queue_mapping(skb); - struct netdev_queue *txq; + /* completion ring can report out-of-order indexes if hw QoS + * is enabled and packets with different priority are queued + * to same DMA ring. Take into account possible out-of-order + * reports incrementing DMA ring tail pointer + */ + while (q->tail != q->head && !q->entry[q->tail].dma_addr) + q->tail = (q->tail + 1) % q->ndesc; - txq = netdev_get_tx_queue(skb->dev, queue); - netdev_tx_completed_queue(txq, 1, skb->len); - if (netif_tx_queue_stopped(txq) && - q->ndesc - q->queued >= q->free_thr) - netif_tx_wake_queue(txq); + if (skb) { + u16 queue = skb_get_queue_mapping(skb); + struct netdev_queue *txq; - dev_kfree_skb_any(skb); - e->skb = NULL; - } + txq = netdev_get_tx_queue(skb->dev, queue); + netdev_tx_completed_queue(txq, 1, skb->len); + if (netif_tx_queue_stopped(txq) && + q->ndesc - q->queued >= q->free_thr) + netif_tx_wake_queue(txq); - if (index == last) - break; + dev_kfree_skb_any(skb); } - +unlock: spin_unlock_bh(&q->lock); } @@ -2026,20 +2039,11 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance) if (intr[0] & INT_TX_MASK) { for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) { - struct airoha_tx_irq_queue *irq_q = &qdma->q_tx_irq[i]; - u32 status, head; - if (!(intr[0] & TX_DONE_INT_MASK(i))) continue; airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX0, TX_DONE_INT_MASK(i)); - - status = airoha_qdma_rr(qdma, REG_IRQ_STATUS(i)); - head = FIELD_GET(IRQ_HEAD_IDX_MASK, status); - irq_q->head = head % irq_q->size; - irq_q->queued = FIELD_GET(IRQ_ENTRY_LEN_MASK, status); - napi_schedule(&qdma->q_tx_irq[i].napi); } } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index f01ceee5f02d..53485142938c 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2227,7 +2227,7 @@ rx_done: eth->rx_bytes += bytes; dim_update_sample(eth->rx_events, eth->rx_packets, eth->rx_bytes, &dim_sample); - net_dim(ð->rx_dim, dim_sample); + net_dim(ð->rx_dim, &dim_sample); if (xdp_flush) xdp_do_flush(); @@ -2377,7 +2377,7 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) dim_update_sample(eth->tx_events, eth->tx_packets, eth->tx_bytes, &dim_sample); - net_dim(ð->tx_dim, dim_sample); + net_dim(ð->tx_dim, &dim_sample); if (mtk_queue_stopped(eth) && (atomic_read(&ring->free_count) > ring->thresh)) diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.h b/drivers/net/ethernet/mediatek/mtk_wed_wo.h index 87a67fa3868d..c01b1e8428f6 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_wo.h +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.h @@ -91,8 +91,8 @@ enum mtk_wed_dummy_cr_idx { #define MT7981_FIRMWARE_WO "mediatek/mt7981_wo.bin" #define MT7986_FIRMWARE_WO0 "mediatek/mt7986_wo_0.bin" #define MT7986_FIRMWARE_WO1 "mediatek/mt7986_wo_1.bin" -#define MT7988_FIRMWARE_WO0 "mediatek/mt7988_wo_0.bin" -#define MT7988_FIRMWARE_WO1 "mediatek/mt7988_wo_1.bin" +#define MT7988_FIRMWARE_WO0 "mediatek/mt7988/mt7988_wo_0.bin" +#define MT7988_FIRMWARE_WO1 "mediatek/mt7988/mt7988_wo_1.bin" #define MTK_WO_MCU_CFG_LS_BASE 0 #define MTK_WO_MCU_CFG_LS_HW_VER_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x000) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 5912f7e614f9..be3d0876c521 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -109,35 +109,48 @@ mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/ktls_stats.o \ en_accel/fs_tcp.o en_accel/ktls.o en_accel/ktls_txrx.o \ en_accel/ktls_tx.o en_accel/ktls_rx.o -mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o \ - steering/dr_matcher.o steering/dr_rule.o \ - steering/dr_icm_pool.o steering/dr_buddy.o \ - steering/dr_ste.o steering/dr_send.o \ - steering/dr_ste_v0.o steering/dr_ste_v1.o \ - steering/dr_ste_v2.o \ - steering/dr_cmd.o steering/dr_fw.o \ - steering/dr_action.o steering/fs_dr.o \ - steering/dr_definer.o steering/dr_ptrn.o \ - steering/dr_arg.o steering/dr_dbg.o lib/smfs.o +# +# SW Steering +# +mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/sws/dr_domain.o \ + steering/sws/dr_table.o \ + steering/sws/dr_matcher.o \ + steering/sws/dr_rule.o \ + steering/sws/dr_icm_pool.o \ + steering/sws/dr_buddy.o \ + steering/sws/dr_ste.o \ + steering/sws/dr_send.o \ + steering/sws/dr_ste_v0.o \ + steering/sws/dr_ste_v1.o \ + steering/sws/dr_ste_v2.o \ + steering/sws/dr_cmd.o \ + steering/sws/dr_fw.o \ + steering/sws/dr_action.o \ + steering/sws/dr_definer.o \ + steering/sws/dr_ptrn.o \ + steering/sws/dr_arg.o \ + steering/sws/dr_dbg.o \ + steering/sws/fs_dr.o \ + lib/smfs.o # # HW Steering # -mlx5_core-$(CONFIG_MLX5_HW_STEERING) += steering/hws/mlx5hws_cmd.o \ - steering/hws/mlx5hws_context.o \ - steering/hws/mlx5hws_pat_arg.o \ - steering/hws/mlx5hws_buddy.o \ - steering/hws/mlx5hws_pool.o \ - steering/hws/mlx5hws_table.o \ - steering/hws/mlx5hws_action.o \ - steering/hws/mlx5hws_rule.o \ - steering/hws/mlx5hws_matcher.o \ - steering/hws/mlx5hws_send.o \ - steering/hws/mlx5hws_definer.o \ - steering/hws/mlx5hws_bwc.o \ - steering/hws/mlx5hws_debug.o \ - steering/hws/mlx5hws_vport.o \ - steering/hws/mlx5hws_bwc_complex.o +mlx5_core-$(CONFIG_MLX5_HW_STEERING) += steering/hws/cmd.o \ + steering/hws/context.o \ + steering/hws/pat_arg.o \ + steering/hws/buddy.o \ + steering/hws/pool.o \ + steering/hws/table.o \ + steering/hws/action.o \ + steering/hws/rule.o \ + steering/hws/matcher.o \ + steering/hws/send.o \ + steering/hws/definer.o \ + steering/hws/bwc.o \ + steering/hws/debug.o \ + steering/hws/vport.o \ + steering/hws/bwc_complex.o # diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index 4caa1b6f40ba..1fd403713baf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -71,6 +71,7 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, { unsigned long flags; struct mlx5_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv; + bool schedule_tasklet = false; spin_lock_irqsave(&tasklet_ctx->lock, flags); /* When migrating CQs between EQs will be implemented, please note @@ -80,9 +81,19 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, */ if (list_empty_careful(&cq->tasklet_ctx.list)) { mlx5_cq_hold(cq); + /* If the tasklet CQ work list isn't empty, mlx5_cq_tasklet_cb() + * is scheduled/running and hasn't processed the list yet, so it + * will see this added CQ when it runs. If the list is empty, + * the tasklet needs to be scheduled to pick up the CQ. The + * spinlock avoids any race with the tasklet accessing the list. + */ + schedule_tasklet = list_empty(&tasklet_ctx->list); list_add_tail(&cq->tasklet_ctx.list, &tasklet_ctx->list); } spin_unlock_irqrestore(&tasklet_ctx->lock, flags); + + if (schedule_tasklet) + tasklet_schedule(&tasklet_ctx->task); } /* Callers must verify outbox status in case of err */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c index 904e08de852e..31142f6cc372 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c @@ -166,9 +166,90 @@ static int mlx5_dpll_device_mode_get(const struct dpll_device *dpll, return 0; } +enum { + MLX5_DPLL_SSM_CODE_PRC = 0b0010, + MLX5_DPLL_SSM_CODE_SSU_A = 0b0100, + MLX5_DPLL_SSM_CODE_SSU_B = 0b1000, + MLX5_DPLL_SSM_CODE_EEC1 = 0b1011, + MLX5_DPLL_SSM_CODE_PRTC = 0b0010, + MLX5_DPLL_SSM_CODE_EPRTC = 0b0010, + MLX5_DPLL_SSM_CODE_EEEC = 0b1011, + MLX5_DPLL_SSM_CODE_EPRC = 0b0010, +}; + +enum { + MLX5_DPLL_ENHANCED_SSM_CODE_PRC = 0xff, + MLX5_DPLL_ENHANCED_SSM_CODE_SSU_A = 0xff, + MLX5_DPLL_ENHANCED_SSM_CODE_SSU_B = 0xff, + MLX5_DPLL_ENHANCED_SSM_CODE_EEC1 = 0xff, + MLX5_DPLL_ENHANCED_SSM_CODE_PRTC = 0x20, + MLX5_DPLL_ENHANCED_SSM_CODE_EPRTC = 0x21, + MLX5_DPLL_ENHANCED_SSM_CODE_EEEC = 0x22, + MLX5_DPLL_ENHANCED_SSM_CODE_EPRC = 0x23, +}; + +#define __MLX5_DPLL_SSM_COMBINED_CODE(ssm_code, enhanced_ssm_code) \ + ((ssm_code) | ((enhanced_ssm_code) << 8)) + +#define MLX5_DPLL_SSM_COMBINED_CODE(type) \ + __MLX5_DPLL_SSM_COMBINED_CODE(MLX5_DPLL_SSM_CODE_##type, \ + MLX5_DPLL_ENHANCED_SSM_CODE_##type) + +static int mlx5_dpll_clock_quality_level_get(const struct dpll_device *dpll, + void *priv, unsigned long *qls, + struct netlink_ext_ack *extack) +{ + u8 network_option, ssm_code, enhanced_ssm_code; + u32 out[MLX5_ST_SZ_DW(msecq_reg)] = {}; + u32 in[MLX5_ST_SZ_DW(msecq_reg)] = {}; + struct mlx5_dpll *mdpll = priv; + int err; + + err = mlx5_core_access_reg(mdpll->mdev, in, sizeof(in), + out, sizeof(out), MLX5_REG_MSECQ, 0, 0); + if (err) + return err; + network_option = MLX5_GET(msecq_reg, out, network_option); + if (network_option != 1) + goto errout; + ssm_code = MLX5_GET(msecq_reg, out, local_ssm_code); + enhanced_ssm_code = MLX5_GET(msecq_reg, out, local_enhanced_ssm_code); + + switch (__MLX5_DPLL_SSM_COMBINED_CODE(ssm_code, enhanced_ssm_code)) { + case MLX5_DPLL_SSM_COMBINED_CODE(PRC): + __set_bit(DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_PRC, qls); + return 0; + case MLX5_DPLL_SSM_COMBINED_CODE(SSU_A): + __set_bit(DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_SSU_A, qls); + return 0; + case MLX5_DPLL_SSM_COMBINED_CODE(SSU_B): + __set_bit(DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_SSU_B, qls); + return 0; + case MLX5_DPLL_SSM_COMBINED_CODE(EEC1): + __set_bit(DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_EEC1, qls); + return 0; + case MLX5_DPLL_SSM_COMBINED_CODE(PRTC): + __set_bit(DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_PRTC, qls); + return 0; + case MLX5_DPLL_SSM_COMBINED_CODE(EPRTC): + __set_bit(DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_EPRTC, qls); + return 0; + case MLX5_DPLL_SSM_COMBINED_CODE(EEEC): + __set_bit(DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_EEEC, qls); + return 0; + case MLX5_DPLL_SSM_COMBINED_CODE(EPRC): + __set_bit(DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_EPRC, qls); + return 0; + } +errout: + NL_SET_ERR_MSG_MOD(extack, "Invalid clock quality level obtained from firmware\n"); + return -EINVAL; +} + static const struct dpll_device_ops mlx5_dpll_device_ops = { .lock_status_get = mlx5_dpll_device_lock_status_get, .mode_get = mlx5_dpll_device_mode_get, + .clock_quality_level_get = mlx5_dpll_clock_quality_level_get, }; static int mlx5_dpll_pin_direction_get(const struct dpll_pin *pin, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 57b7298a0e79..979fc56205e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -83,6 +83,7 @@ struct page_pool; #define MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE (8) #define MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE (9) #define MLX5E_SHAMPO_WQ_HEADER_PER_PAGE (PAGE_SIZE >> MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE) +#define MLX5E_SHAMPO_LOG_WQ_HEADER_PER_PAGE (PAGE_SHIFT - MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE) #define MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE (64) #define MLX5E_SHAMPO_WQ_RESRV_SIZE (64 * 1024) #define MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE (4096) @@ -624,16 +625,14 @@ struct mlx5e_dma_info { struct mlx5e_shampo_hd { u32 mkey; - struct mlx5e_dma_info *info; struct mlx5e_frag_page *pages; - u16 curr_page_index; u32 hd_per_wq; u16 hd_per_wqe; + u16 pages_per_wq; unsigned long *bitmap; u16 pi; u16 ci; __be32 key; - u64 last_addr; }; struct mlx5e_hw_gro_data { @@ -755,7 +754,7 @@ struct mlx5e_channel { u8 lag_port; /* XDP_REDIRECT */ - struct mlx5e_xdpsq xdpsq; + struct mlx5e_xdpsq *xdpsq; /* AF_XDP zero-copy */ struct mlx5e_rq xskrq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 4610621a340e..94b291662087 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -865,7 +865,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, if (unlikely(sq_num >= priv->channels.num)) return -ENXIO; - sq = &priv->channels.c[sq_num]->xdpsq; + sq = priv->channels.c[sq_num]->xdpsq; for (i = 0; i < n; i++) { struct mlx5e_xmit_data_frags xdptxdf = {}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f37afa52e2b8..2e27e9d6b820 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -350,19 +350,15 @@ static int mlx5e_rq_shampo_hd_info_alloc(struct mlx5e_rq *rq, int node) shampo->bitmap = bitmap_zalloc_node(shampo->hd_per_wq, GFP_KERNEL, node); - shampo->info = kvzalloc_node(array_size(shampo->hd_per_wq, - sizeof(*shampo->info)), - GFP_KERNEL, node); shampo->pages = kvzalloc_node(array_size(shampo->hd_per_wq, sizeof(*shampo->pages)), GFP_KERNEL, node); - if (!shampo->bitmap || !shampo->info || !shampo->pages) + if (!shampo->bitmap || !shampo->pages) goto err_nomem; return 0; err_nomem: - kvfree(shampo->info); kvfree(shampo->bitmap); kvfree(shampo->pages); @@ -372,7 +368,6 @@ err_nomem: static void mlx5e_rq_shampo_hd_info_free(struct mlx5e_rq *rq) { kvfree(rq->mpwqe.shampo->bitmap); - kvfree(rq->mpwqe.shampo->info); kvfree(rq->mpwqe.shampo->pages); } @@ -767,8 +762,6 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, u32 *pool_size, int node) { - void *wqc = MLX5_ADDR_OF(rqc, rqp->rqc, wq); - int wq_size; int err; if (!test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) @@ -793,9 +786,9 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, cpu_to_be32(rq->mpwqe.shampo->mkey); rq->mpwqe.shampo->hd_per_wqe = mlx5e_shampo_hd_per_wqe(mdev, params, rqp); - wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz)); - *pool_size += (rq->mpwqe.shampo->hd_per_wqe * wq_size) / - MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; + rq->mpwqe.shampo->pages_per_wq = + rq->mpwqe.shampo->hd_per_wq / MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; + *pool_size += rq->mpwqe.shampo->pages_per_wq; return 0; err_hw_gro_data: @@ -2086,6 +2079,44 @@ void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq) mlx5e_free_xdpsq(sq); } +static struct mlx5e_xdpsq *mlx5e_open_xdpredirect_sq(struct mlx5e_channel *c, + struct mlx5e_params *params, + struct mlx5e_channel_param *cparam, + struct mlx5e_create_cq_param *ccp) +{ + struct mlx5e_xdpsq *xdpsq; + int err; + + xdpsq = kvzalloc_node(sizeof(*xdpsq), GFP_KERNEL, c->cpu); + if (!xdpsq) + return ERR_PTR(-ENOMEM); + + err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, + &cparam->xdp_sq.cqp, ccp, &xdpsq->cq); + if (err) + goto err_free_xdpsq; + + err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL, xdpsq, true); + if (err) + goto err_close_xdpsq_cq; + + return xdpsq; + +err_close_xdpsq_cq: + mlx5e_close_cq(&xdpsq->cq); +err_free_xdpsq: + kvfree(xdpsq); + + return ERR_PTR(err); +} + +static void mlx5e_close_xdpredirect_sq(struct mlx5e_xdpsq *xdpsq) +{ + mlx5e_close_xdpsq(xdpsq); + mlx5e_close_cq(&xdpsq->cq); + kvfree(xdpsq); +} + static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev, struct net_device *netdev, struct workqueue_struct *workqueue, @@ -2476,6 +2507,7 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_channel_param *cparam) { + const struct net_device_ops *netdev_ops = c->netdev->netdev_ops; struct dim_cq_moder icocq_moder = {0, 0}; struct mlx5e_create_cq_param ccp; int err; @@ -2496,15 +2528,18 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, if (err) goto err_close_icosq_cq; - err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp, - &c->xdpsq.cq); - if (err) - goto err_close_tx_cqs; + if (netdev_ops->ndo_xdp_xmit) { + c->xdpsq = mlx5e_open_xdpredirect_sq(c, params, cparam, &ccp); + if (IS_ERR(c->xdpsq)) { + err = PTR_ERR(c->xdpsq); + goto err_close_tx_cqs; + } + } err = mlx5e_open_cq(c->mdev, params->rx_cq_moderation, &cparam->rq.cqp, &ccp, &c->rq.cq); if (err) - goto err_close_xdp_tx_cqs; + goto err_close_xdpredirect_sq; err = c->xdp ? mlx5e_open_cq(c->mdev, params->tx_cq_moderation, &cparam->xdp_sq.cqp, &ccp, &c->rq_xdpsq.cq) : 0; @@ -2516,7 +2551,7 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq, mlx5e_async_icosq_err_cqe_work); if (err) - goto err_close_xdpsq_cq; + goto err_close_rq_xdpsq_cq; mutex_init(&c->icosq_recovery_lock); @@ -2540,16 +2575,8 @@ static int mlx5e_open_queues(struct mlx5e_channel *c, goto err_close_rq; } - err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL, &c->xdpsq, true); - if (err) - goto err_close_xdp_sq; - return 0; -err_close_xdp_sq: - if (c->xdp) - mlx5e_close_xdpsq(&c->rq_xdpsq); - err_close_rq: mlx5e_close_rq(&c->rq); @@ -2562,15 +2589,16 @@ err_close_icosq: err_close_async_icosq: mlx5e_close_icosq(&c->async_icosq); -err_close_xdpsq_cq: +err_close_rq_xdpsq_cq: if (c->xdp) mlx5e_close_cq(&c->rq_xdpsq.cq); err_close_rx_cq: mlx5e_close_cq(&c->rq.cq); -err_close_xdp_tx_cqs: - mlx5e_close_cq(&c->xdpsq.cq); +err_close_xdpredirect_sq: + if (c->xdpsq) + mlx5e_close_xdpredirect_sq(c->xdpsq); err_close_tx_cqs: mlx5e_close_tx_cqs(c); @@ -2586,7 +2614,6 @@ err_close_async_icosq_cq: static void mlx5e_close_queues(struct mlx5e_channel *c) { - mlx5e_close_xdpsq(&c->xdpsq); if (c->xdp) mlx5e_close_xdpsq(&c->rq_xdpsq); /* The same ICOSQ is used for UMRs for both RQ and XSKRQ. */ @@ -2599,7 +2626,8 @@ static void mlx5e_close_queues(struct mlx5e_channel *c) if (c->xdp) mlx5e_close_cq(&c->rq_xdpsq.cq); mlx5e_close_cq(&c->rq.cq); - mlx5e_close_cq(&c->xdpsq.cq); + if (c->xdpsq) + mlx5e_close_xdpredirect_sq(c->xdpsq); mlx5e_close_tx_cqs(c); mlx5e_close_cq(&c->icosq.cq); mlx5e_close_cq(&c->async_icosq.cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 92094bf60d59..554f9cb5b53f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -600,7 +600,8 @@ mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) if (c->xdp) sqs[num_sqs++] = c->rq_xdpsq.sqn; - sqs[num_sqs++] = c->xdpsq.sqn; + if (c->xdpsq) + sqs[num_sqs++] = c->xdpsq->sqn; } } if (ptp_sq) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index d81083f4f316..1963bc5adb18 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -643,83 +643,82 @@ static void build_ksm_umr(struct mlx5e_icosq *sq, struct mlx5e_umr_wqe *umr_wqe, umr_wqe->uctrl.mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE); } +static struct mlx5e_frag_page *mlx5e_shampo_hd_to_frag_page(struct mlx5e_rq *rq, int header_index) +{ + BUILD_BUG_ON(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE > PAGE_SHIFT); + + return &rq->mpwqe.shampo->pages[header_index >> MLX5E_SHAMPO_LOG_WQ_HEADER_PER_PAGE]; +} + +static u64 mlx5e_shampo_hd_offset(int header_index) +{ + return (header_index & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) << + MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE; +} + +static void mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index); + static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, struct mlx5e_icosq *sq, u16 ksm_entries, u16 index) { struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; - u16 entries, pi, header_offset, err, wqe_bbs, new_entries; + u16 pi, header_offset, err, wqe_bbs; u32 lkey = rq->mdev->mlx5e_res.hw_objs.mkey; - u16 page_index = shampo->curr_page_index; - struct mlx5e_frag_page *frag_page; - u64 addr = shampo->last_addr; - struct mlx5e_dma_info *dma_info; struct mlx5e_umr_wqe *umr_wqe; - int headroom, i; + int headroom, i = 0; headroom = rq->buff.headroom; - new_entries = ksm_entries - (shampo->pi & (MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT - 1)); - entries = ALIGN(ksm_entries, MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT); - wqe_bbs = MLX5E_KSM_UMR_WQEBBS(entries); + wqe_bbs = MLX5E_KSM_UMR_WQEBBS(ksm_entries); pi = mlx5e_icosq_get_next_pi(sq, wqe_bbs); umr_wqe = mlx5_wq_cyc_get_wqe(&sq->wq, pi); - build_ksm_umr(sq, umr_wqe, shampo->key, index, entries); + build_ksm_umr(sq, umr_wqe, shampo->key, index, ksm_entries); - frag_page = &shampo->pages[page_index]; + WARN_ON_ONCE(ksm_entries & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)); + while (i < ksm_entries) { + struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index); + u64 addr; - for (i = 0; i < entries; i++, index++) { - dma_info = &shampo->info[index]; - if (i >= ksm_entries || (index < shampo->pi && shampo->pi - index < - MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT)) - goto update_ksm; - header_offset = (index & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) << - MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE; - if (!(header_offset & (PAGE_SIZE - 1))) { - page_index = (page_index + 1) & (shampo->hd_per_wq - 1); - frag_page = &shampo->pages[page_index]; + err = mlx5e_page_alloc_fragmented(rq, frag_page); + if (unlikely(err)) + goto err_unmap; - err = mlx5e_page_alloc_fragmented(rq, frag_page); - if (unlikely(err)) - goto err_unmap; - addr = page_pool_get_dma_addr(frag_page->page); + addr = page_pool_get_dma_addr(frag_page->page); - dma_info->addr = addr; - dma_info->frag_page = frag_page; - } else { - dma_info->addr = addr + header_offset; - dma_info->frag_page = frag_page; - } + for (int j = 0; j < MLX5E_SHAMPO_WQ_HEADER_PER_PAGE; j++) { + header_offset = mlx5e_shampo_hd_offset(index++); -update_ksm: - umr_wqe->inline_ksms[i] = (struct mlx5_ksm) { - .key = cpu_to_be32(lkey), - .va = cpu_to_be64(dma_info->addr + headroom), - }; + umr_wqe->inline_ksms[i++] = (struct mlx5_ksm) { + .key = cpu_to_be32(lkey), + .va = cpu_to_be64(addr + header_offset + headroom), + }; + } } sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) { .wqe_type = MLX5E_ICOSQ_WQE_SHAMPO_HD_UMR, .num_wqebbs = wqe_bbs, - .shampo.len = new_entries, + .shampo.len = ksm_entries, }; - shampo->pi = (shampo->pi + new_entries) & (shampo->hd_per_wq - 1); - shampo->curr_page_index = page_index; - shampo->last_addr = addr; + shampo->pi = (shampo->pi + ksm_entries) & (shampo->hd_per_wq - 1); sq->pc += wqe_bbs; sq->doorbell_cseg = &umr_wqe->ctrl; return 0; err_unmap: - while (--i >= 0) { - dma_info = &shampo->info[--index]; - if (!(i & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1))) { - dma_info->addr = ALIGN_DOWN(dma_info->addr, PAGE_SIZE); - mlx5e_page_release_fragmented(rq, dma_info->frag_page); + while (--i) { + --index; + header_offset = mlx5e_shampo_hd_offset(index); + if (!header_offset) { + struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, index); + + mlx5e_page_release_fragmented(rq, frag_page); } } + rq->stats->buff_alloc_err++; return err; } @@ -731,7 +730,8 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq) struct mlx5e_icosq *sq = rq->icosq; int i, err, max_ksm_entries, len; - max_ksm_entries = MLX5E_MAX_KSM_PER_WQE(rq->mdev); + max_ksm_entries = ALIGN_DOWN(MLX5E_MAX_KSM_PER_WQE(rq->mdev), + MLX5E_SHAMPO_WQ_HEADER_PER_PAGE); ksm_entries = bitmap_find_window(shampo->bitmap, shampo->hd_per_wqe, shampo->hd_per_wq, shampo->pi); @@ -739,8 +739,8 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq) if (!ksm_entries) return 0; - ksm_entries += (shampo->pi & (MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT - 1)); - index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT); + /* pi is aligned to MLX5E_SHAMPO_WQ_HEADER_PER_PAGE */ + index = shampo->pi; entries_before = shampo->hd_per_wq - index; if (unlikely(entries_before < ksm_entries)) @@ -851,13 +851,11 @@ static void mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index) { struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; - u64 addr = shampo->info[header_index].addr; if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) { - struct mlx5e_dma_info *dma_info = &shampo->info[header_index]; + struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index); - dma_info->addr = ALIGN_DOWN(addr, PAGE_SIZE); - mlx5e_page_release_fragmented(rq, dma_info->frag_page); + mlx5e_page_release_fragmented(rq, frag_page); } clear_bit(header_index, shampo->bitmap); } @@ -1211,10 +1209,10 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, static void *mlx5e_shampo_get_packet_hd(struct mlx5e_rq *rq, u16 header_index) { - struct mlx5e_dma_info *last_head = &rq->mpwqe.shampo->info[header_index]; - u16 head_offset = (last_head->addr & (PAGE_SIZE - 1)) + rq->buff.headroom; + struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index); + u16 head_offset = mlx5e_shampo_hd_offset(header_index) + rq->buff.headroom; - return page_address(last_head->frag_page->page) + head_offset; + return page_address(frag_page->page) + head_offset; } static void mlx5e_shampo_update_ipv4_udp_hdr(struct mlx5e_rq *rq, struct iphdr *ipv4) @@ -2185,29 +2183,30 @@ static struct sk_buff * mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct mlx5_cqe64 *cqe, u16 header_index) { - struct mlx5e_dma_info *head = &rq->mpwqe.shampo->info[header_index]; - u16 head_offset = head->addr & (PAGE_SIZE - 1); + struct mlx5e_frag_page *frag_page = mlx5e_shampo_hd_to_frag_page(rq, header_index); + dma_addr_t page_dma_addr = page_pool_get_dma_addr(frag_page->page); + u16 head_offset = mlx5e_shampo_hd_offset(header_index); + dma_addr_t dma_addr = page_dma_addr + head_offset; u16 head_size = cqe->shampo.header_size; u16 rx_headroom = rq->buff.headroom; struct sk_buff *skb = NULL; void *hdr, *data; u32 frag_size; - hdr = page_address(head->frag_page->page) + head_offset; + hdr = page_address(frag_page->page) + head_offset; data = hdr + rx_headroom; frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + head_size); if (likely(frag_size <= BIT(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE))) { /* build SKB around header */ - dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, rq->buff.map_dir); + dma_sync_single_range_for_cpu(rq->pdev, dma_addr, 0, frag_size, rq->buff.map_dir); net_prefetchw(hdr); net_prefetch(data); skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size, 0); - if (unlikely(!skb)) return NULL; - head->frag_page->frags++; + frag_page->frags++; } else { /* allocate SKB and copy header for large header */ rq->stats->gro_large_hds++; @@ -2219,7 +2218,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, } net_prefetchw(skb->data); - mlx5e_copy_skb_header(rq, skb, head->frag_page->page, head->addr, + mlx5e_copy_skb_header(rq, skb, frag_page->page, dma_addr, head_offset + rx_headroom, rx_headroom, head_size); /* skb linear part was allocated with headlen and aligned to long */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 5873fde65c2e..76108299ea57 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -55,7 +55,7 @@ static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq) return; dim_update_sample(sq->cq.event_ctr, stats->packets, stats->bytes, &dim_sample); - net_dim(sq->dim, dim_sample); + net_dim(sq->dim, &dim_sample); } static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq) @@ -67,7 +67,7 @@ static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq) return; dim_update_sample(rq->cq.event_ctr, stats->packets, stats->bytes, &dim_sample); - net_dim(rq->dim, dim_sample); + net_dim(rq->dim, &dim_sample); } void mlx5e_trigger_irq(struct mlx5e_icosq *sq) @@ -165,7 +165,8 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) if (unlikely(!budget)) goto out; - busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq); + if (c->xdpsq) + busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq->cq); if (c->xdp) busy |= mlx5e_poll_xdpsq_cq(&c->rq_xdpsq.cq); @@ -236,7 +237,8 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) mlx5e_cq_arm(&rq->cq); mlx5e_cq_arm(&c->icosq.cq); mlx5e_cq_arm(&c->async_icosq.cq); - mlx5e_cq_arm(&c->xdpsq.cq); + if (c->xdpsq) + mlx5e_cq_arm(&c->xdpsq->cq); if (xsk_open) { mlx5e_handle_rx_dim(xskrq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 859dcf09b770..2b229b6226c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -114,10 +114,10 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, struct mlx5_eq *eq = &eq_comp->core; struct mlx5_eqe *eqe; int num_eqes = 0; - u32 cqn = -1; while ((eqe = next_eqe_sw(eq))) { struct mlx5_core_cq *cq; + u32 cqn; /* Make sure we read EQ entry contents after we've * checked the ownership bit. @@ -144,9 +144,6 @@ static int mlx5_eq_comp_int(struct notifier_block *nb, eq_update_ci(eq, 1); - if (cqn != -1) - tasklet_schedule(&eq_comp->tasklet_ctx.task); - return 0; } @@ -804,15 +801,8 @@ EXPORT_SYMBOL(mlx5_eq_get_eqe); void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm) { - __be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2); - u32 val; - eq->cons_index += cc; - val = (eq->cons_index & 0xffffff) | (eq->eqn << 24); - - __raw_writel((__force u32)cpu_to_be32(val), addr); - /* We still want ordering, just not swabbing, so add a barrier */ - wmb(); + eq_update_ci(eq, arm); } EXPORT_SYMBOL(mlx5_eq_update_ci); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index d0f38818363f..982fe3714683 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -195,7 +195,7 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_vport *vport) return; dl_port = vport->dl_port; - mlx5_esw_qos_vport_update_node(vport, NULL, NULL); + mlx5_esw_qos_vport_update_parent(vport, NULL, NULL); devl_rate_leaf_destroy(&dl_port->dl_port); devl_port_unregister(&dl_port->dl_port); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 7e7f99b38a37..8b7c843446e1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -101,6 +101,12 @@ esw_qos_node_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_ node->esw = parent->esw; } +void mlx5_esw_qos_vport_qos_free(struct mlx5_vport *vport) +{ + kfree(vport->qos.sched_node); + memset(&vport->qos, 0, sizeof(vport->qos)); +} + u32 mlx5_esw_qos_vport_get_sched_elem_ix(const struct mlx5_vport *vport) { if (!vport->qos.sched_node) @@ -118,18 +124,49 @@ mlx5_esw_qos_vport_get_parent(const struct mlx5_vport *vport) return vport->qos.sched_node->parent; } -static void esw_qos_sched_elem_config_warn(struct mlx5_esw_sched_node *node, int err) +static void esw_qos_sched_elem_warn(struct mlx5_esw_sched_node *node, int err, const char *op) { if (node->vport) { esw_warn(node->esw->dev, - "E-Switch modify %s scheduling element failed (vport=%d,err=%d)\n", - sched_node_type_str[node->type], node->vport->vport, err); + "E-Switch %s %s scheduling element failed (vport=%d,err=%d)\n", + op, sched_node_type_str[node->type], node->vport->vport, err); return; } esw_warn(node->esw->dev, - "E-Switch modify %s scheduling element failed (err=%d)\n", - sched_node_type_str[node->type], err); + "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, + struct netlink_ext_ack *extack) +{ + int err; + + err = mlx5_create_scheduling_element_cmd(node->esw->dev, SCHEDULING_HIERARCHY_E_SWITCH, ctx, + &node->ix); + if (err) { + esw_qos_sched_elem_warn(node, err, "create"); + NL_SET_ERR_MSG_MOD(extack, "E-Switch create scheduling element failed"); + } + + return err; +} + +static int esw_qos_node_destroy_sched_element(struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack) +{ + int err; + + err = mlx5_destroy_scheduling_element_cmd(node->esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + node->ix); + if (err) { + esw_qos_sched_elem_warn(node, err, "destroy"); + NL_SET_ERR_MSG_MOD(extack, "E-Switch destroying scheduling element failed."); + } + + return err; } static int esw_qos_sched_elem_config(struct mlx5_esw_sched_node *node, u32 max_rate, u32 bw_share, @@ -143,10 +180,21 @@ static int esw_qos_sched_elem_config(struct mlx5_esw_sched_node *node, u32 max_r if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) return -EOPNOTSUPP; - MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate); - MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share); - bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW; - bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE; + if (bw_share && (!MLX5_CAP_QOS(dev, esw_bw_share) || + MLX5_CAP_QOS(dev, max_tsar_bw_share) < MLX5_MIN_BW_SHARE)) + return -EOPNOTSUPP; + + if (node->max_rate == max_rate && node->bw_share == bw_share) + return 0; + + if (node->max_rate != max_rate) { + MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate); + bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW; + } + if (node->bw_share != bw_share) { + MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share); + bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE; + } err = mlx5_modify_scheduling_element_cmd(dev, SCHEDULING_HIERARCHY_E_SWITCH, @@ -154,12 +202,14 @@ static int esw_qos_sched_elem_config(struct mlx5_esw_sched_node *node, u32 max_r node->ix, bitmask); if (err) { - esw_qos_sched_elem_config_warn(node, err); + esw_qos_sched_elem_warn(node, err, "modify"); NL_SET_ERR_MSG_MOD(extack, "E-Switch modify scheduling element failed"); return err; } + node->max_rate = max_rate; + node->bw_share = bw_share; if (node->type == SCHED_NODE_TYPE_VPORTS_TSAR) trace_mlx5_esw_node_qos_config(dev, node, node->ix, bw_share, max_rate); else if (node->type == SCHED_NODE_TYPE_VPORT) @@ -208,166 +258,51 @@ static u32 esw_qos_calc_bw_share(u32 min_rate, u32 divider, u32 fw_max) return min_t(u32, max_t(u32, DIV_ROUND_UP(min_rate, divider), MLX5_MIN_BW_SHARE), fw_max); } -static int esw_qos_update_sched_node_bw_share(struct mlx5_esw_sched_node *node, - u32 divider, - struct netlink_ext_ack *extack) +static void esw_qos_update_sched_node_bw_share(struct mlx5_esw_sched_node *node, + u32 divider, + struct netlink_ext_ack *extack) { u32 fw_max_bw_share = MLX5_CAP_QOS(node->esw->dev, max_tsar_bw_share); u32 bw_share; - int err; bw_share = esw_qos_calc_bw_share(node->min_rate, divider, fw_max_bw_share); - if (bw_share == node->bw_share) - return 0; - - err = esw_qos_sched_elem_config(node, node->max_rate, bw_share, extack); - if (err) - return err; - - node->bw_share = bw_share; - - return err; + esw_qos_sched_elem_config(node, node->max_rate, bw_share, extack); } -static int esw_qos_normalize_min_rate(struct mlx5_eswitch *esw, - struct mlx5_esw_sched_node *parent, - struct netlink_ext_ack *extack) +static void esw_qos_normalize_min_rate(struct mlx5_eswitch *esw, + struct mlx5_esw_sched_node *parent, + struct netlink_ext_ack *extack) { struct list_head *nodes = parent ? &parent->children : &esw->qos.domain->nodes; u32 divider = esw_qos_calculate_min_rate_divider(esw, parent); struct mlx5_esw_sched_node *node; list_for_each_entry(node, nodes, entry) { - int err; - if (node->esw != esw || node->ix == esw->qos.root_tsar_ix) continue; - err = esw_qos_update_sched_node_bw_share(node, divider, extack); - if (err) - return err; + esw_qos_update_sched_node_bw_share(node, divider, extack); if (list_empty(&node->children)) continue; - err = esw_qos_normalize_min_rate(node->esw, node, extack); - if (err) - return err; + esw_qos_normalize_min_rate(node->esw, node, extack); } - - return 0; -} - -static int esw_qos_set_vport_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; - u32 fw_max_bw_share, previous_min_rate; - bool min_rate_supported; - int err; - - esw_assert_qos_lock_held(vport_node->esw); - fw_max_bw_share = MLX5_CAP_QOS(vport->dev, max_tsar_bw_share); - min_rate_supported = MLX5_CAP_QOS(vport->dev, esw_bw_share) && - fw_max_bw_share >= MLX5_MIN_BW_SHARE; - if (min_rate && !min_rate_supported) - return -EOPNOTSUPP; - if (min_rate == vport_node->min_rate) - return 0; - - previous_min_rate = vport_node->min_rate; - vport_node->min_rate = min_rate; - err = esw_qos_normalize_min_rate(vport_node->parent->esw, vport_node->parent, extack); - if (err) - vport_node->min_rate = previous_min_rate; - - return err; -} - -static int esw_qos_set_vport_max_rate(struct mlx5_vport *vport, - u32 max_rate, struct netlink_ext_ack *extack) -{ - struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; - u32 act_max_rate = max_rate; - bool max_rate_supported; - int err; - - esw_assert_qos_lock_held(vport_node->esw); - max_rate_supported = MLX5_CAP_QOS(vport->dev, esw_rate_limit); - - if (max_rate && !max_rate_supported) - return -EOPNOTSUPP; - if (max_rate == vport_node->max_rate) - return 0; - - /* Use parent node limit if new max rate is 0. */ - if (!max_rate) - act_max_rate = vport_node->parent->max_rate; - - err = esw_qos_sched_elem_config(vport_node, act_max_rate, vport_node->bw_share, extack); - if (!err) - vport_node->max_rate = max_rate; - - return err; } static int esw_qos_set_node_min_rate(struct mlx5_esw_sched_node *node, u32 min_rate, struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = node->esw; - u32 previous_min_rate; - int err; - - if (!MLX5_CAP_QOS(esw->dev, esw_bw_share) || - MLX5_CAP_QOS(esw->dev, max_tsar_bw_share) < MLX5_MIN_BW_SHARE) - return -EOPNOTSUPP; if (min_rate == node->min_rate) return 0; - previous_min_rate = node->min_rate; node->min_rate = min_rate; - err = esw_qos_normalize_min_rate(esw, NULL, extack); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "E-Switch node min rate setting failed"); - - /* Attempt restoring previous configuration */ - node->min_rate = previous_min_rate; - if (esw_qos_normalize_min_rate(esw, NULL, extack)) - NL_SET_ERR_MSG_MOD(extack, "E-Switch BW share restore failed"); - } + esw_qos_normalize_min_rate(esw, node->parent, extack); - return err; -} - -static int esw_qos_set_node_max_rate(struct mlx5_esw_sched_node *node, - u32 max_rate, struct netlink_ext_ack *extack) -{ - struct mlx5_esw_sched_node *vport_node; - int err; - - if (node->max_rate == max_rate) - return 0; - - err = esw_qos_sched_elem_config(node, max_rate, node->bw_share, extack); - if (err) - return err; - - node->max_rate = max_rate; - - /* Any unlimited vports in the node should be set with the value of the node. */ - list_for_each_entry(vport_node, &node->children, entry) { - if (vport_node->max_rate) - continue; - - err = esw_qos_sched_elem_config(vport_node, max_rate, vport_node->bw_share, extack); - if (err) - NL_SET_ERR_MSG_MOD(extack, - "E-Switch vport implicit rate limit setting failed"); - } - - return err; + return 0; } static int esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_element_id, @@ -397,14 +332,12 @@ static int esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_ tsar_ix); } -static int -esw_qos_vport_create_sched_element(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent, - u32 max_rate, u32 bw_share, u32 *sched_elem_ix) +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 = parent->esw->dev; + struct mlx5_core_dev *dev = vport_node->esw->dev; void *attr; - int err; if (!mlx5_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT, @@ -414,93 +347,11 @@ esw_qos_vport_create_sched_element(struct mlx5_vport *vport, struct mlx5_esw_sch 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->vport); - MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent->ix); - MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate); - MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share); - - err = mlx5_create_scheduling_element_cmd(dev, - SCHEDULING_HIERARCHY_E_SWITCH, - sched_ctx, - sched_elem_ix); - if (err) { - esw_warn(dev, - "E-Switch create vport scheduling element failed (vport=%d,err=%d)\n", - vport->vport, err); - return err; - } - - return 0; -} - -static int esw_qos_update_node_scheduling_element(struct mlx5_vport *vport, - struct mlx5_esw_sched_node *curr_node, - struct mlx5_esw_sched_node *new_node, - struct netlink_ext_ack *extack) -{ - struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; - u32 max_rate; - int err; - - err = mlx5_destroy_scheduling_element_cmd(curr_node->esw->dev, - SCHEDULING_HIERARCHY_E_SWITCH, - vport_node->ix); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy vport scheduling element failed"); - return err; - } - - /* Use new node max rate if vport max rate is unlimited. */ - max_rate = vport_node->max_rate ? vport_node->max_rate : new_node->max_rate; - err = esw_qos_vport_create_sched_element(vport, new_node, max_rate, - vport_node->bw_share, - &vport_node->ix); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "E-Switch vport node set failed."); - goto err_sched; - } - - esw_qos_node_set_parent(vport->qos.sched_node, new_node); - - return 0; - -err_sched: - max_rate = vport_node->max_rate ? vport_node->max_rate : curr_node->max_rate; - if (esw_qos_vport_create_sched_element(vport, curr_node, max_rate, - vport_node->bw_share, - &vport_node->ix)) - esw_warn(curr_node->esw->dev, "E-Switch vport node restore failed (vport=%d)\n", - vport->vport); + 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); - return err; -} - -static int esw_qos_vport_update_node(struct mlx5_vport *vport, - struct mlx5_esw_sched_node *node, - struct netlink_ext_ack *extack) -{ - struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; - struct mlx5_eswitch *esw = vport->dev->priv.eswitch; - struct mlx5_esw_sched_node *new_node, *curr_node; - int err; - - esw_assert_qos_lock_held(esw); - curr_node = vport_node->parent; - new_node = node ?: esw->qos.node0; - if (curr_node == new_node) - return 0; - - err = esw_qos_update_node_scheduling_element(vport, curr_node, new_node, extack); - if (err) - return err; - - /* Recalculate bw share weights of old and new nodes */ - if (vport_node->bw_share || new_node->bw_share) { - esw_qos_normalize_min_rate(curr_node->esw, curr_node, extack); - esw_qos_normalize_min_rate(new_node->esw, new_node, extack); - } - - return 0; + return esw_qos_node_create_sched_element(vport_node, sched_ctx, extack); } static struct mlx5_esw_sched_node * @@ -531,6 +382,12 @@ static void __esw_qos_free_node(struct mlx5_esw_sched_node *node) kfree(node); } +static void esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netlink_ext_ack *extack) +{ + esw_qos_node_destroy_sched_element(node, extack); + __esw_qos_free_node(node); +} + 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) @@ -552,17 +409,11 @@ __esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sch goto err_alloc_node; } - err = esw_qos_normalize_min_rate(esw, NULL, extack); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "E-Switch nodes normalization failed"); - goto err_min_rate; - } + esw_qos_normalize_min_rate(esw, NULL, extack); trace_mlx5_esw_node_qos_create(esw->dev, node, node->ix); return node; -err_min_rate: - __esw_qos_free_node(node); err_alloc_node: if (mlx5_destroy_scheduling_element_cmd(esw->dev, SCHEDULING_HIERARCHY_E_SWITCH, @@ -595,26 +446,13 @@ esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct netlink_ext_ac return node; } -static int __esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netlink_ext_ack *extack) +static void __esw_qos_destroy_node(struct mlx5_esw_sched_node *node, struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw = node->esw; - int err; trace_mlx5_esw_node_qos_destroy(esw->dev, node, node->ix); - - err = mlx5_destroy_scheduling_element_cmd(esw->dev, - SCHEDULING_HIERARCHY_E_SWITCH, - node->ix); - if (err) - NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR_ID failed"); - __esw_qos_free_node(node); - - err = esw_qos_normalize_min_rate(esw, NULL, extack); - if (err) - NL_SET_ERR_MSG_MOD(extack, "E-Switch nodes normalization failed"); - - - return err; + esw_qos_destroy_node(node, extack); + esw_qos_normalize_min_rate(esw, NULL, extack); } static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) @@ -699,45 +537,62 @@ static void esw_qos_put(struct mlx5_eswitch *esw) esw_qos_destroy(esw); } -static int esw_qos_vport_enable(struct mlx5_vport *vport, - u32 max_rate, u32 bw_share, struct netlink_ext_ack *extack) +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; + + esw_qos_node_destroy_sched_element(vport_node, extack); + + vport_node->bw_share = 0; + list_del_init(&vport_node->entry); + esw_qos_normalize_min_rate(parent->esw, parent, extack); + + 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, + struct netlink_ext_ack *extack) { - struct mlx5_eswitch *esw = vport->dev->priv.eswitch; - u32 sched_elem_ix; int err; - esw_assert_qos_lock_held(esw); - if (vport->qos.sched_node) - return 0; + esw_assert_qos_lock_held(vport->dev->priv.eswitch); - err = esw_qos_get(esw, extack); + esw_qos_node_set_parent(vport->qos.sched_node, parent); + err = esw_qos_vport_create_sched_element(vport->qos.sched_node, extack); if (err) return err; - err = esw_qos_vport_create_sched_element(vport, esw->qos.node0, max_rate, bw_share, - &sched_elem_ix); - if (err) - goto err_out; + esw_qos_normalize_min_rate(parent->esw, parent, extack); - vport->qos.sched_node = __esw_qos_alloc_node(esw, sched_elem_ix, SCHED_NODE_TYPE_VPORT, - esw->qos.node0); - if (!vport->qos.sched_node) { - err = -ENOMEM; - goto err_alloc; - } + return 0; +} - vport->qos.sched_node->vport = vport; +static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_type type, + struct mlx5_esw_sched_node *parent, u32 max_rate, + u32 min_rate, struct netlink_ext_ack *extack) +{ + struct mlx5_eswitch *esw = vport->dev->priv.eswitch; + struct mlx5_esw_sched_node *sched_node; + int err; - trace_mlx5_esw_vport_qos_create(vport->dev, vport, bw_share, max_rate); + esw_assert_qos_lock_held(esw); + err = esw_qos_get(esw, extack); + if (err) + return err; - return 0; + parent = parent ?: esw->qos.node0; + sched_node = __esw_qos_alloc_node(parent->esw, 0, type, parent); + if (!sched_node) + return -ENOMEM; -err_alloc: - if (mlx5_destroy_scheduling_element_cmd(esw->dev, - SCHEDULING_HIERARCHY_E_SWITCH, sched_elem_ix)) - esw_warn(esw->dev, "E-Switch destroy vport scheduling element failed.\n"); -err_out: - esw_qos_put(esw); + sched_node->max_rate = max_rate; + sched_node->min_rate = min_rate; + sched_node->vport = vport; + vport->qos.sched_node = sched_node; + err = esw_qos_vport_enable(vport, parent, extack); + if (err) + esw_qos_put(esw); return err; } @@ -745,51 +600,61 @@ err_out: void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport) { struct mlx5_eswitch *esw = vport->dev->priv.eswitch; - struct mlx5_esw_sched_node *vport_node; - struct mlx5_core_dev *dev; - int err; + struct mlx5_esw_sched_node *parent; lockdep_assert_held(&esw->state_lock); esw_qos_lock(esw); - vport_node = vport->qos.sched_node; - if (!vport_node) + if (!vport->qos.sched_node) goto unlock; - WARN(vport_node->parent != esw->qos.node0, - "Disabling QoS on port before detaching it from node"); - dev = vport_node->esw->dev; - trace_mlx5_esw_vport_qos_destroy(dev, vport); - - err = mlx5_destroy_scheduling_element_cmd(dev, - SCHEDULING_HIERARCHY_E_SWITCH, - vport_node->ix); - if (err) - esw_warn(dev, - "E-Switch destroy vport scheduling element failed (vport=%d,err=%d)\n", - vport->vport, err); - - __esw_qos_free_node(vport_node); - memset(&vport->qos, 0, sizeof(vport->qos)); + parent = vport->qos.sched_node->parent; + WARN(parent != esw->qos.node0, "Disabling QoS on port before detaching it from node"); + esw_qos_vport_disable(vport, NULL); + mlx5_esw_qos_vport_qos_free(vport); esw_qos_put(esw); unlock: esw_qos_unlock(esw); } +static int mlx5_esw_qos_set_vport_max_rate(struct mlx5_vport *vport, u32 max_rate, + struct netlink_ext_ack *extack) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + + esw_assert_qos_lock_held(vport->dev->priv.eswitch); + + if (!vport_node) + return mlx5_esw_qos_vport_enable(vport, SCHED_NODE_TYPE_VPORT, NULL, max_rate, 0, + extack); + else + return esw_qos_sched_elem_config(vport_node, max_rate, vport_node->bw_share, + extack); +} + +static int mlx5_esw_qos_set_vport_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; + + esw_assert_qos_lock_held(vport->dev->priv.eswitch); + + if (!vport_node) + return mlx5_esw_qos_vport_enable(vport, SCHED_NODE_TYPE_VPORT, NULL, 0, min_rate, + extack); + else + return esw_qos_set_node_min_rate(vport_node, min_rate, extack); +} + int mlx5_esw_qos_set_vport_rate(struct mlx5_vport *vport, u32 max_rate, u32 min_rate) { struct mlx5_eswitch *esw = vport->dev->priv.eswitch; int err; esw_qos_lock(esw); - err = esw_qos_vport_enable(vport, 0, 0, NULL); - if (err) - goto unlock; - - err = esw_qos_set_vport_min_rate(vport, min_rate, NULL); + err = mlx5_esw_qos_set_vport_min_rate(vport, min_rate, NULL); if (!err) - err = esw_qos_set_vport_max_rate(vport, max_rate, NULL); -unlock: + err = mlx5_esw_qos_set_vport_max_rate(vport, max_rate, NULL); esw_qos_unlock(esw); return err; } @@ -809,6 +674,31 @@ bool mlx5_esw_qos_get_vport_rate(struct mlx5_vport *vport, u32 *max_rate, u32 *m return enabled; } +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; + + esw_assert_qos_lock_held(esw); + curr_parent = vport->qos.sched_node->parent; + parent = parent ?: esw->qos.node0; + if (curr_parent == parent) + return 0; + + esw_qos_vport_disable(vport, extack); + + err = esw_qos_vport_enable(vport, parent, extack); + 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); + } + + return err; +} + static u32 mlx5_esw_qos_lag_link_speed_get_locked(struct mlx5_core_dev *mdev) { struct ethtool_link_ksettings lksettings; @@ -875,10 +765,8 @@ static int mlx5_esw_qos_link_speed_verify(struct mlx5_core_dev *mdev, int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32 rate_mbps) { - u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; struct mlx5_vport *vport; u32 link_speed_max; - u32 bitmask; int err; vport = mlx5_eswitch_get_vport(esw, vport_num); @@ -897,20 +785,7 @@ int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32 } esw_qos_lock(esw); - if (!vport->qos.sched_node) { - /* Eswitch QoS wasn't enabled yet. Enable it and vport QoS. */ - err = esw_qos_vport_enable(vport, rate_mbps, 0, NULL); - } else { - struct mlx5_core_dev *dev = vport->qos.sched_node->parent->esw->dev; - - MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps); - bitmask = MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW; - err = mlx5_modify_scheduling_element_cmd(dev, - SCHEDULING_HIERARCHY_E_SWITCH, - ctx, - vport->qos.sched_node->ix, - bitmask); - } + err = mlx5_esw_qos_set_vport_max_rate(vport, rate_mbps, NULL); esw_qos_unlock(esw); return err; @@ -951,6 +826,9 @@ static int esw_qos_devlink_rate_to_mbps(struct mlx5_core_dev *mdev, const char * int mlx5_esw_qos_init(struct mlx5_eswitch *esw) { + if (esw->qos.domain) + return 0; /* Nothing to change. */ + return esw_qos_domain_init(esw); } @@ -978,12 +856,7 @@ int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void return err; esw_qos_lock(esw); - err = esw_qos_vport_enable(vport, 0, 0, extack); - if (err) - goto unlock; - - err = esw_qos_set_vport_min_rate(vport, tx_share, extack); -unlock: + err = mlx5_esw_qos_set_vport_min_rate(vport, tx_share, extack); esw_qos_unlock(esw); return err; } @@ -1004,12 +877,7 @@ int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void * return err; esw_qos_lock(esw); - err = esw_qos_vport_enable(vport, 0, 0, extack); - if (err) - goto unlock; - - err = esw_qos_set_vport_max_rate(vport, tx_max, extack); -unlock: + err = mlx5_esw_qos_set_vport_max_rate(vport, tx_max, extack); esw_qos_unlock(esw); return err; } @@ -1043,7 +911,7 @@ int mlx5_esw_devlink_rate_node_tx_max_set(struct devlink_rate *rate_node, void * return err; esw_qos_lock(esw); - err = esw_qos_set_node_max_rate(node, tx_max, extack); + err = esw_qos_sched_elem_config(node, tx_max, node->bw_share, extack); esw_qos_unlock(esw); return err; } @@ -1084,35 +952,30 @@ int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv, { struct mlx5_esw_sched_node *node = priv; struct mlx5_eswitch *esw = node->esw; - int err; esw_qos_lock(esw); - err = __esw_qos_destroy_node(node, extack); + __esw_qos_destroy_node(node, extack); esw_qos_put(esw); esw_qos_unlock(esw); - return err; + return 0; } -int mlx5_esw_qos_vport_update_node(struct mlx5_vport *vport, - struct mlx5_esw_sched_node *node, - struct netlink_ext_ack *extack) +int mlx5_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; int err = 0; - if (node && node->esw != esw) { + if (parent && parent->esw != esw) { NL_SET_ERR_MSG_MOD(extack, "Cross E-Switch scheduling is not supported"); return -EOPNOTSUPP; } esw_qos_lock(esw); - if (!vport->qos.sched_node && !node) - goto unlock; - - err = esw_qos_vport_enable(vport, 0, 0, extack); - if (!err) - err = esw_qos_vport_update_node(vport, node, extack); -unlock: + 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) + err = esw_qos_vport_update_parent(vport, parent, extack); esw_qos_unlock(esw); return err; } @@ -1126,8 +989,8 @@ int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate, struct mlx5_vport *vport = priv; if (!parent) - return mlx5_esw_qos_vport_update_node(vport, NULL, extack); + return mlx5_esw_qos_vport_update_parent(vport, NULL, extack); node = parent_priv; - return mlx5_esw_qos_vport_update_node(vport, node, extack); + return mlx5_esw_qos_vport_update_parent(vport, node, extack); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h index 61a6fdd5c267..6eb8f6a648c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h @@ -13,6 +13,7 @@ int mlx5_esw_qos_set_vport_rate(struct mlx5_vport *evport, u32 max_rate, u32 min bool mlx5_esw_qos_get_vport_rate(struct mlx5_vport *vport, u32 *max_rate, u32 *min_rate); void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport); +void mlx5_esw_qos_vport_qos_free(struct mlx5_vport *vport); u32 mlx5_esw_qos_vport_get_sched_elem_ix(const struct mlx5_vport *vport); struct mlx5_esw_sched_node *mlx5_esw_qos_vport_get_parent(const struct mlx5_vport *vport); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 09719e9b8611..7fb8a3381f84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1061,8 +1061,7 @@ static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw) unsigned long i; mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) { - kfree(vport->qos.sched_node); - memset(&vport->qos, 0, sizeof(vport->qos)); + mlx5_esw_qos_vport_qos_free(vport); memset(&vport->info, 0, sizeof(vport->info)); vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; } @@ -1074,8 +1073,7 @@ static void mlx5_eswitch_clear_ec_vf_vports_info(struct mlx5_eswitch *esw) unsigned long i; mlx5_esw_for_each_ec_vf_vport(esw, i, vport, esw->esw_funcs.num_ec_vfs) { - kfree(vport->qos.sched_node); - memset(&vport->qos, 0, sizeof(vport->qos)); + mlx5_esw_qos_vport_qos_free(vport); memset(&vport->info, 0, sizeof(vport->info)); vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; } @@ -1485,17 +1483,16 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs) err = mlx5_esw_qos_init(esw); if (err) - goto err_qos_init; + goto err_esw_init; if (esw->mode == MLX5_ESWITCH_LEGACY) { err = esw_legacy_enable(esw); } else { - mlx5_rescan_drivers(esw->dev); err = esw_offloads_enable(esw); } if (err) - goto err_esw_enable; + goto err_esw_init; esw->fdb_table.flags |= MLX5_ESW_FDB_CREATED; @@ -1509,9 +1506,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs) return 0; -err_esw_enable: - mlx5_esw_qos_cleanup(esw); -err_qos_init: +err_esw_init: mlx5_eq_notifier_unregister(esw->dev, &esw->nb); mlx5_esw_acls_ns_cleanup(esw); return err; @@ -1640,7 +1635,6 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw) if (esw->mode == MLX5_ESWITCH_OFFLOADS) devl_rate_nodes_destroy(devlink); - mlx5_esw_qos_cleanup(esw); } void mlx5_eswitch_disable(struct mlx5_eswitch *esw) @@ -1884,6 +1878,11 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) if (err) goto reps_err; + esw->mode = MLX5_ESWITCH_LEGACY; + err = mlx5_esw_qos_init(esw); + if (err) + goto reps_err; + mutex_init(&esw->offloads.encap_tbl_lock); hash_init(esw->offloads.encap_tbl); mutex_init(&esw->offloads.decap_tbl_lock); @@ -1897,7 +1896,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) refcount_set(&esw->qos.refcnt, 0); esw->enabled_vports = 0; - esw->mode = MLX5_ESWITCH_LEGACY; esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE; if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) && MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap)) @@ -1934,6 +1932,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) esw_info(esw->dev, "cleanup\n"); + mlx5_esw_qos_cleanup(esw); destroy_workqueue(esw->work_queue); WARN_ON(refcount_read(&esw->qos.refcnt)); mutex_destroy(&esw->state_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 14dd42d44e6f..a83d41121db6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -427,9 +427,8 @@ int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw, u16 vport_num, bool setting); int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport, u32 max_rate, u32 min_rate); -int mlx5_esw_qos_vport_update_node(struct mlx5_vport *vport, - struct mlx5_esw_sched_node *node, - struct netlink_ext_ack *extack); +int mlx5_esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_sched_node *node, + struct netlink_ext_ack *extack); int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting); int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting); int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index fd34f43d18d5..5f1adebd9669 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2332,18 +2332,35 @@ out_free: return err; } +static void esw_mode_change(struct mlx5_eswitch *esw, u16 mode) +{ + mlx5_devcom_comp_lock(esw->dev->priv.hca_devcom_comp); + + if (esw->dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV) { + esw->mode = mode; + mlx5_devcom_comp_unlock(esw->dev->priv.hca_devcom_comp); + return; + } + + esw->dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(esw->dev); + esw->mode = mode; + esw->dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(esw->dev); + mlx5_devcom_comp_unlock(esw->dev->priv.hca_devcom_comp); +} + static int esw_offloads_start(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) { int err; - esw->mode = MLX5_ESWITCH_OFFLOADS; + esw_mode_change(esw, MLX5_ESWITCH_OFFLOADS); err = mlx5_eswitch_enable_locked(esw, esw->dev->priv.sriov.num_vfs); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to offloads"); - esw->mode = MLX5_ESWITCH_LEGACY; - mlx5_rescan_drivers(esw->dev); + esw_mode_change(esw, MLX5_ESWITCH_LEGACY); return err; } if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) { @@ -3584,7 +3601,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, { int err; - esw->mode = MLX5_ESWITCH_LEGACY; + esw_mode_change(esw, MLX5_ESWITCH_LEGACY); /* If changing from switchdev to legacy mode without sriov enabled, * no need to create legacy fdb. @@ -3770,7 +3787,6 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, err = esw_offloads_start(esw, extack); } else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) { err = esw_offloads_stop(esw, extack); - mlx5_rescan_drivers(esw->dev); } else { err = -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index b30976627c6b..bad2df0715ec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -37,7 +37,7 @@ #include <linux/mlx5/fs.h> #include <linux/rhashtable.h> #include <linux/llist.h> -#include <steering/fs_dr.h> +#include <steering/sws/fs_dr.h> #define FDB_TC_MAX_CHAIN 3 #define FDB_FT_CHAIN (FDB_TC_MAX_CHAIN + 1) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index b306ae79bf97..4822d01123b4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -402,9 +402,7 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts, struct ptp_system_timestamp *sts) { struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info); - struct mlx5_timer *timer = &clock->timer; struct mlx5_core_dev *mdev; - unsigned long flags; u64 cycles, ns; mdev = container_of(clock, struct mlx5_core_dev, clock); @@ -413,10 +411,8 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts, goto out; } - write_seqlock_irqsave(&clock->lock, flags); cycles = mlx5_read_time(mdev, sts, false); - ns = timecounter_cyc2time(&timer->tc, cycles); - write_sequnlock_irqrestore(&clock->lock, flags); + ns = mlx5_timecounter_cyc2time(clock, cycles); *ts = ns_to_timespec64(ns); out: return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index 4b7f7131c560..b1edc71ffc6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -72,7 +72,7 @@ static inline void eq_update_ci(struct mlx5_eq *eq, int arm) __raw_writel((__force u32)cpu_to_be32(val), addr); /* We still want ordering, just not swabbing, so add a barrier */ - mb(); + wmb(); } int mlx5_eq_table_init(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/smfs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/smfs.h index 452d0df339ac..404f3d4b6380 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/smfs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/smfs.h @@ -4,8 +4,8 @@ #ifndef __MLX5_LIB_SMFS_H__ #define __MLX5_LIB_SMFS_H__ -#include "steering/mlx5dr.h" -#include "steering/dr_types.h" +#include "steering/sws/mlx5dr.h" +#include "steering/sws/dr_types.h" struct mlx5dr_matcher * mlx5_smfs_matcher_create(struct mlx5dr_table *table, u32 priority, struct mlx5_flow_spec *spec); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c index b27bb4106532..a897cdc60fdb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" +#include "internal.h" #define MLX5HWS_ACTION_METER_INIT_COLOR_OFFSET 1 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h index bf5c1b241006..e8f562c31826 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#ifndef MLX5HWS_ACTION_H_ -#define MLX5HWS_ACTION_H_ +#ifndef HWS_ACTION_H_ +#define HWS_ACTION_H_ /* Max number of STEs needed for a rule (including match) */ #define MLX5HWS_ACTION_MAX_STE 20 @@ -304,4 +304,4 @@ mlx5hws_action_apply_setter(struct mlx5hws_actions_apply_data *apply, htonl(num_of_actions << 29); } -#endif /* MLX5HWS_ACTION_H_ */ +#endif /* HWS_ACTION_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/buddy.c index e6ed66202a40..b9aef80ba094 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/buddy.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" -#include "mlx5hws_buddy.h" +#include "internal.h" +#include "buddy.h" static int hws_buddy_init(struct mlx5hws_buddy_mem *buddy, u32 max_order) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/buddy.h index 338c44bbedaf..ef6b223677aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/buddy.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#ifndef MLX5HWS_BUDDY_H_ -#define MLX5HWS_BUDDY_H_ +#ifndef HWS_BUDDY_H_ +#define HWS_BUDDY_H_ struct mlx5hws_buddy_mem { unsigned long **bitmap; @@ -18,4 +18,4 @@ int mlx5hws_buddy_alloc_mem(struct mlx5hws_buddy_mem *buddy, u32 order); void mlx5hws_buddy_free_mem(struct mlx5hws_buddy_mem *buddy, u32 seg, u32 order); -#endif /* MLX5HWS_BUDDY_H_ */ +#endif /* HWS_BUDDY_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c index 8f3a6f9d703d..baacf662c0ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" +#include "internal.h" static u16 hws_bwc_gen_queue_idx(struct mlx5hws_context *ctx) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h index 4fe8c32d8fbe..0b745968e21e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#ifndef MLX5HWS_BWC_H_ -#define MLX5HWS_BWC_H_ +#ifndef HWS_BWC_H_ +#define HWS_BWC_H_ #define MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG 1 #define MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP 1 @@ -70,4 +70,4 @@ static inline u16 mlx5hws_bwc_get_queue_id(struct mlx5hws_context *ctx, u16 idx) return idx + mlx5hws_bwc_queues(ctx); } -#endif /* MLX5HWS_BWC_H_ */ +#endif /* HWS_BWC_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c index 601fad5fc54a..c00010ca86bd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" +#include "internal.h" bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx, u8 match_criteria_enable, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h index 068ee8118609..340f0688e394 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#ifndef MLX5HWS_BWC_COMPLEX_H_ -#define MLX5HWS_BWC_COMPLEX_H_ +#ifndef HWS_BWC_COMPLEX_H_ +#define HWS_BWC_COMPLEX_H_ bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx, u8 match_criteria_enable, @@ -26,4 +26,4 @@ int mlx5hws_bwc_rule_create_complex(struct mlx5hws_bwc_rule *bwc_rule, int mlx5hws_bwc_rule_destroy_complex(struct mlx5hws_bwc_rule *bwc_rule); -#endif /* MLX5HWS_BWC_COMPLEX_H_ */ +#endif /* HWS_BWC_COMPLEX_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c index 2c7b14172049..c00c138c3366 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" +#include "internal.h" static enum mlx5_ifc_flow_destination_type hws_cmd_dest_type_to_ifc_dest_type(enum mlx5_flow_destination_type type) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h index 2fbcf4ff571a..434f62b0904e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#ifndef MLX5HWS_CMD_H_ -#define MLX5HWS_CMD_H_ +#ifndef HWS_CMD_H_ +#define HWS_CMD_H_ #define WIRE_PORT 0xFFFF @@ -358,4 +358,4 @@ int mlx5hws_cmd_allow_other_vhca_access(struct mlx5_core_dev *mdev, int mlx5hws_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_function, u16 vport_number, u16 *gvmi); -#endif /* MLX5HWS_CMD_H_ */ +#endif /* HWS_CMD_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c index 00e4fdf4a558..fd48b05e91e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA CORPORATION. All rights reserved. */ -#include "mlx5hws_internal.h" +#include "internal.h" bool mlx5hws_context_cap_dynamic_reparse(struct mlx5hws_context *ctx) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h index 8ab548aa402b..47f5cc8de73f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#ifndef MLX5HWS_CONTEXT_H_ -#define MLX5HWS_CONTEXT_H_ +#ifndef HWS_CONTEXT_H_ +#define HWS_CONTEXT_H_ enum mlx5hws_context_flags { MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT = 1 << 0, @@ -62,4 +62,4 @@ bool mlx5hws_context_cap_dynamic_reparse(struct mlx5hws_context *ctx); u8 mlx5hws_context_get_reparse_mode(struct mlx5hws_context *ctx); -#endif /* MLX5HWS_CONTEXT_H_ */ +#endif /* HWS_CONTEXT_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c index 2b8c5a4e1c4c..5b200b4bc1a8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c @@ -5,7 +5,7 @@ #include <linux/kernel.h> #include <linux/seq_file.h> #include <linux/version.h> -#include "mlx5hws_internal.h" +#include "internal.h" static int hws_debug_dump_matcher_template_definer(struct seq_file *f, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h index b93a536035d9..e44e7ae28f93 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#ifndef MLX5HWS_DEBUG_H_ -#define MLX5HWS_DEBUG_H_ +#ifndef HWS_DEBUG_H_ +#define HWS_DEBUG_H_ #define HWS_DEBUG_FORMAT_VERSION "1.0" @@ -37,4 +37,4 @@ mlx5hws_debug_icm_to_idx(u64 icm_addr) void mlx5hws_debug_init_dump(struct mlx5hws_context *ctx); void mlx5hws_debug_uninit_dump(struct mlx5hws_context *ctx); -#endif /* MLX5HWS_DEBUG_H_ */ +#endif /* HWS_DEBUG_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c index 3f4c58bada37..8fe96eb76baf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" +#include "internal.h" /* Pattern tunnel Layer bits. */ #define MLX5_FLOW_LAYER_VXLAN BIT(12) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h index 2f6a7df4021c..9432d5084def 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#ifndef MLX5HWS_DEFINER_H_ -#define MLX5HWS_DEFINER_H_ +#ifndef HWS_DEFINER_H_ +#define HWS_DEFINER_H_ /* Max available selecotrs */ #define DW_SELECTORS 9 @@ -831,4 +831,4 @@ mlx5hws_definer_conv_match_params_to_compressed_fc(struct mlx5hws_context *ctx, u32 *match_param, int *fc_sz); -#endif /* MLX5HWS_DEFINER_H_ */ +#endif /* HWS_DEFINER_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_internal.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h index 5643be1cd5bf..3c8635f286ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_internal.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#ifndef MLX5HWS_INTERNAL_H_ -#define MLX5HWS_INTERNAL_H_ +#ifndef HWS_INTERNAL_H_ +#define HWS_INTERNAL_H_ #include <linux/mlx5/transobj.h> #include <linux/mlx5/vport.h> @@ -10,22 +10,22 @@ #include "wq.h" #include "lib/mlx5.h" -#include "mlx5hws_prm.h" +#include "prm.h" #include "mlx5hws.h" -#include "mlx5hws_pool.h" -#include "mlx5hws_vport.h" -#include "mlx5hws_context.h" -#include "mlx5hws_table.h" -#include "mlx5hws_send.h" -#include "mlx5hws_rule.h" -#include "mlx5hws_cmd.h" -#include "mlx5hws_action.h" -#include "mlx5hws_definer.h" -#include "mlx5hws_matcher.h" -#include "mlx5hws_debug.h" -#include "mlx5hws_pat_arg.h" -#include "mlx5hws_bwc.h" -#include "mlx5hws_bwc_complex.h" +#include "pool.h" +#include "vport.h" +#include "context.h" +#include "table.h" +#include "send.h" +#include "rule.h" +#include "cmd.h" +#include "action.h" +#include "definer.h" +#include "matcher.h" +#include "debug.h" +#include "pat_arg.h" +#include "bwc.h" +#include "bwc_complex.h" #define W_SIZE 2 #define DW_SIZE 4 @@ -56,4 +56,4 @@ static inline unsigned long align(unsigned long val, unsigned long align) return (val + align - 1) & ~(align - 1); } -#endif /* MLX5HWS_INTERNAL_H_ */ +#endif /* HWS_INTERNAL_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c index 61a1155d4b4f..1bb3a6f8c3cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" +#include "internal.h" enum mlx5hws_matcher_rtc_type { HWS_MATCHER_RTC_TYPE_MATCH, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h index 125391d1a114..81ff487f57be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#ifndef MLX5HWS_MATCHER_H_ -#define MLX5HWS_MATCHER_H_ +#ifndef HWS_MATCHER_H_ +#define HWS_MATCHER_H_ /* We calculated that concatenating a collision table to the main table with * 3% of the main table rows will be enough resources for high insertion @@ -104,4 +104,4 @@ static inline bool mlx5hws_matcher_is_insert_by_idx(struct mlx5hws_matcher *matc return matcher->attr.insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX; } -#endif /* MLX5HWS_MATCHER_H_ */ +#endif /* HWS_MATCHER_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c index e084a5cbf81f..06db5e4726ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" +#include "internal.h" enum mlx5hws_arg_chunk_size mlx5hws_arg_data_size_to_arg_log_size(u16 data_size) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h index 27ca93385b08..27ca93385b08 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c index a8a63e3278be..fed2d913f3b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" -#include "mlx5hws_buddy.h" +#include "internal.h" +#include "buddy.h" static void hws_pool_free_one_resource(struct mlx5hws_pool_resource *resource) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h index 621298b352b2..621298b352b2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_prm.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h index de92cecbeb92..de92cecbeb92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_prm.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c index 8a011b958b43..e20c67a04203 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" +#include "internal.h" static void hws_rule_skip(struct mlx5hws_matcher *matcher, struct mlx5hws_match_template *mt, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h index 495cdd17e9f3..495cdd17e9f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c index 6d443e6ee8d9..424797b6d802 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" +#include "internal.h" #include "lib/clock.h" enum { CQ_OK = 0, CQ_EMPTY = -1, CQ_POLL_ERR = -2 }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h index b50825d6dc53..b50825d6dc53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c index 8c063a8d87d7..9576e02d00c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" +#include "internal.h" u32 mlx5hws_table_get_id(struct mlx5hws_table *tbl) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h index dd50420eec9e..dd50420eec9e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/vport.c index faf42421c43f..d8e382b9fa61 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/vport.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2024 NVIDIA Corporation & Affiliates */ -#include "mlx5hws_internal.h" +#include "internal.h" int mlx5hws_vport_init_vports(struct mlx5hws_context *ctx) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/vport.h index 0912fc166b3a..0912fc166b3a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/vport.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_action.c index 2ebb61ef3ea9..2ebb61ef3ea9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_action.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_arg.c index 01ed6442095d..01ed6442095d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_arg.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_arg.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_buddy.c index fe228d948b47..fe228d948b47 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_buddy.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_cmd.c index baefb9a3fa05..baefb9a3fa05 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_cmd.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c index 030a5776c937..030a5776c937 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.h index 57c6b363b870..57c6b363b870 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_dbg.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_definer.c index d5ea97751945..d5ea97751945 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_definer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_definer.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c index 3d74109f8230..3d74109f8230 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_fw.c index f05ef0cd54ba..f05ef0cd54ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_fw.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_icm_pool.c index 0b5af9f3f605..0b5af9f3f605 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_icm_pool.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_matcher.c index 0726848eb3ff..0726848eb3ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_matcher.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ptrn.c index 8ca534ef5d03..8ca534ef5d03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ptrn.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_rule.c index d1db04baa1fa..d1db04baa1fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_rule.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c index 6fa06ba2d346..6fa06ba2d346 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c index e94fbb015efa..e94fbb015efa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h index 54a6619c3ecb..54a6619c3ecb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c index e9f6c7ed7a7b..e9f6c7ed7a7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v0.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c index 1d49704b9542..1d49704b9542 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h index e2fc69867088..e2fc69867088 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v2.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c index 808b013cf48c..808b013cf48c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v2.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_table.c index 69294a66fd7f..69294a66fd7f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_table.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h index 7618c6147f86..7618c6147f86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c index 4b349d4005e4..4b349d4005e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.c diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h index 99a3b2eff6b8..99a3b2eff6b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/fs_dr.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h index fb078fa0f0cc..fb078fa0f0cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr_ste_v1.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr_ste_v1.h index ca3b0f1453a7..ca3b0f1453a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr_ste_v1.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5_ifc_dr_ste_v1.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h index 3ac7dc67509f..3ac7dc67509f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 060e5b939211..d6f37456fb31 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -389,15 +389,27 @@ static void mlxsw_pci_wqe_frag_unmap(struct mlxsw_pci *mlxsw_pci, char *wqe, dma_unmap_single(&pdev->dev, mapaddr, frag_len, direction); } -static struct sk_buff *mlxsw_pci_rdq_build_skb(struct page *pages[], +static struct sk_buff *mlxsw_pci_rdq_build_skb(struct mlxsw_pci_queue *q, + struct page *pages[], u16 byte_count) { + struct mlxsw_pci_queue *cq = q->u.rdq.cq; unsigned int linear_data_size; + struct page_pool *page_pool; struct sk_buff *skb; int page_index = 0; bool linear_only; void *data; + linear_only = byte_count + MLXSW_PCI_RX_BUF_SW_OVERHEAD <= PAGE_SIZE; + linear_data_size = linear_only ? byte_count : + PAGE_SIZE - + MLXSW_PCI_RX_BUF_SW_OVERHEAD; + + page_pool = cq->u.cq.page_pool; + page_pool_dma_sync_for_cpu(page_pool, pages[page_index], + MLXSW_PCI_SKB_HEADROOM, linear_data_size); + data = page_address(pages[page_index]); net_prefetch(data); @@ -405,11 +417,6 @@ static struct sk_buff *mlxsw_pci_rdq_build_skb(struct page *pages[], if (unlikely(!skb)) return ERR_PTR(-ENOMEM); - linear_only = byte_count + MLXSW_PCI_RX_BUF_SW_OVERHEAD <= PAGE_SIZE; - linear_data_size = linear_only ? byte_count : - PAGE_SIZE - - MLXSW_PCI_RX_BUF_SW_OVERHEAD; - skb_reserve(skb, MLXSW_PCI_SKB_HEADROOM); skb_put(skb, linear_data_size); @@ -425,6 +432,7 @@ static struct sk_buff *mlxsw_pci_rdq_build_skb(struct page *pages[], page = pages[page_index]; frag_size = min(byte_count, PAGE_SIZE); + page_pool_dma_sync_for_cpu(page_pool, page, 0, frag_size); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, 0, frag_size, PAGE_SIZE); byte_count -= frag_size; @@ -760,7 +768,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, if (err) goto out; - skb = mlxsw_pci_rdq_build_skb(pages, byte_count); + skb = mlxsw_pci_rdq_build_skb(q, pages, byte_count); if (IS_ERR(skb)) { dev_err_ratelimited(&pdev->dev, "Failed to build skb for RDQ\n"); mlxsw_pci_rdq_pages_recycle(q, pages, num_sg_entries); @@ -988,12 +996,13 @@ static int mlxsw_pci_cq_page_pool_init(struct mlxsw_pci_queue *q, if (cq_type != MLXSW_PCI_CQ_RDQ) return 0; - pp_params.flags = PP_FLAG_DMA_MAP; + pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; pp_params.pool_size = MLXSW_PCI_WQE_COUNT * mlxsw_pci->num_sg_entries; pp_params.nid = dev_to_node(&mlxsw_pci->pdev->dev); pp_params.dev = &mlxsw_pci->pdev->dev; pp_params.napi = &q->u.cq.napi; pp_params.dma_dir = DMA_FROM_DEVICE; + pp_params.max_len = PAGE_SIZE; page_pool = page_pool_create(&pp_params); if (IS_ERR(page_pool)) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index d761a1235994..7ea798a4949e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -481,11 +481,33 @@ mlxsw_sp_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry, struct netlink_ext_ack *extack) { + u32 new_kvdl_index, old_kvdl_index = ipip_entry->dip_kvdl_index; + struct in6_addr old_addr6 = ipip_entry->parms.daddr.addr6; struct mlxsw_sp_ipip_parms new_parms; + int err; new_parms = mlxsw_sp_ipip_netdev_parms_init_gre6(ipip_entry->ol_dev); - return mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry, - &new_parms, extack); + + err = mlxsw_sp_ipv6_addr_kvdl_index_get(mlxsw_sp, + &new_parms.daddr.addr6, + &new_kvdl_index); + if (err) + return err; + ipip_entry->dip_kvdl_index = new_kvdl_index; + + err = mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry, + &new_parms, extack); + if (err) + goto err_change_gre; + + mlxsw_sp_ipv6_addr_put(mlxsw_sp, &old_addr6); + + return 0; + +err_change_gre: + ipip_entry->dip_kvdl_index = old_kvdl_index; + mlxsw_sp_ipv6_addr_put(mlxsw_sp, &new_parms.daddr.addr6); + return err; } static int diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index 5b174cb95eb8..d94081c7658e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -16,6 +16,7 @@ #include "spectrum.h" #include "spectrum_ptp.h" #include "core.h" +#include "txheader.h" #define MLXSW_SP1_PTP_CLOCK_CYCLES_SHIFT 29 #define MLXSW_SP1_PTP_CLOCK_FREQ_KHZ 156257 /* 6.4nSec */ @@ -1684,6 +1685,12 @@ int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, const struct mlxsw_tx_info *tx_info) { + if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) { + this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); + dev_kfree_skb_any(skb); + return -ENOMEM; + } + mlxsw_sp_txhdr_construct(skb, tx_info); return 0; } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h index fec567c8fe4a..9f9cb9b3e74e 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic.h @@ -48,6 +48,7 @@ struct fbnic_dev { struct fbnic_act_tcam act_tcam[FBNIC_RPC_TCAM_ACT_NUM_ENTRIES]; struct fbnic_mac_addr mac_addr[FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES]; u8 mac_addr_boundary; + u8 tce_tcam_last; /* Number of TCQs/RCQs available on hardware */ u16 max_num_queues; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h index 79cdd231d327..dd407089ca47 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h @@ -397,6 +397,14 @@ enum { #define FBNIC_TCE_DROP_CTRL_TTI_FRM_DROP_EN CSR_BIT(1) #define FBNIC_TCE_DROP_CTRL_TTI_TBI_DROP_EN CSR_BIT(2) +#define FBNIC_TCE_TCAM_IDX2DEST_MAP 0x0404A /* 0x10128 */ +#define FBNIC_TCE_TCAM_IDX2DEST_MAP_DEST_ID_0 CSR_GENMASK(3, 0) +enum { + FBNIC_TCE_TCAM_DEST_MAC = 1, + FBNIC_TCE_TCAM_DEST_BMC = 2, + FBNIC_TCE_TCAM_DEST_FW = 4, +}; + #define FBNIC_TCE_TXB_TX_BMC_Q_CTRL 0x0404B /* 0x1012c */ #define FBNIC_TCE_TXB_BMC_DWRR_CTRL 0x0404C /* 0x10130 */ #define FBNIC_TCE_TXB_BMC_DWRR_CTRL_QUANTUM0 CSR_GENMASK(7, 0) @@ -407,6 +415,18 @@ enum { #define FBNIC_TCE_TXB_BMC_DWRR_CTRL_EXT 0x0404F /* 0x1013c */ #define FBNIC_CSR_END_TCE 0x04050 /* CSR section delimiter */ +/* TCE RAM registers */ +#define FBNIC_CSR_START_TCE_RAM 0x04200 /* CSR section delimiter */ +#define FBNIC_TCE_RAM_TCAM(m, n) \ + (0x04200 + 0x8 * (n) + (m)) /* 0x10800 + 32*n + 4*m */ +#define FBNIC_TCE_RAM_TCAM_MASK CSR_GENMASK(15, 0) +#define FBNIC_TCE_RAM_TCAM_VALUE CSR_GENMASK(31, 16) +#define FBNIC_TCE_RAM_TCAM3(n) (0x04218 + (n)) /* 0x010860 + 4*n */ +#define FBNIC_TCE_RAM_TCAM3_DEST_MASK CSR_GENMASK(5, 3) +#define FBNIC_TCE_RAM_TCAM3_MCQ_MASK CSR_BIT(7) +#define FBNIC_TCE_RAM_TCAM3_VALIDATE CSR_BIT(31) +#define FBNIC_CSR_END_TCE_RAM 0x0421F /* CSR section delimiter */ + /* TMI registers */ #define FBNIC_CSR_START_TMI 0x04400 /* CSR section delimiter */ #define FBNIC_TMI_SOP_PROT_CTRL 0x04400 /* 0x11000 */ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index c08798fad203..fc7d80db5fa6 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -273,6 +273,7 @@ void __fbnic_set_rx_mode(struct net_device *netdev) /* Write updates to hardware */ fbnic_write_rules(fbd); fbnic_write_macda(fbd); + fbnic_write_tce_tcam(fbd); } static void fbnic_set_rx_mode(struct net_device *netdev) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c index 337b8b3aef2f..908c098cd59e 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c @@ -587,6 +587,116 @@ static void fbnic_clear_act_tcam(struct fbnic_dev *fbd, unsigned int idx) wr32(fbd, FBNIC_RPC_TCAM_ACT(idx, i), 0); } +static void fbnic_clear_tce_tcam_entry(struct fbnic_dev *fbd, unsigned int idx) +{ + int i; + + /* Invalidate entry and clear addr state info */ + for (i = 0; i <= FBNIC_TCE_TCAM_WORD_LEN; i++) + wr32(fbd, FBNIC_TCE_RAM_TCAM(idx, i), 0); +} + +static void fbnic_write_tce_tcam_dest(struct fbnic_dev *fbd, unsigned int idx, + struct fbnic_mac_addr *mac_addr) +{ + u32 dest = FBNIC_TCE_TCAM_DEST_BMC; + u32 idx2dest_map; + + if (is_multicast_ether_addr(mac_addr->value.addr8)) + dest |= FBNIC_TCE_TCAM_DEST_MAC; + + idx2dest_map = rd32(fbd, FBNIC_TCE_TCAM_IDX2DEST_MAP); + idx2dest_map &= ~(FBNIC_TCE_TCAM_IDX2DEST_MAP_DEST_ID_0 << (4 * idx)); + idx2dest_map |= dest << (4 * idx); + + wr32(fbd, FBNIC_TCE_TCAM_IDX2DEST_MAP, idx2dest_map); +} + +static void fbnic_write_tce_tcam_entry(struct fbnic_dev *fbd, unsigned int idx, + struct fbnic_mac_addr *mac_addr) +{ + __be16 *mask, *value; + int i; + + mask = &mac_addr->mask.addr16[FBNIC_TCE_TCAM_WORD_LEN - 1]; + value = &mac_addr->value.addr16[FBNIC_TCE_TCAM_WORD_LEN - 1]; + + for (i = 0; i < FBNIC_TCE_TCAM_WORD_LEN; i++) + wr32(fbd, FBNIC_TCE_RAM_TCAM(idx, i), + FIELD_PREP(FBNIC_TCE_RAM_TCAM_MASK, ntohs(*mask--)) | + FIELD_PREP(FBNIC_TCE_RAM_TCAM_VALUE, ntohs(*value--))); + + wrfl(fbd); + + wr32(fbd, FBNIC_TCE_RAM_TCAM3(idx), FBNIC_TCE_RAM_TCAM3_MCQ_MASK | + FBNIC_TCE_RAM_TCAM3_DEST_MASK | + FBNIC_TCE_RAM_TCAM3_VALIDATE); +} + +static void __fbnic_write_tce_tcam_rev(struct fbnic_dev *fbd) +{ + int tcam_idx = FBNIC_TCE_TCAM_NUM_ENTRIES; + int mac_idx; + + for (mac_idx = ARRAY_SIZE(fbd->mac_addr); mac_idx--;) { + struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[mac_idx]; + + /* Verify BMC bit is set */ + if (!test_bit(FBNIC_MAC_ADDR_T_BMC, mac_addr->act_tcam)) + continue; + + if (!tcam_idx) { + dev_err(fbd->dev, "TCE TCAM overflow\n"); + return; + } + + tcam_idx--; + fbnic_write_tce_tcam_dest(fbd, tcam_idx, mac_addr); + fbnic_write_tce_tcam_entry(fbd, tcam_idx, mac_addr); + } + + while (tcam_idx) + fbnic_clear_tce_tcam_entry(fbd, --tcam_idx); + + fbd->tce_tcam_last = tcam_idx; +} + +static void __fbnic_write_tce_tcam(struct fbnic_dev *fbd) +{ + int tcam_idx = 0; + int mac_idx; + + for (mac_idx = 0; mac_idx < ARRAY_SIZE(fbd->mac_addr); mac_idx++) { + struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[mac_idx]; + + /* Verify BMC bit is set */ + if (!test_bit(FBNIC_MAC_ADDR_T_BMC, mac_addr->act_tcam)) + continue; + + if (tcam_idx == FBNIC_TCE_TCAM_NUM_ENTRIES) { + dev_err(fbd->dev, "TCE TCAM overflow\n"); + return; + } + + fbnic_write_tce_tcam_dest(fbd, tcam_idx, mac_addr); + fbnic_write_tce_tcam_entry(fbd, tcam_idx, mac_addr); + tcam_idx++; + } + + while (tcam_idx < FBNIC_TCE_TCAM_NUM_ENTRIES) + fbnic_clear_tce_tcam_entry(fbd, tcam_idx++); + + fbd->tce_tcam_last = tcam_idx; +} + +void fbnic_write_tce_tcam(struct fbnic_dev *fbd) +{ + if (fbd->tce_tcam_last) + __fbnic_write_tce_tcam_rev(fbd); + else + __fbnic_write_tce_tcam(fbd); +} + void fbnic_clear_rules(struct fbnic_dev *fbd) { u32 dest = FIELD_PREP(FBNIC_RPC_ACT_TBL0_DEST_MASK, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h index d62935f722a2..0d8285fa5b45 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h @@ -35,6 +35,9 @@ enum { #define FBNIC_RPC_TCAM_ACT_WORD_LEN 11 #define FBNIC_RPC_TCAM_ACT_NUM_ENTRIES 64 +#define FBNIC_TCE_TCAM_WORD_LEN 3 +#define FBNIC_TCE_TCAM_NUM_ENTRIES 8 + struct fbnic_mac_addr { union { unsigned char addr8[ETH_ALEN]; @@ -186,4 +189,5 @@ static inline int __fbnic_mc_unsync(struct fbnic_mac_addr *mac_addr) void fbnic_clear_rules(struct fbnic_dev *fbd); void fbnic_write_rules(struct fbnic_dev *fbd); +void fbnic_write_tce_tcam(struct fbnic_dev *fbd); #endif /* _FBNIC_RPC_H_ */ diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig index ee046468652c..73832fb2bc32 100644 --- a/drivers/net/ethernet/microchip/Kconfig +++ b/drivers/net/ethernet/microchip/Kconfig @@ -59,6 +59,7 @@ config LAN743X source "drivers/net/ethernet/microchip/lan865x/Kconfig" source "drivers/net/ethernet/microchip/lan966x/Kconfig" +source "drivers/net/ethernet/microchip/lan969x/Kconfig" source "drivers/net/ethernet/microchip/sparx5/Kconfig" source "drivers/net/ethernet/microchip/vcap/Kconfig" source "drivers/net/ethernet/microchip/fdma/Kconfig" diff --git a/drivers/net/ethernet/microchip/Makefile b/drivers/net/ethernet/microchip/Makefile index 3c65baed9fd8..7770df82200f 100644 --- a/drivers/net/ethernet/microchip/Makefile +++ b/drivers/net/ethernet/microchip/Makefile @@ -11,6 +11,7 @@ lan743x-objs := lan743x_main.o lan743x_ethtool.o lan743x_ptp.o obj-$(CONFIG_LAN865X) += lan865x/ obj-$(CONFIG_LAN966X_SWITCH) += lan966x/ +obj-$(CONFIG_LAN969X_SWITCH) += lan969x/ obj-$(CONFIG_SPARX5_SWITCH) += sparx5/ obj-$(CONFIG_VCAP) += vcap/ obj-$(CONFIG_FDMA) += fdma/ diff --git a/drivers/net/ethernet/microchip/lan969x/Kconfig b/drivers/net/ethernet/microchip/lan969x/Kconfig new file mode 100644 index 000000000000..728180d3fa33 --- /dev/null +++ b/drivers/net/ethernet/microchip/lan969x/Kconfig @@ -0,0 +1,5 @@ +config LAN969X_SWITCH + tristate "Lan969x switch driver" + depends on SPARX5_SWITCH + help + This driver supports the lan969x family of network switch devices. diff --git a/drivers/net/ethernet/microchip/lan969x/Makefile b/drivers/net/ethernet/microchip/lan969x/Makefile new file mode 100644 index 000000000000..9a2351b4f111 --- /dev/null +++ b/drivers/net/ethernet/microchip/lan969x/Makefile @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for the Microchip lan969x network device drivers. +# + +obj-$(CONFIG_LAN969X_SWITCH) += lan969x-switch.o + +lan969x-switch-y := lan969x_regs.o lan969x.o lan969x_calendar.o \ + lan969x_vcap_ag_api.o lan969x_vcap_impl.o + +# Provide include files +ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/fdma +ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/vcap diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x.c b/drivers/net/ethernet/microchip/lan969x/lan969x.c new file mode 100644 index 000000000000..ac37d0f74ee3 --- /dev/null +++ b/drivers/net/ethernet/microchip/lan969x/lan969x.c @@ -0,0 +1,353 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip lan969x Switch driver + * + * Copyright (c) 2024 Microchip Technology Inc. and its subsidiaries. + */ + +#include "lan969x.h" + +#define LAN969X_SDLB_GRP_CNT 5 +#define LAN969X_HSCH_LEAK_GRP_CNT 4 + +static const struct sparx5_main_io_resource lan969x_main_iomap[] = { + { TARGET_CPU, 0xc0000, 0 }, /* 0xe00c0000 */ + { TARGET_FDMA, 0xc0400, 0 }, /* 0xe00c0400 */ + { TARGET_GCB, 0x2010000, 1 }, /* 0xe2010000 */ + { TARGET_QS, 0x2030000, 1 }, /* 0xe2030000 */ + { TARGET_PTP, 0x2040000, 1 }, /* 0xe2040000 */ + { TARGET_ANA_ACL, 0x2050000, 1 }, /* 0xe2050000 */ + { TARGET_LRN, 0x2060000, 1 }, /* 0xe2060000 */ + { TARGET_VCAP_SUPER, 0x2080000, 1 }, /* 0xe2080000 */ + { TARGET_QSYS, 0x20a0000, 1 }, /* 0xe20a0000 */ + { TARGET_QFWD, 0x20b0000, 1 }, /* 0xe20b0000 */ + { TARGET_XQS, 0x20c0000, 1 }, /* 0xe20c0000 */ + { TARGET_VCAP_ES2, 0x20d0000, 1 }, /* 0xe20d0000 */ + { TARGET_VCAP_ES0, 0x20e0000, 1 }, /* 0xe20e0000 */ + { TARGET_ANA_AC_POL, 0x2200000, 1 }, /* 0xe2200000 */ + { TARGET_QRES, 0x2280000, 1 }, /* 0xe2280000 */ + { TARGET_EACL, 0x22c0000, 1 }, /* 0xe22c0000 */ + { TARGET_ANA_CL, 0x2400000, 1 }, /* 0xe2400000 */ + { TARGET_ANA_L3, 0x2480000, 1 }, /* 0xe2480000 */ + { TARGET_ANA_AC_SDLB, 0x2500000, 1 }, /* 0xe2500000 */ + { TARGET_HSCH, 0x2580000, 1 }, /* 0xe2580000 */ + { TARGET_REW, 0x2600000, 1 }, /* 0xe2600000 */ + { TARGET_ANA_L2, 0x2800000, 1 }, /* 0xe2800000 */ + { TARGET_ANA_AC, 0x2900000, 1 }, /* 0xe2900000 */ + { TARGET_VOP, 0x2a00000, 1 }, /* 0xe2a00000 */ + { TARGET_DEV2G5, 0x3004000, 1 }, /* 0xe3004000 */ + { TARGET_DEV10G, 0x3008000, 1 }, /* 0xe3008000 */ + { TARGET_PCS10G_BR, 0x300c000, 1 }, /* 0xe300c000 */ + { TARGET_DEV2G5 + 1, 0x3010000, 1 }, /* 0xe3010000 */ + { TARGET_DEV2G5 + 2, 0x3014000, 1 }, /* 0xe3014000 */ + { TARGET_DEV2G5 + 3, 0x3018000, 1 }, /* 0xe3018000 */ + { TARGET_DEV2G5 + 4, 0x301c000, 1 }, /* 0xe301c000 */ + { TARGET_DEV10G + 1, 0x3020000, 1 }, /* 0xe3020000 */ + { TARGET_PCS10G_BR + 1, 0x3024000, 1 }, /* 0xe3024000 */ + { TARGET_DEV2G5 + 5, 0x3028000, 1 }, /* 0xe3028000 */ + { TARGET_DEV2G5 + 6, 0x302c000, 1 }, /* 0xe302c000 */ + { TARGET_DEV2G5 + 7, 0x3030000, 1 }, /* 0xe3030000 */ + { TARGET_DEV2G5 + 8, 0x3034000, 1 }, /* 0xe3034000 */ + { TARGET_DEV10G + 2, 0x3038000, 1 }, /* 0xe3038000 */ + { TARGET_PCS10G_BR + 2, 0x303c000, 1 }, /* 0xe303c000 */ + { TARGET_DEV2G5 + 9, 0x3040000, 1 }, /* 0xe3040000 */ + { TARGET_DEV5G, 0x3044000, 1 }, /* 0xe3044000 */ + { TARGET_PCS5G_BR, 0x3048000, 1 }, /* 0xe3048000 */ + { TARGET_DEV2G5 + 10, 0x304c000, 1 }, /* 0xe304c000 */ + { TARGET_DEV2G5 + 11, 0x3050000, 1 }, /* 0xe3050000 */ + { TARGET_DEV2G5 + 12, 0x3054000, 1 }, /* 0xe3054000 */ + { TARGET_DEV10G + 3, 0x3058000, 1 }, /* 0xe3058000 */ + { TARGET_PCS10G_BR + 3, 0x305c000, 1 }, /* 0xe305c000 */ + { TARGET_DEV2G5 + 13, 0x3060000, 1 }, /* 0xe3060000 */ + { TARGET_DEV5G + 1, 0x3064000, 1 }, /* 0xe3064000 */ + { TARGET_PCS5G_BR + 1, 0x3068000, 1 }, /* 0xe3068000 */ + { TARGET_DEV2G5 + 14, 0x306c000, 1 }, /* 0xe306c000 */ + { TARGET_DEV2G5 + 15, 0x3070000, 1 }, /* 0xe3070000 */ + { TARGET_DEV2G5 + 16, 0x3074000, 1 }, /* 0xe3074000 */ + { TARGET_DEV10G + 4, 0x3078000, 1 }, /* 0xe3078000 */ + { TARGET_PCS10G_BR + 4, 0x307c000, 1 }, /* 0xe307c000 */ + { TARGET_DEV2G5 + 17, 0x3080000, 1 }, /* 0xe3080000 */ + { TARGET_DEV5G + 2, 0x3084000, 1 }, /* 0xe3084000 */ + { TARGET_PCS5G_BR + 2, 0x3088000, 1 }, /* 0xe3088000 */ + { TARGET_DEV2G5 + 18, 0x308c000, 1 }, /* 0xe308c000 */ + { TARGET_DEV2G5 + 19, 0x3090000, 1 }, /* 0xe3090000 */ + { TARGET_DEV2G5 + 20, 0x3094000, 1 }, /* 0xe3094000 */ + { TARGET_DEV10G + 5, 0x3098000, 1 }, /* 0xe3098000 */ + { TARGET_PCS10G_BR + 5, 0x309c000, 1 }, /* 0xe309c000 */ + { TARGET_DEV2G5 + 21, 0x30a0000, 1 }, /* 0xe30a0000 */ + { TARGET_DEV5G + 3, 0x30a4000, 1 }, /* 0xe30a4000 */ + { TARGET_PCS5G_BR + 3, 0x30a8000, 1 }, /* 0xe30a8000 */ + { TARGET_DEV2G5 + 22, 0x30ac000, 1 }, /* 0xe30ac000 */ + { TARGET_DEV2G5 + 23, 0x30b0000, 1 }, /* 0xe30b0000 */ + { TARGET_DEV2G5 + 24, 0x30b4000, 1 }, /* 0xe30b4000 */ + { TARGET_DEV10G + 6, 0x30b8000, 1 }, /* 0xe30b8000 */ + { TARGET_PCS10G_BR + 6, 0x30bc000, 1 }, /* 0xe30bc000 */ + { TARGET_DEV2G5 + 25, 0x30c0000, 1 }, /* 0xe30c0000 */ + { TARGET_DEV10G + 7, 0x30c4000, 1 }, /* 0xe30c4000 */ + { TARGET_PCS10G_BR + 7, 0x30c8000, 1 }, /* 0xe30c8000 */ + { TARGET_DEV2G5 + 26, 0x30cc000, 1 }, /* 0xe30cc000 */ + { TARGET_DEV10G + 8, 0x30d0000, 1 }, /* 0xe30d0000 */ + { TARGET_PCS10G_BR + 8, 0x30d4000, 1 }, /* 0xe30d4000 */ + { TARGET_DEV2G5 + 27, 0x30d8000, 1 }, /* 0xe30d8000 */ + { TARGET_DEV10G + 9, 0x30dc000, 1 }, /* 0xe30dc000 */ + { TARGET_PCS10G_BR + 9, 0x30e0000, 1 }, /* 0xe30e0000 */ + { TARGET_DSM, 0x30ec000, 1 }, /* 0xe30ec000 */ + { TARGET_PORT_CONF, 0x30f0000, 1 }, /* 0xe30f0000 */ + { TARGET_ASM, 0x3200000, 1 }, /* 0xe3200000 */ +}; + +static struct sparx5_sdlb_group lan969x_sdlb_groups[LAN969X_SDLB_GRP_CNT] = { + { 1000000000, 8192 / 2, 64 }, /* 1 G */ + { 500000000, 8192 / 2, 64 }, /* 500 M */ + { 100000000, 8192 / 4, 64 }, /* 100 M */ + { 50000000, 8192 / 4, 64 }, /* 50 M */ + { 5000000, 8192 / 8, 64 }, /* 10 M */ +}; + +static u32 lan969x_hsch_max_group_rate[LAN969X_HSCH_LEAK_GRP_CNT] = { + 655355, 1048568, 6553550, 10485680 +}; + +static struct sparx5_sdlb_group *lan969x_get_sdlb_group(int idx) +{ + return &lan969x_sdlb_groups[idx]; +} + +static u32 lan969x_get_hsch_max_group_rate(int grp) +{ + return lan969x_hsch_max_group_rate[grp]; +} + +static u32 lan969x_get_dev_mode_bit(struct sparx5 *sparx5, int port) +{ + if (lan969x_port_is_2g5(port) || lan969x_port_is_5g(port)) + return port; + + /* 10G */ + switch (port) { + case 0: + return 12; + case 4: + return 13; + case 8: + return 14; + case 12: + return 0; + default: + return port; + } +} + +static u32 lan969x_port_dev_mapping(struct sparx5 *sparx5, int port) +{ + if (lan969x_port_is_5g(port)) { + switch (port) { + case 9: + return 0; + case 13: + return 1; + case 17: + return 2; + case 21: + return 3; + } + } + + if (lan969x_port_is_10g(port)) { + switch (port) { + case 0: + return 0; + case 4: + return 1; + case 8: + return 2; + case 12: + return 3; + case 16: + return 4; + case 20: + return 5; + case 24: + return 6; + case 25: + return 7; + case 26: + return 8; + case 27: + return 9; + } + } + + /* 2g5 port */ + return port; +} + +static int lan969x_port_mux_set(struct sparx5 *sparx5, struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + u32 portno = port->portno; + u32 inst; + + if (port->conf.portmode == conf->portmode) + return 0; /* Nothing to do */ + + switch (conf->portmode) { + case PHY_INTERFACE_MODE_QSGMII: /* QSGMII: 4x2G5 devices. Mode Q' */ + inst = (portno - portno % 4) / 4; + spx5_rmw(BIT(inst), BIT(inst), sparx5, PORT_CONF_QSGMII_ENA); + break; + default: + break; + } + return 0; +} + +static irqreturn_t lan969x_ptp_irq_handler(int irq, void *args) +{ + int budget = SPARX5_MAX_PTP_ID; + struct sparx5 *sparx5 = args; + + while (budget--) { + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct skb_shared_hwtstamps shhwtstamps; + struct sparx5_port *port; + struct timespec64 ts; + unsigned long flags; + u32 val, id, txport; + u32 delay; + + val = spx5_rd(sparx5, PTP_TWOSTEP_CTRL); + + /* Check if a timestamp can be retrieved */ + if (!(val & PTP_TWOSTEP_CTRL_PTP_VLD)) + break; + + WARN_ON(val & PTP_TWOSTEP_CTRL_PTP_OVFL); + + if (!(val & PTP_TWOSTEP_CTRL_STAMP_TX)) + continue; + + /* Retrieve the ts Tx port */ + txport = PTP_TWOSTEP_CTRL_STAMP_PORT_GET(val); + + /* Retrieve its associated skb */ + port = sparx5->ports[txport]; + + /* Retrieve the delay */ + delay = spx5_rd(sparx5, PTP_TWOSTEP_STAMP_NSEC); + delay = PTP_TWOSTEP_STAMP_NSEC_NS_GET(delay); + + /* Get next timestamp from fifo, which needs to be the + * rx timestamp which represents the id of the frame + */ + spx5_rmw(PTP_TWOSTEP_CTRL_PTP_NXT_SET(1), + PTP_TWOSTEP_CTRL_PTP_NXT, + sparx5, PTP_TWOSTEP_CTRL); + + val = spx5_rd(sparx5, PTP_TWOSTEP_CTRL); + + /* Check if a timestamp can be retrieved */ + if (!(val & PTP_TWOSTEP_CTRL_PTP_VLD)) + break; + + /* Read RX timestamping to get the ID */ + id = spx5_rd(sparx5, PTP_TWOSTEP_STAMP_NSEC); + id <<= 8; + id |= spx5_rd(sparx5, PTP_TWOSTEP_STAMP_SUBNS); + + spin_lock_irqsave(&port->tx_skbs.lock, flags); + skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) { + if (SPARX5_SKB_CB(skb)->ts_id != id) + continue; + + __skb_unlink(skb, &port->tx_skbs); + skb_match = skb; + break; + } + spin_unlock_irqrestore(&port->tx_skbs.lock, flags); + + /* Next ts */ + spx5_rmw(PTP_TWOSTEP_CTRL_PTP_NXT_SET(1), + PTP_TWOSTEP_CTRL_PTP_NXT, + sparx5, PTP_TWOSTEP_CTRL); + + if (WARN_ON(!skb_match)) + continue; + + spin_lock(&sparx5->ptp_ts_id_lock); + sparx5->ptp_skbs--; + spin_unlock(&sparx5->ptp_ts_id_lock); + + /* Get the h/w timestamp */ + sparx5_get_hwtimestamp(sparx5, &ts, delay); + + /* Set the timestamp in the skb */ + shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); + skb_tstamp_tx(skb_match, &shhwtstamps); + + dev_kfree_skb_any(skb_match); + } + + return IRQ_HANDLED; +} + +static const struct sparx5_regs lan969x_regs = { + .tsize = lan969x_tsize, + .gaddr = lan969x_gaddr, + .gcnt = lan969x_gcnt, + .gsize = lan969x_gsize, + .raddr = lan969x_raddr, + .rcnt = lan969x_rcnt, + .fpos = lan969x_fpos, + .fsize = lan969x_fsize, +}; + +static const struct sparx5_consts lan969x_consts = { + .n_ports = 30, + .n_ports_all = 35, + .n_hsch_l1_elems = 32, + .n_hsch_queues = 4, + .n_lb_groups = 5, + .n_pgids = 1054, /* (1024 + n_ports) */ + .n_sio_clks = 1, + .n_own_upsids = 1, + .n_auto_cals = 4, + .n_filters = 256, + .n_gates = 256, + .n_sdlbs = 496, + .n_dsm_cal_taxis = 5, + .buf_size = 1572864, + .qres_max_prio_idx = 315, + .qres_max_colour_idx = 323, + .tod_pin = 4, + .vcaps = lan969x_vcaps, + .vcap_stats = &lan969x_vcap_stats, + .vcaps_cfg = lan969x_vcap_inst_cfg, +}; + +static const struct sparx5_ops lan969x_ops = { + .is_port_2g5 = &lan969x_port_is_2g5, + .is_port_5g = &lan969x_port_is_5g, + .is_port_10g = &lan969x_port_is_10g, + .is_port_25g = &lan969x_port_is_25g, + .get_port_dev_index = &lan969x_port_dev_mapping, + .get_port_dev_bit = &lan969x_get_dev_mode_bit, + .get_hsch_max_group_rate = &lan969x_get_hsch_max_group_rate, + .get_sdlb_group = &lan969x_get_sdlb_group, + .set_port_mux = &lan969x_port_mux_set, + .ptp_irq_handler = &lan969x_ptp_irq_handler, + .dsm_calendar_calc = &lan969x_dsm_calendar_calc, +}; + +const struct sparx5_match_data lan969x_desc = { + .iomap = lan969x_main_iomap, + .iomap_size = ARRAY_SIZE(lan969x_main_iomap), + .ioranges = 2, + .regs = &lan969x_regs, + .consts = &lan969x_consts, + .ops = &lan969x_ops, +}; +EXPORT_SYMBOL_GPL(lan969x_desc); + +MODULE_DESCRIPTION("Microchip lan969x switch driver"); +MODULE_AUTHOR("Daniel Machon <[email protected]>"); +MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x.h b/drivers/net/ethernet/microchip/lan969x/lan969x.h new file mode 100644 index 000000000000..2489d0d32dfd --- /dev/null +++ b/drivers/net/ethernet/microchip/lan969x/lan969x.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Microchip lan969x Switch driver + * + * Copyright (c) 2024 Microchip Technology Inc. and its subsidiaries. + */ + +#ifndef __LAN969X_H__ +#define __LAN969X_H__ + +#include "../sparx5/sparx5_main.h" +#include "../sparx5/sparx5_regs.h" +#include "../sparx5/sparx5_vcap_impl.h" + +/* lan969x.c */ +extern const struct sparx5_match_data lan969x_desc; + +/* lan969x_vcap_ag_api.c */ +extern const struct vcap_statistics lan969x_vcap_stats; +extern const struct vcap_info lan969x_vcaps[]; + +/* lan969x_vcap_impl.c */ +extern const struct sparx5_vcap_inst lan969x_vcap_inst_cfg[]; + +/* lan969x_regs.c */ +extern const unsigned int lan969x_tsize[TSIZE_LAST]; +extern const unsigned int lan969x_raddr[RADDR_LAST]; +extern const unsigned int lan969x_rcnt[RCNT_LAST]; +extern const unsigned int lan969x_gaddr[GADDR_LAST]; +extern const unsigned int lan969x_gcnt[GCNT_LAST]; +extern const unsigned int lan969x_gsize[GSIZE_LAST]; +extern const unsigned int lan969x_fpos[FPOS_LAST]; +extern const unsigned int lan969x_fsize[FSIZE_LAST]; + +static inline bool lan969x_port_is_2g5(int portno) +{ + return portno == 1 || portno == 2 || portno == 3 || + portno == 5 || portno == 6 || portno == 7 || + portno == 10 || portno == 11 || portno == 14 || + portno == 15 || portno == 18 || portno == 19 || + portno == 22 || portno == 23; +} + +static inline bool lan969x_port_is_5g(int portno) +{ + return portno == 9 || portno == 13 || portno == 17 || + portno == 21; +} + +static inline bool lan969x_port_is_10g(int portno) +{ + return portno == 0 || portno == 4 || portno == 8 || + portno == 12 || portno == 16 || portno == 20 || + portno == 24 || portno == 25 || portno == 26 || + portno == 27; +} + +static inline bool lan969x_port_is_25g(int portno) +{ + return false; +} + +/* lan969x_calendar.c */ +int lan969x_dsm_calendar_calc(struct sparx5 *sparx5, u32 taxi, + struct sparx5_calendar_data *data); +#endif diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x_calendar.c b/drivers/net/ethernet/microchip/lan969x/lan969x_calendar.c new file mode 100644 index 000000000000..e857640df185 --- /dev/null +++ b/drivers/net/ethernet/microchip/lan969x/lan969x_calendar.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip lan969x Switch driver + * + * Copyright (c) 2024 Microchip Technology Inc. and its subsidiaries. + */ + +#include "lan969x.h" + +#define LAN969X_DSM_CAL_DEVS_PER_TAXI 10 +#define LAN969X_DSM_CAL_TAXIS 5 + +enum lan969x_dsm_cal_dev { + DSM_CAL_DEV_2G5, + DSM_CAL_DEV_5G, + DSM_CAL_DEV_10G, + DSM_CAL_DEV_OTHER, /* 1G or less */ + DSM_CAL_DEV_MAX +}; + +/* Each entry in the following struct defines properties for a given speed + * (10G, 5G, 2.5G, or 1G or less). + */ +struct lan969x_dsm_cal_dev_speed { + /* Number of devices that requires this speed. */ + u32 n_devs; + + /* Array of devices that requires this speed. */ + u32 devs[LAN969X_DSM_CAL_DEVS_PER_TAXI]; + + /* Number of slots required for one device running this speed. */ + u32 n_slots; + + /* Gap between two slots for one device running this speed. */ + u32 gap; +}; + +static u32 +lan969x_taxi_ports[LAN969X_DSM_CAL_TAXIS][LAN969X_DSM_CAL_DEVS_PER_TAXI] = { + { 0, 4, 1, 2, 3, 5, 6, 7, 28, 29 }, + { 8, 12, 9, 13, 10, 11, 14, 15, 99, 99 }, + { 16, 20, 17, 21, 18, 19, 22, 23, 99, 99 }, + { 24, 25, 99, 99, 99, 99, 99, 99, 99, 99 }, + { 26, 27, 99, 99, 99, 99, 99, 99, 99, 99 } +}; + +static int lan969x_dsm_cal_idx_get(u32 *calendar, u32 cal_len, u32 *cal_idx) +{ + if (*cal_idx >= cal_len) + return -EINVAL; + + do { + if (calendar[*cal_idx] == SPX5_DSM_CAL_EMPTY) + return 0; + + (*cal_idx)++; + } while (*cal_idx < cal_len); + + return -ENOENT; +} + +static enum lan969x_dsm_cal_dev lan969x_dsm_cal_get_dev(int speed) +{ + return (speed == 10000 ? DSM_CAL_DEV_10G : + speed == 5000 ? DSM_CAL_DEV_5G : + speed == 2500 ? DSM_CAL_DEV_2G5 : + DSM_CAL_DEV_OTHER); +} + +static int lan969x_dsm_cal_get_speed(enum lan969x_dsm_cal_dev dev) +{ + return (dev == DSM_CAL_DEV_10G ? 10000 : + dev == DSM_CAL_DEV_5G ? 5000 : + dev == DSM_CAL_DEV_2G5 ? 2500 : + 1000); +} + +int lan969x_dsm_calendar_calc(struct sparx5 *sparx5, u32 taxi, + struct sparx5_calendar_data *data) +{ + struct lan969x_dsm_cal_dev_speed dev_speeds[DSM_CAL_DEV_MAX] = {}; + u32 cal_len, n_slots, taxi_bw, n_devs = 0, required_bw = 0; + struct lan969x_dsm_cal_dev_speed *speed; + int err; + + /* Maximum bandwidth for this taxi */ + taxi_bw = (128 * 1000000) / sparx5_clk_period(sparx5->coreclock); + + memcpy(data->taxi_ports, &lan969x_taxi_ports[taxi], + LAN969X_DSM_CAL_DEVS_PER_TAXI * sizeof(u32)); + + for (int i = 0; i < LAN969X_DSM_CAL_DEVS_PER_TAXI; i++) { + u32 portno = data->taxi_ports[i]; + enum sparx5_cal_bw bw; + + bw = sparx5_get_port_cal_speed(sparx5, portno); + + if (portno < sparx5->data->consts->n_ports_all) + data->taxi_speeds[i] = sparx5_cal_speed_to_value(bw); + else + data->taxi_speeds[i] = 0; + } + + /* Determine the different port types (10G, 5G, 2.5G, <= 1G) in the + * this taxi map. + */ + for (int i = 0; i < LAN969X_DSM_CAL_DEVS_PER_TAXI; i++) { + u32 taxi_speed = data->taxi_speeds[i]; + enum lan969x_dsm_cal_dev dev; + + if (taxi_speed == 0) + continue; + + required_bw += taxi_speed; + + dev = lan969x_dsm_cal_get_dev(taxi_speed); + speed = &dev_speeds[dev]; + speed->devs[speed->n_devs++] = i; + n_devs++; + } + + if (required_bw > taxi_bw) { + pr_err("Required bandwidth: %u is higher than total taxi bandwidth: %u", + required_bw, taxi_bw); + return -EINVAL; + } + + if (n_devs == 0) { + data->schedule[0] = SPX5_DSM_CAL_EMPTY; + return 0; + } + + cal_len = n_devs; + + /* Search for a calendar length that fits all active devices. */ + while (cal_len < SPX5_DSM_CAL_LEN) { + u32 bw_per_slot = taxi_bw / cal_len; + + n_slots = 0; + + for (int i = 0; i < DSM_CAL_DEV_MAX; i++) { + speed = &dev_speeds[i]; + + if (speed->n_devs == 0) + continue; + + required_bw = lan969x_dsm_cal_get_speed(i); + speed->n_slots = DIV_ROUND_UP(required_bw, bw_per_slot); + + if (speed->n_slots) + speed->gap = DIV_ROUND_UP(cal_len, + speed->n_slots); + else + speed->gap = 0; + + n_slots += speed->n_slots * speed->n_devs; + } + + if (n_slots <= cal_len) + break; /* Found a suitable calendar length. */ + + /* Not good enough yet. */ + cal_len = n_slots; + } + + if (cal_len > SPX5_DSM_CAL_LEN) { + pr_err("Invalid length: %u for taxi: %u", cal_len, taxi); + return -EINVAL; + } + + for (u32 i = 0; i < SPX5_DSM_CAL_LEN; i++) + data->schedule[i] = SPX5_DSM_CAL_EMPTY; + + /* Place the remaining devices */ + for (u32 i = 0; i < DSM_CAL_DEV_MAX; i++) { + speed = &dev_speeds[i]; + for (u32 dev = 0; dev < speed->n_devs; dev++) { + u32 idx = 0; + + for (n_slots = 0; n_slots < speed->n_slots; n_slots++) { + err = lan969x_dsm_cal_idx_get(data->schedule, + cal_len, &idx); + if (err) + return err; + data->schedule[idx] = speed->devs[dev]; + idx += speed->gap; + } + } + } + + return 0; +} diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x_regs.c b/drivers/net/ethernet/microchip/lan969x/lan969x_regs.c new file mode 100644 index 000000000000..ace4ba21eec4 --- /dev/null +++ b/drivers/net/ethernet/microchip/lan969x/lan969x_regs.c @@ -0,0 +1,222 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip lan969x Switch driver + * + * Copyright (c) 2024 Microchip Technology Inc. + */ + +/* This file is autogenerated by cml-utils 2024-09-30 11:48:29 +0200. + * Commit ID: 9d07b8d19363f3cd3590ddb3f7a2e2768e16524b + */ + +#include "lan969x.h" + +const unsigned int lan969x_tsize[TSIZE_LAST] = { + [TC_DEV10G] = 10, + [TC_DEV2G5] = 28, + [TC_DEV5G] = 4, + [TC_PCS10G_BR] = 10, + [TC_PCS5G_BR] = 4, +}; + +const unsigned int lan969x_raddr[RADDR_LAST] = { + [RA_CPU_PROC_CTRL] = 160, + [RA_GCB_SOFT_RST] = 12, + [RA_GCB_HW_SGPIO_TO_SD_MAP_CFG] = 20, +}; + +const unsigned int lan969x_rcnt[RCNT_LAST] = { + [RC_ANA_AC_OWN_UPSID] = 1, + [RC_ANA_ACL_VCAP_S2_CFG] = 35, + [RC_ANA_ACL_OWN_UPSID] = 1, + [RC_ANA_CL_OWN_UPSID] = 1, + [RC_ANA_L2_OWN_UPSID] = 1, + [RC_ASM_PORT_CFG] = 32, + [RC_DSM_BUF_CFG] = 32, + [RC_DSM_DEV_TX_STOP_WM_CFG] = 32, + [RC_DSM_RX_PAUSE_CFG] = 32, + [RC_DSM_MAC_CFG] = 32, + [RC_DSM_MAC_ADDR_BASE_HIGH_CFG] = 30, + [RC_DSM_MAC_ADDR_BASE_LOW_CFG] = 30, + [RC_DSM_TAXI_CAL_CFG] = 6, + [RC_GCB_HW_SGPIO_TO_SD_MAP_CFG] = 30, + [RC_HSCH_PORT_MODE] = 35, + [RC_QFWD_SWITCH_PORT_MODE] = 35, + [RC_QSYS_PAUSE_CFG] = 35, + [RC_QSYS_ATOP] = 35, + [RC_QSYS_FWD_PRESSURE] = 35, + [RC_QSYS_CAL_AUTO] = 4, + [RC_REW_OWN_UPSID] = 1, + [RC_REW_RTAG_ETAG_CTRL] = 35, +}; + +const unsigned int lan969x_gaddr[GADDR_LAST] = { + [GA_ANA_AC_RAM_CTRL] = 202000, + [GA_ANA_AC_PS_COMMON] = 202880, + [GA_ANA_AC_MIRROR_PROBE] = 203232, + [GA_ANA_AC_SRC] = 201728, + [GA_ANA_AC_PGID] = 131072, + [GA_ANA_AC_TSN_SF] = 202028, + [GA_ANA_AC_TSN_SF_CFG] = 148480, + [GA_ANA_AC_TSN_SF_STATUS] = 147936, + [GA_ANA_AC_SG_ACCESS] = 202032, + [GA_ANA_AC_SG_CONFIG] = 202752, + [GA_ANA_AC_SG_STATUS] = 147952, + [GA_ANA_AC_SG_STATUS_STICKY] = 202044, + [GA_ANA_AC_STAT_GLOBAL_CFG_PORT] = 202048, + [GA_ANA_AC_STAT_CNT_CFG_PORT] = 204800, + [GA_ANA_AC_STAT_GLOBAL_CFG_ACL] = 202068, + [GA_ANA_ACL_COMMON] = 8192, + [GA_ANA_ACL_KEY_SEL] = 9204, + [GA_ANA_ACL_CNT_B] = 4096, + [GA_ANA_ACL_STICKY] = 10852, + [GA_ANA_AC_POL_POL_ALL_CFG] = 17504, + [GA_ANA_AC_POL_COMMON_BDLB] = 19464, + [GA_ANA_AC_POL_COMMON_BUM_SLB] = 19472, + [GA_ANA_AC_SDLB_LBGRP_TBL] = 31788, + [GA_ANA_CL_PORT] = 65536, + [GA_ANA_CL_COMMON] = 87040, + [GA_ANA_L2_COMMON] = 561928, + [GA_ANA_L3_COMMON] = 370752, + [GA_ANA_L3_VLAN_ARP_L3MC_STICKY] = 368580, + [GA_ASM_CFG] = 18304, + [GA_ASM_PFC_TIMER_CFG] = 15568, + [GA_ASM_LBK_WM_CFG] = 15596, + [GA_ASM_LBK_MISC_CFG] = 15608, + [GA_ASM_RAM_CTRL] = 15684, + [GA_EACL_ES2_KEY_SELECT_PROFILE] = 36864, + [GA_EACL_CNT_TBL] = 30720, + [GA_EACL_POL_CFG] = 38400, + [GA_EACL_ES2_STICKY] = 29072, + [GA_EACL_RAM_CTRL] = 29112, + [GA_GCB_SIO_CTRL] = 560, + [GA_HSCH_HSCH_DWRR] = 36480, + [GA_HSCH_HSCH_MISC] = 36608, + [GA_HSCH_HSCH_LEAK_LISTS] = 37256, + [GA_HSCH_SYSTEM] = 37384, + [GA_HSCH_MMGT] = 36260, + [GA_HSCH_TAS_CONFIG] = 37696, + [GA_PTP_PTP_CFG] = 512, + [GA_PTP_PTP_TOD_DOMAINS] = 528, + [GA_PTP_PHASE_DETECTOR_CTRL] = 628, + [GA_QSYS_CALCFG] = 2164, + [GA_QSYS_RAM_CTRL] = 2204, + [GA_REW_COMMON] = 98304, + [GA_REW_PORT] = 49152, + [GA_REW_VOE_PORT_LM_CNT] = 90112, + [GA_REW_RAM_CTRL] = 93992, + [GA_VOP_RAM_CTRL] = 16368, + [GA_XQS_SYSTEM] = 5744, + [GA_XQS_QLIMIT_SHR] = 6912, +}; + +const unsigned int lan969x_gcnt[GCNT_LAST] = { + [GC_ANA_AC_SRC] = 67, + [GC_ANA_AC_PGID] = 1054, + [GC_ANA_AC_TSN_SF_CFG] = 256, + [GC_ANA_AC_STAT_CNT_CFG_PORT] = 35, + [GC_ANA_ACL_KEY_SEL] = 99, + [GC_ANA_ACL_CNT_A] = 1024, + [GC_ANA_ACL_CNT_B] = 1024, + [GC_ANA_AC_SDLB_LBGRP_TBL] = 5, + [GC_ANA_AC_SDLB_LBSET_TBL] = 496, + [GC_ANA_CL_PORT] = 35, + [GC_ANA_L2_ISDX_LIMIT] = 256, + [GC_ANA_L2_ISDX] = 1024, + [GC_ANA_L3_VLAN] = 4608, + [GC_ASM_DEV_STATISTICS] = 30, + [GC_EACL_ES2_KEY_SELECT_PROFILE] = 68, + [GC_EACL_CNT_TBL] = 512, + [GC_GCB_SIO_CTRL] = 1, + [GC_HSCH_HSCH_CFG] = 1120, + [GC_HSCH_HSCH_DWRR] = 32, + [GC_PTP_PTP_PINS] = 8, + [GC_PTP_PHASE_DETECTOR_CTRL] = 8, + [GC_REW_PORT] = 35, + [GC_REW_VOE_PORT_LM_CNT] = 240, +}; + +const unsigned int lan969x_gsize[GSIZE_LAST] = { + [GW_ANA_AC_SRC] = 4, + [GW_ANA_L2_COMMON] = 712, + [GW_ASM_CFG] = 1092, + [GW_CPU_CPU_REGS] = 180, + [GW_DEV2G5_PHASE_DETECTOR_CTRL] = 12, + [GW_FDMA_FDMA] = 448, + [GW_GCB_CHIP_REGS] = 180, + [GW_HSCH_TAS_CONFIG] = 16, + [GW_PTP_PHASE_DETECTOR_CTRL] = 12, + [GW_QSYS_PAUSE_CFG] = 988, +}; + +const unsigned int lan969x_fpos[FPOS_LAST] = { + [FP_CPU_PROC_CTRL_AARCH64_MODE_ENA] = 7, + [FP_CPU_PROC_CTRL_L2_RST_INVALIDATE_DIS] = 6, + [FP_CPU_PROC_CTRL_L1_RST_INVALIDATE_DIS] = 5, + [FP_CPU_PROC_CTRL_BE_EXCEP_MODE] = 4, + [FP_CPU_PROC_CTRL_VINITHI] = 3, + [FP_CPU_PROC_CTRL_CFGTE] = 2, + [FP_CPU_PROC_CTRL_CP15S_DISABLE] = 1, + [FP_CPU_PROC_CTRL_PROC_CRYPTO_DISABLE] = 0, + [FP_CPU_PROC_CTRL_L2_FLUSH_REQ] = 8, + [FP_DEV2G5_PHAD_CTRL_PHAD_ENA] = 5, + [FP_DEV2G5_PHAD_CTRL_PHAD_FAILED] = 3, + [FP_FDMA_CH_CFG_CH_XTR_STATUS_MODE] = 5, + [FP_FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY] = 4, + [FP_FDMA_CH_CFG_CH_INJ_PORT] = 3, + [FP_PTP_PTP_PIN_CFG_PTP_PIN_ACTION] = 27, + [FP_PTP_PTP_PIN_CFG_PTP_PIN_SYNC] = 25, + [FP_PTP_PTP_PIN_CFG_PTP_PIN_INV_POL] = 24, + [FP_PTP_PHAD_CTRL_PHAD_ENA] = 5, + [FP_PTP_PHAD_CTRL_PHAD_FAILED] = 3, +}; + +const unsigned int lan969x_fsize[FSIZE_LAST] = { + [FW_ANA_AC_PROBE_PORT_CFG_PROBE_PORT_MASK] = 30, + [FW_ANA_AC_SRC_CFG_PORT_MASK] = 30, + [FW_ANA_AC_PGID_CFG_PORT_MASK] = 30, + [FW_ANA_AC_TSN_SF_PORT_NUM] = 7, + [FW_ANA_AC_TSN_SF_CFG_TSN_SGID] = 8, + [FW_ANA_AC_TSN_SF_STATUS_TSN_SFID] = 8, + [FW_ANA_AC_SG_ACCESS_CTRL_SGID] = 8, + [FW_ANA_AC_PORT_SGE_CFG_MASK] = 17, + [FW_ANA_AC_SDLB_XLB_START_LBSET_START] = 9, + [FW_ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT] = 3, + [FW_ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_LBSET_NEXT] = 9, + [FW_ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT] = 9, + [FW_ANA_AC_SDLB_XLB_NEXT_LBGRP] = 3, + [FW_ANA_AC_SDLB_INH_LBSET_ADDR_INH_LBSET_ADDR] = 9, + [FW_ANA_L2_AUTO_LRN_CFG_AUTO_LRN_ENA] = 30, + [FW_ANA_L2_DLB_CFG_DLB_IDX] = 9, + [FW_ANA_L2_TSN_CFG_TSN_SFID] = 8, + [FW_ANA_L3_VLAN_MASK_CFG_VLAN_PORT_MASK] = 30, + [FW_FDMA_CH_CFG_CH_DCB_DB_CNT] = 2, + [FW_GCB_HW_SGPIO_TO_SD_MAP_CFG_SGPIO_TO_SD_SEL] = 7, + [FW_HSCH_SE_CFG_SE_DWRR_CNT] = 5, + [FW_HSCH_SE_CONNECT_SE_LEAK_LINK] = 14, + [FW_HSCH_SE_DLB_SENSE_SE_DLB_DPORT] = 6, + [FW_HSCH_HSCH_CFG_CFG_CFG_SE_IDX] = 11, + [FW_HSCH_HSCH_LEAK_CFG_LEAK_FIRST] = 14, + [FW_HSCH_FLUSH_CTRL_FLUSH_PORT] = 6, + [FW_HSCH_FLUSH_CTRL_FLUSH_HIER] = 14, + [FW_LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_ROW] = 13, + [FW_LRN_MAC_ACCESS_CFG_3_MAC_ENTRY_ISDX_LIMIT_IDX] = 8, + [FW_LRN_AUTOAGE_CFG_2_NEXT_ROW] = 13, + [FW_PTP_PTP_PIN_INTR_INTR_PTP] = 8, + [FW_PTP_PTP_PIN_INTR_ENA_INTR_PTP_ENA] = 8, + [FW_PTP_PTP_INTR_IDENT_INTR_PTP_IDENT] = 8, + [FW_PTP_PTP_PIN_CFG_PTP_PIN_SELECT] = 3, + [FW_QFWD_FRAME_COPY_CFG_FRMC_PORT_VAL] = 6, + [FW_QRES_RES_CFG_WM_HIGH] = 11, + [FW_QRES_RES_STAT_MAXUSE] = 19, + [FW_QRES_RES_STAT_CUR_INUSE] = 19, + [FW_QSYS_PAUSE_CFG_PAUSE_START] = 11, + [FW_QSYS_PAUSE_CFG_PAUSE_STOP] = 11, + [FW_QSYS_ATOP_ATOP] = 11, + [FW_QSYS_ATOP_TOT_CFG_ATOP_TOT] = 11, + [FW_REW_RTAG_ETAG_CTRL_IPE_TBL] = 6, + [FW_XQS_STAT_CFG_STAT_VIEW] = 10, + [FW_XQS_QLIMIT_SHR_TOP_CFG_QLIMIT_SHR_TOP] = 14, + [FW_XQS_QLIMIT_SHR_ATOP_CFG_QLIMIT_SHR_ATOP] = 14, + [FW_XQS_QLIMIT_SHR_CTOP_CFG_QLIMIT_SHR_CTOP] = 14, + [FW_XQS_QLIMIT_SHR_QLIM_CFG_QLIMIT_SHR_QLIM] = 14, +}; diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x_vcap_ag_api.c b/drivers/net/ethernet/microchip/lan969x/lan969x_vcap_ag_api.c new file mode 100644 index 000000000000..7acc5bcf337a --- /dev/null +++ b/drivers/net/ethernet/microchip/lan969x/lan969x_vcap_ag_api.c @@ -0,0 +1,3843 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* Copyright (C) 2024 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP API + */ + +/* This file is autogenerated by cml-utils 2024-10-07 11:10:56 +0200. + * Commit ID: b5ddc8e244eb2481a9524f1ddc630a8b41e7c391 + */ + +#include <linux/types.h> +#include <linux/kernel.h> + +#include "lan969x.h" + +/* keyfields */ +static const struct vcap_field is0_normal_7tuple_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_KF_LOOKUP_GEN_IDX_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 2, + }, + [VCAP_KF_LOOKUP_GEN_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 4, + .width = 10, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U72, + .offset = 16, + .width = 65, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 82, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGS] = { + .type = VCAP_FIELD_U32, + .offset = 83, + .width = 3, + }, + [VCAP_KF_8021Q_TPID0] = { + .type = VCAP_FIELD_U32, + .offset = 86, + .width = 3, + }, + [VCAP_KF_8021Q_PCP0] = { + .type = VCAP_FIELD_U32, + .offset = 89, + .width = 3, + }, + [VCAP_KF_8021Q_DEI0] = { + .type = VCAP_FIELD_BIT, + .offset = 92, + .width = 1, + }, + [VCAP_KF_8021Q_VID0] = { + .type = VCAP_FIELD_U32, + .offset = 93, + .width = 12, + }, + [VCAP_KF_8021Q_TPID1] = { + .type = VCAP_FIELD_U32, + .offset = 105, + .width = 3, + }, + [VCAP_KF_8021Q_PCP1] = { + .type = VCAP_FIELD_U32, + .offset = 108, + .width = 3, + }, + [VCAP_KF_8021Q_DEI1] = { + .type = VCAP_FIELD_BIT, + .offset = 111, + .width = 1, + }, + [VCAP_KF_8021Q_VID1] = { + .type = VCAP_FIELD_U32, + .offset = 112, + .width = 12, + }, + [VCAP_KF_8021Q_TPID2] = { + .type = VCAP_FIELD_U32, + .offset = 124, + .width = 3, + }, + [VCAP_KF_8021Q_PCP2] = { + .type = VCAP_FIELD_U32, + .offset = 127, + .width = 3, + }, + [VCAP_KF_8021Q_DEI2] = { + .type = VCAP_FIELD_BIT, + .offset = 130, + .width = 1, + }, + [VCAP_KF_8021Q_VID2] = { + .type = VCAP_FIELD_U32, + .offset = 131, + .width = 12, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 144, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 192, + .width = 48, + }, + [VCAP_KF_IP_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 240, + .width = 1, + }, + [VCAP_KF_ETYPE_LEN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 241, + .width = 1, + }, + [VCAP_KF_ETYPE] = { + .type = VCAP_FIELD_U32, + .offset = 242, + .width = 16, + }, + [VCAP_KF_IP_SNAP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 258, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 259, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 260, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 262, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 263, + .width = 1, + }, + [VCAP_KF_L3_DSCP] = { + .type = VCAP_FIELD_U32, + .offset = 264, + .width = 6, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 270, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 398, + .width = 128, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 526, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 527, + .width = 1, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 528, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 544, + .width = 8, + }, +}; + +static const struct vcap_field is0_normal_5tuple_ip4_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_LOOKUP_GEN_IDX_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 2, + }, + [VCAP_KF_LOOKUP_GEN_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 10, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 15, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U72, + .offset = 17, + .width = 65, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 82, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 83, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGS] = { + .type = VCAP_FIELD_U32, + .offset = 84, + .width = 3, + }, + [VCAP_KF_8021Q_TPID0] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 3, + }, + [VCAP_KF_8021Q_PCP0] = { + .type = VCAP_FIELD_U32, + .offset = 90, + .width = 3, + }, + [VCAP_KF_8021Q_DEI0] = { + .type = VCAP_FIELD_BIT, + .offset = 93, + .width = 1, + }, + [VCAP_KF_8021Q_VID0] = { + .type = VCAP_FIELD_U32, + .offset = 94, + .width = 12, + }, + [VCAP_KF_8021Q_TPID1] = { + .type = VCAP_FIELD_U32, + .offset = 106, + .width = 3, + }, + [VCAP_KF_8021Q_PCP1] = { + .type = VCAP_FIELD_U32, + .offset = 109, + .width = 3, + }, + [VCAP_KF_8021Q_DEI1] = { + .type = VCAP_FIELD_BIT, + .offset = 112, + .width = 1, + }, + [VCAP_KF_8021Q_VID1] = { + .type = VCAP_FIELD_U32, + .offset = 113, + .width = 12, + }, + [VCAP_KF_8021Q_TPID2] = { + .type = VCAP_FIELD_U32, + .offset = 125, + .width = 3, + }, + [VCAP_KF_8021Q_PCP2] = { + .type = VCAP_FIELD_U32, + .offset = 128, + .width = 3, + }, + [VCAP_KF_8021Q_DEI2] = { + .type = VCAP_FIELD_BIT, + .offset = 131, + .width = 1, + }, + [VCAP_KF_8021Q_VID2] = { + .type = VCAP_FIELD_U32, + .offset = 132, + .width = 12, + }, + [VCAP_KF_IP_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 145, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 146, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 147, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 149, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 150, + .width = 1, + }, + [VCAP_KF_L3_DSCP] = { + .type = VCAP_FIELD_U32, + .offset = 151, + .width = 6, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 157, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 189, + .width = 32, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 221, + .width = 8, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 229, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 230, + .width = 1, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 231, + .width = 8, + }, + [VCAP_KF_IP_PAYLOAD_5TUPLE] = { + .type = VCAP_FIELD_U32, + .offset = 239, + .width = 32, + }, +}; + +static const struct vcap_field is2_mac_etype_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 56, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 57, + .width = 10, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 67, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 80, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 81, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 89, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 137, + .width = 48, + }, + [VCAP_KF_ETYPE_LEN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 185, + .width = 1, + }, + [VCAP_KF_ETYPE] = { + .type = VCAP_FIELD_U32, + .offset = 186, + .width = 16, + }, + [VCAP_KF_L2_PAYLOAD_ETYPE] = { + .type = VCAP_FIELD_U64, + .offset = 202, + .width = 64, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 266, + .width = 16, + }, + [VCAP_KF_OAM_CCM_CNTS_EQ0] = { + .type = VCAP_FIELD_BIT, + .offset = 282, + .width = 1, + }, + [VCAP_KF_OAM_Y1731_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 283, + .width = 1, + }, +}; + +static const struct vcap_field is2_arp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 56, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 57, + .width = 10, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 67, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 80, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 81, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 85, + .width = 48, + }, + [VCAP_KF_ARP_ADDR_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 133, + .width = 1, + }, + [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 134, + .width = 1, + }, + [VCAP_KF_ARP_LEN_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 135, + .width = 1, + }, + [VCAP_KF_ARP_TGT_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 136, + .width = 1, + }, + [VCAP_KF_ARP_SENDER_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 137, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE_UNKNOWN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 138, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE] = { + .type = VCAP_FIELD_U32, + .offset = 139, + .width = 2, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 141, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 173, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 205, + .width = 1, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 206, + .width = 16, + }, +}; + +static const struct vcap_field is2_ip4_tcp_udp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 56, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 57, + .width = 10, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 67, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 80, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 81, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 89, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 90, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 92, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 93, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 95, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 103, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 135, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 167, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 168, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 169, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 185, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 201, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 217, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 218, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 219, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 220, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 221, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 222, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 223, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 224, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 225, + .width = 64, + }, +}; + +static const struct vcap_field is2_ip4_other_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 56, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 57, + .width = 10, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 67, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 80, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 81, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 89, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 90, + .width = 2, + }, + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = { + .type = VCAP_FIELD_BIT, + .offset = 92, + .width = 1, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 93, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 94, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 95, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 103, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 135, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 167, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 168, + .width = 8, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 176, + .width = 16, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U112, + .offset = 192, + .width = 96, + }, +}; + +static const struct vcap_field is2_ip6_std_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 4, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 4, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 5, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 32, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 52, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 53, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 54, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 56, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 57, + .width = 10, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 67, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 80, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 81, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 89, + .width = 1, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 90, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 218, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 219, + .width = 8, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 227, + .width = 16, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U48, + .offset = 243, + .width = 40, + }, +}; + +static const struct vcap_field is2_ip_7tuple_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_KF_LOOKUP_PAG] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 8, + }, + [VCAP_KF_IF_IGR_PORT_MASK_L3] = { + .type = VCAP_FIELD_BIT, + .offset = 11, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 12, + .width = 4, + }, + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 2, + }, + [VCAP_KF_IF_IGR_PORT_MASK] = { + .type = VCAP_FIELD_U72, + .offset = 18, + .width = 65, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 83, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 85, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 88, + .width = 10, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 98, + .width = 13, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 111, + .width = 1, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 112, + .width = 3, + }, + [VCAP_KF_L2_FWD_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 115, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 118, + .width = 1, + }, + [VCAP_KF_L3_DST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 119, + .width = 1, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 120, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 168, + .width = 48, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 218, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 219, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 220, + .width = 8, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 228, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 356, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 484, + .width = 1, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 485, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 486, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 487, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 503, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 519, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 535, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 536, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 537, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 538, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 539, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 540, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 541, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 542, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 543, + .width = 64, + }, +}; + +static const struct vcap_field es0_isdx_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_KF_IF_EGR_PORT_NO] = { + .type = VCAP_FIELD_U32, + .offset = 1, + .width = 6, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 7, + .width = 13, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 20, + .width = 3, + }, + [VCAP_KF_8021Q_TPID] = { + .type = VCAP_FIELD_U32, + .offset = 23, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 27, + .width = 1, + }, + [VCAP_KF_PROT_ACTIVE] = { + .type = VCAP_FIELD_BIT, + .offset = 28, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 38, + .width = 10, + }, +}; + +static const struct vcap_field es2_mac_etype_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 10, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 28, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 41, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 44, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 76, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 77, + .width = 7, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 84, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 88, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 91, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 92, + .width = 1, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 96, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 144, + .width = 48, + }, + [VCAP_KF_ETYPE_LEN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 192, + .width = 1, + }, + [VCAP_KF_ETYPE] = { + .type = VCAP_FIELD_U32, + .offset = 193, + .width = 16, + }, + [VCAP_KF_L2_PAYLOAD_ETYPE] = { + .type = VCAP_FIELD_U64, + .offset = 209, + .width = 64, + }, + [VCAP_KF_OAM_CCM_CNTS_EQ0] = { + .type = VCAP_FIELD_BIT, + .offset = 273, + .width = 1, + }, + [VCAP_KF_OAM_Y1731_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 274, + .width = 1, + }, +}; + +static const struct vcap_field es2_arp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 10, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 28, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 41, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 44, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 76, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 77, + .width = 7, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 84, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 88, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 91, + .width = 1, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 95, + .width = 48, + }, + [VCAP_KF_ARP_ADDR_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 143, + .width = 1, + }, + [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 144, + .width = 1, + }, + [VCAP_KF_ARP_LEN_OK_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 145, + .width = 1, + }, + [VCAP_KF_ARP_TGT_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 146, + .width = 1, + }, + [VCAP_KF_ARP_SENDER_MATCH_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 147, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE_UNKNOWN_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 148, + .width = 1, + }, + [VCAP_KF_ARP_OPCODE] = { + .type = VCAP_FIELD_U32, + .offset = 149, + .width = 2, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 151, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 183, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 215, + .width = 1, + }, +}; + +static const struct vcap_field es2_ip4_tcp_udp_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 10, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 28, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 41, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 44, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 76, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 77, + .width = 7, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 84, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 88, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 91, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 92, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 96, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 97, + .width = 2, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 99, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 100, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 101, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 109, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 141, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 173, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 174, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 175, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 191, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 207, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 223, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 224, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 225, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 226, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 227, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 228, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 229, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 230, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 231, + .width = 64, + }, +}; + +static const struct vcap_field es2_ip4_other_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 10, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 28, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 41, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 44, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 76, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 77, + .width = 7, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 84, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 88, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 91, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 92, + .width = 1, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 96, + .width = 1, + }, + [VCAP_KF_L3_FRAGMENT_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 97, + .width = 2, + }, + [VCAP_KF_L3_OPTIONS_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 99, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 100, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 101, + .width = 8, + }, + [VCAP_KF_L3_IP4_DIP] = { + .type = VCAP_FIELD_U32, + .offset = 109, + .width = 32, + }, + [VCAP_KF_L3_IP4_SIP] = { + .type = VCAP_FIELD_U32, + .offset = 141, + .width = 32, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 173, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 174, + .width = 8, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U112, + .offset = 182, + .width = 96, + }, +}; + +static const struct vcap_field es2_ip_7tuple_keyfield[] = { + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 10, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 11, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 12, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 10, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 25, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 38, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 41, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 73, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 74, + .width = 7, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 81, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 85, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 88, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 89, + .width = 1, + }, + [VCAP_KF_L2_DMAC] = { + .type = VCAP_FIELD_U48, + .offset = 93, + .width = 48, + }, + [VCAP_KF_L2_SMAC] = { + .type = VCAP_FIELD_U48, + .offset = 141, + .width = 48, + }, + [VCAP_KF_IP4_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 191, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 192, + .width = 1, + }, + [VCAP_KF_L3_TOS] = { + .type = VCAP_FIELD_U32, + .offset = 193, + .width = 8, + }, + [VCAP_KF_L3_IP6_DIP] = { + .type = VCAP_FIELD_U128, + .offset = 201, + .width = 128, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 329, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 457, + .width = 1, + }, + [VCAP_KF_TCP_UDP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 458, + .width = 1, + }, + [VCAP_KF_TCP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 459, + .width = 1, + }, + [VCAP_KF_L4_DPORT] = { + .type = VCAP_FIELD_U32, + .offset = 460, + .width = 16, + }, + [VCAP_KF_L4_SPORT] = { + .type = VCAP_FIELD_U32, + .offset = 476, + .width = 16, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 492, + .width = 16, + }, + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 508, + .width = 1, + }, + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 509, + .width = 1, + }, + [VCAP_KF_L4_FIN] = { + .type = VCAP_FIELD_BIT, + .offset = 510, + .width = 1, + }, + [VCAP_KF_L4_SYN] = { + .type = VCAP_FIELD_BIT, + .offset = 511, + .width = 1, + }, + [VCAP_KF_L4_RST] = { + .type = VCAP_FIELD_BIT, + .offset = 512, + .width = 1, + }, + [VCAP_KF_L4_PSH] = { + .type = VCAP_FIELD_BIT, + .offset = 513, + .width = 1, + }, + [VCAP_KF_L4_ACK] = { + .type = VCAP_FIELD_BIT, + .offset = 514, + .width = 1, + }, + [VCAP_KF_L4_URG] = { + .type = VCAP_FIELD_BIT, + .offset = 515, + .width = 1, + }, + [VCAP_KF_L4_PAYLOAD] = { + .type = VCAP_FIELD_U64, + .offset = 516, + .width = 64, + }, +}; + +static const struct vcap_field es2_ip6_std_keyfield[] = { + [VCAP_KF_TYPE] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 3, + }, + [VCAP_KF_LOOKUP_FIRST_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 3, + .width = 1, + }, + [VCAP_KF_L2_MC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 13, + .width = 1, + }, + [VCAP_KF_L2_BC_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 14, + .width = 1, + }, + [VCAP_KF_ISDX_GT0_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_KF_ISDX_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 10, + }, + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_KF_8021Q_VID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 28, + .width = 13, + }, + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 41, + .width = 3, + }, + [VCAP_KF_IF_EGR_PORT_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 44, + .width = 32, + }, + [VCAP_KF_IF_IGR_PORT_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 76, + .width = 1, + }, + [VCAP_KF_IF_IGR_PORT] = { + .type = VCAP_FIELD_U32, + .offset = 77, + .width = 7, + }, + [VCAP_KF_8021Q_PCP_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 84, + .width = 3, + }, + [VCAP_KF_8021Q_DEI_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 87, + .width = 1, + }, + [VCAP_KF_COSID_CLS] = { + .type = VCAP_FIELD_U32, + .offset = 88, + .width = 3, + }, + [VCAP_KF_L3_DPL_CLS] = { + .type = VCAP_FIELD_BIT, + .offset = 91, + .width = 1, + }, + [VCAP_KF_L3_RT_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 92, + .width = 1, + }, + [VCAP_KF_L3_TTL_GT0] = { + .type = VCAP_FIELD_BIT, + .offset = 96, + .width = 1, + }, + [VCAP_KF_L3_IP6_SIP] = { + .type = VCAP_FIELD_U128, + .offset = 97, + .width = 128, + }, + [VCAP_KF_L3_DIP_EQ_SIP_IS] = { + .type = VCAP_FIELD_BIT, + .offset = 225, + .width = 1, + }, + [VCAP_KF_L3_IP_PROTO] = { + .type = VCAP_FIELD_U32, + .offset = 226, + .width = 8, + }, + [VCAP_KF_L4_RNG] = { + .type = VCAP_FIELD_U32, + .offset = 234, + .width = 16, + }, + [VCAP_KF_L3_PAYLOAD] = { + .type = VCAP_FIELD_U48, + .offset = 250, + .width = 40, + }, +}; + +/* keyfield_set */ +static const struct vcap_set is0_keyfield_set[] = { + [VCAP_KFS_NORMAL_7TUPLE] = { + .type_id = 0, + .sw_per_item = 12, + .sw_cnt = 1, + }, + [VCAP_KFS_NORMAL_5TUPLE_IP4] = { + .type_id = 2, + .sw_per_item = 6, + .sw_cnt = 2, + }, +}; + +static const struct vcap_set is2_keyfield_set[] = { + [VCAP_KFS_MAC_ETYPE] = { + .type_id = 0, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_ARP] = { + .type_id = 3, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_TCP_UDP] = { + .type_id = 4, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_OTHER] = { + .type_id = 5, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP6_STD] = { + .type_id = 6, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP_7TUPLE] = { + .type_id = 1, + .sw_per_item = 12, + .sw_cnt = 1, + }, +}; + +static const struct vcap_set es0_keyfield_set[] = { + [VCAP_KFS_ISDX] = { + .type_id = 0, + .sw_per_item = 1, + .sw_cnt = 1, + }, +}; + +static const struct vcap_set es2_keyfield_set[] = { + [VCAP_KFS_MAC_ETYPE] = { + .type_id = 0, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_ARP] = { + .type_id = 1, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_TCP_UDP] = { + .type_id = 2, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP4_OTHER] = { + .type_id = 3, + .sw_per_item = 6, + .sw_cnt = 2, + }, + [VCAP_KFS_IP_7TUPLE] = { + .type_id = -1, + .sw_per_item = 12, + .sw_cnt = 1, + }, + [VCAP_KFS_IP6_STD] = { + .type_id = 4, + .sw_per_item = 6, + .sw_cnt = 2, + }, +}; + +/* keyfield_set map */ +static const struct vcap_field *is0_keyfield_set_map[] = { + [VCAP_KFS_NORMAL_7TUPLE] = is0_normal_7tuple_keyfield, + [VCAP_KFS_NORMAL_5TUPLE_IP4] = is0_normal_5tuple_ip4_keyfield, +}; + +static const struct vcap_field *is2_keyfield_set_map[] = { + [VCAP_KFS_MAC_ETYPE] = is2_mac_etype_keyfield, + [VCAP_KFS_ARP] = is2_arp_keyfield, + [VCAP_KFS_IP4_TCP_UDP] = is2_ip4_tcp_udp_keyfield, + [VCAP_KFS_IP4_OTHER] = is2_ip4_other_keyfield, + [VCAP_KFS_IP6_STD] = is2_ip6_std_keyfield, + [VCAP_KFS_IP_7TUPLE] = is2_ip_7tuple_keyfield, +}; + +static const struct vcap_field *es0_keyfield_set_map[] = { + [VCAP_KFS_ISDX] = es0_isdx_keyfield, +}; + +static const struct vcap_field *es2_keyfield_set_map[] = { + [VCAP_KFS_MAC_ETYPE] = es2_mac_etype_keyfield, + [VCAP_KFS_ARP] = es2_arp_keyfield, + [VCAP_KFS_IP4_TCP_UDP] = es2_ip4_tcp_udp_keyfield, + [VCAP_KFS_IP4_OTHER] = es2_ip4_other_keyfield, + [VCAP_KFS_IP_7TUPLE] = es2_ip_7tuple_keyfield, + [VCAP_KFS_IP6_STD] = es2_ip6_std_keyfield, +}; + +/* keyfield_set map sizes */ +static int is0_keyfield_set_map_size[] = { + [VCAP_KFS_NORMAL_7TUPLE] = ARRAY_SIZE(is0_normal_7tuple_keyfield), + [VCAP_KFS_NORMAL_5TUPLE_IP4] = ARRAY_SIZE(is0_normal_5tuple_ip4_keyfield), +}; + +static int is2_keyfield_set_map_size[] = { + [VCAP_KFS_MAC_ETYPE] = ARRAY_SIZE(is2_mac_etype_keyfield), + [VCAP_KFS_ARP] = ARRAY_SIZE(is2_arp_keyfield), + [VCAP_KFS_IP4_TCP_UDP] = ARRAY_SIZE(is2_ip4_tcp_udp_keyfield), + [VCAP_KFS_IP4_OTHER] = ARRAY_SIZE(is2_ip4_other_keyfield), + [VCAP_KFS_IP6_STD] = ARRAY_SIZE(is2_ip6_std_keyfield), + [VCAP_KFS_IP_7TUPLE] = ARRAY_SIZE(is2_ip_7tuple_keyfield), +}; + +static int es0_keyfield_set_map_size[] = { + [VCAP_KFS_ISDX] = ARRAY_SIZE(es0_isdx_keyfield), +}; + +static int es2_keyfield_set_map_size[] = { + [VCAP_KFS_MAC_ETYPE] = ARRAY_SIZE(es2_mac_etype_keyfield), + [VCAP_KFS_ARP] = ARRAY_SIZE(es2_arp_keyfield), + [VCAP_KFS_IP4_TCP_UDP] = ARRAY_SIZE(es2_ip4_tcp_udp_keyfield), + [VCAP_KFS_IP4_OTHER] = ARRAY_SIZE(es2_ip4_other_keyfield), + [VCAP_KFS_IP_7TUPLE] = ARRAY_SIZE(es2_ip_7tuple_keyfield), + [VCAP_KFS_IP6_STD] = ARRAY_SIZE(es2_ip6_std_keyfield), +}; + +/* actionfields */ +static const struct vcap_field is0_classification_actionfield[] = { + [VCAP_AF_TYPE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_DSCP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_DSCP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 6, + }, + [VCAP_AF_QOS_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 12, + .width = 1, + }, + [VCAP_AF_QOS_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 13, + .width = 3, + }, + [VCAP_AF_DP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 16, + .width = 1, + }, + [VCAP_AF_DP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 17, + .width = 2, + }, + [VCAP_AF_DEI_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 19, + .width = 1, + }, + [VCAP_AF_DEI_VAL] = { + .type = VCAP_FIELD_BIT, + .offset = 20, + .width = 1, + }, + [VCAP_AF_PCP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 21, + .width = 1, + }, + [VCAP_AF_PCP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 22, + .width = 3, + }, + [VCAP_AF_MAP_LOOKUP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 25, + .width = 2, + }, + [VCAP_AF_MAP_KEY] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 3, + }, + [VCAP_AF_MAP_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 30, + .width = 7, + }, + [VCAP_AF_CLS_VID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 37, + .width = 3, + }, + [VCAP_AF_VID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 43, + .width = 13, + }, + [VCAP_AF_ISDX_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 66, + .width = 1, + }, + [VCAP_AF_ISDX_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 67, + .width = 10, + }, + [VCAP_AF_PAG_OVERRIDE_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 107, + .width = 8, + }, + [VCAP_AF_PAG_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 115, + .width = 8, + }, + [VCAP_AF_NXT_IDX_CTRL] = { + .type = VCAP_FIELD_U32, + .offset = 167, + .width = 3, + }, + [VCAP_AF_NXT_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 170, + .width = 10, + }, +}; + +static const struct vcap_field is0_full_actionfield[] = { + [VCAP_AF_DSCP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_DSCP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 1, + .width = 6, + }, + [VCAP_AF_QOS_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 11, + .width = 1, + }, + [VCAP_AF_QOS_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 12, + .width = 3, + }, + [VCAP_AF_DP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_AF_DP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 16, + .width = 2, + }, + [VCAP_AF_DEI_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 18, + .width = 1, + }, + [VCAP_AF_DEI_VAL] = { + .type = VCAP_FIELD_BIT, + .offset = 19, + .width = 1, + }, + [VCAP_AF_PCP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 20, + .width = 1, + }, + [VCAP_AF_PCP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 21, + .width = 3, + }, + [VCAP_AF_MAP_LOOKUP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 24, + .width = 2, + }, + [VCAP_AF_MAP_KEY] = { + .type = VCAP_FIELD_U32, + .offset = 26, + .width = 3, + }, + [VCAP_AF_MAP_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 29, + .width = 7, + }, + [VCAP_AF_CLS_VID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 36, + .width = 3, + }, + [VCAP_AF_VID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 42, + .width = 13, + }, + [VCAP_AF_ISDX_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 65, + .width = 1, + }, + [VCAP_AF_ISDX_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 66, + .width = 10, + }, + [VCAP_AF_MASK_MODE] = { + .type = VCAP_FIELD_U32, + .offset = 76, + .width = 3, + }, + [VCAP_AF_PORT_MASK] = { + .type = VCAP_FIELD_U48, + .offset = 79, + .width = 37, + }, + [VCAP_AF_PAG_OVERRIDE_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 174, + .width = 8, + }, + [VCAP_AF_PAG_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 182, + .width = 8, + }, + [VCAP_AF_NXT_IDX_CTRL] = { + .type = VCAP_FIELD_U32, + .offset = 266, + .width = 3, + }, + [VCAP_AF_NXT_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 269, + .width = 10, + }, +}; + +static const struct vcap_field is0_class_reduced_actionfield[] = { + [VCAP_AF_TYPE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_QOS_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 5, + .width = 1, + }, + [VCAP_AF_QOS_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 6, + .width = 3, + }, + [VCAP_AF_DP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 9, + .width = 1, + }, + [VCAP_AF_DP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 10, + .width = 2, + }, + [VCAP_AF_MAP_LOOKUP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 12, + .width = 2, + }, + [VCAP_AF_MAP_KEY] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 3, + }, + [VCAP_AF_CLS_VID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 17, + .width = 3, + }, + [VCAP_AF_VID_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 23, + .width = 13, + }, + [VCAP_AF_ISDX_ADD_REPLACE_SEL] = { + .type = VCAP_FIELD_BIT, + .offset = 46, + .width = 1, + }, + [VCAP_AF_ISDX_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 47, + .width = 10, + }, + [VCAP_AF_NXT_IDX_CTRL] = { + .type = VCAP_FIELD_U32, + .offset = 89, + .width = 3, + }, + [VCAP_AF_NXT_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 92, + .width = 10, + }, +}; + +static const struct vcap_field is2_base_type_actionfield[] = { + [VCAP_AF_PIPELINE_FORCE_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_PIPELINE_PT] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 5, + }, + [VCAP_AF_HIT_ME_ONCE] = { + .type = VCAP_FIELD_BIT, + .offset = 7, + .width = 1, + }, + [VCAP_AF_INTR_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 8, + .width = 1, + }, + [VCAP_AF_CPU_COPY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 9, + .width = 1, + }, + [VCAP_AF_CPU_QUEUE_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 10, + .width = 3, + }, + [VCAP_AF_LRN_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 15, + .width = 1, + }, + [VCAP_AF_RT_DIS] = { + .type = VCAP_FIELD_BIT, + .offset = 16, + .width = 1, + }, + [VCAP_AF_POLICE_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 17, + .width = 1, + }, + [VCAP_AF_POLICE_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 5, + }, + [VCAP_AF_IGNORE_PIPELINE_CTRL] = { + .type = VCAP_FIELD_BIT, + .offset = 23, + .width = 1, + }, + [VCAP_AF_MASK_MODE] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 3, + }, + [VCAP_AF_PORT_MASK] = { + .type = VCAP_FIELD_U48, + .offset = 30, + .width = 37, + }, + [VCAP_AF_MIRROR_PROBE] = { + .type = VCAP_FIELD_U32, + .offset = 78, + .width = 2, + }, + [VCAP_AF_MATCH_ID] = { + .type = VCAP_FIELD_U32, + .offset = 131, + .width = 16, + }, + [VCAP_AF_MATCH_ID_MASK] = { + .type = VCAP_FIELD_U32, + .offset = 147, + .width = 16, + }, + [VCAP_AF_CNT_ID] = { + .type = VCAP_FIELD_U32, + .offset = 163, + .width = 10, + }, +}; + +static const struct vcap_field es0_es0_actionfield[] = { + [VCAP_AF_PUSH_OUTER_TAG] = { + .type = VCAP_FIELD_U32, + .offset = 0, + .width = 2, + }, + [VCAP_AF_PUSH_INNER_TAG] = { + .type = VCAP_FIELD_BIT, + .offset = 2, + .width = 1, + }, + [VCAP_AF_TAG_A_TPID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 3, + .width = 3, + }, + [VCAP_AF_TAG_A_VID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 6, + .width = 2, + }, + [VCAP_AF_TAG_A_PCP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 8, + .width = 3, + }, + [VCAP_AF_TAG_A_DEI_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 11, + .width = 3, + }, + [VCAP_AF_TAG_B_TPID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 14, + .width = 3, + }, + [VCAP_AF_TAG_B_VID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 17, + .width = 2, + }, + [VCAP_AF_TAG_B_PCP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 19, + .width = 3, + }, + [VCAP_AF_TAG_B_DEI_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 22, + .width = 3, + }, + [VCAP_AF_TAG_C_TPID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 25, + .width = 3, + }, + [VCAP_AF_TAG_C_PCP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 28, + .width = 3, + }, + [VCAP_AF_TAG_C_DEI_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 31, + .width = 3, + }, + [VCAP_AF_VID_A_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 34, + .width = 12, + }, + [VCAP_AF_PCP_A_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 46, + .width = 3, + }, + [VCAP_AF_DEI_A_VAL] = { + .type = VCAP_FIELD_BIT, + .offset = 49, + .width = 1, + }, + [VCAP_AF_VID_B_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 50, + .width = 12, + }, + [VCAP_AF_PCP_B_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 62, + .width = 3, + }, + [VCAP_AF_DEI_B_VAL] = { + .type = VCAP_FIELD_BIT, + .offset = 65, + .width = 1, + }, + [VCAP_AF_VID_C_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 66, + .width = 12, + }, + [VCAP_AF_PCP_C_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 78, + .width = 3, + }, + [VCAP_AF_DEI_C_VAL] = { + .type = VCAP_FIELD_BIT, + .offset = 81, + .width = 1, + }, + [VCAP_AF_POP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 82, + .width = 2, + }, + [VCAP_AF_UNTAG_VID_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 84, + .width = 1, + }, + [VCAP_AF_PUSH_CUSTOMER_TAG] = { + .type = VCAP_FIELD_U32, + .offset = 85, + .width = 2, + }, + [VCAP_AF_TAG_C_VID_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 87, + .width = 2, + }, + [VCAP_AF_DSCP_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 127, + .width = 3, + }, + [VCAP_AF_DSCP_VAL] = { + .type = VCAP_FIELD_U32, + .offset = 130, + .width = 6, + }, + [VCAP_AF_ESDX] = { + .type = VCAP_FIELD_U32, + .offset = 319, + .width = 10, + }, + [VCAP_AF_FWD_SEL] = { + .type = VCAP_FIELD_U32, + .offset = 438, + .width = 2, + }, + [VCAP_AF_CPU_QU] = { + .type = VCAP_FIELD_U32, + .offset = 440, + .width = 3, + }, + [VCAP_AF_PIPELINE_PT] = { + .type = VCAP_FIELD_U32, + .offset = 443, + .width = 2, + }, + [VCAP_AF_PIPELINE_ACT] = { + .type = VCAP_FIELD_BIT, + .offset = 445, + .width = 1, + }, + [VCAP_AF_SWAP_MACS_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 454, + .width = 1, + }, + [VCAP_AF_LOOP_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 455, + .width = 1, + }, +}; + +static const struct vcap_field es2_base_type_actionfield[] = { + [VCAP_AF_HIT_ME_ONCE] = { + .type = VCAP_FIELD_BIT, + .offset = 0, + .width = 1, + }, + [VCAP_AF_INTR_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 1, + .width = 1, + }, + [VCAP_AF_FWD_MODE] = { + .type = VCAP_FIELD_U32, + .offset = 2, + .width = 2, + }, + [VCAP_AF_COPY_QUEUE_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 4, + .width = 14, + }, + [VCAP_AF_COPY_PORT_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 18, + .width = 6, + }, + [VCAP_AF_MIRROR_PROBE_ID] = { + .type = VCAP_FIELD_U32, + .offset = 24, + .width = 2, + }, + [VCAP_AF_CPU_COPY_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 26, + .width = 1, + }, + [VCAP_AF_CPU_QUEUE_NUM] = { + .type = VCAP_FIELD_U32, + .offset = 27, + .width = 3, + }, + [VCAP_AF_POLICE_ENA] = { + .type = VCAP_FIELD_BIT, + .offset = 30, + .width = 1, + }, + [VCAP_AF_POLICE_REMARK] = { + .type = VCAP_FIELD_BIT, + .offset = 31, + .width = 1, + }, + [VCAP_AF_POLICE_IDX] = { + .type = VCAP_FIELD_U32, + .offset = 32, + .width = 5, + }, + [VCAP_AF_ES2_REW_CMD] = { + .type = VCAP_FIELD_U32, + .offset = 37, + .width = 3, + }, + [VCAP_AF_CNT_ID] = { + .type = VCAP_FIELD_U32, + .offset = 40, + .width = 9, + }, + [VCAP_AF_IGNORE_PIPELINE_CTRL] = { + .type = VCAP_FIELD_BIT, + .offset = 49, + .width = 1, + }, +}; + +/* actionfield_set */ +static const struct vcap_set is0_actionfield_set[] = { + [VCAP_AFS_CLASSIFICATION] = { + .type_id = 1, + .sw_per_item = 2, + .sw_cnt = 6, + }, + [VCAP_AFS_FULL] = { + .type_id = -1, + .sw_per_item = 3, + .sw_cnt = 4, + }, + [VCAP_AFS_CLASS_REDUCED] = { + .type_id = 1, + .sw_per_item = 1, + .sw_cnt = 12, + }, +}; + +static const struct vcap_set is2_actionfield_set[] = { + [VCAP_AFS_BASE_TYPE] = { + .type_id = -1, + .sw_per_item = 3, + .sw_cnt = 4, + }, +}; + +static const struct vcap_set es0_actionfield_set[] = { + [VCAP_AFS_ES0] = { + .type_id = -1, + .sw_per_item = 1, + .sw_cnt = 1, + }, +}; + +static const struct vcap_set es2_actionfield_set[] = { + [VCAP_AFS_BASE_TYPE] = { + .type_id = -1, + .sw_per_item = 3, + .sw_cnt = 4, + }, +}; + +/* actionfield_set map */ +static const struct vcap_field *is0_actionfield_set_map[] = { + [VCAP_AFS_CLASSIFICATION] = is0_classification_actionfield, + [VCAP_AFS_FULL] = is0_full_actionfield, + [VCAP_AFS_CLASS_REDUCED] = is0_class_reduced_actionfield, +}; + +static const struct vcap_field *is2_actionfield_set_map[] = { + [VCAP_AFS_BASE_TYPE] = is2_base_type_actionfield, +}; + +static const struct vcap_field *es0_actionfield_set_map[] = { + [VCAP_AFS_ES0] = es0_es0_actionfield, +}; + +static const struct vcap_field *es2_actionfield_set_map[] = { + [VCAP_AFS_BASE_TYPE] = es2_base_type_actionfield, +}; + +/* actionfield_set map size */ +static int is0_actionfield_set_map_size[] = { + [VCAP_AFS_CLASSIFICATION] = ARRAY_SIZE(is0_classification_actionfield), + [VCAP_AFS_FULL] = ARRAY_SIZE(is0_full_actionfield), + [VCAP_AFS_CLASS_REDUCED] = ARRAY_SIZE(is0_class_reduced_actionfield), +}; + +static int is2_actionfield_set_map_size[] = { + [VCAP_AFS_BASE_TYPE] = ARRAY_SIZE(is2_base_type_actionfield), +}; + +static int es0_actionfield_set_map_size[] = { + [VCAP_AFS_ES0] = ARRAY_SIZE(es0_es0_actionfield), +}; + +static int es2_actionfield_set_map_size[] = { + [VCAP_AFS_BASE_TYPE] = ARRAY_SIZE(es2_base_type_actionfield), +}; + +/* Type Groups */ +static const struct vcap_typegroup is0_x12_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 5, + .value = 16, + }, + { + .offset = 52, + .width = 1, + .value = 0, + }, + { + .offset = 104, + .width = 2, + .value = 0, + }, + { + .offset = 156, + .width = 3, + .value = 0, + }, + { + .offset = 208, + .width = 2, + .value = 0, + }, + { + .offset = 260, + .width = 1, + .value = 0, + }, + { + .offset = 312, + .width = 4, + .value = 0, + }, + { + .offset = 364, + .width = 1, + .value = 0, + }, + { + .offset = 416, + .width = 2, + .value = 0, + }, + { + .offset = 468, + .width = 3, + .value = 0, + }, + { + .offset = 520, + .width = 2, + .value = 0, + }, + { + .offset = 572, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is0_x6_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 4, + .value = 8, + }, + { + .offset = 52, + .width = 1, + .value = 0, + }, + { + .offset = 104, + .width = 2, + .value = 0, + }, + { + .offset = 156, + .width = 3, + .value = 0, + }, + { + .offset = 208, + .width = 2, + .value = 0, + }, + { + .offset = 260, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is0_x3_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup is0_x2_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup is0_x1_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup is2_x12_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 3, + .value = 4, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + { + .offset = 312, + .width = 2, + .value = 0, + }, + { + .offset = 468, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x6_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x3_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup is2_x1_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup es0_x1_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup es2_x12_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 3, + .value = 4, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + { + .offset = 312, + .width = 2, + .value = 0, + }, + { + .offset = 468, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup es2_x6_keyfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 156, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup es2_x3_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup es2_x1_keyfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup *is0_keyfield_set_typegroups[] = { + [12] = is0_x12_keyfield_set_typegroups, + [6] = is0_x6_keyfield_set_typegroups, + [3] = is0_x3_keyfield_set_typegroups, + [2] = is0_x2_keyfield_set_typegroups, + [1] = is0_x1_keyfield_set_typegroups, + [13] = NULL, +}; + +static const struct vcap_typegroup *is2_keyfield_set_typegroups[] = { + [12] = is2_x12_keyfield_set_typegroups, + [6] = is2_x6_keyfield_set_typegroups, + [3] = is2_x3_keyfield_set_typegroups, + [1] = is2_x1_keyfield_set_typegroups, + [13] = NULL, +}; + +static const struct vcap_typegroup *es0_keyfield_set_typegroups[] = { + [1] = es0_x1_keyfield_set_typegroups, + [2] = NULL, +}; + +static const struct vcap_typegroup *es2_keyfield_set_typegroups[] = { + [12] = es2_x12_keyfield_set_typegroups, + [6] = es2_x6_keyfield_set_typegroups, + [3] = es2_x3_keyfield_set_typegroups, + [1] = es2_x1_keyfield_set_typegroups, + [13] = NULL, +}; + +static const struct vcap_typegroup is0_x3_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 3, + .value = 4, + }, + { + .offset = 103, + .width = 2, + .value = 0, + }, + { + .offset = 206, + .width = 2, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is0_x2_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 103, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is0_x1_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 1, + .value = 1, + }, + {} +}; + +static const struct vcap_typegroup is2_x3_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 95, + .width = 1, + .value = 0, + }, + { + .offset = 190, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup is2_x1_actionfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup es0_x1_actionfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup es2_x3_actionfield_set_typegroups[] = { + { + .offset = 0, + .width = 2, + .value = 2, + }, + { + .offset = 19, + .width = 1, + .value = 0, + }, + { + .offset = 38, + .width = 1, + .value = 0, + }, + {} +}; + +static const struct vcap_typegroup es2_x1_actionfield_set_typegroups[] = { + {} +}; + +static const struct vcap_typegroup *is0_actionfield_set_typegroups[] = { + [3] = is0_x3_actionfield_set_typegroups, + [2] = is0_x2_actionfield_set_typegroups, + [1] = is0_x1_actionfield_set_typegroups, + [13] = NULL, +}; + +static const struct vcap_typegroup *is2_actionfield_set_typegroups[] = { + [3] = is2_x3_actionfield_set_typegroups, + [1] = is2_x1_actionfield_set_typegroups, + [13] = NULL, +}; + +static const struct vcap_typegroup *es0_actionfield_set_typegroups[] = { + [1] = es0_x1_actionfield_set_typegroups, + [2] = NULL, +}; + +static const struct vcap_typegroup *es2_actionfield_set_typegroups[] = { + [3] = es2_x3_actionfield_set_typegroups, + [1] = es2_x1_actionfield_set_typegroups, + [13] = NULL, +}; + +/* Keyfieldset names */ +static const char * const vcap_keyfield_set_names[] = { + [VCAP_KFS_NO_VALUE] = "(None)", + [VCAP_KFS_ARP] = "VCAP_KFS_ARP", + [VCAP_KFS_ETAG] = "VCAP_KFS_ETAG", + [VCAP_KFS_IP4_OTHER] = "VCAP_KFS_IP4_OTHER", + [VCAP_KFS_IP4_TCP_UDP] = "VCAP_KFS_IP4_TCP_UDP", + [VCAP_KFS_IP4_VID] = "VCAP_KFS_IP4_VID", + [VCAP_KFS_IP6_OTHER] = "VCAP_KFS_IP6_OTHER", + [VCAP_KFS_IP6_STD] = "VCAP_KFS_IP6_STD", + [VCAP_KFS_IP6_TCP_UDP] = "VCAP_KFS_IP6_TCP_UDP", + [VCAP_KFS_IP6_VID] = "VCAP_KFS_IP6_VID", + [VCAP_KFS_IP_7TUPLE] = "VCAP_KFS_IP_7TUPLE", + [VCAP_KFS_ISDX] = "VCAP_KFS_ISDX", + [VCAP_KFS_LL_FULL] = "VCAP_KFS_LL_FULL", + [VCAP_KFS_MAC_ETYPE] = "VCAP_KFS_MAC_ETYPE", + [VCAP_KFS_MAC_LLC] = "VCAP_KFS_MAC_LLC", + [VCAP_KFS_MAC_SNAP] = "VCAP_KFS_MAC_SNAP", + [VCAP_KFS_NORMAL_5TUPLE_IP4] = "VCAP_KFS_NORMAL_5TUPLE_IP4", + [VCAP_KFS_NORMAL_7TUPLE] = "VCAP_KFS_NORMAL_7TUPLE", + [VCAP_KFS_OAM] = "VCAP_KFS_OAM", + [VCAP_KFS_PURE_5TUPLE_IP4] = "VCAP_KFS_PURE_5TUPLE_IP4", + [VCAP_KFS_SMAC_SIP4] = "VCAP_KFS_SMAC_SIP4", + [VCAP_KFS_SMAC_SIP6] = "VCAP_KFS_SMAC_SIP6", +}; + +/* Actionfieldset names */ +static const char * const vcap_actionfield_set_names[] = { + [VCAP_AFS_NO_VALUE] = "(None)", + [VCAP_AFS_BASE_TYPE] = "VCAP_AFS_BASE_TYPE", + [VCAP_AFS_CLASSIFICATION] = "VCAP_AFS_CLASSIFICATION", + [VCAP_AFS_CLASS_REDUCED] = "VCAP_AFS_CLASS_REDUCED", + [VCAP_AFS_ES0] = "VCAP_AFS_ES0", + [VCAP_AFS_FULL] = "VCAP_AFS_FULL", + [VCAP_AFS_SMAC_SIP] = "VCAP_AFS_SMAC_SIP", +}; + +/* Keyfield names */ +static const char * const vcap_keyfield_names[] = { + [VCAP_KF_NO_VALUE] = "(None)", + [VCAP_KF_8021BR_ECID_BASE] = "8021BR_ECID_BASE", + [VCAP_KF_8021BR_ECID_EXT] = "8021BR_ECID_EXT", + [VCAP_KF_8021BR_E_TAGGED] = "8021BR_E_TAGGED", + [VCAP_KF_8021BR_GRP] = "8021BR_GRP", + [VCAP_KF_8021BR_IGR_ECID_BASE] = "8021BR_IGR_ECID_BASE", + [VCAP_KF_8021BR_IGR_ECID_EXT] = "8021BR_IGR_ECID_EXT", + [VCAP_KF_8021Q_DEI0] = "8021Q_DEI0", + [VCAP_KF_8021Q_DEI1] = "8021Q_DEI1", + [VCAP_KF_8021Q_DEI2] = "8021Q_DEI2", + [VCAP_KF_8021Q_DEI_CLS] = "8021Q_DEI_CLS", + [VCAP_KF_8021Q_PCP0] = "8021Q_PCP0", + [VCAP_KF_8021Q_PCP1] = "8021Q_PCP1", + [VCAP_KF_8021Q_PCP2] = "8021Q_PCP2", + [VCAP_KF_8021Q_PCP_CLS] = "8021Q_PCP_CLS", + [VCAP_KF_8021Q_TPID] = "8021Q_TPID", + [VCAP_KF_8021Q_TPID0] = "8021Q_TPID0", + [VCAP_KF_8021Q_TPID1] = "8021Q_TPID1", + [VCAP_KF_8021Q_TPID2] = "8021Q_TPID2", + [VCAP_KF_8021Q_VID0] = "8021Q_VID0", + [VCAP_KF_8021Q_VID1] = "8021Q_VID1", + [VCAP_KF_8021Q_VID2] = "8021Q_VID2", + [VCAP_KF_8021Q_VID_CLS] = "8021Q_VID_CLS", + [VCAP_KF_8021Q_VLAN_TAGGED_IS] = "8021Q_VLAN_TAGGED_IS", + [VCAP_KF_8021Q_VLAN_TAGS] = "8021Q_VLAN_TAGS", + [VCAP_KF_ACL_GRP_ID] = "ACL_GRP_ID", + [VCAP_KF_ARP_ADDR_SPACE_OK_IS] = "ARP_ADDR_SPACE_OK_IS", + [VCAP_KF_ARP_LEN_OK_IS] = "ARP_LEN_OK_IS", + [VCAP_KF_ARP_OPCODE] = "ARP_OPCODE", + [VCAP_KF_ARP_OPCODE_UNKNOWN_IS] = "ARP_OPCODE_UNKNOWN_IS", + [VCAP_KF_ARP_PROTO_SPACE_OK_IS] = "ARP_PROTO_SPACE_OK_IS", + [VCAP_KF_ARP_SENDER_MATCH_IS] = "ARP_SENDER_MATCH_IS", + [VCAP_KF_ARP_TGT_MATCH_IS] = "ARP_TGT_MATCH_IS", + [VCAP_KF_COSID_CLS] = "COSID_CLS", + [VCAP_KF_ES0_ISDX_KEY_ENA] = "ES0_ISDX_KEY_ENA", + [VCAP_KF_ETYPE] = "ETYPE", + [VCAP_KF_ETYPE_LEN_IS] = "ETYPE_LEN_IS", + [VCAP_KF_HOST_MATCH] = "HOST_MATCH", + [VCAP_KF_IF_EGR_PORT_MASK] = "IF_EGR_PORT_MASK", + [VCAP_KF_IF_EGR_PORT_MASK_RNG] = "IF_EGR_PORT_MASK_RNG", + [VCAP_KF_IF_EGR_PORT_NO] = "IF_EGR_PORT_NO", + [VCAP_KF_IF_IGR_PORT] = "IF_IGR_PORT", + [VCAP_KF_IF_IGR_PORT_MASK] = "IF_IGR_PORT_MASK", + [VCAP_KF_IF_IGR_PORT_MASK_L3] = "IF_IGR_PORT_MASK_L3", + [VCAP_KF_IF_IGR_PORT_MASK_RNG] = "IF_IGR_PORT_MASK_RNG", + [VCAP_KF_IF_IGR_PORT_MASK_SEL] = "IF_IGR_PORT_MASK_SEL", + [VCAP_KF_IF_IGR_PORT_SEL] = "IF_IGR_PORT_SEL", + [VCAP_KF_IP4_IS] = "IP4_IS", + [VCAP_KF_IP_MC_IS] = "IP_MC_IS", + [VCAP_KF_IP_PAYLOAD_5TUPLE] = "IP_PAYLOAD_5TUPLE", + [VCAP_KF_IP_SNAP_IS] = "IP_SNAP_IS", + [VCAP_KF_ISDX_CLS] = "ISDX_CLS", + [VCAP_KF_ISDX_GT0_IS] = "ISDX_GT0_IS", + [VCAP_KF_L2_BC_IS] = "L2_BC_IS", + [VCAP_KF_L2_DMAC] = "L2_DMAC", + [VCAP_KF_L2_FRM_TYPE] = "L2_FRM_TYPE", + [VCAP_KF_L2_FWD_IS] = "L2_FWD_IS", + [VCAP_KF_L2_LLC] = "L2_LLC", + [VCAP_KF_L2_MC_IS] = "L2_MC_IS", + [VCAP_KF_L2_PAYLOAD0] = "L2_PAYLOAD0", + [VCAP_KF_L2_PAYLOAD1] = "L2_PAYLOAD1", + [VCAP_KF_L2_PAYLOAD2] = "L2_PAYLOAD2", + [VCAP_KF_L2_PAYLOAD_ETYPE] = "L2_PAYLOAD_ETYPE", + [VCAP_KF_L2_SMAC] = "L2_SMAC", + [VCAP_KF_L2_SNAP] = "L2_SNAP", + [VCAP_KF_L3_DIP_EQ_SIP_IS] = "L3_DIP_EQ_SIP_IS", + [VCAP_KF_L3_DPL_CLS] = "L3_DPL_CLS", + [VCAP_KF_L3_DSCP] = "L3_DSCP", + [VCAP_KF_L3_DST_IS] = "L3_DST_IS", + [VCAP_KF_L3_FRAGMENT] = "L3_FRAGMENT", + [VCAP_KF_L3_FRAGMENT_TYPE] = "L3_FRAGMENT_TYPE", + [VCAP_KF_L3_FRAG_INVLD_L4_LEN] = "L3_FRAG_INVLD_L4_LEN", + [VCAP_KF_L3_FRAG_OFS_GT0] = "L3_FRAG_OFS_GT0", + [VCAP_KF_L3_IP4_DIP] = "L3_IP4_DIP", + [VCAP_KF_L3_IP4_SIP] = "L3_IP4_SIP", + [VCAP_KF_L3_IP6_DIP] = "L3_IP6_DIP", + [VCAP_KF_L3_IP6_SIP] = "L3_IP6_SIP", + [VCAP_KF_L3_IP_PROTO] = "L3_IP_PROTO", + [VCAP_KF_L3_OPTIONS_IS] = "L3_OPTIONS_IS", + [VCAP_KF_L3_PAYLOAD] = "L3_PAYLOAD", + [VCAP_KF_L3_RT_IS] = "L3_RT_IS", + [VCAP_KF_L3_TOS] = "L3_TOS", + [VCAP_KF_L3_TTL_GT0] = "L3_TTL_GT0", + [VCAP_KF_L4_1588_DOM] = "L4_1588_DOM", + [VCAP_KF_L4_1588_VER] = "L4_1588_VER", + [VCAP_KF_L4_ACK] = "L4_ACK", + [VCAP_KF_L4_DPORT] = "L4_DPORT", + [VCAP_KF_L4_FIN] = "L4_FIN", + [VCAP_KF_L4_PAYLOAD] = "L4_PAYLOAD", + [VCAP_KF_L4_PSH] = "L4_PSH", + [VCAP_KF_L4_RNG] = "L4_RNG", + [VCAP_KF_L4_RST] = "L4_RST", + [VCAP_KF_L4_SEQUENCE_EQ0_IS] = "L4_SEQUENCE_EQ0_IS", + [VCAP_KF_L4_SPORT] = "L4_SPORT", + [VCAP_KF_L4_SPORT_EQ_DPORT_IS] = "L4_SPORT_EQ_DPORT_IS", + [VCAP_KF_L4_SYN] = "L4_SYN", + [VCAP_KF_L4_URG] = "L4_URG", + [VCAP_KF_LOOKUP_FIRST_IS] = "LOOKUP_FIRST_IS", + [VCAP_KF_LOOKUP_GEN_IDX] = "LOOKUP_GEN_IDX", + [VCAP_KF_LOOKUP_GEN_IDX_SEL] = "LOOKUP_GEN_IDX_SEL", + [VCAP_KF_LOOKUP_PAG] = "LOOKUP_PAG", + [VCAP_KF_MIRROR_PROBE] = "MIRROR_PROBE", + [VCAP_KF_OAM_CCM_CNTS_EQ0] = "OAM_CCM_CNTS_EQ0", + [VCAP_KF_OAM_DETECTED] = "OAM_DETECTED", + [VCAP_KF_OAM_FLAGS] = "OAM_FLAGS", + [VCAP_KF_OAM_MEL_FLAGS] = "OAM_MEL_FLAGS", + [VCAP_KF_OAM_MEPID] = "OAM_MEPID", + [VCAP_KF_OAM_OPCODE] = "OAM_OPCODE", + [VCAP_KF_OAM_VER] = "OAM_VER", + [VCAP_KF_OAM_Y1731_IS] = "OAM_Y1731_IS", + [VCAP_KF_PROT_ACTIVE] = "PROT_ACTIVE", + [VCAP_KF_TCP_IS] = "TCP_IS", + [VCAP_KF_TCP_UDP_IS] = "TCP_UDP_IS", + [VCAP_KF_TYPE] = "TYPE", +}; + +/* Actionfield names */ +static const char * const vcap_actionfield_names[] = { + [VCAP_AF_NO_VALUE] = "(None)", + [VCAP_AF_ACL_ID] = "ACL_ID", + [VCAP_AF_CLS_VID_SEL] = "CLS_VID_SEL", + [VCAP_AF_CNT_ID] = "CNT_ID", + [VCAP_AF_COPY_PORT_NUM] = "COPY_PORT_NUM", + [VCAP_AF_COPY_QUEUE_NUM] = "COPY_QUEUE_NUM", + [VCAP_AF_CPU_COPY_ENA] = "CPU_COPY_ENA", + [VCAP_AF_CPU_QU] = "CPU_QU", + [VCAP_AF_CPU_QUEUE_NUM] = "CPU_QUEUE_NUM", + [VCAP_AF_DEI_A_VAL] = "DEI_A_VAL", + [VCAP_AF_DEI_B_VAL] = "DEI_B_VAL", + [VCAP_AF_DEI_C_VAL] = "DEI_C_VAL", + [VCAP_AF_DEI_ENA] = "DEI_ENA", + [VCAP_AF_DEI_VAL] = "DEI_VAL", + [VCAP_AF_DP_ENA] = "DP_ENA", + [VCAP_AF_DP_VAL] = "DP_VAL", + [VCAP_AF_DSCP_ENA] = "DSCP_ENA", + [VCAP_AF_DSCP_SEL] = "DSCP_SEL", + [VCAP_AF_DSCP_VAL] = "DSCP_VAL", + [VCAP_AF_ES2_REW_CMD] = "ES2_REW_CMD", + [VCAP_AF_ESDX] = "ESDX", + [VCAP_AF_FWD_KILL_ENA] = "FWD_KILL_ENA", + [VCAP_AF_FWD_MODE] = "FWD_MODE", + [VCAP_AF_FWD_SEL] = "FWD_SEL", + [VCAP_AF_HIT_ME_ONCE] = "HIT_ME_ONCE", + [VCAP_AF_HOST_MATCH] = "HOST_MATCH", + [VCAP_AF_IGNORE_PIPELINE_CTRL] = "IGNORE_PIPELINE_CTRL", + [VCAP_AF_INTR_ENA] = "INTR_ENA", + [VCAP_AF_ISDX_ADD_REPLACE_SEL] = "ISDX_ADD_REPLACE_SEL", + [VCAP_AF_ISDX_ENA] = "ISDX_ENA", + [VCAP_AF_ISDX_VAL] = "ISDX_VAL", + [VCAP_AF_LOOP_ENA] = "LOOP_ENA", + [VCAP_AF_LRN_DIS] = "LRN_DIS", + [VCAP_AF_MAP_IDX] = "MAP_IDX", + [VCAP_AF_MAP_KEY] = "MAP_KEY", + [VCAP_AF_MAP_LOOKUP_SEL] = "MAP_LOOKUP_SEL", + [VCAP_AF_MASK_MODE] = "MASK_MODE", + [VCAP_AF_MATCH_ID] = "MATCH_ID", + [VCAP_AF_MATCH_ID_MASK] = "MATCH_ID_MASK", + [VCAP_AF_MIRROR_ENA] = "MIRROR_ENA", + [VCAP_AF_MIRROR_PROBE] = "MIRROR_PROBE", + [VCAP_AF_MIRROR_PROBE_ID] = "MIRROR_PROBE_ID", + [VCAP_AF_NXT_IDX] = "NXT_IDX", + [VCAP_AF_NXT_IDX_CTRL] = "NXT_IDX_CTRL", + [VCAP_AF_PAG_OVERRIDE_MASK] = "PAG_OVERRIDE_MASK", + [VCAP_AF_PAG_VAL] = "PAG_VAL", + [VCAP_AF_PCP_A_VAL] = "PCP_A_VAL", + [VCAP_AF_PCP_B_VAL] = "PCP_B_VAL", + [VCAP_AF_PCP_C_VAL] = "PCP_C_VAL", + [VCAP_AF_PCP_ENA] = "PCP_ENA", + [VCAP_AF_PCP_VAL] = "PCP_VAL", + [VCAP_AF_PIPELINE_ACT] = "PIPELINE_ACT", + [VCAP_AF_PIPELINE_FORCE_ENA] = "PIPELINE_FORCE_ENA", + [VCAP_AF_PIPELINE_PT] = "PIPELINE_PT", + [VCAP_AF_POLICE_ENA] = "POLICE_ENA", + [VCAP_AF_POLICE_IDX] = "POLICE_IDX", + [VCAP_AF_POLICE_REMARK] = "POLICE_REMARK", + [VCAP_AF_POLICE_VCAP_ONLY] = "POLICE_VCAP_ONLY", + [VCAP_AF_POP_VAL] = "POP_VAL", + [VCAP_AF_PORT_MASK] = "PORT_MASK", + [VCAP_AF_PUSH_CUSTOMER_TAG] = "PUSH_CUSTOMER_TAG", + [VCAP_AF_PUSH_INNER_TAG] = "PUSH_INNER_TAG", + [VCAP_AF_PUSH_OUTER_TAG] = "PUSH_OUTER_TAG", + [VCAP_AF_QOS_ENA] = "QOS_ENA", + [VCAP_AF_QOS_VAL] = "QOS_VAL", + [VCAP_AF_REW_OP] = "REW_OP", + [VCAP_AF_RT_DIS] = "RT_DIS", + [VCAP_AF_SWAP_MACS_ENA] = "SWAP_MACS_ENA", + [VCAP_AF_TAG_A_DEI_SEL] = "TAG_A_DEI_SEL", + [VCAP_AF_TAG_A_PCP_SEL] = "TAG_A_PCP_SEL", + [VCAP_AF_TAG_A_TPID_SEL] = "TAG_A_TPID_SEL", + [VCAP_AF_TAG_A_VID_SEL] = "TAG_A_VID_SEL", + [VCAP_AF_TAG_B_DEI_SEL] = "TAG_B_DEI_SEL", + [VCAP_AF_TAG_B_PCP_SEL] = "TAG_B_PCP_SEL", + [VCAP_AF_TAG_B_TPID_SEL] = "TAG_B_TPID_SEL", + [VCAP_AF_TAG_B_VID_SEL] = "TAG_B_VID_SEL", + [VCAP_AF_TAG_C_DEI_SEL] = "TAG_C_DEI_SEL", + [VCAP_AF_TAG_C_PCP_SEL] = "TAG_C_PCP_SEL", + [VCAP_AF_TAG_C_TPID_SEL] = "TAG_C_TPID_SEL", + [VCAP_AF_TAG_C_VID_SEL] = "TAG_C_VID_SEL", + [VCAP_AF_TYPE] = "TYPE", + [VCAP_AF_UNTAG_VID_ENA] = "UNTAG_VID_ENA", + [VCAP_AF_VID_A_VAL] = "VID_A_VAL", + [VCAP_AF_VID_B_VAL] = "VID_B_VAL", + [VCAP_AF_VID_C_VAL] = "VID_C_VAL", + [VCAP_AF_VID_VAL] = "VID_VAL", +}; + +/* VCAPs */ +const struct vcap_info lan969x_vcaps[] = { + [VCAP_TYPE_IS0] = { + .name = "is0", + .rows = 256, + .sw_count = 12, + .sw_width = 52, + .sticky_width = 1, + .act_width = 103, + .default_cnt = 70, + .require_cnt_dis = 0, + .version = 1, + .keyfield_set = is0_keyfield_set, + .keyfield_set_size = ARRAY_SIZE(is0_keyfield_set), + .actionfield_set = is0_actionfield_set, + .actionfield_set_size = ARRAY_SIZE(is0_actionfield_set), + .keyfield_set_map = is0_keyfield_set_map, + .keyfield_set_map_size = is0_keyfield_set_map_size, + .actionfield_set_map = is0_actionfield_set_map, + .actionfield_set_map_size = is0_actionfield_set_map_size, + .keyfield_set_typegroups = is0_keyfield_set_typegroups, + .actionfield_set_typegroups = is0_actionfield_set_typegroups, + }, + [VCAP_TYPE_IS2] = { + .name = "is2", + .rows = 256, + .sw_count = 12, + .sw_width = 52, + .sticky_width = 1, + .act_width = 103, + .default_cnt = 38, + .require_cnt_dis = 0, + .version = 1, + .keyfield_set = is2_keyfield_set, + .keyfield_set_size = ARRAY_SIZE(is2_keyfield_set), + .actionfield_set = is2_actionfield_set, + .actionfield_set_size = ARRAY_SIZE(is2_actionfield_set), + .keyfield_set_map = is2_keyfield_set_map, + .keyfield_set_map_size = is2_keyfield_set_map_size, + .actionfield_set_map = is2_actionfield_set_map, + .actionfield_set_map_size = is2_actionfield_set_map_size, + .keyfield_set_typegroups = is2_keyfield_set_typegroups, + .actionfield_set_typegroups = is2_actionfield_set_typegroups, + }, + [VCAP_TYPE_ES0] = { + .name = "es0", + .rows = 1536, + .sw_count = 1, + .sw_width = 51, + .sticky_width = 1, + .act_width = 469, + .default_cnt = 35, + .require_cnt_dis = 0, + .version = 1, + .keyfield_set = es0_keyfield_set, + .keyfield_set_size = ARRAY_SIZE(es0_keyfield_set), + .actionfield_set = es0_actionfield_set, + .actionfield_set_size = ARRAY_SIZE(es0_actionfield_set), + .keyfield_set_map = es0_keyfield_set_map, + .keyfield_set_map_size = es0_keyfield_set_map_size, + .actionfield_set_map = es0_actionfield_set_map, + .actionfield_set_map_size = es0_actionfield_set_map_size, + .keyfield_set_typegroups = es0_keyfield_set_typegroups, + .actionfield_set_typegroups = es0_actionfield_set_typegroups, + }, + [VCAP_TYPE_ES2] = { + .name = "es2", + .rows = 256, + .sw_count = 12, + .sw_width = 52, + .sticky_width = 1, + .act_width = 19, + .default_cnt = 39, + .require_cnt_dis = 0, + .version = 1, + .keyfield_set = es2_keyfield_set, + .keyfield_set_size = ARRAY_SIZE(es2_keyfield_set), + .actionfield_set = es2_actionfield_set, + .actionfield_set_size = ARRAY_SIZE(es2_actionfield_set), + .keyfield_set_map = es2_keyfield_set_map, + .keyfield_set_map_size = es2_keyfield_set_map_size, + .actionfield_set_map = es2_actionfield_set_map, + .actionfield_set_map_size = es2_actionfield_set_map_size, + .keyfield_set_typegroups = es2_keyfield_set_typegroups, + .actionfield_set_typegroups = es2_actionfield_set_typegroups, + }, +}; + +const struct vcap_statistics lan969x_vcap_stats = { + .name = "lan969x", + .count = 4, + .keyfield_set_names = vcap_keyfield_set_names, + .actionfield_set_names = vcap_actionfield_set_names, + .keyfield_names = vcap_keyfield_names, + .actionfield_names = vcap_actionfield_names, +}; diff --git a/drivers/net/ethernet/microchip/lan969x/lan969x_vcap_impl.c b/drivers/net/ethernet/microchip/lan969x/lan969x_vcap_impl.c new file mode 100644 index 000000000000..543a1f2bf6bd --- /dev/null +++ b/drivers/net/ethernet/microchip/lan969x/lan969x_vcap_impl.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include "vcap_api.h" +#include "lan969x.h" + +const struct sparx5_vcap_inst lan969x_vcap_inst_cfg[] = { + { + .vtype = VCAP_TYPE_IS0, /* CLM-0 */ + .vinst = 0, + .map_id = 1, + .lookups = SPARX5_IS0_LOOKUPS, + .lookups_per_instance = SPARX5_IS0_LOOKUPS / 3, + .first_cid = SPARX5_VCAP_CID_IS0_L0, + .last_cid = SPARX5_VCAP_CID_IS0_L2 - 1, + .blockno = 2, + .blocks = 1, + .ingress = true, + }, + { + .vtype = VCAP_TYPE_IS0, /* CLM-1 */ + .vinst = 1, + .map_id = 2, + .lookups = SPARX5_IS0_LOOKUPS, + .lookups_per_instance = SPARX5_IS0_LOOKUPS / 3, + .first_cid = SPARX5_VCAP_CID_IS0_L2, + .last_cid = SPARX5_VCAP_CID_IS0_L4 - 1, + .blockno = 3, + .blocks = 1, + .ingress = true, + }, + { + .vtype = VCAP_TYPE_IS0, /* CLM-2 */ + .vinst = 2, + .map_id = 3, + .lookups = SPARX5_IS0_LOOKUPS, + .lookups_per_instance = SPARX5_IS0_LOOKUPS / 3, + .first_cid = SPARX5_VCAP_CID_IS0_L4, + .last_cid = SPARX5_VCAP_CID_IS0_MAX, + .blockno = 4, + .blocks = 1, + .ingress = true, + }, + { + .vtype = VCAP_TYPE_IS2, /* IS2-0 */ + .vinst = 0, + .map_id = 4, + .lookups = SPARX5_IS2_LOOKUPS, + .lookups_per_instance = SPARX5_IS2_LOOKUPS / 2, + .first_cid = SPARX5_VCAP_CID_IS2_L0, + .last_cid = SPARX5_VCAP_CID_IS2_L2 - 1, + .blockno = 0, + .blocks = 1, + .ingress = true, + }, + { + .vtype = VCAP_TYPE_IS2, /* IS2-1 */ + .vinst = 1, + .map_id = 5, + .lookups = SPARX5_IS2_LOOKUPS, + .lookups_per_instance = SPARX5_IS2_LOOKUPS / 2, + .first_cid = SPARX5_VCAP_CID_IS2_L2, + .last_cid = SPARX5_VCAP_CID_IS2_MAX, + .blockno = 1, + .blocks = 1, + .ingress = true, + }, + { + .vtype = VCAP_TYPE_ES0, + .lookups = SPARX5_ES0_LOOKUPS, + .lookups_per_instance = SPARX5_ES0_LOOKUPS, + .first_cid = SPARX5_VCAP_CID_ES0_L0, + .last_cid = SPARX5_VCAP_CID_ES0_MAX, + .count = 1536, + .ingress = false, + }, + { + .vtype = VCAP_TYPE_ES2, + .lookups = SPARX5_ES2_LOOKUPS, + .lookups_per_instance = SPARX5_ES2_LOOKUPS, + .first_cid = SPARX5_VCAP_CID_ES2_L0, + .last_cid = SPARX5_VCAP_CID_ES2_MAX, + .count = 1024, + .ingress = false, + }, +}; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_calendar.c b/drivers/net/ethernet/microchip/sparx5/sparx5_calendar.c index b2a8d04ab509..5fe941c66c17 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_calendar.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_calendar.c @@ -15,7 +15,6 @@ #define SPX5_CALBITS_PER_PORT 3 /* Bit per port in calendar register */ /* DSM calendar information */ -#define SPX5_DSM_CAL_EMPTY 0xFFFF #define SPX5_DSM_CAL_TAXIS 8 #define SPX5_DSM_CAL_BW_LOSS 553 @@ -53,27 +52,32 @@ static u32 sparx5_target_bandwidth(struct sparx5 *sparx5) case SPX5_TARGET_CT_7558: case SPX5_TARGET_CT_7558TSN: return 201000; + case SPX5_TARGET_CT_LAN9691VAO: + return 46000; + case SPX5_TARGET_CT_LAN9694RED: + case SPX5_TARGET_CT_LAN9694TSN: + case SPX5_TARGET_CT_LAN9694: + return 68000; + case SPX5_TARGET_CT_LAN9696RED: + case SPX5_TARGET_CT_LAN9696TSN: + case SPX5_TARGET_CT_LAN9692VAO: + case SPX5_TARGET_CT_LAN9696: + return 88000; + case SPX5_TARGET_CT_LAN9698RED: + case SPX5_TARGET_CT_LAN9698TSN: + case SPX5_TARGET_CT_LAN9693VAO: + case SPX5_TARGET_CT_LAN9698: + return 101000; default: return 0; } } -/* This is used in calendar configuration */ -enum sparx5_cal_bw { - SPX5_CAL_SPEED_NONE = 0, - SPX5_CAL_SPEED_1G = 1, - SPX5_CAL_SPEED_2G5 = 2, - SPX5_CAL_SPEED_5G = 3, - SPX5_CAL_SPEED_10G = 4, - SPX5_CAL_SPEED_25G = 5, - SPX5_CAL_SPEED_0G5 = 6, - SPX5_CAL_SPEED_12G5 = 7 -}; - static u32 sparx5_clk_to_bandwidth(enum sparx5_core_clockfreq cclock) { switch (cclock) { case SPX5_CORE_CLOCK_250MHZ: return 83000; /* 250000 / 3 */ + case SPX5_CORE_CLOCK_328MHZ: return 109375; /* 328000 / 3 */ case SPX5_CORE_CLOCK_500MHZ: return 166000; /* 500000 / 3 */ case SPX5_CORE_CLOCK_625MHZ: return 208000; /* 625000 / 3 */ default: return 0; @@ -81,7 +85,7 @@ static u32 sparx5_clk_to_bandwidth(enum sparx5_core_clockfreq cclock) return 0; } -static u32 sparx5_cal_speed_to_value(enum sparx5_cal_bw speed) +u32 sparx5_cal_speed_to_value(enum sparx5_cal_bw speed) { switch (speed) { case SPX5_CAL_SPEED_1G: return 1000; @@ -94,6 +98,7 @@ static u32 sparx5_cal_speed_to_value(enum sparx5_cal_bw speed) default: return 0; } } +EXPORT_SYMBOL_GPL(sparx5_cal_speed_to_value); static u32 sparx5_bandwidth_to_calendar(u32 bw) { @@ -111,8 +116,7 @@ static u32 sparx5_bandwidth_to_calendar(u32 bw) } } -static enum sparx5_cal_bw sparx5_get_port_cal_speed(struct sparx5 *sparx5, - u32 portno) +enum sparx5_cal_bw sparx5_get_port_cal_speed(struct sparx5 *sparx5, u32 portno) { struct sparx5_port *port; @@ -146,6 +150,7 @@ static enum sparx5_cal_bw sparx5_get_port_cal_speed(struct sparx5 *sparx5, return SPX5_CAL_SPEED_NONE; return sparx5_bandwidth_to_calendar(port->conf.bandwidth); } +EXPORT_SYMBOL_GPL(sparx5_get_port_cal_speed); /* Auto configure the QSYS calendar based on port configuration */ int sparx5_config_auto_calendar(struct sparx5 *sparx5) @@ -526,12 +531,23 @@ check_err: static int sparx5_dsm_calendar_update(struct sparx5 *sparx5, u32 taxi, struct sparx5_calendar_data *data) { - u32 idx; - u32 cal_len = sparx5_dsm_cal_len(data->schedule), len; + u32 cal_len = sparx5_dsm_cal_len(data->schedule), len, idx; + + if (!is_sparx5(sparx5)) { + u32 val, act; + + val = spx5_rd(sparx5, DSM_TAXI_CAL_CFG(taxi)); + act = DSM_TAXI_CAL_CFG_CAL_SEL_STAT_GET(val); + + spx5_rmw(DSM_TAXI_CAL_CFG_CAL_PGM_SEL_SET(!act), + DSM_TAXI_CAL_CFG_CAL_PGM_SEL, + sparx5, DSM_TAXI_CAL_CFG(taxi)); + } - spx5_wr(DSM_TAXI_CAL_CFG_CAL_PGM_ENA_SET(1), - sparx5, - DSM_TAXI_CAL_CFG(taxi)); + spx5_rmw(DSM_TAXI_CAL_CFG_CAL_PGM_ENA_SET(1), + DSM_TAXI_CAL_CFG_CAL_PGM_ENA, + sparx5, + DSM_TAXI_CAL_CFG(taxi)); for (idx = 0; idx < cal_len; idx++) { spx5_rmw(DSM_TAXI_CAL_CFG_CAL_IDX_SET(idx), DSM_TAXI_CAL_CFG_CAL_IDX, @@ -542,13 +558,21 @@ static int sparx5_dsm_calendar_update(struct sparx5 *sparx5, u32 taxi, sparx5, DSM_TAXI_CAL_CFG(taxi)); } - spx5_wr(DSM_TAXI_CAL_CFG_CAL_PGM_ENA_SET(0), - sparx5, - DSM_TAXI_CAL_CFG(taxi)); + spx5_rmw(DSM_TAXI_CAL_CFG_CAL_PGM_ENA_SET(0), + DSM_TAXI_CAL_CFG_CAL_PGM_ENA, + sparx5, + DSM_TAXI_CAL_CFG(taxi)); len = DSM_TAXI_CAL_CFG_CAL_CUR_LEN_GET(spx5_rd(sparx5, DSM_TAXI_CAL_CFG(taxi))); if (len != cal_len - 1) goto update_err; + + if (!is_sparx5(sparx5)) { + spx5_rmw(DSM_TAXI_CAL_CFG_CAL_SWITCH_SET(1), + DSM_TAXI_CAL_CFG_CAL_SWITCH, + sparx5, DSM_TAXI_CAL_CFG(taxi)); + } + return 0; update_err: dev_err(sparx5->dev, "Incorrect calendar length: %u\n", len); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c index 88f7509f0980..0027144a2af2 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c @@ -154,7 +154,7 @@ static bool sparx5_fdma_rx_get_frame(struct sparx5 *sparx5, struct sparx5_rx *rx skb = rx->skb[fdma->dcb_index][fdma->db_index]; skb_put(skb, fdma_db_len_get(db_hw)); /* Now do the normal processing of the skb */ - sparx5_ifh_parse((u32 *)skb->data, &fi); + sparx5_ifh_parse(sparx5, (u32 *)skb->data, &fi); /* Map to port netdev */ port = fi.src_port < sparx5->data->consts->n_ports ? sparx5->ports[fi.src_port] : diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index d1e9bc030c80..2f1013f870fb 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -24,10 +24,14 @@ #include <linux/types.h> #include <linux/reset.h> +#include "../lan969x/lan969x.h" /* for lan969x match data */ + #include "sparx5_main_regs.h" #include "sparx5_main.h" #include "sparx5_port.h" #include "sparx5_qos.h" +#include "sparx5_vcap_ag_api.h" +#include "sparx5_vcap_impl.h" const struct sparx5_regs *regs; @@ -227,6 +231,40 @@ bool is_sparx5(struct sparx5 *sparx5) } } +static void sparx5_init_features(struct sparx5 *sparx5) +{ + switch (sparx5->target_ct) { + case SPX5_TARGET_CT_7546: + case SPX5_TARGET_CT_7549: + case SPX5_TARGET_CT_7552: + case SPX5_TARGET_CT_7556: + case SPX5_TARGET_CT_7558: + case SPX5_TARGET_CT_7546TSN: + case SPX5_TARGET_CT_7549TSN: + case SPX5_TARGET_CT_7552TSN: + case SPX5_TARGET_CT_7556TSN: + case SPX5_TARGET_CT_7558TSN: + case SPX5_TARGET_CT_LAN9691VAO: + case SPX5_TARGET_CT_LAN9694TSN: + case SPX5_TARGET_CT_LAN9694RED: + case SPX5_TARGET_CT_LAN9692VAO: + case SPX5_TARGET_CT_LAN9696TSN: + case SPX5_TARGET_CT_LAN9696RED: + case SPX5_TARGET_CT_LAN9693VAO: + case SPX5_TARGET_CT_LAN9698TSN: + case SPX5_TARGET_CT_LAN9698RED: + sparx5->features = (SPX5_FEATURE_PSFP | SPX5_FEATURE_PTP); + break; + default: + break; + } +} + +bool sparx5_has_feature(struct sparx5 *sparx5, enum sparx5_feature feature) +{ + return sparx5->features & feature; +} + static int sparx5_create_targets(struct sparx5 *sparx5) { const struct sparx5_main_io_resource *iomap = sparx5->data->iomap; @@ -475,6 +513,20 @@ static int sparx5_init_coreclock(struct sparx5 *sparx5) else if (sparx5->coreclock == SPX5_CORE_CLOCK_250MHZ) freq = 0; /* Not supported */ break; + case SPX5_TARGET_CT_LAN9694: + case SPX5_TARGET_CT_LAN9691VAO: + case SPX5_TARGET_CT_LAN9694TSN: + case SPX5_TARGET_CT_LAN9694RED: + case SPX5_TARGET_CT_LAN9696: + case SPX5_TARGET_CT_LAN9692VAO: + case SPX5_TARGET_CT_LAN9696TSN: + case SPX5_TARGET_CT_LAN9696RED: + case SPX5_TARGET_CT_LAN9698: + case SPX5_TARGET_CT_LAN9693VAO: + case SPX5_TARGET_CT_LAN9698TSN: + case SPX5_TARGET_CT_LAN9698RED: + freq = SPX5_CORE_CLOCK_328MHZ; + break; default: dev_err(sparx5->dev, "Target (%#04x) not supported\n", sparx5->target_ct); @@ -516,16 +568,19 @@ static int sparx5_init_coreclock(struct sparx5 *sparx5) CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_ENA | CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_ENA, sparx5, CLKGEN_LCPLL1_CORE_CLK_CFG); + } else { + pol_upd_int = 820; // SPX5_CORE_CLOCK_328MHZ } /* Update state with chosen frequency */ sparx5->coreclock = freq; clk_period = sparx5_clk_period(freq); - spx5_rmw(HSCH_SYS_CLK_PER_100PS_SET(clk_period / 100), - HSCH_SYS_CLK_PER_100PS, - sparx5, - HSCH_SYS_CLK_PER); + if (is_sparx5(sparx5)) + spx5_rmw(HSCH_SYS_CLK_PER_100PS_SET(clk_period / 100), + HSCH_SYS_CLK_PER_100PS, + sparx5, + HSCH_SYS_CLK_PER); spx5_rmw(ANA_AC_POL_BDLB_DLB_CTRL_CLK_PERIOD_01NS_SET(clk_period / 100), ANA_AC_POL_BDLB_DLB_CTRL_CLK_PERIOD_01NS, @@ -723,7 +778,7 @@ static int sparx5_start(struct sparx5 *sparx5) /* Start Frame DMA with fallback to register based INJ/XTR */ err = -ENXIO; - if (sparx5->fdma_irq >= 0) { + if (sparx5->fdma_irq >= 0 && is_sparx5(sparx5)) { if (GCB_CHIP_ID_REV_ID_GET(sparx5->chip_id) > 0) err = devm_request_threaded_irq(sparx5->dev, sparx5->fdma_irq, @@ -750,7 +805,8 @@ static int sparx5_start(struct sparx5 *sparx5) sparx5->xtr_irq = -ENXIO; } - if (sparx5->ptp_irq >= 0) { + if (sparx5->ptp_irq >= 0 && + sparx5_has_feature(sparx5, SPX5_FEATURE_PTP)) { err = devm_request_threaded_irq(sparx5->dev, sparx5->ptp_irq, NULL, ops->ptp_irq_handler, IRQF_ONESHOT, "sparx5-ptp", @@ -894,6 +950,9 @@ static int mchp_sparx5_probe(struct platform_device *pdev) sparx5->target_ct = (enum spx5_target_chiptype) GCB_CHIP_ID_PART_ID_GET(sparx5->chip_id); + /* Initialize the features based on the target */ + sparx5_init_features(sparx5); + /* Initialize Switchcore and internal RAMs */ err = sparx5_init_switchcore(sparx5); if (err) { @@ -1004,6 +1063,9 @@ static const struct sparx5_consts sparx5_consts = { .qres_max_prio_idx = 630, .qres_max_colour_idx = 638, .tod_pin = 4, + .vcaps = sparx5_vcaps, + .vcaps_cfg = sparx5_vcap_inst_cfg, + .vcap_stats = &sparx5_vcap_stats, }; static const struct sparx5_ops sparx5_ops = { @@ -1031,6 +1093,9 @@ static const struct sparx5_match_data sparx5_desc = { static const struct of_device_id mchp_sparx5_match[] = { { .compatible = "microchip,sparx5-switch", .data = &sparx5_desc }, +#if IS_ENABLED(CONFIG_LAN969X_SWITCH) + { .compatible = "microchip,lan9691-switch", .data = &lan969x_desc }, +#endif { } }; MODULE_DEVICE_TABLE(of, mchp_sparx5_match); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index 364ae92969bc..d5dd953b0a71 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -26,16 +26,28 @@ /* Target chip type */ enum spx5_target_chiptype { - SPX5_TARGET_CT_7546 = 0x7546, /* SparX-5-64 Enterprise */ - SPX5_TARGET_CT_7549 = 0x7549, /* SparX-5-90 Enterprise */ - SPX5_TARGET_CT_7552 = 0x7552, /* SparX-5-128 Enterprise */ - SPX5_TARGET_CT_7556 = 0x7556, /* SparX-5-160 Enterprise */ - SPX5_TARGET_CT_7558 = 0x7558, /* SparX-5-200 Enterprise */ - SPX5_TARGET_CT_7546TSN = 0x47546, /* SparX-5-64i Industrial */ - SPX5_TARGET_CT_7549TSN = 0x47549, /* SparX-5-90i Industrial */ - SPX5_TARGET_CT_7552TSN = 0x47552, /* SparX-5-128i Industrial */ - SPX5_TARGET_CT_7556TSN = 0x47556, /* SparX-5-160i Industrial */ - SPX5_TARGET_CT_7558TSN = 0x47558, /* SparX-5-200i Industrial */ + SPX5_TARGET_CT_7546 = 0x7546, /* SparX-5-64 Enterprise */ + SPX5_TARGET_CT_7549 = 0x7549, /* SparX-5-90 Enterprise */ + SPX5_TARGET_CT_7552 = 0x7552, /* SparX-5-128 Enterprise */ + SPX5_TARGET_CT_7556 = 0x7556, /* SparX-5-160 Enterprise */ + SPX5_TARGET_CT_7558 = 0x7558, /* SparX-5-200 Enterprise */ + SPX5_TARGET_CT_7546TSN = 0x47546, /* SparX-5-64i Industrial */ + SPX5_TARGET_CT_7549TSN = 0x47549, /* SparX-5-90i Industrial */ + SPX5_TARGET_CT_7552TSN = 0x47552, /* SparX-5-128i Industrial */ + SPX5_TARGET_CT_7556TSN = 0x47556, /* SparX-5-160i Industrial */ + SPX5_TARGET_CT_7558TSN = 0x47558, /* SparX-5-200i Industrial */ + SPX5_TARGET_CT_LAN9694 = 0x9694, /* lan969x-40 */ + SPX5_TARGET_CT_LAN9691VAO = 0x9691, /* lan969x-40-VAO */ + SPX5_TARGET_CT_LAN9694TSN = 0x9695, /* lan969x-40-TSN */ + SPX5_TARGET_CT_LAN9694RED = 0x969A, /* lan969x-40-RED */ + SPX5_TARGET_CT_LAN9696 = 0x9696, /* lan969x-60 */ + SPX5_TARGET_CT_LAN9692VAO = 0x9692, /* lan969x-65-VAO */ + SPX5_TARGET_CT_LAN9696TSN = 0x9697, /* lan969x-60-TSN */ + SPX5_TARGET_CT_LAN9696RED = 0x969B, /* lan969x-60-RED */ + SPX5_TARGET_CT_LAN9698 = 0x9698, /* lan969x-100 */ + SPX5_TARGET_CT_LAN9693VAO = 0x9693, /* lan969x-100-VAO */ + SPX5_TARGET_CT_LAN9698TSN = 0x9699, /* lan969x-100-TSN */ + SPX5_TARGET_CT_LAN9698RED = 0x969C, /* lan969x-100-RED */ }; enum sparx5_port_max_tags { @@ -51,6 +63,23 @@ enum sparx5_vlan_port_type { SPX5_VLAN_PORT_TYPE_S_CUSTOM /* S-port using custom type */ }; +/* This is used in calendar configuration */ +enum sparx5_cal_bw { + SPX5_CAL_SPEED_NONE = 0, + SPX5_CAL_SPEED_1G = 1, + SPX5_CAL_SPEED_2G5 = 2, + SPX5_CAL_SPEED_5G = 3, + SPX5_CAL_SPEED_10G = 4, + SPX5_CAL_SPEED_25G = 5, + SPX5_CAL_SPEED_0G5 = 6, + SPX5_CAL_SPEED_12G5 = 7 +}; + +enum sparx5_feature { + SPX5_FEATURE_PSFP = BIT(0), + SPX5_FEATURE_PTP = BIT(1), +}; + #define SPX5_PORTS 65 #define SPX5_PORTS_ALL 70 /* Total number of ports */ @@ -101,6 +130,9 @@ enum sparx5_vlan_port_type { #define SPX5_DSM_CAL_LEN 64 #define SPX5_DSM_CAL_MAX_DEVS_PER_TAXI 13 +#define SPX5_DSM_CAL_EMPTY 0xFFFF + +#define SPARX5_MAX_PTP_ID 512 struct sparx5; @@ -192,6 +224,7 @@ struct sparx5_port { enum sparx5_core_clockfreq { SPX5_CORE_CLOCK_DEFAULT, /* Defaults to the highest supported frequency */ SPX5_CORE_CLOCK_250MHZ, /* 250MHZ core clock frequency */ + SPX5_CORE_CLOCK_328MHZ, /* 328MHZ core clock frequency */ SPX5_CORE_CLOCK_500MHZ, /* 500MHZ core clock frequency */ SPX5_CORE_CLOCK_625MHZ, /* 625MHZ core clock frequency */ }; @@ -270,6 +303,9 @@ struct sparx5_consts { u32 qres_max_prio_idx; /* Maximum QRES prio index */ u32 qres_max_colour_idx; /* Maximum QRES colour index */ u32 tod_pin; /* PTP TOD pin */ + const struct sparx5_vcap_inst *vcaps_cfg; + const struct vcap_info *vcaps; + const struct vcap_statistics *vcap_stats; }; struct sparx5_ops { @@ -309,6 +345,7 @@ struct sparx5 { struct device *dev; u32 chip_id; enum spx5_target_chiptype target_ct; + u32 features; void __iomem *regs[NUM_TARGETS]; int port_count; struct mutex lock; /* MAC reg lock */ @@ -376,6 +413,7 @@ struct sparx5 { /* sparx5_main.c */ bool is_sparx5(struct sparx5 *sparx5); +bool sparx5_has_feature(struct sparx5 *sparx5, enum sparx5_feature feature); /* sparx5_switchdev.c */ int sparx5_register_notifier_blocks(struct sparx5 *sparx5); @@ -388,7 +426,7 @@ struct frame_info { }; void sparx5_xtr_flush(struct sparx5 *sparx5, u8 grp); -void sparx5_ifh_parse(u32 *ifh, struct frame_info *info); +void sparx5_ifh_parse(struct sparx5 *sparx5, u32 *ifh, struct frame_info *info); irqreturn_t sparx5_xtr_handler(int irq, void *_priv); netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev); int sparx5_manual_injection_mode(struct sparx5 *sparx5); @@ -439,6 +477,8 @@ int sparx5_config_auto_calendar(struct sparx5 *sparx5); int sparx5_config_dsm_calendar(struct sparx5 *sparx5); int sparx5_dsm_calendar_calc(struct sparx5 *sparx5, u32 taxi, struct sparx5_calendar_data *data); +u32 sparx5_cal_speed_to_value(enum sparx5_cal_bw speed); +enum sparx5_cal_bw sparx5_get_port_cal_speed(struct sparx5 *sparx5, u32 portno); /* sparx5_ethtool.c */ @@ -456,10 +496,13 @@ static inline int sparx5_dcb_init(struct sparx5 *sparx5) #endif /* sparx5_netdev.c */ -void sparx5_set_port_ifh_timestamp(void *ifh_hdr, u64 timestamp); +void sparx5_set_port_ifh_timestamp(struct sparx5 *sparx5, void *ifh_hdr, + u64 timestamp); void sparx5_set_port_ifh_rew_op(void *ifh_hdr, u32 rew_op); -void sparx5_set_port_ifh_pdu_type(void *ifh_hdr, u32 pdu_type); -void sparx5_set_port_ifh_pdu_w16_offset(void *ifh_hdr, u32 pdu_w16_offset); +void sparx5_set_port_ifh_pdu_type(struct sparx5 *sparx5, void *ifh_hdr, + u32 pdu_type); +void sparx5_set_port_ifh_pdu_w16_offset(struct sparx5 *sparx5, void *ifh_hdr, + u32 pdu_w16_offset); void sparx5_set_port_ifh(struct sparx5 *sparx5, void *ifh_hdr, u16 portno); bool sparx5_netdevice_check(const struct net_device *dev); struct net_device *sparx5_create_netdev(struct sparx5 *sparx5, u32 portno); @@ -483,6 +526,9 @@ void sparx5_ptp_txtstamp_release(struct sparx5_port *port, struct sk_buff *skb); irqreturn_t sparx5_ptp_irq_handler(int irq, void *args); int sparx5_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts); +void sparx5_get_hwtimestamp(struct sparx5 *sparx5, + struct timespec64 *ts, + u32 nsec); /* sparx5_vcap_impl.c */ int sparx5_vcap_init(struct sparx5 *sparx5); @@ -539,7 +585,7 @@ struct sparx5_sdlb_group *sparx5_get_sdlb_group(int idx); int sparx5_sdlb_pup_token_get(struct sparx5 *sparx5, u32 pup_interval, u64 rate); -int sparx5_sdlb_clk_hz_get(struct sparx5 *sparx5); +u64 sparx5_sdlb_clk_hz_get(struct sparx5 *sparx5); int sparx5_sdlb_group_get_by_rate(struct sparx5 *sparx5, u32 rate, u32 burst); int sparx5_sdlb_group_get_by_index(struct sparx5 *sparx5, u32 idx, u32 *group); @@ -641,6 +687,8 @@ static inline u32 sparx5_clk_period(enum sparx5_core_clockfreq cclock) switch (cclock) { case SPX5_CORE_CLOCK_250MHZ: return 4000; + case SPX5_CORE_CLOCK_328MHZ: + return 3048; case SPX5_CORE_CLOCK_500MHZ: return 2000; case SPX5_CORE_CLOCK_625MHZ: diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h index 0e8b18bcf179..561344f19062 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h @@ -2666,6 +2666,44 @@ extern const struct sparx5_regs *regs; #define CPU_PROC_CTRL_ACP_DISABLE_GET(x)\ FIELD_GET(CPU_PROC_CTRL_ACP_DISABLE, x) +/* DEV1G:PHASE_DETECTOR_CTRL:PHAD_CTRL */ +#define DEV2G5_PHAD_CTRL(t, g) \ + __REG(TARGET_DEV2G5, t, regs->tsize[TC_DEV2G5], 200, g, 2, \ + regs->gsize[GW_DEV2G5_PHASE_DETECTOR_CTRL], 0, 0, 1, 4) + +#define DEV2G5_PHAD_CTRL_PHAD_ENA\ + BIT(regs->fpos[FP_DEV2G5_PHAD_CTRL_PHAD_ENA]) +#define DEV2G5_PHAD_CTRL_PHAD_ENA_SET(x)\ + spx5_field_prep(DEV2G5_PHAD_CTRL_PHAD_ENA, x) +#define DEV2G5_PHAD_CTRL_PHAD_ENA_GET(x)\ + spx5_field_get(DEV2G5_PHAD_CTRL_PHAD_ENA, x) + +/* LAN969X ONLY */ +#define DEV2G5_PHAD_CTRL_DIV_CFG GENMASK(11, 9) +#define DEV2G5_PHAD_CTRL_DIV_CFG_SET(x)\ + FIELD_PREP(DEV2G5_PHAD_CTRL_DIV_CFG, x) +#define DEV2G5_PHAD_CTRL_DIV_CFG_GET(x)\ + FIELD_GET(DEV2G5_PHAD_CTRL_DIV_CFG, x) + +/* DEV1G:PHASE_DETECTOR_CTRL:PHAD_CTRL */ +#define DEV2G5_PHAD_CTRL(t, g) \ + __REG(TARGET_DEV2G5, t, regs->tsize[TC_DEV2G5], 200, g, 2, \ + regs->gsize[GW_DEV2G5_PHASE_DETECTOR_CTRL], 0, 0, 1, 4) + +#define DEV2G5_PHAD_CTRL_PHAD_ENA\ + BIT(regs->fpos[FP_DEV2G5_PHAD_CTRL_PHAD_ENA]) +#define DEV2G5_PHAD_CTRL_PHAD_ENA_SET(x)\ + spx5_field_prep(DEV2G5_PHAD_CTRL_PHAD_ENA, x) +#define DEV2G5_PHAD_CTRL_PHAD_ENA_GET(x)\ + spx5_field_get(DEV2G5_PHAD_CTRL_PHAD_ENA, x) + +/* LAN969X ONLY */ +#define DEV2G5_PHAD_CTRL_DIV_CFG GENMASK(11, 9) +#define DEV2G5_PHAD_CTRL_DIV_CFG_SET(x)\ + FIELD_PREP(DEV2G5_PHAD_CTRL_DIV_CFG, x) +#define DEV2G5_PHAD_CTRL_DIV_CFG_GET(x)\ + FIELD_GET(DEV2G5_PHAD_CTRL_DIV_CFG, x) + /* DEV10G:MAC_CFG_STATUS:MAC_ENA_CFG */ #define DEV10G_MAC_ENA_CFG(t) \ __REG(TARGET_DEV10G, t, regs->tsize[TC_DEV10G], 0, 0, 1, 60, 0, 0, 1, \ @@ -2869,6 +2907,11 @@ extern const struct sparx5_regs *regs; #define DEV10G_DEV_RST_CTRL_MAC_RX_RST_GET(x)\ FIELD_GET(DEV10G_DEV_RST_CTRL_MAC_RX_RST, x) +/* DEV10G:DEV_CFG_STATUS:PTP_STAMPER_CFG */ +#define DEV10G_PTP_STAMPER_CFG(t) \ + __REG(TARGET_DEV10G, t, regs->tsize[TC_DEV10G], 436, 0, 1, 52, 20, 0, \ + 1, 4) + /* DEV10G:PCS25G_CFG_STATUS:PCS25G_CFG */ #define DEV10G_PCS25G_CFG(t) \ __REG(TARGET_DEV10G, t, regs->tsize[TC_DEV10G], 488, 0, 1, 32, 0, 0, 1,\ @@ -4267,6 +4310,11 @@ extern const struct sparx5_regs *regs; #define DEV5G_DEV_RST_CTRL_MAC_RX_RST_GET(x)\ FIELD_GET(DEV5G_DEV_RST_CTRL_MAC_RX_RST, x) +/* DEV10G:DEV_CFG_STATUS:PTP_STAMPER_CFG */ +#define DEV5G_PTP_STAMPER_CFG(t) \ + __REG(TARGET_DEV5G, t, regs->tsize[TC_DEV5G], 436, 0, 1, 52, 20, 0, 1, \ + 4) + /* DSM:RAM_CTRL:RAM_INIT */ #define DSM_RAM_INIT \ __REG(TARGET_DSM, 0, 1, 0, 0, 1, 4, 0, 0, 1, 4) @@ -4444,6 +4492,27 @@ extern const struct sparx5_regs *regs; #define DSM_TAXI_CAL_CFG_CAL_PGM_ENA_GET(x)\ FIELD_GET(DSM_TAXI_CAL_CFG_CAL_PGM_ENA, x) +/* LAN969X ONLY */ +#define DSM_TAXI_CAL_CFG_CAL_SEL_STAT BIT(23) +#define DSM_TAXI_CAL_CFG_CAL_SEL_STAT_SET(x)\ + FIELD_PREP(DSM_TAXI_CAL_CFG_CAL_SEL_STAT, x) +#define DSM_TAXI_CAL_CFG_CAL_SEL_STAT_GET(x)\ + FIELD_GET(DSM_TAXI_CAL_CFG_CAL_SEL_STAT, x) + +/* LAN969X ONLY */ +#define DSM_TAXI_CAL_CFG_CAL_SWITCH BIT(22) +#define DSM_TAXI_CAL_CFG_CAL_SWITCH_SET(x)\ + FIELD_PREP(DSM_TAXI_CAL_CFG_CAL_SWITCH, x) +#define DSM_TAXI_CAL_CFG_CAL_SWITCH_GET(x)\ + FIELD_GET(DSM_TAXI_CAL_CFG_CAL_SWITCH, x) + +/* LAN969X ONLY */ +#define DSM_TAXI_CAL_CFG_CAL_PGM_SEL BIT(21) +#define DSM_TAXI_CAL_CFG_CAL_PGM_SEL_SET(x)\ + FIELD_PREP(DSM_TAXI_CAL_CFG_CAL_PGM_SEL, x) +#define DSM_TAXI_CAL_CFG_CAL_PGM_SEL_GET(x)\ + FIELD_GET(DSM_TAXI_CAL_CFG_CAL_PGM_SEL, x) + /* EACL:ES2_KEY_SELECT_PROFILE:VCAP_ES2_KEY_SEL */ #define EACL_VCAP_ES2_KEY_SEL(g, r) \ __REG(TARGET_EACL, 0, 1, regs->gaddr[GA_EACL_ES2_KEY_SELECT_PROFILE], \ @@ -6720,6 +6789,69 @@ extern const struct sparx5_regs *regs; regs->gcnt[GC_PTP_PHASE_DETECTOR_CTRL], \ regs->gsize[GW_PTP_PHASE_DETECTOR_CTRL], 4, 0, 1, 4) +/* LAN969X ONLY */ +/* DEVCPU_PTP:PTP_TS_FIFO:PTP_TWOSTEP_CTRL */ +#define PTP_TWOSTEP_CTRL \ + __REG(TARGET_PTP, 0, 1, 612, 0, 1, 16, 0, 0, 1, 4) + +#define PTP_TWOSTEP_CTRL_PTP_OVWR_ENA BIT(12) +#define PTP_TWOSTEP_CTRL_PTP_OVWR_ENA_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_PTP_OVWR_ENA, x) +#define PTP_TWOSTEP_CTRL_PTP_OVWR_ENA_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_PTP_OVWR_ENA, x) + +#define PTP_TWOSTEP_CTRL_PTP_NXT BIT(11) +#define PTP_TWOSTEP_CTRL_PTP_NXT_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_PTP_NXT, x) +#define PTP_TWOSTEP_CTRL_PTP_NXT_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_PTP_NXT, x) + +#define PTP_TWOSTEP_CTRL_PTP_VLD BIT(10) +#define PTP_TWOSTEP_CTRL_PTP_VLD_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_PTP_VLD, x) +#define PTP_TWOSTEP_CTRL_PTP_VLD_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_PTP_VLD, x) + +#define PTP_TWOSTEP_CTRL_STAMP_TX BIT(9) +#define PTP_TWOSTEP_CTRL_STAMP_TX_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_STAMP_TX, x) +#define PTP_TWOSTEP_CTRL_STAMP_TX_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_STAMP_TX, x) + +#define PTP_TWOSTEP_CTRL_STAMP_PORT GENMASK(8, 1) +#define PTP_TWOSTEP_CTRL_STAMP_PORT_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_STAMP_PORT, x) +#define PTP_TWOSTEP_CTRL_STAMP_PORT_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_STAMP_PORT, x) + +#define PTP_TWOSTEP_CTRL_PTP_OVFL BIT(0) +#define PTP_TWOSTEP_CTRL_PTP_OVFL_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_PTP_OVFL, x) +#define PTP_TWOSTEP_CTRL_PTP_OVFL_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_PTP_OVFL, x) + +/* LAN969X ONLY */ +/* DEVCPU_PTP:PTP_TS_FIFO:PTP_TWOSTEP_STAMP_NSEC */ +#define PTP_TWOSTEP_STAMP_NSEC \ + __REG(TARGET_PTP, 0, 1, 612, 0, 1, 16, 4, 0, 1, 4) + +#define PTP_TWOSTEP_STAMP_NSEC_NS GENMASK(29, 0) +#define PTP_TWOSTEP_STAMP_NSEC_NS_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_STAMP_NSEC_NS, x) +#define PTP_TWOSTEP_STAMP_NSEC_NS_GET(x)\ + FIELD_GET(PTP_TWOSTEP_STAMP_NSEC_NS, x) + +/* LAN969X ONLY */ +/* DEVCPU_PTP:PTP_TS_FIFO:PTP_TWOSTEP_STAMP_SUBNS */ +#define PTP_TWOSTEP_STAMP_SUBNS \ + __REG(TARGET_PTP, 0, 1, 612, 0, 1, 16, 8, 0, 1, 4) + +#define PTP_TWOSTEP_STAMP_SUBNS_NS GENMASK(7, 0) +#define PTP_TWOSTEP_STAMP_SUBNS_NS_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_STAMP_SUBNS_NS, x) +#define PTP_TWOSTEP_STAMP_SUBNS_NS_GET(x)\ + FIELD_GET(PTP_TWOSTEP_STAMP_SUBNS_NS, x) + /* QFWD:SYSTEM:SWITCH_PORT_MODE */ #define QFWD_SWITCH_PORT_MODE(r) \ __REG(TARGET_QFWD, 0, 1, 0, 0, 1, 340, 0, r, \ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mirror.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mirror.c index 459a53676ae9..9806729e9c62 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_mirror.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mirror.c @@ -24,8 +24,14 @@ static u32 sparx5_mirror_to_dir(bool ingress) /* Get ports belonging to this mirror */ static u64 sparx5_mirror_port_get(struct sparx5 *sparx5, u32 idx) { - return (u64)spx5_rd(sparx5, ANA_AC_PROBE_PORT_CFG1(idx)) << 32 | - spx5_rd(sparx5, ANA_AC_PROBE_PORT_CFG(idx)); + u64 val; + + val = spx5_rd(sparx5, ANA_AC_PROBE_PORT_CFG(idx)); + + if (is_sparx5(sparx5)) + val |= (u64)spx5_rd(sparx5, ANA_AC_PROBE_PORT_CFG1(idx)) << 32; + + return val; } /* Add port to mirror (only front ports) */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c index d4e9986ef16a..1d34af78166a 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c @@ -64,16 +64,16 @@ void sparx5_set_port_ifh(struct sparx5 *sparx5, void *ifh_hdr, u16 portno) /* MISC.CPU_MASK/DPORT = Destination port */ ifh_encode_bitfield(ifh_hdr, portno, 29, 8); /* MISC.PIPELINE_PT */ - ifh_encode_bitfield(ifh_hdr, 16, 37, 5); + ifh_encode_bitfield(ifh_hdr, is_sparx5(sparx5) ? 16 : 17, 37, 5); /* MISC.PIPELINE_ACT */ ifh_encode_bitfield(ifh_hdr, 1, 42, 3); /* FWD.SRC_PORT = CPU */ ifh_encode_bitfield(ifh_hdr, sparx5_get_pgid(sparx5, SPX5_PORT_CPU_0), - 46, 7); + 46, is_sparx5(sparx5) ? 7 : 6); /* FWD.SFLOW_ID (disable SFlow sampling) */ - ifh_encode_bitfield(ifh_hdr, 124, 57, 7); + ifh_encode_bitfield(ifh_hdr, 124, is_sparx5(sparx5) ? 57 : 56, 7); /* FWD.UPDATE_FCS = Enable. Enforce update of FCS. */ - ifh_encode_bitfield(ifh_hdr, 1, 67, 1); + ifh_encode_bitfield(ifh_hdr, 1, is_sparx5(sparx5) ? 67 : 66, 1); } void sparx5_set_port_ifh_rew_op(void *ifh_hdr, u32 rew_op) @@ -81,19 +81,25 @@ void sparx5_set_port_ifh_rew_op(void *ifh_hdr, u32 rew_op) ifh_encode_bitfield(ifh_hdr, rew_op, VSTAX + 32, 10); } -void sparx5_set_port_ifh_pdu_type(void *ifh_hdr, u32 pdu_type) +void sparx5_set_port_ifh_pdu_type(struct sparx5 *sparx5, void *ifh_hdr, + u32 pdu_type) { - ifh_encode_bitfield(ifh_hdr, pdu_type, 191, 4); + ifh_encode_bitfield(ifh_hdr, pdu_type, is_sparx5(sparx5) ? 191 : 190, + 4); } -void sparx5_set_port_ifh_pdu_w16_offset(void *ifh_hdr, u32 pdu_w16_offset) +void sparx5_set_port_ifh_pdu_w16_offset(struct sparx5 *sparx5, void *ifh_hdr, + u32 pdu_w16_offset) { - ifh_encode_bitfield(ifh_hdr, pdu_w16_offset, 195, 6); + ifh_encode_bitfield(ifh_hdr, pdu_w16_offset, + is_sparx5(sparx5) ? 195 : 194, 6); } -void sparx5_set_port_ifh_timestamp(void *ifh_hdr, u64 timestamp) +void sparx5_set_port_ifh_timestamp(struct sparx5 *sparx5, void *ifh_hdr, + u64 timestamp) { - ifh_encode_bitfield(ifh_hdr, timestamp, 232, 40); + ifh_encode_bitfield(ifh_hdr, timestamp, 232, + is_sparx5(sparx5) ? 40 : 38); } static int sparx5_port_open(struct net_device *ndev) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index 5bfa86a71ac8..b6f635d85820 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -32,7 +32,7 @@ void sparx5_xtr_flush(struct sparx5 *sparx5, u8 grp) spx5_wr(0, sparx5, QS_XTR_FLUSH); } -void sparx5_ifh_parse(u32 *ifh, struct frame_info *info) +void sparx5_ifh_parse(struct sparx5 *sparx5, u32 *ifh, struct frame_info *info) { u8 *xtr_hdr = (u8 *)ifh; @@ -43,7 +43,8 @@ void sparx5_ifh_parse(u32 *ifh, struct frame_info *info) ((u32)xtr_hdr[29] << 8) | ((u32)xtr_hdr[30] << 0); fwd = (fwd >> 5); - info->src_port = FIELD_GET(GENMASK(7, 1), fwd); + info->src_port = spx5_field_get(GENMASK(is_sparx5(sparx5) ? 7 : 6, 1), + fwd); /* * Bit 270-271 are occasionally unexpectedly set by the hardware, @@ -72,7 +73,7 @@ static void sparx5_xtr_grp(struct sparx5 *sparx5, u8 grp, bool byte_swap) ifh[i] = spx5_rd(sparx5, QS_XTR_RD(grp)); /* Decode IFH (what's needed) */ - sparx5_ifh_parse(ifh, &fi); + sparx5_ifh_parse(sparx5, ifh, &fi); /* Map to port netdev */ port = fi.src_port < sparx5->data->consts->n_ports ? @@ -242,9 +243,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; sparx5_set_port_ifh_rew_op(ifh, SPARX5_SKB_CB(skb)->rew_op); - sparx5_set_port_ifh_pdu_type(ifh, SPARX5_SKB_CB(skb)->pdu_type); - sparx5_set_port_ifh_pdu_w16_offset(ifh, SPARX5_SKB_CB(skb)->pdu_w16_offset); - sparx5_set_port_ifh_timestamp(ifh, SPARX5_SKB_CB(skb)->ts_id); + sparx5_set_port_ifh_pdu_type(sparx5, ifh, + SPARX5_SKB_CB(skb)->pdu_type); + sparx5_set_port_ifh_pdu_w16_offset(sparx5, ifh, + SPARX5_SKB_CB(skb)->pdu_w16_offset); + sparx5_set_port_ifh_timestamp(sparx5, ifh, + SPARX5_SKB_CB(skb)->ts_id); } skb_tx_timestamp(skb); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c index 0b38b4cb0929..1401761c6251 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c @@ -476,6 +476,9 @@ static int sparx5_port_fifo_sz(struct sparx5 *sparx5, u32 mac_width = 8; u32 addition = 0; + if (!is_sparx5(sparx5)) + return 0; + switch (speed) { case SPEED_25000: return 0; @@ -921,6 +924,20 @@ static int sparx5_port_config_low_set(struct sparx5 *sparx5, sparx5, DEV2G5_DEV_RST_CTRL(port->portno)); + /* Enable PHAD_CTRL for better timestamping */ + if (!is_sparx5(sparx5)) { + for (int i = 0; i < 2; ++i) { + /* Divide the port clock by three for the two + * phase detection registers. + */ + spx5_rmw(DEV2G5_PHAD_CTRL_DIV_CFG_SET(3) | + DEV2G5_PHAD_CTRL_PHAD_ENA_SET(1), + DEV2G5_PHAD_CTRL_DIV_CFG | + DEV2G5_PHAD_CTRL_PHAD_ENA, + sparx5, DEV2G5_PHAD_CTRL(port->portno, i)); + } + } + return 0; } @@ -978,6 +995,7 @@ int sparx5_port_config(struct sparx5 *sparx5, struct sparx5_port_config *conf) { bool high_speed_dev = sparx5_is_baser(conf->portmode); + const struct sparx5_ops *ops = sparx5->data->ops; int err, urgency, stop_wm; err = sparx5_port_verify_speed(sparx5, port, conf); @@ -993,6 +1011,13 @@ int sparx5_port_config(struct sparx5 *sparx5, if (err) return err; + if (!is_sparx5(sparx5) && ops->is_port_10g(port->portno) && + conf->speed < SPEED_10000) + spx5_rmw(DSM_DEV_TX_STOP_WM_CFG_DEV10G_SHADOW_ENA_SET(1), + DSM_DEV_TX_STOP_WM_CFG_DEV10G_SHADOW_ENA, + sparx5, + DSM_DEV_TX_STOP_WM_CFG(port->portno)); + /* Set the DSM stop watermark */ stop_wm = sparx5_port_fifo_sz(sparx5, port->portno, conf->speed); spx5_rmw(DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM_SET(stop_wm), @@ -1144,6 +1169,27 @@ int sparx5_port_init(struct sparx5 *sparx5, DEV25G_PCS25G_SD_CFG(pix)); } + if (!is_sparx5(sparx5)) { + void __iomem *inst; + u32 dev, tinst; + + if (ops->is_port_10g(port->portno)) { + dev = sparx5_to_high_dev(sparx5, port->portno); + tinst = sparx5_port_dev_index(sparx5, port->portno); + inst = spx5_inst_get(sparx5, dev, tinst); + + spx5_inst_wr(5, inst, + DEV10G_PTP_STAMPER_CFG(port->portno)); + } else if (ops->is_port_5g(port->portno)) { + dev = sparx5_to_high_dev(sparx5, port->portno); + tinst = sparx5_port_dev_index(sparx5, port->portno); + inst = spx5_inst_get(sparx5, dev, tinst); + + spx5_inst_wr(5, inst, + DEV5G_PTP_STAMPER_CFG(port->portno)); + } + } + return 0; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c index 9b15e44f9e64..1c2903700a9c 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c @@ -11,8 +11,6 @@ #include "sparx5_main_regs.h" #include "sparx5_main.h" -#define SPARX5_MAX_PTP_ID 512 - #define TOD_ACC_PIN 0x4 enum { @@ -38,6 +36,9 @@ static u64 sparx5_ptp_get_1ppm(struct sparx5 *sparx5) case SPX5_CORE_CLOCK_250MHZ: res = 2301339409586; break; + case SPX5_CORE_CLOCK_328MHZ: + res = 1756832768924; + break; case SPX5_CORE_CLOCK_500MHZ: res = 1150669704793; break; @@ -60,6 +61,9 @@ static u64 sparx5_ptp_get_nominal_value(struct sparx5 *sparx5) case SPX5_CORE_CLOCK_250MHZ: res = 0x1FF0000000000000; break; + case SPX5_CORE_CLOCK_328MHZ: + res = 0x18604697DD0F9B5B; + break; case SPX5_CORE_CLOCK_500MHZ: res = 0x0FF8000000000000; break; @@ -269,9 +273,9 @@ void sparx5_ptp_txtstamp_release(struct sparx5_port *port, spin_unlock_irqrestore(&sparx5->ptp_ts_id_lock, flags); } -static void sparx5_get_hwtimestamp(struct sparx5 *sparx5, - struct timespec64 *ts, - u32 nsec) +void sparx5_get_hwtimestamp(struct sparx5 *sparx5, + struct timespec64 *ts, + u32 nsec) { /* Read current PTP time to get seconds */ const struct sparx5_consts *consts = sparx5->data->consts; @@ -299,6 +303,7 @@ static void sparx5_get_hwtimestamp(struct sparx5 *sparx5, spin_unlock_irqrestore(&sparx5->ptp_clock_lock, flags); } +EXPORT_SYMBOL_GPL(sparx5_get_hwtimestamp); irqreturn_t sparx5_ptp_irq_handler(int irq, void *args) { diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c index d065f8c40d37..e580670f3992 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c @@ -367,9 +367,10 @@ static u32 sparx5_weight_to_hw_cost(u32 weight_min, u32 weight) static int sparx5_dwrr_conf_set(struct sparx5_port *port, struct sparx5_dwrr *dwrr) { + u32 layer = is_sparx5(port->sparx5) ? 2 : 1; int i; - spx5_rmw(HSCH_HSCH_CFG_CFG_HSCH_LAYER_SET(2) | + spx5_rmw(HSCH_HSCH_CFG_CFG_HSCH_LAYER_SET(layer) | HSCH_HSCH_CFG_CFG_CFG_SE_IDX_SET(port->portno), HSCH_HSCH_CFG_CFG_HSCH_LAYER | HSCH_HSCH_CFG_CFG_CFG_SE_IDX, port->sparx5, HSCH_HSCH_CFG_CFG); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_regs.c b/drivers/net/ethernet/microchip/sparx5/sparx5_regs.c index 1db212ce3df7..220e81b714d4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_regs.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_regs.c @@ -4,7 +4,7 @@ * Copyright (c) 2024 Microchip Technology Inc. */ -/* This file is autogenerated by cml-utils 2024-09-24 14:02:24 +0200. +/* This file is autogenerated by cml-utils 2024-09-30 11:48:29 +0200. * Commit ID: 9d07b8d19363f3cd3590ddb3f7a2e2768e16524b */ @@ -140,6 +140,7 @@ const unsigned int sparx5_gsize[GSIZE_LAST] = { [GW_ANA_L2_COMMON] = 700, [GW_ASM_CFG] = 1088, [GW_CPU_CPU_REGS] = 204, + [GW_DEV2G5_PHASE_DETECTOR_CTRL] = 8, [GW_FDMA_FDMA] = 428, [GW_GCB_CHIP_REGS] = 424, [GW_HSCH_TAS_CONFIG] = 12, @@ -157,6 +158,8 @@ const unsigned int sparx5_fpos[FPOS_LAST] = { [FP_CPU_PROC_CTRL_CP15S_DISABLE] = 6, [FP_CPU_PROC_CTRL_PROC_CRYPTO_DISABLE] = 5, [FP_CPU_PROC_CTRL_L2_FLUSH_REQ] = 1, + [FP_DEV2G5_PHAD_CTRL_PHAD_ENA] = 7, + [FP_DEV2G5_PHAD_CTRL_PHAD_FAILED] = 6, [FP_FDMA_CH_CFG_CH_XTR_STATUS_MODE] = 7, [FP_FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY] = 6, [FP_FDMA_CH_CFG_CH_INJ_PORT] = 5, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_regs.h index c4e8b581c1f3..ea28130c2341 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_regs.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_regs.h @@ -4,7 +4,7 @@ * Copyright (c) 2024 Microchip Technology Inc. */ -/* This file is autogenerated by cml-utils 2024-09-24 14:02:24 +0200. +/* This file is autogenerated by cml-utils 2024-09-30 11:48:29 +0200. * Commit ID: 9d07b8d19363f3cd3590ddb3f7a2e2768e16524b */ @@ -151,6 +151,7 @@ enum sparx5_gsize_enum { GW_ANA_L2_COMMON, GW_ASM_CFG, GW_CPU_CPU_REGS, + GW_DEV2G5_PHASE_DETECTOR_CTRL, GW_FDMA_FDMA, GW_GCB_CHIP_REGS, GW_HSCH_TAS_CONFIG, @@ -169,6 +170,8 @@ enum sparx5_fpos_enum { FP_CPU_PROC_CTRL_CP15S_DISABLE, FP_CPU_PROC_CTRL_PROC_CRYPTO_DISABLE, FP_CPU_PROC_CTRL_L2_FLUSH_REQ, + FP_DEV2G5_PHAD_CTRL_PHAD_ENA, + FP_DEV2G5_PHAD_CTRL_PHAD_FAILED, FP_FDMA_CH_CFG_CH_XTR_STATUS_MODE, FP_FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY, FP_FDMA_CH_CFG_CH_INJ_PORT, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_sdlb.c b/drivers/net/ethernet/microchip/sparx5/sparx5_sdlb.c index df1d15600aad..98a3f44c569c 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_sdlb.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_sdlb.c @@ -25,17 +25,13 @@ struct sparx5_sdlb_group *sparx5_get_sdlb_group(int idx) return &sdlb_groups[idx]; } -int sparx5_sdlb_clk_hz_get(struct sparx5 *sparx5) +u64 sparx5_sdlb_clk_hz_get(struct sparx5 *sparx5) { - u32 clk_per_100ps; u64 clk_hz; - clk_per_100ps = HSCH_SYS_CLK_PER_100PS_GET(spx5_rd(sparx5, - HSCH_SYS_CLK_PER)); - if (!clk_per_100ps) - clk_per_100ps = SPX5_CLK_PER_100PS_DEFAULT; + clk_hz = (10 * 1000 * 1000) / + (sparx5_clk_period(sparx5->coreclock) / 100); - clk_hz = (10 * 1000 * 1000) / clk_per_100ps; return clk_hz *= 1000; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c index c3bbed140554..4dc1ebd5d510 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c @@ -1284,6 +1284,11 @@ static int sparx5_tc_flower_replace(struct net_device *ndev, /* Setup PSFP */ if (tc_sg_idx >= 0 || tc_pol_idx >= 0) { + if (!sparx5_has_feature(sparx5, SPX5_FEATURE_PSFP)) { + err = -EOPNOTSUPP; + goto out; + } + err = sparx5_tc_flower_psfp_setup(sparx5, vrule, tc_sg_idx, tc_pol_idx, &sg, &fm, &sf); if (err) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.h b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.h index 7d106f1276fe..e68f5639a40a 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_ag_api.h @@ -10,6 +10,8 @@ #ifndef __SPARX5_VCAP_AG_API_H__ #define __SPARX5_VCAP_AG_API_H__ +#include "vcap_api.h" + /* VCAPs */ extern const struct vcap_info sparx5_vcaps[]; extern const struct vcap_statistics sparx5_vcap_stats; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c index 967c8621c250..25066ddb8d4d 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c @@ -17,7 +17,6 @@ #define SUPER_VCAP_BLK_SIZE 3072 /* addresses per Super VCAP block */ #define STREAMSIZE (64 * 4) /* bytes in the VCAP cache area */ -#define SPARX5_IS2_LOOKUPS 4 #define VCAP_IS2_KEYSEL(_ena, _noneth, _v4_mc, _v4_uc, _v6_mc, _v6_uc, _arp) \ (ANA_ACL_VCAP_S2_KEY_SEL_KEY_SEL_ENA_SET(_ena) | \ ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL_SET(_noneth) | \ @@ -27,7 +26,6 @@ ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL_SET(_v6_uc) | \ ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL_SET(_arp)) -#define SPARX5_IS0_LOOKUPS 6 #define VCAP_IS0_KEYSEL(_ena, _etype, _ipv4, _ipv6, _mpls_uc, _mpls_mc, _mlbs) \ (ANA_CL_ADV_CL_CFG_LOOKUP_ENA_SET(_ena) | \ ANA_CL_ADV_CL_CFG_ETYPE_CLM_KEY_SEL_SET(_etype) | \ @@ -37,31 +35,17 @@ ANA_CL_ADV_CL_CFG_MPLS_MC_CLM_KEY_SEL_SET(_mpls_mc) | \ ANA_CL_ADV_CL_CFG_MLBS_CLM_KEY_SEL_SET(_mlbs)) -#define SPARX5_ES0_LOOKUPS 1 #define VCAP_ES0_KEYSEL(_key) (REW_RTAG_ETAG_CTRL_ES0_ISDX_KEY_ENA_SET(_key)) #define SPARX5_STAT_ESDX_GRN_PKTS 0x300 #define SPARX5_STAT_ESDX_YEL_PKTS 0x301 -#define SPARX5_ES2_LOOKUPS 2 #define VCAP_ES2_KEYSEL(_ena, _arp, _ipv4, _ipv6) \ (EACL_VCAP_ES2_KEY_SEL_KEY_ENA_SET(_ena) | \ EACL_VCAP_ES2_KEY_SEL_ARP_KEY_SEL_SET(_arp) | \ EACL_VCAP_ES2_KEY_SEL_IP4_KEY_SEL_SET(_ipv4) | \ EACL_VCAP_ES2_KEY_SEL_IP6_KEY_SEL_SET(_ipv6)) -static struct sparx5_vcap_inst { - enum vcap_type vtype; /* type of vcap */ - int vinst; /* instance number within the same type */ - int lookups; /* number of lookups in this vcap type */ - int lookups_per_instance; /* number of lookups in this instance */ - int first_cid; /* first chain id in this vcap */ - int last_cid; /* last chain id in this vcap */ - int count; /* number of available addresses, not in super vcap */ - int map_id; /* id in the super vcap block mapping (if applicable) */ - int blockno; /* starting block in super vcap (if applicable) */ - int blocks; /* number of blocks in super vcap (if applicable) */ - bool ingress; /* is vcap in the ingress path */ -} sparx5_vcap_inst_cfg[] = { +const struct sparx5_vcap_inst sparx5_vcap_inst_cfg[] = { { .vtype = VCAP_TYPE_IS0, /* CLM-0 */ .vinst = 0, @@ -1793,6 +1777,7 @@ void sparx5_vcap_set_port_keyset(struct net_device *ndev, static void sparx5_vcap_is0_port_key_selection(struct sparx5 *sparx5, struct vcap_admin *admin) { + const struct sparx5_consts *consts = sparx5->data->consts; int portno, lookup; u32 keysel; @@ -1804,7 +1789,7 @@ static void sparx5_vcap_is0_port_key_selection(struct sparx5 *sparx5, VCAP_IS0_PS_MPLS_FOLLOW_ETYPE, VCAP_IS0_PS_MLBS_FOLLOW_ETYPE); for (lookup = 0; lookup < admin->lookups; ++lookup) { - for (portno = 0; portno < SPX5_PORTS; ++portno) { + for (portno = 0; portno < consts->n_ports; ++portno) { spx5_wr(keysel, sparx5, ANA_CL_ADV_CL_CFG(portno, lookup)); spx5_rmw(ANA_CL_ADV_CL_CFG_LOOKUP_ENA, @@ -1819,6 +1804,7 @@ static void sparx5_vcap_is0_port_key_selection(struct sparx5 *sparx5, static void sparx5_vcap_is2_port_key_selection(struct sparx5 *sparx5, struct vcap_admin *admin) { + const struct sparx5_consts *consts = sparx5->data->consts; int portno, lookup; u32 keysel; @@ -1829,13 +1815,13 @@ static void sparx5_vcap_is2_port_key_selection(struct sparx5 *sparx5, VCAP_IS2_PS_IPV6_UC_IP_7TUPLE, VCAP_IS2_PS_ARP_ARP); for (lookup = 0; lookup < admin->lookups; ++lookup) { - for (portno = 0; portno < SPX5_PORTS; ++portno) { + for (portno = 0; portno < consts->n_ports; ++portno) { spx5_wr(keysel, sparx5, ANA_ACL_VCAP_S2_KEY_SEL(portno, lookup)); } } /* IS2 lookups are in bit 0:3 */ - for (portno = 0; portno < SPX5_PORTS; ++portno) + for (portno = 0; portno < consts->n_ports; ++portno) spx5_rmw(ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(0xf), ANA_ACL_VCAP_S2_CFG_SEC_ENA, sparx5, @@ -1846,11 +1832,12 @@ static void sparx5_vcap_is2_port_key_selection(struct sparx5 *sparx5, static void sparx5_vcap_es0_port_key_selection(struct sparx5 *sparx5, struct vcap_admin *admin) { + const struct sparx5_consts *consts = sparx5->data->consts; int portno; u32 keysel; keysel = VCAP_ES0_KEYSEL(VCAP_ES0_PS_FORCE_ISDX_LOOKUPS); - for (portno = 0; portno < SPX5_PORTS; ++portno) + for (portno = 0; portno < consts->n_ports; ++portno) spx5_rmw(keysel, REW_RTAG_ETAG_CTRL_ES0_ISDX_KEY_ENA, sparx5, REW_RTAG_ETAG_CTRL(portno)); @@ -1862,6 +1849,7 @@ static void sparx5_vcap_es0_port_key_selection(struct sparx5 *sparx5, static void sparx5_vcap_es2_port_key_selection(struct sparx5 *sparx5, struct vcap_admin *admin) { + const struct sparx5_consts *consts = sparx5->data->consts; int portno, lookup; u32 keysel; @@ -1869,7 +1857,7 @@ static void sparx5_vcap_es2_port_key_selection(struct sparx5 *sparx5, VCAP_ES2_PS_IPV4_IP4_TCP_UDP_OTHER, VCAP_ES2_PS_IPV6_IP_7TUPLE); for (lookup = 0; lookup < admin->lookups; ++lookup) - for (portno = 0; portno < SPX5_PORTS; ++portno) + for (portno = 0; portno < consts->n_ports; ++portno) spx5_wr(keysel, sparx5, EACL_VCAP_ES2_KEY_SEL(portno, lookup)); } @@ -1901,19 +1889,20 @@ static void sparx5_vcap_port_key_selection(struct sparx5 *sparx5, static void sparx5_vcap_port_key_deselection(struct sparx5 *sparx5, struct vcap_admin *admin) { + const struct sparx5_consts *consts = sparx5->data->consts; int portno, lookup; switch (admin->vtype) { case VCAP_TYPE_IS0: for (lookup = 0; lookup < admin->lookups; ++lookup) - for (portno = 0; portno < SPX5_PORTS; ++portno) + for (portno = 0; portno < consts->n_ports; ++portno) spx5_rmw(ANA_CL_ADV_CL_CFG_LOOKUP_ENA_SET(0), ANA_CL_ADV_CL_CFG_LOOKUP_ENA, sparx5, ANA_CL_ADV_CL_CFG(portno, lookup)); break; case VCAP_TYPE_IS2: - for (portno = 0; portno < SPX5_PORTS; ++portno) + for (portno = 0; portno < consts->n_ports; ++portno) spx5_rmw(ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(0), ANA_ACL_VCAP_S2_CFG_SEC_ENA, sparx5, @@ -1925,7 +1914,7 @@ static void sparx5_vcap_port_key_deselection(struct sparx5 *sparx5, break; case VCAP_TYPE_ES2: for (lookup = 0; lookup < admin->lookups; ++lookup) - for (portno = 0; portno < SPX5_PORTS; ++portno) + for (portno = 0; portno < consts->n_ports; ++portno) spx5_rmw(EACL_VCAP_ES2_KEY_SEL_KEY_ENA_SET(0), EACL_VCAP_ES2_KEY_SEL_KEY_ENA, sparx5, @@ -2042,6 +2031,7 @@ static void sparx5_vcap_block_alloc(struct sparx5 *sparx5, /* Allocate a vcap control and vcap instances and configure the system */ int sparx5_vcap_init(struct sparx5 *sparx5) { + const struct sparx5_consts *consts = sparx5->data->consts; const struct sparx5_vcap_inst *cfg; struct vcap_control *ctrl; struct vcap_admin *admin; @@ -2063,14 +2053,14 @@ int sparx5_vcap_init(struct sparx5 *sparx5) sparx5->vcap_ctrl = ctrl; /* select the sparx5 VCAP model */ - ctrl->vcaps = sparx5_vcaps; - ctrl->stats = &sparx5_vcap_stats; + ctrl->vcaps = consts->vcaps; + ctrl->stats = consts->vcap_stats; /* Setup callbacks to allow the API to use the VCAP HW */ ctrl->ops = &sparx5_vcap_ops; INIT_LIST_HEAD(&ctrl->list); for (idx = 0; idx < ARRAY_SIZE(sparx5_vcap_inst_cfg); ++idx) { - cfg = &sparx5_vcap_inst_cfg[idx]; + cfg = &consts->vcaps_cfg[idx]; admin = sparx5_vcap_admin_alloc(sparx5, ctrl, cfg); if (IS_ERR(admin)) { err = PTR_ERR(admin); @@ -2085,7 +2075,7 @@ int sparx5_vcap_init(struct sparx5 *sparx5) list_add_tail(&admin->list, &ctrl->list); } dir = vcap_debugfs(sparx5->dev, sparx5->debugfs_root, ctrl); - for (idx = 0; idx < SPX5_PORTS; ++idx) + for (idx = 0; idx < consts->n_ports; ++idx) if (sparx5->ports[idx]) vcap_port_debugfs(sparx5->dev, dir, ctrl, sparx5->ports[idx]->ndev); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.h b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.h index 2684d9199b05..d0a42406bf26 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.h @@ -16,6 +16,11 @@ #include "vcap_api.h" #include "vcap_api_client.h" +#define SPARX5_IS2_LOOKUPS 4 +#define SPARX5_IS0_LOOKUPS 6 +#define SPARX5_ES0_LOOKUPS 1 +#define SPARX5_ES2_LOOKUPS 2 + #define SPARX5_VCAP_CID_IS0_L0 VCAP_CID_INGRESS_L0 /* IS0/CLM lookup 0 */ #define SPARX5_VCAP_CID_IS0_L1 VCAP_CID_INGRESS_L1 /* IS0/CLM lookup 1 */ #define SPARX5_VCAP_CID_IS0_L2 VCAP_CID_INGRESS_L2 /* IS0/CLM lookup 2 */ @@ -40,6 +45,22 @@ #define SPARX5_VCAP_CID_ES2_MAX \ (VCAP_CID_EGRESS_STAGE2_L1 + VCAP_CID_LOOKUP_SIZE - 1) /* ES2 Max */ +struct sparx5_vcap_inst { + enum vcap_type vtype; /* type of vcap */ + int vinst; /* instance number within the same type */ + int lookups; /* number of lookups in this vcap type */ + int lookups_per_instance; /* number of lookups in this instance */ + int first_cid; /* first chain id in this vcap */ + int last_cid; /* last chain id in this vcap */ + int count; /* number of available addresses, not in super vcap */ + int map_id; /* id in the super vcap block mapping (if applicable) */ + int blockno; /* starting block in super vcap (if applicable) */ + int blocks; /* number of blocks in super vcap (if applicable) */ + bool ingress; /* is vcap in the ingress path */ +}; + +extern const struct sparx5_vcap_inst sparx5_vcap_inst_cfg[]; + /* IS0 port keyset selection control */ /* IS0 ethernet, IPv4, IPv6 traffic type keyset generation */ diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index a057ec3dab97..986b1f150e3b 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -228,6 +228,32 @@ ocelot_flower_parse_egress_vlan_modify(struct ocelot_vcap_filter *filter, return 0; } +static int +ocelot_flower_parse_egress_port(struct ocelot *ocelot, struct flow_cls_offload *f, + const struct flow_action_entry *a, bool mirror, + struct netlink_ext_ack *extack) +{ + const char *act_string = mirror ? "mirror" : "redirect"; + int egress_port = ocelot->ops->netdev_to_port(a->dev); + enum flow_action_id offloadable_act_id; + + offloadable_act_id = mirror ? FLOW_ACTION_MIRRED : FLOW_ACTION_REDIRECT; + + /* Mirroring towards foreign interfaces is handled in software */ + if (egress_port < 0 || a->id != offloadable_act_id) { + if (f->common.skip_sw) { + NL_SET_ERR_MSG_FMT(extack, + "Can only %s to %s if filter also runs in software", + act_string, egress_port < 0 ? + "CPU" : "ingress of ocelot port"); + return -EOPNOTSUPP; + } + egress_port = ocelot->num_phys_ports; + } + + return egress_port; +} + static int ocelot_flower_parse_action(struct ocelot *ocelot, int port, bool ingress, struct flow_cls_offload *f, struct ocelot_vcap_filter *filter) @@ -356,6 +382,7 @@ static int ocelot_flower_parse_action(struct ocelot *ocelot, int port, filter->type = OCELOT_VCAP_FILTER_OFFLOAD; break; case FLOW_ACTION_REDIRECT: + case FLOW_ACTION_REDIRECT_INGRESS: if (filter->block_id != VCAP_IS2) { NL_SET_ERR_MSG_MOD(extack, "Redirect action can only be offloaded to VCAP IS2"); @@ -366,17 +393,19 @@ static int ocelot_flower_parse_action(struct ocelot *ocelot, int port, "Last action must be GOTO"); return -EOPNOTSUPP; } - egress_port = ocelot->ops->netdev_to_port(a->dev); - if (egress_port < 0) { - NL_SET_ERR_MSG_MOD(extack, - "Destination not an ocelot port"); - return -EOPNOTSUPP; - } + + egress_port = ocelot_flower_parse_egress_port(ocelot, f, + a, false, + extack); + if (egress_port < 0) + return egress_port; + filter->action.mask_mode = OCELOT_MASK_MODE_REDIRECT; filter->action.port_mask = BIT(egress_port); filter->type = OCELOT_VCAP_FILTER_OFFLOAD; break; case FLOW_ACTION_MIRRED: + case FLOW_ACTION_MIRRED_INGRESS: if (filter->block_id != VCAP_IS2) { NL_SET_ERR_MSG_MOD(extack, "Mirror action can only be offloaded to VCAP IS2"); @@ -387,12 +416,13 @@ static int ocelot_flower_parse_action(struct ocelot *ocelot, int port, "Last action must be GOTO"); return -EOPNOTSUPP; } - egress_port = ocelot->ops->netdev_to_port(a->dev); - if (egress_port < 0) { - NL_SET_ERR_MSG_MOD(extack, - "Destination not an ocelot port"); - return -EOPNOTSUPP; - } + + egress_port = ocelot_flower_parse_egress_port(ocelot, f, + a, true, + extack); + if (egress_port < 0) + return egress_port; + filter->egress_port.value = egress_port; filter->action.mirror_ena = true; filter->type = OCELOT_VCAP_FILTER_OFFLOAD; diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c index d215efc6cad0..f1c6c47564b1 100644 --- a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c @@ -1179,7 +1179,7 @@ int nfp_nfd3_poll(struct napi_struct *napi, int budget) } while (u64_stats_fetch_retry(&r_vec->rx_sync, start)); dim_update_sample(r_vec->event_ctr, pkts, bytes, &dim_sample); - net_dim(&r_vec->rx_dim, dim_sample); + net_dim(&r_vec->rx_dim, &dim_sample); } if (r_vec->nfp_net->tx_coalesce_adapt_on && r_vec->tx_ring) { @@ -1194,7 +1194,7 @@ int nfp_nfd3_poll(struct napi_struct *napi, int budget) } while (u64_stats_fetch_retry(&r_vec->tx_sync, start)); dim_update_sample(r_vec->event_ctr, pkts, bytes, &dim_sample); - net_dim(&r_vec->tx_dim, dim_sample); + net_dim(&r_vec->tx_dim, &dim_sample); } return pkts_polled; diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c index dae5af7d1845..ebeb6ab4465c 100644 --- a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c @@ -1289,7 +1289,7 @@ int nfp_nfdk_poll(struct napi_struct *napi, int budget) } while (u64_stats_fetch_retry(&r_vec->rx_sync, start)); dim_update_sample(r_vec->event_ctr, pkts, bytes, &dim_sample); - net_dim(&r_vec->rx_dim, dim_sample); + net_dim(&r_vec->rx_dim, &dim_sample); } if (r_vec->nfp_net->tx_coalesce_adapt_on && r_vec->tx_ring) { @@ -1304,7 +1304,7 @@ int nfp_nfdk_poll(struct napi_struct *napi, int budget) } while (u64_stats_fetch_retry(&r_vec->tx_sync, start)); dim_update_sample(r_vec->event_ctr, pkts, bytes, &dim_sample); - net_dim(&r_vec->tx_dim, dim_sample); + net_dim(&r_vec->tx_dim, &dim_sample); } return pkts_polled; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 6e0929af0f72..98e098c09c03 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -829,7 +829,7 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, return err; } - irq_set_affinity_hint(r_vec->irq_vector, &r_vec->affinity_mask); + irq_update_affinity_hint(r_vec->irq_vector, &r_vec->affinity_mask); nn_dbg(nn, "RV%02d: irq=%03d/%03d\n", idx, r_vec->irq_vector, r_vec->irq_entry); @@ -840,7 +840,7 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, static void nfp_net_cleanup_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec) { - irq_set_affinity_hint(r_vec->irq_vector, NULL); + irq_update_affinity_hint(r_vec->irq_vector, NULL); nfp_net_napi_del(&nn->dp, r_vec); free_irq(r_vec->irq_vector, r_vec); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index b93791d6b593..f5dc876eb500 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -394,6 +394,7 @@ err_out_free_irqs: err_out_pci: ionic_dev_teardown(ionic); ionic_clear_pci(ionic); + ionic_debugfs_del_dev(ionic); err_out: mutex_destroy(&ionic->dev_cmd_lock); ionic_devlink_free(ionic); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 0eeda7e502db..2ac59564ded1 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -928,7 +928,7 @@ static void ionic_dim_update(struct ionic_qcq *qcq, int napi_mode) dim_update_sample(qcq->cq.bound_intr->rearm_count, pkts, bytes, &dim_sample); - net_dim(&qcq->dim, dim_sample); + net_dim(&qcq->dim, &dim_sample); } int ionic_tx_napi(struct napi_struct *napi, int budget) diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index e50e1df0a433..c553da16d4b1 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -504,7 +504,7 @@ static int qede_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { typeof(cmd->link_modes) *link_modes = &cmd->link_modes; - struct ethtool_link_settings *base = &cmd->base; + struct ethtool_link_settings_hdr *base = &cmd->base; struct qede_dev *edev = netdev_priv(dev); struct qed_link_output current_link; @@ -537,7 +537,7 @@ static int qede_get_link_ksettings(struct net_device *dev, static int qede_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { - const struct ethtool_link_settings *base = &cmd->base; + const struct ethtool_link_settings_hdr *base = &cmd->base; const struct ethtool_forced_speed_map *map; struct qede_dev *edev = netdev_priv(dev); struct qed_link_output current_link; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index b84587841e31..907a482c012f 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -347,6 +347,8 @@ enum rtl8125_registers { TxPoll_8125 = 0x90, LEDSEL3 = 0x96, MAC0_BKP = 0x19e0, + RSS_CTRL_8125 = 0x4500, + Q_NUM_CTRL_8125 = 0x4800, EEE_TXIDLE_TIMER_8125 = 0x6048, }; @@ -660,13 +662,9 @@ struct rtl8169_private { struct work_struct work; } wk; - raw_spinlock_t config25_lock; raw_spinlock_t mac_ocp_lock; struct mutex led_lock; /* serialize LED ctrl RMW access */ - raw_spinlock_t cfg9346_usage_lock; - int cfg9346_usage_count; - unsigned supports_gmii:1; unsigned aspm_manageable:1; unsigned dash_enabled:1; @@ -720,22 +718,12 @@ static inline struct device *tp_to_dev(struct rtl8169_private *tp) static void rtl_lock_config_regs(struct rtl8169_private *tp) { - unsigned long flags; - - raw_spin_lock_irqsave(&tp->cfg9346_usage_lock, flags); - if (!--tp->cfg9346_usage_count) - RTL_W8(tp, Cfg9346, Cfg9346_Lock); - raw_spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); } static void rtl_unlock_config_regs(struct rtl8169_private *tp) { - unsigned long flags; - - raw_spin_lock_irqsave(&tp->cfg9346_usage_lock, flags); - if (!tp->cfg9346_usage_count++) - RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - raw_spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags); + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); } static void rtl_pci_commit(struct rtl8169_private *tp) @@ -746,24 +734,32 @@ static void rtl_pci_commit(struct rtl8169_private *tp) static void rtl_mod_config2(struct rtl8169_private *tp, u8 clear, u8 set) { - unsigned long flags; u8 val; - raw_spin_lock_irqsave(&tp->config25_lock, flags); val = RTL_R8(tp, Config2); RTL_W8(tp, Config2, (val & ~clear) | set); - raw_spin_unlock_irqrestore(&tp->config25_lock, flags); } static void rtl_mod_config5(struct rtl8169_private *tp, u8 clear, u8 set) { - unsigned long flags; u8 val; - raw_spin_lock_irqsave(&tp->config25_lock, flags); val = RTL_R8(tp, Config5); RTL_W8(tp, Config5, (val & ~clear) | set); - raw_spin_unlock_irqrestore(&tp->config25_lock, flags); +} + +static void r8169_mod_reg8_cond(struct rtl8169_private *tp, int reg, + u8 bits, bool cond) +{ + u8 val, old_val; + + old_val = RTL_R8(tp, reg); + if (cond) + val = old_val | bits; + else + val = old_val & ~bits; + if (val != old_val) + RTL_W8(tp, reg, val); } static bool rtl_is_8125(struct rtl8169_private *tp) @@ -1435,19 +1431,11 @@ static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp) static void rtl_set_d3_pll_down(struct rtl8169_private *tp, bool enable) { - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_26: - case RTL_GIGA_MAC_VER_29 ... RTL_GIGA_MAC_VER_30: - case RTL_GIGA_MAC_VER_32 ... RTL_GIGA_MAC_VER_37: - case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_66: - if (enable) - RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~D3_NO_PLL_DOWN); - else - RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | D3_NO_PLL_DOWN); - break; - default: - break; - } + if (tp->mac_version >= RTL_GIGA_MAC_VER_25 && + tp->mac_version != RTL_GIGA_MAC_VER_28 && + tp->mac_version != RTL_GIGA_MAC_VER_31 && + tp->mac_version != RTL_GIGA_MAC_VER_38) + r8169_mod_reg8_cond(tp, PMCH, D3_NO_PLL_DOWN, !enable); } static void rtl_reset_packet_filter(struct rtl8169_private *tp) @@ -1556,61 +1544,40 @@ static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) { - static const struct { - u32 opt; - u16 reg; - u8 mask; - } cfg[] = { - { WAKE_PHY, Config3, LinkUp }, - { WAKE_UCAST, Config5, UWF }, - { WAKE_BCAST, Config5, BWF }, - { WAKE_MCAST, Config5, MWF }, - { WAKE_ANY, Config5, LanWake }, - { WAKE_MAGIC, Config3, MagicPacket } - }; - unsigned int i, tmp = ARRAY_SIZE(cfg); - unsigned long flags; - u8 options; - rtl_unlock_config_regs(tp); if (rtl_is_8168evl_up(tp)) { - tmp--; if (wolopts & WAKE_MAGIC) rtl_eri_set_bits(tp, 0x0dc, MagicPacket_v2); else rtl_eri_clear_bits(tp, 0x0dc, MagicPacket_v2); } else if (rtl_is_8125(tp)) { - tmp--; if (wolopts & WAKE_MAGIC) r8168_mac_ocp_modify(tp, 0xc0b6, 0, BIT(0)); else r8168_mac_ocp_modify(tp, 0xc0b6, BIT(0), 0); + } else { + r8169_mod_reg8_cond(tp, Config3, MagicPacket, + wolopts & WAKE_MAGIC); } - raw_spin_lock_irqsave(&tp->config25_lock, flags); - for (i = 0; i < tmp; i++) { - options = RTL_R8(tp, cfg[i].reg) & ~cfg[i].mask; - if (wolopts & cfg[i].opt) - options |= cfg[i].mask; - RTL_W8(tp, cfg[i].reg, options); - } - raw_spin_unlock_irqrestore(&tp->config25_lock, flags); + r8169_mod_reg8_cond(tp, Config3, LinkUp, wolopts & WAKE_PHY); + if (rtl_is_8125(tp)) + r8168_mac_ocp_modify(tp, 0xe0c6, 0x3f, + wolopts & WAKE_PHY ? 0x13 : 0); + r8169_mod_reg8_cond(tp, Config5, UWF, wolopts & WAKE_UCAST); + r8169_mod_reg8_cond(tp, Config5, BWF, wolopts & WAKE_BCAST); + r8169_mod_reg8_cond(tp, Config5, MWF, wolopts & WAKE_MCAST); + r8169_mod_reg8_cond(tp, Config5, LanWake, wolopts); switch (tp->mac_version) { case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06: - options = RTL_R8(tp, Config1) & ~PMEnable; - if (wolopts) - options |= PMEnable; - RTL_W8(tp, Config1, options); + r8169_mod_reg8_cond(tp, Config1, PMEnable, wolopts); break; case RTL_GIGA_MAC_VER_34: case RTL_GIGA_MAC_VER_37: case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_66: - if (wolopts) - rtl_mod_config2(tp, 0, PME_SIGNAL); - else - rtl_mod_config2(tp, PME_SIGNAL, 0); + r8169_mod_reg8_cond(tp, Config2, PME_SIGNAL, wolopts); break; default: break; @@ -2576,86 +2543,31 @@ static void rtl8169_init_ring_indexes(struct rtl8169_private *tp) tp->dirty_tx = tp->cur_tx = tp->cur_rx = 0; } -static void r8168c_hw_jumbo_enable(struct rtl8169_private *tp) -{ - RTL_W8(tp, Config3, RTL_R8(tp, Config3) | Jumbo_En0); - RTL_W8(tp, Config4, RTL_R8(tp, Config4) | Jumbo_En1); -} - -static void r8168c_hw_jumbo_disable(struct rtl8169_private *tp) -{ - RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Jumbo_En0); - RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~Jumbo_En1); -} - -static void r8168dp_hw_jumbo_enable(struct rtl8169_private *tp) -{ - RTL_W8(tp, Config3, RTL_R8(tp, Config3) | Jumbo_En0); -} - -static void r8168dp_hw_jumbo_disable(struct rtl8169_private *tp) -{ - RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Jumbo_En0); -} - -static void r8168e_hw_jumbo_enable(struct rtl8169_private *tp) -{ - RTL_W8(tp, MaxTxPacketSize, 0x24); - RTL_W8(tp, Config3, RTL_R8(tp, Config3) | Jumbo_En0); - RTL_W8(tp, Config4, RTL_R8(tp, Config4) | 0x01); -} - -static void r8168e_hw_jumbo_disable(struct rtl8169_private *tp) -{ - RTL_W8(tp, MaxTxPacketSize, 0x3f); - RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Jumbo_En0); - RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~0x01); -} - -static void r8168b_1_hw_jumbo_enable(struct rtl8169_private *tp) -{ - RTL_W8(tp, Config4, RTL_R8(tp, Config4) | (1 << 0)); -} - -static void r8168b_1_hw_jumbo_disable(struct rtl8169_private *tp) -{ - RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~(1 << 0)); -} - static void rtl_jumbo_config(struct rtl8169_private *tp) { bool jumbo = tp->dev->mtu > ETH_DATA_LEN; int readrq = 4096; + if (jumbo && tp->mac_version >= RTL_GIGA_MAC_VER_17 && + tp->mac_version <= RTL_GIGA_MAC_VER_26) + readrq = 512; + rtl_unlock_config_regs(tp); switch (tp->mac_version) { case RTL_GIGA_MAC_VER_17: - if (jumbo) { - readrq = 512; - r8168b_1_hw_jumbo_enable(tp); - } else { - r8168b_1_hw_jumbo_disable(tp); - } + r8169_mod_reg8_cond(tp, Config4, BIT(0), jumbo); break; case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_26: - if (jumbo) { - readrq = 512; - r8168c_hw_jumbo_enable(tp); - } else { - r8168c_hw_jumbo_disable(tp); - } + r8169_mod_reg8_cond(tp, Config3, Jumbo_En0, jumbo); + r8169_mod_reg8_cond(tp, Config4, Jumbo_En1, jumbo); break; case RTL_GIGA_MAC_VER_28: - if (jumbo) - r8168dp_hw_jumbo_enable(tp); - else - r8168dp_hw_jumbo_disable(tp); + r8169_mod_reg8_cond(tp, Config3, Jumbo_En0, jumbo); break; case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_33: - if (jumbo) - r8168e_hw_jumbo_enable(tp); - else - r8168e_hw_jumbo_disable(tp); + RTL_W8(tp, MaxTxPacketSize, jumbo ? 0x24 : 0x3f); + r8169_mod_reg8_cond(tp, Config3, Jumbo_En0, jumbo); + r8169_mod_reg8_cond(tp, Config4, BIT(0), jumbo); break; default: break; @@ -3766,8 +3678,8 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp) rtl_pcie_state_l2l3_disable(tp); RTL_W16(tp, 0x382, 0x221b); - RTL_W8(tp, 0x4500, 0); - RTL_W16(tp, 0x4800, 0); + RTL_W32(tp, RSS_CTRL_8125, 0); + RTL_W16(tp, Q_NUM_CTRL_8125, 0); /* disable UPS */ r8168_mac_ocp_modify(tp, 0xd40a, 0x0010, 0x0000); @@ -5487,8 +5399,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->supports_gmii = ent->driver_data == RTL_CFG_NO_GBIT ? 0 : 1; tp->ocp_base = OCP_STD_PHY_BASE; - raw_spin_lock_init(&tp->cfg9346_usage_lock); - raw_spin_lock_init(&tp->config25_lock); raw_spin_lock_init(&tp->mac_ocp_lock); mutex_init(&tp->led_lock); diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c index 8739f4b42aaf..1d5b33f6c4b5 100644 --- a/drivers/net/ethernet/realtek/r8169_phy_config.c +++ b/drivers/net/ethernet/realtek/r8169_phy_config.c @@ -89,19 +89,25 @@ static void rtl8168h_config_eee_phy(struct phy_device *phydev) phy_modify_paged(phydev, 0xa42, 0x14, 0x0000, 0x0080); } -static void rtl8125a_config_eee_phy(struct phy_device *phydev) +static void rtl8125_common_config_eee_phy(struct phy_device *phydev) { - rtl8168h_config_eee_phy(phydev); + phy_modify_paged(phydev, 0xa6d, 0x14, 0x0010, 0x0000); + phy_modify_paged(phydev, 0xa42, 0x14, 0x0080, 0x0000); + phy_modify_paged(phydev, 0xa4a, 0x11, 0x0200, 0x0000); +} +static void rtl8125a_config_eee_phy(struct phy_device *phydev) +{ + rtl8168g_config_eee_phy(phydev); + /* disable EEE at 2.5Gbps */ phy_modify_paged(phydev, 0xa6d, 0x12, 0x0001, 0x0000); - phy_modify_paged(phydev, 0xa6d, 0x14, 0x0010, 0x0000); + rtl8125_common_config_eee_phy(phydev); } static void rtl8125b_config_eee_phy(struct phy_device *phydev) { - phy_modify_paged(phydev, 0xa6d, 0x14, 0x0010, 0x0000); - phy_modify_paged(phydev, 0xa42, 0x14, 0x0080, 0x0000); - phy_modify_paged(phydev, 0xa4a, 0x11, 0x0200, 0x0000); + rtl8168g_config_eee_phy(phydev); + rtl8125_common_config_eee_phy(phydev); } static void rtl8169s_hw_phy_config(struct rtl8169_private *tp, @@ -1067,8 +1073,8 @@ static void rtl8125b_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev) { r8169_apply_firmware(tp); + rtl8168g_enable_gphy_10m(phydev); - phy_modify_paged(phydev, 0xa44, 0x11, 0x0000, 0x0800); phy_modify_paged(phydev, 0xac4, 0x13, 0x00f0, 0x0090); phy_modify_paged(phydev, 0xad3, 0x10, 0x0003, 0x0001); @@ -1107,6 +1113,7 @@ static void rtl8125d_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev) { r8169_apply_firmware(tp); + rtl8168g_enable_gphy_10m(phydev); rtl8125_legacy_force_mode(phydev); rtl8168g_disable_aldps(phydev); rtl8125b_config_eee_phy(phydev); @@ -1116,6 +1123,10 @@ static void rtl8126a_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev) { r8169_apply_firmware(tp); + rtl8168g_enable_gphy_10m(phydev); + rtl8125_legacy_force_mode(phydev); + rtl8168g_disable_aldps(phydev); + rtl8125_common_config_eee_phy(phydev); } void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev, diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index de131fc5fa0b..452009ed7a43 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1751,7 +1751,7 @@ static void efx_ef10_get_stat_mask(struct efx_nic *efx, unsigned long *mask) #endif } -static size_t efx_ef10_describe_stats(struct efx_nic *efx, u8 *names) +static size_t efx_ef10_describe_stats(struct efx_nic *efx, u8 **names) { DECLARE_BITMAP(mask, EF10_STAT_COUNT); diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index 6da06931187d..62e674d6ff60 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -583,7 +583,7 @@ static const struct efx_hw_stat_desc ef100_stat_desc[EF100_STAT_COUNT] = { EFX_GENERIC_SW_STAT(rx_noskb_drops), }; -static size_t ef100_describe_stats(struct efx_nic *efx, u8 *names) +static size_t ef100_describe_stats(struct efx_nic *efx, u8 **names) { DECLARE_BITMAP(mask, EF100_STAT_COUNT) = {}; diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 90bb7db15519..650136dfc642 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -418,14 +418,6 @@ unsigned int efx_usecs_to_ticks(struct efx_nic *efx, unsigned int usecs) return usecs * 1000 / efx->timer_quantum_ns; } -unsigned int efx_ticks_to_usecs(struct efx_nic *efx, unsigned int ticks) -{ - /* We must round up when converting ticks to microseconds - * because we round down when converting the other way. - */ - return DIV_ROUND_UP(ticks * efx->timer_quantum_ns, 1000); -} - /* Set interrupt moderation parameters */ int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs, unsigned int rx_usecs, bool rx_adaptive, diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index 7a6cab883d66..45e191686625 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -168,7 +168,6 @@ extern const struct ethtool_ops efx_ethtool_ops; /* Global */ unsigned int efx_usecs_to_ticks(struct efx_nic *efx, unsigned int usecs); -unsigned int efx_ticks_to_usecs(struct efx_nic *efx, unsigned int ticks); int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs, unsigned int rx_usecs, bool rx_adaptive, bool rx_may_override_tx); diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index 13cf647051af..c88ec3e24836 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -635,22 +635,6 @@ int __efx_reconfigure_port(struct efx_nic *efx) return rc; } -/* Reinitialise the MAC to pick up new PHY settings, even if the port is - * disabled. - */ -int efx_reconfigure_port(struct efx_nic *efx) -{ - int rc; - - EFX_ASSERT_RESET_SERIALISED(efx); - - mutex_lock(&efx->mac_lock); - rc = __efx_reconfigure_port(efx); - mutex_unlock(&efx->mac_lock); - - return rc; -} - /************************************************************************** * * Device reset and suspend diff --git a/drivers/net/ethernet/sfc/efx_common.h b/drivers/net/ethernet/sfc/efx_common.h index 2c54dac3e662..19a8ca530969 100644 --- a/drivers/net/ethernet/sfc/efx_common.h +++ b/drivers/net/ethernet/sfc/efx_common.h @@ -40,7 +40,6 @@ void efx_destroy_reset_workqueue(void); void efx_start_monitor(struct efx_nic *efx); int __efx_reconfigure_port(struct efx_nic *efx); -int efx_reconfigure_port(struct efx_nic *efx); #define EFX_ASSERT_RESET_SERIALISED(efx) \ do { \ diff --git a/drivers/net/ethernet/sfc/ethtool_common.c b/drivers/net/ethernet/sfc/ethtool_common.c index ae32e08540fa..2d734496733f 100644 --- a/drivers/net/ethernet/sfc/ethtool_common.c +++ b/drivers/net/ethernet/sfc/ethtool_common.c @@ -395,7 +395,7 @@ int efx_ethtool_fill_self_tests(struct efx_nic *efx, return n; } -static size_t efx_describe_per_queue_stats(struct efx_nic *efx, u8 *strings) +static size_t efx_describe_per_queue_stats(struct efx_nic *efx, u8 **strings) { size_t n_stats = 0; struct efx_channel *channel; @@ -403,24 +403,22 @@ static size_t efx_describe_per_queue_stats(struct efx_nic *efx, u8 *strings) efx_for_each_channel(channel, efx) { if (efx_channel_has_tx_queues(channel)) { n_stats++; - if (strings != NULL) { - snprintf(strings, ETH_GSTRING_LEN, - "tx-%u.tx_packets", - channel->tx_queue[0].queue / - EFX_MAX_TXQ_PER_CHANNEL); + if (!strings) + continue; - strings += ETH_GSTRING_LEN; - } + ethtool_sprintf(strings, "tx-%u.tx_packets", + channel->tx_queue[0].queue / + EFX_MAX_TXQ_PER_CHANNEL); } } efx_for_each_channel(channel, efx) { if (efx_channel_has_rx_queue(channel)) { n_stats++; - if (strings != NULL) { - snprintf(strings, ETH_GSTRING_LEN, - "rx-%d.rx_packets", channel->channel); - strings += ETH_GSTRING_LEN; - } + if (!strings) + continue; + + ethtool_sprintf(strings, "rx-%d.rx_packets", + channel->channel); } } if (efx->xdp_tx_queue_count && efx->xdp_tx_queues) { @@ -428,11 +426,11 @@ static size_t efx_describe_per_queue_stats(struct efx_nic *efx, u8 *strings) for (xdp = 0; xdp < efx->xdp_tx_queue_count; xdp++) { n_stats++; - if (strings) { - snprintf(strings, ETH_GSTRING_LEN, - "tx-xdp-cpu-%hu.tx_packets", xdp); - strings += ETH_GSTRING_LEN; - } + if (!strings) + continue; + + ethtool_sprintf(strings, "tx-xdp-cpu-%hu.tx_packets", + xdp); } } @@ -464,15 +462,11 @@ void efx_ethtool_get_strings(struct net_device *net_dev, switch (string_set) { case ETH_SS_STATS: - strings += (efx->type->describe_stats(efx, strings) * - ETH_GSTRING_LEN); + efx->type->describe_stats(efx, &strings); for (i = 0; i < EFX_ETHTOOL_SW_STAT_COUNT; i++) - strscpy(strings + i * ETH_GSTRING_LEN, - efx_sw_stat_desc[i].name, ETH_GSTRING_LEN); - strings += EFX_ETHTOOL_SW_STAT_COUNT * ETH_GSTRING_LEN; - strings += (efx_describe_per_queue_stats(efx, strings) * - ETH_GSTRING_LEN); - efx_ptp_describe_stats(efx, strings); + ethtool_puts(&strings, efx_sw_stat_desc[i].name); + efx_describe_per_queue_stats(efx, &strings); + efx_ptp_describe_stats(efx, &strings); break; case ETH_SS_TEST: efx_ethtool_fill_self_tests(efx, NULL, strings, NULL); diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index 8925745f1c17..b07f7e4e2877 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -1886,14 +1886,6 @@ unsigned int ef4_usecs_to_ticks(struct ef4_nic *efx, unsigned int usecs) return usecs * 1000 / efx->timer_quantum_ns; } -unsigned int ef4_ticks_to_usecs(struct ef4_nic *efx, unsigned int ticks) -{ - /* We must round up when converting ticks to microseconds - * because we round down when converting the other way. - */ - return DIV_ROUND_UP(ticks * efx->timer_quantum_ns, 1000); -} - /* Set interrupt moderation parameters */ int ef4_init_irq_moderation(struct ef4_nic *efx, unsigned int tx_usecs, unsigned int rx_usecs, bool rx_adaptive, diff --git a/drivers/net/ethernet/sfc/falcon/efx.h b/drivers/net/ethernet/sfc/falcon/efx.h index d3b4646545fa..52508f2c8cb2 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.h +++ b/drivers/net/ethernet/sfc/falcon/efx.h @@ -198,7 +198,6 @@ int ef4_try_recovery(struct ef4_nic *efx); /* Global */ void ef4_schedule_reset(struct ef4_nic *efx, enum reset_type type); unsigned int ef4_usecs_to_ticks(struct ef4_nic *efx, unsigned int usecs); -unsigned int ef4_ticks_to_usecs(struct ef4_nic *efx, unsigned int ticks); int ef4_init_irq_moderation(struct ef4_nic *efx, unsigned int tx_usecs, unsigned int rx_usecs, bool rx_adaptive, bool rx_may_override_tx); diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c index f4db683b80f7..04766448a545 100644 --- a/drivers/net/ethernet/sfc/falcon/ethtool.c +++ b/drivers/net/ethernet/sfc/falcon/ethtool.c @@ -353,7 +353,7 @@ static int ef4_ethtool_fill_self_tests(struct ef4_nic *efx, return n; } -static size_t ef4_describe_per_queue_stats(struct ef4_nic *efx, u8 *strings) +static size_t ef4_describe_per_queue_stats(struct ef4_nic *efx, u8 **strings) { size_t n_stats = 0; struct ef4_channel *channel; @@ -361,24 +361,22 @@ static size_t ef4_describe_per_queue_stats(struct ef4_nic *efx, u8 *strings) ef4_for_each_channel(channel, efx) { if (ef4_channel_has_tx_queues(channel)) { n_stats++; - if (strings != NULL) { - snprintf(strings, ETH_GSTRING_LEN, - "tx-%u.tx_packets", - channel->tx_queue[0].queue / - EF4_TXQ_TYPES); + if (!strings) + continue; - strings += ETH_GSTRING_LEN; - } + ethtool_sprintf(strings, "tx-%u.tx_packets", + channel->tx_queue[0].queue / + EF4_TXQ_TYPES); } } ef4_for_each_channel(channel, efx) { if (ef4_channel_has_rx_queue(channel)) { n_stats++; - if (strings != NULL) { - snprintf(strings, ETH_GSTRING_LEN, - "rx-%d.rx_packets", channel->channel); - strings += ETH_GSTRING_LEN; - } + if (!strings) + continue; + + ethtool_sprintf(strings, "rx-%d.rx_packets", + channel->channel); } } return n_stats; @@ -409,14 +407,10 @@ static void ef4_ethtool_get_strings(struct net_device *net_dev, switch (string_set) { case ETH_SS_STATS: - strings += (efx->type->describe_stats(efx, strings) * - ETH_GSTRING_LEN); + efx->type->describe_stats(efx, &strings); for (i = 0; i < EF4_ETHTOOL_SW_STAT_COUNT; i++) - strscpy(strings + i * ETH_GSTRING_LEN, - ef4_sw_stat_desc[i].name, ETH_GSTRING_LEN); - strings += EF4_ETHTOOL_SW_STAT_COUNT * ETH_GSTRING_LEN; - strings += (ef4_describe_per_queue_stats(efx, strings) * - ETH_GSTRING_LEN); + ethtool_puts(&strings, ef4_sw_stat_desc[i].name); + ef4_describe_per_queue_stats(efx, &strings); break; case ETH_SS_TEST: ef4_ethtool_fill_self_tests(efx, NULL, strings, NULL); diff --git a/drivers/net/ethernet/sfc/falcon/falcon.c b/drivers/net/ethernet/sfc/falcon/falcon.c index 36114ce88034..4af56333ea49 100644 --- a/drivers/net/ethernet/sfc/falcon/falcon.c +++ b/drivers/net/ethernet/sfc/falcon/falcon.c @@ -2564,7 +2564,7 @@ static void falcon_remove_nic(struct ef4_nic *efx) efx->nic_data = NULL; } -static size_t falcon_describe_nic_stats(struct ef4_nic *efx, u8 *names) +static size_t falcon_describe_nic_stats(struct ef4_nic *efx, u8 **names) { return ef4_nic_describe_stats(falcon_stat_desc, FALCON_STAT_COUNT, falcon_stat_mask, names); diff --git a/drivers/net/ethernet/sfc/falcon/farch.c b/drivers/net/ethernet/sfc/falcon/farch.c index c64623c2e80c..01017c41338e 100644 --- a/drivers/net/ethernet/sfc/falcon/farch.c +++ b/drivers/net/ethernet/sfc/falcon/farch.c @@ -1631,28 +1631,6 @@ void ef4_farch_rx_push_indir_table(struct ef4_nic *efx) } } -/* Looks at available SRAM resources and works out how many queues we - * can support, and where things like descriptor caches should live. - * - * SRAM is split up as follows: - * 0 buftbl entries for channels - * efx->vf_buftbl_base buftbl entries for SR-IOV - * efx->rx_dc_base RX descriptor caches - * efx->tx_dc_base TX descriptor caches - */ -void ef4_farch_dimension_resources(struct ef4_nic *efx, unsigned sram_lim_qw) -{ - unsigned vi_count; - - /* Account for the buffer table entries backing the datapath channels - * and the descriptor caches for those channels. - */ - vi_count = max(efx->n_channels, efx->n_tx_channels * EF4_TXQ_TYPES); - - efx->tx_dc_base = sram_lim_qw - vi_count * TX_DC_ENTRIES; - efx->rx_dc_base = efx->tx_dc_base - vi_count * RX_DC_ENTRIES; -} - u32 ef4_farch_fpga_ver(struct ef4_nic *efx) { ef4_oword_t altera_build; diff --git a/drivers/net/ethernet/sfc/falcon/net_driver.h b/drivers/net/ethernet/sfc/falcon/net_driver.h index a2c7139f2b32..7ab0db44720d 100644 --- a/drivers/net/ethernet/sfc/falcon/net_driver.h +++ b/drivers/net/ethernet/sfc/falcon/net_driver.h @@ -1057,7 +1057,7 @@ struct ef4_nic_type { void (*finish_flush)(struct ef4_nic *efx); void (*prepare_flr)(struct ef4_nic *efx); void (*finish_flr)(struct ef4_nic *efx); - size_t (*describe_stats)(struct ef4_nic *efx, u8 *names); + size_t (*describe_stats)(struct ef4_nic *efx, u8 **names); size_t (*update_stats)(struct ef4_nic *efx, u64 *full_stats, struct rtnl_link_stats64 *core_stats); void (*start_stats)(struct ef4_nic *efx); diff --git a/drivers/net/ethernet/sfc/falcon/nic.c b/drivers/net/ethernet/sfc/falcon/nic.c index 78c851b5a56f..a6304686bc90 100644 --- a/drivers/net/ethernet/sfc/falcon/nic.c +++ b/drivers/net/ethernet/sfc/falcon/nic.c @@ -444,18 +444,15 @@ void ef4_nic_get_regs(struct ef4_nic *efx, void *buf) * bits in the first @count bits of @mask for which a name is defined. */ size_t ef4_nic_describe_stats(const struct ef4_hw_stat_desc *desc, size_t count, - const unsigned long *mask, u8 *names) + const unsigned long *mask, u8 **names) { size_t visible = 0; size_t index; for_each_set_bit(index, mask, count) { if (desc[index].name) { - if (names) { - strscpy(names, desc[index].name, - ETH_GSTRING_LEN); - names += ETH_GSTRING_LEN; - } + if (names) + ethtool_puts(names, desc[index].name); ++visible; } } @@ -511,14 +508,3 @@ void ef4_nic_update_stats(const struct ef4_hw_stat_desc *desc, size_t count, } } } - -void ef4_nic_fix_nodesc_drop_stat(struct ef4_nic *efx, u64 *rx_nodesc_drops) -{ - /* if down, or this is the first update after coming up */ - if (!(efx->net_dev->flags & IFF_UP) || !efx->rx_nodesc_drops_prev_state) - efx->rx_nodesc_drops_while_down += - *rx_nodesc_drops - efx->rx_nodesc_drops_total; - efx->rx_nodesc_drops_total = *rx_nodesc_drops; - efx->rx_nodesc_drops_prev_state = !!(efx->net_dev->flags & IFF_UP); - *rx_nodesc_drops -= efx->rx_nodesc_drops_while_down; -} diff --git a/drivers/net/ethernet/sfc/falcon/nic.h b/drivers/net/ethernet/sfc/falcon/nic.h index ada6e036fd97..bc6ef937d0fe 100644 --- a/drivers/net/ethernet/sfc/falcon/nic.h +++ b/drivers/net/ethernet/sfc/falcon/nic.h @@ -477,7 +477,6 @@ void ef4_farch_finish_flr(struct ef4_nic *efx); void falcon_start_nic_stats(struct ef4_nic *efx); void falcon_stop_nic_stats(struct ef4_nic *efx); int falcon_reset_xaui(struct ef4_nic *efx); -void ef4_farch_dimension_resources(struct ef4_nic *efx, unsigned sram_lim_qw); void ef4_farch_init_common(struct ef4_nic *efx); void ef4_farch_rx_push_indir_table(struct ef4_nic *efx); @@ -498,14 +497,10 @@ size_t ef4_nic_get_regs_len(struct ef4_nic *efx); void ef4_nic_get_regs(struct ef4_nic *efx, void *buf); size_t ef4_nic_describe_stats(const struct ef4_hw_stat_desc *desc, size_t count, - const unsigned long *mask, u8 *names); + const unsigned long *mask, u8 **names); void ef4_nic_update_stats(const struct ef4_hw_stat_desc *desc, size_t count, const unsigned long *mask, u64 *stats, const void *dma_buf, bool accumulate); -void ef4_nic_fix_nodesc_drop_stat(struct ef4_nic *efx, u64 *stat); - -#define EF4_MAX_FLUSH_TIME 5000 - void ef4_farch_generate_event(struct ef4_nic *efx, unsigned int evq, ef4_qword_t *event); diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c index b9369483758c..e6e80b039ca2 100644 --- a/drivers/net/ethernet/sfc/falcon/tx.c +++ b/drivers/net/ethernet/sfc/falcon/tx.c @@ -40,14 +40,6 @@ static inline u8 *ef4_tx_get_copy_buffer(struct ef4_tx_queue *tx_queue, return (u8 *)page_buf->addr + offset; } -u8 *ef4_tx_get_copy_buffer_limited(struct ef4_tx_queue *tx_queue, - struct ef4_tx_buffer *buffer, size_t len) -{ - if (len > EF4_TX_CB_SIZE) - return NULL; - return ef4_tx_get_copy_buffer(tx_queue, buffer); -} - static void ef4_dequeue_buffer(struct ef4_tx_queue *tx_queue, struct ef4_tx_buffer *buffer, unsigned int *pkts_compl, diff --git a/drivers/net/ethernet/sfc/falcon/tx.h b/drivers/net/ethernet/sfc/falcon/tx.h index 2a88c59cbbbe..868ed8a861ab 100644 --- a/drivers/net/ethernet/sfc/falcon/tx.h +++ b/drivers/net/ethernet/sfc/falcon/tx.h @@ -15,9 +15,6 @@ unsigned int ef4_tx_limit_len(struct ef4_tx_queue *tx_queue, dma_addr_t dma_addr, unsigned int len); -u8 *ef4_tx_get_copy_buffer_limited(struct ef4_tx_queue *tx_queue, - struct ef4_tx_buffer *buffer, size_t len); - int ef4_enqueue_skb_tso(struct ef4_tx_queue *tx_queue, struct sk_buff *skb, bool *data_mapped); diff --git a/drivers/net/ethernet/sfc/mae.c b/drivers/net/ethernet/sfc/mae.c index 10709d828a63..50f097487b14 100644 --- a/drivers/net/ethernet/sfc/mae.c +++ b/drivers/net/ethernet/sfc/mae.c @@ -76,17 +76,6 @@ void efx_mae_mport_uplink(struct efx_nic *efx __always_unused, u32 *out) *out = EFX_DWORD_VAL(mport); } -void efx_mae_mport_vf(struct efx_nic *efx __always_unused, u32 vf_id, u32 *out) -{ - efx_dword_t mport; - - EFX_POPULATE_DWORD_3(mport, - MAE_MPORT_SELECTOR_TYPE, MAE_MPORT_SELECTOR_TYPE_FUNC, - MAE_MPORT_SELECTOR_FUNC_PF_ID, MAE_MPORT_SELECTOR_FUNC_PF_ID_CALLER, - MAE_MPORT_SELECTOR_FUNC_VF_ID, vf_id); - *out = EFX_DWORD_VAL(mport); -} - /* Constructs an mport selector from an mport ID, because they're not the same */ void efx_mae_mport_mport(struct efx_nic *efx __always_unused, u32 mport_id, u32 *out) { diff --git a/drivers/net/ethernet/sfc/mae.h b/drivers/net/ethernet/sfc/mae.h index 8df30bc4f3ba..db79912c86d8 100644 --- a/drivers/net/ethernet/sfc/mae.h +++ b/drivers/net/ethernet/sfc/mae.h @@ -23,7 +23,6 @@ int efx_mae_free_mport(struct efx_nic *efx, u32 id); void efx_mae_mport_wire(struct efx_nic *efx, u32 *out); void efx_mae_mport_uplink(struct efx_nic *efx, u32 *out); -void efx_mae_mport_vf(struct efx_nic *efx, u32 vf_id, u32 *out); void efx_mae_mport_mport(struct efx_nic *efx, u32 mport_id, u32 *out); int efx_mae_lookup_mport(struct efx_nic *efx, u32 selector, u32 *id); diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 76578502226e..d461b1a6ce81 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -1051,15 +1051,6 @@ efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd, cookie, false); } -int efx_mcdi_rpc_async_quiet(struct efx_nic *efx, unsigned int cmd, - const efx_dword_t *inbuf, size_t inlen, - size_t outlen, efx_mcdi_async_completer *complete, - unsigned long cookie) -{ - return _efx_mcdi_rpc_async(efx, cmd, inbuf, inlen, outlen, complete, - cookie, true); -} - int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, efx_dword_t *outbuf, size_t outlen, size_t *outlen_actual) @@ -1068,14 +1059,6 @@ int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, outlen_actual, false, NULL, NULL); } -int efx_mcdi_rpc_finish_quiet(struct efx_nic *efx, unsigned cmd, size_t inlen, - efx_dword_t *outbuf, size_t outlen, - size_t *outlen_actual) -{ - return _efx_mcdi_rpc_finish(efx, cmd, inlen, outbuf, outlen, - outlen_actual, true, NULL, NULL); -} - void efx_mcdi_display_error(struct efx_nic *efx, unsigned cmd, size_t inlen, efx_dword_t *outbuf, size_t outlen, int rc) @@ -1982,33 +1965,6 @@ efx_mcdi_wol_filter_set_magic(struct efx_nic *efx, const u8 *mac, int *id_out) } -int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out) -{ - MCDI_DECLARE_BUF(outbuf, MC_CMD_WOL_FILTER_GET_OUT_LEN); - size_t outlen; - int rc; - - rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_GET, NULL, 0, - outbuf, sizeof(outbuf), &outlen); - if (rc) - goto fail; - - if (outlen < MC_CMD_WOL_FILTER_GET_OUT_LEN) { - rc = -EIO; - goto fail; - } - - *id_out = (int)MCDI_DWORD(outbuf, WOL_FILTER_GET_OUT_FILTER_ID); - - return 0; - -fail: - *id_out = -1; - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); - return rc; -} - - int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id) { MCDI_DECLARE_BUF(inbuf, MC_CMD_WOL_FILTER_REMOVE_IN_LEN); @@ -2021,38 +1977,6 @@ int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id) return rc; } -int efx_mcdi_flush_rxqs(struct efx_nic *efx) -{ - struct efx_channel *channel; - struct efx_rx_queue *rx_queue; - MCDI_DECLARE_BUF(inbuf, - MC_CMD_FLUSH_RX_QUEUES_IN_LEN(EFX_MAX_CHANNELS)); - int rc, count; - - BUILD_BUG_ON(EFX_MAX_CHANNELS > - MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM); - - count = 0; - efx_for_each_channel(channel, efx) { - efx_for_each_channel_rx_queue(rx_queue, channel) { - if (rx_queue->flush_pending) { - rx_queue->flush_pending = false; - atomic_dec(&efx->rxq_flush_pending); - MCDI_SET_ARRAY_DWORD( - inbuf, FLUSH_RX_QUEUES_IN_QID_OFST, - count, efx_rx_queue_index(rx_queue)); - count++; - } - } - } - - rc = efx_mcdi_rpc(efx, MC_CMD_FLUSH_RX_QUEUES, inbuf, - MC_CMD_FLUSH_RX_QUEUES_IN_LEN(count), NULL, 0, NULL); - WARN_ON(rc < 0); - - return rc; -} - int efx_mcdi_wol_filter_reset(struct efx_nic *efx) { int rc; diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index ea612c619874..cdb17d7c147f 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -155,9 +155,6 @@ int efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd, int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, efx_dword_t *outbuf, size_t outlen, size_t *outlen_actual); -int efx_mcdi_rpc_finish_quiet(struct efx_nic *efx, unsigned cmd, - size_t inlen, efx_dword_t *outbuf, - size_t outlen, size_t *outlen_actual); typedef void efx_mcdi_async_completer(struct efx_nic *efx, unsigned long cookie, int rc, @@ -167,11 +164,6 @@ int efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd, const efx_dword_t *inbuf, size_t inlen, size_t outlen, efx_mcdi_async_completer *complete, unsigned long cookie); -int efx_mcdi_rpc_async_quiet(struct efx_nic *efx, unsigned int cmd, - const efx_dword_t *inbuf, size_t inlen, - size_t outlen, - efx_mcdi_async_completer *complete, - unsigned long cookie); void efx_mcdi_display_error(struct efx_nic *efx, unsigned cmd, size_t inlen, efx_dword_t *outbuf, @@ -410,10 +402,8 @@ int efx_mcdi_handle_assertion(struct efx_nic *efx); int efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode); int efx_mcdi_wol_filter_set_magic(struct efx_nic *efx, const u8 *mac, int *id_out); -int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out); int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id); int efx_mcdi_wol_filter_reset(struct efx_nic *efx); -int efx_mcdi_flush_rxqs(struct efx_nic *efx); void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev); void efx_mcdi_mac_start_stats(struct efx_nic *efx); void efx_mcdi_mac_stop_stats(struct efx_nic *efx); diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index b54662d32f55..620ba6ef3514 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -1408,7 +1408,7 @@ struct efx_nic_type { int (*fini_dmaq)(struct efx_nic *efx); void (*prepare_flr)(struct efx_nic *efx); void (*finish_flr)(struct efx_nic *efx); - size_t (*describe_stats)(struct efx_nic *efx, u8 *names); + size_t (*describe_stats)(struct efx_nic *efx, u8 **names); size_t (*update_stats)(struct efx_nic *efx, u64 *full_stats, struct rtnl_link_stats64 *core_stats); size_t (*update_stats_atomic)(struct efx_nic *efx, u64 *full_stats, diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index a33ed473cc8a..80aa5e9c732a 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -299,18 +299,15 @@ void efx_nic_get_regs(struct efx_nic *efx, void *buf) * bits in the first @count bits of @mask for which a name is defined. */ size_t efx_nic_describe_stats(const struct efx_hw_stat_desc *desc, size_t count, - const unsigned long *mask, u8 *names) + const unsigned long *mask, u8 **names) { size_t visible = 0; size_t index; for_each_set_bit(index, mask, count) { if (desc[index].name) { - if (names) { - strscpy(names, desc[index].name, - ETH_GSTRING_LEN); - names += ETH_GSTRING_LEN; - } + if (names) + ethtool_puts(names, desc[index].name); ++visible; } } diff --git a/drivers/net/ethernet/sfc/nic_common.h b/drivers/net/ethernet/sfc/nic_common.h index 7ec4ac7b7ff5..821d91efda19 100644 --- a/drivers/net/ethernet/sfc/nic_common.h +++ b/drivers/net/ethernet/sfc/nic_common.h @@ -241,7 +241,7 @@ void efx_nic_get_regs(struct efx_nic *efx, void *buf); #define EFX_MC_STATS_GENERATION_INVALID ((__force __le64)(-1)) size_t efx_nic_describe_stats(const struct efx_hw_stat_desc *desc, size_t count, - const unsigned long *mask, u8 *names); + const unsigned long *mask, u8 **names); int efx_nic_copy_stats(struct efx_nic *efx, __le64 *dest); void efx_nic_update_stats(const struct efx_hw_stat_desc *desc, size_t count, const unsigned long *mask, u64 *stats, diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index aaacdcfa54ae..4c7222bf26be 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -399,7 +399,7 @@ static const unsigned long efx_ptp_stat_mask[] = { [0 ... BITS_TO_LONGS(PTP_STAT_COUNT) - 1] = ~0UL, }; -size_t efx_ptp_describe_stats(struct efx_nic *efx, u8 *strings) +size_t efx_ptp_describe_stats(struct efx_nic *efx, u8 **strings) { if (!efx->ptp_data) return 0; @@ -1800,11 +1800,6 @@ int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb) return NETDEV_TX_OK; } -int efx_ptp_get_mode(struct efx_nic *efx) -{ - return efx->ptp_data->mode; -} - int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted, unsigned int new_mode) { diff --git a/drivers/net/ethernet/sfc/ptp.h b/drivers/net/ethernet/sfc/ptp.h index 6946203499ef..cb9b077921e8 100644 --- a/drivers/net/ethernet/sfc/ptp.h +++ b/drivers/net/ethernet/sfc/ptp.h @@ -26,12 +26,11 @@ int efx_ptp_get_ts_config(struct efx_nic *efx, void efx_ptp_get_ts_info(struct efx_nic *efx, struct kernel_ethtool_ts_info *ts_info); bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb); -int efx_ptp_get_mode(struct efx_nic *efx); int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted, unsigned int new_mode); int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb); void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev); -size_t efx_ptp_describe_stats(struct efx_nic *efx, u8 *strings); +size_t efx_ptp_describe_stats(struct efx_nic *efx, u8 **strings); size_t efx_ptp_update_stats(struct efx_nic *efx, u64 *stats); void efx_time_sync_event(struct efx_channel *channel, efx_qword_t *ev); void __efx_rx_skb_attach_timestamp(struct efx_channel *channel, diff --git a/drivers/net/ethernet/sfc/siena/ethtool_common.c b/drivers/net/ethernet/sfc/siena/ethtool_common.c index 075fef64de68..eeee676fdca7 100644 --- a/drivers/net/ethernet/sfc/siena/ethtool_common.c +++ b/drivers/net/ethernet/sfc/siena/ethtool_common.c @@ -395,7 +395,7 @@ fail: test->flags |= ETH_TEST_FL_FAILED; } -static size_t efx_describe_per_queue_stats(struct efx_nic *efx, u8 *strings) +static size_t efx_describe_per_queue_stats(struct efx_nic *efx, u8 **strings) { size_t n_stats = 0; struct efx_channel *channel; @@ -403,24 +403,22 @@ static size_t efx_describe_per_queue_stats(struct efx_nic *efx, u8 *strings) efx_for_each_channel(channel, efx) { if (efx_channel_has_tx_queues(channel)) { n_stats++; - if (strings != NULL) { - snprintf(strings, ETH_GSTRING_LEN, - "tx-%u.tx_packets", - channel->tx_queue[0].queue / - EFX_MAX_TXQ_PER_CHANNEL); + if (!strings) + continue; - strings += ETH_GSTRING_LEN; - } + ethtool_sprintf(strings, "tx-%u.tx_packets", + channel->tx_queue[0].queue / + EFX_MAX_TXQ_PER_CHANNEL); } } efx_for_each_channel(channel, efx) { if (efx_channel_has_rx_queue(channel)) { n_stats++; - if (strings != NULL) { - snprintf(strings, ETH_GSTRING_LEN, - "rx-%d.rx_packets", channel->channel); - strings += ETH_GSTRING_LEN; - } + if (!strings) + continue; + + ethtool_sprintf(strings, "rx-%d.rx_packets", + channel->channel); } } if (efx->xdp_tx_queue_count && efx->xdp_tx_queues) { @@ -428,11 +426,11 @@ static size_t efx_describe_per_queue_stats(struct efx_nic *efx, u8 *strings) for (xdp = 0; xdp < efx->xdp_tx_queue_count; xdp++) { n_stats++; - if (strings) { - snprintf(strings, ETH_GSTRING_LEN, - "tx-xdp-cpu-%hu.tx_packets", xdp); - strings += ETH_GSTRING_LEN; - } + if (!strings) + continue; + + ethtool_sprintf(strings, "tx-xdp-cpu-%hu.tx_packets", + xdp); } } @@ -464,15 +462,11 @@ void efx_siena_ethtool_get_strings(struct net_device *net_dev, switch (string_set) { case ETH_SS_STATS: - strings += (efx->type->describe_stats(efx, strings) * - ETH_GSTRING_LEN); + efx->type->describe_stats(efx, &strings); for (i = 0; i < EFX_ETHTOOL_SW_STAT_COUNT; i++) - strscpy(strings + i * ETH_GSTRING_LEN, - efx_sw_stat_desc[i].name, ETH_GSTRING_LEN); - strings += EFX_ETHTOOL_SW_STAT_COUNT * ETH_GSTRING_LEN; - strings += (efx_describe_per_queue_stats(efx, strings) * - ETH_GSTRING_LEN); - efx_siena_ptp_describe_stats(efx, strings); + ethtool_puts(&strings, efx_sw_stat_desc[i].name); + efx_describe_per_queue_stats(efx, &strings); + efx_siena_ptp_describe_stats(efx, &strings); break; case ETH_SS_TEST: efx_ethtool_fill_self_tests(efx, NULL, strings, NULL); diff --git a/drivers/net/ethernet/sfc/siena/net_driver.h b/drivers/net/ethernet/sfc/siena/net_driver.h index 3fa7c652ae9b..9785eff10607 100644 --- a/drivers/net/ethernet/sfc/siena/net_driver.h +++ b/drivers/net/ethernet/sfc/siena/net_driver.h @@ -1307,7 +1307,7 @@ struct efx_nic_type { void (*finish_flush)(struct efx_nic *efx); void (*prepare_flr)(struct efx_nic *efx); void (*finish_flr)(struct efx_nic *efx); - size_t (*describe_stats)(struct efx_nic *efx, u8 *names); + size_t (*describe_stats)(struct efx_nic *efx, u8 **names); size_t (*update_stats)(struct efx_nic *efx, u64 *full_stats, struct rtnl_link_stats64 *core_stats); size_t (*update_stats_atomic)(struct efx_nic *efx, u64 *full_stats, diff --git a/drivers/net/ethernet/sfc/siena/nic.c b/drivers/net/ethernet/sfc/siena/nic.c index 0ea0433a6230..32fce70085e3 100644 --- a/drivers/net/ethernet/sfc/siena/nic.c +++ b/drivers/net/ethernet/sfc/siena/nic.c @@ -449,20 +449,20 @@ void efx_siena_get_regs(struct efx_nic *efx, void *buf) * Returns the number of visible statistics, i.e. the number of set * bits in the first @count bits of @mask for which a name is defined. */ -size_t efx_siena_describe_stats(const struct efx_hw_stat_desc *desc, size_t count, - const unsigned long *mask, u8 *names) +size_t efx_siena_describe_stats(const struct efx_hw_stat_desc *desc, + size_t count, const unsigned long *mask, + u8 **names) { size_t visible = 0; size_t index; for_each_set_bit(index, mask, count) { if (desc[index].name) { - if (names) { - strscpy(names, desc[index].name, - ETH_GSTRING_LEN); - names += ETH_GSTRING_LEN; - } ++visible; + if (!names) + continue; + + ethtool_puts(names, desc[index].name); } } diff --git a/drivers/net/ethernet/sfc/siena/nic_common.h b/drivers/net/ethernet/sfc/siena/nic_common.h index 3af0405eeaa4..b7fbe198008d 100644 --- a/drivers/net/ethernet/sfc/siena/nic_common.h +++ b/drivers/net/ethernet/sfc/siena/nic_common.h @@ -239,8 +239,9 @@ void efx_siena_get_regs(struct efx_nic *efx, void *buf); #define EFX_MC_STATS_GENERATION_INVALID ((__force __le64)(-1)) -size_t efx_siena_describe_stats(const struct efx_hw_stat_desc *desc, size_t count, - const unsigned long *mask, u8 *names); +size_t efx_siena_describe_stats(const struct efx_hw_stat_desc *desc, + size_t count, const unsigned long *mask, + u8 **names); void efx_siena_update_stats(const struct efx_hw_stat_desc *desc, size_t count, const unsigned long *mask, u64 *stats, const void *dma_buf, bool accumulate); diff --git a/drivers/net/ethernet/sfc/siena/ptp.c b/drivers/net/ethernet/sfc/siena/ptp.c index 85005196b4c5..062c77c92077 100644 --- a/drivers/net/ethernet/sfc/siena/ptp.c +++ b/drivers/net/ethernet/sfc/siena/ptp.c @@ -393,7 +393,7 @@ static const unsigned long efx_ptp_stat_mask[] = { [0 ... BITS_TO_LONGS(PTP_STAT_COUNT) - 1] = ~0UL, }; -size_t efx_siena_ptp_describe_stats(struct efx_nic *efx, u8 *strings) +size_t efx_siena_ptp_describe_stats(struct efx_nic *efx, u8 **strings) { if (!efx->ptp_data) return 0; diff --git a/drivers/net/ethernet/sfc/siena/ptp.h b/drivers/net/ethernet/sfc/siena/ptp.h index b6133e7c5608..54840036ab67 100644 --- a/drivers/net/ethernet/sfc/siena/ptp.h +++ b/drivers/net/ethernet/sfc/siena/ptp.h @@ -28,7 +28,7 @@ int efx_siena_ptp_change_mode(struct efx_nic *efx, bool enable_wanted, unsigned int new_mode); int efx_siena_ptp_tx(struct efx_nic *efx, struct sk_buff *skb); void efx_siena_ptp_event(struct efx_nic *efx, efx_qword_t *ev); -size_t efx_siena_ptp_describe_stats(struct efx_nic *efx, u8 *strings); +size_t efx_siena_ptp_describe_stats(struct efx_nic *efx, u8 **strings); size_t efx_siena_ptp_update_stats(struct efx_nic *efx, u64 *stats); void efx_siena_time_sync_event(struct efx_channel *channel, efx_qword_t *ev); void __efx_siena_rx_skb_attach_timestamp(struct efx_channel *channel, diff --git a/drivers/net/ethernet/sfc/siena/siena.c b/drivers/net/ethernet/sfc/siena/siena.c index ca33dc08e555..49f0c8a1a90a 100644 --- a/drivers/net/ethernet/sfc/siena/siena.c +++ b/drivers/net/ethernet/sfc/siena/siena.c @@ -545,7 +545,7 @@ static const unsigned long siena_stat_mask[] = { [0 ... BITS_TO_LONGS(SIENA_STAT_COUNT) - 1] = ~0UL, }; -static size_t siena_describe_nic_stats(struct efx_nic *efx, u8 *names) +static size_t siena_describe_nic_stats(struct efx_nic *efx, u8 **names) { return efx_siena_describe_stats(siena_stat_desc, SIENA_STAT_COUNT, siena_stat_mask, names); diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 822ec6564b2d..4dff19b6ef17 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -49,14 +49,6 @@ static inline u8 *efx_tx_get_copy_buffer(struct efx_tx_queue *tx_queue, return (u8 *)page_buf->addr + offset; } -u8 *efx_tx_get_copy_buffer_limited(struct efx_tx_queue *tx_queue, - struct efx_tx_buffer *buffer, size_t len) -{ - if (len > EFX_TX_CB_SIZE) - return NULL; - return efx_tx_get_copy_buffer(tx_queue, buffer); -} - static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1) { /* We need to consider all queues that the net core sees as one */ diff --git a/drivers/net/ethernet/sfc/tx.h b/drivers/net/ethernet/sfc/tx.h index f2c4d2f89919..f882749af8c3 100644 --- a/drivers/net/ethernet/sfc/tx.h +++ b/drivers/net/ethernet/sfc/tx.h @@ -15,9 +15,6 @@ unsigned int efx_tx_limit_len(struct efx_tx_queue *tx_queue, dma_addr_t dma_addr, unsigned int len); -u8 *efx_tx_get_copy_buffer_limited(struct efx_tx_queue *tx_queue, - struct efx_tx_buffer *buffer, size_t len); - /* What TXQ type will satisfy the checksum offloads required for this skb? */ static inline unsigned int efx_tx_csum_type_skb(struct sk_buff *skb) { diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 05cc07b8f48c..6658536a4e17 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -228,6 +228,16 @@ config DWMAC_SUN8I stmmac device driver. This driver is used for H3/A83T/A64 EMAC ethernet controller. +config DWMAC_THEAD + tristate "T-HEAD dwmac support" + depends on OF && (ARCH_THEAD || COMPILE_TEST) + help + Support for ethernet controllers on T-HEAD RISC-V SoCs + + This selects the T-HEAD platform specific glue layer support for + the stmmac device driver. This driver is used for T-HEAD TH1520 + ethernet controller. + config DWMAC_IMX8 tristate "NXP IMX8 DWMAC support" default ARCH_MXC diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index c2f0e91f6bf8..2389fd261344 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -6,7 +6,7 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o \ mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o \ dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o hwif.o \ stmmac_tc.o dwxgmac2_core.o dwxgmac2_dma.o dwxgmac2_descs.o \ - stmmac_xdp.o stmmac_est.o \ + stmmac_xdp.o stmmac_est.o stmmac_fpe.o \ $(stmmac-y) stmmac-$(CONFIG_STMMAC_SELFTESTS) += stmmac_selftests.o @@ -28,6 +28,7 @@ obj-$(CONFIG_DWMAC_STI) += dwmac-sti.o obj-$(CONFIG_DWMAC_STM32) += dwmac-stm32.o obj-$(CONFIG_DWMAC_SUNXI) += dwmac-sunxi.o obj-$(CONFIG_DWMAC_SUN8I) += dwmac-sun8i.o +obj-$(CONFIG_DWMAC_THEAD) += dwmac-thead.o obj-$(CONFIG_DWMAC_DWC_QOS_ETH) += dwmac-dwc-qos-eth.o obj-$(CONFIG_DWMAC_INTEL_PLAT) += dwmac-intel-plat.o obj-$(CONFIG_DWMAC_LOONGSON1) += dwmac-loongson1.o diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c index 598eff926815..b9218c07eb6b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c @@ -56,6 +56,7 @@ static const struct of_device_id dwmac_generic_match[] = { { .compatible = "snps,dwmac-3.610"}, { .compatible = "snps,dwmac-3.70a"}, { .compatible = "snps,dwmac-3.710"}, + { .compatible = "snps,dwmac-3.72a"}, { .compatible = "snps,dwmac-4.00"}, { .compatible = "snps,dwmac-4.10a"}, { .compatible = "snps,dwmac"}, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c new file mode 100644 index 000000000000..dce84ed184e9 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c @@ -0,0 +1,273 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * T-HEAD DWMAC platform driver + * + * Copyright (C) 2021 Alibaba Group Holding Limited. + * Copyright (C) 2023 Jisheng Zhang <[email protected]> + * + */ + +#include <linux/bitfield.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_net.h> +#include <linux/platform_device.h> + +#include "stmmac_platform.h" + +#define GMAC_CLK_EN 0x00 +#define GMAC_TX_CLK_EN BIT(1) +#define GMAC_TX_CLK_N_EN BIT(2) +#define GMAC_TX_CLK_OUT_EN BIT(3) +#define GMAC_RX_CLK_EN BIT(4) +#define GMAC_RX_CLK_N_EN BIT(5) +#define GMAC_EPHY_REF_CLK_EN BIT(6) +#define GMAC_RXCLK_DELAY_CTRL 0x04 +#define GMAC_RXCLK_BYPASS BIT(15) +#define GMAC_RXCLK_INVERT BIT(14) +#define GMAC_RXCLK_DELAY GENMASK(4, 0) +#define GMAC_TXCLK_DELAY_CTRL 0x08 +#define GMAC_TXCLK_BYPASS BIT(15) +#define GMAC_TXCLK_INVERT BIT(14) +#define GMAC_TXCLK_DELAY GENMASK(4, 0) +#define GMAC_PLLCLK_DIV 0x0c +#define GMAC_PLLCLK_DIV_EN BIT(31) +#define GMAC_PLLCLK_DIV_NUM GENMASK(7, 0) +#define GMAC_GTXCLK_SEL 0x18 +#define GMAC_GTXCLK_SEL_PLL BIT(0) +#define GMAC_INTF_CTRL 0x1c +#define PHY_INTF_MASK BIT(0) +#define PHY_INTF_RGMII FIELD_PREP(PHY_INTF_MASK, 1) +#define PHY_INTF_MII_GMII FIELD_PREP(PHY_INTF_MASK, 0) +#define GMAC_TXCLK_OEN 0x20 +#define TXCLK_DIR_MASK BIT(0) +#define TXCLK_DIR_OUTPUT FIELD_PREP(TXCLK_DIR_MASK, 0) +#define TXCLK_DIR_INPUT FIELD_PREP(TXCLK_DIR_MASK, 1) + +#define GMAC_GMII_RGMII_RATE 125000000 +#define GMAC_MII_RATE 25000000 + +struct thead_dwmac { + struct plat_stmmacenet_data *plat; + void __iomem *apb_base; + struct device *dev; +}; + +static int thead_dwmac_set_phy_if(struct plat_stmmacenet_data *plat) +{ + struct thead_dwmac *dwmac = plat->bsp_priv; + u32 phyif; + + switch (plat->mac_interface) { + case PHY_INTERFACE_MODE_MII: + phyif = PHY_INTF_MII_GMII; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_TXID: + case PHY_INTERFACE_MODE_RGMII_RXID: + phyif = PHY_INTF_RGMII; + break; + default: + dev_err(dwmac->dev, "unsupported phy interface %d\n", + plat->mac_interface); + return -EINVAL; + } + + writel(phyif, dwmac->apb_base + GMAC_INTF_CTRL); + return 0; +} + +static int thead_dwmac_set_txclk_dir(struct plat_stmmacenet_data *plat) +{ + struct thead_dwmac *dwmac = plat->bsp_priv; + u32 txclk_dir; + + switch (plat->mac_interface) { + case PHY_INTERFACE_MODE_MII: + txclk_dir = TXCLK_DIR_INPUT; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_TXID: + case PHY_INTERFACE_MODE_RGMII_RXID: + txclk_dir = TXCLK_DIR_OUTPUT; + break; + default: + dev_err(dwmac->dev, "unsupported phy interface %d\n", + plat->mac_interface); + return -EINVAL; + } + + writel(txclk_dir, dwmac->apb_base + GMAC_TXCLK_OEN); + return 0; +} + +static void thead_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode) +{ + struct plat_stmmacenet_data *plat; + struct thead_dwmac *dwmac = priv; + unsigned long rate; + u32 div, reg; + + plat = dwmac->plat; + + switch (plat->mac_interface) { + /* For MII, rxc/txc is provided by phy */ + case PHY_INTERFACE_MODE_MII: + return; + + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + rate = clk_get_rate(plat->stmmac_clk); + if (!rate || rate % GMAC_GMII_RGMII_RATE != 0 || + rate % GMAC_MII_RATE != 0) { + dev_err(dwmac->dev, "invalid gmac rate %ld\n", rate); + return; + } + + writel(0, dwmac->apb_base + GMAC_PLLCLK_DIV); + + switch (speed) { + case SPEED_1000: + div = rate / GMAC_GMII_RGMII_RATE; + break; + case SPEED_100: + div = rate / GMAC_MII_RATE; + break; + case SPEED_10: + div = rate * 10 / GMAC_MII_RATE; + break; + default: + dev_err(dwmac->dev, "invalid speed %u\n", speed); + return; + } + + reg = FIELD_PREP(GMAC_PLLCLK_DIV_EN, 1) | + FIELD_PREP(GMAC_PLLCLK_DIV_NUM, div); + writel(reg, dwmac->apb_base + GMAC_PLLCLK_DIV); + break; + default: + dev_err(dwmac->dev, "unsupported phy interface %d\n", + plat->mac_interface); + return; + } +} + +static int thead_dwmac_enable_clk(struct plat_stmmacenet_data *plat) +{ + struct thead_dwmac *dwmac = plat->bsp_priv; + u32 reg; + + switch (plat->mac_interface) { + case PHY_INTERFACE_MODE_MII: + reg = GMAC_RX_CLK_EN | GMAC_TX_CLK_EN; + break; + + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + /* use pll */ + writel(GMAC_GTXCLK_SEL_PLL, dwmac->apb_base + GMAC_GTXCLK_SEL); + reg = GMAC_TX_CLK_EN | GMAC_TX_CLK_N_EN | GMAC_TX_CLK_OUT_EN | + GMAC_RX_CLK_EN | GMAC_RX_CLK_N_EN; + break; + + default: + dev_err(dwmac->dev, "unsupported phy interface %d\n", + plat->mac_interface); + return -EINVAL; + } + + writel(reg, dwmac->apb_base + GMAC_CLK_EN); + return 0; +} + +static int thead_dwmac_init(struct platform_device *pdev, void *priv) +{ + struct thead_dwmac *dwmac = priv; + unsigned int reg; + int ret; + + ret = thead_dwmac_set_phy_if(dwmac->plat); + if (ret) + return ret; + + ret = thead_dwmac_set_txclk_dir(dwmac->plat); + if (ret) + return ret; + + reg = readl(dwmac->apb_base + GMAC_RXCLK_DELAY_CTRL); + reg &= ~(GMAC_RXCLK_DELAY); + reg |= FIELD_PREP(GMAC_RXCLK_DELAY, 0); + writel(reg, dwmac->apb_base + GMAC_RXCLK_DELAY_CTRL); + + reg = readl(dwmac->apb_base + GMAC_TXCLK_DELAY_CTRL); + reg &= ~(GMAC_TXCLK_DELAY); + reg |= FIELD_PREP(GMAC_TXCLK_DELAY, 0); + writel(reg, dwmac->apb_base + GMAC_TXCLK_DELAY_CTRL); + + return thead_dwmac_enable_clk(dwmac->plat); +} + +static int thead_dwmac_probe(struct platform_device *pdev) +{ + struct stmmac_resources stmmac_res; + struct plat_stmmacenet_data *plat; + struct thead_dwmac *dwmac; + void __iomem *apb; + int ret; + + ret = stmmac_get_platform_resources(pdev, &stmmac_res); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "failed to get resources\n"); + + plat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac); + if (IS_ERR(plat)) + return dev_err_probe(&pdev->dev, PTR_ERR(plat), + "dt configuration failed\n"); + + dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); + if (!dwmac) + return -ENOMEM; + + apb = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(apb)) + return dev_err_probe(&pdev->dev, PTR_ERR(apb), + "failed to remap gmac apb registers\n"); + + dwmac->dev = &pdev->dev; + dwmac->plat = plat; + dwmac->apb_base = apb; + plat->bsp_priv = dwmac; + plat->fix_mac_speed = thead_dwmac_fix_speed; + plat->init = thead_dwmac_init; + + return devm_stmmac_pltfr_probe(pdev, plat, &stmmac_res); +} + +static const struct of_device_id thead_dwmac_match[] = { + { .compatible = "thead,th1520-gmac" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, thead_dwmac_match); + +static struct platform_driver thead_dwmac_driver = { + .probe = thead_dwmac_probe, + .driver = { + .name = "thead-dwmac", + .pm = &stmmac_pltfr_pm_ops, + .of_match_table = thead_dwmac_match, + }, +}; +module_platform_driver(thead_dwmac_driver); + +MODULE_AUTHOR("Jisheng Zhang <[email protected]>"); +MODULE_AUTHOR("Drew Fustini <[email protected]>"); +MODULE_DESCRIPTION("T-HEAD DWMAC platform driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 28fff6cab812..184d41a306af 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -69,7 +69,6 @@ #define GMAC_RXQCTRL_TACPQE BIT(21) #define GMAC_RXQCTRL_TACPQE_SHIFT 21 #define GMAC_RXQCTRL_FPRQ GENMASK(26, 24) -#define GMAC_RXQCTRL_FPRQ_SHIFT 24 /* MAC Packet Filtering */ #define GMAC_PACKET_FILTER_PR BIT(0) @@ -394,8 +393,8 @@ static inline u32 mtl_chanx_base_addr(const struct dwmac4_addrs *addrs, #define MTL_OP_MODE_EHFC BIT(7) -#define MTL_OP_MODE_RTC_MASK 0x18 -#define MTL_OP_MODE_RTC_SHIFT 3 +#define MTL_OP_MODE_RTC_MASK GENMASK(1, 0) +#define MTL_OP_MODE_RTC_SHIFT 0 #define MTL_OP_MODE_RTC_32 (1 << MTL_OP_MODE_RTC_SHIFT) #define MTL_OP_MODE_RTC_64 0 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index e65a65666cc1..c25781874aa7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -16,6 +16,7 @@ #include <linux/io.h> #include <linux/iopoll.h> #include "stmmac.h" +#include "stmmac_fpe.h" #include "stmmac_pcs.h" #include "dwmac4.h" #include "dwmac5.h" @@ -1261,11 +1262,6 @@ const struct stmmac_ops dwmac410_ops = { .set_arp_offload = dwmac4_set_arp_offload, .config_l3_filter = dwmac4_config_l3_filter, .config_l4_filter = dwmac4_config_l4_filter, - .fpe_configure = dwmac5_fpe_configure, - .fpe_send_mpacket = dwmac5_fpe_send_mpacket, - .fpe_irq_status = dwmac5_fpe_irq_status, - .fpe_get_add_frag_size = dwmac5_fpe_get_add_frag_size, - .fpe_set_add_frag_size = dwmac5_fpe_set_add_frag_size, .fpe_map_preemption_class = dwmac5_fpe_map_preemption_class, .add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr, .del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr, @@ -1316,11 +1312,6 @@ const struct stmmac_ops dwmac510_ops = { .set_arp_offload = dwmac4_set_arp_offload, .config_l3_filter = dwmac4_config_l3_filter, .config_l4_filter = dwmac4_config_l4_filter, - .fpe_configure = dwmac5_fpe_configure, - .fpe_send_mpacket = dwmac5_fpe_send_mpacket, - .fpe_irq_status = dwmac5_fpe_irq_status, - .fpe_get_add_frag_size = dwmac5_fpe_get_add_frag_size, - .fpe_set_add_frag_size = dwmac5_fpe_set_add_frag_size, .fpe_map_preemption_class = dwmac5_fpe_map_preemption_class, .add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr, .del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 7c895e0ae71f..0cb84a0041a4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -203,8 +203,12 @@ static void _dwmac4_dump_dma_regs(struct stmmac_priv *priv, readl(ioaddr + DMA_CHAN_TX_CONTROL(dwmac4_addrs, channel)); reg_space[DMA_CHAN_RX_CONTROL(default_addrs, channel) / 4] = readl(ioaddr + DMA_CHAN_RX_CONTROL(dwmac4_addrs, channel)); + reg_space[DMA_CHAN_TX_BASE_ADDR_HI(default_addrs, channel) / 4] = + readl(ioaddr + DMA_CHAN_TX_BASE_ADDR_HI(dwmac4_addrs, channel)); reg_space[DMA_CHAN_TX_BASE_ADDR(default_addrs, channel) / 4] = readl(ioaddr + DMA_CHAN_TX_BASE_ADDR(dwmac4_addrs, channel)); + reg_space[DMA_CHAN_RX_BASE_ADDR_HI(default_addrs, channel) / 4] = + readl(ioaddr + DMA_CHAN_RX_BASE_ADDR_HI(dwmac4_addrs, channel)); reg_space[DMA_CHAN_RX_BASE_ADDR(default_addrs, channel) / 4] = readl(ioaddr + DMA_CHAN_RX_BASE_ADDR(dwmac4_addrs, channel)); reg_space[DMA_CHAN_TX_END_ADDR(default_addrs, channel) / 4] = @@ -225,8 +229,12 @@ static void _dwmac4_dump_dma_regs(struct stmmac_priv *priv, readl(ioaddr + DMA_CHAN_CUR_TX_DESC(dwmac4_addrs, channel)); reg_space[DMA_CHAN_CUR_RX_DESC(default_addrs, channel) / 4] = readl(ioaddr + DMA_CHAN_CUR_RX_DESC(dwmac4_addrs, channel)); + reg_space[DMA_CHAN_CUR_TX_BUF_ADDR_HI(default_addrs, channel) / 4] = + readl(ioaddr + DMA_CHAN_CUR_TX_BUF_ADDR_HI(dwmac4_addrs, channel)); reg_space[DMA_CHAN_CUR_TX_BUF_ADDR(default_addrs, channel) / 4] = readl(ioaddr + DMA_CHAN_CUR_TX_BUF_ADDR(dwmac4_addrs, channel)); + reg_space[DMA_CHAN_CUR_RX_BUF_ADDR_HI(default_addrs, channel) / 4] = + readl(ioaddr + DMA_CHAN_CUR_RX_BUF_ADDR_HI(dwmac4_addrs, channel)); reg_space[DMA_CHAN_CUR_RX_BUF_ADDR(default_addrs, channel) / 4] = readl(ioaddr + DMA_CHAN_CUR_RX_BUF_ADDR(dwmac4_addrs, channel)); reg_space[DMA_CHAN_STATUS(default_addrs, channel) / 4] = @@ -266,7 +274,7 @@ static void dwmac4_dma_rx_chan_op_mode(struct stmmac_priv *priv, } else { pr_debug("GMAC: disable RX SF mode (threshold %d)\n", mode); mtl_rx_op &= ~MTL_OP_MODE_RSF; - mtl_rx_op &= MTL_OP_MODE_RTC_MASK; + mtl_rx_op &= ~MTL_OP_MODE_RTC_MASK; if (mode <= 32) mtl_rx_op |= MTL_OP_MODE_RTC_32; else if (mode <= 64) @@ -335,7 +343,7 @@ static void dwmac4_dma_tx_chan_op_mode(struct stmmac_priv *priv, } else { pr_debug("GMAC: disabling TX SF (threshold %d)\n", mode); mtl_tx_op &= ~MTL_OP_MODE_TSF; - mtl_tx_op &= MTL_OP_MODE_TTC_MASK; + mtl_tx_op &= ~MTL_OP_MODE_TTC_MASK; /* Set the transmit threshold */ if (mode <= 32) mtl_tx_op |= MTL_OP_MODE_TTC_32; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h index 17d9120db5fe..4f980dcd3958 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h @@ -127,7 +127,9 @@ static inline u32 dma_chanx_base_addr(const struct dwmac4_addrs *addrs, #define DMA_CHAN_SLOT_CTRL_STATUS(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x3c) #define DMA_CHAN_CUR_TX_DESC(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x44) #define DMA_CHAN_CUR_RX_DESC(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x4c) +#define DMA_CHAN_CUR_TX_BUF_ADDR_HI(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x50) #define DMA_CHAN_CUR_TX_BUF_ADDR(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x54) +#define DMA_CHAN_CUR_RX_BUF_ADDR_HI(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x58) #define DMA_CHAN_CUR_RX_BUF_ADDR(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x5c) #define DMA_CHAN_STATUS(addrs, x) (dma_chanx_base_addr(addrs, x) + 0x60) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 0d185e54eb7e..57c03d491774 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -185,8 +185,6 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, x->rx_buf_unav_irq++; if (unlikely(intr_status & DMA_CHAN_STATUS_RPS)) x->rx_process_stopped_irq++; - if (unlikely(intr_status & DMA_CHAN_STATUS_RWT)) - x->rx_watchdog_irq++; if (unlikely(intr_status & DMA_CHAN_STATUS_ETI)) x->tx_early_irq++; if (unlikely(intr_status & DMA_CHAN_STATUS_TPS)) { @@ -198,6 +196,10 @@ int dwmac4_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, ret = tx_hard_error; } } + + if (unlikely(intr_status & DMA_CHAN_STATUS_RWT)) + x->rx_watchdog_irq++; + /* TX/RX NORMAL interrupts */ if (likely(intr_status & DMA_CHAN_STATUS_RI)) { u64_stats_update_begin(&stats->syncp); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index 08add508db84..1c431b918719 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -572,153 +572,3 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index, writel(val, ioaddr + MAC_PPS_CONTROL); return 0; } - -void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, - u32 num_txq, u32 num_rxq, - bool tx_enable, bool pmac_enable) -{ - u32 value; - - if (tx_enable) { - cfg->fpe_csr = EFPE; - value = readl(ioaddr + GMAC_RXQ_CTRL1); - value &= ~GMAC_RXQCTRL_FPRQ; - value |= (num_rxq - 1) << GMAC_RXQCTRL_FPRQ_SHIFT; - writel(value, ioaddr + GMAC_RXQ_CTRL1); - } else { - cfg->fpe_csr = 0; - } - writel(cfg->fpe_csr, ioaddr + MAC_FPE_CTRL_STS); - - value = readl(ioaddr + GMAC_INT_EN); - - if (pmac_enable) { - if (!(value & GMAC_INT_FPE_EN)) { - /* Dummy read to clear any pending masked interrupts */ - readl(ioaddr + MAC_FPE_CTRL_STS); - - value |= GMAC_INT_FPE_EN; - } - } else { - value &= ~GMAC_INT_FPE_EN; - } - - writel(value, ioaddr + GMAC_INT_EN); -} - -int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev) -{ - u32 value; - int status; - - status = FPE_EVENT_UNKNOWN; - - /* Reads from the MAC_FPE_CTRL_STS register should only be performed - * here, since the status flags of MAC_FPE_CTRL_STS are "clear on read" - */ - value = readl(ioaddr + MAC_FPE_CTRL_STS); - - if (value & TRSP) { - status |= FPE_EVENT_TRSP; - netdev_dbg(dev, "FPE: Respond mPacket is transmitted\n"); - } - - if (value & TVER) { - status |= FPE_EVENT_TVER; - netdev_dbg(dev, "FPE: Verify mPacket is transmitted\n"); - } - - if (value & RRSP) { - status |= FPE_EVENT_RRSP; - netdev_dbg(dev, "FPE: Respond mPacket is received\n"); - } - - if (value & RVER) { - status |= FPE_EVENT_RVER; - netdev_dbg(dev, "FPE: Verify mPacket is received\n"); - } - - return status; -} - -void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, - enum stmmac_mpacket_type type) -{ - u32 value = cfg->fpe_csr; - - if (type == MPACKET_VERIFY) - value |= SVER; - else if (type == MPACKET_RESPONSE) - value |= SRSP; - - writel(value, ioaddr + MAC_FPE_CTRL_STS); -} - -int dwmac5_fpe_get_add_frag_size(const void __iomem *ioaddr) -{ - return FIELD_GET(DWMAC5_ADD_FRAG_SZ, readl(ioaddr + MTL_FPE_CTRL_STS)); -} - -void dwmac5_fpe_set_add_frag_size(void __iomem *ioaddr, u32 add_frag_size) -{ - u32 value; - - value = readl(ioaddr + MTL_FPE_CTRL_STS); - writel(u32_replace_bits(value, add_frag_size, DWMAC5_ADD_FRAG_SZ), - ioaddr + MTL_FPE_CTRL_STS); -} - -#define ALG_ERR_MSG "TX algorithm SP is not suitable for one-to-many mapping" -#define WEIGHT_ERR_MSG "TXQ weight %u differs across other TXQs in TC: [%u]" - -int dwmac5_fpe_map_preemption_class(struct net_device *ndev, - struct netlink_ext_ack *extack, u32 pclass) -{ - u32 val, offset, count, queue_weight, preemptible_txqs = 0; - struct stmmac_priv *priv = netdev_priv(ndev); - u32 num_tc = ndev->num_tc; - - if (!pclass) - goto update_mapping; - - /* DWMAC CORE4+ can not program TC:TXQ mapping to hardware. - * - * Synopsys Databook: - * "The number of Tx DMA channels is equal to the number of Tx queues, - * and is direct one-to-one mapping." - */ - for (u32 tc = 0; tc < num_tc; tc++) { - count = ndev->tc_to_txq[tc].count; - offset = ndev->tc_to_txq[tc].offset; - - if (pclass & BIT(tc)) - preemptible_txqs |= GENMASK(offset + count - 1, offset); - - /* This is 1:1 mapping, go to next TC */ - if (count == 1) - continue; - - if (priv->plat->tx_sched_algorithm == MTL_TX_ALGORITHM_SP) { - NL_SET_ERR_MSG_MOD(extack, ALG_ERR_MSG); - return -EINVAL; - } - - queue_weight = priv->plat->tx_queues_cfg[offset].weight; - - for (u32 i = 1; i < count; i++) { - if (priv->plat->tx_queues_cfg[offset + i].weight != - queue_weight) { - NL_SET_ERR_MSG_FMT_MOD(extack, WEIGHT_ERR_MSG, - queue_weight, tc); - return -EINVAL; - } - } - } - -update_mapping: - val = readl(priv->ioaddr + MTL_FPE_CTRL_STS); - writel(u32_replace_bits(val, preemptible_txqs, DWMAC5_PREEMPTION_CLASS), - priv->ioaddr + MTL_FPE_CTRL_STS); - - return 0; -} diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h index 6c6eb6790e83..00b151b3b688 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h @@ -11,15 +11,6 @@ #define PRTYEN BIT(1) #define TMOUTEN BIT(0) -#define MAC_FPE_CTRL_STS 0x00000234 -#define TRSP BIT(19) -#define TVER BIT(18) -#define RRSP BIT(17) -#define RVER BIT(16) -#define SRSP BIT(2) -#define SVER BIT(1) -#define EFPE BIT(0) - #define MAC_PPS_CONTROL 0x00000b70 #define PPS_MAXIDX(x) ((((x) + 1) * 8) - 1) #define PPS_MINIDX(x) ((x) * 8) @@ -39,12 +30,6 @@ #define MAC_PPSx_INTERVAL(x) (0x00000b88 + ((x) * 0x10)) #define MAC_PPSx_WIDTH(x) (0x00000b8c + ((x) * 0x10)) -#define MTL_FPE_CTRL_STS 0x00000c90 -/* Preemption Classification */ -#define DWMAC5_PREEMPTION_CLASS GENMASK(15, 8) -/* Additional Fragment Size of preempted frames */ -#define DWMAC5_ADD_FRAG_SZ GENMASK(1, 0) - #define MTL_RXP_CONTROL_STATUS 0x00000ca0 #define RXPI BIT(31) #define NPE GENMASK(23, 16) @@ -108,16 +93,5 @@ int dwmac5_rxp_config(void __iomem *ioaddr, struct stmmac_tc_entry *entries, int dwmac5_flex_pps_config(void __iomem *ioaddr, int index, struct stmmac_pps_cfg *cfg, bool enable, u32 sub_second_inc, u32 systime_flags); -void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, - u32 num_txq, u32 num_rxq, - bool tx_enable, bool pmac_enable); -void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, - struct stmmac_fpe_cfg *cfg, - enum stmmac_mpacket_type type); -int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev); -int dwmac5_fpe_get_add_frag_size(const void __iomem *ioaddr); -void dwmac5_fpe_set_add_frag_size(void __iomem *ioaddr, u32 add_frag_size); -int dwmac5_fpe_map_preemption_class(struct net_device *ndev, - struct netlink_ext_ack *extack, u32 pclass); #endif /* __DWMAC5_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 6a2c7d22df1e..a04a79003692 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -84,8 +84,7 @@ #define XGMAC_MCBCQEN BIT(15) #define XGMAC_MCBCQ GENMASK(11, 8) #define XGMAC_MCBCQ_SHIFT 8 -#define XGMAC_RQ GENMASK(7, 4) -#define XGMAC_RQ_SHIFT 4 +#define XGMAC_FPRQ GENMASK(7, 4) #define XGMAC_UPQ GENMASK(3, 0) #define XGMAC_UPQ_SHIFT 0 #define XGMAC_RXQ_CTRL2 0x000000a8 @@ -96,6 +95,7 @@ #define XGMAC_LPIIS BIT(5) #define XGMAC_PMTIS BIT(4) #define XGMAC_INT_EN 0x000000b4 +#define XGMAC_FPEIE BIT(15) #define XGMAC_TSIE BIT(12) #define XGMAC_LPIIE BIT(5) #define XGMAC_PMTIE BIT(4) @@ -193,8 +193,6 @@ #define XGMAC_MDIO_ADDR 0x00000200 #define XGMAC_MDIO_DATA 0x00000204 #define XGMAC_MDIO_C22P 0x00000220 -#define XGMAC_FPE_CTRL_STS 0x00000280 -#define XGMAC_EFPE BIT(0) #define XGMAC_ADDRx_HIGH(x) (0x00000300 + (x) * 0x8) #define XGMAC_ADDR_MAX 32 #define XGMAC_AE BIT(31) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index f519d43738b0..9a60a6e8f633 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -8,6 +8,7 @@ #include <linux/crc32.h> #include <linux/iopoll.h> #include "stmmac.h" +#include "stmmac_fpe.h" #include "stmmac_ptp.h" #include "dwxlgmac2.h" #include "dwxgmac2.h" @@ -1504,32 +1505,6 @@ static void dwxgmac2_set_arp_offload(struct mac_device_info *hw, bool en, writel(value, ioaddr + XGMAC_RX_CONFIG); } -static void dwxgmac3_fpe_configure(void __iomem *ioaddr, - struct stmmac_fpe_cfg *cfg, - u32 num_txq, u32 num_rxq, - bool tx_enable, bool pmac_enable) -{ - u32 value; - - if (!tx_enable) { - value = readl(ioaddr + XGMAC_FPE_CTRL_STS); - - value &= ~XGMAC_EFPE; - - writel(value, ioaddr + XGMAC_FPE_CTRL_STS); - return; - } - - value = readl(ioaddr + XGMAC_RXQ_CTRL1); - value &= ~XGMAC_RQ; - value |= (num_rxq - 1) << XGMAC_RQ_SHIFT; - writel(value, ioaddr + XGMAC_RXQ_CTRL1); - - value = readl(ioaddr + XGMAC_FPE_CTRL_STS); - value |= XGMAC_EFPE; - writel(value, ioaddr + XGMAC_FPE_CTRL_STS); -} - const struct stmmac_ops dwxgmac210_ops = { .core_init = dwxgmac2_core_init, .set_mac = dwxgmac2_set_mac, @@ -1570,7 +1545,7 @@ const struct stmmac_ops dwxgmac210_ops = { .config_l3_filter = dwxgmac2_config_l3_filter, .config_l4_filter = dwxgmac2_config_l4_filter, .set_arp_offload = dwxgmac2_set_arp_offload, - .fpe_configure = dwxgmac3_fpe_configure, + .fpe_map_preemption_class = dwxgmac3_fpe_map_preemption_class, }; static void dwxlgmac2_rx_queue_enable(struct mac_device_info *hw, u8 mode, @@ -1627,7 +1602,7 @@ const struct stmmac_ops dwxlgmac2_ops = { .config_l3_filter = dwxgmac2_config_l3_filter, .config_l4_filter = dwxgmac2_config_l4_filter, .set_arp_offload = dwxgmac2_set_arp_offload, - .fpe_configure = dwxgmac3_fpe_configure, + .fpe_map_preemption_class = dwxgmac3_fpe_map_preemption_class, }; int dwxgmac2_setup(struct stmmac_priv *priv) diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index 88cce28b2f98..cfc50289aed6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -6,6 +6,7 @@ #include "common.h" #include "stmmac.h" +#include "stmmac_fpe.h" #include "stmmac_ptp.h" #include "stmmac_est.h" @@ -185,6 +186,7 @@ static const struct stmmac_hwif_entry { .ptp_off = PTP_GMAC4_OFFSET, .mmc_off = MMC_GMAC4_OFFSET, .est_off = EST_GMAC4_OFFSET, + .fpe_reg = &dwmac5_fpe_reg, }, .desc = &dwmac4_desc_ops, .dma = &dwmac4_dma_ops, @@ -205,6 +207,7 @@ static const struct stmmac_hwif_entry { .ptp_off = PTP_GMAC4_OFFSET, .mmc_off = MMC_GMAC4_OFFSET, .est_off = EST_GMAC4_OFFSET, + .fpe_reg = &dwmac5_fpe_reg, }, .desc = &dwmac4_desc_ops, .dma = &dwmac410_dma_ops, @@ -225,6 +228,7 @@ static const struct stmmac_hwif_entry { .ptp_off = PTP_GMAC4_OFFSET, .mmc_off = MMC_GMAC4_OFFSET, .est_off = EST_GMAC4_OFFSET, + .fpe_reg = &dwmac5_fpe_reg, }, .desc = &dwmac4_desc_ops, .dma = &dwmac410_dma_ops, @@ -246,6 +250,7 @@ static const struct stmmac_hwif_entry { .ptp_off = PTP_XGMAC_OFFSET, .mmc_off = MMC_XGMAC_OFFSET, .est_off = EST_XGMAC_OFFSET, + .fpe_reg = &dwxgmac3_fpe_reg, }, .desc = &dwxgmac210_desc_ops, .dma = &dwxgmac210_dma_ops, @@ -267,6 +272,7 @@ static const struct stmmac_hwif_entry { .ptp_off = PTP_XGMAC_OFFSET, .mmc_off = MMC_XGMAC_OFFSET, .est_off = EST_XGMAC_OFFSET, + .fpe_reg = &dwxgmac3_fpe_reg, }, .desc = &dwxgmac210_desc_ops, .dma = &dwxgmac210_dma_ops, @@ -353,6 +359,7 @@ int stmmac_hwif_init(struct stmmac_priv *priv) mac->est = mac->est ? : entry->est; priv->hw = mac; + priv->fpe_cfg.reg = entry->regs.fpe_reg; priv->ptpaddr = priv->ioaddr + entry->regs.ptp_off; priv->mmcaddr = priv->ioaddr + entry->regs.mmc_off; if (entry->est) diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index d5a9f01ecac5..64f8ed67dcc4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -420,15 +420,6 @@ struct stmmac_ops { bool en, bool udp, bool sa, bool inv, u32 match); void (*set_arp_offload)(struct mac_device_info *hw, bool en, u32 addr); - void (*fpe_configure)(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, - u32 num_txq, u32 num_rxq, - bool tx_enable, bool pmac_enable); - void (*fpe_send_mpacket)(void __iomem *ioaddr, - struct stmmac_fpe_cfg *cfg, - enum stmmac_mpacket_type type); - int (*fpe_irq_status)(void __iomem *ioaddr, struct net_device *dev); - int (*fpe_get_add_frag_size)(const void __iomem *ioaddr); - void (*fpe_set_add_frag_size)(void __iomem *ioaddr, u32 add_frag_size); int (*fpe_map_preemption_class)(struct net_device *ndev, struct netlink_ext_ack *extack, u32 pclass); @@ -530,16 +521,6 @@ struct stmmac_ops { stmmac_do_callback(__priv, mac, config_l4_filter, __args) #define stmmac_set_arp_offload(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, set_arp_offload, __args) -#define stmmac_fpe_configure(__priv, __args...) \ - stmmac_do_void_callback(__priv, mac, fpe_configure, __args) -#define stmmac_fpe_send_mpacket(__priv, __args...) \ - stmmac_do_void_callback(__priv, mac, fpe_send_mpacket, __args) -#define stmmac_fpe_irq_status(__priv, __args...) \ - stmmac_do_callback(__priv, mac, fpe_irq_status, __args) -#define stmmac_fpe_get_add_frag_size(__priv, __args...) \ - stmmac_do_callback(__priv, mac, fpe_get_add_frag_size, __args) -#define stmmac_fpe_set_add_frag_size(__priv, __args...) \ - stmmac_do_void_callback(__priv, mac, fpe_set_add_frag_size, __args) #define stmmac_fpe_map_preemption_class(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, fpe_map_preemption_class, __args) @@ -678,6 +659,7 @@ struct stmmac_est_ops { stmmac_do_void_callback(__priv, est, irq_status, __args) struct stmmac_regs_off { + const struct stmmac_fpe_reg *fpe_reg; u32 ptp_off; u32 mmc_off; u32 est_off; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index ea135203ff2e..1d86439b8a14 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -146,21 +146,13 @@ struct stmmac_channel { u32 index; }; -/* FPE link-partner hand-shaking mPacket type */ -enum stmmac_mpacket_type { - MPACKET_VERIFY = 0, - MPACKET_RESPONSE = 1, -}; - -#define STMMAC_FPE_MM_MAX_VERIFY_RETRIES 3 -#define STMMAC_FPE_MM_MAX_VERIFY_TIME_MS 128 - struct stmmac_fpe_cfg { /* Serialize access to MAC Merge state between ethtool requests * and link state updates. */ spinlock_t lock; + const struct stmmac_fpe_reg *reg; u32 fpe_csr; /* MAC_FPE_CTRL_STS reg cache */ enum ethtool_mm_verify_status status; @@ -420,7 +412,6 @@ bool stmmac_eee_init(struct stmmac_priv *priv); int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt); int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size); int stmmac_bus_clks_config(struct stmmac_priv *priv, bool enabled); -void stmmac_fpe_apply(struct stmmac_priv *priv); static inline bool stmmac_xdp_is_enabled(struct stmmac_priv *priv) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 2a37592a6281..1d77389ce953 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -17,9 +17,9 @@ #include <linux/net_tstamp.h> #include "stmmac.h" +#include "stmmac_fpe.h" #include "dwmac_dma.h" #include "dwxgmac2.h" -#include "dwmac5.h" #define REG_SPACE_SIZE 0x1060 #define GMAC4_REG_SPACE_SIZE 0x116C @@ -1271,7 +1271,7 @@ static int stmmac_get_mm(struct net_device *ndev, unsigned long flags; u32 frag_size; - if (!priv->dma_cap.fpesel) + if (!stmmac_fpe_supported(priv)) return -EOPNOTSUPP; spin_lock_irqsave(&priv->fpe_cfg.lock, flags); @@ -1294,7 +1294,7 @@ static int stmmac_get_mm(struct net_device *ndev, else state->tx_active = false; - frag_size = stmmac_fpe_get_add_frag_size(priv, priv->ioaddr); + frag_size = stmmac_fpe_get_add_frag_size(priv); state->tx_min_frag_size = ethtool_mm_frag_size_add_to_min(frag_size); spin_unlock_irqrestore(&priv->fpe_cfg.lock, flags); @@ -1329,7 +1329,7 @@ static int stmmac_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg, if (!cfg->verify_enabled) fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_DISABLED; - stmmac_fpe_set_add_frag_size(priv, priv->ioaddr, frag_size); + stmmac_fpe_set_add_frag_size(priv, frag_size); stmmac_fpe_apply(priv); spin_unlock_irqrestore(&fpe_cfg->lock, flags); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c new file mode 100644 index 000000000000..3a4bee029c7f --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c @@ -0,0 +1,413 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 Furong Xu <[email protected]> + * stmmac FPE(802.3 Qbu) handling + */ +#include "stmmac.h" +#include "stmmac_fpe.h" +#include "dwmac4.h" +#include "dwmac5.h" +#include "dwxgmac2.h" + +#define GMAC5_MAC_FPE_CTRL_STS 0x00000234 +#define XGMAC_MAC_FPE_CTRL_STS 0x00000280 + +#define GMAC5_MTL_FPE_CTRL_STS 0x00000c90 +#define XGMAC_MTL_FPE_CTRL_STS 0x00001090 +/* Preemption Classification */ +#define FPE_MTL_PREEMPTION_CLASS GENMASK(15, 8) +/* Additional Fragment Size of preempted frames */ +#define FPE_MTL_ADD_FRAG_SZ GENMASK(1, 0) + +#define STMMAC_MAC_FPE_CTRL_STS_TRSP BIT(19) +#define STMMAC_MAC_FPE_CTRL_STS_TVER BIT(18) +#define STMMAC_MAC_FPE_CTRL_STS_RRSP BIT(17) +#define STMMAC_MAC_FPE_CTRL_STS_RVER BIT(16) +#define STMMAC_MAC_FPE_CTRL_STS_SRSP BIT(2) +#define STMMAC_MAC_FPE_CTRL_STS_SVER BIT(1) +#define STMMAC_MAC_FPE_CTRL_STS_EFPE BIT(0) + +/* FPE link-partner hand-shaking mPacket type */ +enum stmmac_mpacket_type { + MPACKET_VERIFY = 0, + MPACKET_RESPONSE = 1, +}; + +struct stmmac_fpe_reg { + const u32 mac_fpe_reg; /* offset of MAC_FPE_CTRL_STS */ + const u32 mtl_fpe_reg; /* offset of MTL_FPE_CTRL_STS */ + const u32 rxq_ctrl1_reg; /* offset of MAC_RxQ_Ctrl1 */ + const u32 fprq_mask; /* Frame Preemption Residue Queue */ + const u32 int_en_reg; /* offset of MAC_Interrupt_Enable */ + const u32 int_en_bit; /* Frame Preemption Interrupt Enable */ +}; + +bool stmmac_fpe_supported(struct stmmac_priv *priv) +{ + return priv->dma_cap.fpesel && priv->fpe_cfg.reg && + priv->hw->mac->fpe_map_preemption_class; +} + +static void stmmac_fpe_configure(struct stmmac_priv *priv, bool tx_enable, + bool pmac_enable) +{ + struct stmmac_fpe_cfg *cfg = &priv->fpe_cfg; + const struct stmmac_fpe_reg *reg = cfg->reg; + u32 num_rxq = priv->plat->rx_queues_to_use; + void __iomem *ioaddr = priv->ioaddr; + u32 value; + + if (tx_enable) { + cfg->fpe_csr = STMMAC_MAC_FPE_CTRL_STS_EFPE; + value = readl(ioaddr + reg->rxq_ctrl1_reg); + value &= ~reg->fprq_mask; + /* Keep this SHIFT, FIELD_PREP() expects a constant mask :-/ */ + value |= (num_rxq - 1) << __ffs(reg->fprq_mask); + writel(value, ioaddr + reg->rxq_ctrl1_reg); + } else { + cfg->fpe_csr = 0; + } + writel(cfg->fpe_csr, ioaddr + reg->mac_fpe_reg); + + value = readl(ioaddr + reg->int_en_reg); + + if (pmac_enable) { + if (!(value & reg->int_en_bit)) { + /* Dummy read to clear any pending masked interrupts */ + readl(ioaddr + reg->mac_fpe_reg); + + value |= reg->int_en_bit; + } + } else { + value &= ~reg->int_en_bit; + } + + writel(value, ioaddr + reg->int_en_reg); +} + +static void stmmac_fpe_send_mpacket(struct stmmac_priv *priv, + enum stmmac_mpacket_type type) +{ + const struct stmmac_fpe_reg *reg = priv->fpe_cfg.reg; + void __iomem *ioaddr = priv->ioaddr; + u32 value = priv->fpe_cfg.fpe_csr; + + if (type == MPACKET_VERIFY) + value |= STMMAC_MAC_FPE_CTRL_STS_SVER; + else if (type == MPACKET_RESPONSE) + value |= STMMAC_MAC_FPE_CTRL_STS_SRSP; + + writel(value, ioaddr + reg->mac_fpe_reg); +} + +static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status) +{ + struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg; + + /* This is interrupt context, just spin_lock() */ + spin_lock(&fpe_cfg->lock); + + if (!fpe_cfg->pmac_enabled || status == FPE_EVENT_UNKNOWN) + goto unlock_out; + + /* LP has sent verify mPacket */ + if ((status & FPE_EVENT_RVER) == FPE_EVENT_RVER) + stmmac_fpe_send_mpacket(priv, MPACKET_RESPONSE); + + /* Local has sent verify mPacket */ + if ((status & FPE_EVENT_TVER) == FPE_EVENT_TVER && + fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED) + fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_VERIFYING; + + /* LP has sent response mPacket */ + if ((status & FPE_EVENT_RRSP) == FPE_EVENT_RRSP && + fpe_cfg->status == ETHTOOL_MM_VERIFY_STATUS_VERIFYING) + fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED; + +unlock_out: + spin_unlock(&fpe_cfg->lock); +} + +void stmmac_fpe_irq_status(struct stmmac_priv *priv) +{ + const struct stmmac_fpe_reg *reg = priv->fpe_cfg.reg; + void __iomem *ioaddr = priv->ioaddr; + struct net_device *dev = priv->dev; + int status = FPE_EVENT_UNKNOWN; + u32 value; + + /* Reads from the MAC_FPE_CTRL_STS register should only be performed + * here, since the status flags of MAC_FPE_CTRL_STS are "clear on read" + */ + value = readl(ioaddr + reg->mac_fpe_reg); + + if (value & STMMAC_MAC_FPE_CTRL_STS_TRSP) { + status |= FPE_EVENT_TRSP; + netdev_dbg(dev, "FPE: Respond mPacket is transmitted\n"); + } + + if (value & STMMAC_MAC_FPE_CTRL_STS_TVER) { + status |= FPE_EVENT_TVER; + netdev_dbg(dev, "FPE: Verify mPacket is transmitted\n"); + } + + if (value & STMMAC_MAC_FPE_CTRL_STS_RRSP) { + status |= FPE_EVENT_RRSP; + netdev_dbg(dev, "FPE: Respond mPacket is received\n"); + } + + if (value & STMMAC_MAC_FPE_CTRL_STS_RVER) { + status |= FPE_EVENT_RVER; + netdev_dbg(dev, "FPE: Verify mPacket is received\n"); + } + + stmmac_fpe_event_status(priv, status); +} + +/** + * stmmac_fpe_verify_timer - Timer for MAC Merge verification + * @t: timer_list struct containing private info + * + * Verify the MAC Merge capability in the local TX direction, by + * transmitting Verify mPackets up to 3 times. Wait until link + * partner responds with a Response mPacket, otherwise fail. + */ +static void stmmac_fpe_verify_timer(struct timer_list *t) +{ + struct stmmac_fpe_cfg *fpe_cfg = from_timer(fpe_cfg, t, verify_timer); + struct stmmac_priv *priv = container_of(fpe_cfg, struct stmmac_priv, + fpe_cfg); + unsigned long flags; + bool rearm = false; + + spin_lock_irqsave(&fpe_cfg->lock, flags); + + switch (fpe_cfg->status) { + case ETHTOOL_MM_VERIFY_STATUS_INITIAL: + case ETHTOOL_MM_VERIFY_STATUS_VERIFYING: + if (fpe_cfg->verify_retries != 0) { + stmmac_fpe_send_mpacket(priv, MPACKET_VERIFY); + rearm = true; + } else { + fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_FAILED; + } + + fpe_cfg->verify_retries--; + break; + + case ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED: + stmmac_fpe_configure(priv, true, true); + break; + + default: + break; + } + + if (rearm) { + mod_timer(&fpe_cfg->verify_timer, + jiffies + msecs_to_jiffies(fpe_cfg->verify_time)); + } + + spin_unlock_irqrestore(&fpe_cfg->lock, flags); +} + +static void stmmac_fpe_verify_timer_arm(struct stmmac_fpe_cfg *fpe_cfg) +{ + if (fpe_cfg->pmac_enabled && fpe_cfg->tx_enabled && + fpe_cfg->verify_enabled && + fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_FAILED && + fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED) { + timer_setup(&fpe_cfg->verify_timer, stmmac_fpe_verify_timer, 0); + mod_timer(&fpe_cfg->verify_timer, jiffies); + } +} + +void stmmac_fpe_init(struct stmmac_priv *priv) +{ + priv->fpe_cfg.verify_retries = STMMAC_FPE_MM_MAX_VERIFY_RETRIES; + priv->fpe_cfg.verify_time = STMMAC_FPE_MM_MAX_VERIFY_TIME_MS; + priv->fpe_cfg.status = ETHTOOL_MM_VERIFY_STATUS_DISABLED; + timer_setup(&priv->fpe_cfg.verify_timer, stmmac_fpe_verify_timer, 0); + spin_lock_init(&priv->fpe_cfg.lock); + + if ((!priv->fpe_cfg.reg || !priv->hw->mac->fpe_map_preemption_class) && + priv->dma_cap.fpesel) + dev_info(priv->device, "FPE is not supported by driver.\n"); +} + +void stmmac_fpe_apply(struct stmmac_priv *priv) +{ + struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg; + + /* If verification is disabled, configure FPE right away. + * Otherwise let the timer code do it. + */ + if (!fpe_cfg->verify_enabled) { + stmmac_fpe_configure(priv, fpe_cfg->tx_enabled, + fpe_cfg->pmac_enabled); + } else { + fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_INITIAL; + fpe_cfg->verify_retries = STMMAC_FPE_MM_MAX_VERIFY_RETRIES; + + if (netif_running(priv->dev)) + stmmac_fpe_verify_timer_arm(fpe_cfg); + } +} + +void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up) +{ + struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg; + unsigned long flags; + + timer_shutdown_sync(&fpe_cfg->verify_timer); + + spin_lock_irqsave(&fpe_cfg->lock, flags); + + if (is_up && fpe_cfg->pmac_enabled) { + /* VERIFY process requires pmac enabled when NIC comes up */ + stmmac_fpe_configure(priv, false, true); + + /* New link => maybe new partner => new verification process */ + stmmac_fpe_apply(priv); + } else { + /* No link => turn off EFPE */ + stmmac_fpe_configure(priv, false, false); + } + + spin_unlock_irqrestore(&fpe_cfg->lock, flags); +} + +int stmmac_fpe_get_add_frag_size(struct stmmac_priv *priv) +{ + const struct stmmac_fpe_reg *reg = priv->fpe_cfg.reg; + void __iomem *ioaddr = priv->ioaddr; + + return FIELD_GET(FPE_MTL_ADD_FRAG_SZ, readl(ioaddr + reg->mtl_fpe_reg)); +} + +void stmmac_fpe_set_add_frag_size(struct stmmac_priv *priv, u32 add_frag_size) +{ + const struct stmmac_fpe_reg *reg = priv->fpe_cfg.reg; + void __iomem *ioaddr = priv->ioaddr; + u32 value; + + value = readl(ioaddr + reg->mtl_fpe_reg); + writel(u32_replace_bits(value, add_frag_size, FPE_MTL_ADD_FRAG_SZ), + ioaddr + reg->mtl_fpe_reg); +} + +#define ALG_ERR_MSG "TX algorithm SP is not suitable for one-to-many mapping" +#define WEIGHT_ERR_MSG "TXQ weight %u differs across other TXQs in TC: [%u]" + +int dwmac5_fpe_map_preemption_class(struct net_device *ndev, + struct netlink_ext_ack *extack, u32 pclass) +{ + u32 val, offset, count, queue_weight, preemptible_txqs = 0; + struct stmmac_priv *priv = netdev_priv(ndev); + int num_tc = netdev_get_num_tc(ndev); + + if (!pclass) + goto update_mapping; + + /* DWMAC CORE4+ can not program TC:TXQ mapping to hardware. + * + * Synopsys Databook: + * "The number of Tx DMA channels is equal to the number of Tx queues, + * and is direct one-to-one mapping." + */ + for (u32 tc = 0; tc < num_tc; tc++) { + count = ndev->tc_to_txq[tc].count; + offset = ndev->tc_to_txq[tc].offset; + + if (pclass & BIT(tc)) + preemptible_txqs |= GENMASK(offset + count - 1, offset); + + /* This is 1:1 mapping, go to next TC */ + if (count == 1) + continue; + + if (priv->plat->tx_sched_algorithm == MTL_TX_ALGORITHM_SP) { + NL_SET_ERR_MSG_MOD(extack, ALG_ERR_MSG); + return -EINVAL; + } + + queue_weight = priv->plat->tx_queues_cfg[offset].weight; + + for (u32 i = 1; i < count; i++) { + if (priv->plat->tx_queues_cfg[offset + i].weight != + queue_weight) { + NL_SET_ERR_MSG_FMT_MOD(extack, WEIGHT_ERR_MSG, + queue_weight, tc); + return -EINVAL; + } + } + } + +update_mapping: + val = readl(priv->ioaddr + GMAC5_MTL_FPE_CTRL_STS); + writel(u32_replace_bits(val, preemptible_txqs, FPE_MTL_PREEMPTION_CLASS), + priv->ioaddr + GMAC5_MTL_FPE_CTRL_STS); + + return 0; +} + +int dwxgmac3_fpe_map_preemption_class(struct net_device *ndev, + struct netlink_ext_ack *extack, u32 pclass) +{ + u32 val, offset, count, preemptible_txqs = 0; + struct stmmac_priv *priv = netdev_priv(ndev); + int num_tc = netdev_get_num_tc(ndev); + + if (!num_tc) { + /* Restore default TC:Queue mapping */ + for (u32 i = 0; i < priv->plat->tx_queues_to_use; i++) { + val = readl(priv->ioaddr + XGMAC_MTL_TXQ_OPMODE(i)); + writel(u32_replace_bits(val, i, XGMAC_Q2TCMAP), + priv->ioaddr + XGMAC_MTL_TXQ_OPMODE(i)); + } + } + + /* Synopsys Databook: + * "All Queues within a traffic class are selected in a round robin + * fashion (when packets are available) when the traffic class is + * selected by the scheduler for packet transmission. This is true for + * any of the scheduling algorithms." + */ + for (u32 tc = 0; tc < num_tc; tc++) { + count = ndev->tc_to_txq[tc].count; + offset = ndev->tc_to_txq[tc].offset; + + if (pclass & BIT(tc)) + preemptible_txqs |= GENMASK(offset + count - 1, offset); + + for (u32 i = 0; i < count; i++) { + val = readl(priv->ioaddr + XGMAC_MTL_TXQ_OPMODE(offset + i)); + writel(u32_replace_bits(val, tc, XGMAC_Q2TCMAP), + priv->ioaddr + XGMAC_MTL_TXQ_OPMODE(offset + i)); + } + } + + val = readl(priv->ioaddr + XGMAC_MTL_FPE_CTRL_STS); + writel(u32_replace_bits(val, preemptible_txqs, FPE_MTL_PREEMPTION_CLASS), + priv->ioaddr + XGMAC_MTL_FPE_CTRL_STS); + + return 0; +} + +const struct stmmac_fpe_reg dwmac5_fpe_reg = { + .mac_fpe_reg = GMAC5_MAC_FPE_CTRL_STS, + .mtl_fpe_reg = GMAC5_MTL_FPE_CTRL_STS, + .rxq_ctrl1_reg = GMAC_RXQ_CTRL1, + .fprq_mask = GMAC_RXQCTRL_FPRQ, + .int_en_reg = GMAC_INT_EN, + .int_en_bit = GMAC_INT_FPE_EN, +}; + +const struct stmmac_fpe_reg dwxgmac3_fpe_reg = { + .mac_fpe_reg = XGMAC_MAC_FPE_CTRL_STS, + .mtl_fpe_reg = XGMAC_MTL_FPE_CTRL_STS, + .rxq_ctrl1_reg = XGMAC_RXQ_CTRL1, + .fprq_mask = XGMAC_FPRQ, + .int_en_reg = XGMAC_INT_EN, + .int_en_bit = XGMAC_FPEIE, +}; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.h new file mode 100644 index 000000000000..b884eac7142d --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Furong Xu <[email protected]> + * stmmac FPE(802.3 Qbu) handling + */ +#ifndef _STMMAC_FPE_H_ +#define _STMMAC_FPE_H_ + +#include <linux/types.h> +#include <linux/netdevice.h> + +#define STMMAC_FPE_MM_MAX_VERIFY_RETRIES 3 +#define STMMAC_FPE_MM_MAX_VERIFY_TIME_MS 128 + +struct stmmac_priv; + +void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up); +bool stmmac_fpe_supported(struct stmmac_priv *priv); +void stmmac_fpe_init(struct stmmac_priv *priv); +void stmmac_fpe_apply(struct stmmac_priv *priv); +void stmmac_fpe_irq_status(struct stmmac_priv *priv); +int stmmac_fpe_get_add_frag_size(struct stmmac_priv *priv); +void stmmac_fpe_set_add_frag_size(struct stmmac_priv *priv, u32 add_frag_size); + +int dwmac5_fpe_map_preemption_class(struct net_device *ndev, + struct netlink_ext_ack *extack, u32 pclass); +int dwxgmac3_fpe_map_preemption_class(struct net_device *ndev, + struct netlink_ext_ack *extack, u32 pclass); + +extern const struct stmmac_fpe_reg dwmac5_fpe_reg; +extern const struct stmmac_fpe_reg dwxgmac3_fpe_reg; + +#endif diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d3895d7eecfc..3cdc3910f3a0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -43,6 +43,7 @@ #include <net/pkt_cls.h> #include <net/xdp_sock_drv.h> #include "stmmac_ptp.h" +#include "stmmac_fpe.h" #include "stmmac.h" #include "stmmac_xdp.h" #include <linux/reset.h> @@ -966,35 +967,6 @@ static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, /* Nothing to do, xpcs_config() handles everything */ } -static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up) -{ - struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg; - unsigned long flags; - - timer_shutdown_sync(&fpe_cfg->verify_timer); - - spin_lock_irqsave(&fpe_cfg->lock, flags); - - if (is_up && fpe_cfg->pmac_enabled) { - /* VERIFY process requires pmac enabled when NIC comes up */ - stmmac_fpe_configure(priv, priv->ioaddr, fpe_cfg, - priv->plat->tx_queues_to_use, - priv->plat->rx_queues_to_use, - false, true); - - /* New link => maybe new partner => new verification process */ - stmmac_fpe_apply(priv); - } else { - /* No link => turn off EFPE */ - stmmac_fpe_configure(priv, priv->ioaddr, fpe_cfg, - priv->plat->tx_queues_to_use, - priv->plat->rx_queues_to_use, - false, false); - } - - spin_unlock_irqrestore(&fpe_cfg->lock, flags); -} - static void stmmac_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { @@ -1006,7 +978,7 @@ static void stmmac_mac_link_down(struct phylink_config *config, priv->eee_enabled = stmmac_eee_init(priv); stmmac_set_eee_pls(priv, priv->hw, false); - if (priv->dma_cap.fpesel) + if (stmmac_fpe_supported(priv)) stmmac_fpe_link_state_handle(priv, false); } @@ -1120,7 +1092,7 @@ static void stmmac_mac_link_up(struct phylink_config *config, stmmac_set_eee_pls(priv, priv->hw, true); } - if (priv->dma_cap.fpesel) + if (stmmac_fpe_supported(priv)) stmmac_fpe_link_state_handle(priv, true); if (priv->plat->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY) @@ -3780,6 +3752,7 @@ static int stmmac_request_irq_single(struct net_device *dev) /* Request the Wake IRQ in case of another line * is used for WoL */ + priv->wol_irq_disabled = true; if (priv->wol_irq > 0 && priv->wol_irq != dev->irq) { ret = request_irq(priv->wol_irq, stmmac_interrupt, IRQF_SHARED, dev->name, dev); @@ -4068,7 +4041,7 @@ static int stmmac_release(struct net_device *dev) stmmac_release_ptp(priv); - if (priv->dma_cap.fpesel) + if (stmmac_fpe_supported(priv)) timer_shutdown_sync(&priv->fpe_cfg.verify_timer); pm_runtime_put(priv->device); @@ -4304,11 +4277,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) if (dma_mapping_error(priv->device, des)) goto dma_map_err; - tx_q->tx_skbuff_dma[first_entry].buf = des; - tx_q->tx_skbuff_dma[first_entry].len = skb_headlen(skb); - tx_q->tx_skbuff_dma[first_entry].map_as_page = false; - tx_q->tx_skbuff_dma[first_entry].buf_type = STMMAC_TXBUF_T_SKB; - if (priv->dma_cap.addr64 <= 32) { first->des0 = cpu_to_le32(des); @@ -4327,6 +4295,23 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue); + /* In case two or more DMA transmit descriptors are allocated for this + * non-paged SKB data, the DMA buffer address should be saved to + * tx_q->tx_skbuff_dma[].buf corresponding to the last descriptor, + * and leave the other tx_q->tx_skbuff_dma[].buf as NULL to guarantee + * that stmmac_tx_clean() does not unmap the entire DMA buffer too early + * since the tail areas of the DMA buffer can be accessed by DMA engine + * sooner or later. + * By saving the DMA buffer address to tx_q->tx_skbuff_dma[].buf + * corresponding to the last descriptor, stmmac_tx_clean() will unmap + * this DMA buffer right after the DMA engine completely finishes the + * full buffer transmission. + */ + tx_q->tx_skbuff_dma[tx_q->cur_tx].buf = des; + tx_q->tx_skbuff_dma[tx_q->cur_tx].len = skb_headlen(skb); + tx_q->tx_skbuff_dma[tx_q->cur_tx].map_as_page = false; + tx_q->tx_skbuff_dma[tx_q->cur_tx].buf_type = STMMAC_TXBUF_T_SKB; + /* Prepare fragments */ for (i = 0; i < nfrags; i++) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; @@ -5953,35 +5938,6 @@ static int stmmac_set_features(struct net_device *netdev, return 0; } -static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status) -{ - struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg; - - /* This is interrupt context, just spin_lock() */ - spin_lock(&fpe_cfg->lock); - - if (!fpe_cfg->pmac_enabled || status == FPE_EVENT_UNKNOWN) - goto unlock_out; - - /* LP has sent verify mPacket */ - if ((status & FPE_EVENT_RVER) == FPE_EVENT_RVER) - stmmac_fpe_send_mpacket(priv, priv->ioaddr, fpe_cfg, - MPACKET_RESPONSE); - - /* Local has sent verify mPacket */ - if ((status & FPE_EVENT_TVER) == FPE_EVENT_TVER && - fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED) - fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_VERIFYING; - - /* LP has sent response mPacket */ - if ((status & FPE_EVENT_RRSP) == FPE_EVENT_RRSP && - fpe_cfg->status == ETHTOOL_MM_VERIFY_STATUS_VERIFYING) - fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED; - -unlock_out: - spin_unlock(&fpe_cfg->lock); -} - static void stmmac_common_interrupt(struct stmmac_priv *priv) { u32 rx_cnt = priv->plat->rx_queues_to_use; @@ -6000,12 +5956,8 @@ static void stmmac_common_interrupt(struct stmmac_priv *priv) stmmac_est_irq_status(priv, priv, priv->dev, &priv->xstats, tx_cnt); - if (priv->dma_cap.fpesel) { - int status = stmmac_fpe_irq_status(priv, priv->ioaddr, - priv->dev); - - stmmac_fpe_event_status(priv, status); - } + if (stmmac_fpe_supported(priv)) + stmmac_fpe_irq_status(priv); /* To handle GMAC own interrupts */ if ((priv->plat->has_gmac) || xmac) { @@ -7337,90 +7289,6 @@ int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size) return ret; } -/** - * stmmac_fpe_verify_timer - Timer for MAC Merge verification - * @t: timer_list struct containing private info - * - * Verify the MAC Merge capability in the local TX direction, by - * transmitting Verify mPackets up to 3 times. Wait until link - * partner responds with a Response mPacket, otherwise fail. - */ -static void stmmac_fpe_verify_timer(struct timer_list *t) -{ - struct stmmac_fpe_cfg *fpe_cfg = from_timer(fpe_cfg, t, verify_timer); - struct stmmac_priv *priv = container_of(fpe_cfg, struct stmmac_priv, - fpe_cfg); - unsigned long flags; - bool rearm = false; - - spin_lock_irqsave(&fpe_cfg->lock, flags); - - switch (fpe_cfg->status) { - case ETHTOOL_MM_VERIFY_STATUS_INITIAL: - case ETHTOOL_MM_VERIFY_STATUS_VERIFYING: - if (fpe_cfg->verify_retries != 0) { - stmmac_fpe_send_mpacket(priv, priv->ioaddr, - fpe_cfg, MPACKET_VERIFY); - rearm = true; - } else { - fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_FAILED; - } - - fpe_cfg->verify_retries--; - break; - - case ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED: - stmmac_fpe_configure(priv, priv->ioaddr, fpe_cfg, - priv->plat->tx_queues_to_use, - priv->plat->rx_queues_to_use, - true, true); - break; - - default: - break; - } - - if (rearm) { - mod_timer(&fpe_cfg->verify_timer, - jiffies + msecs_to_jiffies(fpe_cfg->verify_time)); - } - - spin_unlock_irqrestore(&fpe_cfg->lock, flags); -} - -static void stmmac_fpe_verify_timer_arm(struct stmmac_fpe_cfg *fpe_cfg) -{ - if (fpe_cfg->pmac_enabled && fpe_cfg->tx_enabled && - fpe_cfg->verify_enabled && - fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_FAILED && - fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED) { - timer_setup(&fpe_cfg->verify_timer, stmmac_fpe_verify_timer, 0); - mod_timer(&fpe_cfg->verify_timer, jiffies); - } -} - -void stmmac_fpe_apply(struct stmmac_priv *priv) -{ - struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg; - - /* If verification is disabled, configure FPE right away. - * Otherwise let the timer code do it. - */ - if (!fpe_cfg->verify_enabled) { - stmmac_fpe_configure(priv, priv->ioaddr, fpe_cfg, - priv->plat->tx_queues_to_use, - priv->plat->rx_queues_to_use, - fpe_cfg->tx_enabled, - fpe_cfg->pmac_enabled); - } else { - fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_INITIAL; - fpe_cfg->verify_retries = STMMAC_FPE_MM_MAX_VERIFY_RETRIES; - - if (netif_running(priv->dev)) - stmmac_fpe_verify_timer_arm(fpe_cfg); - } -} - static int stmmac_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp) { const struct stmmac_xdp_buff *ctx = (void *)_ctx; @@ -7699,11 +7567,7 @@ int stmmac_dvr_probe(struct device *device, mutex_init(&priv->lock); - priv->fpe_cfg.verify_retries = STMMAC_FPE_MM_MAX_VERIFY_RETRIES; - priv->fpe_cfg.verify_time = STMMAC_FPE_MM_MAX_VERIFY_TIME_MS; - priv->fpe_cfg.status = ETHTOOL_MM_VERIFY_STATUS_DISABLED; - timer_setup(&priv->fpe_cfg.verify_timer, stmmac_fpe_verify_timer, 0); - spin_lock_init(&priv->fpe_cfg.lock); + stmmac_fpe_init(priv); /* If a specific clk_csr value is passed from the platform * this means that the CSR Clock Range selection cannot be @@ -7878,7 +7742,7 @@ int stmmac_suspend(struct device *dev) } rtnl_unlock(); - if (priv->dma_cap.fpesel) + if (stmmac_fpe_supported(priv)) timer_shutdown_sync(&priv->fpe_cfg.verify_timer); priv->speed = SPEED_UNKNOWN; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index ad868e8d195d..3ac32444e492 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -522,6 +522,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) if (of_device_is_compatible(np, "st,spear600-gmac") || of_device_is_compatible(np, "snps,dwmac-3.50a") || of_device_is_compatible(np, "snps,dwmac-3.70a") || + of_device_is_compatible(np, "snps,dwmac-3.72a") || of_device_is_compatible(np, "snps,dwmac")) { /* Note that the max-frame-size parameter as defined in the * ePAPR v1.1 spec is defined as max-frame-size, it's diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 75ad2da1a37f..6a79e6a111ed 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -1290,8 +1290,8 @@ const struct stmmac_tc_ops dwxgmac_tc_ops = { .setup_cls_u32 = tc_setup_cls_u32, .setup_cbs = tc_setup_cbs, .setup_cls = tc_setup_cls, - .setup_taprio = tc_setup_taprio_without_fpe, + .setup_taprio = tc_setup_taprio, .setup_etf = tc_setup_etf, .query_caps = tc_query_caps, - .setup_mqprio = tc_setup_mqprio_unimplemented, + .setup_mqprio = tc_setup_dwmac510_mqprio, }; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 6201a09fa5f0..47fb5af16796 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -337,9 +337,9 @@ static int am65_cpsw_nuss_rx_push(struct am65_cpsw_common *common, struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; struct cppi5_host_desc_t *desc_rx; struct device *dev = common->dev; + struct am65_cpsw_swdata *swdata; dma_addr_t desc_dma; dma_addr_t buf_dma; - void *swdata; desc_rx = k3_cppi_desc_pool_alloc(rx_chn->desc_pool); if (!desc_rx) { @@ -363,7 +363,8 @@ static int am65_cpsw_nuss_rx_push(struct am65_cpsw_common *common, cppi5_hdesc_attach_buf(desc_rx, buf_dma, AM65_CPSW_MAX_PACKET_SIZE, buf_dma, AM65_CPSW_MAX_PACKET_SIZE); swdata = cppi5_hdesc_get_swdata(desc_rx); - *((void **)swdata) = page_address(page); + swdata->page = page; + swdata->flow_id = flow_idx; return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, flow_idx, desc_rx, desc_dma); @@ -519,36 +520,31 @@ static enum am65_cpsw_tx_buf_type am65_cpsw_nuss_buf_type(struct am65_cpsw_tx_ch static inline void am65_cpsw_put_page(struct am65_cpsw_rx_flow *flow, struct page *page, - bool allow_direct, - int desc_idx) + bool allow_direct) { page_pool_put_full_page(flow->page_pool, page, allow_direct); - flow->pages[desc_idx] = NULL; } static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma) { - struct am65_cpsw_rx_flow *flow = data; + struct am65_cpsw_rx_chn *rx_chn = data; struct cppi5_host_desc_t *desc_rx; - struct am65_cpsw_rx_chn *rx_chn; + struct am65_cpsw_swdata *swdata; dma_addr_t buf_dma; + struct page *page; u32 buf_dma_len; - void *page_addr; - void **swdata; - int desc_idx; + u32 flow_id; - rx_chn = &flow->common->rx_chns; desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma); swdata = cppi5_hdesc_get_swdata(desc_rx); - page_addr = *swdata; + page = swdata->page; + flow_id = swdata->flow_id; cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len); k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma); dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE); k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); - desc_idx = am65_cpsw_nuss_desc_idx(rx_chn->desc_pool, desc_rx, - rx_chn->dsize_log2); - am65_cpsw_put_page(flow, virt_to_page(page_addr), false, desc_idx); + am65_cpsw_put_page(&rx_chn->flows[flow_id], page, false); } static void am65_cpsw_nuss_xmit_free(struct am65_cpsw_tx_chn *tx_chn, @@ -703,14 +699,13 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) ret = -ENOMEM; goto fail_rx; } - flow->pages[i] = page; ret = am65_cpsw_nuss_rx_push(common, page, flow_idx); if (ret < 0) { dev_err(common->dev, "cannot submit page to rx channel flow %d, error %d\n", flow_idx, ret); - am65_cpsw_put_page(flow, page, false, i); + am65_cpsw_put_page(flow, page, false); goto fail_rx; } } @@ -764,8 +759,8 @@ fail_tx: fail_rx: for (i = 0; i < common->rx_ch_num_flows; i++) - k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, &rx_chn->flows[i], - am65_cpsw_nuss_rx_cleanup, 0); + k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, rx_chn, + am65_cpsw_nuss_rx_cleanup, !!i); am65_cpsw_destroy_xdp_rxqs(common); @@ -817,11 +812,11 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common) dev_err(common->dev, "rx teardown timeout\n"); } - for (i = 0; i < common->rx_ch_num_flows; i++) { + for (i = common->rx_ch_num_flows - 1; i >= 0; i--) { napi_disable(&rx_chn->flows[i].napi_rx); hrtimer_cancel(&rx_chn->flows[i].rx_hrtimer); - k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, &rx_chn->flows[i], - am65_cpsw_nuss_rx_cleanup, 0); + k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, rx_chn, + am65_cpsw_nuss_rx_cleanup, !!i); } k3_udma_glue_disable_rx_chn(rx_chn->rx_chn); @@ -1028,7 +1023,7 @@ pool_free: static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow, struct am65_cpsw_port *port, struct xdp_buff *xdp, - int desc_idx, int cpu, int *len) + int cpu, int *len) { struct am65_cpsw_common *common = flow->common; struct net_device *ndev = port->ndev; @@ -1090,7 +1085,7 @@ drop: } page = virt_to_head_page(xdp->data); - am65_cpsw_put_page(flow, page, true, desc_idx); + am65_cpsw_put_page(flow, page, true); out: return ret; @@ -1138,16 +1133,16 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, struct am65_cpsw_ndev_priv *ndev_priv; struct cppi5_host_desc_t *desc_rx; struct device *dev = common->dev; + struct am65_cpsw_swdata *swdata; struct page *page, *new_page; dma_addr_t desc_dma, buf_dma; struct am65_cpsw_port *port; - int headroom, desc_idx, ret; struct net_device *ndev; u32 flow_idx = flow->id; struct sk_buff *skb; struct xdp_buff xdp; + int headroom, ret; void *page_addr; - void **swdata; u32 *psdata; *xdp_state = AM65_CPSW_XDP_PASS; @@ -1170,8 +1165,8 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, __func__, flow_idx, &desc_dma); swdata = cppi5_hdesc_get_swdata(desc_rx); - page_addr = *swdata; - page = virt_to_page(page_addr); + page = swdata->page; + page_addr = page_address(page); cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len); k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma); pkt_len = cppi5_hdesc_get_pktlen(desc_rx); @@ -1187,9 +1182,6 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); - desc_idx = am65_cpsw_nuss_desc_idx(rx_chn->desc_pool, desc_rx, - rx_chn->dsize_log2); - skb = am65_cpsw_build_skb(page_addr, ndev, AM65_CPSW_MAX_PACKET_SIZE); if (unlikely(!skb)) { @@ -1201,7 +1193,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, xdp_init_buff(&xdp, PAGE_SIZE, &port->xdp_rxq[flow->id]); xdp_prepare_buff(&xdp, page_addr, AM65_CPSW_HEADROOM, pkt_len, false); - *xdp_state = am65_cpsw_run_xdp(flow, port, &xdp, desc_idx, + *xdp_state = am65_cpsw_run_xdp(flow, port, &xdp, cpu, &pkt_len); if (*xdp_state != AM65_CPSW_XDP_PASS) goto allocate; @@ -1230,10 +1222,8 @@ allocate: return -ENOMEM; } - flow->pages[desc_idx] = new_page; - if (netif_dormant(ndev)) { - am65_cpsw_put_page(flow, new_page, true, desc_idx); + am65_cpsw_put_page(flow, new_page, true); ndev->stats.rx_dropped++; return 0; } @@ -1241,7 +1231,7 @@ allocate: requeue: ret = am65_cpsw_nuss_rx_push(common, new_page, flow_idx); if (WARN_ON(ret < 0)) { - am65_cpsw_put_page(flow, new_page, true, desc_idx); + am65_cpsw_put_page(flow, new_page, true); ndev->stats.rx_errors++; ndev->stats.rx_dropped++; } @@ -2343,10 +2333,6 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) for (i = 0; i < common->rx_ch_num_flows; i++) { flow = &rx_chn->flows[i]; flow->page_pool = NULL; - flow->pages = devm_kcalloc(dev, AM65_CPSW_MAX_RX_DESC, - sizeof(*flow->pages), GFP_KERNEL); - if (!flow->pages) - return -ENOMEM; } rx_chn->rx_chn = k3_udma_glue_request_rx_chn(dev, "rx", &rx_cfg); @@ -2396,10 +2382,12 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) flow = &rx_chn->flows[i]; flow->id = i; flow->common = common; + flow->irq = -EINVAL; rx_flow_cfg.ring_rxfdq0_id = fdqring_id; rx_flow_cfg.rx_cfg.size = max_desc_num; - rx_flow_cfg.rxfdq_cfg.size = max_desc_num; + /* share same FDQ for all flows */ + rx_flow_cfg.rxfdq_cfg.size = max_desc_num * rx_cfg.flow_id_num; rx_flow_cfg.rxfdq_cfg.mode = common->pdata.fdqring_mode; ret = k3_udma_glue_rx_flow_init(rx_chn->rx_chn, @@ -2437,6 +2425,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) if (ret) { dev_err(dev, "failure requesting rx %d irq %u, %d\n", i, flow->irq, ret); + flow->irq = -EINVAL; goto err; } } @@ -3274,8 +3263,8 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) for (i = 0; i < common->rx_ch_num_flows; i++) k3_udma_glue_reset_rx_chn(rx_chan->rx_chn, i, - &rx_chan->flows[i], - am65_cpsw_nuss_rx_cleanup, 0); + rx_chan, + am65_cpsw_nuss_rx_cleanup, !!i); k3_udma_glue_disable_rx_chn(rx_chan->rx_chn); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index 3f3e353dfe88..e7832a5cf3cc 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -101,10 +101,14 @@ struct am65_cpsw_rx_flow { struct hrtimer rx_hrtimer; unsigned long rx_pace_timeout; struct page_pool *page_pool; - struct page **pages; char name[32]; }; +struct am65_cpsw_swdata { + u32 flow_id; + struct page *page; +}; + struct am65_cpsw_rx_chn { struct device *dev; struct device *dma_dev; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 0556910938fa..b4d70c6e0cff 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -808,6 +808,47 @@ static netdev_features_t emac_ndo_fix_features(struct net_device *ndev, return features; } +static int emac_ndo_vlan_rx_add_vid(struct net_device *ndev, + __be16 proto, u16 vid) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + int untag_mask = 0; + int port_mask; + + if (prueth->is_hsr_offload_mode) { + port_mask = BIT(PRUETH_PORT_HOST) | BIT(emac->port_id); + untag_mask = 0; + + netdev_dbg(emac->ndev, "VID add vid:%u port_mask:%X untag_mask %X\n", + vid, port_mask, untag_mask); + + icssg_vtbl_modify(emac, vid, port_mask, untag_mask, true); + icssg_set_pvid(emac->prueth, vid, emac->port_id); + } + return 0; +} + +static int emac_ndo_vlan_rx_del_vid(struct net_device *ndev, + __be16 proto, u16 vid) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + int untag_mask = 0; + int port_mask; + + if (prueth->is_hsr_offload_mode) { + port_mask = BIT(PRUETH_PORT_HOST); + untag_mask = 0; + + netdev_dbg(emac->ndev, "VID del vid:%u port_mask:%X untag_mask %X\n", + vid, port_mask, untag_mask); + + icssg_vtbl_modify(emac, vid, port_mask, untag_mask, false); + } + return 0; +} + static const struct net_device_ops emac_netdev_ops = { .ndo_open = emac_ndo_open, .ndo_stop = emac_ndo_stop, @@ -820,6 +861,8 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_get_stats64 = icssg_ndo_get_stats64, .ndo_get_phys_port_name = icssg_ndo_get_phys_port_name, .ndo_fix_features = emac_ndo_fix_features, + .ndo_vlan_rx_add_vid = emac_ndo_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = emac_ndo_vlan_rx_del_vid, }; static int prueth_netdev_init(struct prueth *prueth, @@ -947,7 +990,7 @@ static int prueth_netdev_init(struct prueth *prueth, ndev->netdev_ops = &emac_netdev_ops; ndev->ethtool_ops = &icssg_ethtool_ops; ndev->hw_features = NETIF_F_SG; - ndev->features = ndev->hw_features; + ndev->features = ndev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; ndev->hw_features |= NETIF_PRUETH_HSR_OFFLOAD_FEATURES; netif_napi_add(ndev, &emac->napi_rx, icssg_napi_rx_poll); diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c index a04d4073def9..2c37957478fb 100644 --- a/drivers/net/ethernet/vertexcom/mse102x.c +++ b/drivers/net/ethernet/vertexcom/mse102x.c @@ -222,7 +222,7 @@ static int mse102x_tx_frame_spi(struct mse102x_net *mse, struct sk_buff *txp, struct mse102x_net_spi *mses = to_mse102x_spi(mse); struct spi_transfer *xfer = &mses->spi_xfer; struct spi_message *msg = &mses->spi_msg; - struct sk_buff *tskb; + struct sk_buff *tskb = NULL; int ret; netif_dbg(mse, tx_queued, mse->ndev, "%s: skb %p, %d@%p\n", @@ -235,7 +235,6 @@ static int mse102x_tx_frame_spi(struct mse102x_net *mse, struct sk_buff *txp, if (!tskb) return -ENOMEM; - dev_kfree_skb(txp); txp = tskb; } @@ -257,6 +256,8 @@ static int mse102x_tx_frame_spi(struct mse102x_net *mse, struct sk_buff *txp, mse->stats.xfer_err++; } + dev_kfree_skb(tskb); + return ret; } diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 273ec5f70005..0f4b02fe6f85 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -924,13 +924,13 @@ axienet_start_xmit_dmaengine(struct sk_buff *skb, struct net_device *ndev) skbuf_dma->sg_len = sg_len; dma_tx_desc->callback_param = lp; dma_tx_desc->callback_result = axienet_dma_tx_cb; - dmaengine_submit(dma_tx_desc); - dma_async_issue_pending(lp->tx_chan); txq = skb_get_tx_queue(lp->ndev, skb); netdev_tx_sent_queue(txq, skb->len); netif_txq_maybe_stop(txq, CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX), MAX_SKB_FRAGS + 1, 2 * MAX_SKB_FRAGS); + dmaengine_submit(dma_tx_desc); + dma_async_issue_pending(lp->tx_chan); return NETDEV_TX_OK; xmit_error_unmap_sg: diff --git a/drivers/net/fjes/fjes_ethtool.c b/drivers/net/fjes/fjes_ethtool.c index 19c99529566b..70c53f33d857 100644 --- a/drivers/net/fjes/fjes_ethtool.c +++ b/drivers/net/fjes/fjes_ethtool.c @@ -87,49 +87,31 @@ static void fjes_get_strings(struct net_device *netdev, { struct fjes_adapter *adapter = netdev_priv(netdev); struct fjes_hw *hw = &adapter->hw; - u8 *p = data; int i; - switch (stringset) { - case ETH_SS_STATS: - for (i = 0; i < ARRAY_SIZE(fjes_gstrings_stats); i++) { - memcpy(p, fjes_gstrings_stats[i].stat_string, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - for (i = 0; i < hw->max_epid; i++) { - if (i == hw->my_epid) - continue; - sprintf(p, "ep%u_com_regist_buf_exec", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_com_unregist_buf_exec", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_send_intr_rx", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_send_intr_unshare", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_send_intr_zoneupdate", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_recv_intr_rx", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_recv_intr_unshare", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_recv_intr_stop", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_recv_intr_zoneupdate", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_tx_buffer_full", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_tx_dropped_not_shared", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_tx_dropped_ver_mismatch", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_tx_dropped_buf_size_mismatch", i); - p += ETH_GSTRING_LEN; - sprintf(p, "ep%u_tx_dropped_vlanid_mismatch", i); - p += ETH_GSTRING_LEN; - } - break; + if (stringset != ETH_SS_STATS) + return; + + for (i = 0; i < ARRAY_SIZE(fjes_gstrings_stats); i++) + ethtool_puts(&data, fjes_gstrings_stats[i].stat_string); + + for (i = 0; i < hw->max_epid; i++) { + if (i == hw->my_epid) + continue; + ethtool_sprintf(&data, "ep%u_com_regist_buf_exec", i); + ethtool_sprintf(&data, "ep%u_com_unregist_buf_exec", i); + ethtool_sprintf(&data, "ep%u_send_intr_rx", i); + ethtool_sprintf(&data, "ep%u_send_intr_unshare", i); + ethtool_sprintf(&data, "ep%u_send_intr_zoneupdate", i); + ethtool_sprintf(&data, "ep%u_recv_intr_rx", i); + ethtool_sprintf(&data, "ep%u_recv_intr_unshare", i); + ethtool_sprintf(&data, "ep%u_recv_intr_stop", i); + ethtool_sprintf(&data, "ep%u_recv_intr_zoneupdate", i); + ethtool_sprintf(&data, "ep%u_tx_buffer_full", i); + ethtool_sprintf(&data, "ep%u_tx_dropped_not_shared", i); + ethtool_sprintf(&data, "ep%u_tx_dropped_ver_mismatch", i); + ethtool_sprintf(&data, "ep%u_tx_dropped_buf_size_mismatch", i); + ethtool_sprintf(&data, "ep%u_tx_dropped_vlanid_mismatch", i); } } diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index a60bfb1abb7f..89a996ad8cd0 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1491,10 +1491,8 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, } gtp->role = role; - if (!data[IFLA_GTP_RESTART_COUNT]) - gtp->restart_count = 0; - else - gtp->restart_count = nla_get_u8(data[IFLA_GTP_RESTART_COUNT]); + gtp->restart_count = nla_get_u8_default(data[IFLA_GTP_RESTART_COUNT], + 0); gtp->net = src_net; @@ -1702,20 +1700,24 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]) return -EINVAL; if (data[IFLA_GTP_FD0]) { - u32 fd0 = nla_get_u32(data[IFLA_GTP_FD0]); + int fd0 = nla_get_u32(data[IFLA_GTP_FD0]); - sk0 = gtp_encap_enable_socket(fd0, UDP_ENCAP_GTP0, gtp); - if (IS_ERR(sk0)) - return PTR_ERR(sk0); + if (fd0 >= 0) { + sk0 = gtp_encap_enable_socket(fd0, UDP_ENCAP_GTP0, gtp); + if (IS_ERR(sk0)) + return PTR_ERR(sk0); + } } if (data[IFLA_GTP_FD1]) { - u32 fd1 = nla_get_u32(data[IFLA_GTP_FD1]); + int fd1 = nla_get_u32(data[IFLA_GTP_FD1]); - sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp); - if (IS_ERR(sk1u)) { - gtp_encap_disable_sock(sk0); - return PTR_ERR(sk1u); + if (fd1 >= 0) { + sk1u = gtp_encap_enable_socket(fd1, UDP_ENCAP_GTP1U, gtp); + if (IS_ERR(sk1u)) { + gtp_encap_disable_sock(sk0); + return PTR_ERR(sk1u); + } } } @@ -1825,10 +1827,7 @@ static struct pdp_ctx *gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, version = nla_get_u32(info->attrs[GTPA_VERSION]); - if (info->attrs[GTPA_FAMILY]) - family = nla_get_u8(info->attrs[GTPA_FAMILY]); - else - family = AF_INET; + family = nla_get_u8_default(info->attrs[GTPA_FAMILY], AF_INET); #if !IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6) @@ -2065,10 +2064,7 @@ static struct pdp_ctx *gtp_find_pdp_by_link(struct net *net, struct gtp_dev *gtp; int family; - if (nla[GTPA_FAMILY]) - family = nla_get_u8(nla[GTPA_FAMILY]); - else - family = AF_INET; + family = nla_get_u8_default(nla[GTPA_FAMILY], AF_INET); gtp = gtp_find_dev(net, nla); if (!gtp) diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index 2c1b5def4a0b..67424888ff0a 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -426,22 +426,21 @@ static int __init ifb_init_module(void) { int i, err; - down_write(&pernet_ops_rwsem); - rtnl_lock(); - err = __rtnl_link_register(&ifb_link_ops); + err = rtnl_link_register(&ifb_link_ops); if (err < 0) - goto out; + return err; + + rtnl_net_lock(&init_net); for (i = 0; i < numifbs && !err; i++) { err = ifb_init_one(i); cond_resched(); } - if (err) - __rtnl_link_unregister(&ifb_link_ops); -out: - rtnl_unlock(); - up_write(&pernet_ops_rwsem); + rtnl_net_unlock(&init_net); + + if (err) + rtnl_link_unregister(&ifb_link_ops); return err; } diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index b1afcb8740de..fd591ddb3884 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -3,6 +3,7 @@ */ #include <net/inet_dscp.h> +#include <net/ip.h> #include "ipvlan.h" @@ -422,7 +423,7 @@ static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb) int err, ret = NET_XMIT_DROP; struct flowi4 fl4 = { .flowi4_oif = dev->ifindex, - .flowi4_tos = ip4h->tos & INET_DSCP_MASK, + .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)), .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, .daddr = ip4h->daddr, diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 26034f80d4a4..1bc1e5993f56 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2621,6 +2621,17 @@ static void macsec_set_head_tail_room(struct net_device *dev) dev->needed_tailroom = real_dev->needed_tailroom + needed_tailroom; } +static void macsec_inherit_tso_max(struct net_device *dev) +{ + struct macsec_dev *macsec = macsec_priv(dev); + + /* if macsec is offloaded, we need to follow the lower + * device's capabilities. otherwise, we can ignore them. + */ + if (macsec_is_offloaded(macsec)) + netif_inherit_tso_max(dev, macsec->real_dev); +} + static int macsec_update_offload(struct net_device *dev, enum macsec_offload offload) { enum macsec_offload prev_offload; @@ -2666,6 +2677,10 @@ static int macsec_update_offload(struct net_device *dev, enum macsec_offload off macsec_set_head_tail_room(dev); macsec->insert_tx_tag = macsec_needs_tx_tag(macsec, ops); + macsec_inherit_tso_max(dev); + + netdev_update_features(dev); + return ret; } @@ -3521,6 +3536,10 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, #define MACSEC_FEATURES \ (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST) +#define MACSEC_OFFLOAD_FEATURES \ + (MACSEC_FEATURES | NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES | \ + NETIF_F_LRO | NETIF_F_RXHASH | NETIF_F_CSUM_MASK | NETIF_F_RXCSUM) + static int macsec_dev_init(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); @@ -3531,7 +3550,12 @@ static int macsec_dev_init(struct net_device *dev) if (err) return err; - dev->features = real_dev->features & MACSEC_FEATURES; + macsec_inherit_tso_max(dev); + + dev->hw_features = real_dev->hw_features & MACSEC_OFFLOAD_FEATURES; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + + dev->features = real_dev->features & MACSEC_OFFLOAD_FEATURES; dev->features |= NETIF_F_GSO_SOFTWARE; dev->lltx = true; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; @@ -3561,8 +3585,12 @@ static netdev_features_t macsec_fix_features(struct net_device *dev, { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; + netdev_features_t mask; + + mask = macsec_is_offloaded(macsec) ? MACSEC_OFFLOAD_FEATURES + : MACSEC_FEATURES; - features &= (real_dev->features & MACSEC_FEATURES) | + features &= (real_dev->features & mask) | NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES; return features; @@ -3798,8 +3826,7 @@ static void macsec_free_netdev(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); - if (macsec->secy.tx_sc.md_dst) - metadata_dst_free(macsec->secy.tx_sc.md_dst); + dst_release(&macsec->secy.tx_sc.md_dst->dst); free_percpu(macsec->stats); free_percpu(macsec->secy.tx_sc.stats); @@ -4300,9 +4327,9 @@ static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[], } } - es = data[IFLA_MACSEC_ES] ? nla_get_u8(data[IFLA_MACSEC_ES]) : false; - sci = data[IFLA_MACSEC_INC_SCI] ? nla_get_u8(data[IFLA_MACSEC_INC_SCI]) : false; - scb = data[IFLA_MACSEC_SCB] ? nla_get_u8(data[IFLA_MACSEC_SCB]) : false; + es = nla_get_u8_default(data[IFLA_MACSEC_ES], false); + sci = nla_get_u8_default(data[IFLA_MACSEC_INC_SCI], false); + scb = nla_get_u8_default(data[IFLA_MACSEC_SCB], false); if ((sci && (scb || es)) || (scb && es)) return -EINVAL; @@ -4429,31 +4456,26 @@ static int macsec_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *real_dev = netdev_notifier_info_to_dev(ptr); + struct macsec_rxh_data *rxd; + struct macsec_dev *m, *n; LIST_HEAD(head); if (!is_macsec_master(real_dev)) return NOTIFY_DONE; + rxd = macsec_data_rtnl(real_dev); + switch (event) { case NETDEV_DOWN: case NETDEV_UP: - case NETDEV_CHANGE: { - struct macsec_dev *m, *n; - struct macsec_rxh_data *rxd; - - rxd = macsec_data_rtnl(real_dev); + case NETDEV_CHANGE: list_for_each_entry_safe(m, n, &rxd->secys, secys) { struct net_device *dev = m->secy.netdev; netif_stacked_transfer_operstate(real_dev, dev); } break; - } - case NETDEV_UNREGISTER: { - struct macsec_dev *m, *n; - struct macsec_rxh_data *rxd; - - rxd = macsec_data_rtnl(real_dev); + case NETDEV_UNREGISTER: list_for_each_entry_safe(m, n, &rxd->secys, secys) { macsec_common_dellink(m->secy.netdev, &head); } @@ -4463,12 +4485,7 @@ static int macsec_notify(struct notifier_block *this, unsigned long event, unregister_netdevice_many(&head); break; - } - case NETDEV_CHANGEMTU: { - struct macsec_dev *m; - struct macsec_rxh_data *rxd; - - rxd = macsec_data_rtnl(real_dev); + case NETDEV_CHANGEMTU: list_for_each_entry(m, &rxd->secys, secys) { struct net_device *dev = m->secy.netdev; unsigned int mtu = real_dev->mtu - (m->secy.icv_len + @@ -4477,7 +4494,13 @@ static int macsec_notify(struct notifier_block *this, unsigned long event, if (dev->mtu > mtu) dev_set_mtu(dev, mtu); } - } + break; + case NETDEV_FEAT_CHANGE: + list_for_each_entry(m, &rxd->secys, secys) { + macsec_inherit_tso_max(m->secy.netdev); + netdev_update_features(m->secy.netdev); + } + break; } return NOTIFY_OK; diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index 4dc057c121f5..d2b3f5a59141 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -588,6 +588,9 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev, if (len > MCTP_I2C_MAXMTU) return -EMSGSIZE; + if (!daddr || !saddr) + return -EINVAL; + lldst = *((u8 *)daddr); llsrc = *((u8 *)saddr); @@ -877,7 +880,8 @@ static int mctp_i2c_add_netdev(struct mctp_i2c_client *mcli, goto err; } - rc = mctp_register_netdev(ndev, &mctp_i2c_mctp_ops); + rc = mctp_register_netdev(ndev, &mctp_i2c_mctp_ops, + MCTP_PHYS_BINDING_SMBUS); if (rc < 0) { dev_err(&mcli->client->dev, "register netdev \"%s\" failed %d\n", diff --git a/drivers/net/mctp/mctp-i3c.c b/drivers/net/mctp/mctp-i3c.c index 1bc87a062686..9adad59b8676 100644 --- a/drivers/net/mctp/mctp-i3c.c +++ b/drivers/net/mctp/mctp-i3c.c @@ -607,7 +607,7 @@ __must_hold(&busdevs_lock) goto err_free_uninit; } - rc = mctp_register_netdev(ndev, NULL); + rc = mctp_register_netdev(ndev, NULL, MCTP_PHYS_BINDING_I3C); if (rc < 0) { dev_warn(&ndev->dev, "netdev register failed: %d\n", rc); goto err_free_netdev; diff --git a/drivers/net/mctp/mctp-serial.c b/drivers/net/mctp/mctp-serial.c index e63720ec3238..26c9a33fd636 100644 --- a/drivers/net/mctp/mctp-serial.c +++ b/drivers/net/mctp/mctp-serial.c @@ -23,6 +23,7 @@ #include <linux/mctp.h> #include <net/mctp.h> +#include <net/mctpdevice.h> #include <net/pkt_sched.h> #define MCTP_SERIAL_MTU 68 /* base mtu (64) + mctp header */ @@ -470,7 +471,7 @@ static int mctp_serial_open(struct tty_struct *tty) spin_lock_init(&dev->lock); INIT_WORK(&dev->tx_work, mctp_serial_tx_work); - rc = register_netdev(ndev); + rc = mctp_register_netdev(ndev, NULL, MCTP_PHYS_BINDING_SERIAL); if (rc) goto free_netdev; @@ -492,7 +493,7 @@ static void mctp_serial_close(struct tty_struct *tty) struct mctp_serial *dev = tty->disc_data; int idx = dev->idx; - unregister_netdev(dev->netdev); + mctp_unregister_netdev(dev->netdev); ida_free(&mctp_serial_ida, idx); } diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index 41e80f78b316..16c382c42227 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -1377,10 +1377,12 @@ static ssize_t nsim_nexthop_bucket_activity_write(struct file *file, if (pos != 0) return -EINVAL; - if (size > sizeof(buf)) + if (size > sizeof(buf) - 1) return -EINVAL; if (copy_from_user(buf, user_buf, size)) return -EFAULT; + buf[size] = 0; + if (sscanf(buf, "%u %hu", &nhid, &bucket_index) != 2) return -EINVAL; diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index cad85bb0cf54..0be47fed4efc 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -663,7 +663,11 @@ static void nsim_setup(struct net_device *dev) NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | NETIF_F_TSO; - dev->hw_features |= NETIF_F_HW_TC; + dev->hw_features |= NETIF_F_HW_TC | + NETIF_F_SG | + NETIF_F_FRAGLIST | + NETIF_F_HW_CSUM | + NETIF_F_TSO; dev->max_mtu = ETH_MAX_MTU; dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD; } diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index cd8360b9bbde..bb07725d1c72 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -351,12 +351,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, if (data[IFLA_NETKIT_PEER_INFO]) { attr = data[IFLA_NETKIT_PEER_INFO]; ifmp = nla_data(attr); - err = rtnl_nla_parse_ifinfomsg(peer_tb, attr, extack); - if (err < 0) - return err; - err = netkit_validate(peer_tb, NULL, extack); - if (err < 0) - return err; + rtnl_nla_parse_ifinfomsg(peer_tb, attr, extack); tbp = peer_tb; } if (data[IFLA_NETKIT_SCRUB]) @@ -391,9 +386,6 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, return -EOPNOTSUPP; net = rtnl_link_get_net(src_net, tbp); - if (IS_ERR(net)) - return PTR_ERR(net); - peer = rtnl_create_link(net, ifname, ifname_assign_type, &netkit_link_ops, tbp, extack); if (IS_ERR(peer)) { @@ -978,6 +970,7 @@ static struct rtnl_link_ops netkit_link_ops = { .fill_info = netkit_fill_info, .policy = netkit_policy, .validate = netkit_validate, + .peer_type = IFLA_NETKIT_PEER_INFO, .maxtype = IFLA_NETKIT_MAX, }; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index ee3ea0b56d48..15828f4710a9 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -266,22 +266,7 @@ config MAXLINEAR_GPHY Support for the Maxlinear GPY115, GPY211, GPY212, GPY215, GPY241, GPY245 PHYs. -config MEDIATEK_GE_PHY - tristate "MediaTek Gigabit Ethernet PHYs" - help - Supports the MediaTek Gigabit Ethernet PHYs. - -config MEDIATEK_GE_SOC_PHY - tristate "MediaTek SoC Ethernet PHYs" - depends on (ARM64 && ARCH_MEDIATEK) || COMPILE_TEST - depends on NVMEM_MTK_EFUSE - help - Supports MediaTek SoC built-in Gigabit Ethernet PHYs. - - Include support for built-in Ethernet PHYs which are present in - the MT7981 and MT7988 SoCs. These PHYs need calibration data - present in the SoCs efuse and will dynamically calibrate VCM - (common-mode voltage) during startup. +source "drivers/net/phy/mediatek/Kconfig" config MICREL_PHY tristate "Micrel PHYs" diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 90f886844381..e6145153e837 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -74,8 +74,7 @@ obj-$(CONFIG_MARVELL_PHY) += marvell.o obj-$(CONFIG_MARVELL_88Q2XXX_PHY) += marvell-88q2xxx.o obj-$(CONFIG_MARVELL_88X2222_PHY) += marvell-88x2222.o obj-$(CONFIG_MAXLINEAR_GPHY) += mxl-gpy.o -obj-$(CONFIG_MEDIATEK_GE_PHY) += mediatek-ge.o -obj-$(CONFIG_MEDIATEK_GE_SOC_PHY) += mediatek-ge-soc.o +obj-y += mediatek/ obj-$(CONFIG_MESON_GXL_PHY) += meson-gxl.o obj-$(CONFIG_MICREL_KS8995MA) += spi_ks8995.o obj-$(CONFIG_MICREL_PHY) += micrel.o diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c index 2e1a46e121d9..a2a862bae2ed 100644 --- a/drivers/net/phy/adin.c +++ b/drivers/net/phy/adin.c @@ -801,10 +801,8 @@ static void adin_get_strings(struct phy_device *phydev, u8 *data) { int i; - for (i = 0; i < ARRAY_SIZE(adin_hw_stats); i++) { - strscpy(&data[i * ETH_GSTRING_LEN], - adin_hw_stats[i].string, ETH_GSTRING_LEN); - } + for (i = 0; i < ARRAY_SIZE(adin_hw_stats); i++) + ethtool_puts(&data, adin_hw_stats[i].string); } static int adin_read_mmd_stat_regs(struct phy_device *phydev, diff --git a/drivers/net/phy/aquantia/aquantia_main.c b/drivers/net/phy/aquantia/aquantia_main.c index 38d0dd5c80a4..bb56a66d2a48 100644 --- a/drivers/net/phy/aquantia/aquantia_main.c +++ b/drivers/net/phy/aquantia/aquantia_main.c @@ -54,6 +54,12 @@ #define MDIO_AN_VEND_PROV_DOWNSHIFT_MASK GENMASK(3, 0) #define MDIO_AN_VEND_PROV_DOWNSHIFT_DFLT 4 +#define MDIO_AN_RESVD_VEND_PROV 0xc410 +#define MDIO_AN_RESVD_VEND_PROV_MDIX_AUTO 0 +#define MDIO_AN_RESVD_VEND_PROV_MDIX_MDI 1 +#define MDIO_AN_RESVD_VEND_PROV_MDIX_MDIX 2 +#define MDIO_AN_RESVD_VEND_PROV_MDIX_MASK GENMASK(1, 0) + #define MDIO_AN_TX_VEND_STATUS1 0xc800 #define MDIO_AN_TX_VEND_STATUS1_RATE_MASK GENMASK(3, 1) #define MDIO_AN_TX_VEND_STATUS1_10BASET 0 @@ -64,6 +70,9 @@ #define MDIO_AN_TX_VEND_STATUS1_5000BASET 5 #define MDIO_AN_TX_VEND_STATUS1_FULL_DUPLEX BIT(0) +#define MDIO_AN_RESVD_VEND_STATUS1 0xc810 +#define MDIO_AN_RESVD_VEND_STATUS1_MDIX BIT(8) + #define MDIO_AN_TX_VEND_INT_STATUS1 0xcc00 #define MDIO_AN_TX_VEND_INT_STATUS1_DOWNSHIFT BIT(1) @@ -155,12 +164,40 @@ static void aqr107_get_stats(struct phy_device *phydev, } } +static int aqr_set_mdix(struct phy_device *phydev, int mdix) +{ + u16 val = 0; + + switch (mdix) { + case ETH_TP_MDI: + val = MDIO_AN_RESVD_VEND_PROV_MDIX_MDI; + break; + case ETH_TP_MDI_X: + val = MDIO_AN_RESVD_VEND_PROV_MDIX_MDIX; + break; + case ETH_TP_MDI_AUTO: + case ETH_TP_MDI_INVALID: + default: + val = MDIO_AN_RESVD_VEND_PROV_MDIX_AUTO; + break; + } + + return phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_RESVD_VEND_PROV, + MDIO_AN_RESVD_VEND_PROV_MDIX_MASK, val); +} + static int aqr_config_aneg(struct phy_device *phydev) { bool changed = false; u16 reg; int ret; + ret = aqr_set_mdix(phydev, phydev->mdix_ctrl); + if (ret < 0) + return ret; + if (ret > 0) + changed = true; + if (phydev->autoneg == AUTONEG_DISABLE) return genphy_c45_pma_setup_forced(phydev); @@ -278,6 +315,21 @@ static int aqr_read_status(struct phy_device *phydev) val & MDIO_AN_RX_LP_STAT1_1000BASET_HALF); } + val = genphy_c45_aneg_done(phydev); + if (val < 0) + return val; + if (val) { + val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_RESVD_VEND_STATUS1); + if (val < 0) + return val; + if (val & MDIO_AN_RESVD_VEND_STATUS1_MDIX) + phydev->mdix = ETH_TP_MDI_X; + else + phydev->mdix = ETH_TP_MDI; + } else { + phydev->mdix = ETH_TP_MDI_INVALID; + } + return genphy_c45_read_status(phydev); } diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index 6c52f7dda514..5198d66dbbc0 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -523,8 +523,7 @@ void bcm_phy_get_strings(struct phy_device *phydev, u8 *data) unsigned int i; for (i = 0; i < ARRAY_SIZE(bcm_phy_hw_stats); i++) - strscpy(data + i * ETH_GSTRING_LEN, - bcm_phy_hw_stats[i].string, ETH_GSTRING_LEN); + ethtool_puts(&data, bcm_phy_hw_stats[i].string); } EXPORT_SYMBOL_GPL(bcm_phy_get_strings); @@ -1137,7 +1136,7 @@ int bcm_config_lre_aneg(struct phy_device *phydev, bool changed) { int err; - if (genphy_config_eee_advert(phydev)) + if (genphy_c45_an_config_eee_aneg(phydev) > 0) changed = true; err = bcm_setup_lre_master_slave(phydev); diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 3ab64e04a01c..cf8b6d0bfaa9 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -506,7 +506,7 @@ static int dp83822_config_init(struct phy_device *phydev) return dp83822_config_wol(phydev, &dp83822->wol); } -static int dp83826_config_rmii_mode(struct phy_device *phydev) +static int dp8382x_config_rmii_mode(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; const char *of_val; @@ -544,7 +544,7 @@ static int dp83826_config_init(struct phy_device *phydev) if (ret) return ret; - ret = dp83826_config_rmii_mode(phydev); + ret = dp8382x_config_rmii_mode(phydev); if (ret) return ret; } else { @@ -585,9 +585,14 @@ static int dp83826_config_init(struct phy_device *phydev) return dp83822_config_wol(phydev, &dp83822->wol); } -static int dp8382x_config_init(struct phy_device *phydev) +static int dp83825_config_init(struct phy_device *phydev) { struct dp83822_private *dp83822 = phydev->priv; + int ret; + + ret = dp8382x_config_rmii_mode(phydev); + if (ret) + return ret; return dp83822_config_wol(phydev, &dp83822->wol); } @@ -782,14 +787,14 @@ static int dp83822_resume(struct phy_device *phydev) .resume = dp83822_resume, \ } -#define DP83826_PHY_DRIVER(_id, _name) \ +#define DP83825_PHY_DRIVER(_id, _name) \ { \ PHY_ID_MATCH_MODEL(_id), \ .name = (_name), \ /* PHY_BASIC_FEATURES */ \ - .probe = dp83826_probe, \ + .probe = dp8382x_probe, \ .soft_reset = dp83822_phy_reset, \ - .config_init = dp83826_config_init, \ + .config_init = dp83825_config_init, \ .get_wol = dp83822_get_wol, \ .set_wol = dp83822_set_wol, \ .config_intr = dp83822_config_intr, \ @@ -798,14 +803,14 @@ static int dp83822_resume(struct phy_device *phydev) .resume = dp83822_resume, \ } -#define DP8382X_PHY_DRIVER(_id, _name) \ +#define DP83826_PHY_DRIVER(_id, _name) \ { \ PHY_ID_MATCH_MODEL(_id), \ .name = (_name), \ /* PHY_BASIC_FEATURES */ \ - .probe = dp8382x_probe, \ + .probe = dp83826_probe, \ .soft_reset = dp83822_phy_reset, \ - .config_init = dp8382x_config_init, \ + .config_init = dp83826_config_init, \ .get_wol = dp83822_get_wol, \ .set_wol = dp83822_set_wol, \ .config_intr = dp83822_config_intr, \ @@ -816,12 +821,12 @@ static int dp83822_resume(struct phy_device *phydev) static struct phy_driver dp83822_driver[] = { DP83822_PHY_DRIVER(DP83822_PHY_ID, "TI DP83822"), - DP8382X_PHY_DRIVER(DP83825I_PHY_ID, "TI DP83825I"), + DP83825_PHY_DRIVER(DP83825I_PHY_ID, "TI DP83825I"), + DP83825_PHY_DRIVER(DP83825S_PHY_ID, "TI DP83825S"), + DP83825_PHY_DRIVER(DP83825CM_PHY_ID, "TI DP83825M"), + DP83825_PHY_DRIVER(DP83825CS_PHY_ID, "TI DP83825CS"), DP83826_PHY_DRIVER(DP83826C_PHY_ID, "TI DP83826C"), DP83826_PHY_DRIVER(DP83826NC_PHY_ID, "TI DP83826NC"), - DP8382X_PHY_DRIVER(DP83825S_PHY_ID, "TI DP83825S"), - DP8382X_PHY_DRIVER(DP83825CM_PHY_ID, "TI DP83825M"), - DP8382X_PHY_DRIVER(DP83825CS_PHY_ID, "TI DP83825CS"), }; module_phy_driver(dp83822_driver); diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c index 937061acfc61..351411f0aa6f 100644 --- a/drivers/net/phy/dp83848.c +++ b/drivers/net/phy/dp83848.c @@ -147,6 +147,8 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl); /* IRQ related */ \ .config_intr = dp83848_config_intr, \ .handle_interrupt = dp83848_handle_interrupt, \ + \ + .flags = PHY_RST_AFTER_CLK_EN, \ } static struct phy_driver dp83848_driver[] = { diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c index a00a667454a9..ee438b71a0b4 100644 --- a/drivers/net/phy/icplus.c +++ b/drivers/net/phy/icplus.c @@ -540,8 +540,7 @@ static void ip101g_get_strings(struct phy_device *phydev, u8 *data) int i; for (i = 0; i < ARRAY_SIZE(ip101g_hw_stats); i++) - strscpy(data + i * ETH_GSTRING_LEN, - ip101g_hw_stats[i].name, ETH_GSTRING_LEN); + ethtool_puts(&data, ip101g_hw_stats[i].name); } static u64 ip101g_get_stat(struct phy_device *phydev, int i) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 28aec37acd2c..cd50cd6a7f75 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -2020,10 +2020,8 @@ static void marvell_get_strings(struct phy_device *phydev, u8 *data) int count = marvell_get_sset_count(phydev); int i; - for (i = 0; i < count; i++) { - strscpy(data + i * ETH_GSTRING_LEN, - marvell_hw_stats[i].string, ETH_GSTRING_LEN); - } + for (i = 0; i < count; i++) + ethtool_puts(&data, marvell_hw_stats[i].string); } static void marvell_get_strings_simple(struct phy_device *phydev, u8 *data) @@ -2031,10 +2029,8 @@ static void marvell_get_strings_simple(struct phy_device *phydev, u8 *data) int count = marvell_get_sset_count_simple(phydev); int i; - for (i = 0; i < count; i++) { - strscpy(data + i * ETH_GSTRING_LEN, - marvell_hw_stats_simple[i].string, ETH_GSTRING_LEN); - } + for (i = 0; i < count; i++) + ethtool_puts(&data, marvell_hw_stats_simple[i].string); } static u64 marvell_get_stat(struct phy_device *phydev, int i) diff --git a/drivers/net/phy/mediatek/Kconfig b/drivers/net/phy/mediatek/Kconfig new file mode 100644 index 000000000000..2a8ac5aed0f8 --- /dev/null +++ b/drivers/net/phy/mediatek/Kconfig @@ -0,0 +1,27 @@ +# SPDX-License-Identifier: GPL-2.0-only +config MTK_NET_PHYLIB + tristate + +config MEDIATEK_GE_PHY + tristate "MediaTek Gigabit Ethernet PHYs" + select MTK_NET_PHYLIB + help + Supports the MediaTek non-built-in Gigabit Ethernet PHYs. + + Non-built-in Gigabit Ethernet PHYs include mt7530/mt7531. + You may find mt7530 inside mt7621. This driver shares some + common operations with MediaTek SoC built-in Gigabit + Ethernet PHYs. + +config MEDIATEK_GE_SOC_PHY + tristate "MediaTek SoC Ethernet PHYs" + depends on (ARM64 && ARCH_MEDIATEK) || COMPILE_TEST + depends on NVMEM_MTK_EFUSE + select MTK_NET_PHYLIB + help + Supports MediaTek SoC built-in Gigabit Ethernet PHYs. + + Include support for built-in Ethernet PHYs which are present in + the MT7981 and MT7988 SoCs. These PHYs need calibration data + present in the SoCs efuse and will dynamically calibrate VCM + (common-mode voltage) during startup. diff --git a/drivers/net/phy/mediatek/Makefile b/drivers/net/phy/mediatek/Makefile new file mode 100644 index 000000000000..814879d0abe5 --- /dev/null +++ b/drivers/net/phy/mediatek/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_MTK_NET_PHYLIB) += mtk-phy-lib.o +obj-$(CONFIG_MEDIATEK_GE_PHY) += mtk-ge.o +obj-$(CONFIG_MEDIATEK_GE_SOC_PHY) += mtk-ge-soc.o diff --git a/drivers/net/phy/mediatek-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c index a931832b1418..38dc898eaf7b 100644 --- a/drivers/net/phy/mediatek-ge-soc.c +++ b/drivers/net/phy/mediatek/mtk-ge-soc.c @@ -8,6 +8,8 @@ #include <linux/phy.h> #include <linux/regmap.h> +#include "mtk.h" + #define MTK_GPHY_ID_MT7981 0x03a29461 #define MTK_GPHY_ID_MT7988 0x03a29481 @@ -210,41 +212,6 @@ #define MTK_PHY_DA_TX_R50_PAIR_D 0x540 /* Registers on MDIO_MMD_VEND2 */ -#define MTK_PHY_LED0_ON_CTRL 0x24 -#define MTK_PHY_LED1_ON_CTRL 0x26 -#define MTK_PHY_LED_ON_MASK GENMASK(6, 0) -#define MTK_PHY_LED_ON_LINK1000 BIT(0) -#define MTK_PHY_LED_ON_LINK100 BIT(1) -#define MTK_PHY_LED_ON_LINK10 BIT(2) -#define MTK_PHY_LED_ON_LINK (MTK_PHY_LED_ON_LINK10 |\ - MTK_PHY_LED_ON_LINK100 |\ - MTK_PHY_LED_ON_LINK1000) -#define MTK_PHY_LED_ON_LINKDOWN BIT(3) -#define MTK_PHY_LED_ON_FDX BIT(4) /* Full duplex */ -#define MTK_PHY_LED_ON_HDX BIT(5) /* Half duplex */ -#define MTK_PHY_LED_ON_FORCE_ON BIT(6) -#define MTK_PHY_LED_ON_POLARITY BIT(14) -#define MTK_PHY_LED_ON_ENABLE BIT(15) - -#define MTK_PHY_LED0_BLINK_CTRL 0x25 -#define MTK_PHY_LED1_BLINK_CTRL 0x27 -#define MTK_PHY_LED_BLINK_1000TX BIT(0) -#define MTK_PHY_LED_BLINK_1000RX BIT(1) -#define MTK_PHY_LED_BLINK_100TX BIT(2) -#define MTK_PHY_LED_BLINK_100RX BIT(3) -#define MTK_PHY_LED_BLINK_10TX BIT(4) -#define MTK_PHY_LED_BLINK_10RX BIT(5) -#define MTK_PHY_LED_BLINK_RX (MTK_PHY_LED_BLINK_10RX |\ - MTK_PHY_LED_BLINK_100RX |\ - MTK_PHY_LED_BLINK_1000RX) -#define MTK_PHY_LED_BLINK_TX (MTK_PHY_LED_BLINK_10TX |\ - MTK_PHY_LED_BLINK_100TX |\ - MTK_PHY_LED_BLINK_1000TX) -#define MTK_PHY_LED_BLINK_COLLISION BIT(6) -#define MTK_PHY_LED_BLINK_RX_CRC_ERR BIT(7) -#define MTK_PHY_LED_BLINK_RX_IDLE_ERR BIT(8) -#define MTK_PHY_LED_BLINK_FORCE_BLINK BIT(9) - #define MTK_PHY_LED1_DEFAULT_POLARITIES BIT(1) #define MTK_PHY_RG_BG_RASEL 0x115 @@ -299,29 +266,11 @@ enum CAL_MODE { SW_M }; -#define MTK_PHY_LED_STATE_FORCE_ON 0 -#define MTK_PHY_LED_STATE_FORCE_BLINK 1 -#define MTK_PHY_LED_STATE_NETDEV 2 - -struct mtk_socphy_priv { - unsigned long led_state; -}; - struct mtk_socphy_shared { u32 boottrap; struct mtk_socphy_priv priv[4]; }; -static int mtk_socphy_read_page(struct phy_device *phydev) -{ - return __phy_read(phydev, MTK_EXT_PAGE_ACCESS); -} - -static int mtk_socphy_write_page(struct phy_device *phydev, int page) -{ - return __phy_write(phydev, MTK_EXT_PAGE_ACCESS, page); -} - /* One calibration cycle consists of: * 1.Set DA_CALIN_FLAG high to start calibration. Keep it high * until AD_CAL_COMP is ready to output calibration result. @@ -1172,76 +1121,23 @@ static int mt798x_phy_config_init(struct phy_device *phydev) return mt798x_phy_calibration(phydev); } -static int mt798x_phy_hw_led_on_set(struct phy_device *phydev, u8 index, - bool on) -{ - unsigned int bit_on = MTK_PHY_LED_STATE_FORCE_ON + (index ? 16 : 0); - struct mtk_socphy_priv *priv = phydev->priv; - bool changed; - - if (on) - changed = !test_and_set_bit(bit_on, &priv->led_state); - else - changed = !!test_and_clear_bit(bit_on, &priv->led_state); - - changed |= !!test_and_clear_bit(MTK_PHY_LED_STATE_NETDEV + - (index ? 16 : 0), &priv->led_state); - if (changed) - return phy_modify_mmd(phydev, MDIO_MMD_VEND2, index ? - MTK_PHY_LED1_ON_CTRL : - MTK_PHY_LED0_ON_CTRL, - MTK_PHY_LED_ON_MASK, - on ? MTK_PHY_LED_ON_FORCE_ON : 0); - else - return 0; -} - -static int mt798x_phy_hw_led_blink_set(struct phy_device *phydev, u8 index, - bool blinking) -{ - unsigned int bit_blink = MTK_PHY_LED_STATE_FORCE_BLINK + - (index ? 16 : 0); - struct mtk_socphy_priv *priv = phydev->priv; - bool changed; - - if (blinking) - changed = !test_and_set_bit(bit_blink, &priv->led_state); - else - changed = !!test_and_clear_bit(bit_blink, &priv->led_state); - - changed |= !!test_bit(MTK_PHY_LED_STATE_NETDEV + - (index ? 16 : 0), &priv->led_state); - if (changed) - return phy_write_mmd(phydev, MDIO_MMD_VEND2, index ? - MTK_PHY_LED1_BLINK_CTRL : - MTK_PHY_LED0_BLINK_CTRL, - blinking ? - MTK_PHY_LED_BLINK_FORCE_BLINK : 0); - else - return 0; -} - static int mt798x_phy_led_blink_set(struct phy_device *phydev, u8 index, unsigned long *delay_on, unsigned long *delay_off) { bool blinking = false; - int err = 0; - - if (index > 1) - return -EINVAL; + int err; - if (delay_on && delay_off && (*delay_on > 0) && (*delay_off > 0)) { - blinking = true; - *delay_on = 50; - *delay_off = 50; - } + err = mtk_phy_led_num_dly_cfg(index, delay_on, delay_off, &blinking); + if (err < 0) + return err; - err = mt798x_phy_hw_led_blink_set(phydev, index, blinking); + err = mtk_phy_hw_led_blink_set(phydev, index, blinking); if (err) return err; - return mt798x_phy_hw_led_on_set(phydev, index, false); + return mtk_phy_hw_led_on_set(phydev, index, MTK_GPHY_LED_ON_MASK, + false); } static int mt798x_phy_led_brightness_set(struct phy_device *phydev, @@ -1249,11 +1145,12 @@ static int mt798x_phy_led_brightness_set(struct phy_device *phydev, { int err; - err = mt798x_phy_hw_led_blink_set(phydev, index, false); + err = mtk_phy_hw_led_blink_set(phydev, index, false); if (err) return err; - return mt798x_phy_hw_led_on_set(phydev, index, (value != LED_OFF)); + return mtk_phy_hw_led_on_set(phydev, index, MTK_GPHY_LED_ON_MASK, + (value != LED_OFF)); } static const unsigned long supported_triggers = @@ -1269,155 +1166,26 @@ static const unsigned long supported_triggers = static int mt798x_phy_led_hw_is_supported(struct phy_device *phydev, u8 index, unsigned long rules) { - if (index > 1) - return -EINVAL; - - /* All combinations of the supported triggers are allowed */ - if (rules & ~supported_triggers) - return -EOPNOTSUPP; - - return 0; -}; + return mtk_phy_led_hw_is_supported(phydev, index, rules, + supported_triggers); +} static int mt798x_phy_led_hw_control_get(struct phy_device *phydev, u8 index, unsigned long *rules) { - unsigned int bit_blink = MTK_PHY_LED_STATE_FORCE_BLINK + - (index ? 16 : 0); - unsigned int bit_netdev = MTK_PHY_LED_STATE_NETDEV + (index ? 16 : 0); - unsigned int bit_on = MTK_PHY_LED_STATE_FORCE_ON + (index ? 16 : 0); - struct mtk_socphy_priv *priv = phydev->priv; - int on, blink; - - if (index > 1) - return -EINVAL; - - on = phy_read_mmd(phydev, MDIO_MMD_VEND2, - index ? MTK_PHY_LED1_ON_CTRL : MTK_PHY_LED0_ON_CTRL); - - if (on < 0) - return -EIO; - - blink = phy_read_mmd(phydev, MDIO_MMD_VEND2, - index ? MTK_PHY_LED1_BLINK_CTRL : - MTK_PHY_LED0_BLINK_CTRL); - if (blink < 0) - return -EIO; - - if ((on & (MTK_PHY_LED_ON_LINK | MTK_PHY_LED_ON_FDX | - MTK_PHY_LED_ON_HDX | MTK_PHY_LED_ON_LINKDOWN)) || - (blink & (MTK_PHY_LED_BLINK_RX | MTK_PHY_LED_BLINK_TX))) - set_bit(bit_netdev, &priv->led_state); - else - clear_bit(bit_netdev, &priv->led_state); - - if (on & MTK_PHY_LED_ON_FORCE_ON) - set_bit(bit_on, &priv->led_state); - else - clear_bit(bit_on, &priv->led_state); - - if (blink & MTK_PHY_LED_BLINK_FORCE_BLINK) - set_bit(bit_blink, &priv->led_state); - else - clear_bit(bit_blink, &priv->led_state); - - if (!rules) - return 0; - - if (on & MTK_PHY_LED_ON_LINK) - *rules |= BIT(TRIGGER_NETDEV_LINK); - - if (on & MTK_PHY_LED_ON_LINK10) - *rules |= BIT(TRIGGER_NETDEV_LINK_10); - - if (on & MTK_PHY_LED_ON_LINK100) - *rules |= BIT(TRIGGER_NETDEV_LINK_100); - - if (on & MTK_PHY_LED_ON_LINK1000) - *rules |= BIT(TRIGGER_NETDEV_LINK_1000); - - if (on & MTK_PHY_LED_ON_FDX) - *rules |= BIT(TRIGGER_NETDEV_FULL_DUPLEX); - - if (on & MTK_PHY_LED_ON_HDX) - *rules |= BIT(TRIGGER_NETDEV_HALF_DUPLEX); - - if (blink & MTK_PHY_LED_BLINK_RX) - *rules |= BIT(TRIGGER_NETDEV_RX); - - if (blink & MTK_PHY_LED_BLINK_TX) - *rules |= BIT(TRIGGER_NETDEV_TX); - - return 0; + return mtk_phy_led_hw_ctrl_get(phydev, index, rules, + MTK_GPHY_LED_ON_SET, + MTK_GPHY_LED_RX_BLINK_SET, + MTK_GPHY_LED_TX_BLINK_SET); }; static int mt798x_phy_led_hw_control_set(struct phy_device *phydev, u8 index, unsigned long rules) { - unsigned int bit_netdev = MTK_PHY_LED_STATE_NETDEV + (index ? 16 : 0); - struct mtk_socphy_priv *priv = phydev->priv; - u16 on = 0, blink = 0; - int ret; - - if (index > 1) - return -EINVAL; - - if (rules & BIT(TRIGGER_NETDEV_FULL_DUPLEX)) - on |= MTK_PHY_LED_ON_FDX; - - if (rules & BIT(TRIGGER_NETDEV_HALF_DUPLEX)) - on |= MTK_PHY_LED_ON_HDX; - - if (rules & (BIT(TRIGGER_NETDEV_LINK_10) | BIT(TRIGGER_NETDEV_LINK))) - on |= MTK_PHY_LED_ON_LINK10; - - if (rules & (BIT(TRIGGER_NETDEV_LINK_100) | BIT(TRIGGER_NETDEV_LINK))) - on |= MTK_PHY_LED_ON_LINK100; - - if (rules & (BIT(TRIGGER_NETDEV_LINK_1000) | BIT(TRIGGER_NETDEV_LINK))) - on |= MTK_PHY_LED_ON_LINK1000; - - if (rules & BIT(TRIGGER_NETDEV_RX)) { - blink |= (on & MTK_PHY_LED_ON_LINK) ? - (((on & MTK_PHY_LED_ON_LINK10) ? - MTK_PHY_LED_BLINK_10RX : 0) | - ((on & MTK_PHY_LED_ON_LINK100) ? - MTK_PHY_LED_BLINK_100RX : 0) | - ((on & MTK_PHY_LED_ON_LINK1000) ? - MTK_PHY_LED_BLINK_1000RX : 0)) : - MTK_PHY_LED_BLINK_RX; - } - - if (rules & BIT(TRIGGER_NETDEV_TX)) { - blink |= (on & MTK_PHY_LED_ON_LINK) ? - (((on & MTK_PHY_LED_ON_LINK10) ? - MTK_PHY_LED_BLINK_10TX : 0) | - ((on & MTK_PHY_LED_ON_LINK100) ? - MTK_PHY_LED_BLINK_100TX : 0) | - ((on & MTK_PHY_LED_ON_LINK1000) ? - MTK_PHY_LED_BLINK_1000TX : 0)) : - MTK_PHY_LED_BLINK_TX; - } - - if (blink || on) - set_bit(bit_netdev, &priv->led_state); - else - clear_bit(bit_netdev, &priv->led_state); - - ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, index ? - MTK_PHY_LED1_ON_CTRL : - MTK_PHY_LED0_ON_CTRL, - MTK_PHY_LED_ON_FDX | - MTK_PHY_LED_ON_HDX | - MTK_PHY_LED_ON_LINK, - on); - - if (ret) - return ret; - - return phy_write_mmd(phydev, MDIO_MMD_VEND2, index ? - MTK_PHY_LED1_BLINK_CTRL : - MTK_PHY_LED0_BLINK_CTRL, blink); + return mtk_phy_led_hw_ctrl_set(phydev, index, rules, + MTK_GPHY_LED_ON_SET, + MTK_GPHY_LED_RX_BLINK_SET, + MTK_GPHY_LED_TX_BLINK_SET); }; static bool mt7988_phy_led_get_polarity(struct phy_device *phydev, int led_num) @@ -1492,14 +1260,6 @@ static int mt7988_phy_probe_shared(struct phy_device *phydev) return 0; } -static void mt798x_phy_leds_state_init(struct phy_device *phydev) -{ - int i; - - for (i = 0; i < 2; ++i) - mt798x_phy_led_hw_control_get(phydev, i, NULL); -} - static int mt7988_phy_probe(struct phy_device *phydev) { struct mtk_socphy_shared *shared; @@ -1525,7 +1285,7 @@ static int mt7988_phy_probe(struct phy_device *phydev) phydev->priv = priv; - mt798x_phy_leds_state_init(phydev); + mtk_phy_leds_state_init(phydev); err = mt7988_phy_fix_leds_polarities(phydev); if (err) @@ -1552,7 +1312,7 @@ static int mt7981_phy_probe(struct phy_device *phydev) phydev->priv = priv; - mt798x_phy_leds_state_init(phydev); + mtk_phy_leds_state_init(phydev); return mt798x_phy_calibration(phydev); } @@ -1567,8 +1327,8 @@ static struct phy_driver mtk_socphy_driver[] = { .probe = mt7981_phy_probe, .suspend = genphy_suspend, .resume = genphy_resume, - .read_page = mtk_socphy_read_page, - .write_page = mtk_socphy_write_page, + .read_page = mtk_phy_read_page, + .write_page = mtk_phy_write_page, .led_blink_set = mt798x_phy_led_blink_set, .led_brightness_set = mt798x_phy_led_brightness_set, .led_hw_is_supported = mt798x_phy_led_hw_is_supported, @@ -1584,8 +1344,8 @@ static struct phy_driver mtk_socphy_driver[] = { .probe = mt7988_phy_probe, .suspend = genphy_suspend, .resume = genphy_resume, - .read_page = mtk_socphy_read_page, - .write_page = mtk_socphy_write_page, + .read_page = mtk_phy_read_page, + .write_page = mtk_phy_write_page, .led_blink_set = mt798x_phy_led_blink_set, .led_brightness_set = mt798x_phy_led_brightness_set, .led_hw_is_supported = mt798x_phy_led_hw_is_supported, diff --git a/drivers/net/phy/mediatek-ge.c b/drivers/net/phy/mediatek/mtk-ge.c index 54ea64a37ab3..ed2617bc20f4 100644 --- a/drivers/net/phy/mediatek-ge.c +++ b/drivers/net/phy/mediatek/mtk-ge.c @@ -3,6 +3,11 @@ #include <linux/module.h> #include <linux/phy.h> +#include "mtk.h" + +#define MTK_GPHY_ID_MT7530 0x03a29412 +#define MTK_GPHY_ID_MT7531 0x03a29441 + #define MTK_EXT_PAGE_ACCESS 0x1f #define MTK_PHY_PAGE_STANDARD 0x0000 #define MTK_PHY_PAGE_EXTENDED 0x0001 @@ -11,16 +16,6 @@ #define MTK_PHY_PAGE_EXTENDED_2A30 0x2a30 #define MTK_PHY_PAGE_EXTENDED_52B5 0x52b5 -static int mtk_gephy_read_page(struct phy_device *phydev) -{ - return __phy_read(phydev, MTK_EXT_PAGE_ACCESS); -} - -static int mtk_gephy_write_page(struct phy_device *phydev, int page) -{ - return __phy_write(phydev, MTK_EXT_PAGE_ACCESS, page); -} - static void mtk_gephy_config_init(struct phy_device *phydev) { /* Enable HW auto downshift */ @@ -67,7 +62,7 @@ static int mt7531_phy_config_init(struct phy_device *phydev) static struct phy_driver mtk_gephy_driver[] = { { - PHY_ID_MATCH_EXACT(0x03a29412), + PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7530), .name = "MediaTek MT7530 PHY", .config_init = mt7530_phy_config_init, /* Interrupts are handled by the switch, not the PHY @@ -77,11 +72,11 @@ static struct phy_driver mtk_gephy_driver[] = { .handle_interrupt = genphy_handle_interrupt_no_ack, .suspend = genphy_suspend, .resume = genphy_resume, - .read_page = mtk_gephy_read_page, - .write_page = mtk_gephy_write_page, + .read_page = mtk_phy_read_page, + .write_page = mtk_phy_write_page, }, { - PHY_ID_MATCH_EXACT(0x03a29441), + PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7531), .name = "MediaTek MT7531 PHY", .config_init = mt7531_phy_config_init, /* Interrupts are handled by the switch, not the PHY @@ -91,16 +86,16 @@ static struct phy_driver mtk_gephy_driver[] = { .handle_interrupt = genphy_handle_interrupt_no_ack, .suspend = genphy_suspend, .resume = genphy_resume, - .read_page = mtk_gephy_read_page, - .write_page = mtk_gephy_write_page, + .read_page = mtk_phy_read_page, + .write_page = mtk_phy_write_page, }, }; module_phy_driver(mtk_gephy_driver); static struct mdio_device_id __maybe_unused mtk_gephy_tbl[] = { - { PHY_ID_MATCH_EXACT(0x03a29441) }, - { PHY_ID_MATCH_EXACT(0x03a29412) }, + { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7530) }, + { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7531) }, { } }; diff --git a/drivers/net/phy/mediatek/mtk-phy-lib.c b/drivers/net/phy/mediatek/mtk-phy-lib.c new file mode 100644 index 000000000000..98a09d670e9c --- /dev/null +++ b/drivers/net/phy/mediatek/mtk-phy-lib.c @@ -0,0 +1,270 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/phy.h> +#include <linux/module.h> + +#include <linux/netdevice.h> + +#include "mtk.h" + +int mtk_phy_read_page(struct phy_device *phydev) +{ + return __phy_read(phydev, MTK_EXT_PAGE_ACCESS); +} +EXPORT_SYMBOL_GPL(mtk_phy_read_page); + +int mtk_phy_write_page(struct phy_device *phydev, int page) +{ + return __phy_write(phydev, MTK_EXT_PAGE_ACCESS, page); +} +EXPORT_SYMBOL_GPL(mtk_phy_write_page); + +int mtk_phy_led_hw_is_supported(struct phy_device *phydev, u8 index, + unsigned long rules, + unsigned long supported_triggers) +{ + if (index > 1) + return -EINVAL; + + /* All combinations of the supported triggers are allowed */ + if (rules & ~supported_triggers) + return -EOPNOTSUPP; + + return 0; +} +EXPORT_SYMBOL_GPL(mtk_phy_led_hw_is_supported); + +int mtk_phy_led_hw_ctrl_get(struct phy_device *phydev, u8 index, + unsigned long *rules, u16 on_set, + u16 rx_blink_set, u16 tx_blink_set) +{ + unsigned int bit_blink = MTK_PHY_LED_STATE_FORCE_BLINK + + (index ? 16 : 0); + unsigned int bit_netdev = MTK_PHY_LED_STATE_NETDEV + (index ? 16 : 0); + unsigned int bit_on = MTK_PHY_LED_STATE_FORCE_ON + (index ? 16 : 0); + struct mtk_socphy_priv *priv = phydev->priv; + int on, blink; + + if (index > 1) + return -EINVAL; + + on = phy_read_mmd(phydev, MDIO_MMD_VEND2, + index ? MTK_PHY_LED1_ON_CTRL : MTK_PHY_LED0_ON_CTRL); + + if (on < 0) + return -EIO; + + blink = phy_read_mmd(phydev, MDIO_MMD_VEND2, + index ? MTK_PHY_LED1_BLINK_CTRL : + MTK_PHY_LED0_BLINK_CTRL); + if (blink < 0) + return -EIO; + + if ((on & (on_set | MTK_PHY_LED_ON_FDX | + MTK_PHY_LED_ON_HDX | MTK_PHY_LED_ON_LINKDOWN)) || + (blink & (rx_blink_set | tx_blink_set))) + set_bit(bit_netdev, &priv->led_state); + else + clear_bit(bit_netdev, &priv->led_state); + + if (on & MTK_PHY_LED_ON_FORCE_ON) + set_bit(bit_on, &priv->led_state); + else + clear_bit(bit_on, &priv->led_state); + + if (blink & MTK_PHY_LED_BLINK_FORCE_BLINK) + set_bit(bit_blink, &priv->led_state); + else + clear_bit(bit_blink, &priv->led_state); + + if (!rules) + return 0; + + if (on & on_set) + *rules |= BIT(TRIGGER_NETDEV_LINK); + + if (on & MTK_PHY_LED_ON_LINK10) + *rules |= BIT(TRIGGER_NETDEV_LINK_10); + + if (on & MTK_PHY_LED_ON_LINK100) + *rules |= BIT(TRIGGER_NETDEV_LINK_100); + + if (on & MTK_PHY_LED_ON_LINK1000) + *rules |= BIT(TRIGGER_NETDEV_LINK_1000); + + if (on & MTK_PHY_LED_ON_LINK2500) + *rules |= BIT(TRIGGER_NETDEV_LINK_2500); + + if (on & MTK_PHY_LED_ON_FDX) + *rules |= BIT(TRIGGER_NETDEV_FULL_DUPLEX); + + if (on & MTK_PHY_LED_ON_HDX) + *rules |= BIT(TRIGGER_NETDEV_HALF_DUPLEX); + + if (blink & rx_blink_set) + *rules |= BIT(TRIGGER_NETDEV_RX); + + if (blink & tx_blink_set) + *rules |= BIT(TRIGGER_NETDEV_TX); + + return 0; +} +EXPORT_SYMBOL_GPL(mtk_phy_led_hw_ctrl_get); + +int mtk_phy_led_hw_ctrl_set(struct phy_device *phydev, u8 index, + unsigned long rules, u16 on_set, + u16 rx_blink_set, u16 tx_blink_set) +{ + unsigned int bit_netdev = MTK_PHY_LED_STATE_NETDEV + (index ? 16 : 0); + struct mtk_socphy_priv *priv = phydev->priv; + u16 on = 0, blink = 0; + int ret; + + if (index > 1) + return -EINVAL; + + if (rules & BIT(TRIGGER_NETDEV_FULL_DUPLEX)) + on |= MTK_PHY_LED_ON_FDX; + + if (rules & BIT(TRIGGER_NETDEV_HALF_DUPLEX)) + on |= MTK_PHY_LED_ON_HDX; + + if (rules & (BIT(TRIGGER_NETDEV_LINK_10) | BIT(TRIGGER_NETDEV_LINK))) + on |= MTK_PHY_LED_ON_LINK10; + + if (rules & (BIT(TRIGGER_NETDEV_LINK_100) | BIT(TRIGGER_NETDEV_LINK))) + on |= MTK_PHY_LED_ON_LINK100; + + if (rules & (BIT(TRIGGER_NETDEV_LINK_1000) | BIT(TRIGGER_NETDEV_LINK))) + on |= MTK_PHY_LED_ON_LINK1000; + + if (rules & (BIT(TRIGGER_NETDEV_LINK_2500) | BIT(TRIGGER_NETDEV_LINK))) + on |= MTK_PHY_LED_ON_LINK2500; + + if (rules & BIT(TRIGGER_NETDEV_RX)) { + if (on & on_set) { + if (on & MTK_PHY_LED_ON_LINK10) + blink |= MTK_PHY_LED_BLINK_10RX; + if (on & MTK_PHY_LED_ON_LINK100) + blink |= MTK_PHY_LED_BLINK_100RX; + if (on & MTK_PHY_LED_ON_LINK1000) + blink |= MTK_PHY_LED_BLINK_1000RX; + if (on & MTK_PHY_LED_ON_LINK2500) + blink |= MTK_PHY_LED_BLINK_2500RX; + } else { + blink |= rx_blink_set; + } + } + + if (rules & BIT(TRIGGER_NETDEV_TX)) { + if (on & on_set) { + if (on & MTK_PHY_LED_ON_LINK10) + blink |= MTK_PHY_LED_BLINK_10TX; + if (on & MTK_PHY_LED_ON_LINK100) + blink |= MTK_PHY_LED_BLINK_100TX; + if (on & MTK_PHY_LED_ON_LINK1000) + blink |= MTK_PHY_LED_BLINK_1000TX; + if (on & MTK_PHY_LED_ON_LINK2500) + blink |= MTK_PHY_LED_BLINK_2500TX; + } else { + blink |= tx_blink_set; + } + } + + if (blink || on) + set_bit(bit_netdev, &priv->led_state); + else + clear_bit(bit_netdev, &priv->led_state); + + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, index ? + MTK_PHY_LED1_ON_CTRL : MTK_PHY_LED0_ON_CTRL, + MTK_PHY_LED_ON_FDX | MTK_PHY_LED_ON_HDX | on_set, + on); + + if (ret) + return ret; + + return phy_write_mmd(phydev, MDIO_MMD_VEND2, index ? + MTK_PHY_LED1_BLINK_CTRL : + MTK_PHY_LED0_BLINK_CTRL, blink); +} +EXPORT_SYMBOL_GPL(mtk_phy_led_hw_ctrl_set); + +int mtk_phy_led_num_dly_cfg(u8 index, unsigned long *delay_on, + unsigned long *delay_off, bool *blinking) +{ + if (index > 1) + return -EINVAL; + + if (delay_on && delay_off && (*delay_on > 0) && (*delay_off > 0)) { + *blinking = true; + *delay_on = 50; + *delay_off = 50; + } + + return 0; +} +EXPORT_SYMBOL_GPL(mtk_phy_led_num_dly_cfg); + +int mtk_phy_hw_led_on_set(struct phy_device *phydev, u8 index, + u16 led_on_mask, bool on) +{ + unsigned int bit_on = MTK_PHY_LED_STATE_FORCE_ON + (index ? 16 : 0); + struct mtk_socphy_priv *priv = phydev->priv; + bool changed; + + if (on) + changed = !test_and_set_bit(bit_on, &priv->led_state); + else + changed = !!test_and_clear_bit(bit_on, &priv->led_state); + + changed |= !!test_and_clear_bit(MTK_PHY_LED_STATE_NETDEV + + (index ? 16 : 0), &priv->led_state); + if (changed) + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, index ? + MTK_PHY_LED1_ON_CTRL : + MTK_PHY_LED0_ON_CTRL, + led_on_mask, + on ? MTK_PHY_LED_ON_FORCE_ON : 0); + else + return 0; +} +EXPORT_SYMBOL_GPL(mtk_phy_hw_led_on_set); + +int mtk_phy_hw_led_blink_set(struct phy_device *phydev, u8 index, bool blinking) +{ + unsigned int bit_blink = MTK_PHY_LED_STATE_FORCE_BLINK + + (index ? 16 : 0); + struct mtk_socphy_priv *priv = phydev->priv; + bool changed; + + if (blinking) + changed = !test_and_set_bit(bit_blink, &priv->led_state); + else + changed = !!test_and_clear_bit(bit_blink, &priv->led_state); + + changed |= !!test_bit(MTK_PHY_LED_STATE_NETDEV + + (index ? 16 : 0), &priv->led_state); + if (changed) + return phy_write_mmd(phydev, MDIO_MMD_VEND2, index ? + MTK_PHY_LED1_BLINK_CTRL : + MTK_PHY_LED0_BLINK_CTRL, + blinking ? + MTK_PHY_LED_BLINK_FORCE_BLINK : 0); + else + return 0; +} +EXPORT_SYMBOL_GPL(mtk_phy_hw_led_blink_set); + +void mtk_phy_leds_state_init(struct phy_device *phydev) +{ + int i; + + for (i = 0; i < 2; ++i) + phydev->drv->led_hw_control_get(phydev, i, NULL); +} +EXPORT_SYMBOL_GPL(mtk_phy_leds_state_init); + +MODULE_DESCRIPTION("MediaTek Ethernet PHY driver common"); +MODULE_AUTHOR("Sky Huang <[email protected]>"); +MODULE_AUTHOR("Daniel Golle <[email protected]>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/mediatek/mtk.h b/drivers/net/phy/mediatek/mtk.h new file mode 100644 index 000000000000..63d9fe179b8f --- /dev/null +++ b/drivers/net/phy/mediatek/mtk.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Common definition for Mediatek Ethernet PHYs + * Author: SkyLake Huang <[email protected]> + * Copyright (c) 2024 MediaTek Inc. + */ + +#ifndef _MTK_EPHY_H_ +#define _MTK_EPHY_H_ + +#define MTK_EXT_PAGE_ACCESS 0x1f + +/* Registers on MDIO_MMD_VEND2 */ +#define MTK_PHY_LED0_ON_CTRL 0x24 +#define MTK_PHY_LED1_ON_CTRL 0x26 +#define MTK_GPHY_LED_ON_MASK GENMASK(6, 0) +#define MTK_2P5GPHY_LED_ON_MASK GENMASK(7, 0) +#define MTK_PHY_LED_ON_LINK1000 BIT(0) +#define MTK_PHY_LED_ON_LINK100 BIT(1) +#define MTK_PHY_LED_ON_LINK10 BIT(2) +#define MTK_PHY_LED_ON_LINKDOWN BIT(3) +#define MTK_PHY_LED_ON_FDX BIT(4) /* Full duplex */ +#define MTK_PHY_LED_ON_HDX BIT(5) /* Half duplex */ +#define MTK_PHY_LED_ON_FORCE_ON BIT(6) +#define MTK_PHY_LED_ON_LINK2500 BIT(7) +#define MTK_PHY_LED_ON_POLARITY BIT(14) +#define MTK_PHY_LED_ON_ENABLE BIT(15) + +#define MTK_PHY_LED0_BLINK_CTRL 0x25 +#define MTK_PHY_LED1_BLINK_CTRL 0x27 +#define MTK_PHY_LED_BLINK_1000TX BIT(0) +#define MTK_PHY_LED_BLINK_1000RX BIT(1) +#define MTK_PHY_LED_BLINK_100TX BIT(2) +#define MTK_PHY_LED_BLINK_100RX BIT(3) +#define MTK_PHY_LED_BLINK_10TX BIT(4) +#define MTK_PHY_LED_BLINK_10RX BIT(5) +#define MTK_PHY_LED_BLINK_COLLISION BIT(6) +#define MTK_PHY_LED_BLINK_RX_CRC_ERR BIT(7) +#define MTK_PHY_LED_BLINK_RX_IDLE_ERR BIT(8) +#define MTK_PHY_LED_BLINK_FORCE_BLINK BIT(9) +#define MTK_PHY_LED_BLINK_2500TX BIT(10) +#define MTK_PHY_LED_BLINK_2500RX BIT(11) + +#define MTK_GPHY_LED_ON_SET (MTK_PHY_LED_ON_LINK1000 | \ + MTK_PHY_LED_ON_LINK100 | \ + MTK_PHY_LED_ON_LINK10) +#define MTK_GPHY_LED_RX_BLINK_SET (MTK_PHY_LED_BLINK_1000RX | \ + MTK_PHY_LED_BLINK_100RX | \ + MTK_PHY_LED_BLINK_10RX) +#define MTK_GPHY_LED_TX_BLINK_SET (MTK_PHY_LED_BLINK_1000RX | \ + MTK_PHY_LED_BLINK_100RX | \ + MTK_PHY_LED_BLINK_10RX) + +#define MTK_2P5GPHY_LED_ON_SET (MTK_PHY_LED_ON_LINK2500 | \ + MTK_GPHY_LED_ON_SET) +#define MTK_2P5GPHY_LED_RX_BLINK_SET (MTK_PHY_LED_BLINK_2500RX | \ + MTK_GPHY_LED_RX_BLINK_SET) +#define MTK_2P5GPHY_LED_TX_BLINK_SET (MTK_PHY_LED_BLINK_2500RX | \ + MTK_GPHY_LED_TX_BLINK_SET) + +#define MTK_PHY_LED_STATE_FORCE_ON 0 +#define MTK_PHY_LED_STATE_FORCE_BLINK 1 +#define MTK_PHY_LED_STATE_NETDEV 2 + +struct mtk_socphy_priv { + unsigned long led_state; +}; + +int mtk_phy_read_page(struct phy_device *phydev); +int mtk_phy_write_page(struct phy_device *phydev, int page); + +int mtk_phy_led_hw_is_supported(struct phy_device *phydev, u8 index, + unsigned long rules, + unsigned long supported_triggers); +int mtk_phy_led_hw_ctrl_set(struct phy_device *phydev, u8 index, + unsigned long rules, u16 on_set, + u16 rx_blink_set, u16 tx_blink_set); +int mtk_phy_led_hw_ctrl_get(struct phy_device *phydev, u8 index, + unsigned long *rules, u16 on_set, + u16 rx_blink_set, u16 tx_blink_set); +int mtk_phy_led_num_dly_cfg(u8 index, unsigned long *delay_on, + unsigned long *delay_off, bool *blinking); +int mtk_phy_hw_led_on_set(struct phy_device *phydev, u8 index, + u16 led_on_mask, bool on); +int mtk_phy_hw_led_blink_set(struct phy_device *phydev, u8 index, + bool blinking); +void mtk_phy_leds_state_init(struct phy_device *phydev); + +#endif /* _MTK_EPHY_H_ */ diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 65b0a3115e14..43c82a87bc3a 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2018,10 +2018,8 @@ static void kszphy_get_strings(struct phy_device *phydev, u8 *data) { int i; - for (i = 0; i < ARRAY_SIZE(kszphy_hw_stats); i++) { - strscpy(data + i * ETH_GSTRING_LEN, - kszphy_hw_stats[i].string, ETH_GSTRING_LEN); - } + for (i = 0; i < ARRAY_SIZE(kszphy_hw_stats); i++) + ethtool_puts(&data, kszphy_hw_stats[i].string); } static u64 kszphy_get_stat(struct phy_device *phydev, int i) diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index 6f74ce0ab1aa..bee381200ab8 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -139,8 +139,7 @@ static void vsc85xx_get_strings(struct phy_device *phydev, u8 *data) return; for (i = 0; i < priv->nstats; i++) - strscpy(data + i * ETH_GSTRING_LEN, priv->hw_stats[i].string, - ETH_GSTRING_LEN); + ethtool_puts(&data, priv->hw_stats[i].string); } static u64 vsc85xx_get_stat(struct phy_device *phydev, int i) diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 7e328c2a29a4..ade544bc007d 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -1140,13 +1140,11 @@ static void nxp_c45_get_strings(struct phy_device *phydev, u8 *data) for (i = 0; i < count; i++) { if (i < ARRAY_SIZE(common_hw_stats)) { - strscpy(data + i * ETH_GSTRING_LEN, - common_hw_stats[i].name, ETH_GSTRING_LEN); + ethtool_puts(&data, common_hw_stats[i].name); continue; } idx = i - ARRAY_SIZE(common_hw_stats); - strscpy(data + i * ETH_GSTRING_LEN, - phy_data->stats[idx].name, ETH_GSTRING_LEN); + ethtool_puts(&data, phy_data->stats[idx].name); } } diff --git a/drivers/net/phy/nxp-cbtx.c b/drivers/net/phy/nxp-cbtx.c index 145703f0a406..3d25491043a3 100644 --- a/drivers/net/phy/nxp-cbtx.c +++ b/drivers/net/phy/nxp-cbtx.c @@ -182,7 +182,7 @@ static int cbtx_get_sset_count(struct phy_device *phydev) static void cbtx_get_strings(struct phy_device *phydev, u8 *data) { - strncpy(data, "100btx_rx_err", ETH_GSTRING_LEN); + ethtool_puts(&data, "100btx_rx_err"); } static void cbtx_get_stats(struct phy_device *phydev, diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 5695935fdce9..c1b3576c307f 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -680,7 +680,8 @@ EXPORT_SYMBOL_GPL(genphy_c45_read_mdix); * @phydev: target phy_device struct * @adv: the linkmode advertisement settings */ -int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv) +static int genphy_c45_write_eee_adv(struct phy_device *phydev, + unsigned long *adv) { int val, changed = 0; @@ -950,6 +951,7 @@ int genphy_c45_an_config_eee_aneg(struct phy_device *phydev) return genphy_c45_write_eee_adv(phydev, phydev->advertising_eee); } +EXPORT_SYMBOL_GPL(genphy_c45_an_config_eee_aneg); /** * genphy_c45_pma_baset1_read_abilities - read supported baset1 link modes from PMA @@ -1568,11 +1570,10 @@ int genphy_c45_ethtool_set_eee(struct phy_device *phydev, phydev_warn(phydev, "At least some EEE link modes are not supported.\n"); return -EINVAL; } - } else { - adv = phydev->supported_eee; + linkmode_copy(phydev->advertising_eee, adv); + } else if (linkmode_empty(phydev->advertising_eee)) { + phy_advertise_eee_all(phydev); } - - linkmode_copy(phydev->advertising_eee, adv); } phydev->eee_enabled = data->eee_enabled; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 563497a3274c..bc24c9f2786b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2240,29 +2240,6 @@ static int genphy_c37_config_advert(struct phy_device *phydev) } /** - * genphy_config_eee_advert - disable unwanted eee mode advertisement - * @phydev: target phy_device struct - * - * Description: Writes MDIO_AN_EEE_ADV after disabling unsupported energy - * efficent ethernet modes. Returns 0 if the PHY's advertisement hasn't - * changed, and 1 if it has changed. - */ -int genphy_config_eee_advert(struct phy_device *phydev) -{ - int err; - - /* Nothing to disable */ - if (!phydev->eee_broken_modes) - return 0; - - err = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, - phydev->eee_broken_modes, 0); - /* If the call failed, we assume that EEE is not supported */ - return err < 0 ? 0 : err; -} -EXPORT_SYMBOL(genphy_config_eee_advert); - -/** * genphy_setup_forced - configures/forces speed/duplex from @phydev * @phydev: target phy_device struct * diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 6ca7ea970f51..b1e828a4286d 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1463,76 +1463,66 @@ static void phylink_resolve(struct work_struct *w) } else if (pl->mac_link_dropped) { link_state.link = false; retrigger = true; + } else if (pl->cur_link_an_mode == MLO_AN_FIXED) { + phylink_get_fixed_state(pl, &link_state); + mac_config = link_state.link; + } else if (pl->cur_link_an_mode == MLO_AN_PHY) { + link_state = pl->phy_state; + mac_config = link_state.link; } else { - switch (pl->cur_link_an_mode) { - case MLO_AN_PHY: - link_state = pl->phy_state; - phylink_apply_manual_flow(pl, &link_state); - mac_config = link_state.link; - break; + phylink_mac_pcs_get_state(pl, &link_state); - case MLO_AN_FIXED: - phylink_get_fixed_state(pl, &link_state); - mac_config = link_state.link; - break; + /* The PCS may have a latching link-fail indicator. If the link + * was up, bring the link down and re-trigger the resolve. + * Otherwise, re-read the PCS state to get the current status + * of the link. + */ + if (!link_state.link) { + if (cur_link_state) + retrigger = true; + else + phylink_mac_pcs_get_state(pl, &link_state); + } - case MLO_AN_INBAND: - phylink_mac_pcs_get_state(pl, &link_state); + /* If we have a phy, the "up" state is the union of both the + * PHY and the MAC + */ + if (pl->phydev) + link_state.link &= pl->phy_state.link; - /* The PCS may have a latching link-fail indicator. - * If the link was up, bring the link down and - * re-trigger the resolve. Otherwise, re-read the - * PCS state to get the current status of the link. + /* Only update if the PHY link is up */ + if (pl->phydev && pl->phy_state.link) { + /* If the interface has changed, force a link down + * event if the link isn't already down, and re-resolve. */ - if (!link_state.link) { - if (cur_link_state) - retrigger = true; - else - phylink_mac_pcs_get_state(pl, - &link_state); + if (link_state.interface != pl->phy_state.interface) { + retrigger = true; + link_state.link = false; } - /* If we have a phy, the "up" state is the union of - * both the PHY and the MAC + link_state.interface = pl->phy_state.interface; + + /* If we are doing rate matching, then the link + * speed/duplex comes from the PHY */ - if (pl->phydev) - link_state.link &= pl->phy_state.link; - - /* Only update if the PHY link is up */ - if (pl->phydev && pl->phy_state.link) { - /* If the interface has changed, force a - * link down event if the link isn't already - * down, and re-resolve. - */ - if (link_state.interface != - pl->phy_state.interface) { - retrigger = true; - link_state.link = false; - } - link_state.interface = pl->phy_state.interface; - - /* If we are doing rate matching, then the - * link speed/duplex comes from the PHY - */ - if (pl->phy_state.rate_matching) { - link_state.rate_matching = - pl->phy_state.rate_matching; - link_state.speed = pl->phy_state.speed; - link_state.duplex = - pl->phy_state.duplex; - } - - /* If we have a PHY, we need to update with - * the PHY flow control bits. - */ - link_state.pause = pl->phy_state.pause; - mac_config = true; + if (pl->phy_state.rate_matching) { + link_state.rate_matching = + pl->phy_state.rate_matching; + link_state.speed = pl->phy_state.speed; + link_state.duplex = pl->phy_state.duplex; } - phylink_apply_manual_flow(pl, &link_state); - break; + + /* If we have a PHY, we need to update with the PHY + * flow control bits. + */ + link_state.pause = pl->phy_state.pause; + mac_config = true; } } + if (pl->cur_link_an_mode != MLO_AN_FIXED) + phylink_apply_manual_flow(pl, &link_state); + if (mac_config) { if (link_state.interface != pl->link_config.interface) { /* The interface has changed, force the link down and diff --git a/drivers/net/phy/qcom/qca83xx.c b/drivers/net/phy/qcom/qca83xx.c index a05d0df6fa16..7a5039920b9f 100644 --- a/drivers/net/phy/qcom/qca83xx.c +++ b/drivers/net/phy/qcom/qca83xx.c @@ -42,10 +42,8 @@ static void qca83xx_get_strings(struct phy_device *phydev, u8 *data) { int i; - for (i = 0; i < ARRAY_SIZE(qca83xx_hw_stats); i++) { - strscpy(data + i * ETH_GSTRING_LEN, - qca83xx_hw_stats[i].string, ETH_GSTRING_LEN); - } + for (i = 0; i < ARRAY_SIZE(qca83xx_hw_stats); i++) + ethtool_puts(&data, qca83xx_hw_stats[i].string); } static u64 qca83xx_get_stat(struct phy_device *phydev, int i) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index f137c82f1c0f..0c011d8f5d4d 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1076,6 +1076,7 @@ static const struct usb_device_id products[] = { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7), .driver_info = (unsigned long)&qmi_wwan_info, }, + {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0122)}, /* Quectel RG650V */ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0125)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0306)}, /* Quectel EP06/EG06/EM06 */ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0512)}, /* Quectel EG12/EM12 */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index a5612c799f5e..468c73974046 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -10069,6 +10069,7 @@ static const struct usb_device_id rtl8152_table[] = { { USB_DEVICE(VENDOR_ID_LENOVO, 0x3062) }, { USB_DEVICE(VENDOR_ID_LENOVO, 0x3069) }, { USB_DEVICE(VENDOR_ID_LENOVO, 0x3082) }, + { USB_DEVICE(VENDOR_ID_LENOVO, 0x3098) }, { USB_DEVICE(VENDOR_ID_LENOVO, 0x7205) }, { USB_DEVICE(VENDOR_ID_LENOVO, 0x720c) }, { USB_DEVICE(VENDOR_ID_LENOVO, 0x7214) }, diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 18148e068aa0..0d6d0d749d44 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1781,19 +1781,11 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, /* * create and register peer first */ - if (data != NULL && data[VETH_INFO_PEER] != NULL) { - struct nlattr *nla_peer; + if (data && data[VETH_INFO_PEER]) { + struct nlattr *nla_peer = data[VETH_INFO_PEER]; - nla_peer = data[VETH_INFO_PEER]; ifmp = nla_data(nla_peer); - err = rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); - if (err < 0) - return err; - - err = veth_validate(peer_tb, NULL, extack); - if (err < 0) - return err; - + rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); tbp = peer_tb; } else { ifmp = NULL; @@ -1809,9 +1801,6 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, } net = rtnl_link_get_net(src_net, tbp); - if (IS_ERR(net)) - return PTR_ERR(net); - peer = rtnl_create_link(net, ifname, name_assign_type, &veth_link_ops, tbp, extack); if (IS_ERR(peer)) { @@ -1952,6 +1941,7 @@ static struct rtnl_link_ops veth_link_ops = { .newlink = veth_newlink, .dellink = veth_dellink, .policy = veth_policy, + .peer_type = VETH_INFO_PEER, .maxtype = VETH_INFO_MAX, .get_link_net = veth_get_link_net, .get_num_tx_queues = veth_get_num_queues, diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 792e9eadbfc3..ec06da34cd10 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -356,9 +356,6 @@ struct receive_queue { struct xdp_rxq_info xsk_rxq_info; struct xdp_buff **xsk_buffs; - - /* Do dma by self */ - bool do_dma; }; /* This structure can contain rss message with maximum settings for indirection table and keysize @@ -368,15 +365,16 @@ struct receive_queue { * because table sizes may be differ according to the device configuration. */ #define VIRTIO_NET_RSS_MAX_KEY_SIZE 40 -#define VIRTIO_NET_RSS_MAX_TABLE_LEN 128 struct virtio_net_ctrl_rss { u32 hash_types; u16 indirection_table_mask; u16 unclassified_queue; - u16 indirection_table[VIRTIO_NET_RSS_MAX_TABLE_LEN]; + u16 hash_cfg_reserved; /* for HASH_CONFIG (see virtio_net_hash_config for details) */ u16 max_tx_vq; u8 hash_key_length; u8 key[VIRTIO_NET_RSS_MAX_KEY_SIZE]; + + u16 *indirection_table; }; /* Control VQ buffers: protected by the rtnl lock */ @@ -512,6 +510,25 @@ static struct sk_buff *virtnet_skb_append_frag(struct sk_buff *head_skb, struct page *page, void *buf, int len, int truesize); +static int rss_indirection_table_alloc(struct virtio_net_ctrl_rss *rss, u16 indir_table_size) +{ + if (!indir_table_size) { + rss->indirection_table = NULL; + return 0; + } + + rss->indirection_table = kmalloc_array(indir_table_size, sizeof(u16), GFP_KERNEL); + if (!rss->indirection_table) + return -ENOMEM; + + return 0; +} + +static void rss_indirection_table_free(struct virtio_net_ctrl_rss *rss) +{ + kfree(rss->indirection_table); +} + static bool is_xdp_frame(void *ptr) { return (unsigned long)ptr & VIRTIO_XDP_FLAG; @@ -856,11 +873,14 @@ ok: static void virtnet_rq_unmap(struct receive_queue *rq, void *buf, u32 len) { + struct virtnet_info *vi = rq->vq->vdev->priv; struct page *page = virt_to_head_page(buf); struct virtnet_rq_dma *dma; void *head; int offset; + BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); + head = page_address(page); dma = head; @@ -885,10 +905,13 @@ static void virtnet_rq_unmap(struct receive_queue *rq, void *buf, u32 len) static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx) { + struct virtnet_info *vi = rq->vq->vdev->priv; void *buf; + BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); + buf = virtqueue_get_buf_ctx(rq->vq, len, ctx); - if (buf && rq->do_dma) + if (buf) virtnet_rq_unmap(rq, buf, *len); return buf; @@ -896,15 +919,13 @@ static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx) static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len) { + struct virtnet_info *vi = rq->vq->vdev->priv; struct virtnet_rq_dma *dma; dma_addr_t addr; u32 offset; void *head; - if (!rq->do_dma) { - sg_init_one(rq->sg, buf, len); - return; - } + BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); head = page_address(rq->alloc_frag.page); @@ -922,53 +943,51 @@ static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len) static void *virtnet_rq_alloc(struct receive_queue *rq, u32 size, gfp_t gfp) { struct page_frag *alloc_frag = &rq->alloc_frag; + struct virtnet_info *vi = rq->vq->vdev->priv; struct virtnet_rq_dma *dma; void *buf, *head; dma_addr_t addr; - if (unlikely(!skb_page_frag_refill(size, alloc_frag, gfp))) - return NULL; + BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); head = page_address(alloc_frag->page); - if (rq->do_dma) { - dma = head; - - /* new pages */ - if (!alloc_frag->offset) { - if (rq->last_dma) { - /* Now, the new page is allocated, the last dma - * will not be used. So the dma can be unmapped - * if the ref is 0. - */ - virtnet_rq_unmap(rq, rq->last_dma, 0); - rq->last_dma = NULL; - } + dma = head; - dma->len = alloc_frag->size - sizeof(*dma); + /* new pages */ + if (!alloc_frag->offset) { + if (rq->last_dma) { + /* Now, the new page is allocated, the last dma + * will not be used. So the dma can be unmapped + * if the ref is 0. + */ + virtnet_rq_unmap(rq, rq->last_dma, 0); + rq->last_dma = NULL; + } - addr = virtqueue_dma_map_single_attrs(rq->vq, dma + 1, - dma->len, DMA_FROM_DEVICE, 0); - if (virtqueue_dma_mapping_error(rq->vq, addr)) - return NULL; + dma->len = alloc_frag->size - sizeof(*dma); - dma->addr = addr; - dma->need_sync = virtqueue_dma_need_sync(rq->vq, addr); + addr = virtqueue_dma_map_single_attrs(rq->vq, dma + 1, + dma->len, DMA_FROM_DEVICE, 0); + if (virtqueue_dma_mapping_error(rq->vq, addr)) + return NULL; - /* Add a reference to dma to prevent the entire dma from - * being released during error handling. This reference - * will be freed after the pages are no longer used. - */ - get_page(alloc_frag->page); - dma->ref = 1; - alloc_frag->offset = sizeof(*dma); + dma->addr = addr; + dma->need_sync = virtqueue_dma_need_sync(rq->vq, addr); - rq->last_dma = dma; - } + /* Add a reference to dma to prevent the entire dma from + * being released during error handling. This reference + * will be freed after the pages are no longer used. + */ + get_page(alloc_frag->page); + dma->ref = 1; + alloc_frag->offset = sizeof(*dma); - ++dma->ref; + rq->last_dma = dma; } + ++dma->ref; + buf = head + alloc_frag->offset; get_page(alloc_frag->page); @@ -990,7 +1009,7 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf) return; } - if (rq->do_dma) + if (!vi->big_packets || vi->mergeable_rx_bufs) virtnet_rq_unmap(rq, buf, 0); virtnet_rq_free_buf(vi, rq, buf); @@ -2423,6 +2442,9 @@ static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq, len = SKB_DATA_ALIGN(len) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + if (unlikely(!skb_page_frag_refill(len, &rq->alloc_frag, gfp))) + return -ENOMEM; + buf = virtnet_rq_alloc(rq, len, gfp); if (unlikely(!buf)) return -ENOMEM; @@ -2433,8 +2455,7 @@ static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq, err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp); if (err < 0) { - if (rq->do_dma) - virtnet_rq_unmap(rq, buf, 0); + virtnet_rq_unmap(rq, buf, 0); put_page(virt_to_head_page(buf)); } @@ -2525,6 +2546,12 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi, */ len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len, room); + if (unlikely(!skb_page_frag_refill(len + room, alloc_frag, gfp))) + return -ENOMEM; + + if (!alloc_frag->offset && len + room + sizeof(struct virtnet_rq_dma) > alloc_frag->size) + len -= sizeof(struct virtnet_rq_dma); + buf = virtnet_rq_alloc(rq, len + room, gfp); if (unlikely(!buf)) return -ENOMEM; @@ -2548,8 +2575,7 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi, ctx = mergeable_len_to_ctx(len + room, headroom); err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp); if (err < 0) { - if (rq->do_dma) - virtnet_rq_unmap(rq, buf, 0); + virtnet_rq_unmap(rq, buf, 0); put_page(virt_to_head_page(buf)); } @@ -2706,7 +2732,7 @@ static int virtnet_receive_packets(struct virtnet_info *vi, } } else { while (packets < budget && - (buf = virtnet_rq_get_buf(rq, &len, NULL)) != NULL) { + (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) { receive_buf(vi, rq, buf, len, NULL, xdp_xmit, stats); packets++; } @@ -2804,7 +2830,7 @@ static void virtnet_rx_dim_update(struct virtnet_info *vi, struct receive_queue u64_stats_read(&rq->stats.bytes), &cur_sample); - net_dim(&rq->dim, cur_sample); + net_dim(&rq->dim, &cur_sample); rq->packets_in_napi = 0; } @@ -3374,15 +3400,59 @@ static void virtnet_ack_link_announce(struct virtnet_info *vi) dev_warn(&vi->dev->dev, "Failed to ack link announce.\n"); } +static bool virtnet_commit_rss_command(struct virtnet_info *vi); + +static void virtnet_rss_update_by_qpairs(struct virtnet_info *vi, u16 queue_pairs) +{ + u32 indir_val = 0; + int i = 0; + + for (; i < vi->rss_indir_table_size; ++i) { + indir_val = ethtool_rxfh_indir_default(i, queue_pairs); + vi->rss.indirection_table[i] = indir_val; + } + vi->rss.max_tx_vq = queue_pairs; +} + static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) { struct virtio_net_ctrl_mq *mq __free(kfree) = NULL; - struct scatterlist sg; + struct virtio_net_ctrl_rss old_rss; struct net_device *dev = vi->dev; + struct scatterlist sg; if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ)) return 0; + /* Firstly check if we need update rss. Do updating if both (1) rss enabled and + * (2) no user configuration. + * + * During rss command processing, device updates queue_pairs using rss.max_tx_vq. That is, + * the device updates queue_pairs together with rss, so we can skip the sperate queue_pairs + * update (VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET below) and return directly. + */ + if (vi->has_rss && !netif_is_rxfh_configured(dev)) { + memcpy(&old_rss, &vi->rss, sizeof(old_rss)); + if (rss_indirection_table_alloc(&vi->rss, vi->rss_indir_table_size)) { + vi->rss.indirection_table = old_rss.indirection_table; + return -ENOMEM; + } + + virtnet_rss_update_by_qpairs(vi, queue_pairs); + + if (!virtnet_commit_rss_command(vi)) { + /* restore ctrl_rss if commit_rss_command failed */ + rss_indirection_table_free(&vi->rss); + memcpy(&vi->rss, &old_rss, sizeof(old_rss)); + + dev_warn(&dev->dev, "Fail to set num of queue pairs to %d, because committing RSS failed\n", + queue_pairs); + return -EINVAL; + } + rss_indirection_table_free(&old_rss); + goto succ; + } + mq = kzalloc(sizeof(*mq), GFP_KERNEL); if (!mq) return -ENOMEM; @@ -3395,12 +3465,12 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n", queue_pairs); return -EINVAL; - } else { - vi->curr_queue_pairs = queue_pairs; - /* virtnet_open() will refill when device is going to up. */ - if (dev->flags & IFF_UP) - schedule_delayed_work(&vi->refill, 0); } +succ: + vi->curr_queue_pairs = queue_pairs; + /* virtnet_open() will refill when device is going to up. */ + if (dev->flags & IFF_UP) + schedule_delayed_work(&vi->refill, 0); return 0; } @@ -3828,11 +3898,15 @@ static bool virtnet_commit_rss_command(struct virtnet_info *vi) /* prepare sgs */ sg_init_table(sgs, 4); - sg_buf_size = offsetof(struct virtio_net_ctrl_rss, indirection_table); + sg_buf_size = offsetof(struct virtio_net_ctrl_rss, hash_cfg_reserved); sg_set_buf(&sgs[0], &vi->rss, sg_buf_size); - sg_buf_size = sizeof(uint16_t) * (vi->rss.indirection_table_mask + 1); - sg_set_buf(&sgs[1], vi->rss.indirection_table, sg_buf_size); + if (vi->has_rss) { + sg_buf_size = sizeof(uint16_t) * vi->rss_indir_table_size; + sg_set_buf(&sgs[1], vi->rss.indirection_table, sg_buf_size); + } else { + sg_set_buf(&sgs[1], &vi->rss.hash_cfg_reserved, sizeof(uint16_t)); + } sg_buf_size = offsetof(struct virtio_net_ctrl_rss, key) - offsetof(struct virtio_net_ctrl_rss, max_tx_vq); @@ -3856,21 +3930,14 @@ err: static void virtnet_init_default_rss(struct virtnet_info *vi) { - u32 indir_val = 0; - int i = 0; - vi->rss.hash_types = vi->rss_hash_types_supported; vi->rss_hash_types_saved = vi->rss_hash_types_supported; vi->rss.indirection_table_mask = vi->rss_indir_table_size ? vi->rss_indir_table_size - 1 : 0; vi->rss.unclassified_queue = 0; - for (; i < vi->rss_indir_table_size; ++i) { - indir_val = ethtool_rxfh_indir_default(i, vi->curr_queue_pairs); - vi->rss.indirection_table[i] = indir_val; - } + virtnet_rss_update_by_qpairs(vi, vi->curr_queue_pairs); - vi->rss.max_tx_vq = vi->has_rss ? vi->curr_queue_pairs : 0; vi->rss.hash_key_length = vi->rss_key_size; netdev_rss_key_fill(vi->rss.key, vi->rss_key_size); @@ -5916,7 +5983,7 @@ static void free_receive_page_frags(struct virtnet_info *vi) int i; for (i = 0; i < vi->max_queue_pairs; i++) if (vi->rq[i].alloc_frag.page) { - if (vi->rq[i].do_dma && vi->rq[i].last_dma) + if (vi->rq[i].last_dma) virtnet_rq_unmap(&vi->rq[i], vi->rq[i].last_dma, 0); put_page(vi->rq[i].alloc_frag.page); } @@ -6101,6 +6168,15 @@ err_ctrl: return -ENOMEM; } +static void virtnet_rq_set_premapped(struct virtnet_info *vi) +{ + int i; + + for (i = 0; i < vi->max_queue_pairs; i++) + /* error should never happen */ + BUG_ON(virtqueue_set_dma_premapped(vi->rq[i].vq)); +} + static int init_vqs(struct virtnet_info *vi) { int ret; @@ -6114,6 +6190,10 @@ static int init_vqs(struct virtnet_info *vi) if (ret) goto err_free; + /* disable for big mode */ + if (!vi->big_packets || vi->mergeable_rx_bufs) + virtnet_rq_set_premapped(vi); + cpus_read_lock(); virtnet_set_affinity(vi); cpus_read_unlock(); @@ -6420,10 +6500,19 @@ static int virtnet_probe(struct virtio_device *vdev) virtio_cread16(vdev, offsetof(struct virtio_net_config, rss_max_indirection_table_length)); } + err = rss_indirection_table_alloc(&vi->rss, vi->rss_indir_table_size); + if (err) + goto free; if (vi->has_rss || vi->has_rss_hash_report) { vi->rss_key_size = virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size)); + if (vi->rss_key_size > VIRTIO_NET_RSS_MAX_KEY_SIZE) { + dev_err(&vdev->dev, "rss_max_key_size=%u exceeds the limit %u.\n", + vi->rss_key_size, VIRTIO_NET_RSS_MAX_KEY_SIZE); + err = -EINVAL; + goto free; + } vi->rss_hash_types_supported = virtio_cread32(vdev, offsetof(struct virtio_net_config, supported_hash_types)); @@ -6551,6 +6640,15 @@ static int virtnet_probe(struct virtio_device *vdev) virtio_device_ready(vdev); + if (vi->has_rss || vi->has_rss_hash_report) { + if (!virtnet_commit_rss_command(vi)) { + dev_warn(&vdev->dev, "RSS disabled because committing failed.\n"); + dev->hw_features &= ~NETIF_F_RXHASH; + vi->has_rss_hash_report = false; + vi->has_rss = false; + } + } + virtnet_set_queues(vi, vi->curr_queue_pairs); /* a random MAC address has been assigned, notify the device. @@ -6674,6 +6772,8 @@ static void virtnet_remove(struct virtio_device *vdev) remove_vq_common(vi); + rss_indirection_table_free(&vi->rss); + free_netdev(vi->dev); } diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 4087f72f0d2b..67d25f4f94ef 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -521,7 +521,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, /* needed to match OIF rule */ fl4.flowi4_l3mdev = vrf_dev->ifindex; fl4.flowi4_iif = LOOPBACK_IFINDEX; - fl4.flowi4_tos = ip4h->tos & INET_DSCP_MASK; + fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)); fl4.flowi4_flags = FLOWI_FLAG_ANYSRC; fl4.flowi4_proto = ip4h->protocol; fl4.daddr = ip4h->daddr; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 841b59d1c1c2..42b07bc2b107 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1232,10 +1232,7 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, *ifindex = 0; } - if (tb[NDA_NH_ID]) - *nhid = nla_get_u32(tb[NDA_NH_ID]); - else - *nhid = 0; + *nhid = nla_get_u32_default(tb[NDA_NH_ID], 0); return 0; } diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c index dbaf26d6a7a6..16d07d619b4d 100644 --- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c +++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c @@ -3043,9 +3043,14 @@ ath10k_wmi_tlv_op_cleanup_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu) { struct ath10k_skb_cb *cb = ATH10K_SKB_CB(msdu); + struct ath10k_mgmt_tx_pkt_addr *pkt_addr; struct ath10k_wmi *wmi = &ar->wmi; - idr_remove(&wmi->mgmt_pending_tx, cb->msdu_id); + spin_lock_bh(&ar->data_lock); + pkt_addr = idr_remove(&wmi->mgmt_pending_tx, cb->msdu_id); + spin_unlock_bh(&ar->data_lock); + + kfree(pkt_addr); return 0; } diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index 4861179b2217..5e061f7525a6 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -2441,6 +2441,7 @@ wmi_process_mgmt_tx_comp(struct ath10k *ar, struct mgmt_tx_compl_params *param) dma_unmap_single(ar->dev, pkt_addr->paddr, msdu->len, DMA_TO_DEVICE); info = IEEE80211_SKB_CB(msdu); + kfree(pkt_addr); if (param->status) { info->flags &= ~IEEE80211_TX_STAT_ACK; @@ -9612,6 +9613,7 @@ static int ath10k_wmi_mgmt_tx_clean_up_pending(int msdu_id, void *ptr, dma_unmap_single(ar->dev, pkt_addr->paddr, msdu->len, DMA_TO_DEVICE); ieee80211_free_txskb(ar->hw, msdu); + kfree(pkt_addr); return 0; } diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index c087d8a0f5b2..40088e62572e 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -5291,8 +5291,11 @@ int ath11k_dp_rx_process_mon_status(struct ath11k_base *ab, int mac_id, hal_status == HAL_TLV_STATUS_PPDU_DONE) { rx_mon_stats->status_ppdu_done++; pmon->mon_ppdu_status = DP_PPDU_STATUS_DONE; - ath11k_dp_rx_mon_dest_process(ar, mac_id, budget, napi); - pmon->mon_ppdu_status = DP_PPDU_STATUS_START; + if (!ab->hw_params.full_monitor_mode) { + ath11k_dp_rx_mon_dest_process(ar, mac_id, + budget, napi); + pmon->mon_ppdu_status = DP_PPDU_STATUS_START; + } } if (ppdu_info->peer_id == HAL_INVALID_PEERID || diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c index f29ac6de7139..19702b6f09c3 100644 --- a/drivers/net/wireless/ath/wil6210/txrx.c +++ b/drivers/net/wireless/ath/wil6210/txrx.c @@ -306,7 +306,7 @@ static void wil_rx_add_radiotap_header(struct wil6210_priv *wil, struct sk_buff *skb) { struct wil6210_rtap { - struct ieee80211_radiotap_header rthdr; + struct ieee80211_radiotap_header_fixed rthdr; /* fields should be in the order of bits in rthdr.it_present */ /* flags */ u8 flags; diff --git a/drivers/net/wireless/broadcom/brcm80211/Kconfig b/drivers/net/wireless/broadcom/brcm80211/Kconfig index 3a1a35b5672f..19d0c003f626 100644 --- a/drivers/net/wireless/broadcom/brcm80211/Kconfig +++ b/drivers/net/wireless/broadcom/brcm80211/Kconfig @@ -27,6 +27,7 @@ source "drivers/net/wireless/broadcom/brcm80211/brcmfmac/Kconfig" config BRCM_TRACING bool "Broadcom device tracing" depends on BRCMSMAC || BRCMFMAC + depends on TRACING help If you say Y here, the Broadcom wireless drivers will register with ftrace to dump event information into the trace ringbuffer. diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c index 15bf35f2de2a..215814861cbd 100644 --- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c @@ -2515,7 +2515,7 @@ static void isr_rx_monitor(struct ipw2100_priv *priv, int i, * to build this manually element by element, we can write it much * more efficiently than we can parse it. ORDER MATTERS HERE */ struct ipw_rt_hdr { - struct ieee80211_radiotap_header rt_hdr; + struct ieee80211_radiotap_header_fixed rt_hdr; s8 rt_dbmsignal; /* signal in dbM, kluged to signed */ } *ipw_rt; diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.h b/drivers/net/wireless/intel/ipw2x00/ipw2200.h index d3db54e6d37c..19310fd0d8eb 100644 --- a/drivers/net/wireless/intel/ipw2x00/ipw2200.h +++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.h @@ -1141,7 +1141,7 @@ struct ipw_prom_priv { * structure is provided regardless of any bits unset. */ struct ipw_rt_hdr { - struct ieee80211_radiotap_header rt_hdr; + struct ieee80211_radiotap_header_fixed rt_hdr; u64 rt_tsf; /* TSF */ /* XXX */ u8 rt_flags; /* radiotap packet flags */ u8 rt_rate; /* rate in 500kb/s */ diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c index 9d33a66a49b5..958dd4f9bc69 100644 --- a/drivers/net/wireless/intel/iwlegacy/common.c +++ b/drivers/net/wireless/intel/iwlegacy/common.c @@ -3122,6 +3122,7 @@ il_enqueue_hcmd(struct il_priv *il, struct il_host_cmd *cmd) struct il_cmd_meta *out_meta; dma_addr_t phys_addr; unsigned long flags; + u8 *out_payload; u32 idx; u16 fix_size; @@ -3157,6 +3158,16 @@ il_enqueue_hcmd(struct il_priv *il, struct il_host_cmd *cmd) out_cmd = txq->cmd[idx]; out_meta = &txq->meta[idx]; + /* The payload is in the same place in regular and huge + * command buffers, but we need to let the compiler know when + * we're using a larger payload buffer to avoid "field- + * spanning write" warnings at run-time for huge commands. + */ + if (cmd->flags & CMD_SIZE_HUGE) + out_payload = ((struct il_device_cmd_huge *)out_cmd)->cmd.payload; + else + out_payload = out_cmd->cmd.payload; + if (WARN_ON(out_meta->flags & CMD_MAPPED)) { spin_unlock_irqrestore(&il->hcmd_lock, flags); return -ENOSPC; @@ -3170,7 +3181,7 @@ il_enqueue_hcmd(struct il_priv *il, struct il_host_cmd *cmd) out_meta->callback = cmd->callback; out_cmd->hdr.cmd = cmd->id; - memcpy(&out_cmd->cmd.payload, cmd->data, cmd->len); + memcpy(out_payload, cmd->data, cmd->len); /* At this point, the out_cmd now has all of the incoming cmd * information */ @@ -4962,6 +4973,8 @@ il_pci_resume(struct device *device) */ pci_write_config_byte(pdev, PCI_CFG_RETRY_TIMEOUT, 0x00); + _il_wr(il, CSR_INT, 0xffffffff); + _il_wr(il, CSR_FH_INT_STATUS, 0xffffffff); il_enable_interrupts(il); if (!(_il_rd(il, CSR_GP_CNTRL) & CSR_GP_CNTRL_REG_FLAG_HW_RF_KILL_SW)) diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h index 2147781b5fff..725c2a88ddb7 100644 --- a/drivers/net/wireless/intel/iwlegacy/common.h +++ b/drivers/net/wireless/intel/iwlegacy/common.h @@ -560,6 +560,18 @@ struct il_device_cmd { #define TFD_MAX_PAYLOAD_SIZE (sizeof(struct il_device_cmd)) +/** + * struct il_device_cmd_huge + * + * For use when sending huge commands. + */ +struct il_device_cmd_huge { + struct il_cmd_header hdr; /* uCode API */ + union { + u8 payload[IL_MAX_CMD_SIZE - sizeof(struct il_cmd_header)]; + } __packed cmd; +} __packed; + struct il_host_cmd { const void *data; unsigned long reply_page; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index a7cea0a55b35..0bc32291815e 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -429,38 +429,28 @@ out_free: return ret; } -static int iwl_acpi_sar_set_profile(union acpi_object *table, - struct iwl_sar_profile *profile, - bool enabled, u8 num_chains, - u8 num_sub_bands) +static int +iwl_acpi_parse_chains_table(union acpi_object *table, + struct iwl_sar_profile_chain *chains, + u8 num_chains, u8 num_sub_bands) { - int i, j, idx = 0; - - /* - * The table from ACPI is flat, but we store it in a - * structured array. - */ - for (i = 0; i < BIOS_SAR_MAX_CHAINS_PER_PROFILE; i++) { - for (j = 0; j < BIOS_SAR_MAX_SUB_BANDS_NUM; j++) { + for (u8 chain = 0; chain < num_chains; chain++) { + for (u8 subband = 0; subband < BIOS_SAR_MAX_SUB_BANDS_NUM; + subband++) { /* if we don't have the values, use the default */ - if (i >= num_chains || j >= num_sub_bands) { - profile->chains[i].subbands[j] = 0; + if (subband >= num_sub_bands) { + chains[chain].subbands[subband] = 0; + } else if (table->type != ACPI_TYPE_INTEGER || + table->integer.value > U8_MAX) { + return -EINVAL; } else { - if (table[idx].type != ACPI_TYPE_INTEGER || - table[idx].integer.value > U8_MAX) - return -EINVAL; - - profile->chains[i].subbands[j] = - table[idx].integer.value; - - idx++; + chains[chain].subbands[subband] = + table->integer.value; + table++; } } } - /* Only if all values were valid can the profile be enabled */ - profile->enabled = enabled; - return 0; } @@ -543,9 +533,11 @@ read_table: /* The profile from WRDS is officially profile 1, but goes * into sar_profiles[0] (because we don't have a profile 0). */ - ret = iwl_acpi_sar_set_profile(table, &fwrt->sar_profiles[0], - flags & IWL_SAR_ENABLE_MSK, - num_chains, num_sub_bands); + ret = iwl_acpi_parse_chains_table(table, fwrt->sar_profiles[0].chains, + num_chains, num_sub_bands); + if (!ret && flags & IWL_SAR_ENABLE_MSK) + fwrt->sar_profiles[0].enabled = true; + out_free: kfree(data); return ret; @@ -557,7 +549,7 @@ int iwl_acpi_get_ewrd_table(struct iwl_fw_runtime *fwrt) bool enabled; int i, n_profiles, tbl_rev, pos; int ret = 0; - u8 num_chains, num_sub_bands; + u8 num_sub_bands; data = iwl_acpi_get_object(fwrt->dev, ACPI_EWRD_METHOD); if (IS_ERR(data)) @@ -573,7 +565,6 @@ int iwl_acpi_get_ewrd_table(struct iwl_fw_runtime *fwrt) goto out_free; } - num_chains = ACPI_SAR_NUM_CHAINS_REV2; num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV2; goto read_table; @@ -589,7 +580,6 @@ int iwl_acpi_get_ewrd_table(struct iwl_fw_runtime *fwrt) goto out_free; } - num_chains = ACPI_SAR_NUM_CHAINS_REV1; num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV1; goto read_table; @@ -605,7 +595,6 @@ int iwl_acpi_get_ewrd_table(struct iwl_fw_runtime *fwrt) goto out_free; } - num_chains = ACPI_SAR_NUM_CHAINS_REV0; num_sub_bands = ACPI_SAR_NUM_SUB_BANDS_REV0; goto read_table; @@ -637,23 +626,54 @@ read_table: /* the tables start at element 3 */ pos = 3; + BUILD_BUG_ON(ACPI_SAR_NUM_CHAINS_REV0 != ACPI_SAR_NUM_CHAINS_REV1); + BUILD_BUG_ON(ACPI_SAR_NUM_CHAINS_REV2 != 2 * ACPI_SAR_NUM_CHAINS_REV0); + + /* parse non-cdb chains for all profiles */ for (i = 0; i < n_profiles; i++) { union acpi_object *table = &wifi_pkg->package.elements[pos]; + /* The EWRD profiles officially go from 2 to 4, but we * save them in sar_profiles[1-3] (because we don't * have profile 0). So in the array we start from 1. */ - ret = iwl_acpi_sar_set_profile(table, - &fwrt->sar_profiles[i + 1], - enabled, num_chains, - num_sub_bands); + ret = iwl_acpi_parse_chains_table(table, + fwrt->sar_profiles[i + 1].chains, + ACPI_SAR_NUM_CHAINS_REV0, + num_sub_bands); if (ret < 0) - break; + goto out_free; /* go to the next table */ - pos += num_chains * num_sub_bands; + pos += ACPI_SAR_NUM_CHAINS_REV0 * num_sub_bands; } + /* non-cdb table revisions */ + if (tbl_rev < 2) + goto set_enabled; + + /* parse cdb chains for all profiles */ + for (i = 0; i < n_profiles; i++) { + struct iwl_sar_profile_chain *chains; + union acpi_object *table; + + table = &wifi_pkg->package.elements[pos]; + chains = &fwrt->sar_profiles[i + 1].chains[ACPI_SAR_NUM_CHAINS_REV0]; + ret = iwl_acpi_parse_chains_table(table, + chains, + ACPI_SAR_NUM_CHAINS_REV0, + num_sub_bands); + if (ret < 0) + goto out_free; + + /* go to the next table */ + pos += ACPI_SAR_NUM_CHAINS_REV0 * num_sub_bands; + } + +set_enabled: + for (i = 0; i < n_profiles; i++) + fwrt->sar_profiles[i + 1].enabled = enabled; + out_free: kfree(data); return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/init.c b/drivers/net/wireless/intel/iwlwifi/fw/init.c index d8b083be5b6b..de87e0e3e072 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/init.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/init.c @@ -39,10 +39,12 @@ void iwl_fw_runtime_init(struct iwl_fw_runtime *fwrt, struct iwl_trans *trans, } IWL_EXPORT_SYMBOL(iwl_fw_runtime_init); +/* Assumes the appropriate lock is held by the caller */ void iwl_fw_runtime_suspend(struct iwl_fw_runtime *fwrt) { iwl_fw_suspend_timestamp(fwrt); - iwl_dbg_tlv_time_point(fwrt, IWL_FW_INI_TIME_POINT_HOST_D3_START, NULL); + iwl_dbg_tlv_time_point_sync(fwrt, IWL_FW_INI_TIME_POINT_HOST_D3_START, + NULL); } IWL_EXPORT_SYMBOL(iwl_fw_runtime_suspend); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 2abfc986701f..c620911a1193 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1413,25 +1413,35 @@ _iwl_op_mode_start(struct iwl_drv *drv, struct iwlwifi_opmode_table *op) const struct iwl_op_mode_ops *ops = op->ops; struct dentry *dbgfs_dir = NULL; struct iwl_op_mode *op_mode = NULL; + int retry, max_retry = !!iwlwifi_mod_params.fw_restart * IWL_MAX_INIT_RETRY; /* also protects start/stop from racing against each other */ lockdep_assert_held(&iwlwifi_opmode_table_mtx); + for (retry = 0; retry <= max_retry; retry++) { + #ifdef CONFIG_IWLWIFI_DEBUGFS - drv->dbgfs_op_mode = debugfs_create_dir(op->name, - drv->dbgfs_drv); - dbgfs_dir = drv->dbgfs_op_mode; + drv->dbgfs_op_mode = debugfs_create_dir(op->name, + drv->dbgfs_drv); + dbgfs_dir = drv->dbgfs_op_mode; #endif - op_mode = ops->start(drv->trans, drv->trans->cfg, - &drv->fw, dbgfs_dir); - if (op_mode) - return op_mode; + op_mode = ops->start(drv->trans, drv->trans->cfg, + &drv->fw, dbgfs_dir); + + if (op_mode) + return op_mode; + + if (test_bit(STATUS_TRANS_DEAD, &drv->trans->status)) + break; + + IWL_ERR(drv, "retry init count %d\n", retry); #ifdef CONFIG_IWLWIFI_DEBUGFS - debugfs_remove_recursive(drv->dbgfs_op_mode); - drv->dbgfs_op_mode = NULL; + debugfs_remove_recursive(drv->dbgfs_op_mode); + drv->dbgfs_op_mode = NULL; #endif + } return NULL; } diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h index 1549ff429549..6a1d31892417 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h @@ -98,6 +98,9 @@ void iwl_drv_stop(struct iwl_drv *drv); #define VISIBLE_IF_IWLWIFI_KUNIT static #endif +/* max retry for init flow */ +#define IWL_MAX_INIT_RETRY 2 + #define FW_NAME_PRE_BUFSIZE 64 struct iwl_trans; const char *iwl_drv_get_fwname_pre(struct iwl_trans *trans, char *buf); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 84c2c87b017f..f85c01e04ebf 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -1416,7 +1416,9 @@ int iwl_mvm_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) iwl_mvm_pause_tcm(mvm, true); + mutex_lock(&mvm->mutex); iwl_fw_runtime_suspend(&mvm->fwrt); + mutex_unlock(&mvm->mutex); return __iwl_mvm_suspend(hw, wowlan, false); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 3fb9e9ebcd17..5ea684802ad1 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1307,8 +1307,8 @@ static void iwl_mvm_disconnect_iterator(void *data, u8 *mac, void iwl_mvm_send_recovery_cmd(struct iwl_mvm *mvm, u32 flags) { u32 error_log_size = mvm->fw->ucode_capa.error_log_size; + u32 status = 0; int ret; - u32 resp; struct iwl_fw_error_recovery_cmd recovery_cmd = { .flags = cpu_to_le32(flags), @@ -1316,7 +1316,6 @@ void iwl_mvm_send_recovery_cmd(struct iwl_mvm *mvm, u32 flags) }; struct iwl_host_cmd host_cmd = { .id = WIDE_ID(SYSTEM_GROUP, FW_ERROR_RECOVERY_CMD), - .flags = CMD_WANT_SKB, .data = {&recovery_cmd, }, .len = {sizeof(recovery_cmd), }, }; @@ -1336,7 +1335,7 @@ void iwl_mvm_send_recovery_cmd(struct iwl_mvm *mvm, u32 flags) recovery_cmd.buf_size = cpu_to_le32(error_log_size); } - ret = iwl_mvm_send_cmd(mvm, &host_cmd); + ret = iwl_mvm_send_cmd_status(mvm, &host_cmd, &status); kfree(mvm->error_recovery_buf); mvm->error_recovery_buf = NULL; @@ -1347,11 +1346,10 @@ void iwl_mvm_send_recovery_cmd(struct iwl_mvm *mvm, u32 flags) /* skb respond is only relevant in ERROR_RECOVERY_UPDATE_DB */ if (flags & ERROR_RECOVERY_UPDATE_DB) { - resp = le32_to_cpu(*(__le32 *)host_cmd.resp_pkt->data); - if (resp) { + if (status) { IWL_ERR(mvm, "Failed to send recovery cmd blob was invalid %d\n", - resp); + status); ieee80211_iterate_interfaces(mvm->hw, 0, iwl_mvm_disconnect_iterator, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index c4fc99ec97e6..07778d55878b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1294,12 +1294,14 @@ int iwl_mvm_mac_start(struct ieee80211_hw *hw) { struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); int ret; + int retry, max_retry = 0; mutex_lock(&mvm->mutex); /* we are starting the mac not in error flow, and restart is enabled */ if (!test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status) && iwlwifi_mod_params.fw_restart) { + max_retry = IWL_MAX_INIT_RETRY; /* * This will prevent mac80211 recovery flows to trigger during * init failures @@ -1307,7 +1309,13 @@ int iwl_mvm_mac_start(struct ieee80211_hw *hw) set_bit(IWL_MVM_STATUS_STARTING, &mvm->status); } - ret = __iwl_mvm_mac_start(mvm); + for (retry = 0; retry <= max_retry; retry++) { + ret = __iwl_mvm_mac_start(mvm); + if (!ret) + break; + + IWL_ERR(mvm, "mac start retry %d\n", retry); + } clear_bit(IWL_MVM_STATUS_STARTING, &mvm->status); mutex_unlock(&mvm->mutex); @@ -1996,7 +2004,6 @@ static void iwl_mvm_mac_remove_interface(struct ieee80211_hw *hw, mvm->p2p_device_vif = NULL; } - iwl_mvm_unset_link_mapping(mvm, vif, &vif->bss_conf); iwl_mvm_mac_ctxt_remove(mvm, vif); RCU_INIT_POINTER(mvm->vif_id_to_mac[mvmvif->id], NULL); @@ -2005,6 +2012,7 @@ static void iwl_mvm_mac_remove_interface(struct ieee80211_hw *hw, mvm->monitor_on = false; out: + iwl_mvm_unset_link_mapping(mvm, vif, &vif->bss_conf); if (vif->type == NL80211_IFTYPE_AP || vif->type == NL80211_IFTYPE_ADHOC) { iwl_mvm_dealloc_int_sta(mvm, &mvmvif->deflink.mcast_sta); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c index 75ca960857ed..b807046144c0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c @@ -41,8 +41,6 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw, /* reset deflink MLO parameters */ mvmvif->deflink.fw_link_id = IWL_MVM_FW_LINK_ID_INVALID; mvmvif->deflink.active = 0; - /* the first link always points to the default one */ - mvmvif->link[0] = &mvmvif->deflink; ret = iwl_mvm_mld_mac_ctxt_add(mvm, vif); if (ret) @@ -60,9 +58,19 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw, IEEE80211_VIF_SUPPORTS_CQM_RSSI; } - ret = iwl_mvm_add_link(mvm, vif, &vif->bss_conf); - if (ret) - goto out_free_bf; + /* We want link[0] to point to the default link, unless we have MLO and + * in this case this will be modified later by .change_vif_links() + * If we are in the restart flow with an MLD connection, we will wait + * to .change_vif_links() to setup the links. + */ + if (!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) || + !ieee80211_vif_is_mld(vif)) { + mvmvif->link[0] = &mvmvif->deflink; + + ret = iwl_mvm_add_link(mvm, vif, &vif->bss_conf); + if (ret) + goto out_free_bf; + } /* Save a pointer to p2p device vif, so it can later be used to * update the p2p device MAC when a GO is started/stopped @@ -1178,7 +1186,11 @@ iwl_mvm_mld_change_vif_links(struct ieee80211_hw *hw, mutex_lock(&mvm->mutex); - if (old_links == 0) { + /* If we're in RESTART flow, the default link wasn't added in + * drv_add_interface(), and link[0] doesn't point to it. + */ + if (old_links == 0 && !test_bit(IWL_MVM_STATUS_IN_HW_RESTART, + &mvm->status)) { err = iwl_mvm_disable_link(mvm, vif, &vif->bss_conf); if (err) goto out_err; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 6fb241d0c5f5..376b9b12fa62 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1774,7 +1774,7 @@ iwl_mvm_umac_scan_cfg_channels_v7_6g(struct iwl_mvm *mvm, &cp->channel_config[ch_cnt]; u32 s_ssid_bitmap = 0, bssid_bitmap = 0, flags = 0; - u8 j, k, n_s_ssids = 0, n_bssids = 0; + u8 k, n_s_ssids = 0, n_bssids = 0; u8 max_s_ssids, max_bssids; bool force_passive = false, found = false, allow_passive = true, unsolicited_probe_on_chan = false, psc_no_listen = false; @@ -1799,7 +1799,7 @@ iwl_mvm_umac_scan_cfg_channels_v7_6g(struct iwl_mvm *mvm, cfg->v5.iter_count = 1; cfg->v5.iter_interval = 0; - for (j = 0; j < params->n_6ghz_params; j++) { + for (u32 j = 0; j < params->n_6ghz_params; j++) { s8 tmp_psd_20; if (!(scan_6ghz_params[j].channel_idx == i)) @@ -1873,7 +1873,7 @@ iwl_mvm_umac_scan_cfg_channels_v7_6g(struct iwl_mvm *mvm, * SSID. * TODO: improve this logic */ - for (j = 0; j < params->n_6ghz_params; j++) { + for (u32 j = 0; j < params->n_6ghz_params; j++) { if (!(scan_6ghz_params[j].channel_idx == i)) continue; diff --git a/drivers/net/wireless/marvell/libertas/radiotap.h b/drivers/net/wireless/marvell/libertas/radiotap.h index 1ed5608d353f..d543bfe739dc 100644 --- a/drivers/net/wireless/marvell/libertas/radiotap.h +++ b/drivers/net/wireless/marvell/libertas/radiotap.h @@ -2,7 +2,7 @@ #include <net/ieee80211_radiotap.h> struct tx_radiotap_hdr { - struct ieee80211_radiotap_header hdr; + struct ieee80211_radiotap_header_fixed hdr; u8 rate; u8 txpower; u8 rts_retries; @@ -31,7 +31,7 @@ struct tx_radiotap_hdr { #define IEEE80211_FC_DSTODS 0x0300 struct rx_radiotap_hdr { - struct ieee80211_radiotap_header hdr; + struct ieee80211_radiotap_header_fixed hdr; u8 flags; u8 rate; u8 antsignal; diff --git a/drivers/net/wireless/mediatek/mt76/mcu.c b/drivers/net/wireless/mediatek/mt76/mcu.c index 98da82b74094..3353012e8542 100644 --- a/drivers/net/wireless/mediatek/mt76/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mcu.c @@ -84,13 +84,16 @@ int mt76_mcu_skb_send_and_get_msg(struct mt76_dev *dev, struct sk_buff *skb, mutex_lock(&dev->mcu.mutex); if (dev->mcu_ops->mcu_skb_prepare_msg) { + orig_skb = skb; ret = dev->mcu_ops->mcu_skb_prepare_msg(dev, skb, cmd, &seq); if (ret < 0) goto out; } retry: - orig_skb = skb_get(skb); + /* orig skb might be needed for retry, mcu_skb_send_msg consumes it */ + if (orig_skb) + skb_get(orig_skb); ret = dev->mcu_ops->mcu_skb_send_msg(dev, skb, cmd, &seq); if (ret < 0) goto out; @@ -105,7 +108,7 @@ retry: do { skb = mt76_mcu_get_response(dev, expires); if (!skb && !test_bit(MT76_MCU_RESET, &dev->phy.state) && - retry++ < dev->mcu_ops->max_retry) { + orig_skb && retry++ < dev->mcu_ops->max_retry) { dev_err(dev->dev, "Retry message %08x (seq %d)\n", cmd, seq); skb = orig_skb; diff --git a/drivers/net/wireless/microchip/wilc1000/mon.c b/drivers/net/wireless/microchip/wilc1000/mon.c index 03b7229a0ff5..c3d27aaec297 100644 --- a/drivers/net/wireless/microchip/wilc1000/mon.c +++ b/drivers/net/wireless/microchip/wilc1000/mon.c @@ -7,12 +7,12 @@ #include "cfg80211.h" struct wilc_wfi_radiotap_hdr { - struct ieee80211_radiotap_header hdr; + struct ieee80211_radiotap_header_fixed hdr; u8 rate; } __packed; struct wilc_wfi_radiotap_cb_hdr { - struct ieee80211_radiotap_header hdr; + struct ieee80211_radiotap_header_fixed hdr; u8 rate; u8 dump; u16 tx_flags; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c index d069a81ac617..cc699efa9c79 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192du/sw.c @@ -352,7 +352,6 @@ static const struct usb_device_id rtl8192d_usb_ids[] = { {RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x8194, rtl92du_hal_cfg)}, {RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x8111, rtl92du_hal_cfg)}, {RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x0193, rtl92du_hal_cfg)}, - {RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0x8171, rtl92du_hal_cfg)}, {RTL_USB_DEVICE(USB_VENDOR_ID_REALTEK, 0xe194, rtl92du_hal_cfg)}, {RTL_USB_DEVICE(0x2019, 0xab2c, rtl92du_hal_cfg)}, {RTL_USB_DEVICE(0x2019, 0xab2d, rtl92du_hal_cfg)}, diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c index 6fa3c37205f5..8d6db68246f1 100644 --- a/drivers/net/wireless/realtek/rtw88/usb.c +++ b/drivers/net/wireless/realtek/rtw88/usb.c @@ -773,7 +773,6 @@ static void rtw_usb_dynamic_rx_agg_v1(struct rtw_dev *rtwdev, bool enable) u8 size, timeout; u16 val16; - rtw_write32_set(rtwdev, REG_RXDMA_AGG_PG_TH, BIT_EN_PRE_CALC); rtw_write8_set(rtwdev, REG_TXDMA_PQ_MAP, BIT_RXDMA_AGG_EN); rtw_write8_clr(rtwdev, REG_RXDMA_AGG_PG_TH + 3, BIT(7)); diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c index ced42f9d297d..68316d44b204 100644 --- a/drivers/net/wireless/realtek/rtw89/coex.c +++ b/drivers/net/wireless/realtek/rtw89/coex.c @@ -6514,6 +6514,8 @@ static void _update_wl_info_v7(struct rtw89_dev *rtwdev, u8 rid) /* todo DBCC related event */ rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC] wl_info phy_now=%d\n", phy_now); + rtw89_debug(rtwdev, RTW89_DBG_BTC, + "[BTC] rlink cnt_2g=%d cnt_5g=%d\n", cnt_2g, cnt_5g); if (wl_rinfo->dbcc_en != rtwdev->dbcc_en) { wl_rinfo->dbcc_chg = 1; diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c index b0477ece7012..f923bec03d41 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.c +++ b/drivers/net/wireless/realtek/rtw89/pci.c @@ -3052,24 +3052,54 @@ static void rtw89_pci_declaim_device(struct rtw89_dev *rtwdev, pci_disable_device(pdev); } -static void rtw89_pci_cfg_dac(struct rtw89_dev *rtwdev) +static bool rtw89_pci_chip_is_manual_dac(struct rtw89_dev *rtwdev) { - struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv; const struct rtw89_chip_info *chip = rtwdev->chip; - if (!rtwpci->enable_dac) - return; - switch (chip->chip_id) { case RTL8852A: case RTL8852B: case RTL8851B: case RTL8852BT: - break; + return true; default: - return; + return false; + } +} + +static bool rtw89_pci_is_dac_compatible_bridge(struct rtw89_dev *rtwdev) +{ + struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv; + struct pci_dev *bridge = pci_upstream_bridge(rtwpci->pdev); + + if (!rtw89_pci_chip_is_manual_dac(rtwdev)) + return true; + + if (!bridge) + return false; + + switch (bridge->vendor) { + case PCI_VENDOR_ID_INTEL: + return true; + case PCI_VENDOR_ID_ASMEDIA: + if (bridge->device == 0x2806) + return true; + break; } + return false; +} + +static void rtw89_pci_cfg_dac(struct rtw89_dev *rtwdev) +{ + struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv; + + if (!rtwpci->enable_dac) + return; + + if (!rtw89_pci_chip_is_manual_dac(rtwdev)) + return; + rtw89_pci_config_byte_set(rtwdev, RTW89_PCIE_L1_CTRL, RTW89_PCIE_BIT_EN_64BITS); } @@ -3087,6 +3117,9 @@ static int rtw89_pci_setup_mapping(struct rtw89_dev *rtwdev, goto err; } + if (!rtw89_pci_is_dac_compatible_bridge(rtwdev)) + goto no_dac; + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(36)); if (!ret) { rtwpci->enable_dac = true; @@ -3099,6 +3132,7 @@ static int rtw89_pci_setup_mapping(struct rtw89_dev *rtwdev, goto err_release_regions; } } +no_dac: resource_len = pci_resource_len(pdev, bar_id); rtwpci->mmap = pci_iomap(pdev, bar_id, resource_len); diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c index 2a36b58f7a15..347a15544afe 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -763,7 +763,7 @@ static const struct rhashtable_params hwsim_rht_params = { }; struct hwsim_radiotap_hdr { - struct ieee80211_radiotap_header hdr; + struct ieee80211_radiotap_header_fixed hdr; __le64 rt_tsft; u8 rt_flags; u8 rt_rate; @@ -772,7 +772,7 @@ struct hwsim_radiotap_hdr { } __packed; struct hwsim_radiotap_ack_hdr { - struct ieee80211_radiotap_header hdr; + struct ieee80211_radiotap_header_fixed hdr; u8 rt_flags; u8 pad; __le16 rt_channel; diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c index 210d84c67ef9..7a9c09cd4fdc 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c @@ -226,7 +226,7 @@ int t7xx_dpmaif_rx_buf_alloc(struct dpmaif_ctrl *dpmaif_ctrl, return 0; err_unmap_skbs: - while (--i > 0) + while (i--) t7xx_unmap_bat_skb(dpmaif_ctrl->dev, bat_req->bat_skb, i); return ret; diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.c b/drivers/net/wwan/t7xx/t7xx_modem_ops.c index 79f17100f70b..7968e208dd37 100644 --- a/drivers/net/wwan/t7xx/t7xx_modem_ops.c +++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.c @@ -198,6 +198,7 @@ int t7xx_reset_device(struct t7xx_pci_dev *t7xx_dev, enum reset_type type) pci_save_state(t7xx_dev->pdev); t7xx_pci_reprobe_early(t7xx_dev); t7xx_mode_update(t7xx_dev, T7XX_RESET); + WRITE_ONCE(t7xx_dev->debug_ports_show, false); if (type == FLDR) { ret = t7xx_acpi_reset(t7xx_dev, "_RST"); diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index e556e5bd49ab..7b8c17b029c7 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -41,6 +41,7 @@ #include "t7xx_pcie_mac.h" #include "t7xx_reg.h" #include "t7xx_state_monitor.h" +#include "t7xx_port_proxy.h" #define T7XX_PCI_IREG_BASE 0 #define T7XX_PCI_EREG_BASE 2 @@ -120,13 +121,58 @@ static ssize_t t7xx_mode_show(struct device *dev, static DEVICE_ATTR_RW(t7xx_mode); -static struct attribute *t7xx_mode_attr[] = { +static ssize_t t7xx_debug_ports_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct t7xx_pci_dev *t7xx_dev; + struct pci_dev *pdev; + bool show; + int ret; + + pdev = to_pci_dev(dev); + t7xx_dev = pci_get_drvdata(pdev); + if (!t7xx_dev) + return -ENODEV; + + ret = kstrtobool(buf, &show); + if (ret < 0) + return ret; + + t7xx_proxy_debug_ports_show(t7xx_dev, show); + WRITE_ONCE(t7xx_dev->debug_ports_show, show); + + return count; +}; + +static ssize_t t7xx_debug_ports_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct t7xx_pci_dev *t7xx_dev; + struct pci_dev *pdev; + bool show; + + pdev = to_pci_dev(dev); + t7xx_dev = pci_get_drvdata(pdev); + if (!t7xx_dev) + return -ENODEV; + + show = READ_ONCE(t7xx_dev->debug_ports_show); + + return sysfs_emit(buf, "%d\n", show); +} + +static DEVICE_ATTR_RW(t7xx_debug_ports); + +static struct attribute *t7xx_attr[] = { &dev_attr_t7xx_mode.attr, + &dev_attr_t7xx_debug_ports.attr, NULL }; -static const struct attribute_group t7xx_mode_attribute_group = { - .attrs = t7xx_mode_attr, +static const struct attribute_group t7xx_attribute_group = { + .attrs = t7xx_attr, }; void t7xx_mode_update(struct t7xx_pci_dev *t7xx_dev, enum t7xx_mode mode) @@ -839,7 +885,7 @@ static int t7xx_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) t7xx_pcie_mac_interrupts_dis(t7xx_dev); ret = sysfs_create_group(&t7xx_dev->pdev->dev.kobj, - &t7xx_mode_attribute_group); + &t7xx_attribute_group); if (ret) goto err_md_exit; @@ -855,7 +901,7 @@ static int t7xx_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_remove_group: sysfs_remove_group(&t7xx_dev->pdev->dev.kobj, - &t7xx_mode_attribute_group); + &t7xx_attribute_group); err_md_exit: t7xx_md_exit(t7xx_dev); @@ -870,7 +916,7 @@ static void t7xx_pci_remove(struct pci_dev *pdev) t7xx_dev = pci_get_drvdata(pdev); sysfs_remove_group(&t7xx_dev->pdev->dev.kobj, - &t7xx_mode_attribute_group); + &t7xx_attribute_group); t7xx_md_exit(t7xx_dev); for (i = 0; i < EXT_INT_NUM; i++) { diff --git a/drivers/net/wwan/t7xx/t7xx_pci.h b/drivers/net/wwan/t7xx/t7xx_pci.h index cd8ea17c2644..b25d867e72d2 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.h +++ b/drivers/net/wwan/t7xx/t7xx_pci.h @@ -94,6 +94,7 @@ struct t7xx_pci_dev { struct dentry *debugfs_dir; #endif u32 mode; + bool debug_ports_show; }; enum t7xx_pm_id { diff --git a/drivers/net/wwan/t7xx/t7xx_port.h b/drivers/net/wwan/t7xx/t7xx_port.h index f74d3bab810d..9f5d6d288c97 100644 --- a/drivers/net/wwan/t7xx/t7xx_port.h +++ b/drivers/net/wwan/t7xx/t7xx_port.h @@ -42,6 +42,8 @@ enum port_ch { /* to AP */ PORT_CH_AP_CONTROL_RX = 0x1000, PORT_CH_AP_CONTROL_TX = 0x1001, + PORT_CH_AP_ADB_RX = 0x100a, + PORT_CH_AP_ADB_TX = 0x100b, /* to MD */ PORT_CH_CONTROL_RX = 0x2000, @@ -100,6 +102,7 @@ struct t7xx_port_conf { struct port_ops *ops; char *name; enum wwan_port_type port_type; + bool debug; }; struct t7xx_port { diff --git a/drivers/net/wwan/t7xx/t7xx_port_proxy.c b/drivers/net/wwan/t7xx/t7xx_port_proxy.c index 35743e7de0c3..4fc131f9632f 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_proxy.c +++ b/drivers/net/wwan/t7xx/t7xx_port_proxy.c @@ -38,7 +38,8 @@ #include "t7xx_state_monitor.h" #define Q_IDX_CTRL 0 -#define Q_IDX_MBIM 2 +#define Q_IDX_MBIM_MIPC 2 +#define Q_IDX_ADB 3 #define Q_IDX_AT_CMD 5 #define INVALID_SEQ_NUM GENMASK(15, 0) @@ -66,8 +67,8 @@ static const struct t7xx_port_conf t7xx_port_conf[] = { }, { .tx_ch = PORT_CH_MBIM_TX, .rx_ch = PORT_CH_MBIM_RX, - .txq_index = Q_IDX_MBIM, - .rxq_index = Q_IDX_MBIM, + .txq_index = Q_IDX_MBIM_MIPC, + .rxq_index = Q_IDX_MBIM_MIPC, .path_id = CLDMA_ID_MD, .ops = &wwan_sub_port_ops, .name = "MBIM", @@ -100,7 +101,27 @@ static const struct t7xx_port_conf t7xx_port_conf[] = { .path_id = CLDMA_ID_AP, .ops = &ctl_port_ops, .name = "t7xx_ap_ctrl", - }, + }, { + .tx_ch = PORT_CH_AP_ADB_TX, + .rx_ch = PORT_CH_AP_ADB_RX, + .txq_index = Q_IDX_ADB, + .rxq_index = Q_IDX_ADB, + .path_id = CLDMA_ID_AP, + .ops = &wwan_sub_port_ops, + .name = "adb", + .port_type = WWAN_PORT_ADB, + .debug = true, + }, { + .tx_ch = PORT_CH_MIPC_TX, + .rx_ch = PORT_CH_MIPC_RX, + .txq_index = Q_IDX_MBIM_MIPC, + .rxq_index = Q_IDX_MBIM_MIPC, + .path_id = CLDMA_ID_MD, + .ops = &wwan_sub_port_ops, + .name = "mipc", + .port_type = WWAN_PORT_MIPC, + .debug = true, + } }; static const struct t7xx_port_conf t7xx_early_port_conf[] = { @@ -505,13 +526,33 @@ static void t7xx_proxy_init_all_ports(struct t7xx_modem *md) spin_lock_init(&port->port_update_lock); port->chan_enable = false; - if (port_conf->ops && port_conf->ops->init) + if (!port_conf->debug && + port_conf->ops && + port_conf->ops->init) port_conf->ops->init(port); } t7xx_proxy_setup_ch_mapping(port_prox); } +void t7xx_proxy_debug_ports_show(struct t7xx_pci_dev *t7xx_dev, bool show) +{ + struct port_proxy *port_prox = t7xx_dev->md->port_prox; + struct t7xx_port *port; + int i; + + for_each_proxy_port(i, port, port_prox) { + const struct t7xx_port_conf *port_conf = port->port_conf; + + if (port_conf->debug && port_conf->ops) { + if (show && port_conf->ops->init) + port_conf->ops->init(port); + else if (!show && port_conf->ops->uninit) + port_conf->ops->uninit(port); + } + } +} + void t7xx_port_proxy_set_cfg(struct t7xx_modem *md, enum port_cfg_id cfg_id) { struct port_proxy *port_prox = md->port_prox; diff --git a/drivers/net/wwan/t7xx/t7xx_port_proxy.h b/drivers/net/wwan/t7xx/t7xx_port_proxy.h index 7f5706811445..f0918b36e899 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_proxy.h +++ b/drivers/net/wwan/t7xx/t7xx_port_proxy.h @@ -98,6 +98,7 @@ extern struct port_ops ctl_port_ops; extern struct port_ops t7xx_trace_port_ops; #endif +void t7xx_proxy_debug_ports_show(struct t7xx_pci_dev *t7xx_dev, bool show); void t7xx_port_proxy_reset(struct port_proxy *port_prox); void t7xx_port_proxy_uninit(struct port_proxy *port_prox); int t7xx_port_proxy_init(struct t7xx_modem *md); diff --git a/drivers/net/wwan/t7xx/t7xx_port_wwan.c b/drivers/net/wwan/t7xx/t7xx_port_wwan.c index 4b23ba693f3f..7fc569565ff9 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_wwan.c +++ b/drivers/net/wwan/t7xx/t7xx_port_wwan.c @@ -169,7 +169,9 @@ static int t7xx_port_wwan_init(struct t7xx_port *port) { const struct t7xx_port_conf *port_conf = port->port_conf; - if (port_conf->port_type == WWAN_PORT_FASTBOOT) + if (port_conf->port_type == WWAN_PORT_FASTBOOT || + port_conf->port_type == WWAN_PORT_ADB || + port_conf->port_type == WWAN_PORT_MIPC) t7xx_port_wwan_create(port); port->rx_length_th = RX_QUEUE_MAXLEN; @@ -224,7 +226,9 @@ static void t7xx_port_wwan_md_state_notify(struct t7xx_port *port, unsigned int { const struct t7xx_port_conf *port_conf = port->port_conf; - if (port_conf->port_type == WWAN_PORT_FASTBOOT) + if (port_conf->port_type == WWAN_PORT_FASTBOOT || + port_conf->port_type == WWAN_PORT_ADB || + port_conf->port_type == WWAN_PORT_MIPC) return; if (state != MD_STATE_READY) diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 8dc88cc65781..a51e2755991a 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -334,6 +334,14 @@ static const struct { .name = "FASTBOOT", .devsuf = "fastboot", }, + [WWAN_PORT_ADB] = { + .name = "ADB", + .devsuf = "adb", + }, + [WWAN_PORT_MIPC] = { + .name = "MIPC", + .devsuf = "mipc", + }, }; static ssize_t type_show(struct device *dev, struct device_attribute *attr, diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 84cb859a911d..b149b638453f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -92,6 +92,17 @@ MODULE_PARM_DESC(apst_secondary_latency_tol_us, "secondary APST latency tolerance in us"); /* + * Older kernels didn't enable protection information if it was at an offset. + * Newer kernels do, so it breaks reads on the upgrade if such formats were + * used in prior kernels since the metadata written did not contain a valid + * checksum. + */ +static bool disable_pi_offsets = false; +module_param(disable_pi_offsets, bool, 0444); +MODULE_PARM_DESC(disable_pi_offsets, + "disable protection information if it has an offset"); + +/* * nvme_wq - hosts nvme related works that are not reset or delete * nvme_reset_wq - hosts nvme reset works * nvme_delete_wq - hosts nvme delete works @@ -1390,17 +1401,30 @@ static void nvme_update_keep_alive(struct nvme_ctrl *ctrl, nvme_start_keep_alive(ctrl); } -/* - * In NVMe 1.0 the CNS field was just a binary controller or namespace - * flag, thus sending any new CNS opcodes has a big chance of not working. - * Qemu unfortunately had that bug after reporting a 1.1 version compliance - * (but not for any later version). - */ -static bool nvme_ctrl_limited_cns(struct nvme_ctrl *ctrl) +static bool nvme_id_cns_ok(struct nvme_ctrl *ctrl, u8 cns) { - if (ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS) - return ctrl->vs < NVME_VS(1, 2, 0); - return ctrl->vs < NVME_VS(1, 1, 0); + /* + * The CNS field occupies a full byte starting with NVMe 1.2 + */ + if (ctrl->vs >= NVME_VS(1, 2, 0)) + return true; + + /* + * NVMe 1.1 expanded the CNS value to two bits, which means values + * larger than that could get truncated and treated as an incorrect + * value. + * + * Qemu implemented 1.0 behavior for controllers claiming 1.1 + * compliance, so they need to be quirked here. + */ + if (ctrl->vs >= NVME_VS(1, 1, 0) && + !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) + return cns <= 3; + + /* + * NVMe 1.0 used a single bit for the CNS value. + */ + return cns <= 1; } static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id) @@ -1913,8 +1937,12 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl, if (head->pi_size && head->ms >= head->pi_size) head->pi_type = id->dps & NVME_NS_DPS_PI_MASK; - if (!(id->dps & NVME_NS_DPS_PI_FIRST)) - info->pi_offset = head->ms - head->pi_size; + if (!(id->dps & NVME_NS_DPS_PI_FIRST)) { + if (disable_pi_offsets) + head->pi_type = 0; + else + info->pi_offset = head->ms - head->pi_size; + } if (ctrl->ops->flags & NVME_F_FABRICS) { /* @@ -3104,7 +3132,7 @@ static int nvme_init_non_mdts_limits(struct nvme_ctrl *ctrl) ctrl->max_zeroes_sectors = 0; if (ctrl->subsys->subtype != NVME_NQN_NVME || - nvme_ctrl_limited_cns(ctrl) || + !nvme_id_cns_ok(ctrl, NVME_ID_CNS_CS_CTRL) || test_bit(NVME_CTRL_SKIP_ID_CNS_CS, &ctrl->flags)) return 0; @@ -4200,7 +4228,7 @@ static void nvme_scan_work(struct work_struct *work) } mutex_lock(&ctrl->scan_lock); - if (nvme_ctrl_limited_cns(ctrl)) { + if (!nvme_id_cns_ok(ctrl, NVME_ID_CNS_NS_ACTIVE_LIST)) { nvme_scan_ns_sequential(ctrl); } else { /* diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index b9b79ccfabf8..a96976b22fa7 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -421,10 +421,13 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, struct io_uring_cmd *ioucmd = req->end_io_data; struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); - if (nvme_req(req)->flags & NVME_REQ_CANCELLED) + if (nvme_req(req)->flags & NVME_REQ_CANCELLED) { pdu->status = -EINTR; - else + } else { pdu->status = nvme_req(req)->status; + if (!pdu->status) + pdu->status = blk_status_to_errno(err); + } pdu->result = le64_to_cpu(nvme_req(req)->result.u64); /* diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index 29f8639cfe7f..b47d675232d2 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -115,6 +115,7 @@ int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id) pr_debug("%s: ctrl %d failed to generate private key, err %d\n", __func__, ctrl->cntlid, ret); kfree_sensitive(ctrl->dh_key); + ctrl->dh_key = NULL; return ret; } ctrl->dh_keysize = crypto_kpp_maxsize(ctrl->dh_tfm); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 7d85c04fbba2..225a6cd2e9ca 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1067,8 +1067,15 @@ static void pci_std_enable_acs(struct pci_dev *dev, struct pci_acs *caps) static void pci_enable_acs(struct pci_dev *dev) { struct pci_acs caps; + bool enable_acs = false; int pos; + /* If an iommu is present we start with kernel default caps */ + if (pci_acs_enable) { + if (pci_dev_specific_enable_acs(dev)) + enable_acs = true; + } + pos = dev->acs_cap; if (!pos) return; @@ -1077,11 +1084,8 @@ static void pci_enable_acs(struct pci_dev *dev) pci_read_config_word(dev, pos + PCI_ACS_CTRL, &caps.ctrl); caps.fw_ctrl = caps.ctrl; - /* If an iommu is present we start with kernel default caps */ - if (pci_acs_enable) { - if (pci_dev_specific_enable_acs(dev)) - pci_std_enable_acs(dev, &caps); - } + if (enable_acs) + pci_std_enable_acs(dev, &caps); /* * Always apply caps from the command line, even if there is no iommu. diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 4f68414c3086..f1615805f5b0 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -3105,7 +3105,9 @@ int pci_host_probe(struct pci_host_bridge *bridge) list_for_each_entry(child, &bus->children, node) pcie_bus_configure_settings(child); + pci_lock_rescan_remove(); pci_bus_add_devices(bus); + pci_unlock_rescan_remove(); return 0; } EXPORT_SYMBOL_GPL(pci_host_probe); diff --git a/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c b/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c index a23a4312574b..0e6bd47671c2 100644 --- a/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c +++ b/drivers/pci/pwrctl/pci-pwrctl-pwrseq.c @@ -6,9 +6,9 @@ #include <linux/device.h> #include <linux/mod_devicetable.h> #include <linux/module.h> -#include <linux/of.h> #include <linux/pci-pwrctl.h> #include <linux/platform_device.h> +#include <linux/property.h> #include <linux/pwrseq/consumer.h> #include <linux/slab.h> #include <linux/types.h> @@ -18,6 +18,40 @@ struct pci_pwrctl_pwrseq_data { struct pwrseq_desc *pwrseq; }; +struct pci_pwrctl_pwrseq_pdata { + const char *target; + /* + * Called before doing anything else to perform device-specific + * verification between requesting the power sequencing handle. + */ + int (*validate_device)(struct device *dev); +}; + +static int pci_pwrctl_pwrseq_qcm_wcn_validate_device(struct device *dev) +{ + /* + * Old device trees for some platforms already define wifi nodes for + * the WCN family of chips since before power sequencing was added + * upstream. + * + * These nodes don't consume the regulator outputs from the PMU, and + * if we allow this driver to bind to one of such "incomplete" nodes, + * we'll see a kernel log error about the indefinite probe deferral. + * + * Check the existence of the regulator supply that exists on all + * WCN models before moving forward. + */ + if (!device_property_present(dev, "vddaon-supply")) + return -ENODEV; + + return 0; +} + +static const struct pci_pwrctl_pwrseq_pdata pci_pwrctl_pwrseq_qcom_wcn_pdata = { + .target = "wlan", + .validate_device = pci_pwrctl_pwrseq_qcm_wcn_validate_device, +}; + static void devm_pci_pwrctl_pwrseq_power_off(void *data) { struct pwrseq_desc *pwrseq = data; @@ -27,15 +61,26 @@ static void devm_pci_pwrctl_pwrseq_power_off(void *data) static int pci_pwrctl_pwrseq_probe(struct platform_device *pdev) { + const struct pci_pwrctl_pwrseq_pdata *pdata; struct pci_pwrctl_pwrseq_data *data; struct device *dev = &pdev->dev; int ret; + pdata = device_get_match_data(dev); + if (!pdata || !pdata->target) + return -EINVAL; + + if (pdata->validate_device) { + ret = pdata->validate_device(dev); + if (ret) + return ret; + } + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; - data->pwrseq = devm_pwrseq_get(dev, of_device_get_match_data(dev)); + data->pwrseq = devm_pwrseq_get(dev, pdata->target); if (IS_ERR(data->pwrseq)) return dev_err_probe(dev, PTR_ERR(data->pwrseq), "Failed to get the power sequencer\n"); @@ -64,17 +109,17 @@ static const struct of_device_id pci_pwrctl_pwrseq_of_match[] = { { /* ATH11K in QCA6390 package. */ .compatible = "pci17cb,1101", - .data = "wlan", + .data = &pci_pwrctl_pwrseq_qcom_wcn_pdata, }, { /* ATH11K in WCN6855 package. */ .compatible = "pci17cb,1103", - .data = "wlan", + .data = &pci_pwrctl_pwrseq_qcom_wcn_pdata, }, { /* ATH12K in WCN7850 package. */ .compatible = "pci17cb,1107", - .data = "wlan", + .data = &pci_pwrctl_pwrseq_qcom_wcn_pdata, }, { } }; diff --git a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c index 4c10cafded4e..950b7ae1d1a8 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c +++ b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c @@ -153,7 +153,9 @@ static void xhci_soft_reset(struct brcm_usb_init_params *params, } else { USB_CTRL_SET(ctrl, USB_PM, XHC_SOFT_RESETB); /* Required for COMMONONN to be set */ - USB_XHCI_GBL_UNSET(xhci_gbl, GUSB2PHYCFG, U2_FREECLK_EXISTS); + if (params->supported_port_modes != USB_CTLR_MODE_DRD) + USB_XHCI_GBL_UNSET(xhci_gbl, GUSB2PHYCFG, + U2_FREECLK_EXISTS); } } @@ -328,8 +330,12 @@ static void usb_init_common_7216(struct brcm_usb_init_params *params) /* 1 millisecond - for USB clocks to settle down */ usleep_range(1000, 2000); - /* Disable PHY when port is suspended */ - USB_CTRL_SET(ctrl, P0_U2PHY_CFG1, COMMONONN); + /* + * Disable PHY when port is suspended + * Does not work in DRD mode + */ + if (params->supported_port_modes != USB_CTLR_MODE_DRD) + USB_CTRL_SET(ctrl, P0_U2PHY_CFG1, COMMONONN); usb_wake_enable_7216(params, false); usb_init_common(params); diff --git a/drivers/phy/broadcom/phy-brcm-usb-init.c b/drivers/phy/broadcom/phy-brcm-usb-init.c index 39536b6d96a9..5ebb3a616115 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init.c +++ b/drivers/phy/broadcom/phy-brcm-usb-init.c @@ -220,6 +220,8 @@ usb_reg_bits_map_table[BRCM_FAMILY_COUNT][USB_CTRL_SELECTOR_COUNT] = { 0, /* USB_CTRL_SETUP_SCB2_EN_MASK */ 0, /* USB_CTRL_SETUP_SS_EHCI64BIT_EN_MASK */ 0, /* USB_CTRL_SETUP_STRAP_IPP_SEL_MASK */ + 0, /* USB_CTRL_SETUP_OC3_DISABLE_PORT0_MASK */ + 0, /* USB_CTRL_SETUP_OC3_DISABLE_PORT1_MASK */ 0, /* USB_CTRL_SETUP_OC3_DISABLE_MASK */ 0, /* USB_CTRL_PLL_CTL_PLL_IDDQ_PWRDN_MASK */ 0, /* USB_CTRL_USB_PM_BDC_SOFT_RESETB_MASK */ diff --git a/drivers/phy/cadence/phy-cadence-sierra.c b/drivers/phy/cadence/phy-cadence-sierra.c index aeec6eb6be23..dfc4f55d112e 100644 --- a/drivers/phy/cadence/phy-cadence-sierra.c +++ b/drivers/phy/cadence/phy-cadence-sierra.c @@ -174,8 +174,9 @@ #define SIERRA_DEQ_TAU_CTRL1_SLOW_MAINT_PREG 0x150 #define SIERRA_DEQ_TAU_CTRL2_PREG 0x151 #define SIERRA_DEQ_TAU_CTRL3_PREG 0x152 -#define SIERRA_DEQ_OPENEYE_CTRL_PREG 0x158 +#define SIERRA_DEQ_TAU_EPIOFFSET_MODE_PREG 0x158 #define SIERRA_DEQ_CONCUR_EPIOFFSET_MODE_PREG 0x159 +#define SIERRA_DEQ_OPENEYE_CTRL_PREG 0x15C #define SIERRA_DEQ_PICTRL_PREG 0x161 #define SIERRA_CPICAL_TMRVAL_MODE1_PREG 0x170 #define SIERRA_CPICAL_TMRVAL_MODE0_PREG 0x171 @@ -1733,7 +1734,7 @@ static const struct cdns_reg_pairs ml_pcie_100_no_ssc_ln_regs[] = { {0x3C0F, SIERRA_DEQ_TAU_CTRL1_SLOW_MAINT_PREG}, {0x1C0C, SIERRA_DEQ_TAU_CTRL2_PREG}, {0x0100, SIERRA_DEQ_TAU_CTRL3_PREG}, - {0x5E82, SIERRA_DEQ_OPENEYE_CTRL_PREG}, + {0x5E82, SIERRA_DEQ_TAU_EPIOFFSET_MODE_PREG}, {0x002B, SIERRA_CPI_TRIM_PREG}, {0x0003, SIERRA_EPI_CTRL_PREG}, {0x803F, SIERRA_SDFILT_H2L_A_PREG}, @@ -1797,7 +1798,7 @@ static const struct cdns_reg_pairs ti_ml_pcie_100_no_ssc_ln_regs[] = { {0x3C0F, SIERRA_DEQ_TAU_CTRL1_SLOW_MAINT_PREG}, {0x1C0C, SIERRA_DEQ_TAU_CTRL2_PREG}, {0x0100, SIERRA_DEQ_TAU_CTRL3_PREG}, - {0x5E82, SIERRA_DEQ_OPENEYE_CTRL_PREG}, + {0x5E82, SIERRA_DEQ_TAU_EPIOFFSET_MODE_PREG}, {0x002B, SIERRA_CPI_TRIM_PREG}, {0x0003, SIERRA_EPI_CTRL_PREG}, {0x803F, SIERRA_SDFILT_H2L_A_PREG}, @@ -1874,7 +1875,7 @@ static const struct cdns_reg_pairs ml_pcie_100_int_ssc_ln_regs[] = { {0x3C0F, SIERRA_DEQ_TAU_CTRL1_SLOW_MAINT_PREG}, {0x1C0C, SIERRA_DEQ_TAU_CTRL2_PREG}, {0x0100, SIERRA_DEQ_TAU_CTRL3_PREG}, - {0x5E82, SIERRA_DEQ_OPENEYE_CTRL_PREG}, + {0x5E82, SIERRA_DEQ_TAU_EPIOFFSET_MODE_PREG}, {0x002B, SIERRA_CPI_TRIM_PREG}, {0x0003, SIERRA_EPI_CTRL_PREG}, {0x803F, SIERRA_SDFILT_H2L_A_PREG}, @@ -1941,7 +1942,7 @@ static const struct cdns_reg_pairs ti_ml_pcie_100_int_ssc_ln_regs[] = { {0x3C0F, SIERRA_DEQ_TAU_CTRL1_SLOW_MAINT_PREG}, {0x1C0C, SIERRA_DEQ_TAU_CTRL2_PREG}, {0x0100, SIERRA_DEQ_TAU_CTRL3_PREG}, - {0x5E82, SIERRA_DEQ_OPENEYE_CTRL_PREG}, + {0x5E82, SIERRA_DEQ_TAU_EPIOFFSET_MODE_PREG}, {0x002B, SIERRA_CPI_TRIM_PREG}, {0x0003, SIERRA_EPI_CTRL_PREG}, {0x803F, SIERRA_SDFILT_H2L_A_PREG}, @@ -2012,7 +2013,7 @@ static const struct cdns_reg_pairs ml_pcie_100_ext_ssc_ln_regs[] = { {0x3C0F, SIERRA_DEQ_TAU_CTRL1_SLOW_MAINT_PREG}, {0x1C0C, SIERRA_DEQ_TAU_CTRL2_PREG}, {0x0100, SIERRA_DEQ_TAU_CTRL3_PREG}, - {0x5E82, SIERRA_DEQ_OPENEYE_CTRL_PREG}, + {0x5E82, SIERRA_DEQ_TAU_EPIOFFSET_MODE_PREG}, {0x002B, SIERRA_CPI_TRIM_PREG}, {0x0003, SIERRA_EPI_CTRL_PREG}, {0x803F, SIERRA_SDFILT_H2L_A_PREG}, @@ -2079,7 +2080,7 @@ static const struct cdns_reg_pairs ti_ml_pcie_100_ext_ssc_ln_regs[] = { {0x3C0F, SIERRA_DEQ_TAU_CTRL1_SLOW_MAINT_PREG}, {0x1C0C, SIERRA_DEQ_TAU_CTRL2_PREG}, {0x0100, SIERRA_DEQ_TAU_CTRL3_PREG}, - {0x5E82, SIERRA_DEQ_OPENEYE_CTRL_PREG}, + {0x5E82, SIERRA_DEQ_TAU_EPIOFFSET_MODE_PREG}, {0x002B, SIERRA_CPI_TRIM_PREG}, {0x0003, SIERRA_EPI_CTRL_PREG}, {0x803F, SIERRA_SDFILT_H2L_A_PREG}, @@ -2140,7 +2141,7 @@ static const struct cdns_reg_pairs cdns_pcie_ln_regs_no_ssc[] = { {0x3C0F, SIERRA_DEQ_TAU_CTRL1_SLOW_MAINT_PREG}, {0x1C0C, SIERRA_DEQ_TAU_CTRL2_PREG}, {0x0100, SIERRA_DEQ_TAU_CTRL3_PREG}, - {0x5E82, SIERRA_DEQ_OPENEYE_CTRL_PREG}, + {0x5E82, SIERRA_DEQ_TAU_EPIOFFSET_MODE_PREG}, {0x002B, SIERRA_CPI_TRIM_PREG}, {0x0003, SIERRA_EPI_CTRL_PREG}, {0x803F, SIERRA_SDFILT_H2L_A_PREG}, @@ -2215,7 +2216,7 @@ static const struct cdns_reg_pairs cdns_pcie_ln_regs_int_ssc[] = { {0x3C0F, SIERRA_DEQ_TAU_CTRL1_SLOW_MAINT_PREG}, {0x1C0C, SIERRA_DEQ_TAU_CTRL2_PREG}, {0x0100, SIERRA_DEQ_TAU_CTRL3_PREG}, - {0x5E82, SIERRA_DEQ_OPENEYE_CTRL_PREG}, + {0x5E82, SIERRA_DEQ_TAU_EPIOFFSET_MODE_PREG}, {0x002B, SIERRA_CPI_TRIM_PREG}, {0x0003, SIERRA_EPI_CTRL_PREG}, {0x803F, SIERRA_SDFILT_H2L_A_PREG}, @@ -2284,7 +2285,7 @@ static const struct cdns_reg_pairs cdns_pcie_ln_regs_ext_ssc[] = { {0x3C0F, SIERRA_DEQ_TAU_CTRL1_SLOW_MAINT_PREG}, {0x1C0C, SIERRA_DEQ_TAU_CTRL2_PREG}, {0x0100, SIERRA_DEQ_TAU_CTRL3_PREG}, - {0x5E82, SIERRA_DEQ_OPENEYE_CTRL_PREG}, + {0x5E82, SIERRA_DEQ_TAU_EPIOFFSET_MODE_PREG}, {0x002B, SIERRA_CPI_TRIM_PREG}, {0x0003, SIERRA_EPI_CTRL_PREG}, {0x803F, SIERRA_SDFILT_H2L_A_PREG}, diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c index 11fcb1867118..e98361dcdead 100644 --- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c +++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c @@ -141,11 +141,6 @@ static int imx8_pcie_phy_power_on(struct phy *phy) IMX8MM_GPR_PCIE_REF_CLK_PLL); usleep_range(100, 200); - /* Do the PHY common block reset */ - regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, - IMX8MM_GPR_PCIE_CMN_RST, - IMX8MM_GPR_PCIE_CMN_RST); - switch (imx8_phy->drvdata->variant) { case IMX8MP: reset_control_deassert(imx8_phy->perst); @@ -156,6 +151,11 @@ static int imx8_pcie_phy_power_on(struct phy *phy) break; } + /* Do the PHY common block reset */ + regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14, + IMX8MM_GPR_PCIE_CMN_RST, + IMX8MM_GPR_PCIE_CMN_RST); + /* Polling to check the phy is ready or not. */ ret = readl_poll_timeout(imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG075, val, val == ANA_PLL_DONE, 10, 20000); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index a8adc3214bfe..643045c9024e 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -3673,6 +3673,7 @@ static int qmp_combo_probe(struct platform_device *pdev) return -ENOMEM; qmp->dev = dev; + dev_set_drvdata(dev, qmp); qmp->orientation = TYPEC_ORIENTATION_NORMAL; @@ -3749,8 +3750,6 @@ static int qmp_combo_probe(struct platform_device *pdev) phy_set_drvdata(qmp->dp_phy, qmp); - dev_set_drvdata(dev, qmp); - if (usb_np == dev->of_node) phy_provider = devm_of_phy_provider_register(dev, qmp_combo_phy_xlate); else diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c index f71787fb4d7e..36aaac34e6c6 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c @@ -3661,8 +3661,8 @@ static const struct qmp_phy_cfg x1e80100_qmp_gen4x2_pciephy_cfg = { .reset_list = sdm845_pciephy_reset_l, .num_resets = ARRAY_SIZE(sdm845_pciephy_reset_l), - .vreg_list = sm8550_qmp_phy_vreg_l, - .num_vregs = ARRAY_SIZE(sm8550_qmp_phy_vreg_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), .regs = pciephy_v6_regs_layout, .pwrdn_ctrl = SW_PWRDN | REFCLK_DRV_DSBL, @@ -3695,8 +3695,8 @@ static const struct qmp_phy_cfg x1e80100_qmp_gen4x4_pciephy_cfg = { .reset_list = sdm845_pciephy_reset_l, .num_resets = ARRAY_SIZE(sdm845_pciephy_reset_l), - .vreg_list = sm8550_qmp_phy_vreg_l, - .num_vregs = ARRAY_SIZE(sm8550_qmp_phy_vreg_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), .regs = pciephy_v6_regs_layout, .pwrdn_ctrl = SW_PWRDN | REFCLK_DRV_DSBL, diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb-legacy.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb-legacy.c index 6d0ba39c1943..8bf951b0490c 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usb-legacy.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb-legacy.c @@ -1248,6 +1248,7 @@ static int qmp_usb_legacy_probe(struct platform_device *pdev) return -ENOMEM; qmp->dev = dev; + dev_set_drvdata(dev, qmp); qmp->cfg = of_device_get_match_data(dev); if (!qmp->cfg) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c index 2fd49355aa37..1246d3bc8b92 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c @@ -2179,6 +2179,7 @@ static int qmp_usb_probe(struct platform_device *pdev) return -ENOMEM; qmp->dev = dev; + dev_set_drvdata(dev, qmp); qmp->cfg = of_device_get_match_data(dev); if (!qmp->cfg) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usbc.c b/drivers/phy/qualcomm/phy-qcom-qmp-usbc.c index d4fa1063ea61..cf12a6f12134 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usbc.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usbc.c @@ -1050,6 +1050,7 @@ static int qmp_usbc_probe(struct platform_device *pdev) return -ENOMEM; qmp->dev = dev; + dev_set_drvdata(dev, qmp); qmp->orientation = TYPEC_ORIENTATION_NORMAL; diff --git a/drivers/phy/rockchip/Kconfig b/drivers/phy/rockchip/Kconfig index 490263375057..2f7a05f21dc5 100644 --- a/drivers/phy/rockchip/Kconfig +++ b/drivers/phy/rockchip/Kconfig @@ -86,6 +86,7 @@ config PHY_ROCKCHIP_PCIE config PHY_ROCKCHIP_SAMSUNG_HDPTX tristate "Rockchip Samsung HDMI/eDP Combo PHY driver" depends on (ARCH_ROCKCHIP || COMPILE_TEST) && OF + depends on COMMON_CLK depends on HAS_IOMEM select GENERIC_PHY select MFD_SYSCON diff --git a/drivers/phy/starfive/phy-jh7110-usb.c b/drivers/phy/starfive/phy-jh7110-usb.c index 633912f8a05d..cb5454fbe2c8 100644 --- a/drivers/phy/starfive/phy-jh7110-usb.c +++ b/drivers/phy/starfive/phy-jh7110-usb.c @@ -10,18 +10,24 @@ #include <linux/clk.h> #include <linux/err.h> #include <linux/io.h> +#include <linux/mfd/syscon.h> #include <linux/module.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> +#include <linux/regmap.h> #include <linux/usb/of.h> #define USB_125M_CLK_RATE 125000000 #define USB_LS_KEEPALIVE_OFF 0x4 #define USB_LS_KEEPALIVE_ENABLE BIT(4) +#define USB_PDRSTN_SPLIT BIT(17) +#define SYSCON_USB_SPLIT_OFFSET 0x18 + struct jh7110_usb2_phy { struct phy *phy; void __iomem *regs; + struct regmap *sys_syscon; struct clk *usb_125m_clk; struct clk *app_125m; enum phy_mode mode; @@ -61,6 +67,10 @@ static int usb2_phy_set_mode(struct phy *_phy, usb2_set_ls_keepalive(phy, (mode != PHY_MODE_USB_DEVICE)); } + /* Connect usb 2.0 phy mode */ + regmap_update_bits(phy->sys_syscon, SYSCON_USB_SPLIT_OFFSET, + USB_PDRSTN_SPLIT, USB_PDRSTN_SPLIT); + return 0; } @@ -129,6 +139,12 @@ static int jh7110_usb_phy_probe(struct platform_device *pdev) phy_set_drvdata(phy->phy, phy); phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); + phy->sys_syscon = + syscon_regmap_lookup_by_compatible("starfive,jh7110-sys-syscon"); + if (IS_ERR(phy->sys_syscon)) + return dev_err_probe(dev, PTR_ERR(phy->sys_syscon), + "Failed to get sys-syscon\n"); + return PTR_ERR_OR_ZERO(phy_provider); } diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index cfdb54b6070a..342f5ccf611d 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -699,6 +699,8 @@ static int tegra_xusb_setup_usb_role_switch(struct tegra_xusb_port *port) return -ENOMEM; lane = tegra_xusb_find_lane(port->padctl, "usb2", port->index); + if (IS_ERR(lane)) + return PTR_ERR(lane); /* * Assign phy dev to usb-phy dev. Host/device drivers can use phy diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c index a6c0c5607ffd..c6e846d385d2 100644 --- a/drivers/phy/ti/phy-j721e-wiz.c +++ b/drivers/phy/ti/phy-j721e-wiz.c @@ -450,8 +450,8 @@ static int wiz_mode_select(struct wiz *wiz) } else if (wiz->lane_phy_type[i] == PHY_TYPE_USXGMII) { ret = regmap_field_write(wiz->p0_mac_src_sel[i], 0x3); ret = regmap_field_write(wiz->p0_rxfclk_sel[i], 0x3); - ret = regmap_field_write(wiz->p0_refclk_sel[i], 0x3); - mode = LANE_MODE_GEN1; + ret = regmap_field_write(wiz->p0_refclk_sel[i], 0x2); + mode = LANE_MODE_GEN2; } else { continue; } diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index bbb8edb62e00..5669f94c3d06 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -998,6 +998,11 @@ static int amd_pmc_s2d_init(struct amd_pmc_dev *dev) amd_pmc_send_cmd(dev, S2D_PHYS_ADDR_LOW, &phys_addr_low, dev->s2d_msg_id, true); amd_pmc_send_cmd(dev, S2D_PHYS_ADDR_HIGH, &phys_addr_hi, dev->s2d_msg_id, true); + if (!phys_addr_hi && !phys_addr_low) { + dev_err(dev->dev, "STB is not enabled on the system; disable enable_stb or contact system vendor\n"); + return -EINVAL; + } + stb_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low); /* Clear msg_port for other SMU operation */ diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index d6af0ca036f1..347bb43a5f2b 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -261,6 +261,7 @@ int amd_pmf_set_dram_addr(struct amd_pmf_dev *dev, bool alloc_buffer) dev->mtable_size = sizeof(dev->m_table); break; case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT: + case PCI_DEVICE_ID_AMD_1AH_M60H_ROOT: dev->mtable_size = sizeof(dev->m_table_v2); break; default: diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c index b5183969f9bf..06226eb0eab3 100644 --- a/drivers/platform/x86/amd/pmf/spc.c +++ b/drivers/platform/x86/amd/pmf/spc.c @@ -86,6 +86,7 @@ static void amd_pmf_get_smu_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_ta ARRAY_SIZE(dev->m_table.avg_core_c0residency), in); break; case PCI_DEVICE_ID_AMD_1AH_M20H_ROOT: + case PCI_DEVICE_ID_AMD_1AH_M60H_ROOT: memcpy(&dev->m_table_v2, dev->buf, dev->mtable_size); in->ev_info.socket_power = dev->m_table_v2.apu_power + dev->m_table_v2.dgpu_power; in->ev_info.skin_temperature = dev->m_table_v2.skin_temp; diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 7a48220b4f5a..abdca3f05c5c 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -3908,6 +3908,16 @@ static int platform_profile_setup(struct asus_wmi *asus) if (!asus->throttle_thermal_policy_dev) return 0; + /* + * We need to set the default thermal profile during probe or otherwise + * the system will often remain in silent mode, causing low performance. + */ + err = throttle_thermal_policy_set_default(asus); + if (err < 0) { + pr_warn("Failed to set default thermal profile\n"); + return err; + } + dev_info(dev, "Using throttle_thermal_policy for platform_profile support\n"); asus->platform_profile_handler.profile_get = asus_wmi_platform_profile_get; diff --git a/drivers/platform/x86/dell/dell-smbios-base.c b/drivers/platform/x86/dell/dell-smbios-base.c index 73e41eb69cb5..01c72b91a50d 100644 --- a/drivers/platform/x86/dell/dell-smbios-base.c +++ b/drivers/platform/x86/dell/dell-smbios-base.c @@ -576,6 +576,7 @@ static int __init dell_smbios_init(void) int ret, wmi, smm; if (!dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "Dell System", NULL) && + !dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "Alienware", NULL) && !dmi_find_device(DMI_DEV_TYPE_OEM_STRING, "www.dell.com", NULL)) { pr_err("Unable to run on non-Dell system\n"); return -ENODEV; diff --git a/drivers/platform/x86/dell/dell-wmi-base.c b/drivers/platform/x86/dell/dell-wmi-base.c index 502783a7adb1..841a5414d28a 100644 --- a/drivers/platform/x86/dell/dell-wmi-base.c +++ b/drivers/platform/x86/dell/dell-wmi-base.c @@ -80,6 +80,12 @@ static const struct dmi_system_id dell_wmi_smbios_list[] __initconst = { static const struct key_entry dell_wmi_keymap_type_0000[] = { { KE_IGNORE, 0x003a, { KEY_CAPSLOCK } }, + /* Meta key lock */ + { KE_IGNORE, 0xe000, { KEY_RIGHTMETA } }, + + /* Meta key unlock */ + { KE_IGNORE, 0xe001, { KEY_RIGHTMETA } }, + /* Key code is followed by brightness level */ { KE_KEY, 0xe005, { KEY_BRIGHTNESSDOWN } }, { KE_KEY, 0xe006, { KEY_BRIGHTNESSUP } }, @@ -264,6 +270,15 @@ static const struct key_entry dell_wmi_keymap_type_0010[] = { /*Speaker Mute*/ { KE_KEY, 0x109, { KEY_MUTE} }, + /* S2Idle screen off */ + { KE_IGNORE, 0x120, { KEY_RESERVED }}, + + /* Leaving S4 or S2Idle suspend */ + { KE_IGNORE, 0x130, { KEY_RESERVED }}, + + /* Entering S2Idle suspend */ + { KE_IGNORE, 0x140, { KEY_RESERVED }}, + /* Mic mute */ { KE_KEY, 0x150, { KEY_MICMUTE } }, diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index c64dfc56651d..c908f52ed717 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1294,6 +1294,9 @@ static const struct key_entry ideapad_keymap[] = { { KE_KEY, 0x27 | IDEAPAD_WMI_KEY, { KEY_HELP } }, /* Refresh Rate Toggle */ { KE_KEY, 0x0a | IDEAPAD_WMI_KEY, { KEY_REFRESH_RATE_TOGGLE } }, + /* Specific to some newer models */ + { KE_KEY, 0x3e | IDEAPAD_WMI_KEY, { KEY_MICMUTE } }, + { KE_KEY, 0x3f | IDEAPAD_WMI_KEY, { KEY_RFKILL } }, { KE_END }, }; diff --git a/drivers/platform/x86/intel/pmc/adl.c b/drivers/platform/x86/intel/pmc/adl.c index 9d9c07f44ff6..e7878558fd90 100644 --- a/drivers/platform/x86/intel/pmc/adl.c +++ b/drivers/platform/x86/intel/pmc/adl.c @@ -295,8 +295,6 @@ const struct pmc_reg_map adl_reg_map = { .ppfear_buckets = CNP_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT, - .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, - .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .ltr_ignore_max = ADL_NUM_IP_IGN_ALLOWED, .lpm_num_modes = ADL_LPM_NUM_MODES, .lpm_num_maps = ADL_LPM_NUM_MAPS, diff --git a/drivers/platform/x86/intel/pmc/cnp.c b/drivers/platform/x86/intel/pmc/cnp.c index 513c02670c5a..dd72974bf71e 100644 --- a/drivers/platform/x86/intel/pmc/cnp.c +++ b/drivers/platform/x86/intel/pmc/cnp.c @@ -200,8 +200,6 @@ const struct pmc_reg_map cnp_reg_map = { .ppfear_buckets = CNP_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT, - .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, - .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .ltr_ignore_max = CNP_NUM_IP_IGN_ALLOWED, .etr3_offset = ETR3_OFFSET, }; diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index ecb47f8b4f83..4e9c8c96c8cc 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -11,7 +11,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/acpi_pmtmr.h> #include <linux/bitfield.h> #include <linux/debugfs.h> #include <linux/delay.h> @@ -1258,39 +1257,6 @@ static bool pmc_core_is_pson_residency_enabled(struct pmc_dev *pmcdev) return val == 1; } -/* - * Enable or disable ACPI PM Timer - * - * This function is intended to be a callback for ACPI PM suspend/resume event. - * The ACPI PM Timer is enabled on resume only if it was enabled during suspend. - */ -static void pmc_core_acpi_pm_timer_suspend_resume(void *data, bool suspend) -{ - struct pmc_dev *pmcdev = data; - struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; - const struct pmc_reg_map *map = pmc->map; - bool enabled; - u32 reg; - - if (!map->acpi_pm_tmr_ctl_offset) - return; - - guard(mutex)(&pmcdev->lock); - - if (!suspend && !pmcdev->enable_acpi_pm_timer_on_resume) - return; - - reg = pmc_core_reg_read(pmc, map->acpi_pm_tmr_ctl_offset); - enabled = !(reg & map->acpi_pm_tmr_disable_bit); - if (suspend) - reg |= map->acpi_pm_tmr_disable_bit; - else - reg &= ~map->acpi_pm_tmr_disable_bit; - pmc_core_reg_write(pmc, map->acpi_pm_tmr_ctl_offset, reg); - - pmcdev->enable_acpi_pm_timer_on_resume = suspend && enabled; -} - static void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev) { debugfs_remove_recursive(pmcdev->dbgfs_dir); @@ -1486,7 +1452,6 @@ static int pmc_core_probe(struct platform_device *pdev) struct pmc_dev *pmcdev; const struct x86_cpu_id *cpu_id; int (*core_init)(struct pmc_dev *pmcdev); - const struct pmc_reg_map *map; struct pmc *primary_pmc; int ret; @@ -1545,11 +1510,6 @@ static int pmc_core_probe(struct platform_device *pdev) pm_report_max_hw_sleep(FIELD_MAX(SLP_S0_RES_COUNTER_MASK) * pmc_core_adjust_slp_s0_step(primary_pmc, 1)); - map = primary_pmc->map; - if (map->acpi_pm_tmr_ctl_offset) - acpi_pmtmr_register_suspend_resume_callback(pmc_core_acpi_pm_timer_suspend_resume, - pmcdev); - device_initialized = true; dev_info(&pdev->dev, " initialized\n"); @@ -1559,12 +1519,6 @@ static int pmc_core_probe(struct platform_device *pdev) static void pmc_core_remove(struct platform_device *pdev) { struct pmc_dev *pmcdev = platform_get_drvdata(pdev); - const struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; - const struct pmc_reg_map *map = pmc->map; - - if (map->acpi_pm_tmr_ctl_offset) - acpi_pmtmr_unregister_suspend_resume_callback(); - pmc_core_dbgfs_unregister(pmcdev); pmc_core_clean_structure(pdev); } diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h index 75fd593a7b0f..b9d3291d0bf2 100644 --- a/drivers/platform/x86/intel/pmc/core.h +++ b/drivers/platform/x86/intel/pmc/core.h @@ -68,8 +68,6 @@ struct telem_endpoint; #define SPT_PMC_LTR_SCC 0x3A0 #define SPT_PMC_LTR_ISH 0x3A4 -#define SPT_PMC_ACPI_PM_TMR_CTL_OFFSET 0x18FC - /* Sunrise Point: PGD PFET Enable Ack Status Registers */ enum ppfear_regs { SPT_PMC_XRAM_PPFEAR0A = 0x590, @@ -150,8 +148,6 @@ enum ppfear_regs { #define SPT_PMC_VRIC1_SLPS0LVEN BIT(13) #define SPT_PMC_VRIC1_XTALSDQDIS BIT(22) -#define SPT_PMC_BIT_ACPI_PM_TMR_DISABLE BIT(1) - /* Cannonlake Power Management Controller register offsets */ #define CNP_PMC_SLPS0_DBG_OFFSET 0x10B4 #define CNP_PMC_PM_CFG_OFFSET 0x1818 @@ -355,8 +351,6 @@ struct pmc_reg_map { const u8 *lpm_reg_index; const u32 pson_residency_offset; const u32 pson_residency_counter_step; - const u32 acpi_pm_tmr_ctl_offset; - const u32 acpi_pm_tmr_disable_bit; }; /** @@ -432,8 +426,6 @@ struct pmc_dev { u32 die_c6_offset; struct telem_endpoint *punit_ep; struct pmc_info *regmap_list; - - bool enable_acpi_pm_timer_on_resume; }; enum pmc_index { diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c index c259c96b7dfd..8504154b649f 100644 --- a/drivers/platform/x86/intel/pmc/core_ssram.c +++ b/drivers/platform/x86/intel/pmc/core_ssram.c @@ -29,7 +29,7 @@ #define LPM_REG_COUNT 28 #define LPM_MODE_OFFSET 1 -DEFINE_FREE(pmc_core_iounmap, void __iomem *, iounmap(_T)); +DEFINE_FREE(pmc_core_iounmap, void __iomem *, if (_T) iounmap(_T)) static u32 pmc_core_find_guid(struct pmc_info *list, const struct pmc_reg_map *map) { @@ -262,6 +262,8 @@ pmc_core_ssram_get_pmc(struct pmc_dev *pmcdev, int pmc_idx, u32 offset) ssram_base = ssram_pcidev->resource[0].start; tmp_ssram = ioremap(ssram_base, SSRAM_HDR_SIZE); + if (!tmp_ssram) + return -ENOMEM; if (pmc_idx != PMC_IDX_MAIN) { /* diff --git a/drivers/platform/x86/intel/pmc/icl.c b/drivers/platform/x86/intel/pmc/icl.c index cbbd44054468..71b0fd6cb7d8 100644 --- a/drivers/platform/x86/intel/pmc/icl.c +++ b/drivers/platform/x86/intel/pmc/icl.c @@ -46,8 +46,6 @@ const struct pmc_reg_map icl_reg_map = { .ppfear_buckets = ICL_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT, - .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, - .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .ltr_ignore_max = ICL_NUM_IP_IGN_ALLOWED, .etr3_offset = ETR3_OFFSET, }; diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c index 91f2fa728f5c..c7d15d864039 100644 --- a/drivers/platform/x86/intel/pmc/mtl.c +++ b/drivers/platform/x86/intel/pmc/mtl.c @@ -462,8 +462,6 @@ const struct pmc_reg_map mtl_socm_reg_map = { .ppfear_buckets = MTL_SOCM_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT, - .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, - .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .lpm_num_maps = ADL_LPM_NUM_MAPS, .ltr_ignore_max = MTL_SOCM_NUM_IP_IGN_ALLOWED, .lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2, diff --git a/drivers/platform/x86/intel/pmc/tgl.c b/drivers/platform/x86/intel/pmc/tgl.c index 371b4e30f142..e0580de18077 100644 --- a/drivers/platform/x86/intel/pmc/tgl.c +++ b/drivers/platform/x86/intel/pmc/tgl.c @@ -197,8 +197,6 @@ const struct pmc_reg_map tgl_reg_map = { .ppfear_buckets = ICL_PPFEAR_NUM_ENTRIES, .pm_cfg_offset = CNP_PMC_PM_CFG_OFFSET, .pm_read_disable_bit = CNP_PMC_READ_DISABLE_BIT, - .acpi_pm_tmr_ctl_offset = SPT_PMC_ACPI_PM_TMR_CTL_OFFSET, - .acpi_pm_tmr_disable_bit = SPT_PMC_BIT_ACPI_PM_TMR_DISABLE, .ltr_ignore_max = TGL_NUM_IP_IGN_ALLOWED, .lpm_num_maps = TGL_LPM_NUM_MAPS, .lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2, diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 4c1b0553f872..6371a9f765c1 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -7936,6 +7936,7 @@ static u8 fan_control_resume_level; static int fan_watchdog_maxinterval; static bool fan_with_ns_addr; +static bool ecfw_with_fan_dec_rpm; static struct mutex fan_mutex; @@ -8682,7 +8683,11 @@ static ssize_t fan_fan1_input_show(struct device *dev, if (res < 0) return res; - return sysfs_emit(buf, "%u\n", speed); + /* Check for fan speeds displayed in hexadecimal */ + if (!ecfw_with_fan_dec_rpm) + return sysfs_emit(buf, "%u\n", speed); + else + return sysfs_emit(buf, "%x\n", speed); } static DEVICE_ATTR(fan1_input, S_IRUGO, fan_fan1_input_show, NULL); @@ -8699,7 +8704,11 @@ static ssize_t fan_fan2_input_show(struct device *dev, if (res < 0) return res; - return sysfs_emit(buf, "%u\n", speed); + /* Check for fan speeds displayed in hexadecimal */ + if (!ecfw_with_fan_dec_rpm) + return sysfs_emit(buf, "%u\n", speed); + else + return sysfs_emit(buf, "%x\n", speed); } static DEVICE_ATTR(fan2_input, S_IRUGO, fan_fan2_input_show, NULL); @@ -8775,6 +8784,7 @@ static const struct attribute_group fan_driver_attr_group = { #define TPACPI_FAN_2CTL 0x0004 /* selects fan2 control */ #define TPACPI_FAN_NOFAN 0x0008 /* no fan available */ #define TPACPI_FAN_NS 0x0010 /* For EC with non-Standard register addresses */ +#define TPACPI_FAN_DECRPM 0x0020 /* For ECFW's with RPM in register as decimal */ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_QEC_IBM('1', 'Y', TPACPI_FAN_Q1), @@ -8803,6 +8813,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('R', '1', 'D', TPACPI_FAN_NS), /* 11e Gen5 GL-R */ TPACPI_Q_LNV3('R', '0', 'V', TPACPI_FAN_NS), /* 11e Gen5 KL-Y */ TPACPI_Q_LNV3('N', '1', 'O', TPACPI_FAN_NOFAN), /* X1 Tablet (2nd gen) */ + TPACPI_Q_LNV3('R', '0', 'Q', TPACPI_FAN_DECRPM),/* L480 */ }; static int __init fan_init(struct ibm_init_struct *iibm) @@ -8847,6 +8858,13 @@ static int __init fan_init(struct ibm_init_struct *iibm) tp_features.fan_ctrl_status_undef = 1; } + /* Check for the EC/BIOS with RPM reported in decimal*/ + if (quirks & TPACPI_FAN_DECRPM) { + pr_info("ECFW with fan RPM as decimal in EC register\n"); + ecfw_with_fan_dec_rpm = 1; + tp_features.fan_ctrl_status_undef = 1; + } + if (gfan_handle) { /* 570, 600e/x, 770e, 770x */ fan_status_access_mode = TPACPI_FAN_RD_ACPI_GFAN; @@ -9067,7 +9085,11 @@ static int fan_read(struct seq_file *m) if (rc < 0) return rc; - seq_printf(m, "speed:\t\t%d\n", speed); + /* Check for fan speeds displayed in hexadecimal */ + if (!ecfw_with_fan_dec_rpm) + seq_printf(m, "speed:\t\t%d\n", speed); + else + seq_printf(m, "speed:\t\t%x\n", speed); if (fan_status_access_mode == TPACPI_FAN_RD_TPEC_NS) { /* diff --git a/drivers/powercap/dtpm_devfreq.c b/drivers/powercap/dtpm_devfreq.c index f40bce8176df..d1dff6ccab12 100644 --- a/drivers/powercap/dtpm_devfreq.c +++ b/drivers/powercap/dtpm_devfreq.c @@ -178,7 +178,7 @@ static int __dtpm_devfreq_setup(struct devfreq *devfreq, struct dtpm *parent) ret = dev_pm_qos_add_request(dev, &dtpm_devfreq->qos_req, DEV_PM_QOS_MAX_FREQUENCY, PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); - if (ret) { + if (ret < 0) { pr_err("Failed to add QoS request: %d\n", ret); goto out_dtpm_unregister; } diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index e98c9767e0ef..07bf7f9aae01 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -135,12 +135,16 @@ config PTP_1588_CLOCK_VMCLOCK tristate "Virtual machine PTP clock" depends on X86_TSC || ARM_ARCH_TIMER depends on PTP_1588_CLOCK && ACPI && ARCH_SUPPORTS_INT128 - default y + default PTP_1588_CLOCK_KVM help This driver adds support for using a virtual precision clock advertised by the hypervisor. This clock is only useful in virtual machines where such a device is present. + Unlike the KVM virtual PTP clock, the VMCLOCK device offers support + for reliable timekeeping even across live migration. So this driver + is enabled by default whenever the KVM PTP clock is. + To compile this driver as a module, choose M here: the module will be called ptp_vmclock. @@ -237,4 +241,15 @@ config PTP_DFL_TOD To compile this driver as a module, choose M here: the module will be called ptp_dfl_tod. +config PTP_S390 + tristate "S390 PTP driver" + depends on PTP_1588_CLOCK + depends on S390 + help + This driver adds support for S390 time steering via the PtP + interface. This works by adding a in-kernel clock delta value, + which is always added to time values used in the kernel. The PtP + driver provides the raw clock value without the delta to + userspace. That way userspace programs like chrony could steer + the kernel clock. endmenu diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile index 01b5cd91eb61..25f846fe48c9 100644 --- a/drivers/ptp/Makefile +++ b/drivers/ptp/Makefile @@ -22,3 +22,4 @@ obj-$(CONFIG_PTP_1588_CLOCK_MOCK) += ptp_mock.o obj-$(CONFIG_PTP_1588_CLOCK_VMW) += ptp_vmw.o obj-$(CONFIG_PTP_1588_CLOCK_OCP) += ptp_ocp.o obj-$(CONFIG_PTP_DFL_TOD) += ptp_dfl_tod.o +obj-$(CONFIG_PTP_S390) += ptp_s390.o diff --git a/drivers/ptp/ptp_fc3.c b/drivers/ptp/ptp_fc3.c index e14e149b746e..879b82f03535 100644 --- a/drivers/ptp/ptp_fc3.c +++ b/drivers/ptp/ptp_fc3.c @@ -986,11 +986,6 @@ static int idtfc3_probe(struct platform_device *pdev) mutex_unlock(idtfc3->lock); - if (err) { - ptp_clock_unregister(idtfc3->ptp_clock); - return err; - } - platform_set_drvdata(pdev, idtfc3); return 0; diff --git a/drivers/ptp/ptp_pch.c b/drivers/ptp/ptp_pch.c index 33355d5eb033..b8a9a54a176c 100644 --- a/drivers/ptp/ptp_pch.c +++ b/drivers/ptp/ptp_pch.c @@ -462,14 +462,14 @@ pch_probe(struct pci_dev *pdev, const struct pci_device_id *id) return ret; } - ret = pcim_iomap_regions(pdev, BIT(IO_MEM_BAR), "1588_regs"); + /* get the virtual address to the 1588 registers */ + chip->regs = pcim_iomap_region(pdev, IO_MEM_BAR, KBUILD_MODNAME); + ret = PTR_ERR_OR_ZERO(chip->regs); if (ret) { dev_err(&pdev->dev, "could not locate IO memory address\n"); return ret; } - /* get the virtual address to the 1588 registers */ - chip->regs = pcim_iomap_table(pdev)[IO_MEM_BAR]; chip->caps = ptp_pch_caps; chip->ptp_clock = ptp_clock_register(&chip->caps, &pdev->dev); if (IS_ERR(chip->ptp_clock)) diff --git a/drivers/ptp/ptp_s390.c b/drivers/ptp/ptp_s390.c new file mode 100644 index 000000000000..29618eb9bf44 --- /dev/null +++ b/drivers/ptp/ptp_s390.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * s390 PTP clock driver + * + */ + +#include "ptp_private.h" +#include <linux/time.h> +#include <asm/stp.h> + +static struct ptp_clock *ptp_stcke_clock, *ptp_qpt_clock; + +static int ptp_s390_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + return -EOPNOTSUPP; +} + +static int ptp_s390_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + return -EOPNOTSUPP; +} + +static struct timespec64 eitod_to_timespec64(union tod_clock *clk) +{ + return ns_to_timespec64(eitod_to_ns(clk->eitod - TOD_UNIX_EPOCH)); +} + +static struct timespec64 tod_to_timespec64(unsigned long tod) +{ + return ns_to_timespec64(tod_to_ns(tod - TOD_UNIX_EPOCH)); +} + +static int ptp_s390_stcke_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + union tod_clock tod; + + if (!stp_enabled()) + return -EOPNOTSUPP; + + store_tod_clock_ext(&tod); + *ts = eitod_to_timespec64(&tod); + return 0; +} + +static int ptp_s390_qpt_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + unsigned long tod; + + ptff(&tod, sizeof(tod), PTFF_QPT); + *ts = tod_to_timespec64(tod); + return 0; +} + +static int ptp_s390_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + return -EOPNOTSUPP; +} + +static int s390_arch_ptp_get_crosststamp(ktime_t *device_time, + struct system_counterval_t *system_counter, + void *ctx) +{ + union tod_clock clk; + + store_tod_clock_ext(&clk); + *device_time = ns_to_ktime(tod_to_ns(clk.tod - TOD_UNIX_EPOCH)); + system_counter->cycles = clk.tod; + system_counter->cs_id = CSID_S390_TOD; + return 0; +} + +static int ptp_s390_getcrosststamp(struct ptp_clock_info *ptp, + struct system_device_crosststamp *xtstamp) +{ + if (!stp_enabled()) + return -EOPNOTSUPP; + return get_device_system_crosststamp(s390_arch_ptp_get_crosststamp, NULL, NULL, xtstamp); +} + +static struct ptp_clock_info ptp_s390_stcke_info = { + .owner = THIS_MODULE, + .name = "s390 STCKE Clock", + .max_adj = 0, + .adjfine = ptp_s390_adjfine, + .adjtime = ptp_s390_adjtime, + .gettime64 = ptp_s390_stcke_gettime, + .settime64 = ptp_s390_settime, + .getcrosststamp = ptp_s390_getcrosststamp, +}; + +static struct ptp_clock_info ptp_s390_qpt_info = { + .owner = THIS_MODULE, + .name = "s390 Physical Clock", + .max_adj = 0, + .adjfine = ptp_s390_adjfine, + .adjtime = ptp_s390_adjtime, + .gettime64 = ptp_s390_qpt_gettime, + .settime64 = ptp_s390_settime, +}; + +static __init int ptp_s390_init(void) +{ + ptp_stcke_clock = ptp_clock_register(&ptp_s390_stcke_info, NULL); + if (IS_ERR(ptp_stcke_clock)) + return PTR_ERR(ptp_stcke_clock); + + ptp_qpt_clock = ptp_clock_register(&ptp_s390_qpt_info, NULL); + if (IS_ERR(ptp_qpt_clock)) { + ptp_clock_unregister(ptp_stcke_clock); + return PTR_ERR(ptp_qpt_clock); + } + return 0; +} + +static __exit void ptp_s390_exit(void) +{ + ptp_clock_unregister(ptp_qpt_clock); + ptp_clock_unregister(ptp_stcke_clock); +} + +module_init(ptp_s390_init); +module_exit(ptp_s390_exit); + +MODULE_AUTHOR("Sven Schnelle <[email protected]>"); +MODULE_DESCRIPTION("s390 Physical/STCKE Clock PtP Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pwm/pwm-imx-tpm.c b/drivers/pwm/pwm-imx-tpm.c index 96ea343856f0..7ee7b65b9b90 100644 --- a/drivers/pwm/pwm-imx-tpm.c +++ b/drivers/pwm/pwm-imx-tpm.c @@ -106,7 +106,9 @@ static int pwm_imx_tpm_round_state(struct pwm_chip *chip, p->prescale = prescale; period_count = (clock_unit + ((1 << prescale) >> 1)) >> prescale; - p->mod = period_count; + if (period_count == 0) + return -EINVAL; + p->mod = period_count - 1; /* calculate real period HW can support */ tmp = (u64)period_count << prescale; diff --git a/drivers/rpmsg/qcom_glink_native.c b/drivers/rpmsg/qcom_glink_native.c index 0b2f29006908..d3af1dfa3c7d 100644 --- a/drivers/rpmsg/qcom_glink_native.c +++ b/drivers/rpmsg/qcom_glink_native.c @@ -1440,14 +1440,18 @@ static int qcom_glink_request_intent(struct qcom_glink *glink, goto unlock; ret = wait_event_timeout(channel->intent_req_wq, - READ_ONCE(channel->intent_req_result) >= 0 && - READ_ONCE(channel->intent_received), + READ_ONCE(channel->intent_req_result) == 0 || + (READ_ONCE(channel->intent_req_result) > 0 && + READ_ONCE(channel->intent_received)) || + glink->abort_tx, 10 * HZ); if (!ret) { dev_err(glink->dev, "intent request timed out\n"); ret = -ETIMEDOUT; + } else if (glink->abort_tx) { + ret = -ECANCELED; } else { - ret = READ_ONCE(channel->intent_req_result) ? 0 : -ECANCELED; + ret = READ_ONCE(channel->intent_req_result) ? 0 : -EAGAIN; } unlock: diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index de15fc0df104..b52513eeeafa 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -3651,7 +3651,7 @@ static int do_device_access(struct sdeb_store_info *sip, struct scsi_cmnd *scp, enum dma_data_direction dir; struct scsi_data_buffer *sdb = &scp->sdb; u8 *fsp; - int i; + int i, total = 0; /* * Even though reads are inherently atomic (in this driver), we expect @@ -3688,18 +3688,16 @@ static int do_device_access(struct sdeb_store_info *sip, struct scsi_cmnd *scp, fsp + (block * sdebug_sector_size), sdebug_sector_size, sg_skip, do_write); sdeb_data_sector_unlock(sip, do_write); - if (ret != sdebug_sector_size) { - ret += (i * sdebug_sector_size); + total += ret; + if (ret != sdebug_sector_size) break; - } sg_skip += sdebug_sector_size; if (++block >= sdebug_store_sectors) block = 0; } - ret = num * sdebug_sector_size; sdeb_data_unlock(sip, atomic); - return ret; + return total; } /* Returns number of bytes copied or -1 if error. */ diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index b811446e0fa5..0b60ed16297c 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -891,7 +891,7 @@ void dpaa2_io_update_net_dim(struct dpaa2_io *d, __u64 frames, __u64 bytes) d->frames += frames; dim_update_sample(d->event_ctr, d->frames, d->bytes, &dim_sample); - net_dim(&d->rx_dim, dim_sample); + net_dim(&d->rx_dim, &dim_sample); spin_unlock(&d->dim_lock); } diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c index 8fa4ffd3a9b5..28bcc65e91be 100644 --- a/drivers/soc/qcom/llcc-qcom.c +++ b/drivers/soc/qcom/llcc-qcom.c @@ -139,6 +139,7 @@ struct qcom_llcc_config { int size; bool need_llcc_cfg; bool no_edac; + bool irq_configured; }; struct qcom_sct_config { @@ -718,6 +719,7 @@ static const struct qcom_llcc_config x1e80100_cfg[] = { .need_llcc_cfg = true, .reg_offset = llcc_v2_1_reg_offset, .edac_reg_offset = &llcc_v2_1_edac_reg_offset, + .irq_configured = true, }, }; @@ -1345,6 +1347,7 @@ static int qcom_llcc_probe(struct platform_device *pdev) drv_data->cfg = llcc_cfg; drv_data->cfg_size = sz; drv_data->edac_reg_offset = cfg->edac_reg_offset; + drv_data->ecc_irq_configured = cfg->irq_configured; mutex_init(&drv_data->lock); platform_set_drvdata(pdev, drv_data); diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c index 9606222993fd..baa4ac6704a9 100644 --- a/drivers/soc/qcom/pmic_glink.c +++ b/drivers/soc/qcom/pmic_glink.c @@ -4,6 +4,7 @@ * Copyright (c) 2022, Linaro Ltd */ #include <linux/auxiliary_bus.h> +#include <linux/delay.h> #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> @@ -13,6 +14,8 @@ #include <linux/soc/qcom/pmic_glink.h> #include <linux/spinlock.h> +#define PMIC_GLINK_SEND_TIMEOUT (5 * HZ) + enum { PMIC_GLINK_CLIENT_BATT = 0, PMIC_GLINK_CLIENT_ALTMODE, @@ -112,13 +115,29 @@ EXPORT_SYMBOL_GPL(pmic_glink_client_register); int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len) { struct pmic_glink *pg = client->pg; + bool timeout_reached = false; + unsigned long start; int ret; mutex_lock(&pg->state_lock); - if (!pg->ept) + if (!pg->ept) { ret = -ECONNRESET; - else - ret = rpmsg_send(pg->ept, data, len); + } else { + start = jiffies; + for (;;) { + ret = rpmsg_send(pg->ept, data, len); + if (ret != -EAGAIN) + break; + + if (timeout_reached) { + ret = -ETIMEDOUT; + break; + } + + usleep_range(1000, 5000); + timeout_reached = time_after(jiffies, start + PMIC_GLINK_SEND_TIMEOUT); + } + } mutex_unlock(&pg->state_lock); return ret; diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c index 64fc4f41da77..ecfd3da9d5e8 100644 --- a/drivers/soc/qcom/socinfo.c +++ b/drivers/soc/qcom/socinfo.c @@ -786,10 +786,16 @@ static int qcom_socinfo_probe(struct platform_device *pdev) qs->attr.revision = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%u.%u", SOCINFO_MAJOR(le32_to_cpu(info->ver)), SOCINFO_MINOR(le32_to_cpu(info->ver))); - if (offsetof(struct socinfo, serial_num) <= item_size) + if (!qs->attr.soc_id || !qs->attr.revision) + return -ENOMEM; + + if (offsetof(struct socinfo, serial_num) <= item_size) { qs->attr.serial_number = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%u", le32_to_cpu(info->serial_num)); + if (!qs->attr.serial_number) + return -ENOMEM; + } qs->soc_dev = soc_device_register(&qs->attr); if (IS_ERR(qs->soc_dev)) diff --git a/drivers/soundwire/intel_ace2x.c b/drivers/soundwire/intel_ace2x.c index fff312c6968d..4f3dd70d6a1a 100644 --- a/drivers/soundwire/intel_ace2x.c +++ b/drivers/soundwire/intel_ace2x.c @@ -376,11 +376,12 @@ static int intel_hw_params(struct snd_pcm_substream *substream, static int intel_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); struct sdw_cdns *cdns = snd_soc_dai_get_drvdata(dai); struct sdw_intel *sdw = cdns_to_intel(cdns); struct sdw_cdns_dai_runtime *dai_runtime; + struct snd_pcm_hw_params *hw_params; int ch, dir; - int ret = 0; dai_runtime = cdns->dai_runtime_array[dai->id]; if (!dai_runtime) { @@ -389,12 +390,8 @@ static int intel_prepare(struct snd_pcm_substream *substream, return -EIO; } + hw_params = &rtd->dpcm[substream->stream].hw_params; if (dai_runtime->suspended) { - struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); - struct snd_pcm_hw_params *hw_params; - - hw_params = &rtd->dpcm[substream->stream].hw_params; - dai_runtime->suspended = false; /* @@ -415,15 +412,11 @@ static int intel_prepare(struct snd_pcm_substream *substream, /* the SHIM will be configured in the callback functions */ sdw_cdns_config_stream(cdns, ch, dir, dai_runtime->pdi); - - /* Inform DSP about PDI stream number */ - ret = intel_params_stream(sdw, substream, dai, - hw_params, - sdw->instance, - dai_runtime->pdi->intel_alh_id); } - return ret; + /* Inform DSP about PDI stream number */ + return intel_params_stream(sdw, substream, dai, hw_params, sdw->instance, + dai_runtime->pdi->intel_alh_id); } static int diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 191de1917f83..3fa990fb59c7 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -1003,6 +1003,7 @@ static int dspi_setup(struct spi_device *spi) u32 cs_sck_delay = 0, sck_cs_delay = 0; struct fsl_dspi_platform_data *pdata; unsigned char pasc = 0, asc = 0; + struct gpio_desc *gpio_cs; struct chip_data *chip; unsigned long clkrate; bool cs = true; @@ -1077,7 +1078,10 @@ static int dspi_setup(struct spi_device *spi) chip->ctar_val |= SPI_CTAR_LSBFE; } - gpiod_direction_output(spi_get_csgpiod(spi, 0), false); + gpio_cs = spi_get_csgpiod(spi, 0); + if (gpio_cs) + gpiod_direction_output(gpio_cs, false); + dspi_deassert_cs(spi, &cs); spi_set_ctldata(spi, chip); diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c index f6e40f90418f..768d7482102a 100644 --- a/drivers/spi/spi-geni-qcom.c +++ b/drivers/spi/spi-geni-qcom.c @@ -1116,6 +1116,11 @@ static int spi_geni_probe(struct platform_device *pdev) init_completion(&mas->tx_reset_done); init_completion(&mas->rx_reset_done); spin_lock_init(&mas->lock); + + ret = geni_icc_get(&mas->se, NULL); + if (ret) + return ret; + pm_runtime_use_autosuspend(&pdev->dev); pm_runtime_set_autosuspend_delay(&pdev->dev, 250); ret = devm_pm_runtime_enable(dev); @@ -1125,9 +1130,6 @@ static int spi_geni_probe(struct platform_device *pdev) if (device_property_read_bool(&pdev->dev, "spi-slave")) spi->target = true; - ret = geni_icc_get(&mas->se, NULL); - if (ret) - return ret; /* Set the bus quota to a reasonable value for register access */ mas->se.icc_paths[GENI_TO_CORE].avg_bw = Bps_to_icc(CORE_2X_50_MHZ); mas->se.icc_paths[CPU_TO_GENI].avg_bw = GENI_DEFAULT_BW; diff --git a/drivers/spi/spi-mtk-snfi.c b/drivers/spi/spi-mtk-snfi.c index ddd98ddb7913..c5677fd94e5e 100644 --- a/drivers/spi/spi-mtk-snfi.c +++ b/drivers/spi/spi-mtk-snfi.c @@ -1187,7 +1187,7 @@ cleanup: /** * mtk_snand_is_page_ops() - check if the op is a controller supported page op. - * @op spi-mem op to check + * @op: spi-mem op to check * * Check whether op can be executed with read_from_cache or program_load * mode in the controller. diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index 4c4ff074e3f6..fc72a89fb3a7 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -2044,6 +2044,7 @@ static const struct stm32_spi_cfg stm32mp25_spi_cfg = { .baud_rate_div_max = STM32H7_SPI_MBR_DIV_MAX, .has_fifo = true, .prevent_dma_burst = true, + .has_device_mode = true, }; static const struct of_device_id stm32_spi_of_match[] = { diff --git a/drivers/staging/iio/frequency/ad9832.c b/drivers/staging/iio/frequency/ad9832.c index 6c390c4eb26d..492612e8f8ba 100644 --- a/drivers/staging/iio/frequency/ad9832.c +++ b/drivers/staging/iio/frequency/ad9832.c @@ -129,12 +129,15 @@ static unsigned long ad9832_calc_freqreg(unsigned long mclk, unsigned long fout) static int ad9832_write_frequency(struct ad9832_state *st, unsigned int addr, unsigned long fout) { + unsigned long clk_freq; unsigned long regval; - if (fout > (clk_get_rate(st->mclk) / 2)) + clk_freq = clk_get_rate(st->mclk); + + if (!clk_freq || fout > (clk_freq / 2)) return -EINVAL; - regval = ad9832_calc_freqreg(clk_get_rate(st->mclk), fout); + regval = ad9832_calc_freqreg(clk_freq, fout); st->freq_data[0] = cpu_to_be16((AD9832_CMD_FRE8BITSW << CMD_SHIFT) | (addr << ADD_SHIFT) | diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c index 721319329afa..7db9869a9f3f 100644 --- a/drivers/thunderbolt/retimer.c +++ b/drivers/thunderbolt/retimer.c @@ -516,7 +516,7 @@ int tb_retimer_scan(struct tb_port *port, bool add) */ tb_retimer_set_inbound_sbtx(port); - for (i = 1; i <= TB_MAX_RETIMER_INDEX; i++) { + for (max = 1, i = 1; i <= TB_MAX_RETIMER_INDEX; i++) { /* * Last retimer is true only for the last on-board * retimer (the one connected directly to the Type-C @@ -527,9 +527,10 @@ int tb_retimer_scan(struct tb_port *port, bool add) last_idx = i; else if (ret < 0) break; + + max = i; } - max = i; ret = 0; /* Add retimers if they do not exist already */ diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 10e719dd837c..4f777788e917 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -288,6 +288,24 @@ static void tb_increase_tmu_accuracy(struct tb_tunnel *tunnel) device_for_each_child(&sw->dev, NULL, tb_increase_switch_tmu_accuracy); } +static int tb_switch_tmu_hifi_uni_required(struct device *dev, void *not_used) +{ + struct tb_switch *sw = tb_to_switch(dev); + + if (sw && tb_switch_tmu_is_enabled(sw) && + tb_switch_tmu_is_configured(sw, TB_SWITCH_TMU_MODE_HIFI_UNI)) + return 1; + + return device_for_each_child(dev, NULL, + tb_switch_tmu_hifi_uni_required); +} + +static bool tb_tmu_hifi_uni_required(struct tb *tb) +{ + return device_for_each_child(&tb->dev, NULL, + tb_switch_tmu_hifi_uni_required) == 1; +} + static int tb_enable_tmu(struct tb_switch *sw) { int ret; @@ -302,12 +320,30 @@ static int tb_enable_tmu(struct tb_switch *sw) ret = tb_switch_tmu_configure(sw, TB_SWITCH_TMU_MODE_MEDRES_ENHANCED_UNI); if (ret == -EOPNOTSUPP) { - if (tb_switch_clx_is_enabled(sw, TB_CL1)) - ret = tb_switch_tmu_configure(sw, - TB_SWITCH_TMU_MODE_LOWRES); - else - ret = tb_switch_tmu_configure(sw, - TB_SWITCH_TMU_MODE_HIFI_BI); + if (tb_switch_clx_is_enabled(sw, TB_CL1)) { + /* + * Figure out uni-directional HiFi TMU requirements + * currently in the domain. If there are no + * uni-directional HiFi requirements we can put the TMU + * into LowRes mode. + * + * Deliberately skip bi-directional HiFi links + * as these work independently of other links + * (and they do not allow any CL states anyway). + */ + if (tb_tmu_hifi_uni_required(sw->tb)) + ret = tb_switch_tmu_configure(sw, + TB_SWITCH_TMU_MODE_HIFI_UNI); + else + ret = tb_switch_tmu_configure(sw, + TB_SWITCH_TMU_MODE_LOWRES); + } else { + ret = tb_switch_tmu_configure(sw, TB_SWITCH_TMU_MODE_HIFI_BI); + } + + /* If not supported, fallback to bi-directional HiFi */ + if (ret == -EOPNOTSUPP) + ret = tb_switch_tmu_configure(sw, TB_SWITCH_TMU_MODE_HIFI_BI); } if (ret) return ret; diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index a63dcf48e59d..f5846598d80e 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -8219,7 +8219,7 @@ static void ufshcd_update_rtc(struct ufs_hba *hba) err = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR, QUERY_ATTR_IDN_SECONDS_PASSED, 0, 0, &val); - ufshcd_rpm_put_sync(hba); + ufshcd_rpm_put(hba); if (err) dev_err(hba->dev, "%s: Failed to update rtc %d\n", __func__, err); diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c index 21585ed89ef8..03c22114214b 100644 --- a/drivers/usb/core/usb-acpi.c +++ b/drivers/usb/core/usb-acpi.c @@ -170,11 +170,11 @@ static int usb_acpi_add_usb4_devlink(struct usb_device *udev) struct fwnode_handle *nhi_fwnode __free(fwnode_handle) = fwnode_find_reference(dev_fwnode(&port_dev->dev), "usb4-host-interface", 0); - if (IS_ERR(nhi_fwnode)) + if (IS_ERR(nhi_fwnode) || !nhi_fwnode->dev) return 0; link = device_link_add(&port_dev->child->dev, nhi_fwnode->dev, - DL_FLAG_AUTOREMOVE_CONSUMER | + DL_FLAG_STATELESS | DL_FLAG_RPM_ACTIVE | DL_FLAG_PM_RUNTIME); if (!link) { diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c index 68226defdc60..4d73fae80b12 100644 --- a/drivers/usb/dwc2/params.c +++ b/drivers/usb/dwc2/params.c @@ -23,7 +23,6 @@ static void dwc2_set_bcm_params(struct dwc2_hsotg *hsotg) p->max_transfer_size = 65535; p->max_packet_count = 511; p->ahbcfg = 0x10; - p->no_clock_gating = true; } static void dwc2_set_his_params(struct dwc2_hsotg *hsotg) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 7e538194a0a4..cb07cee9ed0c 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -640,7 +640,7 @@ int xhci_pci_common_probe(struct pci_dev *dev, const struct pci_device_id *id) pm_runtime_put_noidle(&dev->dev); if (pci_choose_state(dev, PMSG_SUSPEND) == PCI_D0) - pm_runtime_forbid(&dev->dev); + pm_runtime_get(&dev->dev); else if (xhci->quirks & XHCI_DEFAULT_PM_RUNTIME_ALLOW) pm_runtime_allow(&dev->dev); @@ -683,7 +683,9 @@ void xhci_pci_remove(struct pci_dev *dev) xhci->xhc_state |= XHCI_STATE_REMOVING; - if (xhci->quirks & XHCI_DEFAULT_PM_RUNTIME_ALLOW) + if (pci_choose_state(dev, PMSG_SUSPEND) == PCI_D0) + pm_runtime_put(&dev->dev); + else if (xhci->quirks & XHCI_DEFAULT_PM_RUNTIME_ALLOW) pm_runtime_forbid(&dev->dev); if (xhci->shared_hcd) { diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index b6eb928e260f..928b93ad1ee8 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1718,6 +1718,14 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, trace_xhci_handle_command(xhci->cmd_ring, &cmd_trb->generic); + cmd_comp_code = GET_COMP_CODE(le32_to_cpu(event->status)); + + /* If CMD ring stopped we own the trbs between enqueue and dequeue */ + if (cmd_comp_code == COMP_COMMAND_RING_STOPPED) { + complete_all(&xhci->cmd_ring_stop_completion); + return; + } + cmd_dequeue_dma = xhci_trb_virt_to_dma(xhci->cmd_ring->deq_seg, cmd_trb); /* @@ -1734,14 +1742,6 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, cancel_delayed_work(&xhci->cmd_timer); - cmd_comp_code = GET_COMP_CODE(le32_to_cpu(event->status)); - - /* If CMD ring stopped we own the trbs between enqueue and dequeue */ - if (cmd_comp_code == COMP_COMMAND_RING_STOPPED) { - complete_all(&xhci->cmd_ring_stop_completion); - return; - } - if (cmd->command_trb != xhci->cmd_ring->dequeue) { xhci_err(xhci, "Command completion event does not match command\n"); diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c index 06e0fb23566c..06f789097989 100644 --- a/drivers/usb/phy/phy.c +++ b/drivers/usb/phy/phy.c @@ -628,7 +628,7 @@ void devm_usb_put_phy(struct device *dev, struct usb_phy *phy) { int r; - r = devres_destroy(dev, devm_usb_phy_release, devm_usb_phy_match, phy); + r = devres_release(dev, devm_usb_phy_release, devm_usb_phy_match, phy); dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n"); } EXPORT_SYMBOL_GPL(devm_usb_put_phy); diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index d61b4c74648d..58f40156de56 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -2293,7 +2293,7 @@ void typec_port_register_altmodes(struct typec_port *port, const struct typec_altmode_ops *ops, void *drvdata, struct typec_altmode **altmodes, size_t n) { - struct fwnode_handle *altmodes_node, *child; + struct fwnode_handle *child; struct typec_altmode_desc desc; struct typec_altmode *alt; size_t index = 0; @@ -2301,7 +2301,9 @@ void typec_port_register_altmodes(struct typec_port *port, u32 vdo; int ret; - altmodes_node = device_get_named_child_node(&port->dev, "altmodes"); + struct fwnode_handle *altmodes_node __free(fwnode_handle) = + device_get_named_child_node(&port->dev, "altmodes"); + if (!altmodes_node) return; /* No altmodes specified */ diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c index 501eddb294e4..b80eb2d78d88 100644 --- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c +++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec.c @@ -93,8 +93,10 @@ static int qcom_pmic_typec_probe(struct platform_device *pdev) return -EINVAL; bridge_dev = devm_drm_dp_hpd_bridge_alloc(tcpm->dev, to_of_node(tcpm->tcpc.fwnode)); - if (IS_ERR(bridge_dev)) - return PTR_ERR(bridge_dev); + if (IS_ERR(bridge_dev)) { + ret = PTR_ERR(bridge_dev); + goto fwnode_remove; + } tcpm->tcpm_port = tcpm_register_port(tcpm->dev, &tcpm->tcpc); if (IS_ERR(tcpm->tcpm_port)) { @@ -123,7 +125,7 @@ port_stop: port_unregister: tcpm_unregister_port(tcpm->tcpm_port); fwnode_remove: - fwnode_remove_software_node(tcpm->tcpc.fwnode); + fwnode_handle_put(tcpm->tcpc.fwnode); return ret; } @@ -135,7 +137,7 @@ static void qcom_pmic_typec_remove(struct platform_device *pdev) tcpm->pdphy_stop(tcpm); tcpm->port_stop(tcpm); tcpm_unregister_port(tcpm->tcpm_port); - fwnode_remove_software_node(tcpm->tcpc.fwnode); + fwnode_handle_put(tcpm->tcpc.fwnode); } static const struct pmic_typec_resources pm8150b_typec_res = { diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index fc619478200f..7ae341a40342 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4515,7 +4515,8 @@ static inline enum tcpm_state hard_reset_state(struct tcpm_port *port) return ERROR_RECOVERY; if (port->pwr_role == TYPEC_SOURCE) return SRC_UNATTACHED; - if (port->state == SNK_WAIT_CAPABILITIES_TIMEOUT) + if (port->state == SNK_WAIT_CAPABILITIES || + port->state == SNK_WAIT_CAPABILITIES_TIMEOUT) return SNK_READY; return SNK_UNATTACHED; } @@ -5043,8 +5044,11 @@ static void run_state_machine(struct tcpm_port *port) tcpm_set_state(port, SNK_SOFT_RESET, PD_T_SINK_WAIT_CAP); } else { - tcpm_set_state(port, SNK_WAIT_CAPABILITIES_TIMEOUT, - PD_T_SINK_WAIT_CAP); + if (!port->self_powered) + upcoming_state = SNK_WAIT_CAPABILITIES_TIMEOUT; + else + upcoming_state = hard_reset_state(port); + tcpm_set_state(port, upcoming_state, PD_T_SINK_WAIT_CAP); } break; case SNK_WAIT_CAPABILITIES_TIMEOUT: diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index f16279351db5..9ad37c012189 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1325,7 +1325,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) vqs[VHOST_NET_VQ_RX]); f->private_data = n; - n->pf_cache.va = NULL; + page_frag_cache_init(&n->pf_cache); return 0; } diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index ea36c6956bf3..de035071fedb 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -1236,7 +1236,6 @@ config FB_3DFX_I2C config FB_VOODOO1 tristate "3Dfx Voodoo Graphics (sst1) support" depends on FB && PCI - depends on FB_DEVICE select FB_IOMEM_HELPERS help Say Y here if you have a 3Dfx Voodoo Graphics (Voodoo1/sst1) or @@ -1374,6 +1373,7 @@ config FB_VT8500 config FB_WM8505 bool "Wondermedia WM8xxx-series frame buffer support" depends on (FB = y) && HAS_IOMEM && (ARCH_VT8500 || COMPILE_TEST) + select FB_IOMEM_FOPS select FB_SYS_FILLRECT if (!FB_WMT_GE_ROPS) select FB_SYS_COPYAREA if (!FB_WMT_GE_ROPS) select FB_SYS_IMAGEBLIT @@ -1660,19 +1660,6 @@ config FB_SH7760 and 8, 15 or 16 bpp color; 90 degrees clockwise display rotation for panels <= 320 pixel horizontal resolution. -config FB_DA8XX - tristate "DA8xx/OMAP-L1xx/AM335x Framebuffer support" - depends on FB && HAVE_CLK && HAS_IOMEM - depends on ARCH_DAVINCI_DA8XX || SOC_AM33XX || COMPILE_TEST - select FB_CFB_REV_PIXELS_IN_BYTE - select FB_IOMEM_HELPERS - select FB_MODE_HELPERS - select VIDEOMODE_HELPERS - help - This is the frame buffer device driver for the TI LCD controller - found on DA8xx/OMAP-L1xx/AM335x SoCs. - If unsure, say N. - config FB_VIRTUAL tristate "Virtual Frame Buffer support (ONLY FOR TESTING!)" depends on FB diff --git a/drivers/video/fbdev/Makefile b/drivers/video/fbdev/Makefile index 3eecd51267fa..b3d12f977c06 100644 --- a/drivers/video/fbdev/Makefile +++ b/drivers/video/fbdev/Makefile @@ -121,7 +121,6 @@ obj-$(CONFIG_FB_VESA) += vesafb.o obj-$(CONFIG_FB_EFI) += efifb.o obj-$(CONFIG_FB_VGA16) += vga16fb.o obj-$(CONFIG_FB_OF) += offb.o -obj-$(CONFIG_FB_DA8XX) += da8xx-fb.o obj-$(CONFIG_FB_SSD1307) += ssd1307fb.o obj-$(CONFIG_FB_SIMPLE) += simplefb.o diff --git a/drivers/video/fbdev/bw2.c b/drivers/video/fbdev/bw2.c index 4a64940e0c00..e757462af0a6 100644 --- a/drivers/video/fbdev/bw2.c +++ b/drivers/video/fbdev/bw2.c @@ -147,7 +147,7 @@ bw2_blank(int blank, struct fb_info *info) return 0; } -static struct sbus_mmap_map bw2_mmap_map[] = { +static const struct sbus_mmap_map bw2_mmap_map[] = { { .size = SBUS_MMAP_FBSIZE(1) }, diff --git a/drivers/video/fbdev/cg14.c b/drivers/video/fbdev/cg14.c index 430e1a7b352b..5389f8f07346 100644 --- a/drivers/video/fbdev/cg14.c +++ b/drivers/video/fbdev/cg14.c @@ -360,7 +360,7 @@ static void cg14_init_fix(struct fb_info *info, int linebytes, info->fix.accel = FB_ACCEL_SUN_CG14; } -static struct sbus_mmap_map __cg14_mmap_map[CG14_MMAP_ENTRIES] = { +static const struct sbus_mmap_map __cg14_mmap_map[CG14_MMAP_ENTRIES] = { { .voff = CG14_REGS, .poff = 0x80000000, diff --git a/drivers/video/fbdev/cg3.c b/drivers/video/fbdev/cg3.c index e4c53c6632ba..a58a483014e6 100644 --- a/drivers/video/fbdev/cg3.c +++ b/drivers/video/fbdev/cg3.c @@ -209,7 +209,7 @@ static int cg3_blank(int blank, struct fb_info *info) return 0; } -static struct sbus_mmap_map cg3_mmap_map[] = { +static const struct sbus_mmap_map cg3_mmap_map[] = { { .voff = CG3_MMAP_OFFSET, .poff = CG3_RAM_OFFSET, diff --git a/drivers/video/fbdev/cg6.c b/drivers/video/fbdev/cg6.c index 0b60df51e7bc..56d74468040a 100644 --- a/drivers/video/fbdev/cg6.c +++ b/drivers/video/fbdev/cg6.c @@ -545,7 +545,7 @@ static int cg6_blank(int blank, struct fb_info *info) return 0; } -static struct sbus_mmap_map cg6_mmap_map[] = { +static const struct sbus_mmap_map cg6_mmap_map[] = { { .voff = CG6_FBC, .poff = CG6_FBC_OFFSET, diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c deleted file mode 100644 index fad1e13c6332..000000000000 --- a/drivers/video/fbdev/da8xx-fb.c +++ /dev/null @@ -1,1665 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (C) 2008-2009 MontaVista Software Inc. - * Copyright (C) 2008-2009 Texas Instruments Inc - * - * Based on the LCD driver for TI Avalanche processors written by - * Ajay Singh and Shalom Hai. - */ -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/fb.h> -#include <linux/dma-mapping.h> -#include <linux/device.h> -#include <linux/platform_device.h> -#include <linux/uaccess.h> -#include <linux/pm_runtime.h> -#include <linux/interrupt.h> -#include <linux/wait.h> -#include <linux/clk.h> -#include <linux/cpufreq.h> -#include <linux/console.h> -#include <linux/regulator/consumer.h> -#include <linux/spinlock.h> -#include <linux/slab.h> -#include <linux/delay.h> -#include <linux/lcm.h> -#include <video/da8xx-fb.h> -#include <asm/div64.h> - -#define DRIVER_NAME "da8xx_lcdc" - -#define LCD_VERSION_1 1 -#define LCD_VERSION_2 2 - -/* LCD Status Register */ -#define LCD_END_OF_FRAME1 BIT(9) -#define LCD_END_OF_FRAME0 BIT(8) -#define LCD_PL_LOAD_DONE BIT(6) -#define LCD_FIFO_UNDERFLOW BIT(5) -#define LCD_SYNC_LOST BIT(2) -#define LCD_FRAME_DONE BIT(0) - -/* LCD DMA Control Register */ -#define LCD_DMA_BURST_SIZE(x) ((x) << 4) -#define LCD_DMA_BURST_1 0x0 -#define LCD_DMA_BURST_2 0x1 -#define LCD_DMA_BURST_4 0x2 -#define LCD_DMA_BURST_8 0x3 -#define LCD_DMA_BURST_16 0x4 -#define LCD_V1_END_OF_FRAME_INT_ENA BIT(2) -#define LCD_V2_END_OF_FRAME0_INT_ENA BIT(8) -#define LCD_V2_END_OF_FRAME1_INT_ENA BIT(9) -#define LCD_DUAL_FRAME_BUFFER_ENABLE BIT(0) - -/* LCD Control Register */ -#define LCD_CLK_DIVISOR(x) ((x) << 8) -#define LCD_RASTER_MODE 0x01 - -/* LCD Raster Control Register */ -#define LCD_PALETTE_LOAD_MODE(x) ((x) << 20) -#define PALETTE_AND_DATA 0x00 -#define PALETTE_ONLY 0x01 -#define DATA_ONLY 0x02 - -#define LCD_MONO_8BIT_MODE BIT(9) -#define LCD_RASTER_ORDER BIT(8) -#define LCD_TFT_MODE BIT(7) -#define LCD_V1_UNDERFLOW_INT_ENA BIT(6) -#define LCD_V2_UNDERFLOW_INT_ENA BIT(5) -#define LCD_V1_PL_INT_ENA BIT(4) -#define LCD_V2_PL_INT_ENA BIT(6) -#define LCD_MONOCHROME_MODE BIT(1) -#define LCD_RASTER_ENABLE BIT(0) -#define LCD_TFT_ALT_ENABLE BIT(23) -#define LCD_STN_565_ENABLE BIT(24) -#define LCD_V2_DMA_CLK_EN BIT(2) -#define LCD_V2_LIDD_CLK_EN BIT(1) -#define LCD_V2_CORE_CLK_EN BIT(0) -#define LCD_V2_LPP_B10 26 -#define LCD_V2_TFT_24BPP_MODE BIT(25) -#define LCD_V2_TFT_24BPP_UNPACK BIT(26) - -/* LCD Raster Timing 2 Register */ -#define LCD_AC_BIAS_TRANSITIONS_PER_INT(x) ((x) << 16) -#define LCD_AC_BIAS_FREQUENCY(x) ((x) << 8) -#define LCD_SYNC_CTRL BIT(25) -#define LCD_SYNC_EDGE BIT(24) -#define LCD_INVERT_PIXEL_CLOCK BIT(22) -#define LCD_INVERT_LINE_CLOCK BIT(21) -#define LCD_INVERT_FRAME_CLOCK BIT(20) - -/* LCD Block */ -#define LCD_PID_REG 0x0 -#define LCD_CTRL_REG 0x4 -#define LCD_STAT_REG 0x8 -#define LCD_RASTER_CTRL_REG 0x28 -#define LCD_RASTER_TIMING_0_REG 0x2C -#define LCD_RASTER_TIMING_1_REG 0x30 -#define LCD_RASTER_TIMING_2_REG 0x34 -#define LCD_DMA_CTRL_REG 0x40 -#define LCD_DMA_FRM_BUF_BASE_ADDR_0_REG 0x44 -#define LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG 0x48 -#define LCD_DMA_FRM_BUF_BASE_ADDR_1_REG 0x4C -#define LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG 0x50 - -/* Interrupt Registers available only in Version 2 */ -#define LCD_RAW_STAT_REG 0x58 -#define LCD_MASKED_STAT_REG 0x5c -#define LCD_INT_ENABLE_SET_REG 0x60 -#define LCD_INT_ENABLE_CLR_REG 0x64 -#define LCD_END_OF_INT_IND_REG 0x68 - -/* Clock registers available only on Version 2 */ -#define LCD_CLK_ENABLE_REG 0x6c -#define LCD_CLK_RESET_REG 0x70 -#define LCD_CLK_MAIN_RESET BIT(3) - -#define LCD_NUM_BUFFERS 2 - -#define PALETTE_SIZE 256 - -#define CLK_MIN_DIV 2 -#define CLK_MAX_DIV 255 - -static void __iomem *da8xx_fb_reg_base; -static unsigned int lcd_revision; -static irq_handler_t lcdc_irq_handler; -static wait_queue_head_t frame_done_wq; -static int frame_done_flag; - -static unsigned int lcdc_read(unsigned int addr) -{ - return (unsigned int)__raw_readl(da8xx_fb_reg_base + (addr)); -} - -static void lcdc_write(unsigned int val, unsigned int addr) -{ - __raw_writel(val, da8xx_fb_reg_base + (addr)); -} - -struct da8xx_fb_par { - struct device *dev; - dma_addr_t p_palette_base; - unsigned char *v_palette_base; - dma_addr_t vram_phys; - unsigned long vram_size; - void *vram_virt; - unsigned int dma_start; - unsigned int dma_end; - struct clk *lcdc_clk; - int irq; - unsigned int palette_sz; - int blank; - wait_queue_head_t vsync_wait; - int vsync_flag; - int vsync_timeout; - spinlock_t lock_for_chan_update; - - /* - * LCDC has 2 ping pong DMA channels, channel 0 - * and channel 1. - */ - unsigned int which_dma_channel_done; -#ifdef CONFIG_CPU_FREQ - struct notifier_block freq_transition; -#endif - unsigned int lcdc_clk_rate; - struct regulator *lcd_supply; - u32 pseudo_palette[16]; - struct fb_videomode mode; - struct lcd_ctrl_config cfg; -}; - -static struct fb_var_screeninfo da8xx_fb_var; - -static struct fb_fix_screeninfo da8xx_fb_fix = { - .id = "DA8xx FB Drv", - .type = FB_TYPE_PACKED_PIXELS, - .type_aux = 0, - .visual = FB_VISUAL_PSEUDOCOLOR, - .xpanstep = 0, - .ypanstep = 1, - .ywrapstep = 0, - .accel = FB_ACCEL_NONE -}; - -static struct fb_videomode known_lcd_panels[] = { - /* Sharp LCD035Q3DG01 */ - [0] = { - .name = "Sharp_LCD035Q3DG01", - .xres = 320, - .yres = 240, - .pixclock = KHZ2PICOS(4607), - .left_margin = 6, - .right_margin = 8, - .upper_margin = 2, - .lower_margin = 2, - .hsync_len = 0, - .vsync_len = 0, - .sync = FB_SYNC_CLK_INVERT, - }, - /* Sharp LK043T1DG01 */ - [1] = { - .name = "Sharp_LK043T1DG01", - .xres = 480, - .yres = 272, - .pixclock = KHZ2PICOS(7833), - .left_margin = 2, - .right_margin = 2, - .upper_margin = 2, - .lower_margin = 2, - .hsync_len = 41, - .vsync_len = 10, - .sync = 0, - .flag = 0, - }, - [2] = { - /* Hitachi SP10Q010 */ - .name = "SP10Q010", - .xres = 320, - .yres = 240, - .pixclock = KHZ2PICOS(7833), - .left_margin = 10, - .right_margin = 10, - .upper_margin = 10, - .lower_margin = 10, - .hsync_len = 10, - .vsync_len = 10, - .sync = 0, - .flag = 0, - }, - [3] = { - /* Densitron 84-0023-001T */ - .name = "Densitron_84-0023-001T", - .xres = 320, - .yres = 240, - .pixclock = KHZ2PICOS(6400), - .left_margin = 0, - .right_margin = 0, - .upper_margin = 0, - .lower_margin = 0, - .hsync_len = 30, - .vsync_len = 3, - .sync = 0, - }, -}; - -static bool da8xx_fb_is_raster_enabled(void) -{ - return !!(lcdc_read(LCD_RASTER_CTRL_REG) & LCD_RASTER_ENABLE); -} - -/* Enable the Raster Engine of the LCD Controller */ -static void lcd_enable_raster(void) -{ - u32 reg; - - /* Put LCDC in reset for several cycles */ - if (lcd_revision == LCD_VERSION_2) - /* Write 1 to reset LCDC */ - lcdc_write(LCD_CLK_MAIN_RESET, LCD_CLK_RESET_REG); - mdelay(1); - - /* Bring LCDC out of reset */ - if (lcd_revision == LCD_VERSION_2) - lcdc_write(0, LCD_CLK_RESET_REG); - mdelay(1); - - /* Above reset sequence doesnot reset register context */ - reg = lcdc_read(LCD_RASTER_CTRL_REG); - if (!(reg & LCD_RASTER_ENABLE)) - lcdc_write(reg | LCD_RASTER_ENABLE, LCD_RASTER_CTRL_REG); -} - -/* Disable the Raster Engine of the LCD Controller */ -static void lcd_disable_raster(enum da8xx_frame_complete wait_for_frame_done) -{ - u32 reg; - int ret; - - reg = lcdc_read(LCD_RASTER_CTRL_REG); - if (reg & LCD_RASTER_ENABLE) - lcdc_write(reg & ~LCD_RASTER_ENABLE, LCD_RASTER_CTRL_REG); - else - /* return if already disabled */ - return; - - if ((wait_for_frame_done == DA8XX_FRAME_WAIT) && - (lcd_revision == LCD_VERSION_2)) { - frame_done_flag = 0; - ret = wait_event_interruptible_timeout(frame_done_wq, - frame_done_flag != 0, - msecs_to_jiffies(50)); - if (ret == 0) - pr_err("LCD Controller timed out\n"); - } -} - -static void lcd_blit(int load_mode, struct da8xx_fb_par *par) -{ - u32 start; - u32 end; - u32 reg_ras; - u32 reg_dma; - u32 reg_int; - - /* init reg to clear PLM (loading mode) fields */ - reg_ras = lcdc_read(LCD_RASTER_CTRL_REG); - reg_ras &= ~(3 << 20); - - reg_dma = lcdc_read(LCD_DMA_CTRL_REG); - - if (load_mode == LOAD_DATA) { - start = par->dma_start; - end = par->dma_end; - - reg_ras |= LCD_PALETTE_LOAD_MODE(DATA_ONLY); - if (lcd_revision == LCD_VERSION_1) { - reg_dma |= LCD_V1_END_OF_FRAME_INT_ENA; - } else { - reg_int = lcdc_read(LCD_INT_ENABLE_SET_REG) | - LCD_V2_END_OF_FRAME0_INT_ENA | - LCD_V2_END_OF_FRAME1_INT_ENA | - LCD_FRAME_DONE | LCD_SYNC_LOST; - lcdc_write(reg_int, LCD_INT_ENABLE_SET_REG); - } - reg_dma |= LCD_DUAL_FRAME_BUFFER_ENABLE; - - lcdc_write(start, LCD_DMA_FRM_BUF_BASE_ADDR_0_REG); - lcdc_write(end, LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG); - lcdc_write(start, LCD_DMA_FRM_BUF_BASE_ADDR_1_REG); - lcdc_write(end, LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG); - } else if (load_mode == LOAD_PALETTE) { - start = par->p_palette_base; - end = start + par->palette_sz - 1; - - reg_ras |= LCD_PALETTE_LOAD_MODE(PALETTE_ONLY); - - if (lcd_revision == LCD_VERSION_1) { - reg_ras |= LCD_V1_PL_INT_ENA; - } else { - reg_int = lcdc_read(LCD_INT_ENABLE_SET_REG) | - LCD_V2_PL_INT_ENA; - lcdc_write(reg_int, LCD_INT_ENABLE_SET_REG); - } - - lcdc_write(start, LCD_DMA_FRM_BUF_BASE_ADDR_0_REG); - lcdc_write(end, LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG); - } - - lcdc_write(reg_dma, LCD_DMA_CTRL_REG); - lcdc_write(reg_ras, LCD_RASTER_CTRL_REG); - - /* - * The Raster enable bit must be set after all other control fields are - * set. - */ - lcd_enable_raster(); -} - -/* Configure the Burst Size and fifo threhold of DMA */ -static int lcd_cfg_dma(int burst_size, int fifo_th) -{ - u32 reg; - - reg = lcdc_read(LCD_DMA_CTRL_REG) & 0x00000001; - switch (burst_size) { - case 1: - reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_1); - break; - case 2: - reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_2); - break; - case 4: - reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_4); - break; - case 8: - reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_8); - break; - case 16: - default: - reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_16); - break; - } - - reg |= (fifo_th << 8); - - lcdc_write(reg, LCD_DMA_CTRL_REG); - - return 0; -} - -static void lcd_cfg_ac_bias(int period, int transitions_per_int) -{ - u32 reg; - - /* Set the AC Bias Period and Number of Transisitons per Interrupt */ - reg = lcdc_read(LCD_RASTER_TIMING_2_REG) & 0xFFF00000; - reg |= LCD_AC_BIAS_FREQUENCY(period) | - LCD_AC_BIAS_TRANSITIONS_PER_INT(transitions_per_int); - lcdc_write(reg, LCD_RASTER_TIMING_2_REG); -} - -static void lcd_cfg_horizontal_sync(int back_porch, int pulse_width, - int front_porch) -{ - u32 reg; - - reg = lcdc_read(LCD_RASTER_TIMING_0_REG) & 0x3ff; - reg |= (((back_porch-1) & 0xff) << 24) - | (((front_porch-1) & 0xff) << 16) - | (((pulse_width-1) & 0x3f) << 10); - lcdc_write(reg, LCD_RASTER_TIMING_0_REG); - - /* - * LCDC Version 2 adds some extra bits that increase the allowable - * size of the horizontal timing registers. - * remember that the registers use 0 to represent 1 so all values - * that get set into register need to be decremented by 1 - */ - if (lcd_revision == LCD_VERSION_2) { - /* Mask off the bits we want to change */ - reg = lcdc_read(LCD_RASTER_TIMING_2_REG) & ~0x780000ff; - reg |= ((front_porch-1) & 0x300) >> 8; - reg |= ((back_porch-1) & 0x300) >> 4; - reg |= ((pulse_width-1) & 0x3c0) << 21; - lcdc_write(reg, LCD_RASTER_TIMING_2_REG); - } -} - -static void lcd_cfg_vertical_sync(int back_porch, int pulse_width, - int front_porch) -{ - u32 reg; - - reg = lcdc_read(LCD_RASTER_TIMING_1_REG) & 0x3ff; - reg |= ((back_porch & 0xff) << 24) - | ((front_porch & 0xff) << 16) - | (((pulse_width-1) & 0x3f) << 10); - lcdc_write(reg, LCD_RASTER_TIMING_1_REG); -} - -static int lcd_cfg_display(const struct lcd_ctrl_config *cfg, - struct fb_videomode *panel) -{ - u32 reg; - u32 reg_int; - - reg = lcdc_read(LCD_RASTER_CTRL_REG) & ~(LCD_TFT_MODE | - LCD_MONO_8BIT_MODE | - LCD_MONOCHROME_MODE); - - switch (cfg->panel_shade) { - case MONOCHROME: - reg |= LCD_MONOCHROME_MODE; - if (cfg->mono_8bit_mode) - reg |= LCD_MONO_8BIT_MODE; - break; - case COLOR_ACTIVE: - reg |= LCD_TFT_MODE; - if (cfg->tft_alt_mode) - reg |= LCD_TFT_ALT_ENABLE; - break; - - case COLOR_PASSIVE: - /* AC bias applicable only for Pasive panels */ - lcd_cfg_ac_bias(cfg->ac_bias, cfg->ac_bias_intrpt); - if (cfg->bpp == 12 && cfg->stn_565_mode) - reg |= LCD_STN_565_ENABLE; - break; - - default: - return -EINVAL; - } - - /* enable additional interrupts here */ - if (lcd_revision == LCD_VERSION_1) { - reg |= LCD_V1_UNDERFLOW_INT_ENA; - } else { - reg_int = lcdc_read(LCD_INT_ENABLE_SET_REG) | - LCD_V2_UNDERFLOW_INT_ENA; - lcdc_write(reg_int, LCD_INT_ENABLE_SET_REG); - } - - lcdc_write(reg, LCD_RASTER_CTRL_REG); - - reg = lcdc_read(LCD_RASTER_TIMING_2_REG); - - reg |= LCD_SYNC_CTRL; - - if (cfg->sync_edge) - reg |= LCD_SYNC_EDGE; - else - reg &= ~LCD_SYNC_EDGE; - - if ((panel->sync & FB_SYNC_HOR_HIGH_ACT) == 0) - reg |= LCD_INVERT_LINE_CLOCK; - else - reg &= ~LCD_INVERT_LINE_CLOCK; - - if ((panel->sync & FB_SYNC_VERT_HIGH_ACT) == 0) - reg |= LCD_INVERT_FRAME_CLOCK; - else - reg &= ~LCD_INVERT_FRAME_CLOCK; - - lcdc_write(reg, LCD_RASTER_TIMING_2_REG); - - return 0; -} - -static int lcd_cfg_frame_buffer(struct da8xx_fb_par *par, u32 width, u32 height, - u32 bpp, u32 raster_order) -{ - u32 reg; - - if (bpp > 16 && lcd_revision == LCD_VERSION_1) - return -EINVAL; - - /* Set the Panel Width */ - /* Pixels per line = (PPL + 1)*16 */ - if (lcd_revision == LCD_VERSION_1) { - /* - * 0x3F in bits 4..9 gives max horizontal resolution = 1024 - * pixels. - */ - width &= 0x3f0; - } else { - /* - * 0x7F in bits 4..10 gives max horizontal resolution = 2048 - * pixels. - */ - width &= 0x7f0; - } - - reg = lcdc_read(LCD_RASTER_TIMING_0_REG); - reg &= 0xfffffc00; - if (lcd_revision == LCD_VERSION_1) { - reg |= ((width >> 4) - 1) << 4; - } else { - width = (width >> 4) - 1; - reg |= ((width & 0x3f) << 4) | ((width & 0x40) >> 3); - } - lcdc_write(reg, LCD_RASTER_TIMING_0_REG); - - /* Set the Panel Height */ - /* Set bits 9:0 of Lines Per Pixel */ - reg = lcdc_read(LCD_RASTER_TIMING_1_REG); - reg = ((height - 1) & 0x3ff) | (reg & 0xfffffc00); - lcdc_write(reg, LCD_RASTER_TIMING_1_REG); - - /* Set bit 10 of Lines Per Pixel */ - if (lcd_revision == LCD_VERSION_2) { - reg = lcdc_read(LCD_RASTER_TIMING_2_REG); - reg |= ((height - 1) & 0x400) << 16; - lcdc_write(reg, LCD_RASTER_TIMING_2_REG); - } - - /* Set the Raster Order of the Frame Buffer */ - reg = lcdc_read(LCD_RASTER_CTRL_REG) & ~(1 << 8); - if (raster_order) - reg |= LCD_RASTER_ORDER; - - par->palette_sz = 16 * 2; - - switch (bpp) { - case 1: - case 2: - case 4: - case 16: - break; - case 24: - reg |= LCD_V2_TFT_24BPP_MODE; - break; - case 32: - reg |= LCD_V2_TFT_24BPP_MODE; - reg |= LCD_V2_TFT_24BPP_UNPACK; - break; - case 8: - par->palette_sz = 256 * 2; - break; - - default: - return -EINVAL; - } - - lcdc_write(reg, LCD_RASTER_CTRL_REG); - - return 0; -} - -#define CNVT_TOHW(val, width) ((((val) << (width)) + 0x7FFF - (val)) >> 16) -static int fb_setcolreg(unsigned regno, unsigned red, unsigned green, - unsigned blue, unsigned transp, - struct fb_info *info) -{ - struct da8xx_fb_par *par = info->par; - unsigned short *palette = (unsigned short *) par->v_palette_base; - u_short pal; - int update_hw = 0; - - if (regno > 255) - return 1; - - if (info->fix.visual == FB_VISUAL_DIRECTCOLOR) - return 1; - - if (info->var.bits_per_pixel > 16 && lcd_revision == LCD_VERSION_1) - return -EINVAL; - - switch (info->fix.visual) { - case FB_VISUAL_TRUECOLOR: - red = CNVT_TOHW(red, info->var.red.length); - green = CNVT_TOHW(green, info->var.green.length); - blue = CNVT_TOHW(blue, info->var.blue.length); - break; - case FB_VISUAL_PSEUDOCOLOR: - switch (info->var.bits_per_pixel) { - case 4: - if (regno > 15) - return -EINVAL; - - if (info->var.grayscale) { - pal = regno; - } else { - red >>= 4; - green >>= 8; - blue >>= 12; - - pal = red & 0x0f00; - pal |= green & 0x00f0; - pal |= blue & 0x000f; - } - if (regno == 0) - pal |= 0x2000; - palette[regno] = pal; - break; - - case 8: - red >>= 4; - green >>= 8; - blue >>= 12; - - pal = (red & 0x0f00); - pal |= (green & 0x00f0); - pal |= (blue & 0x000f); - - if (palette[regno] != pal) { - update_hw = 1; - palette[regno] = pal; - } - break; - } - break; - } - - /* Truecolor has hardware independent palette */ - if (info->fix.visual == FB_VISUAL_TRUECOLOR) { - u32 v; - - if (regno > 15) - return -EINVAL; - - v = (red << info->var.red.offset) | - (green << info->var.green.offset) | - (blue << info->var.blue.offset); - - ((u32 *) (info->pseudo_palette))[regno] = v; - if (palette[0] != 0x4000) { - update_hw = 1; - palette[0] = 0x4000; - } - } - - /* Update the palette in the h/w as needed. */ - if (update_hw) - lcd_blit(LOAD_PALETTE, par); - - return 0; -} -#undef CNVT_TOHW - -static void da8xx_fb_lcd_reset(void) -{ - /* DMA has to be disabled */ - lcdc_write(0, LCD_DMA_CTRL_REG); - lcdc_write(0, LCD_RASTER_CTRL_REG); - - if (lcd_revision == LCD_VERSION_2) { - lcdc_write(0, LCD_INT_ENABLE_SET_REG); - /* Write 1 to reset */ - lcdc_write(LCD_CLK_MAIN_RESET, LCD_CLK_RESET_REG); - lcdc_write(0, LCD_CLK_RESET_REG); - } -} - -static int da8xx_fb_config_clk_divider(struct da8xx_fb_par *par, - unsigned lcdc_clk_div, - unsigned lcdc_clk_rate) -{ - int ret; - - if (par->lcdc_clk_rate != lcdc_clk_rate) { - ret = clk_set_rate(par->lcdc_clk, lcdc_clk_rate); - if (ret) { - dev_err(par->dev, - "unable to set clock rate at %u\n", - lcdc_clk_rate); - return ret; - } - par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk); - } - - /* Configure the LCD clock divisor. */ - lcdc_write(LCD_CLK_DIVISOR(lcdc_clk_div) | - (LCD_RASTER_MODE & 0x1), LCD_CTRL_REG); - - if (lcd_revision == LCD_VERSION_2) - lcdc_write(LCD_V2_DMA_CLK_EN | LCD_V2_LIDD_CLK_EN | - LCD_V2_CORE_CLK_EN, LCD_CLK_ENABLE_REG); - - return 0; -} - -static unsigned int da8xx_fb_calc_clk_divider(struct da8xx_fb_par *par, - unsigned pixclock, - unsigned *lcdc_clk_rate) -{ - unsigned lcdc_clk_div; - - pixclock = PICOS2KHZ(pixclock) * 1000; - - *lcdc_clk_rate = par->lcdc_clk_rate; - - if (pixclock < (*lcdc_clk_rate / CLK_MAX_DIV)) { - *lcdc_clk_rate = clk_round_rate(par->lcdc_clk, - pixclock * CLK_MAX_DIV); - lcdc_clk_div = CLK_MAX_DIV; - } else if (pixclock > (*lcdc_clk_rate / CLK_MIN_DIV)) { - *lcdc_clk_rate = clk_round_rate(par->lcdc_clk, - pixclock * CLK_MIN_DIV); - lcdc_clk_div = CLK_MIN_DIV; - } else { - lcdc_clk_div = *lcdc_clk_rate / pixclock; - } - - return lcdc_clk_div; -} - -static int da8xx_fb_calc_config_clk_divider(struct da8xx_fb_par *par, - struct fb_videomode *mode) -{ - unsigned lcdc_clk_rate; - unsigned lcdc_clk_div = da8xx_fb_calc_clk_divider(par, mode->pixclock, - &lcdc_clk_rate); - - return da8xx_fb_config_clk_divider(par, lcdc_clk_div, lcdc_clk_rate); -} - -static unsigned da8xx_fb_round_clk(struct da8xx_fb_par *par, - unsigned pixclock) -{ - unsigned lcdc_clk_div, lcdc_clk_rate; - - lcdc_clk_div = da8xx_fb_calc_clk_divider(par, pixclock, &lcdc_clk_rate); - return KHZ2PICOS(lcdc_clk_rate / (1000 * lcdc_clk_div)); -} - -static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg, - struct fb_videomode *panel) -{ - u32 bpp; - int ret = 0; - - ret = da8xx_fb_calc_config_clk_divider(par, panel); - if (ret) { - dev_err(par->dev, "unable to configure clock\n"); - return ret; - } - - if (panel->sync & FB_SYNC_CLK_INVERT) - lcdc_write((lcdc_read(LCD_RASTER_TIMING_2_REG) | - LCD_INVERT_PIXEL_CLOCK), LCD_RASTER_TIMING_2_REG); - else - lcdc_write((lcdc_read(LCD_RASTER_TIMING_2_REG) & - ~LCD_INVERT_PIXEL_CLOCK), LCD_RASTER_TIMING_2_REG); - - /* Configure the DMA burst size and fifo threshold. */ - ret = lcd_cfg_dma(cfg->dma_burst_sz, cfg->fifo_th); - if (ret < 0) - return ret; - - /* Configure the vertical and horizontal sync properties. */ - lcd_cfg_vertical_sync(panel->upper_margin, panel->vsync_len, - panel->lower_margin); - lcd_cfg_horizontal_sync(panel->left_margin, panel->hsync_len, - panel->right_margin); - - /* Configure for disply */ - ret = lcd_cfg_display(cfg, panel); - if (ret < 0) - return ret; - - bpp = cfg->bpp; - - if (bpp == 12) - bpp = 16; - ret = lcd_cfg_frame_buffer(par, (unsigned int)panel->xres, - (unsigned int)panel->yres, bpp, - cfg->raster_order); - if (ret < 0) - return ret; - - /* Configure FDD */ - lcdc_write((lcdc_read(LCD_RASTER_CTRL_REG) & 0xfff00fff) | - (cfg->fdd << 12), LCD_RASTER_CTRL_REG); - - return 0; -} - -/* IRQ handler for version 2 of LCDC */ -static irqreturn_t lcdc_irq_handler_rev02(int irq, void *arg) -{ - struct da8xx_fb_par *par = arg; - u32 stat = lcdc_read(LCD_MASKED_STAT_REG); - - if ((stat & LCD_SYNC_LOST) && (stat & LCD_FIFO_UNDERFLOW)) { - lcd_disable_raster(DA8XX_FRAME_NOWAIT); - lcdc_write(stat, LCD_MASKED_STAT_REG); - lcd_enable_raster(); - } else if (stat & LCD_PL_LOAD_DONE) { - /* - * Must disable raster before changing state of any control bit. - * And also must be disabled before clearing the PL loading - * interrupt via the following write to the status register. If - * this is done after then one gets multiple PL done interrupts. - */ - lcd_disable_raster(DA8XX_FRAME_NOWAIT); - - lcdc_write(stat, LCD_MASKED_STAT_REG); - - /* Disable PL completion interrupt */ - lcdc_write(LCD_V2_PL_INT_ENA, LCD_INT_ENABLE_CLR_REG); - - /* Setup and start data loading mode */ - lcd_blit(LOAD_DATA, par); - } else { - lcdc_write(stat, LCD_MASKED_STAT_REG); - - if (stat & LCD_END_OF_FRAME0) { - par->which_dma_channel_done = 0; - lcdc_write(par->dma_start, - LCD_DMA_FRM_BUF_BASE_ADDR_0_REG); - lcdc_write(par->dma_end, - LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG); - par->vsync_flag = 1; - wake_up_interruptible(&par->vsync_wait); - } - - if (stat & LCD_END_OF_FRAME1) { - par->which_dma_channel_done = 1; - lcdc_write(par->dma_start, - LCD_DMA_FRM_BUF_BASE_ADDR_1_REG); - lcdc_write(par->dma_end, - LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG); - par->vsync_flag = 1; - wake_up_interruptible(&par->vsync_wait); - } - - /* Set only when controller is disabled and at the end of - * active frame - */ - if (stat & BIT(0)) { - frame_done_flag = 1; - wake_up_interruptible(&frame_done_wq); - } - } - - lcdc_write(0, LCD_END_OF_INT_IND_REG); - return IRQ_HANDLED; -} - -/* IRQ handler for version 1 LCDC */ -static irqreturn_t lcdc_irq_handler_rev01(int irq, void *arg) -{ - struct da8xx_fb_par *par = arg; - u32 stat = lcdc_read(LCD_STAT_REG); - u32 reg_ras; - - if ((stat & LCD_SYNC_LOST) && (stat & LCD_FIFO_UNDERFLOW)) { - lcd_disable_raster(DA8XX_FRAME_NOWAIT); - lcdc_write(stat, LCD_STAT_REG); - lcd_enable_raster(); - } else if (stat & LCD_PL_LOAD_DONE) { - /* - * Must disable raster before changing state of any control bit. - * And also must be disabled before clearing the PL loading - * interrupt via the following write to the status register. If - * this is done after then one gets multiple PL done interrupts. - */ - lcd_disable_raster(DA8XX_FRAME_NOWAIT); - - lcdc_write(stat, LCD_STAT_REG); - - /* Disable PL completion inerrupt */ - reg_ras = lcdc_read(LCD_RASTER_CTRL_REG); - reg_ras &= ~LCD_V1_PL_INT_ENA; - lcdc_write(reg_ras, LCD_RASTER_CTRL_REG); - - /* Setup and start data loading mode */ - lcd_blit(LOAD_DATA, par); - } else { - lcdc_write(stat, LCD_STAT_REG); - - if (stat & LCD_END_OF_FRAME0) { - par->which_dma_channel_done = 0; - lcdc_write(par->dma_start, - LCD_DMA_FRM_BUF_BASE_ADDR_0_REG); - lcdc_write(par->dma_end, - LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG); - par->vsync_flag = 1; - wake_up_interruptible(&par->vsync_wait); - } - - if (stat & LCD_END_OF_FRAME1) { - par->which_dma_channel_done = 1; - lcdc_write(par->dma_start, - LCD_DMA_FRM_BUF_BASE_ADDR_1_REG); - lcdc_write(par->dma_end, - LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG); - par->vsync_flag = 1; - wake_up_interruptible(&par->vsync_wait); - } - } - - return IRQ_HANDLED; -} - -static int fb_check_var(struct fb_var_screeninfo *var, - struct fb_info *info) -{ - int err = 0; - struct da8xx_fb_par *par = info->par; - int bpp = var->bits_per_pixel >> 3; - unsigned long line_size = var->xres_virtual * bpp; - - if (var->bits_per_pixel > 16 && lcd_revision == LCD_VERSION_1) - return -EINVAL; - - switch (var->bits_per_pixel) { - case 1: - case 8: - var->red.offset = 0; - var->red.length = 8; - var->green.offset = 0; - var->green.length = 8; - var->blue.offset = 0; - var->blue.length = 8; - var->transp.offset = 0; - var->transp.length = 0; - var->nonstd = 0; - break; - case 4: - var->red.offset = 0; - var->red.length = 4; - var->green.offset = 0; - var->green.length = 4; - var->blue.offset = 0; - var->blue.length = 4; - var->transp.offset = 0; - var->transp.length = 0; - var->nonstd = FB_NONSTD_REV_PIX_IN_B; - break; - case 16: /* RGB 565 */ - var->red.offset = 11; - var->red.length = 5; - var->green.offset = 5; - var->green.length = 6; - var->blue.offset = 0; - var->blue.length = 5; - var->transp.offset = 0; - var->transp.length = 0; - var->nonstd = 0; - break; - case 24: - var->red.offset = 16; - var->red.length = 8; - var->green.offset = 8; - var->green.length = 8; - var->blue.offset = 0; - var->blue.length = 8; - var->nonstd = 0; - break; - case 32: - var->transp.offset = 24; - var->transp.length = 8; - var->red.offset = 16; - var->red.length = 8; - var->green.offset = 8; - var->green.length = 8; - var->blue.offset = 0; - var->blue.length = 8; - var->nonstd = 0; - break; - default: - err = -EINVAL; - } - - var->red.msb_right = 0; - var->green.msb_right = 0; - var->blue.msb_right = 0; - var->transp.msb_right = 0; - - if (line_size * var->yres_virtual > par->vram_size) - var->yres_virtual = par->vram_size / line_size; - - if (var->yres > var->yres_virtual) - var->yres = var->yres_virtual; - - if (var->xres > var->xres_virtual) - var->xres = var->xres_virtual; - - if (var->xres + var->xoffset > var->xres_virtual) - var->xoffset = var->xres_virtual - var->xres; - if (var->yres + var->yoffset > var->yres_virtual) - var->yoffset = var->yres_virtual - var->yres; - - var->pixclock = da8xx_fb_round_clk(par, var->pixclock); - - return err; -} - -#ifdef CONFIG_CPU_FREQ -static int lcd_da8xx_cpufreq_transition(struct notifier_block *nb, - unsigned long val, void *data) -{ - struct da8xx_fb_par *par; - - par = container_of(nb, struct da8xx_fb_par, freq_transition); - if (val == CPUFREQ_POSTCHANGE) { - if (par->lcdc_clk_rate != clk_get_rate(par->lcdc_clk)) { - par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk); - lcd_disable_raster(DA8XX_FRAME_WAIT); - da8xx_fb_calc_config_clk_divider(par, &par->mode); - if (par->blank == FB_BLANK_UNBLANK) - lcd_enable_raster(); - } - } - - return 0; -} - -static int lcd_da8xx_cpufreq_register(struct da8xx_fb_par *par) -{ - par->freq_transition.notifier_call = lcd_da8xx_cpufreq_transition; - - return cpufreq_register_notifier(&par->freq_transition, - CPUFREQ_TRANSITION_NOTIFIER); -} - -static void lcd_da8xx_cpufreq_deregister(struct da8xx_fb_par *par) -{ - cpufreq_unregister_notifier(&par->freq_transition, - CPUFREQ_TRANSITION_NOTIFIER); -} -#endif - -static void fb_remove(struct platform_device *dev) -{ - struct fb_info *info = platform_get_drvdata(dev); - struct da8xx_fb_par *par = info->par; - int ret; - -#ifdef CONFIG_CPU_FREQ - lcd_da8xx_cpufreq_deregister(par); -#endif - if (par->lcd_supply) { - ret = regulator_disable(par->lcd_supply); - if (ret) - dev_warn(&dev->dev, "Failed to disable regulator (%pe)\n", - ERR_PTR(ret)); - } - - lcd_disable_raster(DA8XX_FRAME_WAIT); - lcdc_write(0, LCD_RASTER_CTRL_REG); - - /* disable DMA */ - lcdc_write(0, LCD_DMA_CTRL_REG); - - unregister_framebuffer(info); - fb_dealloc_cmap(&info->cmap); - pm_runtime_put_sync(&dev->dev); - pm_runtime_disable(&dev->dev); - framebuffer_release(info); -} - -/* - * Function to wait for vertical sync which for this LCD peripheral - * translates into waiting for the current raster frame to complete. - */ -static int fb_wait_for_vsync(struct fb_info *info) -{ - struct da8xx_fb_par *par = info->par; - int ret; - - /* - * Set flag to 0 and wait for isr to set to 1. It would seem there is a - * race condition here where the ISR could have occurred just before or - * just after this set. But since we are just coarsely waiting for - * a frame to complete then that's OK. i.e. if the frame completed - * just before this code executed then we have to wait another full - * frame time but there is no way to avoid such a situation. On the - * other hand if the frame completed just after then we don't need - * to wait long at all. Either way we are guaranteed to return to the - * user immediately after a frame completion which is all that is - * required. - */ - par->vsync_flag = 0; - ret = wait_event_interruptible_timeout(par->vsync_wait, - par->vsync_flag != 0, - par->vsync_timeout); - if (ret < 0) - return ret; - if (ret == 0) - return -ETIMEDOUT; - - return 0; -} - -static int fb_ioctl(struct fb_info *info, unsigned int cmd, - unsigned long arg) -{ - struct lcd_sync_arg sync_arg; - - switch (cmd) { - case FBIOGET_CONTRAST: - case FBIOPUT_CONTRAST: - case FBIGET_BRIGHTNESS: - case FBIPUT_BRIGHTNESS: - case FBIGET_COLOR: - case FBIPUT_COLOR: - return -ENOTTY; - case FBIPUT_HSYNC: - if (copy_from_user(&sync_arg, (char *)arg, - sizeof(struct lcd_sync_arg))) - return -EFAULT; - lcd_cfg_horizontal_sync(sync_arg.back_porch, - sync_arg.pulse_width, - sync_arg.front_porch); - break; - case FBIPUT_VSYNC: - if (copy_from_user(&sync_arg, (char *)arg, - sizeof(struct lcd_sync_arg))) - return -EFAULT; - lcd_cfg_vertical_sync(sync_arg.back_porch, - sync_arg.pulse_width, - sync_arg.front_porch); - break; - case FBIO_WAITFORVSYNC: - return fb_wait_for_vsync(info); - default: - return -EINVAL; - } - return 0; -} - -static int cfb_blank(int blank, struct fb_info *info) -{ - struct da8xx_fb_par *par = info->par; - int ret = 0; - - if (par->blank == blank) - return 0; - - par->blank = blank; - switch (blank) { - case FB_BLANK_UNBLANK: - lcd_enable_raster(); - - if (par->lcd_supply) { - ret = regulator_enable(par->lcd_supply); - if (ret) - return ret; - } - break; - case FB_BLANK_NORMAL: - case FB_BLANK_VSYNC_SUSPEND: - case FB_BLANK_HSYNC_SUSPEND: - case FB_BLANK_POWERDOWN: - if (par->lcd_supply) { - ret = regulator_disable(par->lcd_supply); - if (ret) - return ret; - } - - lcd_disable_raster(DA8XX_FRAME_WAIT); - break; - default: - ret = -EINVAL; - } - - return ret; -} - -/* - * Set new x,y offsets in the virtual display for the visible area and switch - * to the new mode. - */ -static int da8xx_pan_display(struct fb_var_screeninfo *var, - struct fb_info *fbi) -{ - int ret = 0; - struct fb_var_screeninfo new_var; - struct da8xx_fb_par *par = fbi->par; - struct fb_fix_screeninfo *fix = &fbi->fix; - unsigned int end; - unsigned int start; - unsigned long irq_flags; - - if (var->xoffset != fbi->var.xoffset || - var->yoffset != fbi->var.yoffset) { - memcpy(&new_var, &fbi->var, sizeof(new_var)); - new_var.xoffset = var->xoffset; - new_var.yoffset = var->yoffset; - if (fb_check_var(&new_var, fbi)) - ret = -EINVAL; - else { - memcpy(&fbi->var, &new_var, sizeof(new_var)); - - start = fix->smem_start + - new_var.yoffset * fix->line_length + - new_var.xoffset * fbi->var.bits_per_pixel / 8; - end = start + fbi->var.yres * fix->line_length - 1; - par->dma_start = start; - par->dma_end = end; - spin_lock_irqsave(&par->lock_for_chan_update, - irq_flags); - if (par->which_dma_channel_done == 0) { - lcdc_write(par->dma_start, - LCD_DMA_FRM_BUF_BASE_ADDR_0_REG); - lcdc_write(par->dma_end, - LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG); - } else if (par->which_dma_channel_done == 1) { - lcdc_write(par->dma_start, - LCD_DMA_FRM_BUF_BASE_ADDR_1_REG); - lcdc_write(par->dma_end, - LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG); - } - spin_unlock_irqrestore(&par->lock_for_chan_update, - irq_flags); - } - } - - return ret; -} - -static int da8xxfb_set_par(struct fb_info *info) -{ - struct da8xx_fb_par *par = info->par; - int ret; - bool raster = da8xx_fb_is_raster_enabled(); - - if (raster) - lcd_disable_raster(DA8XX_FRAME_WAIT); - - fb_var_to_videomode(&par->mode, &info->var); - - par->cfg.bpp = info->var.bits_per_pixel; - - info->fix.visual = (par->cfg.bpp <= 8) ? - FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR; - info->fix.line_length = (par->mode.xres * par->cfg.bpp) / 8; - - ret = lcd_init(par, &par->cfg, &par->mode); - if (ret < 0) { - dev_err(par->dev, "lcd init failed\n"); - return ret; - } - - par->dma_start = info->fix.smem_start + - info->var.yoffset * info->fix.line_length + - info->var.xoffset * info->var.bits_per_pixel / 8; - par->dma_end = par->dma_start + - info->var.yres * info->fix.line_length - 1; - - lcdc_write(par->dma_start, LCD_DMA_FRM_BUF_BASE_ADDR_0_REG); - lcdc_write(par->dma_end, LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG); - lcdc_write(par->dma_start, LCD_DMA_FRM_BUF_BASE_ADDR_1_REG); - lcdc_write(par->dma_end, LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG); - - if (raster) - lcd_enable_raster(); - - return 0; -} - -static const struct fb_ops da8xx_fb_ops = { - .owner = THIS_MODULE, - FB_DEFAULT_IOMEM_OPS, - .fb_check_var = fb_check_var, - .fb_set_par = da8xxfb_set_par, - .fb_setcolreg = fb_setcolreg, - .fb_pan_display = da8xx_pan_display, - .fb_ioctl = fb_ioctl, - .fb_blank = cfb_blank, -}; - -static struct fb_videomode *da8xx_fb_get_videomode(struct platform_device *dev) -{ - struct da8xx_lcdc_platform_data *fb_pdata = dev_get_platdata(&dev->dev); - struct fb_videomode *lcdc_info; - int i; - - for (i = 0, lcdc_info = known_lcd_panels; - i < ARRAY_SIZE(known_lcd_panels); i++, lcdc_info++) { - if (strcmp(fb_pdata->type, lcdc_info->name) == 0) - break; - } - - if (i == ARRAY_SIZE(known_lcd_panels)) { - dev_err(&dev->dev, "no panel found\n"); - return NULL; - } - dev_info(&dev->dev, "found %s panel\n", lcdc_info->name); - - return lcdc_info; -} - -static int fb_probe(struct platform_device *device) -{ - struct da8xx_lcdc_platform_data *fb_pdata = - dev_get_platdata(&device->dev); - struct lcd_ctrl_config *lcd_cfg; - struct fb_videomode *lcdc_info; - struct fb_info *da8xx_fb_info; - struct da8xx_fb_par *par; - struct clk *tmp_lcdc_clk; - int ret; - unsigned long ulcm; - - if (fb_pdata == NULL) { - dev_err(&device->dev, "Can not get platform data\n"); - return -ENOENT; - } - - lcdc_info = da8xx_fb_get_videomode(device); - if (lcdc_info == NULL) - return -ENODEV; - - da8xx_fb_reg_base = devm_platform_ioremap_resource(device, 0); - if (IS_ERR(da8xx_fb_reg_base)) - return PTR_ERR(da8xx_fb_reg_base); - - tmp_lcdc_clk = devm_clk_get(&device->dev, "fck"); - if (IS_ERR(tmp_lcdc_clk)) - return dev_err_probe(&device->dev, PTR_ERR(tmp_lcdc_clk), - "Can not get device clock\n"); - - pm_runtime_enable(&device->dev); - pm_runtime_get_sync(&device->dev); - - /* Determine LCD IP Version */ - switch (lcdc_read(LCD_PID_REG)) { - case 0x4C100102: - lcd_revision = LCD_VERSION_1; - break; - case 0x4F200800: - case 0x4F201000: - lcd_revision = LCD_VERSION_2; - break; - default: - dev_warn(&device->dev, "Unknown PID Reg value 0x%x, " - "defaulting to LCD revision 1\n", - lcdc_read(LCD_PID_REG)); - lcd_revision = LCD_VERSION_1; - break; - } - - lcd_cfg = (struct lcd_ctrl_config *)fb_pdata->controller_data; - - if (!lcd_cfg) { - ret = -EINVAL; - goto err_pm_runtime_disable; - } - - da8xx_fb_info = framebuffer_alloc(sizeof(struct da8xx_fb_par), - &device->dev); - if (!da8xx_fb_info) { - ret = -ENOMEM; - goto err_pm_runtime_disable; - } - - par = da8xx_fb_info->par; - par->dev = &device->dev; - par->lcdc_clk = tmp_lcdc_clk; - par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk); - - par->lcd_supply = devm_regulator_get_optional(&device->dev, "lcd"); - if (IS_ERR(par->lcd_supply)) { - if (PTR_ERR(par->lcd_supply) == -EPROBE_DEFER) { - ret = -EPROBE_DEFER; - goto err_release_fb; - } - - par->lcd_supply = NULL; - } else { - ret = regulator_enable(par->lcd_supply); - if (ret) - goto err_release_fb; - } - - fb_videomode_to_var(&da8xx_fb_var, lcdc_info); - par->cfg = *lcd_cfg; - - da8xx_fb_lcd_reset(); - - /* allocate frame buffer */ - par->vram_size = lcdc_info->xres * lcdc_info->yres * lcd_cfg->bpp; - ulcm = lcm((lcdc_info->xres * lcd_cfg->bpp)/8, PAGE_SIZE); - par->vram_size = roundup(par->vram_size/8, ulcm); - par->vram_size = par->vram_size * LCD_NUM_BUFFERS; - - par->vram_virt = dmam_alloc_coherent(par->dev, - par->vram_size, - &par->vram_phys, - GFP_KERNEL | GFP_DMA); - if (!par->vram_virt) { - dev_err(&device->dev, - "GLCD: kmalloc for frame buffer failed\n"); - ret = -EINVAL; - goto err_disable_reg; - } - - da8xx_fb_info->screen_base = (char __iomem *) par->vram_virt; - da8xx_fb_fix.smem_start = par->vram_phys; - da8xx_fb_fix.smem_len = par->vram_size; - da8xx_fb_fix.line_length = (lcdc_info->xres * lcd_cfg->bpp) / 8; - - par->dma_start = par->vram_phys; - par->dma_end = par->dma_start + lcdc_info->yres * - da8xx_fb_fix.line_length - 1; - - /* allocate palette buffer */ - par->v_palette_base = dmam_alloc_coherent(par->dev, PALETTE_SIZE, - &par->p_palette_base, - GFP_KERNEL | GFP_DMA); - if (!par->v_palette_base) { - dev_err(&device->dev, - "GLCD: kmalloc for palette buffer failed\n"); - ret = -EINVAL; - goto err_release_fb; - } - - par->irq = platform_get_irq(device, 0); - if (par->irq < 0) { - ret = -ENOENT; - goto err_release_fb; - } - - da8xx_fb_var.grayscale = - lcd_cfg->panel_shade == MONOCHROME ? 1 : 0; - da8xx_fb_var.bits_per_pixel = lcd_cfg->bpp; - - /* Initialize fbinfo */ - da8xx_fb_info->fix = da8xx_fb_fix; - da8xx_fb_info->var = da8xx_fb_var; - da8xx_fb_info->fbops = &da8xx_fb_ops; - da8xx_fb_info->pseudo_palette = par->pseudo_palette; - da8xx_fb_info->fix.visual = (da8xx_fb_info->var.bits_per_pixel <= 8) ? - FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR; - - ret = fb_alloc_cmap(&da8xx_fb_info->cmap, PALETTE_SIZE, 0); - if (ret) - goto err_disable_reg; - da8xx_fb_info->cmap.len = par->palette_sz; - - /* initialize var_screeninfo */ - da8xx_fb_var.activate = FB_ACTIVATE_FORCE; - fb_set_var(da8xx_fb_info, &da8xx_fb_var); - - platform_set_drvdata(device, da8xx_fb_info); - - /* initialize the vsync wait queue */ - init_waitqueue_head(&par->vsync_wait); - par->vsync_timeout = HZ / 5; - par->which_dma_channel_done = -1; - spin_lock_init(&par->lock_for_chan_update); - - /* Register the Frame Buffer */ - if (register_framebuffer(da8xx_fb_info) < 0) { - dev_err(&device->dev, - "GLCD: Frame Buffer Registration Failed!\n"); - ret = -EINVAL; - goto err_dealloc_cmap; - } - -#ifdef CONFIG_CPU_FREQ - ret = lcd_da8xx_cpufreq_register(par); - if (ret) { - dev_err(&device->dev, "failed to register cpufreq\n"); - goto err_cpu_freq; - } -#endif - - if (lcd_revision == LCD_VERSION_1) - lcdc_irq_handler = lcdc_irq_handler_rev01; - else { - init_waitqueue_head(&frame_done_wq); - lcdc_irq_handler = lcdc_irq_handler_rev02; - } - - ret = devm_request_irq(&device->dev, par->irq, lcdc_irq_handler, 0, - DRIVER_NAME, par); - if (ret) - goto irq_freq; - return 0; - -irq_freq: -#ifdef CONFIG_CPU_FREQ - lcd_da8xx_cpufreq_deregister(par); -err_cpu_freq: -#endif - unregister_framebuffer(da8xx_fb_info); - -err_dealloc_cmap: - fb_dealloc_cmap(&da8xx_fb_info->cmap); - -err_disable_reg: - if (par->lcd_supply) - regulator_disable(par->lcd_supply); -err_release_fb: - framebuffer_release(da8xx_fb_info); - -err_pm_runtime_disable: - pm_runtime_put_sync(&device->dev); - pm_runtime_disable(&device->dev); - - return ret; -} - -#ifdef CONFIG_PM_SLEEP -static struct lcdc_context { - u32 clk_enable; - u32 ctrl; - u32 dma_ctrl; - u32 raster_timing_0; - u32 raster_timing_1; - u32 raster_timing_2; - u32 int_enable_set; - u32 dma_frm_buf_base_addr_0; - u32 dma_frm_buf_ceiling_addr_0; - u32 dma_frm_buf_base_addr_1; - u32 dma_frm_buf_ceiling_addr_1; - u32 raster_ctrl; -} reg_context; - -static void lcd_context_save(void) -{ - if (lcd_revision == LCD_VERSION_2) { - reg_context.clk_enable = lcdc_read(LCD_CLK_ENABLE_REG); - reg_context.int_enable_set = lcdc_read(LCD_INT_ENABLE_SET_REG); - } - - reg_context.ctrl = lcdc_read(LCD_CTRL_REG); - reg_context.dma_ctrl = lcdc_read(LCD_DMA_CTRL_REG); - reg_context.raster_timing_0 = lcdc_read(LCD_RASTER_TIMING_0_REG); - reg_context.raster_timing_1 = lcdc_read(LCD_RASTER_TIMING_1_REG); - reg_context.raster_timing_2 = lcdc_read(LCD_RASTER_TIMING_2_REG); - reg_context.dma_frm_buf_base_addr_0 = - lcdc_read(LCD_DMA_FRM_BUF_BASE_ADDR_0_REG); - reg_context.dma_frm_buf_ceiling_addr_0 = - lcdc_read(LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG); - reg_context.dma_frm_buf_base_addr_1 = - lcdc_read(LCD_DMA_FRM_BUF_BASE_ADDR_1_REG); - reg_context.dma_frm_buf_ceiling_addr_1 = - lcdc_read(LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG); - reg_context.raster_ctrl = lcdc_read(LCD_RASTER_CTRL_REG); - return; -} - -static void lcd_context_restore(void) -{ - if (lcd_revision == LCD_VERSION_2) { - lcdc_write(reg_context.clk_enable, LCD_CLK_ENABLE_REG); - lcdc_write(reg_context.int_enable_set, LCD_INT_ENABLE_SET_REG); - } - - lcdc_write(reg_context.ctrl, LCD_CTRL_REG); - lcdc_write(reg_context.dma_ctrl, LCD_DMA_CTRL_REG); - lcdc_write(reg_context.raster_timing_0, LCD_RASTER_TIMING_0_REG); - lcdc_write(reg_context.raster_timing_1, LCD_RASTER_TIMING_1_REG); - lcdc_write(reg_context.raster_timing_2, LCD_RASTER_TIMING_2_REG); - lcdc_write(reg_context.dma_frm_buf_base_addr_0, - LCD_DMA_FRM_BUF_BASE_ADDR_0_REG); - lcdc_write(reg_context.dma_frm_buf_ceiling_addr_0, - LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG); - lcdc_write(reg_context.dma_frm_buf_base_addr_1, - LCD_DMA_FRM_BUF_BASE_ADDR_1_REG); - lcdc_write(reg_context.dma_frm_buf_ceiling_addr_1, - LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG); - lcdc_write(reg_context.raster_ctrl, LCD_RASTER_CTRL_REG); - return; -} - -static int fb_suspend(struct device *dev) -{ - struct fb_info *info = dev_get_drvdata(dev); - struct da8xx_fb_par *par = info->par; - int ret; - - console_lock(); - if (par->lcd_supply) { - ret = regulator_disable(par->lcd_supply); - if (ret) - return ret; - } - - fb_set_suspend(info, 1); - lcd_disable_raster(DA8XX_FRAME_WAIT); - lcd_context_save(); - pm_runtime_put_sync(dev); - console_unlock(); - - return 0; -} -static int fb_resume(struct device *dev) -{ - struct fb_info *info = dev_get_drvdata(dev); - struct da8xx_fb_par *par = info->par; - int ret; - - console_lock(); - pm_runtime_get_sync(dev); - lcd_context_restore(); - if (par->blank == FB_BLANK_UNBLANK) { - lcd_enable_raster(); - - if (par->lcd_supply) { - ret = regulator_enable(par->lcd_supply); - if (ret) - return ret; - } - } - - fb_set_suspend(info, 0); - console_unlock(); - - return 0; -} -#endif - -static SIMPLE_DEV_PM_OPS(fb_pm_ops, fb_suspend, fb_resume); - -static struct platform_driver da8xx_fb_driver = { - .probe = fb_probe, - .remove = fb_remove, - .driver = { - .name = DRIVER_NAME, - .pm = &fb_pm_ops, - }, -}; -module_platform_driver(da8xx_fb_driver); - -MODULE_DESCRIPTION("Framebuffer driver for TI da8xx/omap-l1xx"); -MODULE_AUTHOR("Texas Instruments"); -MODULE_LICENSE("GPL"); diff --git a/drivers/video/fbdev/ffb.c b/drivers/video/fbdev/ffb.c index 0b7e7b38c05a..34b6abff9493 100644 --- a/drivers/video/fbdev/ffb.c +++ b/drivers/video/fbdev/ffb.c @@ -710,7 +710,7 @@ static int ffb_blank(int blank, struct fb_info *info) return 0; } -static struct sbus_mmap_map ffb_mmap_map[] = { +static const struct sbus_mmap_map ffb_mmap_map[] = { { .voff = FFB_SFB8R_VOFF, .poff = FFB_SFB8R_POFF, diff --git a/drivers/video/fbdev/leo.c b/drivers/video/fbdev/leo.c index 271e2e8c6a84..b9fb059df2c7 100644 --- a/drivers/video/fbdev/leo.c +++ b/drivers/video/fbdev/leo.c @@ -338,7 +338,7 @@ static int leo_blank(int blank, struct fb_info *info) return 0; } -static struct sbus_mmap_map leo_mmap_map[] = { +static const struct sbus_mmap_map leo_mmap_map[] = { { .voff = LEO_SS0_MAP, .poff = LEO_OFF_SS0, diff --git a/drivers/video/fbdev/nvidia/nv_hw.c b/drivers/video/fbdev/nvidia/nv_hw.c index 9b0a324bb1b4..75afaa07e7eb 100644 --- a/drivers/video/fbdev/nvidia/nv_hw.c +++ b/drivers/video/fbdev/nvidia/nv_hw.c @@ -1509,10 +1509,10 @@ void NVLoadStateExt(struct nvidia_par *par, RIVA_HW_STATE * state) NV_WR32(par->PFIFO, 0x0495 * 4, 0x00000001); NV_WR32(par->PFIFO, 0x0140 * 4, 0x00000001); - if (!state) { - par->CurrentState = NULL; - return; - } + if (!state) { + par->CurrentState = NULL; + return; + } if (par->Architecture >= NV_ARCH_10) { if (par->twoHeads) { diff --git a/drivers/video/fbdev/p9100.c b/drivers/video/fbdev/p9100.c index 124468f0e9ef..0bc0f78fe4b9 100644 --- a/drivers/video/fbdev/p9100.c +++ b/drivers/video/fbdev/p9100.c @@ -206,7 +206,7 @@ p9100_blank(int blank, struct fb_info *info) return 0; } -static struct sbus_mmap_map p9100_mmap_map[] = { +static const struct sbus_mmap_map p9100_mmap_map[] = { { CG3_MMAP_OFFSET, 0, SBUS_MMAP_FBSIZE(1) }, { 0, 0, 0 } }; diff --git a/drivers/video/fbdev/sbuslib.c b/drivers/video/fbdev/sbuslib.c index 634e3d159452..4c79654bda30 100644 --- a/drivers/video/fbdev/sbuslib.c +++ b/drivers/video/fbdev/sbuslib.c @@ -38,7 +38,7 @@ static unsigned long sbusfb_mmapsize(long size, unsigned long fbsize) return fbsize * (-size); } -int sbusfb_mmap_helper(struct sbus_mmap_map *map, +int sbusfb_mmap_helper(const struct sbus_mmap_map *map, unsigned long physbase, unsigned long fbsize, unsigned long iospace, diff --git a/drivers/video/fbdev/sbuslib.h b/drivers/video/fbdev/sbuslib.h index 6466b4cbcd7b..e9af2dc93f94 100644 --- a/drivers/video/fbdev/sbuslib.h +++ b/drivers/video/fbdev/sbuslib.h @@ -19,7 +19,7 @@ struct sbus_mmap_map { extern void sbusfb_fill_var(struct fb_var_screeninfo *var, struct device_node *dp, int bpp); -extern int sbusfb_mmap_helper(struct sbus_mmap_map *map, +extern int sbusfb_mmap_helper(const struct sbus_mmap_map *map, unsigned long physbase, unsigned long fbsize, unsigned long iospace, struct vm_area_struct *vma); diff --git a/drivers/video/fbdev/sstfb.c b/drivers/video/fbdev/sstfb.c index f8ae54ca0cc3..2ea947f57efb 100644 --- a/drivers/video/fbdev/sstfb.c +++ b/drivers/video/fbdev/sstfb.c @@ -716,6 +716,7 @@ static void sstfb_setvgapass( struct fb_info *info, int enable ) pci_write_config_dword(sst_dev, PCI_INIT_ENABLE, tmp); } +#ifdef CONFIG_FB_DEVICE static ssize_t store_vgapass(struct device *device, struct device_attribute *attr, const char *buf, size_t count) { @@ -739,7 +740,8 @@ static ssize_t show_vgapass(struct device *device, struct device_attribute *attr static struct device_attribute device_attrs[] = { __ATTR(vgapass, S_IRUGO|S_IWUSR, show_vgapass, store_vgapass) - }; +}; +#endif static int sstfb_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg) @@ -1436,9 +1438,10 @@ static int sstfb_probe(struct pci_dev *pdev, const struct pci_device_id *id) sstfb_clear_screen(info); +#ifdef CONFIG_FB_DEVICE if (device_create_file(info->dev, &device_attrs[0])) printk(KERN_WARNING "sstfb: can't create sysfs entry.\n"); - +#endif fb_info(info, "%s frame buffer device at 0x%p\n", fix->id, info->screen_base); @@ -1468,7 +1471,9 @@ static void sstfb_remove(struct pci_dev *pdev) info = pci_get_drvdata(pdev); par = info->par; +#ifdef CONFIG_FB_DEVICE device_remove_file(info->dev, &device_attrs[0]); +#endif sst_shutdown(info); iounmap(info->screen_base); iounmap(par->mmio_vbase); diff --git a/drivers/video/fbdev/tcx.c b/drivers/video/fbdev/tcx.c index 6eb8bb2e3501..f9a0085ad72b 100644 --- a/drivers/video/fbdev/tcx.c +++ b/drivers/video/fbdev/tcx.c @@ -236,7 +236,7 @@ tcx_blank(int blank, struct fb_info *info) return 0; } -static struct sbus_mmap_map __tcx_mmap_map[TCX_MMAP_ENTRIES] = { +static const struct sbus_mmap_map __tcx_mmap_map[TCX_MMAP_ENTRIES] = { { .voff = TCX_RAM8BIT, .size = SBUS_MMAP_FBSIZE(1) diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 1775fcc7f0e8..698c43dd5dc8 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -179,14 +179,16 @@ extern int v9fs_vfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); -extern struct inode *v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid, - bool new); +extern struct inode *v9fs_inode_from_fid(struct v9fs_session_info *v9ses, + struct p9_fid *fid, + struct super_block *sb, int new); extern const struct inode_operations v9fs_dir_inode_operations_dotl; extern const struct inode_operations v9fs_file_inode_operations_dotl; extern const struct inode_operations v9fs_symlink_inode_operations_dotl; extern const struct netfs_request_ops v9fs_req_ops; -extern struct inode *v9fs_fid_iget_dotl(struct super_block *sb, - struct p9_fid *fid, bool new); +extern struct inode *v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses, + struct p9_fid *fid, + struct super_block *sb, int new); /* other default globals */ #define V9FS_PORT 564 @@ -225,12 +227,30 @@ static inline int v9fs_proto_dotl(struct v9fs_session_info *v9ses) */ static inline struct inode * v9fs_get_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid, - struct super_block *sb, bool new) + struct super_block *sb) { if (v9fs_proto_dotl(v9ses)) - return v9fs_fid_iget_dotl(sb, fid, new); + return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 0); else - return v9fs_fid_iget(sb, fid, new); + return v9fs_inode_from_fid(v9ses, fid, sb, 0); +} + +/** + * v9fs_get_new_inode_from_fid - Helper routine to populate an inode by + * issuing a attribute request + * @v9ses: session information + * @fid: fid to issue attribute request for + * @sb: superblock on which to create inode + * + */ +static inline struct inode * +v9fs_get_new_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid, + struct super_block *sb) +{ + if (v9fs_proto_dotl(v9ses)) + return v9fs_inode_from_fid_dotl(v9ses, fid, sb, 1); + else + return v9fs_inode_from_fid(v9ses, fid, sb, 1); } #endif diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index 7923c3c347cb..d3aefbec4de6 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -42,7 +42,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb); void v9fs_free_inode(struct inode *inode); void v9fs_set_netfs_context(struct inode *inode); int v9fs_init_inode(struct v9fs_session_info *v9ses, - struct inode *inode, struct p9_qid *qid, umode_t mode, dev_t rdev); + struct inode *inode, umode_t mode, dev_t rdev); void v9fs_evict_inode(struct inode *inode); #if (BITS_PER_LONG == 32) #define QID2INO(q) ((ino_t) (((q)->path+2) ^ (((q)->path) >> 32))) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index fd72fc38c8f5..3e68521f4e2f 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -256,12 +256,9 @@ void v9fs_set_netfs_context(struct inode *inode) } int v9fs_init_inode(struct v9fs_session_info *v9ses, - struct inode *inode, struct p9_qid *qid, umode_t mode, dev_t rdev) + struct inode *inode, umode_t mode, dev_t rdev) { int err = 0; - struct v9fs_inode *v9inode = V9FS_I(inode); - - memcpy(&v9inode->qid, qid, sizeof(struct p9_qid)); inode_init_owner(&nop_mnt_idmap, inode, NULL, mode); inode->i_blocks = 0; @@ -365,59 +362,105 @@ void v9fs_evict_inode(struct inode *inode) clear_inode(inode); } -struct inode * -v9fs_fid_iget(struct super_block *sb, struct p9_fid *fid, bool new) +static int v9fs_test_inode(struct inode *inode, void *data) +{ + int umode; + dev_t rdev; + struct v9fs_inode *v9inode = V9FS_I(inode); + struct p9_wstat *st = (struct p9_wstat *)data; + struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode); + + umode = p9mode2unixmode(v9ses, st, &rdev); + /* don't match inode of different type */ + if (inode_wrong_type(inode, umode)) + return 0; + + /* compare qid details */ + if (memcmp(&v9inode->qid.version, + &st->qid.version, sizeof(v9inode->qid.version))) + return 0; + + if (v9inode->qid.type != st->qid.type) + return 0; + + if (v9inode->qid.path != st->qid.path) + return 0; + return 1; +} + +static int v9fs_test_new_inode(struct inode *inode, void *data) +{ + return 0; +} + +static int v9fs_set_inode(struct inode *inode, void *data) +{ + struct v9fs_inode *v9inode = V9FS_I(inode); + struct p9_wstat *st = (struct p9_wstat *)data; + + memcpy(&v9inode->qid, &st->qid, sizeof(st->qid)); + return 0; +} + +static struct inode *v9fs_qid_iget(struct super_block *sb, + struct p9_qid *qid, + struct p9_wstat *st, + int new) { dev_t rdev; int retval; umode_t umode; struct inode *inode; - struct p9_wstat *st; struct v9fs_session_info *v9ses = sb->s_fs_info; + int (*test)(struct inode *inode, void *data); - inode = iget_locked(sb, QID2INO(&fid->qid)); - if (unlikely(!inode)) - return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) { - if (!new) { - goto done; - } else { - p9_debug(P9_DEBUG_VFS, "WARNING: Inode collision %ld\n", - inode->i_ino); - iput(inode); - remove_inode_hash(inode); - inode = iget_locked(sb, QID2INO(&fid->qid)); - WARN_ON(!(inode->i_state & I_NEW)); - } - } + if (new) + test = v9fs_test_new_inode; + else + test = v9fs_test_inode; + inode = iget5_locked(sb, QID2INO(qid), test, v9fs_set_inode, st); + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode->i_state & I_NEW)) + return inode; /* * initialize the inode with the stat info * FIXME!! we may need support for stale inodes * later. */ - st = p9_client_stat(fid); - if (IS_ERR(st)) { - retval = PTR_ERR(st); - goto error; - } - + inode->i_ino = QID2INO(qid); umode = p9mode2unixmode(v9ses, st, &rdev); - retval = v9fs_init_inode(v9ses, inode, &fid->qid, umode, rdev); - v9fs_stat2inode(st, inode, sb, 0); - p9stat_free(st); - kfree(st); + retval = v9fs_init_inode(v9ses, inode, umode, rdev); if (retval) goto error; + v9fs_stat2inode(st, inode, sb, 0); v9fs_set_netfs_context(inode); v9fs_cache_inode_get_cookie(inode); unlock_new_inode(inode); -done: return inode; error: iget_failed(inode); return ERR_PTR(retval); + +} + +struct inode * +v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid, + struct super_block *sb, int new) +{ + struct p9_wstat *st; + struct inode *inode = NULL; + + st = p9_client_stat(fid); + if (IS_ERR(st)) + return ERR_CAST(st); + + inode = v9fs_qid_iget(sb, &st->qid, st, new); + p9stat_free(st); + kfree(st); + return inode; } /** @@ -449,15 +492,8 @@ static int v9fs_at_to_dotl_flags(int flags) */ static void v9fs_dec_count(struct inode *inode) { - if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2) { - if (inode->i_nlink) { - drop_nlink(inode); - } else { - p9_debug(P9_DEBUG_VFS, - "WARNING: unexpected i_nlink zero %d inode %ld\n", - inode->i_nlink, inode->i_ino); - } - } + if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2) + drop_nlink(inode); } /** @@ -508,9 +544,6 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags) } else v9fs_dec_count(inode); - if (inode->i_nlink <= 0) /* no more refs unhash it */ - remove_inode_hash(inode); - v9fs_invalidate_inode_attr(inode); v9fs_invalidate_inode_attr(dir); @@ -576,7 +609,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir, /* * instantiate inode and assign the unopened fid to the dentry */ - inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb, true); + inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); p9_debug(P9_DEBUG_VFS, @@ -704,8 +737,10 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, inode = NULL; else if (IS_ERR(fid)) inode = ERR_CAST(fid); + else if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) + inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb); else - inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb, false); + inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb); /* * If we had a rename on the server and a parallel lookup * for the new name, then make sure we instantiate with diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index c61b97bd13b9..143ac03b7425 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -52,50 +52,80 @@ static kgid_t v9fs_get_fsgid_for_create(struct inode *dir_inode) return current_fsgid(); } +static int v9fs_test_inode_dotl(struct inode *inode, void *data) +{ + struct v9fs_inode *v9inode = V9FS_I(inode); + struct p9_stat_dotl *st = (struct p9_stat_dotl *)data; + /* don't match inode of different type */ + if (inode_wrong_type(inode, st->st_mode)) + return 0; -struct inode * -v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid, bool new) + if (inode->i_generation != st->st_gen) + return 0; + + /* compare qid details */ + if (memcmp(&v9inode->qid.version, + &st->qid.version, sizeof(v9inode->qid.version))) + return 0; + + if (v9inode->qid.type != st->qid.type) + return 0; + + if (v9inode->qid.path != st->qid.path) + return 0; + return 1; +} + +/* Always get a new inode */ +static int v9fs_test_new_inode_dotl(struct inode *inode, void *data) +{ + return 0; +} + +static int v9fs_set_inode_dotl(struct inode *inode, void *data) +{ + struct v9fs_inode *v9inode = V9FS_I(inode); + struct p9_stat_dotl *st = (struct p9_stat_dotl *)data; + + memcpy(&v9inode->qid, &st->qid, sizeof(st->qid)); + inode->i_generation = st->st_gen; + return 0; +} + +static struct inode *v9fs_qid_iget_dotl(struct super_block *sb, + struct p9_qid *qid, + struct p9_fid *fid, + struct p9_stat_dotl *st, + int new) { int retval; struct inode *inode; - struct p9_stat_dotl *st; struct v9fs_session_info *v9ses = sb->s_fs_info; + int (*test)(struct inode *inode, void *data); - inode = iget_locked(sb, QID2INO(&fid->qid)); - if (unlikely(!inode)) - return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) { - if (!new) { - goto done; - } else { /* deal with race condition in inode number reuse */ - p9_debug(P9_DEBUG_ERROR, "WARNING: Inode collision %lx\n", - inode->i_ino); - iput(inode); - remove_inode_hash(inode); - inode = iget_locked(sb, QID2INO(&fid->qid)); - WARN_ON(!(inode->i_state & I_NEW)); - } - } + if (new) + test = v9fs_test_new_inode_dotl; + else + test = v9fs_test_inode_dotl; + inode = iget5_locked(sb, QID2INO(qid), test, v9fs_set_inode_dotl, st); + if (!inode) + return ERR_PTR(-ENOMEM); + if (!(inode->i_state & I_NEW)) + return inode; /* * initialize the inode with the stat info * FIXME!! we may need support for stale inodes * later. */ - st = p9_client_getattr_dotl(fid, P9_STATS_BASIC | P9_STATS_GEN); - if (IS_ERR(st)) { - retval = PTR_ERR(st); - goto error; - } - - retval = v9fs_init_inode(v9ses, inode, &fid->qid, + inode->i_ino = QID2INO(qid); + retval = v9fs_init_inode(v9ses, inode, st->st_mode, new_decode_dev(st->st_rdev)); - v9fs_stat2inode_dotl(st, inode, 0); - kfree(st); if (retval) goto error; + v9fs_stat2inode_dotl(st, inode, 0); v9fs_set_netfs_context(inode); v9fs_cache_inode_get_cookie(inode); retval = v9fs_get_acl(inode, fid); @@ -103,11 +133,27 @@ v9fs_fid_iget_dotl(struct super_block *sb, struct p9_fid *fid, bool new) goto error; unlock_new_inode(inode); -done: return inode; error: iget_failed(inode); return ERR_PTR(retval); + +} + +struct inode * +v9fs_inode_from_fid_dotl(struct v9fs_session_info *v9ses, struct p9_fid *fid, + struct super_block *sb, int new) +{ + struct p9_stat_dotl *st; + struct inode *inode = NULL; + + st = p9_client_getattr_dotl(fid, P9_STATS_BASIC | P9_STATS_GEN); + if (IS_ERR(st)) + return ERR_CAST(st); + + inode = v9fs_qid_iget_dotl(sb, &st->qid, fid, st, new); + kfree(st); + return inode; } struct dotl_openflag_map { @@ -259,7 +305,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err); goto out; } - inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true); + inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", err); @@ -309,6 +355,7 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap, umode_t omode) { int err; + struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL, *dfid = NULL; kgid_t gid; const unsigned char *name; @@ -318,6 +365,7 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap, struct posix_acl *dacl = NULL, *pacl = NULL; p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry); + v9ses = v9fs_inode2v9ses(dir); omode |= S_IFDIR; if (dir->i_mode & S_ISGID) @@ -352,7 +400,7 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap, } /* instantiate inode and assign the unopened fid to the dentry */ - inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true); + inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", @@ -749,6 +797,7 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir, kgid_t gid; const unsigned char *name; umode_t mode; + struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL, *dfid = NULL; struct inode *inode; struct p9_qid qid; @@ -758,6 +807,7 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir, dir->i_ino, dentry, omode, MAJOR(rdev), MINOR(rdev)); + v9ses = v9fs_inode2v9ses(dir); dfid = v9fs_parent_fid(dentry); if (IS_ERR(dfid)) { err = PTR_ERR(dfid); @@ -788,7 +838,7 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir, err); goto error; } - inode = v9fs_fid_iget_dotl(dir->i_sb, fid, true); + inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); p9_debug(P9_DEBUG_VFS, "inode creation failed %d\n", diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index f52fdf42945c..489db161abc9 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -139,7 +139,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, else sb->s_d_op = &v9fs_dentry_operations; - inode = v9fs_get_inode_from_fid(v9ses, fid, sb, true); + inode = v9fs_get_new_inode_from_fid(v9ses, fid, sb); if (IS_ERR(inode)) { retval = PTR_ERR(inode); goto release_sb; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index f8622ed72e08..ada363af5aab 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -12,6 +12,7 @@ #include <linux/swap.h> #include <linux/ctype.h> #include <linux/sched.h> +#include <linux/iversion.h> #include <linux/task_io_accounting_ops.h> #include "internal.h" #include "afs_fs.h" @@ -1823,6 +1824,8 @@ error: static void afs_rename_success(struct afs_operation *op) { + struct afs_vnode *vnode = AFS_FS_I(d_inode(op->dentry)); + _enter("op=%08x", op->debug_id); op->ctime = op->file[0].scb.status.mtime_client; @@ -1832,6 +1835,22 @@ static void afs_rename_success(struct afs_operation *op) op->ctime = op->file[1].scb.status.mtime_client; afs_vnode_commit_status(op, &op->file[1]); } + + /* If we're moving a subdir between dirs, we need to update + * its DV counter too as the ".." will be altered. + */ + if (S_ISDIR(vnode->netfs.inode.i_mode) && + op->file[0].vnode != op->file[1].vnode) { + u64 new_dv; + + write_seqlock(&vnode->cb_lock); + + new_dv = vnode->status.data_version + 1; + vnode->status.data_version = new_dv; + inode_set_iversion_raw(&vnode->netfs.inode, new_dv); + + write_sequnlock(&vnode->cb_lock); + } } static void afs_rename_edit_dir(struct afs_operation *op) @@ -1873,6 +1892,12 @@ static void afs_rename_edit_dir(struct afs_operation *op) &vnode->fid, afs_edit_dir_for_rename_2); } + if (S_ISDIR(vnode->netfs.inode.i_mode) && + new_dvnode != orig_dvnode && + test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) + afs_edit_dir_update_dotdot(vnode, new_dvnode, + afs_edit_dir_for_rename_sub); + new_inode = d_inode(new_dentry); if (new_inode) { spin_lock(&new_inode->i_lock); diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index a71bff10496b..fe223fb78111 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -127,10 +127,10 @@ static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index) /* * Scan a directory block looking for a dirent of the right name. */ -static int afs_dir_scan_block(union afs_xdr_dir_block *block, struct qstr *name, +static int afs_dir_scan_block(const union afs_xdr_dir_block *block, const struct qstr *name, unsigned int blocknum) { - union afs_xdr_dirent *de; + const union afs_xdr_dirent *de; u64 bitmap; int d, len, n; @@ -492,3 +492,90 @@ error: clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); goto out_unmap; } + +/* + * Edit a subdirectory that has been moved between directories to update the + * ".." entry. + */ +void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_dvnode, + enum afs_edit_dir_reason why) +{ + union afs_xdr_dir_block *block; + union afs_xdr_dirent *de; + struct folio *folio; + unsigned int nr_blocks, b; + pgoff_t index; + loff_t i_size; + int slot; + + _enter(""); + + i_size = i_size_read(&vnode->netfs.inode); + if (i_size < AFS_DIR_BLOCK_SIZE) { + clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + return; + } + nr_blocks = i_size / AFS_DIR_BLOCK_SIZE; + + /* Find a block that has sufficient slots available. Each folio + * contains two or more directory blocks. + */ + for (b = 0; b < nr_blocks; b++) { + index = b / AFS_DIR_BLOCKS_PER_PAGE; + folio = afs_dir_get_folio(vnode, index); + if (!folio) + goto error; + + block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_pos(folio)); + + /* Abandon the edit if we got a callback break. */ + if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) + goto invalidated; + + slot = afs_dir_scan_block(block, &dotdot_name, b); + if (slot >= 0) + goto found_dirent; + + kunmap_local(block); + folio_unlock(folio); + folio_put(folio); + } + + /* Didn't find the dirent to clobber. Download the directory again. */ + trace_afs_edit_dir(vnode, why, afs_edit_dir_update_nodd, + 0, 0, 0, 0, ".."); + clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + goto out; + +found_dirent: + de = &block->dirents[slot]; + de->u.vnode = htonl(new_dvnode->fid.vnode); + de->u.unique = htonl(new_dvnode->fid.unique); + + trace_afs_edit_dir(vnode, why, afs_edit_dir_update_dd, b, slot, + ntohl(de->u.vnode), ntohl(de->u.unique), ".."); + + kunmap_local(block); + folio_unlock(folio); + folio_put(folio); + inode_set_iversion_raw(&vnode->netfs.inode, vnode->status.data_version); + +out: + _leave(""); + return; + +invalidated: + kunmap_local(block); + folio_unlock(folio); + folio_put(folio); + trace_afs_edit_dir(vnode, why, afs_edit_dir_update_inval, + 0, 0, 0, 0, ".."); + clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + goto out; + +error: + trace_afs_edit_dir(vnode, why, afs_edit_dir_update_error, + 0, 0, 0, 0, ".."); + clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); + goto out; +} diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 52aab09a32a9..c9d620175e80 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1073,6 +1073,8 @@ extern void afs_check_for_remote_deletion(struct afs_operation *); extern void afs_edit_dir_add(struct afs_vnode *, struct qstr *, struct afs_fid *, enum afs_edit_dir_reason); extern void afs_edit_dir_remove(struct afs_vnode *, struct qstr *, enum afs_edit_dir_reason); +void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_dvnode, + enum afs_edit_dir_reason why); /* * dir_silly.c diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c index f011e026358e..6d57efbb8110 100644 --- a/fs/autofs/dev-ioctl.c +++ b/fs/autofs/dev-ioctl.c @@ -110,6 +110,7 @@ static inline void free_dev_ioctl(struct autofs_dev_ioctl *param) */ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) { + unsigned int inr = _IOC_NR(cmd); int err; err = check_dev_ioctl_version(cmd, param); @@ -133,7 +134,7 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) * check_name() return for AUTOFS_DEV_IOCTL_TIMEOUT_CMD. */ err = check_name(param->path); - if (cmd == AUTOFS_DEV_IOCTL_TIMEOUT_CMD) + if (inr == AUTOFS_DEV_IOCTL_TIMEOUT_CMD) err = err ? 0 : -EINVAL; if (err) { pr_warn("invalid path supplied for cmd(0x%08x)\n", @@ -141,8 +142,6 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) goto out; } } else { - unsigned int inr = _IOC_NR(cmd); - if (inr == AUTOFS_DEV_IOCTL_OPENMOUNT_CMD || inr == AUTOFS_DEV_IOCTL_REQUESTER_CMD || inr == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) { diff --git a/fs/backing-file.c b/fs/backing-file.c index 8860dac58c37..09a9be945d45 100644 --- a/fs/backing-file.c +++ b/fs/backing-file.c @@ -80,7 +80,7 @@ struct backing_aio { refcount_t ref; struct kiocb *orig_iocb; /* used for aio completion */ - void (*end_write)(struct file *); + void (*end_write)(struct file *, loff_t, ssize_t); struct work_struct work; long res; }; @@ -109,7 +109,7 @@ static void backing_aio_cleanup(struct backing_aio *aio, long res) struct kiocb *orig_iocb = aio->orig_iocb; if (aio->end_write) - aio->end_write(orig_iocb->ki_filp); + aio->end_write(orig_iocb->ki_filp, iocb->ki_pos, res); orig_iocb->ki_pos = iocb->ki_pos; backing_aio_put(aio); @@ -239,7 +239,7 @@ ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter, ret = vfs_iter_write(file, iter, &iocb->ki_pos, rwf); if (ctx->end_write) - ctx->end_write(ctx->user_file); + ctx->end_write(ctx->user_file, iocb->ki_pos, ret); } else { struct backing_aio *aio; @@ -317,7 +317,7 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe, revert_creds(old_cred); if (ctx->end_write) - ctx->end_write(ctx->user_file); + ctx->end_write(ctx->user_file, ppos ? *ppos : 0, ret); return ret; } diff --git a/fs/bcachefs/alloc_background.h b/fs/bcachefs/alloc_background.h index f8e87c6721b1..163a67b97a40 100644 --- a/fs/bcachefs/alloc_background.h +++ b/fs/bcachefs/alloc_background.h @@ -168,6 +168,9 @@ static inline bool data_type_movable(enum bch_data_type type) static inline u64 alloc_lru_idx_fragmentation(struct bch_alloc_v4 a, struct bch_dev *ca) { + if (a.data_type >= BCH_DATA_NR) + return 0; + if (!data_type_movable(a.data_type) || !bch2_bucket_sectors_fragmented(ca, a)) return 0; diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c index 5836870ab882..372178c8d416 100644 --- a/fs/bcachefs/alloc_foreground.c +++ b/fs/bcachefs/alloc_foreground.c @@ -162,6 +162,10 @@ static void open_bucket_free_unused(struct bch_fs *c, struct open_bucket *ob) ARRAY_SIZE(c->open_buckets_partial)); spin_lock(&c->freelist_lock); + rcu_read_lock(); + bch2_dev_rcu(c, ob->dev)->nr_partial_buckets++; + rcu_read_unlock(); + ob->on_partial_list = true; c->open_buckets_partial[c->open_buckets_partial_nr++] = ob - c->open_buckets; @@ -972,7 +976,7 @@ static int bucket_alloc_set_partial(struct bch_fs *c, u64 avail; bch2_dev_usage_read_fast(ca, &usage); - avail = dev_buckets_free(ca, usage, watermark); + avail = dev_buckets_free(ca, usage, watermark) + ca->nr_partial_buckets; if (!avail) continue; @@ -981,6 +985,10 @@ static int bucket_alloc_set_partial(struct bch_fs *c, i); ob->on_partial_list = false; + rcu_read_lock(); + bch2_dev_rcu(c, ob->dev)->nr_partial_buckets--; + rcu_read_unlock(); + ret = add_new_bucket(c, ptrs, devs_may_alloc, nr_replicas, nr_effective, have_cache, ob); @@ -1191,7 +1199,13 @@ void bch2_open_buckets_stop(struct bch_fs *c, struct bch_dev *ca, --c->open_buckets_partial_nr; swap(c->open_buckets_partial[i], c->open_buckets_partial[c->open_buckets_partial_nr]); + ob->on_partial_list = false; + + rcu_read_lock(); + bch2_dev_rcu(c, ob->dev)->nr_partial_buckets--; + rcu_read_unlock(); + spin_unlock(&c->freelist_lock); bch2_open_bucket_put(c, ob); spin_lock(&c->freelist_lock); @@ -1610,8 +1624,7 @@ void bch2_open_buckets_to_text(struct printbuf *out, struct bch_fs *c, ob < c->open_buckets + ARRAY_SIZE(c->open_buckets); ob++) { spin_lock(&ob->lock); - if (ob->valid && !ob->on_partial_list && - (!ca || ob->dev == ca->dev_idx)) + if (ob->valid && (!ca || ob->dev == ca->dev_idx)) bch2_open_bucket_to_text(out, c, ob); spin_unlock(&ob->lock); } diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index f4151ee51b03..e94a83b8113e 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -555,6 +555,7 @@ struct bch_dev { u64 alloc_cursor[3]; unsigned nr_open_buckets; + unsigned nr_partial_buckets; unsigned nr_btree_reserve; size_t inc_gen_needs_gc; diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index 0883cf6e1a3e..eef9b89c561d 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -882,6 +882,18 @@ static noinline int btree_node_iter_and_journal_peek(struct btree_trans *trans, __bch2_btree_and_journal_iter_init_node_iter(trans, &jiter, l->b, l->iter, path->pos); k = bch2_btree_and_journal_iter_peek(&jiter); + if (!k.k) { + struct printbuf buf = PRINTBUF; + + prt_str(&buf, "node not found at pos "); + bch2_bpos_to_text(&buf, path->pos); + prt_str(&buf, " at btree "); + bch2_btree_pos_to_text(&buf, c, l->b); + + ret = bch2_fs_topology_error(c, "%s", buf.buf); + printbuf_exit(&buf); + goto err; + } bch2_bkey_buf_reassemble(out, c, k); @@ -889,6 +901,7 @@ static noinline int btree_node_iter_and_journal_peek(struct btree_trans *trans, c->opts.btree_node_prefetch) ret = btree_path_prefetch_j(trans, path, &jiter); +err: bch2_btree_and_journal_iter_exit(&jiter); return ret; } diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index a6ee0beee6b0..8e75a852b358 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -236,7 +236,8 @@ static int __bch2_data_update_index_update(struct btree_trans *trans, if (((1U << i) & m->data_opts.rewrite_ptrs) && (ptr = bch2_extent_has_ptr(old, p, bkey_i_to_s(insert))) && !ptr->cached) { - bch2_extent_ptr_set_cached(bkey_i_to_s(insert), ptr); + bch2_extent_ptr_set_cached(c, &m->op.opts, + bkey_i_to_s(insert), ptr); rewrites_found |= 1U << i; } i++; @@ -284,7 +285,8 @@ restart_drop_extra_replicas: durability - ptr_durability >= m->op.opts.data_replicas) { durability -= ptr_durability; - bch2_extent_ptr_set_cached(bkey_i_to_s(insert), &entry->ptr); + bch2_extent_ptr_set_cached(c, &m->op.opts, + bkey_i_to_s(insert), &entry->ptr); goto restart_drop_extra_replicas; } } @@ -295,7 +297,7 @@ restart_drop_extra_replicas: bch2_extent_ptr_decoded_append(insert, &p); bch2_bkey_narrow_crcs(insert, (struct bch_extent_crc_unpacked) { 0 }); - bch2_extent_normalize(c, bkey_i_to_s(insert)); + bch2_extent_normalize_by_opts(c, &m->op.opts, bkey_i_to_s(insert)); ret = bch2_sum_sector_overwrites(trans, &iter, insert, &should_check_enospc, @@ -558,7 +560,8 @@ void bch2_data_update_to_text(struct printbuf *out, struct data_update *m) int bch2_extent_drop_ptrs(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, - struct data_update_opts data_opts) + struct bch_io_opts *io_opts, + struct data_update_opts *data_opts) { struct bch_fs *c = trans->c; struct bkey_i *n; @@ -569,11 +572,11 @@ int bch2_extent_drop_ptrs(struct btree_trans *trans, if (ret) return ret; - while (data_opts.kill_ptrs) { - unsigned i = 0, drop = __fls(data_opts.kill_ptrs); + while (data_opts->kill_ptrs) { + unsigned i = 0, drop = __fls(data_opts->kill_ptrs); bch2_bkey_drop_ptrs_noerror(bkey_i_to_s(n), ptr, i++ == drop); - data_opts.kill_ptrs ^= 1U << drop; + data_opts->kill_ptrs ^= 1U << drop; } /* @@ -581,7 +584,7 @@ int bch2_extent_drop_ptrs(struct btree_trans *trans, * will do the appropriate thing with it (turning it into a * KEY_TYPE_error key, or just a discard if it was a cached extent) */ - bch2_extent_normalize(c, bkey_i_to_s(n)); + bch2_extent_normalize_by_opts(c, io_opts, bkey_i_to_s(n)); /* * Since we're not inserting through an extent iterator @@ -720,7 +723,7 @@ int bch2_data_update_init(struct btree_trans *trans, m->data_opts.rewrite_ptrs = 0; /* if iter == NULL, it's just a promote */ if (iter) - ret = bch2_extent_drop_ptrs(trans, iter, k, m->data_opts); + ret = bch2_extent_drop_ptrs(trans, iter, k, &io_opts, &m->data_opts); goto out; } diff --git a/fs/bcachefs/data_update.h b/fs/bcachefs/data_update.h index 8d36365bdea8..e4b50723428e 100644 --- a/fs/bcachefs/data_update.h +++ b/fs/bcachefs/data_update.h @@ -40,7 +40,8 @@ void bch2_data_update_read_done(struct data_update *, int bch2_extent_drop_ptrs(struct btree_trans *, struct btree_iter *, struct bkey_s_c, - struct data_update_opts); + struct bch_io_opts *, + struct data_update_opts *); void bch2_data_update_exit(struct data_update *); int bch2_data_update_init(struct btree_trans *, struct btree_iter *, diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c index a0aa5bb467d9..749dcf368841 100644 --- a/fs/bcachefs/ec.c +++ b/fs/bcachefs/ec.c @@ -1870,6 +1870,10 @@ __bch2_ec_stripe_head_get(struct btree_trans *trans, } h = ec_new_stripe_head_alloc(c, disk_label, algo, redundancy, watermark); + if (!h) { + h = ERR_PTR(-BCH_ERR_ENOMEM_stripe_head_alloc); + goto err; + } found: if (h->rw_devs_change_count != c->rw_devs_change_count) ec_stripe_head_devs_update(c, h); diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index 649263516ab1..a1bc6c7a8ba0 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -83,6 +83,7 @@ x(ENOMEM, ENOMEM_fs_other_alloc) \ x(ENOMEM, ENOMEM_dev_alloc) \ x(ENOMEM, ENOMEM_disk_accounting) \ + x(ENOMEM, ENOMEM_stripe_head_alloc) \ x(ENOSPC, ENOSPC_disk_reservation) \ x(ENOSPC, ENOSPC_bucket_alloc) \ x(ENOSPC, ENOSPC_disk_label_add) \ @@ -222,6 +223,7 @@ x(BCH_ERR_invalid_sb_layout, invalid_sb_layout_type) \ x(BCH_ERR_invalid_sb_layout, invalid_sb_layout_nr_superblocks) \ x(BCH_ERR_invalid_sb_layout, invalid_sb_layout_superblocks_overlap) \ + x(BCH_ERR_invalid_sb_layout, invalid_sb_layout_sb_max_size_bits) \ x(BCH_ERR_invalid_sb, invalid_sb_members_missing) \ x(BCH_ERR_invalid_sb, invalid_sb_members) \ x(BCH_ERR_invalid_sb, invalid_sb_disk_groups) \ diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index cc0d22085aef..c4e91d123849 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -978,31 +978,54 @@ bch2_extent_has_ptr(struct bkey_s_c k1, struct extent_ptr_decoded p1, struct bke return NULL; } -void bch2_extent_ptr_set_cached(struct bkey_s k, struct bch_extent_ptr *ptr) +static bool want_cached_ptr(struct bch_fs *c, struct bch_io_opts *opts, + struct bch_extent_ptr *ptr) +{ + if (!opts->promote_target || + !bch2_dev_in_target(c, ptr->dev, opts->promote_target)) + return false; + + struct bch_dev *ca = bch2_dev_rcu_noerror(c, ptr->dev); + + return ca && bch2_dev_is_readable(ca) && !dev_ptr_stale_rcu(ca, ptr); +} + +void bch2_extent_ptr_set_cached(struct bch_fs *c, + struct bch_io_opts *opts, + struct bkey_s k, + struct bch_extent_ptr *ptr) { struct bkey_ptrs ptrs = bch2_bkey_ptrs(k); union bch_extent_entry *entry; - union bch_extent_entry *ec = NULL; + struct extent_ptr_decoded p; - bkey_extent_entry_for_each(ptrs, entry) { + rcu_read_lock(); + if (!want_cached_ptr(c, opts, ptr)) { + bch2_bkey_drop_ptr_noerror(k, ptr); + goto out; + } + + /* + * Stripes can't contain cached data, for - reasons. + * + * Possibly something we can fix in the future? + */ + bkey_for_each_ptr_decode(k.k, ptrs, p, entry) if (&entry->ptr == ptr) { - ptr->cached = true; - if (ec) - extent_entry_drop(k, ec); - return; + if (p.has_ec) + bch2_bkey_drop_ptr_noerror(k, ptr); + else + ptr->cached = true; + goto out; } - if (extent_entry_is_stripe_ptr(entry)) - ec = entry; - else if (extent_entry_is_ptr(entry)) - ec = NULL; - } - BUG(); +out: + rcu_read_unlock(); } /* - * bch_extent_normalize - clean up an extent, dropping stale pointers etc. + * bch2_extent_normalize - clean up an extent, dropping stale pointers etc. * * Returns true if @k should be dropped entirely * @@ -1016,8 +1039,39 @@ bool bch2_extent_normalize(struct bch_fs *c, struct bkey_s k) rcu_read_lock(); bch2_bkey_drop_ptrs(k, ptr, ptr->cached && - (ca = bch2_dev_rcu(c, ptr->dev)) && - dev_ptr_stale_rcu(ca, ptr) > 0); + (!(ca = bch2_dev_rcu(c, ptr->dev)) || + dev_ptr_stale_rcu(ca, ptr) > 0)); + rcu_read_unlock(); + + return bkey_deleted(k.k); +} + +/* + * bch2_extent_normalize_by_opts - clean up an extent, dropping stale pointers etc. + * + * Like bch2_extent_normalize(), but also only keeps a single cached pointer on + * the promote target. + */ +bool bch2_extent_normalize_by_opts(struct bch_fs *c, + struct bch_io_opts *opts, + struct bkey_s k) +{ + struct bkey_ptrs ptrs; + bool have_cached_ptr; + + rcu_read_lock(); +restart_drop_ptrs: + ptrs = bch2_bkey_ptrs(k); + have_cached_ptr = false; + + bkey_for_each_ptr(ptrs, ptr) + if (ptr->cached) { + if (have_cached_ptr || !want_cached_ptr(c, opts, ptr)) { + bch2_bkey_drop_ptr(k, ptr); + goto restart_drop_ptrs; + } + have_cached_ptr = true; + } rcu_read_unlock(); return bkey_deleted(k.k); diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h index 923a5f1849a8..bcffcf60aaaf 100644 --- a/fs/bcachefs/extents.h +++ b/fs/bcachefs/extents.h @@ -686,9 +686,12 @@ bool bch2_extents_match(struct bkey_s_c, struct bkey_s_c); struct bch_extent_ptr * bch2_extent_has_ptr(struct bkey_s_c, struct extent_ptr_decoded, struct bkey_s); -void bch2_extent_ptr_set_cached(struct bkey_s, struct bch_extent_ptr *); +void bch2_extent_ptr_set_cached(struct bch_fs *, struct bch_io_opts *, + struct bkey_s, struct bch_extent_ptr *); +bool bch2_extent_normalize_by_opts(struct bch_fs *, struct bch_io_opts *, struct bkey_s); bool bch2_extent_normalize(struct bch_fs *, struct bkey_s); + void bch2_extent_ptr_to_text(struct printbuf *out, struct bch_fs *, const struct bch_extent_ptr *); void bch2_bkey_ptrs_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c); diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c index 15d3f073b824..2456c41b215e 100644 --- a/fs/bcachefs/fs-io.c +++ b/fs/bcachefs/fs-io.c @@ -587,7 +587,7 @@ static noinline int __bchfs_fallocate(struct bch_inode_info *inode, int mode, POS(inode->v.i_ino, start_sector), BTREE_ITER_slots|BTREE_ITER_intent); - while (!ret && bkey_lt(iter.pos, end_pos)) { + while (!ret) { s64 i_sectors_delta = 0; struct quota_res quota_res = { 0 }; struct bkey_s_c k; @@ -598,6 +598,9 @@ static noinline int __bchfs_fallocate(struct bch_inode_info *inode, int mode, bch2_trans_begin(trans); + if (bkey_ge(iter.pos, end_pos)) + break; + ret = bch2_subvolume_get_snapshot(trans, inode->ei_inum.subvol, &snapshot); if (ret) @@ -634,12 +637,15 @@ static noinline int __bchfs_fallocate(struct bch_inode_info *inode, int mode, if (bch2_clamp_data_hole(&inode->v, &hole_start, &hole_end, - opts.data_replicas, true)) + opts.data_replicas, true)) { ret = drop_locks_do(trans, (bch2_clamp_data_hole(&inode->v, &hole_start, &hole_end, opts.data_replicas, false), 0)); + if (ret) + goto bkey_err; + } bch2_btree_iter_set_pos(&iter, POS(iter.pos.inode, hole_start)); if (ret) @@ -667,10 +673,13 @@ static noinline int __bchfs_fallocate(struct bch_inode_info *inode, int mode, bch2_i_sectors_acct(c, inode, "a_res, i_sectors_delta); if (bch2_mark_pagecache_reserved(inode, &hole_start, - iter.pos.offset, true)) - drop_locks_do(trans, + iter.pos.offset, true)) { + ret = drop_locks_do(trans, bch2_mark_pagecache_reserved(inode, &hole_start, iter.pos.offset, false)); + if (ret) + goto bkey_err; + } bkey_err: bch2_quota_reservation_put(c, inode, "a_res); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c index 8c456d8b8b99..0ef4a86850bb 100644 --- a/fs/bcachefs/move.c +++ b/fs/bcachefs/move.c @@ -266,7 +266,7 @@ int bch2_move_extent(struct moving_context *ctxt, if (!data_opts.rewrite_ptrs && !data_opts.extra_replicas) { if (data_opts.kill_ptrs) - return bch2_extent_drop_ptrs(trans, iter, k, data_opts); + return bch2_extent_drop_ptrs(trans, iter, k, &io_opts, &data_opts); return 0; } diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 454b5a32dd7f..32d15aacc069 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -94,11 +94,10 @@ static void bch2_reconstruct_alloc(struct bch_fs *c) __set_bit_le64(BCH_FSCK_ERR_accounting_mismatch, ext->errors_silent); c->sb.compat &= ~(1ULL << BCH_COMPAT_alloc_info); - bch2_write_super(c); - mutex_unlock(&c->sb_lock); - c->opts.recovery_passes |= bch2_recovery_passes_from_stable(le64_to_cpu(ext->recovery_passes_required[0])); + bch2_write_super(c); + mutex_unlock(&c->sb_lock); bch2_shoot_down_journal_keys(c, BTREE_ID_alloc, 0, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); @@ -1002,6 +1001,7 @@ int bch2_fs_initialize(struct bch_fs *c) struct bch_inode_unpacked root_inode, lostfound_inode; struct bkey_inode_buf packed_inode; struct qstr lostfound = QSTR("lost+found"); + struct bch_member *m; int ret; bch_notice(c, "initializing new filesystem"); @@ -1018,6 +1018,14 @@ int bch2_fs_initialize(struct bch_fs *c) SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, bcachefs_metadata_version_current); bch2_write_super(c); } + + for_each_member_device(c, ca) { + m = bch2_members_v2_get_mut(c->disk_sb.sb, ca->dev_idx); + SET_BCH_MEMBER_FREESPACE_INITIALIZED(m, false); + ca->mi = bch2_mi_to_cpu(m); + } + + bch2_write_super(c); mutex_unlock(&c->sb_lock); c->curr_recovery_pass = BCH_RECOVERY_PASS_NR; diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index ae715ff658e8..8767c33c2b51 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -143,6 +143,9 @@ UPGRADE_TABLE() static int have_stripes(struct bch_fs *c) { + if (IS_ERR_OR_NULL(c->btree_roots_known[BTREE_ID_stripes].b)) + return 0; + return !btree_node_fake(c->btree_roots_known[BTREE_ID_stripes].b); } diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index ce7410d72089..7c71594f6a8b 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -287,6 +287,11 @@ static int validate_sb_layout(struct bch_sb_layout *layout, struct printbuf *out return -BCH_ERR_invalid_sb_layout_nr_superblocks; } + if (layout->sb_max_size_bits > BCH_SB_LAYOUT_SIZE_BITS_MAX) { + prt_printf(out, "Invalid superblock layout: max_size_bits too high"); + return -BCH_ERR_invalid_sb_layout_sb_max_size_bits; + } + max_sectors = 1 << layout->sb_max_size_bits; prev_offset = le64_to_cpu(layout->sb_offset[0]); diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index fec5c6cde0a7..7e0f9600b80c 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -49,6 +49,7 @@ void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info, bbio->end_io = end_io; bbio->private = private; atomic_set(&bbio->pending_ios, 1); + WRITE_ONCE(bbio->status, BLK_STS_OK); } /* @@ -113,41 +114,29 @@ static void __btrfs_bio_end_io(struct btrfs_bio *bbio) } } -static void btrfs_orig_write_end_io(struct bio *bio); - -static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio, - struct btrfs_bio *orig_bbio) -{ - /* - * For writes we tolerate nr_mirrors - 1 write failures, so we can't - * just blindly propagate a write failure here. Instead increment the - * error count in the original I/O context so that it is guaranteed to - * be larger than the error tolerance. - */ - if (bbio->bio.bi_end_io == &btrfs_orig_write_end_io) { - struct btrfs_io_stripe *orig_stripe = orig_bbio->bio.bi_private; - struct btrfs_io_context *orig_bioc = orig_stripe->bioc; - - atomic_add(orig_bioc->max_errors, &orig_bioc->error); - } else { - orig_bbio->bio.bi_status = bbio->bio.bi_status; - } -} - void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status) { bbio->bio.bi_status = status; if (bbio->bio.bi_pool == &btrfs_clone_bioset) { struct btrfs_bio *orig_bbio = bbio->private; - if (bbio->bio.bi_status) - btrfs_bbio_propagate_error(bbio, orig_bbio); btrfs_cleanup_bio(bbio); bbio = orig_bbio; } - if (atomic_dec_and_test(&bbio->pending_ios)) + /* + * At this point, bbio always points to the original btrfs_bio. Save + * the first error in it. + */ + if (status != BLK_STS_OK) + cmpxchg(&bbio->status, BLK_STS_OK, status); + + if (atomic_dec_and_test(&bbio->pending_ios)) { + /* Load split bio's error which might be set above. */ + if (status == BLK_STS_OK) + bbio->bio.bi_status = READ_ONCE(bbio->status); __btrfs_bio_end_io(bbio); + } } static int next_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror) diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h index e48612340745..e2fe16074ad6 100644 --- a/fs/btrfs/bio.h +++ b/fs/btrfs/bio.h @@ -79,6 +79,9 @@ struct btrfs_bio { /* File system that this I/O operates on. */ struct btrfs_fs_info *fs_info; + /* Save the first error status of split bio. */ + blk_status_t status; + /* * This member must come last, bio_alloc_bioset will allocate enough * bytes for entire btrfs_bio but relies on bio being last. diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c index b95ef44c326b..968dae953948 100644 --- a/fs/btrfs/defrag.c +++ b/fs/btrfs/defrag.c @@ -763,12 +763,12 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start, * We can get a merged extent, in that case, we need to re-search * tree to get the original em for defrag. * - * If @newer_than is 0 or em::generation < newer_than, we can trust - * this em, as either we don't care about the generation, or the - * merged extent map will be rejected anyway. + * This is because even if we have adjacent extents that are contiguous + * and compatible (same type and flags), we still want to defrag them + * so that we use less metadata (extent items in the extent tree and + * file extent items in the inode's subvolume tree). */ - if (em && (em->flags & EXTENT_FLAG_MERGED) && - newer_than && em->generation >= newer_than) { + if (em && (em->flags & EXTENT_FLAG_MERGED)) { free_extent_map(em); em = NULL; } diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 668c617444a5..1d93e1202c33 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -230,7 +230,12 @@ static bool mergeable_maps(const struct extent_map *prev, const struct extent_ma if (extent_map_end(prev) != next->start) return false; - if (prev->flags != next->flags) + /* + * The merged flag is not an on-disk flag, it just indicates we had the + * extent maps of 2 (or more) adjacent extents merged, so factor it out. + */ + if ((prev->flags & ~EXTENT_FLAG_MERGED) != + (next->flags & ~EXTENT_FLAG_MERGED)) return false; if (next->disk_bytenr < EXTENT_MAP_LAST_BYTE - 1) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 8f340ad1d938..eb51b609190f 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1105,6 +1105,7 @@ static void btrfs_close_one_device(struct btrfs_device *device) if (device->bdev) { fs_devices->open_devices--; device->bdev = NULL; + device->bdev_file = NULL; } clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); btrfs_destroy_dev_zone_info(device); @@ -1262,35 +1262,46 @@ static s64 dax_unshare_iter(struct iomap_iter *iter) { struct iomap *iomap = &iter->iomap; const struct iomap *srcmap = iomap_iter_srcmap(iter); - loff_t pos = iter->pos; - loff_t length = iomap_length(iter); + loff_t copy_pos = iter->pos; + u64 copy_len = iomap_length(iter); + u32 mod; int id = 0; s64 ret = 0; void *daddr = NULL, *saddr = NULL; - /* don't bother with blocks that are not shared to start with */ - if (!(iomap->flags & IOMAP_F_SHARED)) - return length; + if (!iomap_want_unshare_iter(iter)) + return iomap_length(iter); + + /* + * Extend the file range to be aligned to fsblock/pagesize, because + * we need to copy entire blocks, not just the byte range specified. + * Invalidate the mapping because we're about to CoW. + */ + mod = offset_in_page(copy_pos); + if (mod) { + copy_len += mod; + copy_pos -= mod; + } + + mod = offset_in_page(copy_pos + copy_len); + if (mod) + copy_len += PAGE_SIZE - mod; + + invalidate_inode_pages2_range(iter->inode->i_mapping, + copy_pos >> PAGE_SHIFT, + (copy_pos + copy_len - 1) >> PAGE_SHIFT); id = dax_read_lock(); - ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL); + ret = dax_iomap_direct_access(iomap, copy_pos, copy_len, &daddr, NULL); if (ret < 0) goto out_unlock; - /* zero the distance if srcmap is HOLE or UNWRITTEN */ - if (srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN) { - memset(daddr, 0, length); - dax_flush(iomap->dax_dev, daddr, length); - ret = length; - goto out_unlock; - } - - ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL); + ret = dax_iomap_direct_access(srcmap, copy_pos, copy_len, &saddr, NULL); if (ret < 0) goto out_unlock; - if (copy_mc_to_kernel(daddr, saddr, length) == 0) - ret = length; + if (copy_mc_to_kernel(daddr, saddr, copy_len) == 0) + ret = iomap_length(iter); else ret = -EIO; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 320d586c3896..bed3dbe5b7cb 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -709,7 +709,9 @@ static int erofs_fc_get_tree(struct fs_context *fc) if (IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) return get_tree_nodev(fc, erofs_fc_fill_super); - ret = get_tree_bdev(fc, erofs_fc_fill_super); + ret = get_tree_bdev_flags(fc, erofs_fc_fill_super, + IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) ? + GET_TREE_BDEV_QUIET_LOOKUP : 0); #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE if (ret == -ENOTBLK) { if (!fc->source) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 1ae4542f0bd8..83bcb559b89f 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -420,7 +420,9 @@ static bool busy_loop_ep_timeout(unsigned long start_time, static bool ep_busy_loop_on(struct eventpoll *ep) { - return !!READ_ONCE(ep->busy_poll_usecs) || net_busy_loop_on(); + return !!READ_ONCE(ep->busy_poll_usecs) || + READ_ONCE(ep->prefer_busy_poll) || + net_busy_loop_on(); } static bool ep_busy_loop_end(void *p, unsigned long start_time) @@ -455,6 +457,8 @@ static bool ep_busy_loop(struct eventpoll *ep, int nonblock) * it back in when we have moved a socket with a valid NAPI * ID onto the ready list. */ + if (prefer_busy_poll) + napi_resume_irqs(napi_id); ep->napi_id = 0; return false; } @@ -538,6 +542,22 @@ static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, } } +static void ep_suspend_napi_irqs(struct eventpoll *ep) +{ + unsigned int napi_id = READ_ONCE(ep->napi_id); + + if (napi_id >= MIN_NAPI_ID && READ_ONCE(ep->prefer_busy_poll)) + napi_suspend_irqs(napi_id); +} + +static void ep_resume_napi_irqs(struct eventpoll *ep) +{ + unsigned int napi_id = READ_ONCE(ep->napi_id); + + if (napi_id >= MIN_NAPI_ID && READ_ONCE(ep->prefer_busy_poll)) + napi_resume_irqs(napi_id); +} + #else static inline bool ep_busy_loop(struct eventpoll *ep, int nonblock) @@ -555,6 +575,14 @@ static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, return -EOPNOTSUPP; } +static void ep_suspend_napi_irqs(struct eventpoll *ep) +{ +} + +static void ep_resume_napi_irqs(struct eventpoll *ep) +{ +} + #endif /* CONFIG_NET_RX_BUSY_POLL */ /* @@ -786,6 +814,7 @@ static bool ep_refcount_dec_and_test(struct eventpoll *ep) static void ep_free(struct eventpoll *ep) { + ep_resume_napi_irqs(ep); mutex_destroy(&ep->mtx); free_uid(ep->user); wakeup_source_unregister(ep->ws); @@ -2003,8 +2032,11 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, * trying again in search of more luck. */ res = ep_send_events(ep, events, maxevents); - if (res) + if (res) { + if (res > 0) + ep_suspend_napi_irqs(ep); return res; + } } if (timed_out) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index f33fbce86ae0..dafdf766b1d5 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2288,6 +2288,13 @@ static int fuse_writepages_fill(struct folio *folio, struct folio *tmp_folio; int err; + if (!data->ff) { + err = -EIO; + data->ff = fuse_write_file_get(fi); + if (!data->ff) + goto out_unlock; + } + if (wpa && fuse_writepage_need_send(fc, &folio->page, ap, data)) { fuse_writepages_send(data); data->wpa = NULL; @@ -2351,13 +2358,13 @@ static int fuse_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; - struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_fill_wb_data data; int err; + err = -EIO; if (fuse_is_bad(inode)) - return -EIO; + goto out; if (wbc->sync_mode == WB_SYNC_NONE && fc->num_background >= fc->congestion_threshold) @@ -2365,9 +2372,7 @@ static int fuse_writepages(struct address_space *mapping, data.inode = inode; data.wpa = NULL; - data.ff = fuse_write_file_get(fi); - if (!data.ff) - return -EIO; + data.ff = NULL; err = -ENOMEM; data.orig_pages = kcalloc(fc->max_pages, @@ -2381,10 +2386,11 @@ static int fuse_writepages(struct address_space *mapping, WARN_ON(!data.wpa->ia.ap.num_pages); fuse_writepages_send(&data); } + if (data.ff) + fuse_file_put(data.ff, false); kfree(data.orig_pages); out: - fuse_file_put(data.ff, false); return err; } diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c index 62aee8289d11..bbac547dfcb3 100644 --- a/fs/fuse/passthrough.c +++ b/fs/fuse/passthrough.c @@ -18,11 +18,11 @@ static void fuse_file_accessed(struct file *file) fuse_invalidate_atime(inode); } -static void fuse_file_modified(struct file *file) +static void fuse_passthrough_end_write(struct file *file, loff_t pos, ssize_t ret) { struct inode *inode = file_inode(file); - fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE); + fuse_write_update_attr(inode, pos, ret); } ssize_t fuse_passthrough_read_iter(struct kiocb *iocb, struct iov_iter *iter) @@ -63,7 +63,7 @@ ssize_t fuse_passthrough_write_iter(struct kiocb *iocb, struct backing_file_ctx ctx = { .cred = ff->cred, .user_file = file, - .end_write = fuse_file_modified, + .end_write = fuse_passthrough_end_write, }; pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu\n", __func__, @@ -110,7 +110,7 @@ ssize_t fuse_passthrough_splice_write(struct pipe_inode_info *pipe, struct backing_file_ctx ctx = { .cred = ff->cred, .user_file = out, - .end_write = fuse_file_modified, + .end_write = fuse_passthrough_end_write, }; pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu, flags=0x%x\n", __func__, @@ -234,7 +234,6 @@ int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map) goto out; backing_sb = file_inode(file)->i_sb; - pr_info("%s: %x:%pD %i\n", __func__, backing_sb->s_dev, file, backing_sb->s_stack_depth); res = -ELOOP; if (backing_sb->s_stack_depth >= fc->max_stack_depth) goto out_fput; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index aa587b2142e2..ef0b68bccbb6 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1277,22 +1277,7 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter) loff_t length = iomap_length(iter); loff_t written = 0; - /* Don't bother with blocks that are not shared to start with. */ - if (!(iomap->flags & IOMAP_F_SHARED)) - return length; - - /* - * Don't bother with delalloc reservations, holes or unwritten extents. - * - * Note that we use srcmap directly instead of iomap_iter_srcmap as - * unsharing requires providing a separate source map, and the presence - * of one is a good indicator that unsharing is needed, unlike - * IOMAP_F_SHARED which can be set for any data that goes into the COW - * fork for XFS. - */ - if (iter->srcmap.type == IOMAP_HOLE || - iter->srcmap.type == IOMAP_DELALLOC || - iter->srcmap.type == IOMAP_UNWRITTEN) + if (!iomap_want_unshare_iter(iter)) return length; do { diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 114282398716..03ecc7765615 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -181,8 +181,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) #if IS_ENABLED(CONFIG_NFS_LOCALIO) seqlock_init(&clp->cl_boot_lock); ktime_get_real_ts64(&clp->cl_nfssvc_boot); - clp->cl_uuid.net = NULL; - clp->cl_uuid.dom = NULL; + nfs_uuid_init(&clp->cl_uuid); spin_lock_init(&clp->cl_localio_lock); #endif /* CONFIG_NFS_LOCALIO */ diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 542c7d97b235..596f35170137 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -205,12 +205,15 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) nfs_fscache_invalidate(inode, 0); flags &= ~NFS_INO_REVAL_FORCED; - nfsi->cache_validity |= flags; + flags |= nfsi->cache_validity; + if (inode->i_mapping->nrpages == 0) + flags &= ~NFS_INO_INVALID_DATA; - if (inode->i_mapping->nrpages == 0) { - nfsi->cache_validity &= ~NFS_INO_INVALID_DATA; - nfs_ooo_clear(nfsi); - } else if (nfsi->cache_validity & NFS_INO_INVALID_DATA) { + /* pairs with nfs_clear_invalid_mapping()'s smp_load_acquire() */ + smp_store_release(&nfsi->cache_validity, flags); + + if (inode->i_mapping->nrpages == 0 || + nfsi->cache_validity & NFS_INO_INVALID_DATA) { nfs_ooo_clear(nfsi); } trace_nfs_set_cache_invalid(inode, 0); @@ -628,23 +631,35 @@ nfs_fattr_fixup_delegated(struct inode *inode, struct nfs_fattr *fattr) } } +static void nfs_update_timestamps(struct inode *inode, unsigned int ia_valid) +{ + enum file_time_flags time_flags = 0; + unsigned int cache_flags = 0; + + if (ia_valid & ATTR_MTIME) { + time_flags |= S_MTIME | S_CTIME; + cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME; + } + if (ia_valid & ATTR_ATIME) { + time_flags |= S_ATIME; + cache_flags |= NFS_INO_INVALID_ATIME; + } + inode_update_timestamps(inode, time_flags); + NFS_I(inode)->cache_validity &= ~cache_flags; +} + void nfs_update_delegated_atime(struct inode *inode) { spin_lock(&inode->i_lock); - if (nfs_have_delegated_atime(inode)) { - inode_update_timestamps(inode, S_ATIME); - NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ATIME; - } + if (nfs_have_delegated_atime(inode)) + nfs_update_timestamps(inode, ATTR_ATIME); spin_unlock(&inode->i_lock); } void nfs_update_delegated_mtime_locked(struct inode *inode) { - if (nfs_have_delegated_mtime(inode)) { - inode_update_timestamps(inode, S_CTIME | S_MTIME); - NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_CTIME | - NFS_INO_INVALID_MTIME); - } + if (nfs_have_delegated_mtime(inode)) + nfs_update_timestamps(inode, ATTR_MTIME); } void nfs_update_delegated_mtime(struct inode *inode) @@ -682,15 +697,16 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, attr->ia_valid &= ~ATTR_SIZE; } - if (nfs_have_delegated_mtime(inode)) { - if (attr->ia_valid & ATTR_MTIME) { - nfs_update_delegated_mtime(inode); - attr->ia_valid &= ~ATTR_MTIME; - } - if (attr->ia_valid & ATTR_ATIME) { - nfs_update_delegated_atime(inode); - attr->ia_valid &= ~ATTR_ATIME; - } + if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) { + spin_lock(&inode->i_lock); + nfs_update_timestamps(inode, attr->ia_valid); + spin_unlock(&inode->i_lock); + attr->ia_valid &= ~(ATTR_MTIME | ATTR_ATIME); + } else if (nfs_have_delegated_atime(inode) && + attr->ia_valid & ATTR_ATIME && + !(attr->ia_valid & ATTR_MTIME)) { + nfs_update_delegated_atime(inode); + attr->ia_valid &= ~ATTR_ATIME; } /* Optimization: if the end result is no change, don't RPC */ @@ -1408,6 +1424,13 @@ int nfs_clear_invalid_mapping(struct address_space *mapping) TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); if (ret) goto out; + smp_rmb(); /* pairs with smp_wmb() below */ + if (test_bit(NFS_INO_INVALIDATING, bitlock)) + continue; + /* pairs with nfs_set_cache_invalid()'s smp_store_release() */ + if (!(smp_load_acquire(&nfsi->cache_validity) & NFS_INO_INVALID_DATA)) + goto out; + /* Slow-path that double-checks with spinlock held */ spin_lock(&inode->i_lock); if (test_bit(NFS_INO_INVALIDATING, bitlock)) { spin_unlock(&inode->i_lock); @@ -1633,6 +1656,7 @@ void nfs_fattr_init(struct nfs_fattr *fattr) fattr->gencount = nfs_inc_attr_generation_counter(); fattr->owner_name = NULL; fattr->group_name = NULL; + fattr->mdsthreshold = NULL; } EXPORT_SYMBOL_GPL(nfs_fattr_init); diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index d0aa680ec816..8f0ce82a677e 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -205,7 +205,8 @@ void nfs_local_probe(struct nfs_client *clp) nfs_local_disable(clp); } - nfs_uuid_begin(&clp->cl_uuid); + if (!nfs_uuid_begin(&clp->cl_uuid)) + return; if (nfs_server_uuid_is_local(clp)) nfs_local_enable(clp); nfs_uuid_end(&clp->cl_uuid); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index cd2fbde2e6d7..9d40319e063d 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3452,6 +3452,10 @@ static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, adjust_flags |= NFS_INO_INVALID_MODE; if (sattr->ia_valid & (ATTR_UID | ATTR_GID)) adjust_flags |= NFS_INO_INVALID_OTHER; + if (sattr->ia_valid & ATTR_ATIME) + adjust_flags |= NFS_INO_INVALID_ATIME; + if (sattr->ia_valid & ATTR_MTIME) + adjust_flags |= NFS_INO_INVALID_MTIME; do { nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, fattr->label), diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 9723b6c53397..ae5c5e39afa0 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -885,7 +885,15 @@ static int nfs_request_mount(struct fs_context *fc, * Now ask the mount server to map our export path * to a file handle. */ - status = nfs_mount(&request, ctx->timeo, ctx->retrans); + if ((request.protocol == XPRT_TRANSPORT_UDP) == + !(ctx->flags & NFS_MOUNT_TCP)) + /* + * NFS protocol and mount protocol are both UDP or neither UDP + * so timeouts are compatible. Use NFS timeouts for MOUNT + */ + status = nfs_mount(&request, ctx->timeo, ctx->retrans); + else + status = nfs_mount(&request, NFS_UNSPEC_TIMEO, NFS_UNSPEC_RETRANS); if (status != 0) { dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n", request.hostname, status); diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c index 5c8ce5066c16..09404d142d1a 100644 --- a/fs/nfs_common/nfslocalio.c +++ b/fs/nfs_common/nfslocalio.c @@ -5,7 +5,7 @@ */ #include <linux/module.h> -#include <linux/rculist.h> +#include <linux/list.h> #include <linux/nfslocalio.h> #include <net/netns/generic.h> @@ -20,15 +20,27 @@ static DEFINE_SPINLOCK(nfs_uuid_lock); */ static LIST_HEAD(nfs_uuids); -void nfs_uuid_begin(nfs_uuid_t *nfs_uuid) +void nfs_uuid_init(nfs_uuid_t *nfs_uuid) { nfs_uuid->net = NULL; nfs_uuid->dom = NULL; - uuid_gen(&nfs_uuid->uuid); + INIT_LIST_HEAD(&nfs_uuid->list); +} +EXPORT_SYMBOL_GPL(nfs_uuid_init); +bool nfs_uuid_begin(nfs_uuid_t *nfs_uuid) +{ spin_lock(&nfs_uuid_lock); - list_add_tail_rcu(&nfs_uuid->list, &nfs_uuids); + /* Is this nfs_uuid already in use? */ + if (!list_empty(&nfs_uuid->list)) { + spin_unlock(&nfs_uuid_lock); + return false; + } + uuid_gen(&nfs_uuid->uuid); + list_add_tail(&nfs_uuid->list, &nfs_uuids); spin_unlock(&nfs_uuid_lock); + + return true; } EXPORT_SYMBOL_GPL(nfs_uuid_begin); @@ -36,7 +48,8 @@ void nfs_uuid_end(nfs_uuid_t *nfs_uuid) { if (nfs_uuid->net == NULL) { spin_lock(&nfs_uuid_lock); - list_del_init(&nfs_uuid->list); + if (nfs_uuid->net == NULL) + list_del_init(&nfs_uuid->list); spin_unlock(&nfs_uuid_lock); } } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index b5a6bf4f459f..d32f2dfd148f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1841,14 +1841,12 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (!async_copy) goto out_err; async_copy->cp_nn = nn; + INIT_LIST_HEAD(&async_copy->copies); + refcount_set(&async_copy->refcount, 1); /* Arbitrary cap on number of pending async copy operations */ if (atomic_inc_return(&nn->pending_async_copies) > - (int)rqstp->rq_pool->sp_nrthreads) { - atomic_dec(&nn->pending_async_copies); + (int)rqstp->rq_pool->sp_nrthreads) goto out_err; - } - INIT_LIST_HEAD(&async_copy->copies); - refcount_set(&async_copy->refcount, 1); async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); if (!async_copy->cp_src) goto out_err; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 56b261608af4..551d2958ec29 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1359,21 +1359,47 @@ static void destroy_delegation(struct nfs4_delegation *dp) destroy_unhashed_deleg(dp); } +/** + * revoke_delegation - perform nfs4 delegation structure cleanup + * @dp: pointer to the delegation + * + * This function assumes that it's called either from the administrative + * interface (nfsd4_revoke_states()) that's revoking a specific delegation + * stateid or it's called from a laundromat thread (nfsd4_landromat()) that + * determined that this specific state has expired and needs to be revoked + * (both mark state with the appropriate stid sc_status mode). It is also + * assumed that a reference was taken on the @dp state. + * + * If this function finds that the @dp state is SC_STATUS_FREED it means + * that a FREE_STATEID operation for this stateid has been processed and + * we can proceed to removing it from recalled list. However, if @dp state + * isn't marked SC_STATUS_FREED, it means we need place it on the cl_revoked + * list and wait for the FREE_STATEID to arrive from the client. At the same + * time, we need to mark it as SC_STATUS_FREEABLE to indicate to the + * nfsd4_free_stateid() function that this stateid has already been added + * to the cl_revoked list and that nfsd4_free_stateid() is now responsible + * for removing it from the list. Inspection of where the delegation state + * in the revocation process is protected by the clp->cl_lock. + */ static void revoke_delegation(struct nfs4_delegation *dp) { struct nfs4_client *clp = dp->dl_stid.sc_client; WARN_ON(!list_empty(&dp->dl_recall_lru)); + WARN_ON_ONCE(!(dp->dl_stid.sc_status & + (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED))); trace_nfsd_stid_revoke(&dp->dl_stid); - if (dp->dl_stid.sc_status & - (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED)) { - spin_lock(&clp->cl_lock); - refcount_inc(&dp->dl_stid.sc_count); - list_add(&dp->dl_recall_lru, &clp->cl_revoked); - spin_unlock(&clp->cl_lock); + spin_lock(&clp->cl_lock); + if (dp->dl_stid.sc_status & SC_STATUS_FREED) { + list_del_init(&dp->dl_recall_lru); + goto out; } + list_add(&dp->dl_recall_lru, &clp->cl_revoked); + dp->dl_stid.sc_status |= SC_STATUS_FREEABLE; +out: + spin_unlock(&clp->cl_lock); destroy_unhashed_deleg(dp); } @@ -1780,6 +1806,7 @@ void nfsd4_revoke_states(struct net *net, struct super_block *sb) mutex_unlock(&stp->st_mutex); break; case SC_TYPE_DELEG: + refcount_inc(&stid->sc_count); dp = delegstateid(stid); spin_lock(&state_lock); if (!unhash_delegation_locked( @@ -6545,6 +6572,7 @@ nfs4_laundromat(struct nfsd_net *nn) dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); if (!state_expired(<, dp->dl_time)) break; + refcount_inc(&dp->dl_stid.sc_count); unhash_delegation_locked(dp, SC_STATUS_REVOKED); list_add(&dp->dl_recall_lru, &reaplist); } @@ -7157,7 +7185,9 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, s->sc_status |= SC_STATUS_CLOSED; spin_unlock(&s->sc_lock); dp = delegstateid(s); - list_del_init(&dp->dl_recall_lru); + if (s->sc_status & SC_STATUS_FREEABLE) + list_del_init(&dp->dl_recall_lru); + s->sc_status |= SC_STATUS_FREED; spin_unlock(&cl->cl_lock); nfs4_put_stid(s); ret = nfs_ok; @@ -7487,7 +7517,9 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) return status; - status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, 0, &s, nn); + status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, + SC_STATUS_REVOKED | SC_STATUS_FREEABLE, + &s, nn); if (status) goto out; dp = delegstateid(s); @@ -8684,7 +8716,7 @@ nfs4_state_shutdown_net(struct net *net) struct nfsd_net *nn = net_generic(net, nfsd_net_id); shrinker_free(nn->nfsd_client_shrinker); - cancel_work(&nn->nfsd_shrinker_work); + cancel_work_sync(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 79c743c01a47..35b3564c065f 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -114,6 +114,8 @@ struct nfs4_stid { /* For a deleg stateid kept around only to process free_stateid's: */ #define SC_STATUS_REVOKED BIT(1) #define SC_STATUS_ADMIN_REVOKED BIT(2) +#define SC_STATUS_FREEABLE BIT(3) +#define SC_STATUS_FREED BIT(4) unsigned short sc_status; struct list_head sc_cp_list; diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 4905063790c5..9b108052d9f7 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -157,6 +157,9 @@ static int nilfs_symlink(struct mnt_idmap *idmap, struct inode *dir, /* slow symlink */ inode->i_op = &nilfs_symlink_inode_operations; inode_nohighmem(inode); + mapping_set_gfp_mask(inode->i_mapping, + mapping_gfp_constraint(inode->i_mapping, + ~__GFP_FS)); inode->i_mapping->a_ops = &nilfs_aops; err = page_symlink(inode, symname, l); if (err) diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 5436eb0424bd..10def4b55995 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -401,6 +401,7 @@ void nilfs_clear_folio_dirty(struct folio *folio) folio_clear_uptodate(folio); folio_clear_mappedtodisk(folio); + folio_clear_checked(folio); head = folio_buffers(folio); if (head) { diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 58887456e3c5..06af21982c16 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1787,6 +1787,14 @@ int ocfs2_remove_inode_range(struct inode *inode, return 0; if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + int id_count = ocfs2_max_inline_data_with_xattr(inode->i_sb, di); + + if (byte_start > id_count || byte_start + byte_len > id_count) { + ret = -EINVAL; + mlog_errno(ret); + goto out; + } + ret = ocfs2_truncate_inline(inode, di_bh, byte_start, byte_start + byte_len, 0); if (ret) { diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 4504493b20be..4444c78e2e0c 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -231,6 +231,11 @@ static void ovl_file_modified(struct file *file) ovl_copyattr(file_inode(file)); } +static void ovl_file_end_write(struct file *file, loff_t pos, ssize_t ret) +{ + ovl_file_modified(file); +} + static void ovl_file_accessed(struct file *file) { struct inode *inode, *upperinode; @@ -294,7 +299,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) struct backing_file_ctx ctx = { .cred = ovl_creds(inode->i_sb), .user_file = file, - .end_write = ovl_file_modified, + .end_write = ovl_file_end_write, }; if (!iov_iter_count(iter)) @@ -364,7 +369,7 @@ static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out, struct backing_file_ctx ctx = { .cred = ovl_creds(inode->i_sb), .user_file = out, - .end_write = ovl_file_modified, + .end_write = ovl_file_end_write, }; inode_lock(inode); diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c index f4616083faef..04bb29721419 100644 --- a/fs/proc/softirqs.c +++ b/fs/proc/softirqs.c @@ -20,7 +20,7 @@ static int show_softirqs(struct seq_file *p, void *v) for (i = 0; i < NR_SOFTIRQS; i++) { seq_printf(p, "%12s:", softirq_to_name[i]); for_each_possible_cpu(j) - seq_printf(p, " %10u", kstat_softirqs_cpu(i, j)); + seq_put_decimal_ull_width(p, " ", kstat_softirqs_cpu(i, j), 10); seq_putc(p, '\n'); } return 0; diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 000e1ef3beea..20cafdff5081 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -1780,7 +1780,7 @@ static int cifs_init_netfs(void) nomem_subreqpool: kmem_cache_destroy(cifs_io_subrequest_cachep); nomem_subreq: - mempool_destroy(&cifs_io_request_pool); + mempool_exit(&cifs_io_request_pool); nomem_reqpool: kmem_cache_destroy(cifs_io_request_cachep); nomem_req: diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 28c4e576d460..5c5a52019efa 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -920,8 +920,15 @@ static int smb3_reconfigure(struct fs_context *fc) else { kfree_sensitive(ses->password); ses->password = kstrdup(ctx->password, GFP_KERNEL); + if (!ses->password) + return -ENOMEM; kfree_sensitive(ses->password2); ses->password2 = kstrdup(ctx->password2, GFP_KERNEL); + if (!ses->password2) { + kfree_sensitive(ses->password); + ses->password = NULL; + return -ENOMEM; + } } STEAL_STRING(cifs_sb, ctx, domainname); STEAL_STRING(cifs_sb, ctx, nodename); diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index 22251743fadf..d19d4db74af8 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -30,7 +30,8 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, int mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; loff_t start_index = folio->index & ~mask; loff_t end_index = start_index | mask; - int i, n, pages, bytes, res = -ENOMEM; + loff_t index; + int i, pages, bytes, res = -ENOMEM; struct page **page, *last_page; struct squashfs_page_actor *actor; void *pageaddr; @@ -45,9 +46,9 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, return res; /* Try to grab all the pages covered by the Squashfs block */ - for (i = 0, n = start_index; n <= end_index; n++) { - page[i] = (n == folio->index) ? target_page : - grab_cache_page_nowait(target_page->mapping, n); + for (i = 0, index = start_index; index <= end_index; index++) { + page[i] = (index == folio->index) ? target_page : + grab_cache_page_nowait(target_page->mapping, index); if (page[i] == NULL) continue; diff --git a/fs/super.c b/fs/super.c index 1db230432960..c9c7223bc2a2 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1596,13 +1596,14 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, EXPORT_SYMBOL_GPL(setup_bdev_super); /** - * get_tree_bdev - Get a superblock based on a single block device + * get_tree_bdev_flags - Get a superblock based on a single block device * @fc: The filesystem context holding the parameters * @fill_super: Helper to initialise a new superblock + * @flags: GET_TREE_BDEV_* flags */ -int get_tree_bdev(struct fs_context *fc, - int (*fill_super)(struct super_block *, - struct fs_context *)) +int get_tree_bdev_flags(struct fs_context *fc, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc), unsigned int flags) { struct super_block *s; int error = 0; @@ -1613,10 +1614,10 @@ int get_tree_bdev(struct fs_context *fc, error = lookup_bdev(fc->source, &dev); if (error) { - errorf(fc, "%s: Can't lookup blockdev", fc->source); + if (!(flags & GET_TREE_BDEV_QUIET_LOOKUP)) + errorf(fc, "%s: Can't lookup blockdev", fc->source); return error; } - fc->sb_flags |= SB_NOSEC; s = sget_dev(fc, dev); if (IS_ERR(s)) @@ -1644,6 +1645,19 @@ int get_tree_bdev(struct fs_context *fc, fc->root = dget(s->s_root); return 0; } +EXPORT_SYMBOL_GPL(get_tree_bdev_flags); + +/** + * get_tree_bdev - Get a superblock based on a single block device + * @fc: The filesystem context holding the parameters + * @fill_super: Helper to initialise a new superblock + */ +int get_tree_bdev(struct fs_context *fc, + int (*fill_super)(struct super_block *, + struct fs_context *)) +{ + return get_tree_bdev_flags(fc, fill_super, 0); +} EXPORT_SYMBOL(get_tree_bdev); static int test_bdev_super(struct super_block *s, void *data) diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 1748dff58c3b..cfc614c638da 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -392,6 +392,9 @@ static int tracefs_reconfigure(struct fs_context *fc) struct tracefs_fs_info *sb_opts = sb->s_fs_info; struct tracefs_fs_info *new_opts = fc->s_fs_info; + if (!new_opts) + return 0; + sync_filesystem(sb); /* structure copy of new mount options to sb */ *sb_opts = *new_opts; @@ -478,14 +481,17 @@ static int tracefs_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_op = &tracefs_super_operations; sb->s_d_op = &tracefs_dentry_operations; - tracefs_apply_options(sb, false); - return 0; } static int tracefs_get_tree(struct fs_context *fc) { - return get_tree_single(fc, tracefs_fill_super); + int err = get_tree_single(fc, tracefs_fill_super); + + if (err) + return err; + + return tracefs_reconfigure(fc); } static void tracefs_free_fc(struct fs_context *fc) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 68cdd89c97a3..7c0bd0b55f88 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -692,6 +692,34 @@ void dup_userfaultfd_complete(struct list_head *fcs) } } +void dup_userfaultfd_fail(struct list_head *fcs) +{ + struct userfaultfd_fork_ctx *fctx, *n; + + /* + * An error has occurred on fork, we will tear memory down, but have + * allocated memory for fctx's and raised reference counts for both the + * original and child contexts (and on the mm for each as a result). + * + * These would ordinarily be taken care of by a user handling the event, + * but we are no longer doing so, so manually clean up here. + * + * mm tear down will take care of cleaning up VMA contexts. + */ + list_for_each_entry_safe(fctx, n, fcs, list) { + struct userfaultfd_ctx *octx = fctx->orig; + struct userfaultfd_ctx *ctx = fctx->new; + + atomic_dec(&octx->mmap_changing); + VM_BUG_ON(atomic_read(&octx->mmap_changing) < 0); + userfaultfd_ctx_put(octx); + userfaultfd_ctx_put(ctx); + + list_del(&fctx->list); + kfree(fctx); + } +} + void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *vm_ctx) { diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 5f0494702e0b..5ca8d0106827 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -185,17 +185,20 @@ out: } /* - * Free up the per-ag resources associated with the mount structure. + * Free up the per-ag resources within the specified AG range. */ void -xfs_free_perag( - struct xfs_mount *mp) +xfs_free_perag_range( + struct xfs_mount *mp, + xfs_agnumber_t first_agno, + xfs_agnumber_t end_agno) + { - struct xfs_perag *pag; xfs_agnumber_t agno; - for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) { - pag = xa_erase(&mp->m_perags, agno); + for (agno = first_agno; agno < end_agno; agno++) { + struct xfs_perag *pag = xa_erase(&mp->m_perags, agno); + ASSERT(pag); XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0); xfs_defer_drain_free(&pag->pag_intents_drain); @@ -270,54 +273,37 @@ xfs_agino_range( return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last); } -/* - * Free perag within the specified AG range, it is only used to free unused - * perags under the error handling path. - */ -void -xfs_free_unused_perag_range( +int +xfs_update_last_ag_size( struct xfs_mount *mp, - xfs_agnumber_t agstart, - xfs_agnumber_t agend) + xfs_agnumber_t prev_agcount) { - struct xfs_perag *pag; - xfs_agnumber_t index; + struct xfs_perag *pag = xfs_perag_grab(mp, prev_agcount - 1); - for (index = agstart; index < agend; index++) { - pag = xa_erase(&mp->m_perags, index); - if (!pag) - break; - xfs_buf_cache_destroy(&pag->pag_bcache); - xfs_defer_drain_free(&pag->pag_intents_drain); - kfree(pag); - } + if (!pag) + return -EFSCORRUPTED; + pag->block_count = __xfs_ag_block_count(mp, prev_agcount - 1, + mp->m_sb.sb_agcount, mp->m_sb.sb_dblocks); + __xfs_agino_range(mp, pag->block_count, &pag->agino_min, + &pag->agino_max); + xfs_perag_rele(pag); + return 0; } int xfs_initialize_perag( struct xfs_mount *mp, - xfs_agnumber_t agcount, + xfs_agnumber_t old_agcount, + xfs_agnumber_t new_agcount, xfs_rfsblock_t dblocks, xfs_agnumber_t *maxagi) { struct xfs_perag *pag; xfs_agnumber_t index; - xfs_agnumber_t first_initialised = NULLAGNUMBER; int error; - /* - * Walk the current per-ag tree so we don't try to initialise AGs - * that already exist (growfs case). Allocate and insert all the - * AGs we don't find ready for initialisation. - */ - for (index = 0; index < agcount; index++) { - pag = xfs_perag_get(mp, index); - if (pag) { - xfs_perag_put(pag); - continue; - } - - pag = kzalloc(sizeof(*pag), GFP_KERNEL | __GFP_RETRY_MAYFAIL); + for (index = old_agcount; index < new_agcount; index++) { + pag = kzalloc(sizeof(*pag), GFP_KERNEL); if (!pag) { error = -ENOMEM; goto out_unwind_new_pags; @@ -353,21 +339,17 @@ xfs_initialize_perag( /* Active ref owned by mount indicates AG is online. */ atomic_set(&pag->pag_active_ref, 1); - /* first new pag is fully initialized */ - if (first_initialised == NULLAGNUMBER) - first_initialised = index; - /* * Pre-calculated geometry */ - pag->block_count = __xfs_ag_block_count(mp, index, agcount, + pag->block_count = __xfs_ag_block_count(mp, index, new_agcount, dblocks); pag->min_block = XFS_AGFL_BLOCK(mp); __xfs_agino_range(mp, pag->block_count, &pag->agino_min, &pag->agino_max); } - index = xfs_set_inode_alloc(mp, agcount); + index = xfs_set_inode_alloc(mp, new_agcount); if (maxagi) *maxagi = index; @@ -381,8 +363,7 @@ out_remove_pag: out_free_pag: kfree(pag); out_unwind_new_pags: - /* unwind any prior newly initialized pags */ - xfs_free_unused_perag_range(mp, first_initialised, agcount); + xfs_free_perag_range(mp, old_agcount, index); return error; } diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h index d9cccd093b60..9edfe0e96439 100644 --- a/fs/xfs/libxfs/xfs_ag.h +++ b/fs/xfs/libxfs/xfs_ag.h @@ -144,12 +144,13 @@ __XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA) __XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES) __XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET) -void xfs_free_unused_perag_range(struct xfs_mount *mp, xfs_agnumber_t agstart, - xfs_agnumber_t agend); -int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount, - xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi); +int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t old_agcount, + xfs_agnumber_t agcount, xfs_rfsblock_t dcount, + xfs_agnumber_t *maxagi); +void xfs_free_perag_range(struct xfs_mount *mp, xfs_agnumber_t first_agno, + xfs_agnumber_t end_agno); int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno); -void xfs_free_perag(struct xfs_mount *mp); +int xfs_update_last_ag_size(struct xfs_mount *mp, xfs_agnumber_t prev_agcount); /* Passive AG references */ struct xfs_perag *xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 04f64cf9777e..22bdbb3e9980 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -1923,7 +1923,7 @@ restart: error = -EFSCORRUPTED; goto error0; } - if (flen < bestrlen) + if (flen <= bestrlen) break; busy = xfs_alloc_compute_aligned(args, fbno, flen, &rbno, &rlen, &busy_gen); diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 67478294f11a..155bbaaa496e 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -1084,9 +1084,11 @@ xrep_metadata_inode_forks( return error; /* Make sure the attr fork looks ok before we delete it. */ - error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTA); - if (error) - return error; + if (xfs_inode_hasattr(sc->ip)) { + error = xrep_metadata_inode_subtype(sc, XFS_SCRUB_TYPE_BMBTA); + if (error) + return error; + } /* Clear the reflink flag since metadata never shares. */ if (xfs_is_reflink_inode(sc->ip)) { diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index 09e893cf563c..5180cbf5a90b 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -22,6 +22,9 @@ #include "xfs_inode.h" #include "xfs_dir2.h" #include "xfs_quota.h" +#include "xfs_alloc.h" +#include "xfs_ag.h" +#include "xfs_sb.h" /* * This is the number of entries in the l_buf_cancel_table used during @@ -685,6 +688,67 @@ xlog_recover_do_inode_buffer( } /* + * Update the in-memory superblock and perag structures from the primary SB + * buffer. + * + * This is required because transactions running after growfs may require the + * updated values to be set in a previous fully commit transaction. + */ +static int +xlog_recover_do_primary_sb_buffer( + struct xfs_mount *mp, + struct xlog_recover_item *item, + struct xfs_buf *bp, + struct xfs_buf_log_format *buf_f, + xfs_lsn_t current_lsn) +{ + struct xfs_dsb *dsb = bp->b_addr; + xfs_agnumber_t orig_agcount = mp->m_sb.sb_agcount; + int error; + + xlog_recover_do_reg_buffer(mp, item, bp, buf_f, current_lsn); + + if (orig_agcount == 0) { + xfs_alert(mp, "Trying to grow file system without AGs"); + return -EFSCORRUPTED; + } + + /* + * Update the in-core super block from the freshly recovered on-disk one. + */ + xfs_sb_from_disk(&mp->m_sb, dsb); + + if (mp->m_sb.sb_agcount < orig_agcount) { + xfs_alert(mp, "Shrinking AG count in log recovery not supported"); + return -EFSCORRUPTED; + } + + /* + * Growfs can also grow the last existing AG. In this case we also need + * to update the length in the in-core perag structure and values + * depending on it. + */ + error = xfs_update_last_ag_size(mp, orig_agcount); + if (error) + return error; + + /* + * Initialize the new perags, and also update various block and inode + * allocator setting based off the number of AGs or total blocks. + * Because of the latter this also needs to happen if the agcount did + * not change. + */ + error = xfs_initialize_perag(mp, orig_agcount, mp->m_sb.sb_agcount, + mp->m_sb.sb_dblocks, &mp->m_maxagi); + if (error) { + xfs_warn(mp, "Failed recovery per-ag init: %d", error); + return error; + } + mp->m_alloc_set_aside = xfs_alloc_set_aside(mp); + return 0; +} + +/* * V5 filesystems know the age of the buffer on disk being recovered. We can * have newer objects on disk than we are replaying, and so for these cases we * don't want to replay the current change as that will make the buffer contents @@ -967,6 +1031,12 @@ xlog_recover_buf_commit_pass2( dirty = xlog_recover_do_dquot_buffer(mp, log, item, bp, buf_f); if (!dirty) goto out_release; + } else if ((xfs_blft_from_flags(buf_f) & XFS_BLFT_SB_BUF) && + xfs_buf_daddr(bp) == 0) { + error = xlog_recover_do_primary_sb_buffer(mp, item, bp, buf_f, + current_lsn); + if (error) + goto out_release; } else { xlog_recover_do_reg_buffer(mp, item, bp, buf_f, current_lsn); } diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c index e3aaa0555597..290ba8887d29 100644 --- a/fs/xfs/xfs_filestream.c +++ b/fs/xfs/xfs_filestream.c @@ -64,25 +64,31 @@ xfs_filestream_pick_ag( struct xfs_perag *pag; struct xfs_perag *max_pag = NULL; xfs_extlen_t minlen = *longest; - xfs_extlen_t free = 0, minfree, maxfree = 0; + xfs_extlen_t minfree, maxfree = 0; xfs_agnumber_t agno; bool first_pass = true; - int err; /* 2% of an AG's blocks must be free for it to be chosen. */ minfree = mp->m_sb.sb_agblocks / 50; restart: for_each_perag_wrap(mp, start_agno, agno, pag) { + int err; + trace_xfs_filestream_scan(pag, pino); + *longest = 0; err = xfs_bmap_longest_free_extent(pag, NULL, longest); if (err) { - if (err != -EAGAIN) - break; - /* Couldn't lock the AGF, skip this AG. */ - err = 0; - continue; + if (err == -EAGAIN) { + /* Couldn't lock the AGF, skip this AG. */ + err = 0; + continue; + } + xfs_perag_rele(pag); + if (max_pag) + xfs_perag_rele(max_pag); + return err; } /* Keep track of the AG with the most free blocks. */ @@ -107,8 +113,9 @@ restart: !(flags & XFS_PICK_USERDATA) || (flags & XFS_PICK_LOWSPACE))) { /* Break out, retaining the reference on the AG. */ - free = pag->pagf_freeblks; - break; + if (max_pag) + xfs_perag_rele(max_pag); + goto done; } } @@ -116,57 +123,47 @@ restart: atomic_dec(&pag->pagf_fstrms); } - if (err) { - xfs_perag_rele(pag); - if (max_pag) - xfs_perag_rele(max_pag); - return err; + /* + * Allow a second pass to give xfs_bmap_longest_free_extent() another + * attempt at locking AGFs that it might have skipped over before we + * fail. + */ + if (first_pass) { + first_pass = false; + goto restart; } - if (!pag) { - /* - * Allow a second pass to give xfs_bmap_longest_free_extent() - * another attempt at locking AGFs that it might have skipped - * over before we fail. - */ - if (first_pass) { - first_pass = false; - goto restart; - } + /* + * We must be low on data space, so run a final lowspace optimised + * selection pass if we haven't already. + */ + if (!(flags & XFS_PICK_LOWSPACE)) { + flags |= XFS_PICK_LOWSPACE; + goto restart; + } - /* - * We must be low on data space, so run a final lowspace - * optimised selection pass if we haven't already. - */ - if (!(flags & XFS_PICK_LOWSPACE)) { - flags |= XFS_PICK_LOWSPACE; - goto restart; + /* + * No unassociated AGs are available, so select the AG with the most + * free space, regardless of whether it's already in use by another + * filestream. It none suit, just use whatever AG we can grab. + */ + if (!max_pag) { + for_each_perag_wrap(args->mp, 0, start_agno, pag) { + max_pag = pag; + break; } - /* - * No unassociated AGs are available, so select the AG with the - * most free space, regardless of whether it's already in use by - * another filestream. It none suit, just use whatever AG we can - * grab. - */ - if (!max_pag) { - for_each_perag_wrap(args->mp, 0, start_agno, args->pag) - break; - atomic_inc(&args->pag->pagf_fstrms); - *longest = 0; - } else { - pag = max_pag; - free = maxfree; - atomic_inc(&pag->pagf_fstrms); - } - } else if (max_pag) { - xfs_perag_rele(max_pag); + /* Bail if there are no AGs at all to select from. */ + if (!max_pag) + return -ENOSPC; } - trace_xfs_filestream_pick(pag, pino, free); + pag = max_pag; + atomic_inc(&pag->pagf_fstrms); +done: + trace_xfs_filestream_pick(pag, pino); args->pag = pag; return 0; - } static struct xfs_inode * diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 3643cc843f62..b247d895c276 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -87,6 +87,7 @@ xfs_growfs_data_private( struct xfs_mount *mp, /* mount point for filesystem */ struct xfs_growfs_data *in) /* growfs data input struct */ { + xfs_agnumber_t oagcount = mp->m_sb.sb_agcount; struct xfs_buf *bp; int error; xfs_agnumber_t nagcount; @@ -94,7 +95,6 @@ xfs_growfs_data_private( xfs_rfsblock_t nb, nb_div, nb_mod; int64_t delta; bool lastag_extended = false; - xfs_agnumber_t oagcount; struct xfs_trans *tp; struct aghdr_init_data id = {}; struct xfs_perag *last_pag; @@ -138,16 +138,14 @@ xfs_growfs_data_private( if (delta == 0) return 0; - oagcount = mp->m_sb.sb_agcount; - /* allocate the new per-ag structures */ - if (nagcount > oagcount) { - error = xfs_initialize_perag(mp, nagcount, nb, &nagimax); - if (error) - return error; - } else if (nagcount < oagcount) { - /* TODO: shrinking the entire AGs hasn't yet completed */ + /* TODO: shrinking the entire AGs hasn't yet completed */ + if (nagcount < oagcount) return -EINVAL; - } + + /* allocate the new per-ag structures */ + error = xfs_initialize_perag(mp, oagcount, nagcount, nb, &nagimax); + if (error) + return error; if (delta > 0) error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata, @@ -231,7 +229,7 @@ out_trans_cancel: xfs_trans_cancel(tp); out_free_unused_perag: if (nagcount > oagcount) - xfs_free_unused_perag_range(mp, oagcount, nagcount); + xfs_free_perag_range(mp, oagcount, nagcount); return error; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index bcc277fc0a83..19dcb569a3e7 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1409,7 +1409,7 @@ xfs_inactive( if (S_ISREG(VFS_I(ip)->i_mode) && (ip->i_disk_size != 0 || XFS_ISIZE(ip) != 0 || - ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0)) + xfs_inode_has_filedata(ip))) truncate = 1; if (xfs_iflags_test(ip, XFS_IQUOTAUNCHECKED)) { diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 97ed912306fd..03944b6c5fba 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -292,6 +292,11 @@ static inline bool xfs_is_cow_inode(struct xfs_inode *ip) return xfs_is_reflink_inode(ip) || xfs_is_always_cow_inode(ip); } +static inline bool xfs_inode_has_filedata(const struct xfs_inode *ip) +{ + return ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0; +} + /* * Check if an inode has any data in the COW fork. This might be often false * even for inodes with the reflink flag when there is no pending COW operation. diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index a20d426ef021..2567fd2a0994 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -481,7 +481,7 @@ xfs_ioctl_setattr_xflags( if (rtflag != XFS_IS_REALTIME_INODE(ip)) { /* Can't change realtime flag if any extents are allocated. */ - if (ip->i_df.if_nextents || ip->i_delayed_blks) + if (xfs_inode_has_filedata(ip)) return -EINVAL; /* @@ -602,7 +602,7 @@ xfs_ioctl_setattr_check_extsize( if (!fa->fsx_valid) return 0; - if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_df.if_nextents && + if (S_ISREG(VFS_I(ip)->i_mode) && xfs_inode_has_filedata(ip) && XFS_FSB_TO_B(mp, ip->i_extsize) != fa->fsx_extsize) return -EINVAL; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 916531d9f83c..86da16f54be9 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -707,7 +707,7 @@ imap_needs_cow( return false; /* when zeroing we don't have to COW holes or unwritten extents */ - if (flags & IOMAP_ZERO) { + if (flags & (IOMAP_UNSHARE | IOMAP_ZERO)) { if (!nimaps || imap->br_startblock == HOLESTARTBLOCK || imap->br_state == XFS_EXT_UNWRITTEN) diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index a13bf53fea49..704aaadb61cf 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -3393,13 +3393,6 @@ xlog_do_recover( /* re-initialise in-core superblock and geometry structures */ mp->m_features |= xfs_sb_version_to_features(sbp); xfs_reinit_percpu_counters(mp); - error = xfs_initialize_perag(mp, sbp->sb_agcount, sbp->sb_dblocks, - &mp->m_maxagi); - if (error) { - xfs_warn(mp, "Failed post-recovery per-ag init: %d", error); - return error; - } - mp->m_alloc_set_aside = xfs_alloc_set_aside(mp); /* Normal transactions can now occur */ clear_bit(XLOG_ACTIVE_RECOVERY, &log->l_opstate); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 1fdd79c5bfa0..25bbcc3f4ee0 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -810,8 +810,8 @@ xfs_mountfs( /* * Allocate and initialize the per-ag data. */ - error = xfs_initialize_perag(mp, sbp->sb_agcount, mp->m_sb.sb_dblocks, - &mp->m_maxagi); + error = xfs_initialize_perag(mp, 0, sbp->sb_agcount, + mp->m_sb.sb_dblocks, &mp->m_maxagi); if (error) { xfs_warn(mp, "Failed per-ag init: %d", error); goto out_free_dir; @@ -1048,7 +1048,7 @@ xfs_mountfs( xfs_buftarg_drain(mp->m_logdev_targp); xfs_buftarg_drain(mp->m_ddev_targp); out_free_perag: - xfs_free_perag(mp); + xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount); out_free_dir: xfs_da_unmount(mp); out_remove_uuid: @@ -1129,8 +1129,7 @@ xfs_unmountfs( xfs_errortag_clearall(mp); #endif shrinker_free(mp->m_inodegc_shrinker); - xfs_free_perag(mp); - + xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount); xfs_errortag_del(mp); xfs_error_sysfs_del(mp); xchk_stats_unregister(mp->m_scrub_stats); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index ee9f0b1f548d..fcb2bad4f76e 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -691,8 +691,8 @@ DEFINE_FILESTREAM_EVENT(xfs_filestream_lookup); DEFINE_FILESTREAM_EVENT(xfs_filestream_scan); TRACE_EVENT(xfs_filestream_pick, - TP_PROTO(struct xfs_perag *pag, xfs_ino_t ino, xfs_extlen_t free), - TP_ARGS(pag, ino, free), + TP_PROTO(struct xfs_perag *pag, xfs_ino_t ino), + TP_ARGS(pag, ino), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) @@ -703,14 +703,9 @@ TRACE_EVENT(xfs_filestream_pick, TP_fast_assign( __entry->dev = pag->pag_mount->m_super->s_dev; __entry->ino = ino; - if (pag) { - __entry->agno = pag->pag_agno; - __entry->streams = atomic_read(&pag->pagf_fstrms); - } else { - __entry->agno = NULLAGNUMBER; - __entry->streams = 0; - } - __entry->free = free; + __entry->agno = pag->pag_agno; + __entry->streams = atomic_read(&pag->pagf_fstrms); + __entry->free = pag->pagf_freeblks; ), TP_printk("dev %d:%d ino 0x%llx agno 0x%x streams %d free %d", MAJOR(__entry->dev), MINOR(__entry->dev), diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h index 76e44e102780..62d368bcd9ec 100644 --- a/include/acpi/cppc_acpi.h +++ b/include/acpi/cppc_acpi.h @@ -65,7 +65,7 @@ struct cpc_desc { int write_cmd_status; int write_cmd_id; /* Lock used for RMW operations in cpc_write() */ - spinlock_t rmw_lock; + raw_spinlock_t rmw_lock; struct cpc_register_resource cpc_regs[MAX_CPC_REG_ENT]; struct acpi_psd_package domain_info; struct kobject kobj; diff --git a/include/drm/drm_kunit_helpers.h b/include/drm/drm_kunit_helpers.h index e7cc17ee4934..afdd46ef04f7 100644 --- a/include/drm/drm_kunit_helpers.h +++ b/include/drm/drm_kunit_helpers.h @@ -120,4 +120,8 @@ drm_kunit_helper_create_crtc(struct kunit *test, const struct drm_crtc_funcs *funcs, const struct drm_crtc_helper_funcs *helper_funcs); +struct drm_display_mode * +drm_kunit_display_mode_from_cea_vic(struct kunit *test, struct drm_device *dev, + u8 video_code); + #endif // DRM_KUNIT_HELPERS_H_ diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 1f0a9ff23a2c..941deffc590d 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -135,18 +135,21 @@ static inline void alloc_tag_sub_check(union codetag_ref *ref) {} #endif /* Caller should verify both ref and tag to be valid */ -static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +static inline bool __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) { alloc_tag_add_check(ref, tag); if (!ref || !tag) - return; + return false; ref->ct = &tag->ct; + return true; } -static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +static inline bool alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) { - __alloc_tag_ref_set(ref, tag); + if (unlikely(!__alloc_tag_ref_set(ref, tag))) + return false; + /* * We need in increment the call counter every time we have a new * allocation or when we split a large allocation into smaller ones. @@ -154,12 +157,13 @@ static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *t * counter because when we free each part the counter will be decremented. */ this_cpu_inc(tag->counters->calls); + return true; } static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) { - alloc_tag_ref_set(ref, tag); - this_cpu_add(tag->counters->bytes, bytes); + if (likely(alloc_tag_ref_set(ref, tag))) + this_cpu_add(tag->counters->bytes, bytes); } static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h index 4b61b0e57720..2eed0ffb5e8f 100644 --- a/include/linux/backing-file.h +++ b/include/linux/backing-file.h @@ -16,7 +16,7 @@ struct backing_file_ctx { const struct cred *cred; struct file *user_file; void (*accessed)(struct file *); - void (*end_write)(struct file *); + void (*end_write)(struct file *, loff_t, ssize_t); }; struct file *backing_file_open(const struct path *user_path, int flags, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 19d8ca8ac960..bdadb0bb6cec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -635,6 +635,7 @@ enum bpf_type_flag { */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), + /* MEM can be uninitialized. */ MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), /* DYNPTR points to memory local to the bpf program. */ @@ -700,6 +701,13 @@ enum bpf_type_flag { */ MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS), + /* MEM is being written to, often combined with MEM_UNINIT. Non-presence + * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the + * MEM_UNINIT means that memory needs to be initialized since it is also + * read. + */ + MEM_WRITE = BIT(18 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -758,10 +766,10 @@ enum bpf_arg_type { ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, - /* pointer to memory does not need to be initialized, helper function must fill - * all bytes or clear them in error case. + /* Pointer to memory does not need to be initialized, since helper function + * fills all bytes or clears them in error case. */ - ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, + ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM, /* Pointer to valid memory of size known at compile time. */ ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index aaf004d94322..e45162ef59bb 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -33,6 +33,9 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); +/* Check the allocation size for kmalloc equivalent allocator */ +int bpf_mem_alloc_check_size(bool percpu, size_t size); + /* kmalloc/kfree equivalent: */ void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size); void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9f2a6b83b49e..fa78f49d4a9a 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -146,6 +146,7 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter) BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx) BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit) +BPF_LINK_TYPE(BPF_LINK_TYPE_SOCKMAP, sockmap) #endif #ifdef CONFIG_PERF_EVENTS BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) diff --git a/include/linux/clocksource_ids.h b/include/linux/clocksource_ids.h index 2bb4d8c2f1b0..c4ef4ae2eded 100644 --- a/include/linux/clocksource_ids.h +++ b/include/linux/clocksource_ids.h @@ -6,6 +6,7 @@ enum clocksource_ids { CSID_GENERIC = 0, CSID_ARM_ARCH_COUNTER, + CSID_S390_TOD, CSID_X86_TSC_EARLY, CSID_X86_TSC, CSID_X86_KVM_CLK, diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index f805adaa316e..cd6f9aae311f 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -80,7 +80,11 @@ #define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif +#ifdef __SANITIZE_HWADDRESS__ +#define __no_sanitize_address __attribute__((__no_sanitize__("hwaddress"))) +#else #define __no_sanitize_address __attribute__((__no_sanitize_address__)) +#endif #if defined(__SANITIZE_THREAD__) #define __no_sanitize_thread __attribute__((__no_sanitize_thread__)) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 1a957ea2f4fe..0c8b9601e603 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -266,6 +266,12 @@ struct ftrace_likely_data { #define noinline_for_stack noinline /* + * Use noinline_for_tracing for functions that should not be inlined. + * For tracing reasons. + */ +#define noinline_for_tracing noinline + +/* * Sanitizer helper attributes: Because using __always_inline and * __no_sanitize_* conflict, provide helper attributes that will either expand * to __no_sanitize_* in compilation units where instrumentation is enabled diff --git a/include/linux/device.h b/include/linux/device.h index b4bde8d22697..667cb6db9019 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1078,6 +1078,9 @@ int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); +int device_for_each_child_reverse_from(struct device *parent, + struct device *from, const void *data, + int (*fn)(struct device *, const void *)); struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); struct device *device_find_child_by_name(struct device *parent, diff --git a/include/linux/dim.h b/include/linux/dim.h index 1b581ff25a15..06543fd40fcc 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -351,7 +351,8 @@ void dim_park_tired(struct dim *dim); * Takes into consideration counter wrap-around. * Returned boolean indicates whether curr_stats are reliable. */ -bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end, +bool dim_calc_stats(const struct dim_sample *start, + const struct dim_sample *end, struct dim_stats *curr_stats); /** @@ -424,7 +425,7 @@ struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode); * This is the main logic of the algorithm, where data is processed in order * to decide on next required action. */ -void net_dim(struct dim *dim, struct dim_sample end_sample); +void net_dim(struct dim *dim, const struct dim_sample *end_sample); /* RDMA DIM */ diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 81f7b623d0ba..5e4f9ab1cf75 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -26,6 +26,10 @@ struct dpll_device_ops { struct netlink_ext_ack *extack); int (*temp_get)(const struct dpll_device *dpll, void *dpll_priv, s32 *temp, struct netlink_ext_ack *extack); + int (*clock_quality_level_get)(const struct dpll_device *dpll, + void *dpll_priv, + unsigned long *qls, + struct netlink_ext_ack *extack); }; struct dpll_pin_ops { diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index 281298e77a15..808b1a5102e7 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -127,7 +127,7 @@ static inline void dql_queued(struct dql *dql, unsigned int count) if (WARN_ON_ONCE(count > DQL_MAX_OBJECT)) return; - dql->last_obj_cnt = count; + WRITE_ONCE(dql->last_obj_cnt, count); /* We want to force a write first, so that cpu do not attempt * to get cache line containing last_obj_cnt, num_queued, adj_limit diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 12f6dc567598..1199e308c8dd 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -211,7 +211,7 @@ void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id); * fields, but they are allowed to overwrite them (will be ignored). */ struct ethtool_link_ksettings { - struct ethtool_link_settings base; + struct ethtool_link_settings_hdr base; struct { __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index c13e99cbbf81..4b4bfef6f053 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -160,6 +160,12 @@ extern int get_tree_keyed(struct fs_context *fc, int setup_bdev_super(struct super_block *sb, int sb_flags, struct fs_context *fc); + +#define GET_TREE_BDEV_QUIET_LOOKUP 0x0001 +int get_tree_bdev_flags(struct fs_context *fc, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc), unsigned int flags); + extern int get_tree_bdev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)); diff --git a/include/linux/fsl/netc_global.h b/include/linux/fsl/netc_global.h new file mode 100644 index 000000000000..fdecca8c90f0 --- /dev/null +++ b/include/linux/fsl/netc_global.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* Copyright 2024 NXP + */ +#ifndef __NETC_GLOBAL_H +#define __NETC_GLOBAL_H + +#include <linux/io.h> + +static inline u32 netc_read(void __iomem *reg) +{ + return ioread32(reg); +} + +static inline void netc_write(void __iomem *reg, u32 val) +{ + iowrite32(val, reg); +} + +#endif diff --git a/include/linux/gfp.h b/include/linux/gfp.h index a951de920e20..a0a6d25f883f 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -371,28 +371,6 @@ __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mas extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); -struct page_frag_cache; -void page_frag_cache_drain(struct page_frag_cache *nc); -extern void __page_frag_cache_drain(struct page *page, unsigned int count); -void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, - gfp_t gfp_mask, unsigned int align_mask); - -static inline void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align) -{ - WARN_ON_ONCE(!is_power_of_2(align)); - return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); -} - -static inline void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask) -{ - return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); -} - -extern void page_frag_free(void *addr); - #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) diff --git a/include/linux/input.h b/include/linux/input.h index 89a0be6ee0e2..cd866b020a01 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -339,12 +339,16 @@ struct input_handler { * @name: name given to the handle by handler that created it * @dev: input device the handle is attached to * @handler: handler that works with the device through this handle + * @handle_events: event sequence handler. It is set up by the input core + * according to event handling method specified in the @handler. See + * input_handle_setup_event_handler(). + * This method is being called by the input core with interrupts disabled + * and dev->event_lock spinlock held and so it may not sleep. * @d_node: used to put the handle on device's list of attached handles * @h_node: used to put the handle on handler's list of handles from which * it gets events */ struct input_handle { - void *private; int open; @@ -353,6 +357,10 @@ struct input_handle { struct input_dev *dev; struct input_handler *handler; + unsigned int (*handle_events)(struct input_handle *handle, + struct input_value *vals, + unsigned int count); + struct list_head d_node; struct list_head h_node; }; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index d0420e962ffd..f61407e3b121 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -270,6 +270,25 @@ static inline loff_t iomap_last_written_block(struct inode *inode, loff_t pos, return round_up(pos + written, i_blocksize(inode)); } +/* + * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE + * operation. + * + * Don't bother with blocks that are not shared to start with; or mappings that + * cannot be shared, such as inline data, delalloc reservations, holes or + * unwritten extents. + * + * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing + * requires providing a separate source map, and the presence of one is a good + * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set + * for any data that goes into the COW fork for XFS. + */ +static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter) +{ + return (iter->iomap.flags & IOMAP_F_SHARED) && + iter->srcmap.type == IOMAP_MAPPED; +} + ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops, void *private); int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 11690dacd986..ec9c05044d4f 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm) return atomic_long_read(&mm->ksm_zero_pages); } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { + /* Adding mm to ksm is best effort on fork. */ if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) - return __ksm_enter(mm); - - return 0; + __ksm_enter(mm); } static inline int ksm_execve(struct mm_struct *mm) @@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_struct *mm) return 0; } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - return 0; } static inline int ksm_execve(struct mm_struct *mm) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6e3bdf8e38bc..92314ef2d978 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -521,9 +521,6 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) -#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) -#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) - /* * page_private can be used on tail pages. However, PagePrivate is only * checked by the VM on the head page. So page_private on the tail pages @@ -542,21 +539,6 @@ static inline void *folio_get_private(struct folio *folio) return folio->private; } -struct page_frag_cache { - void * va; -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - __u16 offset; - __u16 size; -#else - __u32 offset; -#endif - /* we maintain a pagecount bias, so that we dont dirty cache line - * containing page->_refcount every time we allocate a fragment. - */ - unsigned int pagecnt_bias; - bool pfmemalloc; -}; - typedef unsigned long vm_flags_t; /* diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index bff5706b76e1..a82aa80c0ba4 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -8,6 +8,7 @@ * (These are defined separately to decouple sched.h from mm_types.h as much as possible.) */ +#include <linux/align.h> #include <linux/types.h> #include <asm/page.h> @@ -43,6 +44,26 @@ struct page_frag { #endif }; +#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) +#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) +struct page_frag_cache { + /* encoded_page consists of the virtual address, pfmemalloc bit and + * order of a page. + */ + unsigned long encoded_page; + + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_refcount every time we allocate a fragment. + */ +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) && (BITS_PER_LONG <= 32) + __u16 offset; + __u16 pagecnt_bias; +#else + __u32 offset; + __u32 pagecnt_bias; +#endif +}; + /* Track pages that require TLB flushes */ struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 17506e4a2835..5b1c984daf45 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -458,9 +458,7 @@ struct lru_gen_folio { enum { MM_LEAF_TOTAL, /* total leaf entries */ - MM_LEAF_OLD, /* old leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ - MM_NONLEAF_TOTAL, /* total non-leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS @@ -557,7 +555,7 @@ struct lru_gen_memcg { void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); @@ -576,8 +574,9 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } -static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { + return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3c552b648b27..0aae346d919e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -52,6 +52,7 @@ #include <net/net_trackers.h> #include <net/net_debug.h> #include <net/dropreason-core.h> +#include <net/neighbour_tables.h> struct netpoll_info; struct device; @@ -347,6 +348,7 @@ struct gro_list { */ struct napi_config { u64 gro_flush_timeout; + u64 irq_suspend_timeout; u32 defer_hard_irqs; unsigned int napi_id; }; @@ -383,6 +385,7 @@ struct napi_struct { struct hrtimer timer; struct task_struct *thread; unsigned long gro_flush_timeout; + unsigned long irq_suspend_timeout; u32 defer_hard_irqs; /* control-path-only fields follow */ struct list_head dev_list; @@ -2032,6 +2035,9 @@ enum netdev_reg_state { * @napi_defer_hard_irqs: If not zero, provides a counter that would * allow to avoid NIC hard IRQ, on busy queues. * + * @neighbours: List heads pointing to this device's neighbours' + * dev_list, one per address-family. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2440,6 +2446,9 @@ struct net_device { */ struct net_shaper_hierarchy *net_shaper_hierarchy; #endif + + struct hlist_head neighbours[NEIGH_NR_TABLES]; + u8 priv[] ____cacheline_aligned __counted_by(priv_len); } ____cacheline_aligned; diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index b0dd9b1eef4f..3982fea79919 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -32,7 +32,8 @@ typedef struct { struct auth_domain *dom; /* auth_domain for localio */ } nfs_uuid_t; -void nfs_uuid_begin(nfs_uuid_t *); +void nfs_uuid_init(nfs_uuid_t *); +bool nfs_uuid_begin(nfs_uuid_t *); void nfs_uuid_end(nfs_uuid_t *); void nfs_uuid_is_local(const uuid_t *, struct list_head *, struct net *, struct auth_domain *, struct module *); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1b3a76710487..cc839e4365c1 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -975,12 +975,16 @@ static __always_inline bool folio_test_##fname(const struct folio *folio) \ } \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ + if (folio_test_##fname(folio)) \ + return; \ VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \ folio); \ folio->page.page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ + if (folio->page.page_type == UINT_MAX) \ + return; \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ folio->page.page_type = UINT_MAX; \ } @@ -993,11 +997,15 @@ static __always_inline int Page##uname(const struct page *page) \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ + if (Page##uname(page)) \ + return; \ VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \ page->page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ + if (page->page_type == UINT_MAX) \ + return; \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type = UINT_MAX; \ } diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h new file mode 100644 index 000000000000..41a91df82631 --- /dev/null +++ b/include/linux/page_frag_cache.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_PAGE_FRAG_CACHE_H +#define _LINUX_PAGE_FRAG_CACHE_H + +#include <linux/bits.h> +#include <linux/log2.h> +#include <linux/mm_types_task.h> +#include <linux/types.h> + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) +/* Use a full byte here to enable assembler optimization as the shift + * operation is usually expecting a byte. + */ +#define PAGE_FRAG_CACHE_ORDER_MASK GENMASK(7, 0) +#else +/* Compiler should be able to figure out we don't read things as any value + * ANDed with 0 is 0. + */ +#define PAGE_FRAG_CACHE_ORDER_MASK 0 +#endif + +#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT (PAGE_FRAG_CACHE_ORDER_MASK + 1) + +static inline bool encoded_page_decode_pfmemalloc(unsigned long encoded_page) +{ + return !!(encoded_page & PAGE_FRAG_CACHE_PFMEMALLOC_BIT); +} + +static inline void page_frag_cache_init(struct page_frag_cache *nc) +{ + nc->encoded_page = 0; +} + +static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc) +{ + return encoded_page_decode_pfmemalloc(nc->encoded_page); +} + +void page_frag_cache_drain(struct page_frag_cache *nc); +void __page_frag_cache_drain(struct page *page, unsigned int count); +void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, + gfp_t gfp_mask, unsigned int align_mask); + +static inline void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); +} + +static inline void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); +} + +void page_frag_free(void *addr); + +#endif diff --git a/include/linux/phy.h b/include/linux/phy.h index bf0eb4e5d35c..1e4127c495c0 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1885,7 +1885,6 @@ int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart); -int genphy_config_eee_advert(struct phy_device *phydev); int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); @@ -1953,7 +1952,6 @@ int genphy_c45_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data); int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data); -int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv); int genphy_c45_an_config_eee_aneg(struct phy_device *phydev); int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 48f1e0fa2a13..58009fa66102 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -31,6 +31,7 @@ #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> +#include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> @@ -2681,6 +2682,12 @@ static inline void skb_assert_len(struct sk_buff *skb) #endif /* CONFIG_DEBUG_NET */ } +#if defined(CONFIG_FAIL_SKB_REALLOC) +void skb_might_realloc(struct sk_buff *skb); +#else +static inline void skb_might_realloc(struct sk_buff *skb) {} +#endif + /* * Add data to an sk_buff */ @@ -2781,6 +2788,7 @@ static inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb_might_realloc(skb); if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; @@ -2909,9 +2917,19 @@ static inline void skb_reset_inner_headers(struct sk_buff *skb) skb->inner_transport_header = skb->transport_header; } +static inline int skb_mac_header_was_set(const struct sk_buff *skb) +{ + return skb->mac_header != (typeof(skb->mac_header))~0U; +} + static inline void skb_reset_mac_len(struct sk_buff *skb) { - skb->mac_len = skb->network_header - skb->mac_header; + if (!skb_mac_header_was_set(skb)) { + DEBUG_NET_WARN_ON_ONCE(1); + skb->mac_len = 0; + } else { + skb->mac_len = skb->network_header - skb->mac_header; + } } static inline unsigned char *skb_inner_transport_header(const struct sk_buff @@ -2927,7 +2945,10 @@ static inline int skb_inner_transport_offset(const struct sk_buff *skb) static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { - skb->inner_transport_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_transport_header))offset); + skb->inner_transport_header = offset; } static inline void skb_set_inner_transport_header(struct sk_buff *skb, @@ -2944,7 +2965,10 @@ static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) static inline void skb_reset_inner_network_header(struct sk_buff *skb) { - skb->inner_network_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_network_header))offset); + skb->inner_network_header = offset; } static inline void skb_set_inner_network_header(struct sk_buff *skb, @@ -2966,7 +2990,10 @@ static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) static inline void skb_reset_inner_mac_header(struct sk_buff *skb) { - skb->inner_mac_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_mac_header))offset); + skb->inner_mac_header = offset; } static inline void skb_set_inner_mac_header(struct sk_buff *skb, @@ -2988,7 +3015,10 @@ static inline unsigned char *skb_transport_header(const struct sk_buff *skb) static inline void skb_reset_transport_header(struct sk_buff *skb) { - skb->transport_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->transport_header))offset); + skb->transport_header = offset; } static inline void skb_set_transport_header(struct sk_buff *skb, @@ -3005,7 +3035,10 @@ static inline unsigned char *skb_network_header(const struct sk_buff *skb) static inline void skb_reset_network_header(struct sk_buff *skb) { - skb->network_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->network_header))offset); + skb->network_header = offset; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) @@ -3014,11 +3047,6 @@ static inline void skb_set_network_header(struct sk_buff *skb, const int offset) skb->network_header += offset; } -static inline int skb_mac_header_was_set(const struct sk_buff *skb) -{ - return skb->mac_header != (typeof(skb->mac_header))~0U; -} - static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); @@ -3043,7 +3071,10 @@ static inline void skb_unset_mac_header(struct sk_buff *skb) static inline void skb_reset_mac_header(struct sk_buff *skb) { - skb->mac_header = skb->data - skb->head; + long offset = skb->data - skb->head; + + DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->mac_header))offset); + skb->mac_header = offset; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) @@ -3216,6 +3247,7 @@ static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) static inline int pskb_trim(struct sk_buff *skb, unsigned int len) { + skb_might_realloc(skb); return (len < skb->len) ? __pskb_trim(skb, len) : 0; } @@ -3970,6 +4002,7 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { + skb_might_realloc(skb); if (likely(len >= skb->len)) return 0; return pskb_trim_rcsum_slow(skb, len); diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 9e9f528b1370..2f20281d4ad4 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -125,6 +125,7 @@ struct llcc_edac_reg_offset { * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids * @ecc_irq: interrupt for llcc cache error detection and reporting + * @ecc_irq_configured: 'True' if firmware has already configured the irq propagation * @version: Indicates the LLCC version */ struct llcc_drv_data { @@ -139,6 +140,7 @@ struct llcc_drv_data { u32 num_banks; unsigned long *bitmap; int ecc_irq; + bool ecc_irq_configured; u32 version; }; diff --git a/include/linux/swap.h b/include/linux/swap.h index ca533b478c21..f3e0ac20c2e8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -335,6 +335,7 @@ struct swap_info_struct { * list. */ struct work_struct discard_work; /* discard worker */ + struct work_struct reclaim_work; /* reclaim worker */ struct list_head discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 6a5e08b937b3..f88daaa76d83 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -200,7 +200,6 @@ struct tcp_sock { /* TX read-mostly hotpath cache lines */ __cacheline_group_begin(tcp_sock_read_tx); - /* timestamp of last sent data packet (for restart window) */ u32 max_window; /* Maximal window ever seen from peer */ u32 rcv_ssthresh; /* Current window clamp */ u32 reordering; /* Packet reordering metric. */ @@ -263,7 +262,7 @@ struct tcp_sock { u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ u32 pushed_seq; /* Last pushed seq, required to talk to windows */ - u32 lsndtime; + u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ u32 mdev_us; /* medium deviation */ u32 rtt_seq; /* sequence number to update rttvar */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ diff --git a/include/linux/tick.h b/include/linux/tick.h index 72744638c5b0..99c9c5a7252a 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -251,12 +251,19 @@ static inline void tick_dep_set_task(struct task_struct *tsk, if (tick_nohz_full_enabled()) tick_nohz_dep_set_task(tsk, bit); } + static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) tick_nohz_dep_clear_task(tsk, bit); } + +static inline void tick_dep_init_task(struct task_struct *tsk) +{ + atomic_set(&tsk->tick_dep_mask, 0); +} + static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { @@ -290,6 +297,7 @@ static inline void tick_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { } +static inline void tick_dep_init_task(struct task_struct *tsk) { } static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_signal(struct signal_struct *signal, diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 39c7cf82b0c2..43844510d5d0 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -38,6 +38,7 @@ #else #define can_do_masked_user_access() 0 #define masked_user_access_begin(src) NULL + #define mask_user_address(src) (src) #endif /* @@ -159,19 +160,27 @@ _inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); - if (!should_fail_usercopy() && likely(access_ok(from, n))) { + if (should_fail_usercopy()) + goto fail; + if (can_do_masked_user_access()) + from = mask_user_address(from); + else { + if (!access_ok(from, n)) + goto fail; /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); - instrument_copy_from_user_before(to, from, n); - res = raw_copy_from_user(to, from, n); - instrument_copy_from_user_after(to, from, n, res); } - if (unlikely(res)) - memset(to + (n - res), 0, res); + instrument_copy_from_user_before(to, from, n); + res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); + if (likely(!res)) + return 0; +fail: + memset(to + (n - res), 0, res); return res; } extern __must_check unsigned long diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 9fc6ce15c499..cb40f1a1d081 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -249,6 +249,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); +void dup_userfaultfd_fail(struct list_head *); extern void mremap_userfaultfd_prep(struct vm_area_struct *, struct vm_userfaultfd_ctx *); @@ -351,6 +352,10 @@ static inline void dup_userfaultfd_complete(struct list_head *l) { } +static inline void dup_userfaultfd_fail(struct list_head *l) +{ +} + static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *ctx) { diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 170fdee6339c..79c781875c09 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -17,6 +17,8 @@ * @WWAN_PORT_FIREHOSE: XML based command protocol * @WWAN_PORT_XMMRPC: Control protocol for Intel XMM modems * @WWAN_PORT_FASTBOOT: Fastboot protocol control + * @WWAN_PORT_ADB: ADB protocol control + * @WWAN_PORT_MIPC: MTK MIPC diagnostic interface * * @WWAN_PORT_MAX: Highest supported port types * @WWAN_PORT_UNKNOWN: Special value to indicate an unknown port type @@ -30,6 +32,8 @@ enum wwan_port_type { WWAN_PORT_FIREHOSE, WWAN_PORT_XMMRPC, WWAN_PORT_FASTBOOT, + WWAN_PORT_ADB, + WWAN_PORT_MIPC, /* Add new port types above this line */ diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index f03040baaefd..c858270141bc 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -52,6 +52,9 @@ void napi_busy_loop_rcu(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget); +void napi_suspend_irqs(unsigned int napi_id); +void napi_resume_irqs(unsigned int napi_id); + #else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on(void) { diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8f9853b1a5d1..27acf1292a5c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6135,6 +6135,50 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy, struct wiphy_delayed_work *dwork); /** + * wiphy_delayed_work_pending - Find out whether a wiphy delayable + * work item is currently pending. + * + * @wiphy: the wiphy, for debug purposes + * @dwork: the delayed work in question + * + * Return: true if timer is pending, false otherwise + * + * How wiphy_delayed_work_queue() works is by setting a timer which + * when it expires calls wiphy_work_queue() to queue the wiphy work. + * Because wiphy_delayed_work_queue() uses mod_timer(), if it is + * called twice and the second call happens before the first call + * deadline, the work will rescheduled for the second deadline and + * won't run before that. + * + * wiphy_delayed_work_pending() can be used to detect if calling + * wiphy_work_delayed_work_queue() would start a new work schedule + * or delayed a previous one. As seen below it cannot be used to + * detect precisely if the work has finished to execute nor if it + * is currently executing. + * + * CPU0 CPU1 + * wiphy_delayed_work_queue(wk) + * mod_timer(wk->timer) + * wiphy_delayed_work_pending(wk) -> true + * + * [...] + * expire_timers(wk->timer) + * detach_timer(wk->timer) + * wiphy_delayed_work_pending(wk) -> false + * wk->timer->function() | + * wiphy_work_queue(wk) | delayed work pending + * list_add_tail() | returns false but + * queue_work(cfg80211_wiphy_work) | wk->func() has not + * | been run yet + * [...] | + * cfg80211_wiphy_work() | + * wk->func() V + * + */ +bool wiphy_delayed_work_pending(struct wiphy *wiphy, + struct wiphy_delayed_work *dwork); + +/** * enum ieee80211_ap_reg_power - regulatory power for an Access Point * * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode diff --git a/include/net/checksum.h b/include/net/checksum.h index 1338cb92c8e7..243f972267b8 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -151,6 +151,12 @@ static inline void csum_replace(__wsum *csum, __wsum old, __wsum new) *csum = csum_add(csum_sub(*csum, old), new); } +static inline unsigned short csum_from32to16(unsigned int sum) +{ + sum += (sum >> 16) | (sum << 16); + return (unsigned short)(sum >> 16); +} + struct sk_buff; void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr); diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index d59bb96c5a02..6c5a1ea209a2 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -76,6 +76,10 @@ FN(INVALID_PROTO) \ FN(IP_INADDRERRORS) \ FN(IP_INNOROUTES) \ + FN(IP_LOCAL_SOURCE) \ + FN(IP_INVALID_SOURCE) \ + FN(IP_LOCALNET) \ + FN(IP_INVALID_DEST) \ FN(PKT_TOO_BIG) \ FN(DUP_FRAG) \ FN(FRAG_REASM_TIMEOUT) \ @@ -100,6 +104,7 @@ FN(IP_TUNNEL_ECN) \ FN(TUNNEL_TXINFO) \ FN(LOCAL_MAC) \ + FN(ARP_PVLAN_DISABLE) \ FNe(MAX) /** @@ -373,6 +378,21 @@ enum skb_drop_reason { * IPSTATS_MIB_INADDRERRORS */ SKB_DROP_REASON_IP_INNOROUTES, + /** @SKB_DROP_REASON_IP_LOCAL_SOURCE: the source ip is local */ + SKB_DROP_REASON_IP_LOCAL_SOURCE, + /** + * @SKB_DROP_REASON_IP_INVALID_SOURCE: the source ip is invalid: + * 1) source ip is multicast or limited broadcast + * 2) source ip is zero and not IGMP + */ + SKB_DROP_REASON_IP_INVALID_SOURCE, + /** @SKB_DROP_REASON_IP_LOCALNET: source or dest ip is local net */ + SKB_DROP_REASON_IP_LOCALNET, + /** + * @SKB_DROP_REASON_IP_INVALID_DEST: the dest ip is invalid: + * 1) dest ip is 0 + */ + SKB_DROP_REASON_IP_INVALID_DEST, /** * @SKB_DROP_REASON_PKT_TOO_BIG: packet size is too big (maybe exceed the * MTU) @@ -459,6 +479,12 @@ enum skb_drop_reason { */ SKB_DROP_REASON_LOCAL_MAC, /** + * @SKB_DROP_REASON_ARP_PVLAN_DISABLE: packet which is not IP is + * forwarded to the in_dev, and the proxy_arp_pvlan is not + * enabled. + */ + SKB_DROP_REASON_ARP_PVLAN_DISABLE, + /** * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which * shouldn't be used as a real 'reason' - only for tracing code gen */ diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 292cd8f4b762..596ab9791e4d 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -685,6 +685,7 @@ struct flow_cls_common_offload { u32 chain_index; __be16 protocol; u32 prio; + bool skip_sw; struct netlink_ext_ack *extack; }; diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 02fbc036f34e..813e163ce27c 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -24,25 +24,27 @@ * struct ieee80211_radiotap_header - base radiotap header */ struct ieee80211_radiotap_header { - /** - * @it_version: radiotap version, always 0 - */ - uint8_t it_version; - - /** - * @it_pad: padding (or alignment) - */ - uint8_t it_pad; - - /** - * @it_len: overall radiotap header length - */ - __le16 it_len; - - /** - * @it_present: (first) present word - */ - __le32 it_present; + __struct_group(ieee80211_radiotap_header_fixed, hdr, __packed, + /** + * @it_version: radiotap version, always 0 + */ + uint8_t it_version; + + /** + * @it_pad: padding (or alignment) + */ + uint8_t it_pad; + + /** + * @it_len: overall radiotap header length + */ + __le16 it_len; + + /** + * @it_present: (first) present word + */ + __le32 it_present; + ); /** * @it_optional: all remaining presence bitmaps @@ -50,6 +52,9 @@ struct ieee80211_radiotap_header { __le32 it_optional[]; } __packed; +static_assert(offsetof(struct ieee80211_radiotap_header, it_optional) == sizeof(struct ieee80211_radiotap_header_fixed), + "struct member likely outside of __struct_group()"); + /* version is always 0 */ #define PKTHDR_RADIOTAP_VERSION 0 diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index b6e44f4eaa4c..a113c11ab56b 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -452,6 +452,18 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); +static inline enum skb_drop_reason +fib_validate_source_reason(struct sk_buff *skb, __be32 src, __be32 dst, + dscp_t dscp, int oif, struct net_device *dev, + struct in_device *idev, u32 *itag) +{ + int err = fib_validate_source(skb, src, dst, dscp, oif, dev, idev, + itag); + if (err < 0) + return -err; + return SKB_NOT_DROPPED_YET; +} + #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 4e4f9e24c9c1..1aa31bdb2b31 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -354,7 +354,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4, memset(fl4, 0, sizeof(*fl4)); if (oif) { - fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif); + fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index(net, oif); /* Legacy VRF/l3mdev use case */ fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif; } diff --git a/include/net/mctp.h b/include/net/mctp.h index 28d59ae94ca3..1ecbff7116f6 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -298,4 +298,22 @@ void mctp_routes_exit(void); int mctp_device_init(void); void mctp_device_exit(void); +/* MCTP IDs and Codes from DMTF specification + * "DSP0239 Management Component Transport Protocol (MCTP) IDs and Codes" + * https://www.dmtf.org/sites/default/files/standards/documents/DSP0239_1.11.1.pdf + */ +enum mctp_phys_binding { + MCTP_PHYS_BINDING_UNSPEC = 0x00, + MCTP_PHYS_BINDING_SMBUS = 0x01, + MCTP_PHYS_BINDING_PCIE_VDM = 0x02, + MCTP_PHYS_BINDING_USB = 0x03, + MCTP_PHYS_BINDING_KCS = 0x04, + MCTP_PHYS_BINDING_SERIAL = 0x05, + MCTP_PHYS_BINDING_I3C = 0x06, + MCTP_PHYS_BINDING_MMBI = 0x07, + MCTP_PHYS_BINDING_PCC = 0x08, + MCTP_PHYS_BINDING_UCIE = 0x09, + MCTP_PHYS_BINDING_VENDOR = 0xFF, +}; + #endif /* __NET_MCTP_H */ diff --git a/include/net/mctpdevice.h b/include/net/mctpdevice.h index 5c0d04b5c12c..957d9ef924c5 100644 --- a/include/net/mctpdevice.h +++ b/include/net/mctpdevice.h @@ -22,6 +22,7 @@ struct mctp_dev { refcount_t refs; unsigned int net; + enum mctp_phys_binding binding; const struct mctp_netdev_ops *ops; @@ -44,7 +45,8 @@ struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev); struct mctp_dev *__mctp_dev_get(const struct net_device *dev); int mctp_register_netdev(struct net_device *dev, - const struct mctp_netdev_ops *ops); + const struct mctp_netdev_ops *ops, + enum mctp_phys_binding binding); void mctp_unregister_netdev(struct net_device *dev); void mctp_dev_hold(struct mctp_dev *mdev); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3887ed9e5026..9a832cab5b1d 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -29,6 +29,7 @@ #include <linux/sysctl.h> #include <linux/workqueue.h> #include <net/rtnetlink.h> +#include <net/neighbour_tables.h> /* * NUD stands for "neighbor unreachability detection" @@ -135,7 +136,8 @@ struct neigh_statistics { #define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field) struct neighbour { - struct neighbour __rcu *next; + struct hlist_node hash; + struct hlist_node dev_list; struct neigh_table *tbl; struct neigh_parms *parms; unsigned long confirmed; @@ -190,7 +192,7 @@ struct pneigh_entry { #define NEIGH_NUM_HASH_RND 4 struct neigh_hash_table { - struct neighbour __rcu **hash_buckets; + struct hlist_head *hash_heads; unsigned int hash_shift; __u32 hash_rnd[NEIGH_NUM_HASH_RND]; struct rcu_head rcu; @@ -236,13 +238,6 @@ struct neigh_table { struct pneigh_entry **phash_buckets; }; -enum { - NEIGH_ARP_TABLE = 0, - NEIGH_ND_TABLE = 1, - NEIGH_NR_TABLES, - NEIGH_LINK_TABLE = NEIGH_NR_TABLES /* Pseudo table for neigh_xmit */ -}; - static inline int neigh_parms_family(struct neigh_parms *p) { return p->tbl->family; @@ -275,6 +270,12 @@ static inline void *neighbour_priv(const struct neighbour *n) extern const struct nla_policy nda_policy[]; +#define neigh_for_each_in_bucket(pos, head) hlist_for_each_entry(pos, head, hash) +#define neigh_for_each_in_bucket_rcu(pos, head) \ + hlist_for_each_entry_rcu(pos, head, hash) +#define neigh_for_each_in_bucket_safe(pos, tmp, head) \ + hlist_for_each_entry_safe(pos, tmp, head, hash) + static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey) { return *(const u32 *)n->primary_key == *(const u32 *)pkey; @@ -303,12 +304,9 @@ static inline struct neighbour *___neigh_lookup_noref( u32 hash_val; hash_val = hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); - for (n = rcu_dereference(nht->hash_buckets[hash_val]); - n != NULL; - n = rcu_dereference(n->next)) { + neigh_for_each_in_bucket_rcu(n, &nht->hash_heads[hash_val]) if (n->dev == dev && key_eq(n, pkey)) return n; - } return NULL; } @@ -349,7 +347,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid); void __neigh_set_probe_once(struct neighbour *neigh); -bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl); +bool neigh_remove_one(struct neighbour *ndel); void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); int neigh_carrier_down(struct neigh_table *tbl, struct net_device *dev); diff --git a/include/net/neighbour_tables.h b/include/net/neighbour_tables.h new file mode 100644 index 000000000000..bcffbe8f7601 --- /dev/null +++ b/include/net/neighbour_tables.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NET_NEIGHBOUR_TABLES_H +#define _NET_NEIGHBOUR_TABLES_H + +enum { + NEIGH_ARP_TABLE = 0, + NEIGH_ND_TABLE = 1, + NEIGH_NR_TABLES, + NEIGH_LINK_TABLE = NEIGH_NR_TABLES /* Pseudo table for neigh_xmit */ +}; + +#endif diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 91ae20cb7648..f24278767bfd 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1103,6 +1103,7 @@ struct nft_rule_blob { * @name: name of the chain * @udlen: user data length * @udata: user data in the chain + * @rcu_head: rcu head for deferred release * @blob_next: rule blob pointer to the next in the chain */ struct nft_chain { @@ -1120,6 +1121,7 @@ struct nft_chain { char *name; u16 udlen; u8 *udata; + struct rcu_head rcu_head; /* Only used during control plane commit phase: */ struct nft_rule_blob *blob_next; @@ -1263,6 +1265,7 @@ static inline void nft_use_inc_restore(u32 *use) * @sets: sets in the table * @objects: stateful objects in the table * @flowtables: flow tables in the table + * @net: netnamespace this table belongs to * @hgenerator: handle generator state * @handle: table handle * @use: number of chain references to this table @@ -1282,6 +1285,7 @@ struct nft_table { struct list_head sets; struct list_head objects; struct list_head flowtables; + possible_net_t net; u64 hgenerator; u64 handle; u32 use; @@ -1463,7 +1467,8 @@ struct nft_flowtable { struct nf_flowtable data; }; -struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table, +struct nft_flowtable *nft_flowtable_lookup(const struct net *net, + const struct nft_table *table, const struct nlattr *nla, u8 genmask); diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 529160f76cac..4afd934b1238 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -208,6 +208,7 @@ struct netlbl_lsm_secattr { * struct netlbl_calipso_ops - NetLabel CALIPSO operations * @doi_add: add a CALIPSO DOI * @doi_free: free a CALIPSO DOI + * @doi_remove: remove a CALIPSO DOI * @doi_getdef: returns a reference to a DOI * @doi_putdef: releases a reference of a DOI * @doi_walk: enumerate the DOI list diff --git a/include/net/netlink.h b/include/net/netlink.h index db6af207287c..39eaa6be6ca8 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -142,6 +142,8 @@ * nla_get_flag(nla) return 1 if flag is true * nla_get_msecs(nla) get payload for a msecs attribute * + * The same functions also exist with _default(). + * * Attribute Misc: * nla_memcpy(dest, nla, count) copy attribute into memory * nla_memcmp(nla, data, size) compare attribute with memory area @@ -469,6 +471,7 @@ struct nla_policy { .max = _len \ } #define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len) +#define NLA_POLICY_MAX_LEN(_len) NLA_POLICY_MAX(NLA_BINARY, _len) /** * struct nl_info - netlink source information @@ -1695,6 +1698,20 @@ static inline u32 nla_get_u32(const struct nlattr *nla) } /** + * nla_get_u32_default - return payload of u32 attribute or default + * @nla: u32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u32 nla_get_u32_default(const struct nlattr *nla, u32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u32(nla); +} + +/** * nla_get_be32 - return payload of __be32 attribute * @nla: __be32 netlink attribute */ @@ -1704,6 +1721,21 @@ static inline __be32 nla_get_be32(const struct nlattr *nla) } /** + * nla_get_be32_default - return payload of be32 attribute or default + * @nla: __be32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be32 nla_get_be32_default(const struct nlattr *nla, + __be32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_be32(nla); +} + +/** * nla_get_le32 - return payload of __le32 attribute * @nla: __le32 netlink attribute */ @@ -1713,6 +1745,21 @@ static inline __le32 nla_get_le32(const struct nlattr *nla) } /** + * nla_get_le32_default - return payload of le32 attribute or default + * @nla: __le32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __le32 nla_get_le32_default(const struct nlattr *nla, + __le32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_le32(nla); +} + +/** * nla_get_u16 - return payload of u16 attribute * @nla: u16 netlink attribute */ @@ -1722,6 +1769,20 @@ static inline u16 nla_get_u16(const struct nlattr *nla) } /** + * nla_get_u16_default - return payload of u16 attribute or default + * @nla: u16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u16 nla_get_u16_default(const struct nlattr *nla, u16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u16(nla); +} + +/** * nla_get_be16 - return payload of __be16 attribute * @nla: __be16 netlink attribute */ @@ -1731,6 +1792,21 @@ static inline __be16 nla_get_be16(const struct nlattr *nla) } /** + * nla_get_be16_default - return payload of be16 attribute or default + * @nla: __be16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be16 nla_get_be16_default(const struct nlattr *nla, + __be16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_be16(nla); +} + +/** * nla_get_le16 - return payload of __le16 attribute * @nla: __le16 netlink attribute */ @@ -1740,6 +1816,21 @@ static inline __le16 nla_get_le16(const struct nlattr *nla) } /** + * nla_get_le16_default - return payload of le16 attribute or default + * @nla: __le16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __le16 nla_get_le16_default(const struct nlattr *nla, + __le16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_le16(nla); +} + +/** * nla_get_u8 - return payload of u8 attribute * @nla: u8 netlink attribute */ @@ -1749,6 +1840,20 @@ static inline u8 nla_get_u8(const struct nlattr *nla) } /** + * nla_get_u8_default - return payload of u8 attribute or default + * @nla: u8 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u8 nla_get_u8_default(const struct nlattr *nla, u8 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u8(nla); +} + +/** * nla_get_u64 - return payload of u64 attribute * @nla: u64 netlink attribute */ @@ -1762,6 +1867,20 @@ static inline u64 nla_get_u64(const struct nlattr *nla) } /** + * nla_get_u64_default - return payload of u64 attribute or default + * @nla: u64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u64 nla_get_u64_default(const struct nlattr *nla, u64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_u64(nla); +} + +/** * nla_get_uint - return payload of uint attribute * @nla: uint netlink attribute */ @@ -1773,6 +1892,20 @@ static inline u64 nla_get_uint(const struct nlattr *nla) } /** + * nla_get_uint_default - return payload of uint attribute or default + * @nla: uint netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline u64 nla_get_uint_default(const struct nlattr *nla, u64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_uint(nla); +} + +/** * nla_get_be64 - return payload of __be64 attribute * @nla: __be64 netlink attribute */ @@ -1786,6 +1919,21 @@ static inline __be64 nla_get_be64(const struct nlattr *nla) } /** + * nla_get_be64_default - return payload of be64 attribute or default + * @nla: __be64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be64 nla_get_be64_default(const struct nlattr *nla, + __be64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_be64(nla); +} + +/** * nla_get_le64 - return payload of __le64 attribute * @nla: __le64 netlink attribute */ @@ -1795,6 +1943,21 @@ static inline __le64 nla_get_le64(const struct nlattr *nla) } /** + * nla_get_le64_default - return payload of le64 attribute or default + * @nla: __le64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __le64 nla_get_le64_default(const struct nlattr *nla, + __le64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_le64(nla); +} + +/** * nla_get_s32 - return payload of s32 attribute * @nla: s32 netlink attribute */ @@ -1804,6 +1967,20 @@ static inline s32 nla_get_s32(const struct nlattr *nla) } /** + * nla_get_s32_default - return payload of s32 attribute or default + * @nla: s32 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s32 nla_get_s32_default(const struct nlattr *nla, s32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s32(nla); +} + +/** * nla_get_s16 - return payload of s16 attribute * @nla: s16 netlink attribute */ @@ -1813,6 +1990,20 @@ static inline s16 nla_get_s16(const struct nlattr *nla) } /** + * nla_get_s16_default - return payload of s16 attribute or default + * @nla: s16 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s16 nla_get_s16_default(const struct nlattr *nla, s16 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s16(nla); +} + +/** * nla_get_s8 - return payload of s8 attribute * @nla: s8 netlink attribute */ @@ -1822,6 +2013,20 @@ static inline s8 nla_get_s8(const struct nlattr *nla) } /** + * nla_get_s8_default - return payload of s8 attribute or default + * @nla: s8 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s8 nla_get_s8_default(const struct nlattr *nla, s8 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s8(nla); +} + +/** * nla_get_s64 - return payload of s64 attribute * @nla: s64 netlink attribute */ @@ -1835,6 +2040,20 @@ static inline s64 nla_get_s64(const struct nlattr *nla) } /** + * nla_get_s64_default - return payload of s64 attribute or default + * @nla: s64 netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s64 nla_get_s64_default(const struct nlattr *nla, s64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_s64(nla); +} + +/** * nla_get_sint - return payload of uint attribute * @nla: uint netlink attribute */ @@ -1846,6 +2065,20 @@ static inline s64 nla_get_sint(const struct nlattr *nla) } /** + * nla_get_sint_default - return payload of sint attribute or default + * @nla: sint netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline s64 nla_get_sint_default(const struct nlattr *nla, s64 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_sint(nla); +} + +/** * nla_get_flag - return payload of flag attribute * @nla: flag netlink attribute */ @@ -1868,6 +2101,21 @@ static inline unsigned long nla_get_msecs(const struct nlattr *nla) } /** + * nla_get_msecs_default - return payload of msecs attribute or default + * @nla: msecs netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline unsigned long nla_get_msecs_default(const struct nlattr *nla, + unsigned long defvalue) +{ + if (!nla) + return defvalue; + return nla_get_msecs(nla); +} + +/** * nla_get_in_addr - return payload of IPv4 address attribute * @nla: IPv4 address netlink attribute */ @@ -1877,6 +2125,21 @@ static inline __be32 nla_get_in_addr(const struct nlattr *nla) } /** + * nla_get_in_addr_default - return payload of be32 attribute or default + * @nla: IPv4 address netlink attribute, may be %NULL + * @defvalue: default value to use if @nla is %NULL + * + * Return: the value of the attribute, or the default value if not present + */ +static inline __be32 nla_get_in_addr_default(const struct nlattr *nla, + __be32 defvalue) +{ + if (!nla) + return defvalue; + return nla_get_in_addr(nla); +} + +/** * nla_get_in6_addr - return payload of IPv6 address attribute * @nla: IPv6 address netlink attribute */ diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index dc36519d16aa..09efcaed7c3f 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -475,7 +475,7 @@ struct nci_rf_discover_ntf { #define NCI_OP_RF_INTF_ACTIVATED_NTF nci_opcode_pack(NCI_GID_RF_MGMT, 0x05) struct activation_params_nfca_poll_iso_dep { __u8 rats_res_len; - __u8 rats_res[20]; + __u8 rats_res[NFC_ATS_MAXSIZE]; }; struct activation_params_nfcb_poll_iso_dep { diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index ea8595651c38..e180bdf2f82b 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -265,6 +265,10 @@ struct nci_dev { /* stored during intf_activated_ntf */ __u8 remote_gb[NFC_MAX_GT_LEN]; __u8 remote_gb_len; + + /* stored during intf_activated_ntf */ + __u8 target_ats[NFC_ATS_MAXSIZE]; + __u8 target_ats_len; }; /* ----- NCI Devices ----- */ diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 3a3781838c67..127e6c7d910d 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -86,6 +86,8 @@ struct nfc_ops { * is a type A one. The %sens_res most significant byte must be byte 2 * as described by the NFC Forum digital specification (i.e. the platform * configuration one) while %sens_res least significant byte is byte 1. + * @ats_len: length of Answer To Select in bytes + * @ats: Answer To Select returned by an ISO 14443 Type A target upon activation */ struct nfc_target { u32 idx; @@ -105,6 +107,8 @@ struct nfc_target { u8 is_iso15693; u8 iso15693_dsfid; u8 iso15693_uid[NFC_ISO15693_UID_MAXSIZE]; + u8 ats_len; + u8 ats[NFC_ATS_MAXSIZE]; }; /** diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 4880b3a7aced..cf199af85c52 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -755,6 +755,7 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, cls_common->chain_index = tp->chain->index; cls_common->protocol = tp->protocol; cls_common->prio = tp->prio >> 16; + cls_common->skip_sw = tc_skip_sw(flags); if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE) cls_common->extack = extack; } diff --git a/include/net/route.h b/include/net/route.h index 586e59f7ed8a..84cb1e04f5cd 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -156,12 +156,12 @@ static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 * structure is only partially set, it may bypass some fib-rules. */ static inline struct rtable *ip_route_output(struct net *net, __be32 daddr, - __be32 saddr, u8 tos, int oif, - __u8 scope) + __be32 saddr, dscp_t dscp, + int oif, __u8 scope) { struct flowi4 fl4 = { .flowi4_oif = oif, - .flowi4_tos = tos, + .flowi4_tos = inet_dscp_to_dsfield(dscp), .flowi4_scope = scope, .daddr = daddr, .saddr = saddr, @@ -199,30 +199,34 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 return ip_route_output_key(net, fl4); } -int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, - dscp_t dscp, struct net_device *dev, - struct in_device *in_dev, u32 *itag); -int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, - dscp_t dscp, struct net_device *dev); -int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, +enum skb_drop_reason +ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, dscp_t dscp, struct net_device *dev, - const struct sk_buff *hint); - -static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, - dscp_t dscp, struct net_device *devin) + struct in_device *in_dev, u32 *itag); +enum skb_drop_reason +ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev); +enum skb_drop_reason +ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev, + const struct sk_buff *hint); + +static inline enum skb_drop_reason +ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, dscp_t dscp, + struct net_device *devin) { - int err; + enum skb_drop_reason reason; rcu_read_lock(); - err = ip_route_input_noref(skb, dst, src, dscp, devin); - if (!err) { + reason = ip_route_input_noref(skb, dst, src, dscp, devin); + if (!reason) { skb_dst_force(skb); if (!skb_dst(skb)) - err = -EINVAL; + reason = SKB_DROP_REASON_NOT_SPECIFIED; } rcu_read_unlock(); - return err; + return reason; } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index b260c0cc9671..bc0069a8b6ea 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -13,6 +13,7 @@ typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = BIT(0), #define RTNL_FLAG_DOIT_PERNET RTNL_FLAG_DOIT_UNLOCKED +#define RTNL_FLAG_DOIT_PERNET_WIP RTNL_FLAG_DOIT_UNLOCKED RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1), RTNL_FLAG_DUMP_UNLOCKED = BIT(2), RTNL_FLAG_DUMP_SPLIT_NLM_DONE = BIT(3), /* legacy behavior */ @@ -71,10 +72,11 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) /** * struct rtnl_link_ops - rtnetlink link operations * - * @list: Used internally, protected by RTNL and SRCU + * @list: Used internally, protected by link_ops_mutex and SRCU * @srcu: Used internally * @kind: Identifier * @netns_refund: Physical device, move to init_net on netns exit + * @peer_type: Peer device specific netlink attribute number (e.g. VETH_INFO_PEER) * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters @@ -116,6 +118,7 @@ struct rtnl_link_ops { void (*setup)(struct net_device *dev); bool netns_refund; + const u16 peer_type; unsigned int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], @@ -164,9 +167,6 @@ struct rtnl_link_ops { int *prividx, int attr); }; -int __rtnl_link_register(struct rtnl_link_ops *ops); -void __rtnl_link_unregister(struct rtnl_link_ops *ops); - int rtnl_link_register(struct rtnl_link_ops *ops); void rtnl_link_unregister(struct rtnl_link_ops *ops); diff --git a/include/net/tcp.h b/include/net/tcp.h index 739a9fb83d0c..e9b37b76e894 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2430,6 +2430,20 @@ void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb, void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb); void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb); +static inline void tcp_warn_once(const struct sock *sk, bool cond, const char *str) +{ + WARN_ONCE(cond, + "%scwn:%u out:%u sacked:%u lost:%u retrans:%u tlp_high_seq:%u sk_state:%u ca_state:%u advmss:%u mss_cache:%u pmtu:%u\n", + str, + tcp_snd_cwnd(tcp_sk(sk)), + tcp_sk(sk)->packets_out, tcp_sk(sk)->sacked_out, + tcp_sk(sk)->lost_out, tcp_sk(sk)->retrans_out, + tcp_sk(sk)->tlp_high_seq, sk->sk_state, + inet_csk(sk)->icsk_ca_state, + tcp_sk(sk)->advmss, tcp_sk(sk)->mss_cache, + inet_csk(sk)->icsk_pmtu_cookie); +} + /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { @@ -2441,17 +2455,7 @@ static inline s64 tcp_rto_delta_us(const struct sock *sk) return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp; } else { - WARN_ONCE(1, - "rtx queue empty: " - "out:%u sacked:%u lost:%u retrans:%u " - "tlp_high_seq:%u sk_state:%u ca_state:%u " - "advmss:%u mss_cache:%u pmtu:%u\n", - tcp_sk(sk)->packets_out, tcp_sk(sk)->sacked_out, - tcp_sk(sk)->lost_out, tcp_sk(sk)->retrans_out, - tcp_sk(sk)->tlp_high_seq, sk->sk_state, - inet_csk(sk)->icsk_ca_state, - tcp_sk(sk)->advmss, tcp_sk(sk)->mss_cache, - inet_csk(sk)->icsk_pmtu_cookie); + tcp_warn_once(sk, 1, "rtx queue empty: "); return jiffies_to_usecs(rto); } diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index 1d46460d0fef..df655ce6987d 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -183,7 +183,8 @@ int tcp_ao_hash_skb(unsigned short int family, const u8 *tkey, int hash_offset, u32 sne); int tcp_parse_ao(struct sock *sk, int cmd, unsigned short int family, sockptr_t optval, int optlen); -struct tcp_ao_key *tcp_ao_established_key(struct tcp_ao_info *ao, +struct tcp_ao_key *tcp_ao_established_key(const struct sock *sk, + struct tcp_ao_info *ao, int sndid, int rcvid); int tcp_ao_copy_all_matching(const struct sock *sk, struct sock *newsk, struct request_sock *req, struct sk_buff *skb, diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h index 0d3d6beb7fdb..7f7a4932d7f1 100644 --- a/include/soc/fsl/qman.h +++ b/include/soc/fsl/qman.h @@ -242,7 +242,7 @@ static inline void qm_sg_entry_set_f(struct qm_sg_entry *sg, int len) static inline int qm_sg_entry_get_off(const struct qm_sg_entry *sg) { - return be32_to_cpu(sg->offset) & QM_SG_OFF_MASK; + return be16_to_cpu(sg->offset) & QM_SG_OFF_MASK; } /* "Frame Dequeue Response" */ diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 450c44c83a5d..a0aed1a428a1 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -331,7 +331,11 @@ enum yfs_cm_operation { EM(afs_edit_dir_delete, "delete") \ EM(afs_edit_dir_delete_error, "d_err ") \ EM(afs_edit_dir_delete_inval, "d_invl") \ - E_(afs_edit_dir_delete_noent, "d_nent") + EM(afs_edit_dir_delete_noent, "d_nent") \ + EM(afs_edit_dir_update_dd, "u_ddot") \ + EM(afs_edit_dir_update_error, "u_fail") \ + EM(afs_edit_dir_update_inval, "u_invl") \ + E_(afs_edit_dir_update_nodd, "u_nodd") #define afs_edit_dir_reasons \ EM(afs_edit_dir_for_create, "Create") \ @@ -340,6 +344,7 @@ enum yfs_cm_operation { EM(afs_edit_dir_for_rename_0, "Renam0") \ EM(afs_edit_dir_for_rename_1, "Renam1") \ EM(afs_edit_dir_for_rename_2, "Renam2") \ + EM(afs_edit_dir_for_rename_sub, "RnmSub") \ EM(afs_edit_dir_for_rmdir, "RmDir ") \ EM(afs_edit_dir_for_silly_0, "S_Ren0") \ EM(afs_edit_dir_for_silly_1, "S_Ren1") \ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index a1b126a6b0d7..d03e0bd8c028 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -287,6 +287,7 @@ EM(rxrpc_call_see_input, "SEE input ") \ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ + EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ E_(rxrpc_call_see_zap, "SEE zap ") #define rxrpc_txqueue_traces \ @@ -772,6 +773,31 @@ TRACE_EVENT(rxrpc_rx_done, TP_printk("r=%d a=%d", __entry->result, __entry->abort_code) ); +TRACE_EVENT(rxrpc_abort_call, + TP_PROTO(const struct rxrpc_call *call, int abort_code), + + TP_ARGS(call, abort_code), + + TP_STRUCT__entry( + __field(unsigned int, call_nr) + __field(enum rxrpc_abort_reason, why) + __field(int, abort_code) + __field(int, error) + ), + + TP_fast_assign( + __entry->call_nr = call->debug_id; + __entry->why = call->send_abort_why; + __entry->abort_code = abort_code; + __entry->error = call->send_abort_err; + ), + + TP_printk("c=%08x a=%d e=%d %s", + __entry->call_nr, + __entry->abort_code, __entry->error, + __print_symbolic(__entry->why, rxrpc_abort_reasons)) + ); + TRACE_EVENT(rxrpc_abort, TP_PROTO(unsigned int call_nr, enum rxrpc_abort_reason why, u32 cid, u32 call_id, rxrpc_seq_t seq, int abort_code, int error), diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e8241b320c6d..4a939c90dc2e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1121,6 +1121,9 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[] + * in sync with the definitions below. + */ enum bpf_link_type { BPF_LINK_TYPE_UNSPEC = 0, BPF_LINK_TYPE_RAW_TRACEPOINT = 1, diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index b0654ade7b7e..bf97d4b6d51f 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -79,6 +79,29 @@ enum dpll_lock_status_error { DPLL_LOCK_STATUS_ERROR_MAX = (__DPLL_LOCK_STATUS_ERROR_MAX - 1) }; +/* + * level of quality of a clock device. This mainly applies when the dpll + * lock-status is DPLL_LOCK_STATUS_HOLDOVER. The current list is defined + * according to the table 11-7 contained in ITU-T G.8264/Y.1364 document. One + * may extend this list freely by other ITU-T defined clock qualities, or + * different ones defined by another standardization body (for those, please + * use different prefix). + */ +enum dpll_clock_quality_level { + DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_PRC = 1, + DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_SSU_A, + DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_SSU_B, + DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_EEC1, + DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_PRTC, + DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_EPRTC, + DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_EEEC, + DPLL_CLOCK_QUALITY_LEVEL_ITU_OPT1_EPRC, + + /* private: */ + __DPLL_CLOCK_QUALITY_LEVEL_MAX, + DPLL_CLOCK_QUALITY_LEVEL_MAX = (__DPLL_CLOCK_QUALITY_LEVEL_MAX - 1) +}; + #define DPLL_TEMP_DIVIDER 1000 /** @@ -180,6 +203,7 @@ enum dpll_a { DPLL_A_TEMP, DPLL_A_TYPE, DPLL_A_LOCK_STATUS_ERROR, + DPLL_A_CLOCK_QUALITY_LEVEL, __DPLL_A_MAX, DPLL_A_MAX = (__DPLL_A_MAX - 1) diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index c405ed63acfa..fc1f54b065f9 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2511,21 +2511,24 @@ enum ethtool_reset_flags { * autonegotiation; 0 if unknown or not applicable. Read-only. */ struct ethtool_link_settings { - __u32 cmd; - __u32 speed; - __u8 duplex; - __u8 port; - __u8 phy_address; - __u8 autoneg; - __u8 mdio_support; - __u8 eth_tp_mdix; - __u8 eth_tp_mdix_ctrl; - __s8 link_mode_masks_nwords; - __u8 transceiver; - __u8 master_slave_cfg; - __u8 master_slave_state; - __u8 rate_matching; - __u32 reserved[7]; + /* New members MUST be added within the __struct_group() macro below. */ + __struct_group(ethtool_link_settings_hdr, hdr, /* no attrs */, + __u32 cmd; + __u32 speed; + __u8 duplex; + __u8 port; + __u8 phy_address; + __u8 autoneg; + __u8 mdio_support; + __u8 eth_tp_mdix; + __u8 eth_tp_mdix_ctrl; + __s8 link_mode_masks_nwords; + __u8 transceiver; + __u8 master_slave_cfg; + __u8 master_slave_state; + __u8 rate_matching; + __u32 reserved[7]; + ); __u32 link_mode_masks[]; /* layout of link_mode_masks fields: * __u32 map_supported[link_mode_masks_nwords]; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 8516c1ccd57a..2575e0cd9b48 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -1958,6 +1958,7 @@ struct ifla_rmnet_flags { enum { IFLA_MCTP_UNSPEC, IFLA_MCTP_NET, + IFLA_MCTP_PHYS_BINDING, __IFLA_MCTP_MAX, }; diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index e3ebb49f60d2..e4be227d3ad6 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -124,6 +124,7 @@ enum { NETDEV_A_NAPI_PID, NETDEV_A_NAPI_DEFER_HARD_IRQS, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, + NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h index 4fa4e979e948..2f5b4be25261 100644 --- a/include/uapi/linux/nfc.h +++ b/include/uapi/linux/nfc.h @@ -164,6 +164,7 @@ enum nfc_commands { * @NFC_ATTR_VENDOR_SUBCMD: Vendor specific sub command * @NFC_ATTR_VENDOR_DATA: Vendor specific data, to be optionally passed * to a vendor specific command implementation + * @NFC_ATTR_TARGET_ATS: ISO 14443 type A target Answer To Select */ enum nfc_attrs { NFC_ATTR_UNSPEC, @@ -198,6 +199,7 @@ enum nfc_attrs { NFC_ATTR_VENDOR_ID, NFC_ATTR_VENDOR_SUBCMD, NFC_ATTR_VENDOR_DATA, + NFC_ATTR_TARGET_ATS, /* private: internal use only */ __NFC_ATTR_AFTER_LAST }; @@ -225,6 +227,7 @@ enum nfc_sdp_attr { #define NFC_GB_MAXSIZE 48 #define NFC_FIRMWARE_NAME_MAXSIZE 32 #define NFC_ISO15693_UID_MAXSIZE 8 +#define NFC_ATS_MAXSIZE 20 /* NFC protocols */ #define NFC_PROTO_JEWEL 1 diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 3b687d20c9ed..db7254d52d93 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -174,7 +174,7 @@ enum { #define RTM_GETLINKPROP RTM_GETLINKPROP RTM_NEWVLAN = 112, -#define RTM_NEWNVLAN RTM_NEWVLAN +#define RTM_NEWVLAN RTM_NEWVLAN RTM_DELVLAN, #define RTM_DELVLAN RTM_DELVLAN RTM_GETVLAN, diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 99333cbd3114..c117672d4439 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -88,7 +88,7 @@ /* ABI version */ #define SND_SOC_TPLG_ABI_VERSION 0x5 /* current version */ -#define SND_SOC_TPLG_ABI_VERSION_MIN 0x4 /* oldest version supported */ +#define SND_SOC_TPLG_ABI_VERSION_MIN 0x5 /* oldest version supported */ /* Max size of TLV data */ #define SND_SOC_TPLG_TLV_SIZE 32 diff --git a/include/video/da8xx-fb.h b/include/video/da8xx-fb.h deleted file mode 100644 index 1d19ae62b844..000000000000 --- a/include/video/da8xx-fb.h +++ /dev/null @@ -1,94 +0,0 @@ -/* - * Header file for TI DA8XX LCD controller platform data. - * - * Copyright (C) 2008-2009 MontaVista Software Inc. - * Copyright (C) 2008-2009 Texas Instruments Inc - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ - -#ifndef DA8XX_FB_H -#define DA8XX_FB_H - -enum panel_shade { - MONOCHROME = 0, - COLOR_ACTIVE, - COLOR_PASSIVE, -}; - -enum raster_load_mode { - LOAD_DATA = 1, - LOAD_PALETTE, -}; - -enum da8xx_frame_complete { - DA8XX_FRAME_WAIT, - DA8XX_FRAME_NOWAIT, -}; - -struct da8xx_lcdc_platform_data { - const char manu_name[10]; - void *controller_data; - const char type[25]; -}; - -struct lcd_ctrl_config { - enum panel_shade panel_shade; - - /* AC Bias Pin Frequency */ - int ac_bias; - - /* AC Bias Pin Transitions per Interrupt */ - int ac_bias_intrpt; - - /* DMA burst size */ - int dma_burst_sz; - - /* Bits per pixel */ - int bpp; - - /* FIFO DMA Request Delay */ - int fdd; - - /* TFT Alternative Signal Mapping (Only for active) */ - unsigned char tft_alt_mode; - - /* 12 Bit Per Pixel (5-6-5) Mode (Only for passive) */ - unsigned char stn_565_mode; - - /* Mono 8-bit Mode: 1=D0-D7 or 0=D0-D3 */ - unsigned char mono_8bit_mode; - - /* Horizontal and Vertical Sync Edge: 0=rising 1=falling */ - unsigned char sync_edge; - - /* Raster Data Order Select: 1=Most-to-least 0=Least-to-most */ - unsigned char raster_order; - - /* DMA FIFO threshold */ - int fifo_th; -}; - -struct lcd_sync_arg { - int back_porch; - int front_porch; - int pulse_width; -}; - -/* ioctls */ -#define FBIOGET_CONTRAST _IOR('F', 1, int) -#define FBIOPUT_CONTRAST _IOW('F', 2, int) -#define FBIGET_BRIGHTNESS _IOR('F', 3, int) -#define FBIPUT_BRIGHTNESS _IOW('F', 3, int) -#define FBIGET_COLOR _IOR('F', 5, int) -#define FBIPUT_COLOR _IOW('F', 6, int) -#define FBIPUT_HSYNC _IOW('F', 9, int) -#define FBIPUT_VSYNC _IOW('F', 10, int) - -/* Proprietary FB_SYNC_ flags */ -#define FB_SYNC_CLK_INVERT 0x40000000 - -#endif /* ifndef DA8XX_FB_H */ - diff --git a/io_uring/rw.c b/io_uring/rw.c index 354c4e175654..155938f10093 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -1014,6 +1014,25 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } +static bool io_kiocb_start_write(struct io_kiocb *req, struct kiocb *kiocb) +{ + struct inode *inode; + bool ret; + + if (!(req->flags & REQ_F_ISREG)) + return true; + if (!(kiocb->ki_flags & IOCB_NOWAIT)) { + kiocb_start_write(kiocb); + return true; + } + + inode = file_inode(kiocb->ki_filp); + ret = sb_start_write_trylock(inode->i_sb); + if (ret) + __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); + return ret; +} + int io_write(struct io_kiocb *req, unsigned int issue_flags) { bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; @@ -1051,8 +1070,8 @@ int io_write(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(ret)) return ret; - if (req->flags & REQ_F_ISREG) - kiocb_start_write(kiocb); + if (unlikely(!io_kiocb_start_write(req, kiocb))) + return -EAGAIN; kiocb->ki_flags |= IOCB_WRITE; if (likely(req->file->f_op->write_iter)) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index e7113d700b87..025d7e2214ae 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -24,6 +24,23 @@ DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_CGROUP_BPF_ATTACH_TYPE); EXPORT_SYMBOL(cgroup_bpf_enabled_key); +/* + * cgroup bpf destruction makes heavy use of work items and there can be a lot + * of concurrent destructions. Use a separate workqueue so that cgroup bpf + * destruction work items don't end up filling up max_active of system_wq + * which may lead to deadlock. + */ +static struct workqueue_struct *cgroup_bpf_destroy_wq; + +static int __init cgroup_bpf_wq_init(void) +{ + cgroup_bpf_destroy_wq = alloc_workqueue("cgroup_bpf_destroy", 0, 1); + if (!cgroup_bpf_destroy_wq) + panic("Failed to alloc workqueue for cgroup bpf destroy.\n"); + return 0; +} +core_initcall(cgroup_bpf_wq_init); + /* __always_inline is necessary to prevent indirect call through run_prog * function pointer. */ @@ -334,7 +351,7 @@ static void cgroup_bpf_release_fn(struct percpu_ref *ref) struct cgroup *cgrp = container_of(ref, struct cgroup, bpf.refcnt); INIT_WORK(&cgrp->bpf.release_work, cgroup_bpf_release); - queue_work(system_wq, &cgrp->bpf.release_work); + queue_work(cgroup_bpf_destroy_wq, &cgrp->bpf.release_work); } /* Get underlying bpf_prog of bpf_prog_list entry, regardless if it's through diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1a43d06eab28..3d45ebe8afb4 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -111,7 +111,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) @@ -124,7 +124,7 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT, + .arg2_type = ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu) @@ -538,7 +538,7 @@ const struct bpf_func_proto bpf_strtol_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(s64), }; @@ -566,7 +566,7 @@ const struct bpf_func_proto bpf_strtoul_proto = { .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(u64), }; @@ -1742,7 +1742,7 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = { .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src, @@ -2851,21 +2851,47 @@ struct bpf_iter_bits { __u64 __opaque[2]; } __aligned(8); +#define BITS_ITER_NR_WORDS_MAX 511 + struct bpf_iter_bits_kern { union { - unsigned long *bits; - unsigned long bits_copy; + __u64 *bits; + __u64 bits_copy; }; - u32 nr_bits; + int nr_bits; int bit; } __aligned(8); +/* On 64-bit hosts, unsigned long and u64 have the same size, so passing + * a u64 pointer and an unsigned long pointer to find_next_bit() will + * return the same result, as both point to the same 8-byte area. + * + * For 32-bit little-endian hosts, using a u64 pointer or unsigned long + * pointer also makes no difference. This is because the first iterated + * unsigned long is composed of bits 0-31 of the u64 and the second unsigned + * long is composed of bits 32-63 of the u64. + * + * However, for 32-bit big-endian hosts, this is not the case. The first + * iterated unsigned long will be bits 32-63 of the u64, so swap these two + * ulong values within the u64. + */ +static void swap_ulong_in_u64(u64 *bits, unsigned int nr) +{ +#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN) + unsigned int i; + + for (i = 0; i < nr; i++) + bits[i] = (bits[i] >> 32) | ((u64)(u32)bits[i] << 32); +#endif +} + /** * bpf_iter_bits_new() - Initialize a new bits iterator for a given memory area * @it: The new bpf_iter_bits to be created * @unsafe_ptr__ign: A pointer pointing to a memory area to be iterated over * @nr_words: The size of the specified memory area, measured in 8-byte units. - * Due to the limitation of memalloc, it can't be greater than 512. + * The maximum value of @nr_words is @BITS_ITER_NR_WORDS_MAX. This limit may be + * further reduced by the BPF memory allocator implementation. * * This function initializes a new bpf_iter_bits structure for iterating over * a memory area which is specified by the @unsafe_ptr__ign and @nr_words. It @@ -2892,6 +2918,8 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w if (!unsafe_ptr__ign || !nr_words) return -EINVAL; + if (nr_words > BITS_ITER_NR_WORDS_MAX) + return -E2BIG; /* Optimization for u64 mask */ if (nr_bits == 64) { @@ -2899,10 +2927,15 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w if (err) return -EFAULT; + swap_ulong_in_u64(&kit->bits_copy, nr_words); + kit->nr_bits = nr_bits; return 0; } + if (bpf_mem_alloc_check_size(false, nr_bytes)) + return -E2BIG; + /* Fallback to memalloc */ kit->bits = bpf_mem_alloc(&bpf_global_ma, nr_bytes); if (!kit->bits) @@ -2914,6 +2947,8 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w return err; } + swap_ulong_in_u64(kit->bits, nr_words); + kit->nr_bits = nr_bits; return 0; } @@ -2930,17 +2965,16 @@ bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, u32 nr_w __bpf_kfunc int *bpf_iter_bits_next(struct bpf_iter_bits *it) { struct bpf_iter_bits_kern *kit = (void *)it; - u32 nr_bits = kit->nr_bits; - const unsigned long *bits; - int bit; + int bit = kit->bit, nr_bits = kit->nr_bits; + const void *bits; - if (nr_bits == 0) + if (!nr_bits || bit >= nr_bits) return NULL; bits = nr_bits == 64 ? &kit->bits_copy : kit->bits; - bit = find_next_bit(bits, nr_bits, kit->bit + 1); + bit = find_next_bit(bits, nr_bits, bit + 1); if (bit >= nr_bits) { - kit->nr_bits = 0; + kit->bit = bit; return NULL; } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index d8fc5eba529d..9aaf5124648b 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -880,7 +880,7 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) const struct btf_type *enum_t; const char *enum_pfx; u64 *delegate_msk, msk = 0; - char *p; + char *p, *str; int val; /* ignore errors, fallback to hex */ @@ -911,7 +911,8 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) return -EINVAL; } - while ((p = strsep(¶m->string, ":"))) { + str = param->string; + while ((p = strsep(&str, ":"))) { if (strcmp(p, "any") == 0) { msk |= ~0ULL; } else if (find_btf_enum_const(info.btf, enum_t, enum_pfx, p, &val)) { diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 0218a5132ab5..9b60eda0f727 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -655,7 +655,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) if (!key || key->prefixlen > trie->max_prefixlen) goto find_leftmost; - node_stack = kmalloc_array(trie->max_prefixlen, + node_stack = kmalloc_array(trie->max_prefixlen + 1, sizeof(struct lpm_trie_node *), GFP_ATOMIC | __GFP_NOWARN); if (!node_stack) diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index b3858a76e0b3..146f5b57cfb1 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -35,6 +35,8 @@ */ #define LLIST_NODE_SZ sizeof(struct llist_node) +#define BPF_MEM_ALLOC_SIZE_MAX 4096 + /* similar to kmalloc, but sizeof == 8 bucket is gone */ static u8 size_index[24] __ro_after_init = { 3, /* 8 */ @@ -65,7 +67,7 @@ static u8 size_index[24] __ro_after_init = { static int bpf_mem_cache_idx(size_t size) { - if (!size || size > 4096) + if (!size || size > BPF_MEM_ALLOC_SIZE_MAX) return -1; if (size <= 192) @@ -1005,3 +1007,13 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) return !ret ? NULL : ret + LLIST_NODE_SZ; } + +int bpf_mem_alloc_check_size(bool percpu, size_t size) +{ + /* The size of percpu allocation doesn't have LLIST_NODE_SZ overhead */ + if ((percpu && size > BPF_MEM_ALLOC_SIZE_MAX) || + (!percpu && size > BPF_MEM_ALLOC_SIZE_MAX - LLIST_NODE_SZ)) + return -E2BIG; + + return 0; +} diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index de3b681d1d13..e1cfe890e0be 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -632,7 +632,7 @@ const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT, + .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT | MEM_WRITE, }; BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8cfa7183d2ef..c5aa127ed4cc 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3069,13 +3069,17 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_link *link = filp->private_data; const struct bpf_prog *prog = link->prog; + enum bpf_link_type type = link->type; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - seq_printf(m, - "link_type:\t%s\n" - "link_id:\t%u\n", - bpf_link_type_strs[link->type], - link->id); + if (type < ARRAY_SIZE(bpf_link_type_strs) && bpf_link_type_strs[type]) { + seq_printf(m, "link_type:\t%s\n", bpf_link_type_strs[type]); + } else { + WARN_ONCE(1, "missing BPF_LINK_TYPE(...) for link type %u\n", type); + seq_printf(m, "link_type:\t<%u>\n", type); + } + seq_printf(m, "link_id:\t%u\n", link->id); + if (prog) { bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, @@ -5892,7 +5896,7 @@ static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(u64), }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 411ab1b57af4..bb99bada7e2e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6804,20 +6804,10 @@ static int check_stack_slot_within_bounds(struct bpf_verifier_env *env, struct bpf_func_state *state, enum bpf_access_type t) { - struct bpf_insn_aux_data *aux = &env->insn_aux_data[env->insn_idx]; - int min_valid_off, max_bpf_stack; - - /* If accessing instruction is a spill/fill from bpf_fastcall pattern, - * add room for all caller saved registers below MAX_BPF_STACK. - * In case if bpf_fastcall rewrite won't happen maximal stack depth - * would be checked by check_max_stack_depth_subprog(). - */ - max_bpf_stack = MAX_BPF_STACK; - if (aux->fastcall_pattern) - max_bpf_stack += CALLER_SAVED_REGS * BPF_REG_SIZE; + int min_valid_off; if (t == BPF_WRITE || env->allow_uninit_stack) - min_valid_off = -max_bpf_stack; + min_valid_off = -MAX_BPF_STACK; else min_valid_off = -state->allocated_stack; @@ -7438,7 +7428,8 @@ mark: } static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, - int access_size, bool zero_size_allowed, + int access_size, enum bpf_access_type access_type, + bool zero_size_allowed, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; @@ -7450,7 +7441,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MAP_KEY: - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -7458,15 +7449,13 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_mem_region_access(env, regno, reg->off, access_size, reg->map_ptr->key_size, false); case PTR_TO_MAP_VALUE: - if (check_map_access_type(env, regno, reg->off, access_size, - meta && meta->raw_mode ? BPF_WRITE : - BPF_READ)) + if (check_map_access_type(env, regno, reg->off, access_size, access_type)) return -EACCES; return check_map_access(env, regno, reg->off, access_size, zero_size_allowed, ACCESS_HELPER); case PTR_TO_MEM: if (type_is_rdonly_mem(reg->type)) { - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -7477,7 +7466,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, zero_size_allowed); case PTR_TO_BUF: if (type_is_rdonly_mem(reg->type)) { - if (meta && meta->raw_mode) { + if (access_type == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", regno, reg_type_str(env, reg->type)); return -EACCES; @@ -7505,7 +7494,6 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, * Dynamically check it now. */ if (!env->ops->convert_ctx_access) { - enum bpf_access_type atype = meta && meta->raw_mode ? BPF_WRITE : BPF_READ; int offset = access_size - 1; /* Allow zero-byte read from PTR_TO_CTX */ @@ -7513,7 +7501,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return zero_size_allowed ? 0 : -EACCES; return check_mem_access(env, env->insn_idx, regno, offset, BPF_B, - atype, -1, false, false); + access_type, -1, false, false); } fallthrough; @@ -7538,6 +7526,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, */ static int check_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, + enum bpf_access_type access_type, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { @@ -7553,15 +7542,12 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, */ meta->msize_max_value = reg->umax_value; - /* The register is SCALAR_VALUE; the access check - * happens using its boundaries. + /* The register is SCALAR_VALUE; the access check happens using + * its boundaries. For unprivileged variable accesses, disable + * raw mode so that the program is required to initialize all + * the memory that the helper could just partially fill up. */ if (!tnum_is_const(reg->var_off)) - /* For unprivileged variable accesses, disable raw - * mode so that the program is required to - * initialize all the memory that the helper could - * just partially fill up. - */ meta = NULL; if (reg->smin_value < 0) { @@ -7581,9 +7567,8 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, regno); return -EACCES; } - err = check_helper_mem_access(env, regno - 1, - reg->umax_value, - zero_size_allowed, meta); + err = check_helper_mem_access(env, regno - 1, reg->umax_value, + access_type, zero_size_allowed, meta); if (!err) err = mark_chain_precision(env, regno); return err; @@ -7594,13 +7579,11 @@ static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg { bool may_be_null = type_may_be_null(reg->type); struct bpf_reg_state saved_reg; - struct bpf_call_arg_meta meta; int err; if (register_is_null(reg)) return 0; - memset(&meta, 0, sizeof(meta)); /* Assuming that the register contains a value check if the memory * access is safe. Temporarily save and restore the register's state as * the conversion shouldn't be visible to a caller. @@ -7610,10 +7593,8 @@ static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg mark_ptr_not_null_reg(reg); } - err = check_helper_mem_access(env, regno, mem_size, true, &meta); - /* Check access for BPF_WRITE */ - meta.raw_mode = true; - err = err ?: check_helper_mem_access(env, regno, mem_size, true, &meta); + err = check_helper_mem_access(env, regno, mem_size, BPF_READ, true, NULL); + err = err ?: check_helper_mem_access(env, regno, mem_size, BPF_WRITE, true, NULL); if (may_be_null) *reg = saved_reg; @@ -7639,13 +7620,12 @@ static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg mark_ptr_not_null_reg(mem_reg); } - err = check_mem_size_reg(env, reg, regno, true, &meta); - /* Check access for BPF_WRITE */ - meta.raw_mode = true; - err = err ?: check_mem_size_reg(env, reg, regno, true, &meta); + err = check_mem_size_reg(env, reg, regno, BPF_READ, true, &meta); + err = err ?: check_mem_size_reg(env, reg, regno, BPF_WRITE, true, &meta); if (may_be_null) *mem_reg = saved_reg; + return err; } @@ -8948,9 +8928,8 @@ skip_type_check: verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } - err = check_helper_mem_access(env, regno, - meta->map_ptr->key_size, false, - NULL); + err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, + BPF_READ, false, NULL); break; case ARG_PTR_TO_MAP_VALUE: if (type_may_be_null(arg_type) && register_is_null(reg)) @@ -8965,9 +8944,9 @@ skip_type_check: return -EACCES; } meta->raw_mode = arg_type & MEM_UNINIT; - err = check_helper_mem_access(env, regno, - meta->map_ptr->value_size, false, - meta); + err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, + arg_type & MEM_WRITE ? BPF_WRITE : BPF_READ, + false, meta); break; case ARG_PTR_TO_PERCPU_BTF_ID: if (!reg->btf_id) { @@ -9009,7 +8988,9 @@ skip_type_check: */ meta->raw_mode = arg_type & MEM_UNINIT; if (arg_type & MEM_FIXED_SIZE) { - err = check_helper_mem_access(env, regno, fn->arg_size[arg], false, meta); + err = check_helper_mem_access(env, regno, fn->arg_size[arg], + arg_type & MEM_WRITE ? BPF_WRITE : BPF_READ, + false, meta); if (err) return err; if (arg_type & MEM_ALIGNED) @@ -9017,10 +8998,16 @@ skip_type_check: } break; case ARG_CONST_SIZE: - err = check_mem_size_reg(env, reg, regno, false, meta); + err = check_mem_size_reg(env, reg, regno, + fn->arg_type[arg - 1] & MEM_WRITE ? + BPF_WRITE : BPF_READ, + false, meta); break; case ARG_CONST_SIZE_OR_ZERO: - err = check_mem_size_reg(env, reg, regno, true, meta); + err = check_mem_size_reg(env, reg, regno, + fn->arg_type[arg - 1] & MEM_WRITE ? + BPF_WRITE : BPF_READ, + true, meta); break; case ARG_PTR_TO_DYNPTR: err = process_dynptr_func(env, regno, insn_idx, arg_type, 0); @@ -17889,9 +17876,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) struct bpf_verifier_state_list *sl, **pprev; struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry; int i, j, n, err, states_cnt = 0; - bool force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx); - bool add_new_state = force_new_state; - bool force_exact; + bool force_new_state, add_new_state, force_exact; + + force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx) || + /* Avoid accumulating infinitely long jmp history */ + cur->jmp_history_cnt > 40; /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 @@ -17901,6 +17890,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * In tests that amounts to up to 50% reduction into total verifier * memory consumption and 20% verifier time speedup. */ + add_new_state = force_new_state; if (env->jmps_processed - env->prev_jmps_processed >= 2 && env->insn_processed - env->prev_insn_processed >= 8) add_new_state = true; @@ -21213,7 +21203,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_kptr_xchg inline */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 5886b95c6eae..044c7ba1cc48 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5789,7 +5789,7 @@ static bool cgroup_check_hierarchy_limits(struct cgroup *parent) { struct cgroup *cgroup; int ret = false; - int level = 1; + int level = 0; lockdep_assert_held(&cgroup_mutex); @@ -5797,7 +5797,7 @@ static bool cgroup_check_hierarchy_limits(struct cgroup *parent) if (cgroup->nr_descendants >= cgroup->max_descendants) goto fail; - if (level > cgroup->max_depth) + if (level >= cgroup->max_depth) goto fail; level++; diff --git a/kernel/events/core.c b/kernel/events/core.c index cdd09769e6c5..df27d08a7232 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -13959,7 +13959,7 @@ static void perf_event_clear_cpumask(unsigned int cpu) } /* migrate */ - list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) { + list_for_each_entry(pmu, &pmus, entry) { if (pmu->scope == PERF_PMU_SCOPE_NONE || WARN_ON_ONCE(pmu->scope >= PERF_PMU_MAX_SCOPE)) continue; diff --git a/kernel/fork.c b/kernel/fork.c index 89ceb4a68af2..22f43721d031 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -105,6 +105,7 @@ #include <linux/rseq.h> #include <uapi/linux/pidfd.h> #include <linux/pidfs.h> +#include <linux/tick.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> @@ -653,11 +654,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; - retval = ksm_fork(mm, oldmm); - if (retval) - goto out; - khugepaged_fork(mm, oldmm); - /* Use __mt_dup() to efficiently build an identical maple tree. */ retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); if (unlikely(retval)) @@ -760,6 +756,8 @@ loop_out: vma_iter_free(&vmi); if (!retval) { mt_set_in_rcu(vmi.mas.tree); + ksm_fork(mm, oldmm); + khugepaged_fork(mm, oldmm); } else if (mpnt) { /* * The entire maple tree has already been duplicated. If the @@ -775,7 +773,10 @@ out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); - dup_userfaultfd_complete(&uf); + if (!retval) + dup_userfaultfd_complete(&uf); + else + dup_userfaultfd_fail(&uf); fail_uprobe_end: uprobe_end_dup_mmap(); return retval; @@ -2292,6 +2293,7 @@ __latent_entropy struct task_struct *copy_process( acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); + tick_dep_init_task(p); p->io_context = NULL; audit_set_context(p, NULL); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 3a24d6b5f559..396a067a8a56 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -718,7 +718,7 @@ static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq, ret = ops->msi_init(domain, info, virq + i, hwirq + i, arg); if (ret < 0) { if (ops->msi_free) { - for (i--; i > 0; i--) + for (i--; i >= 0; i--) ops->msi_free(domain, info, virq + i); } irq_domain_free_irqs_top(domain, virq, nr_irqs); diff --git a/kernel/resource.c b/kernel/resource.c index b730bd28b422..4101016e8b20 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -459,9 +459,7 @@ int walk_system_ram_res_rev(u64 start, u64 end, void *arg, rams_size += 16; } - rams[i].start = res.start; - rams[i++].end = res.end; - + rams[i++] = res; start = res.end + 1; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index dbfb5717d6af..719e0ed1e976 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4711,7 +4711,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) if (rt_prio(p->prio)) { p->sched_class = &rt_sched_class; #ifdef CONFIG_SCHED_CLASS_EXT - } else if (task_should_scx(p)) { + } else if (task_should_scx(p->policy)) { p->sched_class = &ext_sched_class; #endif } else { @@ -7025,7 +7025,7 @@ int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flag } EXPORT_SYMBOL(default_wake_function); -const struct sched_class *__setscheduler_class(struct task_struct *p, int prio) +const struct sched_class *__setscheduler_class(int policy, int prio) { if (dl_prio(prio)) return &dl_sched_class; @@ -7034,7 +7034,7 @@ const struct sched_class *__setscheduler_class(struct task_struct *p, int prio) return &rt_sched_class; #ifdef CONFIG_SCHED_CLASS_EXT - if (task_should_scx(p)) + if (task_should_scx(policy)) return &ext_sched_class; #endif @@ -7142,7 +7142,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) queue_flag &= ~DEQUEUE_MOVE; prev_class = p->sched_class; - next_class = __setscheduler_class(p, prio); + next_class = __setscheduler_class(p->policy, prio); if (prev_class != next_class && p->se.sched_delayed) dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK); diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 5900b06fd036..b5f4b1a5ae98 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -862,7 +862,8 @@ static DEFINE_MUTEX(scx_ops_enable_mutex); DEFINE_STATIC_KEY_FALSE(__scx_ops_enabled); DEFINE_STATIC_PERCPU_RWSEM(scx_fork_rwsem); static atomic_t scx_ops_enable_state_var = ATOMIC_INIT(SCX_OPS_DISABLED); -static atomic_t scx_ops_bypass_depth = ATOMIC_INIT(0); +static int scx_ops_bypass_depth; +static DEFINE_RAW_SPINLOCK(__scx_ops_bypass_lock); static bool scx_ops_init_task_enabled; static bool scx_switching_all; DEFINE_STATIC_KEY_FALSE(__scx_switched_all); @@ -4256,14 +4257,14 @@ static const struct kset_uevent_ops scx_uevent_ops = { * Used by sched_fork() and __setscheduler_prio() to pick the matching * sched_class. dl/rt are already handled. */ -bool task_should_scx(struct task_struct *p) +bool task_should_scx(int policy) { if (!scx_enabled() || unlikely(scx_ops_enable_state() == SCX_OPS_DISABLING)) return false; if (READ_ONCE(scx_switching_all)) return true; - return p->policy == SCHED_EXT; + return policy == SCHED_EXT; } /** @@ -4298,18 +4299,20 @@ bool task_should_scx(struct task_struct *p) */ static void scx_ops_bypass(bool bypass) { - int depth, cpu; + int cpu; + unsigned long flags; + raw_spin_lock_irqsave(&__scx_ops_bypass_lock, flags); if (bypass) { - depth = atomic_inc_return(&scx_ops_bypass_depth); - WARN_ON_ONCE(depth <= 0); - if (depth != 1) - return; + scx_ops_bypass_depth++; + WARN_ON_ONCE(scx_ops_bypass_depth <= 0); + if (scx_ops_bypass_depth != 1) + goto unlock; } else { - depth = atomic_dec_return(&scx_ops_bypass_depth); - WARN_ON_ONCE(depth < 0); - if (depth != 0) - return; + scx_ops_bypass_depth--; + WARN_ON_ONCE(scx_ops_bypass_depth < 0); + if (scx_ops_bypass_depth != 0) + goto unlock; } /* @@ -4326,7 +4329,7 @@ static void scx_ops_bypass(bool bypass) struct rq_flags rf; struct task_struct *p, *n; - rq_lock_irqsave(rq, &rf); + rq_lock(rq, &rf); if (bypass) { WARN_ON_ONCE(rq->scx.flags & SCX_RQ_BYPASSING); @@ -4362,11 +4365,13 @@ static void scx_ops_bypass(bool bypass) sched_enq_and_set_task(&ctx); } - rq_unlock_irqrestore(rq, &rf); + rq_unlock(rq, &rf); /* resched to restore ticks and idle state */ resched_cpu(cpu); } +unlock: + raw_spin_unlock_irqrestore(&__scx_ops_bypass_lock, flags); } static void free_exit_info(struct scx_exit_info *ei) @@ -4489,11 +4494,16 @@ static void scx_ops_disable_workfn(struct kthread_work *work) scx_task_iter_start(&sti); while ((p = scx_task_iter_next_locked(&sti))) { const struct sched_class *old_class = p->sched_class; + const struct sched_class *new_class = + __setscheduler_class(p->policy, p->prio); struct sched_enq_and_set_ctx ctx; + if (old_class != new_class && p->se.sched_delayed) + dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED); + sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx); - p->sched_class = __setscheduler_class(p, p->prio); + p->sched_class = new_class; check_class_changing(task_rq(p), p, old_class); sched_enq_and_set_task(&ctx); @@ -5199,12 +5209,17 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) scx_task_iter_start(&sti); while ((p = scx_task_iter_next_locked(&sti))) { const struct sched_class *old_class = p->sched_class; + const struct sched_class *new_class = + __setscheduler_class(p->policy, p->prio); struct sched_enq_and_set_ctx ctx; + if (old_class != new_class && p->se.sched_delayed) + dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED); + sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx); p->scx.slice = SCX_SLICE_DFL; - p->sched_class = __setscheduler_class(p, p->prio); + p->sched_class = new_class; check_class_changing(task_rq(p), p, old_class); sched_enq_and_set_task(&ctx); diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 246019519231..b1675bb59fc4 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -18,7 +18,7 @@ bool scx_can_stop_tick(struct rq *rq); void scx_rq_activate(struct rq *rq); void scx_rq_deactivate(struct rq *rq); int scx_check_setscheduler(struct task_struct *p, int policy); -bool task_should_scx(struct task_struct *p); +bool task_should_scx(int policy); void init_sched_ext_class(void); static inline u32 scx_cpuperf_target(s32 cpu) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c157d4860a3b..2d16c8545c71 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3369,7 +3369,7 @@ retry_pids: vma = vma_next(&vmi); } - do { + for (; vma; vma = vma_next(&vmi)) { if (!vma_migratable(vma) || !vma_policy_mof(vma) || is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) { trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_UNSUITABLE); @@ -3491,7 +3491,7 @@ retry_pids: */ if (vma_pids_forced) break; - } for_each_vma(vmi, vma); + } /* * If no VMAs are remaining and VMAs were skipped due to the PID @@ -5625,8 +5625,9 @@ pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq) struct sched_entity *se = pick_eevdf(cfs_rq); if (se->sched_delayed) { dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED); - SCHED_WARN_ON(se->sched_delayed); - SCHED_WARN_ON(se->on_rq); + /* + * Must not reference @se again, see __block_task(). + */ return NULL; } return se; @@ -7176,7 +7177,11 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) /* Fix-up what dequeue_task_fair() skipped */ hrtick_update(rq); - /* Fix-up what block_task() skipped. */ + /* + * Fix-up what block_task() skipped. + * + * Must be last, @p might not be valid after this. + */ __block_task(rq, p); } @@ -7193,12 +7198,14 @@ static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (!(p->se.sched_delayed && (task_on_rq_migrating(p) || (flags & DEQUEUE_SAVE)))) util_est_dequeue(&rq->cfs, p); - if (dequeue_entities(rq, &p->se, flags) < 0) { - util_est_update(&rq->cfs, p, DEQUEUE_SLEEP); + util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP); + if (dequeue_entities(rq, &p->se, flags) < 0) return false; - } - util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP); + /* + * Must not reference @p after dequeue_entities(DEQUEUE_DELAYED). + */ + hrtick_update(rq); return true; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 081519ffab46..6c54a57275cc 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2769,8 +2769,6 @@ static inline void sub_nr_running(struct rq *rq, unsigned count) static inline void __block_task(struct rq *rq, struct task_struct *p) { - WRITE_ONCE(p->on_rq, 0); - ASSERT_EXCLUSIVE_WRITER(p->on_rq); if (p->sched_contributes_to_load) rq->nr_uninterruptible++; @@ -2778,6 +2776,38 @@ static inline void __block_task(struct rq *rq, struct task_struct *p) atomic_inc(&rq->nr_iowait); delayacct_blkio_start(); } + + ASSERT_EXCLUSIVE_WRITER(p->on_rq); + + /* + * The moment this write goes through, ttwu() can swoop in and migrate + * this task, rendering our rq->__lock ineffective. + * + * __schedule() try_to_wake_up() + * LOCK rq->__lock LOCK p->pi_lock + * pick_next_task() + * pick_next_task_fair() + * pick_next_entity() + * dequeue_entities() + * __block_task() + * RELEASE p->on_rq = 0 if (p->on_rq && ...) + * break; + * + * ACQUIRE (after ctrl-dep) + * + * cpu = select_task_rq(); + * set_task_cpu(p, cpu); + * ttwu_queue() + * ttwu_do_activate() + * LOCK rq->__lock + * activate_task() + * STORE p->on_rq = 1 + * UNLOCK rq->__lock + * + * Callers must ensure to not reference @p after this -- we no longer + * own it. + */ + smp_store_release(&p->on_rq, 0); } extern void activate_task(struct rq *rq, struct task_struct *p, int flags); @@ -3800,7 +3830,7 @@ static inline int rt_effective_prio(struct task_struct *p, int prio) extern int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi); extern int __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx); -extern const struct sched_class *__setscheduler_class(struct task_struct *p, int prio); +extern const struct sched_class *__setscheduler_class(int policy, int prio); extern void set_load_weight(struct task_struct *p, bool update_load); extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags); extern bool dequeue_task(struct rq *rq, struct task_struct *p, int flags); diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 0470bcc3d204..24f9f90b6574 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -707,7 +707,7 @@ change: } prev_class = p->sched_class; - next_class = __setscheduler_class(p, newprio); + next_class = __setscheduler_class(policy, newprio); if (prev_class != next_class && p->se.sched_delayed) dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 3bd402fa62a4..630b763e5240 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1202,7 +1202,7 @@ static const struct bpf_func_proto bpf_get_func_arg_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u64), }; @@ -1219,7 +1219,7 @@ static const struct bpf_func_proto bpf_get_func_ret_proto = { .func = get_func_ret, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg2_size = sizeof(u64), }; @@ -2216,8 +2216,6 @@ void perf_event_detach_bpf_prog(struct perf_event *event) old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array); - if (ret == -ENOENT) - goto unlock; if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); } else { diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 41e7a15dcb50..69e226a48daa 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -1252,10 +1252,10 @@ int register_ftrace_graph(struct fgraph_ops *gops) int ret = 0; int i = -1; - mutex_lock(&ftrace_lock); + guard(mutex)(&ftrace_lock); if (!fgraph_initialized) { - ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "fgraph_idle_init", + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "fgraph:online", fgraph_cpu_init, NULL); if (ret < 0) { pr_warn("fgraph: Error to init cpu hotplug support\n"); @@ -1273,10 +1273,8 @@ int register_ftrace_graph(struct fgraph_ops *gops) } i = fgraph_lru_alloc_index(); - if (i < 0 || WARN_ON_ONCE(fgraph_array[i] != &fgraph_stub)) { - ret = -ENOSPC; - goto out; - } + if (i < 0 || WARN_ON_ONCE(fgraph_array[i] != &fgraph_stub)) + return -ENOSPC; gops->idx = i; ftrace_graph_active++; @@ -1313,8 +1311,6 @@ error: gops->saved_func = NULL; fgraph_lru_release_index(i); } -out: - mutex_unlock(&ftrace_lock); return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a8f52b6527ca..2b64b3ec67d9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5501,6 +5501,10 @@ static const struct file_operations tracing_iter_fops = { static const char readme_msg[] = "tracing mini-HOWTO:\n\n" + "By default tracefs removes all OTH file permission bits.\n" + "When mounting tracefs an optional group id can be specified\n" + "which adds the group to every directory and file in tracefs:\n\n" + "\t e.g. mount -t tracefs [-o [gid=<gid>]] nodev /sys/kernel/tracing\n\n" "# echo 0 > tracing_on : quick way to disable tracing\n" "# echo 1 > tracing_on : quick way to re-enable tracing\n\n" " Important files:\n" diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 7312ae7c3cc5..67b669d2e70e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2115,6 +2115,16 @@ config FAIL_SUNRPC Provide fault-injection capability for SunRPC and its consumers. +config FAIL_SKB_REALLOC + bool "Fault-injection capability forcing skb to reallocate" + depends on FAULT_INJECTION_DEBUG_FS + help + Provide fault-injection capability that forces the skb to be + reallocated, catching possible invalid pointers to the skb. + + For more information, check + Documentation/dev-tools/fault-injection/fault-injection.rst + config FAULT_INJECTION_CONFIGFS bool "Configfs interface for fault-injection capabilities" depends on FAULT_INJECTION diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 233ab2096924..98016e137b7f 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -22,11 +22,8 @@ config ARCH_DISABLE_KASAN_INLINE config CC_HAS_KASAN_GENERIC def_bool $(cc-option, -fsanitize=kernel-address) -# GCC appears to ignore no_sanitize_address when -fsanitize=kernel-hwaddress -# is passed. See https://bugzilla.kernel.org/show_bug.cgi?id=218854 (and -# the linked LKML thread) for more details. config CC_HAS_KASAN_SW_TAGS - def_bool !CC_IS_GCC && $(cc-option, -fsanitize=kernel-hwaddress) + def_bool $(cc-option, -fsanitize=kernel-hwaddress) # This option is only required for software KASAN modes. # Old GCC versions do not have proper support for no_sanitize_address. @@ -101,7 +98,7 @@ config KASAN_SW_TAGS help Enables Software Tag-Based KASAN. - Requires Clang. + Requires GCC 11+ or Clang. Supported only on arm64 CPUs and relies on Top Byte Ignore. diff --git a/lib/checksum.c b/lib/checksum.c index 6860d6b05a17..025ba546e1ec 100644 --- a/lib/checksum.c +++ b/lib/checksum.c @@ -34,15 +34,6 @@ #include <asm/byteorder.h> #ifndef do_csum -static inline unsigned short from32to16(unsigned int x) -{ - /* add up 16-bit and 16-bit for 16+c bit */ - x = (x & 0xffff) + (x >> 16); - /* add up carry.. */ - x = (x & 0xffff) + (x >> 16); - return x; -} - static unsigned int do_csum(const unsigned char *buff, int len) { int odd; @@ -90,7 +81,7 @@ static unsigned int do_csum(const unsigned char *buff, int len) #else result += (*buff << 8); #endif - result = from32to16(result); + result = csum_from32to16(result); if (odd) result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); out: diff --git a/lib/dim/dim.c b/lib/dim/dim.c index 83b65ac74d73..97c3d084ebf0 100644 --- a/lib/dim/dim.c +++ b/lib/dim/dim.c @@ -54,7 +54,8 @@ void dim_park_tired(struct dim *dim) } EXPORT_SYMBOL(dim_park_tired); -bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end, +bool dim_calc_stats(const struct dim_sample *start, + const struct dim_sample *end, struct dim_stats *curr_stats) { /* u32 holds up to 71 minutes, should be enough */ diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index d7e7028e9b19..d6aa09a979b3 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -347,7 +347,7 @@ static bool net_dim_decision(struct dim_stats *curr_stats, struct dim *dim) return dim->profile_ix != prev_ix; } -void net_dim(struct dim *dim, struct dim_sample end_sample) +void net_dim(struct dim *dim, const struct dim_sample *end_sample) { struct dim_stats curr_stats; u16 nevents; @@ -355,11 +355,11 @@ void net_dim(struct dim *dim, struct dim_sample end_sample) switch (dim->state) { case DIM_MEASURE_IN_PROGRESS: nevents = BIT_GAP(BITS_PER_TYPE(u16), - end_sample.event_ctr, + end_sample->event_ctr, dim->start_sample.event_ctr); if (nevents < DIM_NEVENTS) break; - if (!dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats)) + if (!dim_calc_stats(&dim->start_sample, end_sample, &curr_stats)) break; if (net_dim_decision(&curr_stats, dim)) { dim->state = DIM_APPLY_NEW_PROFILE; @@ -368,8 +368,8 @@ void net_dim(struct dim *dim, struct dim_sample end_sample) } fallthrough; case DIM_START_MEASURE: - dim_update_sample(end_sample.event_ctr, end_sample.pkt_ctr, - end_sample.byte_ctr, &dim->start_sample); + dim_update_sample(end_sample->event_ctr, end_sample->pkt_ctr, + end_sample->byte_ctr, &dim->start_sample); dim->state = DIM_MEASURE_IN_PROGRESS; break; case DIM_APPLY_NEW_PROFILE: diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index e49deddd3de9..c1b7638a594a 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -179,7 +179,7 @@ void dql_completed(struct dql *dql, unsigned int count) dql->adj_limit = limit + completed; dql->prev_ovlimit = ovlimit; - dql->prev_last_obj_cnt = dql->last_obj_cnt; + dql->prev_last_obj_cnt = READ_ONCE(dql->last_obj_cnt); dql->num_completed = completed; dql->prev_num_queued = num_queued; diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 1abb32c0da50..908e75a28d90 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -461,6 +461,8 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t n, copied = 0; + bool uses_kmap = IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || + PageHighMem(page); if (!page_copy_sane(page, offset, bytes)) return 0; @@ -471,7 +473,7 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset, char *p; n = bytes - copied; - if (PageHighMem(page)) { + if (uses_kmap) { page += offset / PAGE_SIZE; offset %= PAGE_SIZE; n = min_t(size_t, n, PAGE_SIZE - offset); @@ -482,7 +484,7 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset, kunmap_atomic(p); copied += n; offset += n; - } while (PageHighMem(page) && copied != bytes && n > 0); + } while (uses_kmap && copied != bytes && n > 0); return copied; } @@ -1021,15 +1023,18 @@ static ssize_t iter_folioq_get_pages(struct iov_iter *iter, size_t offset = iov_offset, fsize = folioq_folio_size(folioq, slot); size_t part = PAGE_SIZE - offset % PAGE_SIZE; - part = umin(part, umin(maxsize - extracted, fsize - offset)); - count -= part; - iov_offset += part; - extracted += part; + if (offset < fsize) { + part = umin(part, umin(maxsize - extracted, fsize - offset)); + count -= part; + iov_offset += part; + extracted += part; + + *pages = folio_page(folio, offset / PAGE_SIZE); + get_page(*pages); + pages++; + maxpages--; + } - *pages = folio_page(folio, offset / PAGE_SIZE); - get_page(*pages); - pages++; - maxpages--; if (maxpages == 0 || extracted >= maxsize) break; diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c index 80e39f003344..33564f965958 100644 --- a/lib/slub_kunit.c +++ b/lib/slub_kunit.c @@ -141,7 +141,7 @@ static void test_kmalloc_redzone_access(struct kunit *test) { struct kmem_cache *s = test_kmem_cache_create("TestSlub_RZ_kmalloc", 32, SLAB_KMALLOC|SLAB_STORE_USER|SLAB_RED_ZONE); - u8 *p = __kmalloc_cache_noprof(s, GFP_KERNEL, 18); + u8 *p = alloc_hooks(__kmalloc_cache_noprof(s, GFP_KERNEL, 18)); kasan_disable_current(); diff --git a/mm/Kconfig b/mm/Kconfig index 4c9f5ea13271..33fa51d608dc 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1085,7 +1085,6 @@ config HMM_MIRROR depends on MMU config GET_FREE_REGION - depends on SPARSEMEM bool config DEVICE_PRIVATE diff --git a/mm/Makefile b/mm/Makefile index d5639b036166..dba52bb0da8a 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -65,6 +65,7 @@ page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) += shuffle.o memory-hotplug-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o obj-y += page-alloc.o +obj-y += page_frag_cache.o obj-y += init-mm.o obj-y += memblock.o obj-y += $(memory-hotplug-y) @@ -2394,20 +2394,25 @@ err: } /* - * Check whether all folios are *allowed* to be pinned indefinitely (longterm). + * Check whether all folios are *allowed* to be pinned indefinitely (long term). * Rather confusingly, all folios in the range are required to be pinned via * FOLL_PIN, before calling this routine. * - * If any folios in the range are not allowed to be pinned, then this routine - * will migrate those folios away, unpin all the folios in the range and return - * -EAGAIN. The caller should re-pin the entire range with FOLL_PIN and then - * call this routine again. + * Return values: * - * If an error other than -EAGAIN occurs, this indicates a migration failure. - * The caller should give up, and propagate the error back up the call stack. - * - * If everything is OK and all folios in the range are allowed to be pinned, + * 0: if everything is OK and all folios in the range are allowed to be pinned, * then this routine leaves all folios pinned and returns zero for success. + * + * -EAGAIN: if any folios in the range are not allowed to be pinned, then this + * routine will migrate those folios away, unpin all the folios in the range. If + * migration of the entire set of folios succeeds, then -EAGAIN is returned. The + * caller should re-pin the entire range with FOLL_PIN and then call this + * routine again. + * + * -ENOMEM, or any other -errno: if an error *other* than -EAGAIN occurs, this + * indicates a migration failure. The caller should give up, and propagate the + * error back up the call stack. The caller does not need to unpin any folios in + * that case, because this routine will do the unpinning. */ static long check_and_migrate_movable_folios(unsigned long nr_folios, struct folio **folios) @@ -2425,10 +2430,8 @@ static long check_and_migrate_movable_folios(unsigned long nr_folios, } /* - * This routine just converts all the pages in the @pages array to folios and - * calls check_and_migrate_movable_folios() to do the heavy lifting. - * - * Please see the check_and_migrate_movable_folios() documentation for details. + * Return values and behavior are the same as those for + * check_and_migrate_movable_folios(). */ static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) @@ -2437,8 +2440,10 @@ static long check_and_migrate_movable_pages(unsigned long nr_pages, long i, ret; folios = kmalloc_array(nr_pages, sizeof(*folios), GFP_KERNEL); - if (!folios) + if (!folios) { + unpin_user_pages(pages, nr_pages); return -ENOMEM; + } for (i = 0; i < nr_pages; i++) folios[i] = page_folio(pages[i]); diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c index a181e4780d9d..d8fb281e439d 100644 --- a/mm/kasan/kasan_test_c.c +++ b/mm/kasan/kasan_test_c.c @@ -1810,32 +1810,6 @@ static void vm_map_ram_tags(struct kunit *test) free_pages((unsigned long)p_ptr, 1); } -static void vmalloc_percpu(struct kunit *test) -{ - char __percpu *ptr; - int cpu; - - /* - * This test is specifically crafted for the software tag-based mode, - * the only tag-based mode that poisons percpu mappings. - */ - KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_SW_TAGS); - - ptr = __alloc_percpu(PAGE_SIZE, PAGE_SIZE); - - for_each_possible_cpu(cpu) { - char *c_ptr = per_cpu_ptr(ptr, cpu); - - KUNIT_EXPECT_GE(test, (u8)get_tag(c_ptr), (u8)KASAN_TAG_MIN); - KUNIT_EXPECT_LT(test, (u8)get_tag(c_ptr), (u8)KASAN_TAG_KERNEL); - - /* Make sure that in-bounds accesses don't crash the kernel. */ - *c_ptr = 0; - } - - free_percpu(ptr); -} - /* * Check that the assigned pointer tag falls within the [KASAN_TAG_MIN, * KASAN_TAG_KERNEL) range (note: excluding the match-all tag) for tag-based @@ -2023,7 +1997,6 @@ static struct kunit_case kasan_kunit_test_cases[] = { KUNIT_CASE(vmalloc_oob), KUNIT_CASE(vmap_tags), KUNIT_CASE(vm_map_ram_tags), - KUNIT_CASE(vmalloc_percpu), KUNIT_CASE(match_all_not_assigned), KUNIT_CASE(match_all_ptr_tag), KUNIT_CASE(match_all_mem_tag), diff --git a/mm/memory.c b/mm/memory.c index 3ccee51adfbb..bdf77a3ec47b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4187,6 +4187,8 @@ static struct folio *alloc_swap_folio(struct vm_fault *vmf) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static DECLARE_WAIT_QUEUE_HEAD(swapcache_wq); + /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. @@ -4199,6 +4201,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *swapcache, *folio = NULL; + DECLARE_WAITQUEUE(wait, current); struct page *page; struct swap_info_struct *si = NULL; rmap_t rmap_flags = RMAP_NONE; @@ -4297,7 +4300,9 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) * Relax a bit to prevent rapid * repeated page faults. */ + add_wait_queue(&swapcache_wq, &wait); schedule_timeout_uninterruptible(1); + remove_wait_queue(&swapcache_wq, &wait); goto out_page; } need_clear_cache = true; @@ -4604,8 +4609,11 @@ unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: /* Clear the swap cache pin for direct swapin after PTL unlock */ - if (need_clear_cache) + if (need_clear_cache) { swapcache_clear(si, entry, nr_pages); + if (waitqueue_active(&swapcache_wq)) + wake_up(&swapcache_wq); + } if (si) put_swap_device(si); return ret; @@ -4620,8 +4628,11 @@ out_release: folio_unlock(swapcache); folio_put(swapcache); } - if (need_clear_cache) + if (need_clear_cache) { swapcache_clear(si, entry, nr_pages); + if (waitqueue_active(&swapcache_wq)) + wake_up(&swapcache_wq); + } if (si) put_swap_device(si); return ret; diff --git a/mm/migrate.c b/mm/migrate.c index df91248755e4..fab84a776088 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -206,7 +206,8 @@ static bool try_to_map_unused_to_zeropage(struct page_vma_mapped_walk *pvmw, pte_t newpte; void *addr; - VM_BUG_ON_PAGE(PageCompound(page), page); + if (PageCompound(page)) + return false; VM_BUG_ON_PAGE(!PageAnon(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(pte_present(*pvmw->pte), page); @@ -1177,7 +1178,7 @@ static void migrate_folio_done(struct folio *src, * not accounted to NR_ISOLATED_*. They can be recognized * as __folio_test_movable */ - if (likely(!__folio_test_movable(src))) + if (likely(!__folio_test_movable(src)) && reason != MR_DEMOTION) mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON + folio_is_file_lru(src), -folio_nr_pages(src)); diff --git a/mm/mmap.c b/mm/mmap.c index 9c0fb43064b5..9841b41e3c76 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -900,7 +900,8 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, if (get_area) { addr = get_area(file, addr, len, pgoff, flags); - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) + && IS_ALIGNED(len, PMD_SIZE)) { /* Ensures that larger anonymous mappings are THP aligned. */ addr = thp_get_unmapped_area_vmflags(file, addr, len, pgoff, flags, vm_flags); @@ -1418,6 +1419,13 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vmg.flags = vm_flags; } + /* + * clear PTEs while the vma is still in the tree so that rmap + * cannot race with the freeing later in the truncate scenario. + * This is also needed for call_mmap(), which is why vm_ops + * close function is called. + */ + vms_clean_up_area(&vms, &mas_detach); vma = vma_merge_new_range(&vmg); if (vma) goto expanded; @@ -1439,11 +1447,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr, if (file) { vma->vm_file = get_file(file); - /* - * call_mmap() may map PTE, so ensure there are no existing PTEs - * and call the vm_ops close function if one exists. - */ - vms_clean_up_area(&vms, &mas_detach); error = call_mmap(file, vma); if (error) goto unmap_and_free_vma; @@ -1640,6 +1643,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long populate = 0; unsigned long ret = -EINVAL; struct file *file; + vm_flags_t vm_flags; pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n", current->comm, current->pid); @@ -1656,12 +1660,60 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (pgoff + (size >> PAGE_SHIFT) < pgoff) return ret; - if (mmap_write_lock_killable(mm)) + if (mmap_read_lock_killable(mm)) + return -EINTR; + + /* + * Look up VMA under read lock first so we can perform the security + * without holding locks (which can be problematic). We reacquire a + * write lock later and check nothing changed underneath us. + */ + vma = vma_lookup(mm, start); + + if (!vma || !(vma->vm_flags & VM_SHARED)) { + mmap_read_unlock(mm); + return -EINVAL; + } + + prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; + prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; + prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; + + flags &= MAP_NONBLOCK; + flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; + if (vma->vm_flags & VM_LOCKED) + flags |= MAP_LOCKED; + + /* Save vm_flags used to calculate prot and flags, and recheck later. */ + vm_flags = vma->vm_flags; + file = get_file(vma->vm_file); + + mmap_read_unlock(mm); + + /* Call outside mmap_lock to be consistent with other callers. */ + ret = security_mmap_file(file, prot, flags); + if (ret) { + fput(file); + return ret; + } + + ret = -EINVAL; + + /* OK security check passed, take write lock + let it rip. */ + if (mmap_write_lock_killable(mm)) { + fput(file); return -EINTR; + } vma = vma_lookup(mm, start); - if (!vma || !(vma->vm_flags & VM_SHARED)) + if (!vma) + goto out; + + /* Make sure things didn't change under us. */ + if (vma->vm_flags != vm_flags) + goto out; + if (vma->vm_file != file) goto out; if (start + size > vma->vm_end) { @@ -1689,25 +1741,11 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, goto out; } - prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; - prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; - prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; - - flags &= MAP_NONBLOCK; - flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; - if (vma->vm_flags & VM_LOCKED) - flags |= MAP_LOCKED; - - file = get_file(vma->vm_file); - ret = security_mmap_file(vma->vm_file, prot, flags); - if (ret) - goto out_fput; ret = do_mmap(vma->vm_file, start, size, prot, flags, 0, pgoff, &populate, NULL); -out_fput: - fput(file); out: mmap_write_unlock(mm); + fput(file); if (populate) mm_populate(ret, populate); if (!IS_ERR_VALUE(ret)) @@ -1754,7 +1792,8 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, VMG_STATE(vmg, mm, vmi, addr, addr + len, flags, PHYS_PFN(addr)); vmg.prev = vma; - vma_iter_next_range(vmi); + /* vmi is positioned at prev, which this mode expects. */ + vmg.merge_flags = VMG_FLAG_JUST_EXPAND; if (vma_merge_new_range(&vmg)) goto out; diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c index be52b93a9c58..a3877e9bc878 100644 --- a/mm/numa_memblks.c +++ b/mm/numa_memblks.c @@ -349,7 +349,7 @@ static void __init numa_clear_kernel_node_hotplug(void) for_each_reserved_mem_region(mb_region) { int nid = memblock_get_region_node(mb_region); - if (nid != MAX_NUMNODES) + if (numa_valid_node(nid)) node_set(nid, reserved_nodemask); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8afab64814dc..34b3eb74630a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2893,12 +2893,12 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone, page = __rmqueue(zone, order, migratetype, alloc_flags); /* - * If the allocation fails, allow OOM handling access - * to HIGHATOMIC reserves as failing now is worse than - * failing a high-order atomic allocation in the - * future. + * If the allocation fails, allow OOM handling and + * order-0 (atomic) allocs access to HIGHATOMIC + * reserves as failing now is worse than failing a + * high-order atomic allocation in the future. */ - if (!page && (alloc_flags & ALLOC_OOM)) + if (!page && (alloc_flags & (ALLOC_OOM|ALLOC_NON_BLOCK))) page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); if (!page) { @@ -4836,142 +4836,6 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); -/* - * Page Fragment: - * An arbitrary-length arbitrary-offset area of memory which resides - * within a 0 or higher order page. Multiple fragments within that page - * are individually refcounted, in the page's reference counter. - * - * The page_frag functions below provide a simple allocation framework for - * page fragments. This is used by the network stack and network device - * drivers to provide a backing region of memory for use as either an - * sk_buff->head, or to be used in the "frags" portion of skb_shared_info. - */ -static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, - gfp_t gfp_mask) -{ - struct page *page = NULL; - gfp_t gfp = gfp_mask; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | - __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; - page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, - PAGE_FRAG_CACHE_MAX_ORDER); - nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; -#endif - if (unlikely(!page)) - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - - nc->va = page ? page_address(page) : NULL; - - return page; -} - -void page_frag_cache_drain(struct page_frag_cache *nc) -{ - if (!nc->va) - return; - - __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); - nc->va = NULL; -} -EXPORT_SYMBOL(page_frag_cache_drain); - -void __page_frag_cache_drain(struct page *page, unsigned int count) -{ - VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); - - if (page_ref_sub_and_test(page, count)) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(__page_frag_cache_drain); - -void *__page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) -{ - unsigned int size = PAGE_SIZE; - struct page *page; - int offset; - - if (unlikely(!nc->va)) { -refill: - page = __page_frag_cache_refill(nc, gfp_mask); - if (!page) - return NULL; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* Even if we own the page, we do not use atomic_set(). - * This would break get_page_unless_zero() users. - */ - page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); - - /* reset page count bias and offset to start of new frag */ - nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - nc->offset = size; - } - - offset = nc->offset - fragsz; - if (unlikely(offset < 0)) { - page = virt_to_page(nc->va); - - if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) - goto refill; - - if (unlikely(nc->pfmemalloc)) { - free_unref_page(page, compound_order(page)); - goto refill; - } - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size = nc->size; -#endif - /* OK, page count is 0, we can safely set it */ - set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); - - /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; - offset = size - fragsz; - if (unlikely(offset < 0)) { - /* - * The caller is trying to allocate a fragment - * with fragsz > PAGE_SIZE but the cache isn't big - * enough to satisfy the request, this may - * happen in low memory conditions. - * We don't release the cache page because - * it could make memory pressure worse - * so we simply return NULL here. - */ - return NULL; - } - } - - nc->pagecnt_bias--; - offset &= align_mask; - nc->offset = offset; - - return nc->va + offset; -} -EXPORT_SYMBOL(__page_frag_alloc_align); - -/* - * Frees a page fragment allocated out of either a compound or order 0 page. - */ -void page_frag_free(void *addr) -{ - struct page *page = virt_to_head_page(addr); - - if (unlikely(put_page_testzero(page))) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(page_frag_free); - static void *make_alloc_exact(unsigned long addr, unsigned int order, size_t size) { diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c new file mode 100644 index 000000000000..3f7a203d35c6 --- /dev/null +++ b/mm/page_frag_cache.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Page fragment allocator + * + * Page Fragment: + * An arbitrary-length arbitrary-offset area of memory which resides within a + * 0 or higher order page. Multiple fragments within that page are + * individually refcounted, in the page's reference counter. + * + * The page_frag functions provide a simple allocation framework for page + * fragments. This is used by the network stack and network device drivers to + * provide a backing region of memory for use as either an sk_buff->head, or to + * be used in the "frags" portion of skb_shared_info. + */ + +#include <linux/build_bug.h> +#include <linux/export.h> +#include <linux/gfp_types.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/page_frag_cache.h> +#include "internal.h" + +static unsigned long encoded_page_create(struct page *page, unsigned int order, + bool pfmemalloc) +{ + BUILD_BUG_ON(PAGE_FRAG_CACHE_MAX_ORDER > PAGE_FRAG_CACHE_ORDER_MASK); + BUILD_BUG_ON(PAGE_FRAG_CACHE_PFMEMALLOC_BIT >= PAGE_SIZE); + + return (unsigned long)page_address(page) | + (order & PAGE_FRAG_CACHE_ORDER_MASK) | + ((unsigned long)pfmemalloc * PAGE_FRAG_CACHE_PFMEMALLOC_BIT); +} + +static unsigned long encoded_page_decode_order(unsigned long encoded_page) +{ + return encoded_page & PAGE_FRAG_CACHE_ORDER_MASK; +} + +static void *encoded_page_decode_virt(unsigned long encoded_page) +{ + return (void *)(encoded_page & PAGE_MASK); +} + +static struct page *encoded_page_decode_page(unsigned long encoded_page) +{ + return virt_to_page((void *)encoded_page); +} + +static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, + gfp_t gfp_mask) +{ + unsigned long order = PAGE_FRAG_CACHE_MAX_ORDER; + struct page *page = NULL; + gfp_t gfp = gfp_mask; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | + __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; + page = __alloc_pages(gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER, + numa_mem_id(), NULL); +#endif + if (unlikely(!page)) { + page = __alloc_pages(gfp, 0, numa_mem_id(), NULL); + order = 0; + } + + nc->encoded_page = page ? + encoded_page_create(page, order, page_is_pfmemalloc(page)) : 0; + + return page; +} + +void page_frag_cache_drain(struct page_frag_cache *nc) +{ + if (!nc->encoded_page) + return; + + __page_frag_cache_drain(encoded_page_decode_page(nc->encoded_page), + nc->pagecnt_bias); + nc->encoded_page = 0; +} +EXPORT_SYMBOL(page_frag_cache_drain); + +void __page_frag_cache_drain(struct page *page, unsigned int count) +{ + VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); + + if (page_ref_sub_and_test(page, count)) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(__page_frag_cache_drain); + +void *__page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) +{ + unsigned long encoded_page = nc->encoded_page; + unsigned int size, offset; + struct page *page; + + if (unlikely(!encoded_page)) { +refill: + page = __page_frag_cache_refill(nc, gfp_mask); + if (!page) + return NULL; + + encoded_page = nc->encoded_page; + + /* Even if we own the page, we do not use atomic_set(). + * This would break get_page_unless_zero() users. + */ + page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); + + /* reset page count bias and offset to start of new frag */ + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + nc->offset = 0; + } + + size = PAGE_SIZE << encoded_page_decode_order(encoded_page); + offset = __ALIGN_KERNEL_MASK(nc->offset, ~align_mask); + if (unlikely(offset + fragsz > size)) { + if (unlikely(fragsz > PAGE_SIZE)) { + /* + * The caller is trying to allocate a fragment + * with fragsz > PAGE_SIZE but the cache isn't big + * enough to satisfy the request, this may + * happen in low memory conditions. + * We don't release the cache page because + * it could make memory pressure worse + * so we simply return NULL here. + */ + return NULL; + } + + page = encoded_page_decode_page(encoded_page); + + if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) + goto refill; + + if (unlikely(encoded_page_decode_pfmemalloc(encoded_page))) { + free_unref_page(page, + encoded_page_decode_order(encoded_page)); + goto refill; + } + + /* OK, page count is 0, we can safely set it */ + set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); + + /* reset page count bias and offset to start of new frag */ + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; + offset = 0; + } + + nc->pagecnt_bias--; + nc->offset = offset + fragsz; + + return encoded_page_decode_virt(encoded_page) + offset; +} +EXPORT_SYMBOL(__page_frag_alloc_align); + +/* + * Frees a page fragment allocated out of either a compound or order 0 page. + */ +void page_frag_free(void *addr) +{ + struct page *page = virt_to_head_page(addr); + + if (unlikely(put_page_testzero(page))) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(page_frag_free); diff --git a/mm/page_io.c b/mm/page_io.c index 78bc88acee79..69536a2b3c13 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -570,7 +570,7 @@ static void swap_read_folio_bdev_sync(struct folio *folio, * attempt to access it in the page fault retry time check. */ get_task_struct(current); - count_vm_event(PSWPIN); + count_vm_events(PSWPIN, folio_nr_pages(folio)); submit_bio_wait(&bio); __end_swap_bio_read(&bio); put_task_struct(current); @@ -585,7 +585,7 @@ static void swap_read_folio_bdev_async(struct folio *folio, bio->bi_iter.bi_sector = swap_folio_sector(folio); bio->bi_end_io = end_swap_bio_read; bio_add_folio_nofail(bio, folio, folio_size(folio), 0); - count_vm_event(PSWPIN); + count_vm_events(PSWPIN, folio_nr_pages(folio)); submit_bio(bio); } diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 461ea3bbd8d9..5f9f01532e67 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -744,7 +744,8 @@ struct folio *folio_walk_start(struct folio_walk *fw, pud = pudp_get(pudp); if (pud_none(pud)) goto not_found; - if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && pud_leaf(pud)) { + if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && + (!pud_present(pud) || pud_leaf(pud))) { ptl = pud_lock(vma->vm_mm, pudp); pud = pudp_get(pudp); @@ -753,6 +754,10 @@ struct folio *folio_walk_start(struct folio_walk *fw, fw->pudp = pudp; fw->pud = pud; + /* + * TODO: FW_MIGRATION support for PUD migration entries + * once there are relevant users. + */ if (!pud_present(pud) || pud_devmap(pud) || pud_special(pud)) { spin_unlock(ptl); goto not_found; @@ -769,12 +774,13 @@ struct folio *folio_walk_start(struct folio_walk *fw, } pmd_table: - VM_WARN_ON_ONCE(pud_leaf(*pudp)); + VM_WARN_ON_ONCE(!pud_present(pud) || pud_leaf(pud)); pmdp = pmd_offset(pudp, addr); pmd = pmdp_get_lockless(pmdp); if (pmd_none(pmd)) goto not_found; - if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && pmd_leaf(pmd)) { + if (IS_ENABLED(CONFIG_PGTABLE_HAS_HUGE_LEAVES) && + (!pmd_present(pmd) || pmd_leaf(pmd))) { ptl = pmd_lock(vma->vm_mm, pmdp); pmd = pmdp_get(pmdp); @@ -786,7 +792,7 @@ pmd_table: if (pmd_none(pmd)) { spin_unlock(ptl); goto not_found; - } else if (!pmd_leaf(pmd)) { + } else if (pmd_present(pmd) && !pmd_leaf(pmd)) { spin_unlock(ptl); goto pte_table; } else if (pmd_present(pmd)) { @@ -812,7 +818,7 @@ pmd_table: } pte_table: - VM_WARN_ON_ONCE(pmd_leaf(pmdp_get_lockless(pmdp))); + VM_WARN_ON_ONCE(!pmd_present(pmd) || pmd_leaf(pmd)); ptep = pte_offset_map_lock(vma->vm_mm, pmdp, addr, &ptl); if (!ptep) goto not_found; diff --git a/mm/rmap.c b/mm/rmap.c index a8797d1b3d49..73d5998677d4 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -885,13 +885,10 @@ static bool folio_referenced_one(struct folio *folio, return false; } - if (pvmw.pte) { - if (lru_gen_enabled() && - pte_young(ptep_get(pvmw.pte))) { - lru_gen_look_around(&pvmw); + if (lru_gen_enabled() && pvmw.pte) { + if (lru_gen_look_around(&pvmw)) referenced++; - } - + } else if (pvmw.pte) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) referenced++; diff --git a/mm/shmem.c b/mm/shmem.c index c5adb987b23c..4ba1d00fabda 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1166,7 +1166,9 @@ static int shmem_getattr(struct mnt_idmap *idmap, stat->attributes_mask |= (STATX_ATTR_APPEND | STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); + inode_lock_shared(inode); generic_fillattr(idmap, request_mask, inode, stat); + inode_unlock_shared(inode); if (shmem_huge_global_enabled(inode, 0, 0, false, NULL, 0)) stat->blksize = HPAGE_PMD_SIZE; diff --git a/mm/shrinker.c b/mm/shrinker.c index dc5d2a6fcfc4..4a93fd433689 100644 --- a/mm/shrinker.c +++ b/mm/shrinker.c @@ -76,19 +76,21 @@ void free_shrinker_info(struct mem_cgroup *memcg) int alloc_shrinker_info(struct mem_cgroup *memcg) { - struct shrinker_info *info; int nid, ret = 0; int array_size = 0; mutex_lock(&shrinker_mutex); array_size = shrinker_unit_size(shrinker_nr_max); for_each_node(nid) { - info = kvzalloc_node(sizeof(*info) + array_size, GFP_KERNEL, nid); + struct shrinker_info *info = kvzalloc_node(sizeof(*info) + array_size, + GFP_KERNEL, nid); if (!info) goto err; info->map_nr_max = shrinker_nr_max; - if (shrinker_unit_alloc(info, NULL, nid)) + if (shrinker_unit_alloc(info, NULL, nid)) { + kvfree(info); goto err; + } rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } mutex_unlock(&shrinker_mutex); diff --git a/mm/slab_common.c b/mm/slab_common.c index 3d26c257ed8b..552b92dfdac7 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1209,7 +1209,7 @@ __do_krealloc(const void *p, size_t new_size, gfp_t flags) /* Zero out spare memory. */ if (want_init_on_alloc(flags)) { kasan_disable_current(); - memset((void *)p + new_size, 0, ks - new_size); + memset(kasan_reset_tag(p) + new_size, 0, ks - new_size); kasan_enable_current(); } diff --git a/mm/swapfile.c b/mm/swapfile.c index b0915f3fab31..46bd4b1a3c07 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -731,15 +731,16 @@ done: return offset; } -static void swap_reclaim_full_clusters(struct swap_info_struct *si) +/* Return true if reclaimed a whole cluster */ +static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) { long to_scan = 1; unsigned long offset, end; struct swap_cluster_info *ci; unsigned char *map = si->swap_map; - int nr_reclaim, total_reclaimed = 0; + int nr_reclaim; - if (atomic_long_read(&nr_swap_pages) <= SWAPFILE_CLUSTER) + if (force) to_scan = si->inuse_pages / SWAPFILE_CLUSTER; while (!list_empty(&si->full_clusters)) { @@ -749,28 +750,36 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si) end = min(si->max, offset + SWAPFILE_CLUSTER); to_scan--; + spin_unlock(&si->lock); while (offset < end) { if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) { - spin_unlock(&si->lock); nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT); - spin_lock(&si->lock); - if (nr_reclaim > 0) { - offset += nr_reclaim; - total_reclaimed += nr_reclaim; - continue; - } else if (nr_reclaim < 0) { - offset += -nr_reclaim; + if (nr_reclaim) { + offset += abs(nr_reclaim); continue; } } offset++; } - if (to_scan <= 0 || total_reclaimed) + spin_lock(&si->lock); + + if (to_scan <= 0) break; } } +static void swap_reclaim_work(struct work_struct *work) +{ + struct swap_info_struct *si; + + si = container_of(work, struct swap_info_struct, reclaim_work); + + spin_lock(&si->lock); + swap_reclaim_full_clusters(si, true); + spin_unlock(&si->lock); +} + /* * Try to get swap entries with specified order from current cpu's swap entry * pool (a cluster). This might involve allocating a new cluster for current CPU @@ -800,6 +809,10 @@ new_cluster: goto done; } + /* Try reclaim from full clusters if free clusters list is drained */ + if (vm_swap_full()) + swap_reclaim_full_clusters(si, false); + if (order < PMD_ORDER) { unsigned int frags = 0; @@ -881,13 +894,6 @@ new_cluster: } done: - /* Try reclaim from full clusters if device is nearfull */ - if (vm_swap_full() && (!found || (si->pages - si->inuse_pages) < SWAPFILE_CLUSTER)) { - swap_reclaim_full_clusters(si); - if (!found && !order && si->pages != si->inuse_pages) - goto new_cluster; - } - cluster->next[order] = offset; return found; } @@ -922,6 +928,9 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, si->lowest_bit = si->max; si->highest_bit = 0; del_from_avail_list(si); + + if (vm_swap_full()) + schedule_work(&si->reclaim_work); } } @@ -2816,6 +2825,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) wait_for_completion(&p->comp); flush_work(&p->discard_work); + flush_work(&p->reclaim_work); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) @@ -3376,6 +3386,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) return PTR_ERR(si); INIT_WORK(&si->discard_work, swap_discard_work); + INIT_WORK(&si->reclaim_work, swap_reclaim_work); name = getname(specialfile); if (IS_ERR(name)) { @@ -917,6 +917,7 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) pgoff_t pgoff = vmg->pgoff; pgoff_t pglen = PHYS_PFN(end - start); bool can_merge_left, can_merge_right; + bool just_expand = vmg->merge_flags & VMG_FLAG_JUST_EXPAND; mmap_assert_write_locked(vmg->mm); VM_WARN_ON(vmg->vma); @@ -930,7 +931,7 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) return NULL; can_merge_left = can_vma_merge_left(vmg); - can_merge_right = can_vma_merge_right(vmg, can_merge_left); + can_merge_right = !just_expand && can_vma_merge_right(vmg, can_merge_left); /* If we can merge with the next VMA, adjust vmg accordingly. */ if (can_merge_right) { @@ -953,7 +954,11 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) if (can_merge_right && !can_merge_remove_vma(next)) vmg->end = end; - vma_prev(vmg->vmi); /* Equivalent to going to the previous range */ + /* In expand-only case we are already positioned at prev. */ + if (!just_expand) { + /* Equivalent to going to the previous range. */ + vma_prev(vmg->vmi); + } } /* @@ -967,12 +972,14 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) } /* If expansion failed, reset state. Allows us to retry merge later. */ - vmg->vma = NULL; - vmg->start = start; - vmg->end = end; - vmg->pgoff = pgoff; - if (vmg->vma == prev) - vma_iter_set(vmg->vmi, start); + if (!just_expand) { + vmg->vma = NULL; + vmg->start = start; + vmg->end = end; + vmg->pgoff = pgoff; + if (vmg->vma == prev) + vma_iter_set(vmg->vmi, start); + } return NULL; } @@ -59,6 +59,17 @@ enum vma_merge_state { VMA_MERGE_SUCCESS, }; +enum vma_merge_flags { + VMG_FLAG_DEFAULT = 0, + /* + * If we can expand, simply do so. We know there is nothing to merge to + * the right. Does not reset state upon failure to merge. The VMA + * iterator is assumed to be positioned at the previous VMA, rather than + * at the gap. + */ + VMG_FLAG_JUST_EXPAND = 1 << 0, +}; + /* Represents a VMA merge operation. */ struct vma_merge_struct { struct mm_struct *mm; @@ -75,6 +86,7 @@ struct vma_merge_struct { struct mempolicy *policy; struct vm_userfaultfd_ctx uffd_ctx; struct anon_vma_name *anon_name; + enum vma_merge_flags merge_flags; enum vma_merge_state state; }; @@ -99,6 +111,7 @@ static inline pgoff_t vma_pgoff_offset(struct vm_area_struct *vma, .flags = flags_, \ .pgoff = pgoff_, \ .state = VMA_MERGE_START, \ + .merge_flags = VMG_FLAG_DEFAULT, \ } #define VMG_VMA_STATE(name, vmi_, prev_, vma_, start_, end_) \ @@ -118,6 +131,7 @@ static inline pgoff_t vma_pgoff_offset(struct vm_area_struct *vma, .uffd_ctx = vma_->vm_userfaultfd_ctx, \ .anon_name = anon_vma_name(vma_), \ .state = VMA_MERGE_START, \ + .merge_flags = VMG_FLAG_DEFAULT, \ } #ifdef CONFIG_DEBUG_VM_MAPLE_TREE @@ -241,15 +255,9 @@ static inline void vms_abort_munmap_vmas(struct vma_munmap_struct *vms, * failure method of leaving a gap where the MAP_FIXED mapping failed. */ mas_set_range(mas, vms->start, vms->end - 1); - if (unlikely(mas_store_gfp(mas, NULL, GFP_KERNEL))) { - pr_warn_once("%s: (%d) Unable to abort munmap() operation\n", - current->comm, current->pid); - /* Leaving vmas detached and in-tree may hamper recovery */ - reattach_vmas(mas_detach); - } else { - /* Clean up the insertion of the unfortunate gap */ - vms_complete_munmap_vmas(vms, mas_detach); - } + mas_store_gfp(mas, NULL, GFP_KERNEL|__GFP_NOFAIL); + /* Clean up the insertion of the unfortunate gap */ + vms_complete_munmap_vmas(vms, mas_detach); } int diff --git a/mm/vmscan.c b/mm/vmscan.c index eb4e8440c507..ddaaff67642e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -56,6 +56,7 @@ #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> +#include <linux/mmu_notifier.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -3294,7 +3295,8 @@ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk return false; } -static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr) +static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr, + struct pglist_data *pgdat) { unsigned long pfn = pte_pfn(pte); @@ -3306,13 +3308,20 @@ static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) return -1; + if (!pte_young(pte) && !mm_has_notifiers(vma->vm_mm)) + return -1; + if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; + if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) + return -1; + return pfn; } -static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr) +static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr, + struct pglist_data *pgdat) { unsigned long pfn = pmd_pfn(pmd); @@ -3324,9 +3333,15 @@ static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned if (WARN_ON_ONCE(pmd_devmap(pmd))) return -1; + if (!pmd_young(pmd) && !mm_has_notifiers(vma->vm_mm)) + return -1; + if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; + if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) + return -1; + return pfn; } @@ -3335,10 +3350,6 @@ static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, { struct folio *folio; - /* try to avoid unnecessary memory loads */ - if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) - return NULL; - folio = pfn_folio(pfn); if (folio_nid(folio) != pgdat->node_id) return NULL; @@ -3394,21 +3405,16 @@ restart: total++; walk->mm_stats[MM_LEAF_TOTAL]++; - pfn = get_pte_pfn(ptent, args->vma, addr); + pfn = get_pte_pfn(ptent, args->vma, addr, pgdat); if (pfn == -1) continue; - if (!pte_young(ptent)) { - walk->mm_stats[MM_LEAF_OLD]++; - continue; - } - folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) continue; - if (!ptep_test_and_clear_young(args->vma, addr, pte + i)) - VM_WARN_ON_ONCE(true); + if (!ptep_clear_young_notify(args->vma, addr, pte + i)) + continue; young++; walk->mm_stats[MM_LEAF_YOUNG]++; @@ -3474,21 +3480,25 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area /* don't round down the first address */ addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first; - pfn = get_pmd_pfn(pmd[i], vma, addr); - if (pfn == -1) + if (!pmd_present(pmd[i])) goto next; if (!pmd_trans_huge(pmd[i])) { - if (!walk->force_scan && should_clear_pmd_young()) + if (!walk->force_scan && should_clear_pmd_young() && + !mm_has_notifiers(args->mm)) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; } + pfn = get_pmd_pfn(pmd[i], vma, addr, pgdat); + if (pfn == -1) + goto next; + folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) goto next; - if (!pmdp_test_and_clear_young(vma, addr, pmd + i)) + if (!pmdp_clear_young_notify(vma, addr, pmd + i)) goto next; walk->mm_stats[MM_LEAF_YOUNG]++; @@ -3546,27 +3556,18 @@ restart: } if (pmd_trans_huge(val)) { - unsigned long pfn = pmd_pfn(val); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); + unsigned long pfn = get_pmd_pfn(val, vma, addr, pgdat); walk->mm_stats[MM_LEAF_TOTAL]++; - if (!pmd_young(val)) { - walk->mm_stats[MM_LEAF_OLD]++; - continue; - } - - /* try to avoid unnecessary memory loads */ - if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) - continue; - - walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); + if (pfn != -1) + walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); continue; } - walk->mm_stats[MM_NONLEAF_TOTAL]++; - - if (!walk->force_scan && should_clear_pmd_young()) { + if (!walk->force_scan && should_clear_pmd_young() && + !mm_has_notifiers(args->mm)) { if (!pmd_young(val)) continue; @@ -4040,13 +4041,13 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) * the PTE table to the Bloom filter. This forms a feedback loop between the * eviction and the aging. */ -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; unsigned long start; unsigned long end; struct lru_gen_mm_walk *walk; - int young = 0; + int young = 1; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; @@ -4062,12 +4063,15 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); + if (!ptep_clear_young_notify(vma, addr, pte)) + return false; + if (spin_is_contended(pvmw->ptl)) - return; + return true; /* exclude special VMAs containing anon pages from COW */ if (vma->vm_flags & VM_SPECIAL) - return; + return true; /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; @@ -4075,6 +4079,9 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) start = max(addr & PMD_MASK, vma->vm_start); end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; + if (end - start == PAGE_SIZE) + return true; + if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) end = start + MIN_LRU_BATCH * PAGE_SIZE; @@ -4088,7 +4095,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) - return; + return true; arch_enter_lazy_mmu_mode(); @@ -4098,19 +4105,16 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) unsigned long pfn; pte_t ptent = ptep_get(pte + i); - pfn = get_pte_pfn(ptent, vma, addr); + pfn = get_pte_pfn(ptent, vma, addr, pgdat); if (pfn == -1) continue; - if (!pte_young(ptent)) - continue; - folio = get_pfn_folio(pfn, memcg, pgdat, can_swap); if (!folio) continue; - if (!ptep_test_and_clear_young(vma, addr, pte + i)) - VM_WARN_ON_ONCE(true); + if (!ptep_clear_young_notify(vma, addr, pte + i)) + continue; young++; @@ -4140,6 +4144,8 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) update_bloom_filter(mm_state, max_seq, pvmw->pmd); + + return true; } /****************************************************************************** @@ -5254,11 +5260,11 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); for (type = 0; type < ANON_AND_FILE; type++) { - const char *s = " "; + const char *s = "xxx"; unsigned long n[3] = {}; if (seq == max_seq) { - s = "RT "; + s = "RTx"; n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); n[1] = READ_ONCE(lrugen->avg_total[type][tier]); } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { @@ -5280,14 +5286,14 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, seq_puts(m, " "); for (i = 0; i < NR_MM_STATS; i++) { - const char *s = " "; + const char *s = "xxxx"; unsigned long n = 0; if (seq == max_seq && NR_HIST_GENS == 1) { - s = "LOYNFA"; + s = "TYFA"; n = READ_ONCE(mm_state->stats[hist][i]); } else if (seq != max_seq && NR_HIST_GENS > 1) { - s = "loynfa"; + s = "tyfa"; n = READ_ONCE(mm_state->stats[hist][i]); } diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index cf5219df7903..134419667d59 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -161,10 +161,8 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, return -ENODEV; } - if (data[IFLA_VLAN_PROTOCOL]) - proto = nla_get_be16(data[IFLA_VLAN_PROTOCOL]); - else - proto = htons(ETH_P_8021Q); + proto = nla_get_be16_default(data[IFLA_VLAN_PROTOCOL], + htons(ETH_P_8021Q)); vlan->vlan_proto = proto; vlan->vlan_id = nla_get_u16(data[IFLA_VLAN_ID]); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index ae7a5817883a..c0203a2b5107 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -206,6 +206,12 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, return ERR_PTR(err); } + /* If command return a status event skb will be set to NULL as there are + * no parameters. + */ + if (!skb) + return ERR_PTR(-ENODATA); + return skb; } EXPORT_SYMBOL(__hci_cmd_sync_sk); @@ -255,6 +261,11 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, u8 status; skb = __hci_cmd_sync_sk(hdev, opcode, plen, param, event, timeout, sk); + + /* If command return a status event, skb will be set to -ENODATA */ + if (skb == ERR_PTR(-ENODATA)) + return 0; + if (IS_ERR(skb)) { if (!event) bt_dev_err(hdev, "Opcode 0x%4.4x failed: %ld", opcode, @@ -262,13 +273,6 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, return PTR_ERR(skb); } - /* If command return a status event skb will be set to NULL as there are - * no parameters, in case of failure IS_ERR(skb) would have be set to - * the actual error would be found with PTR_ERR(skb). - */ - if (!skb) - return 0; - status = skb->data[0]; kfree_skb(skb); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 6d7a442ceb89..501ec4249fed 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -246,6 +246,7 @@ static void reset_ctx(struct xdp_page_head *head) head->ctx.data_meta = head->orig_ctx.data_meta; head->ctx.data_end = head->orig_ctx.data_end; xdp_update_frame_from_buff(&head->ctx, head->frame); + head->frame->mem = head->orig_ctx.rxq->mem; } static int xdp_recv_frames(struct xdp_frame **frames, int nframes, diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 1cd7bade9b3b..77f110035df1 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -1319,7 +1319,6 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], { struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; - struct net_bridge_vlan *v; struct net_bridge *br; int err; @@ -1338,14 +1337,10 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], } if (vid) { - v = br_vlan_find(vg, vid); - if (!v) { - pr_info("bridge: RTM_DELNEIGH with unconfigured vlan %d on %s\n", vid, dev->name); - return -EINVAL; - } - err = __br_fdb_delete(br, p, addr, vid); } else { + struct net_bridge_vlan *v; + err = -ENOENT; err &= __br_fdb_delete(br, p, addr, 0); if (!vg || !vg->num_vlans) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 17a5f5923d61..451e45b9a6a5 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -373,8 +373,8 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_ struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct net_device *dev = skb->dev, *br_indev; const struct iphdr *iph = ip_hdr(skb); + enum skb_drop_reason reason; struct rtable *rt; - int err; br_indev = nf_bridge_get_physindev(skb, net); if (!br_indev) { @@ -390,9 +390,9 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_ } nf_bridge->in_prerouting = 0; if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) { - err = ip_route_input(skb, iph->daddr, iph->saddr, - ip4h_dscp(iph), dev); - if (err) { + reason = ip_route_input(skb, iph->daddr, iph->saddr, + ip4h_dscp(iph), dev); + if (reason) { struct in_device *in_dev = __in_dev_get_rcu(dev); /* If err equals -EHOSTUNREACH the error is due to a @@ -402,11 +402,12 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_ * martian destinations: loopback destinations and destination * 0.0.0.0. In both cases the packet will be dropped because the * destination is the loopback device and not the bridge. */ - if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev)) + if (reason != SKB_DROP_REASON_IP_INADDRERRORS || !in_dev || + IN_DEV_FORWARD(in_dev)) goto free_skb; rt = ip_route_output(net, iph->daddr, 0, - iph->tos & INET_DSCP_MASK, 0, + ip4h_dscp(iph), 0, RT_SCOPE_UNIVERSE); if (!IS_ERR(rt)) { /* - Bridged-and-DNAT'ed traffic doesn't diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 104c0125e32e..f16bbbbb9481 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -41,7 +41,13 @@ config NF_CONNTRACK_BRIDGE # old sockopt interface and eval loop config BRIDGE_NF_EBTABLES_LEGACY - tristate + tristate "Legacy EBTABLES support" + depends on BRIDGE && NETFILTER_XTABLES + default n + help + Legacy ebtables packet/frame classifier. + This is not needed if you are using ebtables over nftables + (iptables-nft). menuconfig BRIDGE_NF_EBTABLES tristate "Ethernet Bridge tables (ebtables) support" diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index d12a221366d6..5adced1e7d0c 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -63,7 +63,7 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr, return nft_meta_get_eval(expr, regs, pkt); } - strncpy((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ); + strscpy_pad((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ); return; err: regs->verdict.code = NFT_BREAK; diff --git a/net/core/Makefile b/net/core/Makefile index 5a72a87ee0f1..d9326600e289 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -46,3 +46,4 @@ obj-$(CONFIG_OF) += of_net.o obj-$(CONFIG_NET_TEST) += net_test.o obj-$(CONFIG_NET_DEVMEM) += devmem.o obj-$(CONFIG_DEBUG_NET_SMALL_RTNL) += rtnl_net_debug.o +obj-$(CONFIG_FAIL_SKB_REALLOC) += skb_fault_injection.o diff --git a/net/core/dev.c b/net/core/dev.c index c682173a7642..13d00fc10f55 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3641,6 +3641,9 @@ int skb_csum_hwoffload_help(struct sk_buff *skb, return 0; if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { + if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) && + skb_network_header_len(skb) != sizeof(struct ipv6hdr)) + goto sw_checksum; switch (skb->csum_offset) { case offsetof(struct tcphdr, check): case offsetof(struct udphdr, check): @@ -3648,6 +3651,7 @@ int skb_csum_hwoffload_help(struct sk_buff *skb, } } +sw_checksum: return skb_checksum_help(skb); } EXPORT_SYMBOL(skb_csum_hwoffload_help); @@ -6503,6 +6507,43 @@ void napi_busy_loop(unsigned int napi_id, } EXPORT_SYMBOL(napi_busy_loop); +void napi_suspend_irqs(unsigned int napi_id) +{ + struct napi_struct *napi; + + rcu_read_lock(); + napi = napi_by_id(napi_id); + if (napi) { + unsigned long timeout = napi_get_irq_suspend_timeout(napi); + + if (timeout) + hrtimer_start(&napi->timer, ns_to_ktime(timeout), + HRTIMER_MODE_REL_PINNED); + } + rcu_read_unlock(); +} + +void napi_resume_irqs(unsigned int napi_id) +{ + struct napi_struct *napi; + + rcu_read_lock(); + napi = napi_by_id(napi_id); + if (napi) { + /* If irq_suspend_timeout is set to 0 between the call to + * napi_suspend_irqs and now, the original value still + * determines the safety timeout as intended and napi_watchdog + * will resume irq processing. + */ + if (napi_get_irq_suspend_timeout(napi)) { + local_bh_disable(); + napi_schedule(napi); + local_bh_enable(); + } + } + rcu_read_unlock(); +} + #endif /* CONFIG_NET_RX_BUSY_POLL */ static void __napi_hash_add_with_id(struct napi_struct *napi, @@ -6662,6 +6703,7 @@ static void napi_restore_config(struct napi_struct *n) { n->defer_hard_irqs = n->config->defer_hard_irqs; n->gro_flush_timeout = n->config->gro_flush_timeout; + n->irq_suspend_timeout = n->config->irq_suspend_timeout; /* a NAPI ID might be stored in the config, if so use it. if not, use * napi_hash_add to generate one for us. It will be saved to the config * in napi_disable. @@ -6676,6 +6718,7 @@ static void napi_save_config(struct napi_struct *n) { n->config->defer_hard_irqs = n->defer_hard_irqs; n->config->gro_flush_timeout = n->gro_flush_timeout; + n->config->irq_suspend_timeout = n->irq_suspend_timeout; n->config->napi_id = n->napi_id; napi_hash_del(n); } diff --git a/net/core/dev.h b/net/core/dev.h index 7881bced70a9..d043dee25a68 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -236,6 +236,31 @@ static inline void netdev_set_gro_flush_timeout(struct net_device *netdev, netdev->napi_config[i].gro_flush_timeout = timeout; } +/** + * napi_get_irq_suspend_timeout - get the irq_suspend_timeout + * @n: napi struct to get the irq_suspend_timeout from + * + * Return: the per-NAPI value of the irq_suspend_timeout field. + */ +static inline unsigned long +napi_get_irq_suspend_timeout(const struct napi_struct *n) +{ + return READ_ONCE(n->irq_suspend_timeout); +} + +/** + * napi_set_irq_suspend_timeout - set the irq_suspend_timeout for a napi + * @n: napi struct to set the irq_suspend_timeout + * @timeout: timeout value to set + * + * napi_set_irq_suspend_timeout sets the per-NAPI irq_suspend_timeout + */ +static inline void napi_set_irq_suspend_timeout(struct napi_struct *n, + unsigned long timeout) +{ + WRITE_ONCE(n->irq_suspend_timeout, timeout); +} + int rps_cpumask_housekeeping(struct cpumask *mask); #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index d0de9677f450..34185d138c95 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -558,8 +558,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, nlrule->pref = fib_default_rule_pref(ops); } - nlrule->proto = tb[FRA_PROTOCOL] ? - nla_get_u8(tb[FRA_PROTOCOL]) : RTPROT_UNSPEC; + nlrule->proto = nla_get_u8_default(tb[FRA_PROTOCOL], RTPROT_UNSPEC); if (tb[FRA_IIFNAME]) { struct net_device *dev; diff --git a/net/core/filter.c b/net/core/filter.c index 58761263176c..82f92ed0dc72 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1654,18 +1654,6 @@ void sk_reuseport_prog_free(struct bpf_prog *prog) bpf_prog_destroy(prog); } -struct bpf_scratchpad { - union { - __be32 diff[MAX_BPF_STACK / sizeof(__be32)]; - u8 buff[MAX_BPF_STACK]; - }; - local_lock_t bh_lock; -}; - -static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp) = { - .bh_lock = INIT_LOCAL_LOCK(bh_lock), -}; - static inline int __bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { @@ -2022,11 +2010,6 @@ static const struct bpf_func_proto bpf_l4_csum_replace_proto = { BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, __be32 *, to, u32, to_size, __wsum, seed) { - struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); - u32 diff_size = from_size + to_size; - int i, j = 0; - __wsum ret; - /* This is quite flexible, some examples: * * from_size == 0, to_size > 0, seed := csum --> pushing data @@ -2035,19 +2018,19 @@ BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, * * Even for diffing, from_size and to_size don't need to be equal. */ - if (unlikely(((from_size | to_size) & (sizeof(__be32) - 1)) || - diff_size > sizeof(sp->diff))) - return -EINVAL; - local_lock_nested_bh(&bpf_sp.bh_lock); - for (i = 0; i < from_size / sizeof(__be32); i++, j++) - sp->diff[j] = ~from[i]; - for (i = 0; i < to_size / sizeof(__be32); i++, j++) - sp->diff[j] = to[i]; + __wsum ret = seed; - ret = csum_partial(sp->diff, diff_size, seed); - local_unlock_nested_bh(&bpf_sp.bh_lock); - return ret; + if (from_size && to_size) + ret = csum_sub(csum_partial(to, to_size, ret), + csum_partial(from, from_size, 0)); + else if (to_size) + ret = csum_partial(to, to_size, ret); + + else if (from_size) + ret = ~csum_partial(from, from_size, ~ret); + + return csum_from32to16((__force unsigned int)ret); } static const struct bpf_func_proto bpf_csum_diff_proto = { @@ -6292,24 +6275,16 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, { int ret = BPF_MTU_CHK_RET_FRAG_NEEDED; struct net_device *dev = skb->dev; - int skb_len, dev_len; - int mtu = 0; - - if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) { - ret = -EINVAL; - goto out; - } + int mtu, dev_len, skb_len; - if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) { - ret = -EINVAL; - goto out; - } + if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) + return -EINVAL; + if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) + return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); - if (unlikely(!dev)) { - ret = -ENODEV; - goto out; - } + if (unlikely(!dev)) + return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; @@ -6344,19 +6319,15 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, struct net_device *dev = xdp->rxq->dev; int xdp_len = xdp->data_end - xdp->data; int ret = BPF_MTU_CHK_RET_SUCCESS; - int mtu = 0, dev_len; + int mtu, dev_len; /* XDP variant doesn't support multi-buffer segment check (yet) */ - if (unlikely(flags)) { - ret = -EINVAL; - goto out; - } + if (unlikely(flags)) + return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); - if (unlikely(!dev)) { - ret = -ENODEV; - goto out; - } + if (unlikely(!dev)) + return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; @@ -6368,7 +6339,7 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, xdp_len += len_diff; /* minus result pass check */ if (xdp_len > dev_len) ret = BPF_MTU_CHK_RET_FRAG_NEEDED; -out: + *mtu_len = mtu; return ret; } @@ -6379,7 +6350,7 @@ static const struct bpf_func_proto bpf_skb_check_mtu_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6391,7 +6362,7 @@ static const struct bpf_func_proto bpf_xdp_check_mtu_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index e0ca24a58810..8a78bff53b2c 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -88,6 +88,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, static int bpf_lwt_input_reroute(struct sk_buff *skb) { + enum skb_drop_reason reason; int err = -EINVAL; if (skb->protocol == htons(ETH_P_IP)) { @@ -96,8 +97,9 @@ static int bpf_lwt_input_reroute(struct sk_buff *skb) dev_hold(dev); skb_dst_drop(skb); - err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - ip4h_dscp(iph), dev); + reason = ip_route_input_noref(skb, iph->daddr, iph->saddr, + ip4h_dscp(iph), dev); + err = reason ? -EINVAL : 0; dev_put(dev); } else if (skb->protocol == htons(ETH_P_IPV6)) { skb_dst_drop(skb); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 4b871cecd2ce..5e572f6eaf2c 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -60,6 +60,25 @@ static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, static const struct seq_operations neigh_stat_seq_ops; #endif +static struct hlist_head *neigh_get_dev_table(struct net_device *dev, int family) +{ + int i; + + switch (family) { + default: + DEBUG_NET_WARN_ON_ONCE(1); + fallthrough; /* to avoid panic by null-ptr-deref */ + case AF_INET: + i = NEIGH_ARP_TABLE; + break; + case AF_INET6: + i = NEIGH_ND_TABLE; + break; + } + + return &dev->neighbours[i]; +} + /* Neighbour hash table buckets are protected with rwlock tbl->lock. @@ -204,18 +223,14 @@ static void neigh_update_flags(struct neighbour *neigh, u32 flags, int *notify, } } -static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np, - struct neigh_table *tbl) +bool neigh_remove_one(struct neighbour *n) { bool retval = false; write_lock(&n->lock); if (refcount_read(&n->refcnt) == 1) { - struct neighbour *neigh; - - neigh = rcu_dereference_protected(n->next, - lockdep_is_held(&tbl->lock)); - rcu_assign_pointer(*np, neigh); + hlist_del_rcu(&n->hash); + hlist_del_rcu(&n->dev_list); neigh_mark_dead(n); retval = true; } @@ -225,29 +240,6 @@ static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np, return retval; } -bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl) -{ - struct neigh_hash_table *nht; - void *pkey = ndel->primary_key; - u32 hash_val; - struct neighbour *n; - struct neighbour __rcu **np; - - nht = rcu_dereference_protected(tbl->nht, - lockdep_is_held(&tbl->lock)); - hash_val = tbl->hash(pkey, ndel->dev, nht->hash_rnd); - hash_val = hash_val >> (32 - nht->hash_shift); - - np = &nht->hash_buckets[hash_val]; - while ((n = rcu_dereference_protected(*np, - lockdep_is_held(&tbl->lock)))) { - if (n == ndel) - return neigh_del(n, np, tbl); - np = &n->next; - } - return false; -} - static int neigh_forced_gc(struct neigh_table *tbl) { int max_clean = atomic_read(&tbl->gc_entries) - @@ -275,7 +267,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) remove = true; write_unlock(&n->lock); - if (remove && neigh_remove_one(n, tbl)) + if (remove && neigh_remove_one(n)) shrunk++; if (shrunk >= max_clean) break; @@ -379,54 +371,42 @@ static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net, static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev, bool skip_perm) { - int i; - struct neigh_hash_table *nht; + struct hlist_head *dev_head; + struct hlist_node *tmp; + struct neighbour *n; - nht = rcu_dereference_protected(tbl->nht, - lockdep_is_held(&tbl->lock)); + dev_head = neigh_get_dev_table(dev, tbl->family); - for (i = 0; i < (1 << nht->hash_shift); i++) { - struct neighbour *n; - struct neighbour __rcu **np = &nht->hash_buckets[i]; + hlist_for_each_entry_safe(n, tmp, dev_head, dev_list) { + if (skip_perm && n->nud_state & NUD_PERMANENT) + continue; - while ((n = rcu_dereference_protected(*np, - lockdep_is_held(&tbl->lock))) != NULL) { - if (dev && n->dev != dev) { - np = &n->next; - continue; - } - if (skip_perm && n->nud_state & NUD_PERMANENT) { - np = &n->next; - continue; - } - rcu_assign_pointer(*np, - rcu_dereference_protected(n->next, - lockdep_is_held(&tbl->lock))); - write_lock(&n->lock); - neigh_del_timer(n); - neigh_mark_dead(n); - if (refcount_read(&n->refcnt) != 1) { - /* The most unpleasant situation. - We must destroy neighbour entry, - but someone still uses it. - - The destroy will be delayed until - the last user releases us, but - we must kill timers etc. and move - it to safe state. - */ - __skb_queue_purge(&n->arp_queue); - n->arp_queue_len_bytes = 0; - WRITE_ONCE(n->output, neigh_blackhole); - if (n->nud_state & NUD_VALID) - n->nud_state = NUD_NOARP; - else - n->nud_state = NUD_NONE; - neigh_dbg(2, "neigh %p is stray\n", n); - } - write_unlock(&n->lock); - neigh_cleanup_and_release(n); + hlist_del_rcu(&n->hash); + hlist_del_rcu(&n->dev_list); + write_lock(&n->lock); + neigh_del_timer(n); + neigh_mark_dead(n); + if (refcount_read(&n->refcnt) != 1) { + /* The most unpleasant situation. + * We must destroy neighbour entry, + * but someone still uses it. + * + * The destroy will be delayed until + * the last user releases us, but + * we must kill timers etc. and move + * it to safe state. + */ + __skb_queue_purge(&n->arp_queue); + n->arp_queue_len_bytes = 0; + WRITE_ONCE(n->output, neigh_blackhole); + if (n->nud_state & NUD_VALID) + n->nud_state = NUD_NOARP; + else + n->nud_state = NUD_NONE; + neigh_dbg(2, "neigh %p is stray\n", n); } + write_unlock(&n->lock); + neigh_cleanup_and_release(n); } } @@ -529,20 +509,21 @@ static void neigh_get_hash_rnd(u32 *x) static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) { - size_t size = (1 << shift) * sizeof(struct neighbour *); + size_t size = (1 << shift) * sizeof(struct hlist_head); + struct hlist_head *hash_heads; struct neigh_hash_table *ret; - struct neighbour __rcu **buckets; int i; ret = kmalloc(sizeof(*ret), GFP_ATOMIC); if (!ret) return NULL; - buckets = kvzalloc(size, GFP_ATOMIC); - if (!buckets) { + + hash_heads = kvzalloc(size, GFP_ATOMIC); + if (!hash_heads) { kfree(ret); return NULL; } - ret->hash_buckets = buckets; + ret->hash_heads = hash_heads; ret->hash_shift = shift; for (i = 0; i < NEIGH_NUM_HASH_RND; i++) neigh_get_hash_rnd(&ret->hash_rnd[i]); @@ -555,7 +536,7 @@ static void neigh_hash_free_rcu(struct rcu_head *head) struct neigh_hash_table, rcu); - kvfree(nht->hash_buckets); + kvfree(nht->hash_heads); kfree(nht); } @@ -574,24 +555,17 @@ static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl, return old_nht; for (i = 0; i < (1 << old_nht->hash_shift); i++) { - struct neighbour *n, *next; + struct hlist_node *tmp; + struct neighbour *n; - for (n = rcu_dereference_protected(old_nht->hash_buckets[i], - lockdep_is_held(&tbl->lock)); - n != NULL; - n = next) { + neigh_for_each_in_bucket_safe(n, tmp, &old_nht->hash_heads[i]) { hash = tbl->hash(n->primary_key, n->dev, new_nht->hash_rnd); hash >>= (32 - new_nht->hash_shift); - next = rcu_dereference_protected(n->next, - lockdep_is_held(&tbl->lock)); - rcu_assign_pointer(n->next, - rcu_dereference_protected( - new_nht->hash_buckets[hash], - lockdep_is_held(&tbl->lock))); - rcu_assign_pointer(new_nht->hash_buckets[hash], n); + hlist_del_rcu(&n->hash); + hlist_add_head_rcu(&n->hash, &new_nht->hash_heads[hash]); } } @@ -678,11 +652,7 @@ ___neigh_create(struct neigh_table *tbl, const void *pkey, goto out_tbl_unlock; } - for (n1 = rcu_dereference_protected(nht->hash_buckets[hash_val], - lockdep_is_held(&tbl->lock)); - n1 != NULL; - n1 = rcu_dereference_protected(n1->next, - lockdep_is_held(&tbl->lock))) { + neigh_for_each_in_bucket(n1, &nht->hash_heads[hash_val]) { if (dev == n1->dev && !memcmp(n1->primary_key, n->primary_key, key_len)) { if (want_ref) neigh_hold(n1); @@ -698,10 +668,11 @@ ___neigh_create(struct neigh_table *tbl, const void *pkey, list_add_tail(&n->managed_list, &n->tbl->managed_list); if (want_ref) neigh_hold(n); - rcu_assign_pointer(n->next, - rcu_dereference_protected(nht->hash_buckets[hash_val], - lockdep_is_held(&tbl->lock))); - rcu_assign_pointer(nht->hash_buckets[hash_val], n); + hlist_add_head_rcu(&n->hash, &nht->hash_heads[hash_val]); + + hlist_add_head_rcu(&n->dev_list, + neigh_get_dev_table(dev, tbl->family)); + write_unlock_bh(&tbl->lock); neigh_dbg(2, "neigh %p is created\n", n); rc = n; @@ -933,10 +904,10 @@ static void neigh_connect(struct neighbour *neigh) static void neigh_periodic_work(struct work_struct *work) { struct neigh_table *tbl = container_of(work, struct neigh_table, gc_work.work); + struct neigh_hash_table *nht; + struct hlist_node *tmp; struct neighbour *n; - struct neighbour __rcu **np; unsigned int i; - struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs); @@ -961,10 +932,7 @@ static void neigh_periodic_work(struct work_struct *work) goto out; for (i = 0 ; i < (1 << nht->hash_shift); i++) { - np = &nht->hash_buckets[i]; - - while ((n = rcu_dereference_protected(*np, - lockdep_is_held(&tbl->lock))) != NULL) { + neigh_for_each_in_bucket_safe(n, tmp, &nht->hash_heads[i]) { unsigned int state; write_lock(&n->lock); @@ -973,7 +941,7 @@ static void neigh_periodic_work(struct work_struct *work) if ((state & (NUD_PERMANENT | NUD_IN_TIMER)) || (n->flags & NTF_EXT_LEARNED)) { write_unlock(&n->lock); - goto next_elt; + continue; } if (time_before(n->used, n->confirmed) && @@ -984,18 +952,14 @@ static void neigh_periodic_work(struct work_struct *work) (state == NUD_FAILED || !time_in_range_open(jiffies, n->used, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { - rcu_assign_pointer(*np, - rcu_dereference_protected(n->next, - lockdep_is_held(&tbl->lock))); + hlist_del_rcu(&n->hash); + hlist_del_rcu(&n->dev_list); neigh_mark_dead(n); write_unlock(&n->lock); neigh_cleanup_and_release(n); continue; } write_unlock(&n->lock); - -next_elt: - np = &n->next; } /* * It's fine to release lock here, even if hash table @@ -1942,7 +1906,7 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, NETLINK_CB(skb).portid, extack); write_lock_bh(&tbl->lock); neigh_release(neigh); - neigh_remove_one(neigh, tbl); + neigh_remove_one(neigh); write_unlock_bh(&tbl->lock); out: @@ -2713,9 +2677,8 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, for (h = s_h; h < (1 << nht->hash_shift); h++) { if (h > s_h) s_idx = 0; - for (n = rcu_dereference(nht->hash_buckets[h]), idx = 0; - n != NULL; - n = rcu_dereference(n->next)) { + idx = 0; + neigh_for_each_in_bucket_rcu(n, &nht->hash_heads[h]) { if (idx < s_idx || !net_eq(dev_net(n->dev), net)) goto next; if (neigh_ifindex_filtered(n->dev, filter->dev_idx) || @@ -3082,9 +3045,7 @@ void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; - for (n = rcu_dereference(nht->hash_buckets[chain]); - n != NULL; - n = rcu_dereference(n->next)) + neigh_for_each_in_bucket(n, &nht->hash_heads[chain]) cb(n, cookie); } read_unlock_bh(&tbl->lock); @@ -3096,29 +3057,25 @@ EXPORT_SYMBOL(neigh_for_each); void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)) { - int chain; struct neigh_hash_table *nht; + int chain; nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); for (chain = 0; chain < (1 << nht->hash_shift); chain++) { + struct hlist_node *tmp; struct neighbour *n; - struct neighbour __rcu **np; - np = &nht->hash_buckets[chain]; - while ((n = rcu_dereference_protected(*np, - lockdep_is_held(&tbl->lock))) != NULL) { + neigh_for_each_in_bucket_safe(n, tmp, &nht->hash_heads[chain]) { int release; write_lock(&n->lock); release = cb(n); if (release) { - rcu_assign_pointer(*np, - rcu_dereference_protected(n->next, - lockdep_is_held(&tbl->lock))); + hlist_del_rcu(&n->hash); + hlist_del_rcu(&n->dev_list); neigh_mark_dead(n); - } else - np = &n->next; + } write_unlock(&n->lock); if (release) neigh_cleanup_and_release(n); @@ -3175,43 +3132,53 @@ EXPORT_SYMBOL(neigh_xmit); #ifdef CONFIG_PROC_FS -static struct neighbour *neigh_get_first(struct seq_file *seq) +static struct neighbour *neigh_get_valid(struct seq_file *seq, + struct neighbour *n, + loff_t *pos) { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); + + if (!net_eq(dev_net(n->dev), net)) + return NULL; + + if (state->neigh_sub_iter) { + loff_t fakep = 0; + void *v; + + v = state->neigh_sub_iter(state, n, pos ? pos : &fakep); + if (!v) + return NULL; + if (pos) + return v; + } + + if (!(state->flags & NEIGH_SEQ_SKIP_NOARP)) + return n; + + if (READ_ONCE(n->nud_state) & ~NUD_NOARP) + return n; + + return NULL; +} + +static struct neighbour *neigh_get_first(struct seq_file *seq) +{ + struct neigh_seq_state *state = seq->private; struct neigh_hash_table *nht = state->nht; - struct neighbour *n = NULL; - int bucket; + struct neighbour *n, *tmp; state->flags &= ~NEIGH_SEQ_IS_PNEIGH; - for (bucket = 0; bucket < (1 << nht->hash_shift); bucket++) { - n = rcu_dereference(nht->hash_buckets[bucket]); - - while (n) { - if (!net_eq(dev_net(n->dev), net)) - goto next; - if (state->neigh_sub_iter) { - loff_t fakep = 0; - void *v; - v = state->neigh_sub_iter(state, n, &fakep); - if (!v) - goto next; - } - if (!(state->flags & NEIGH_SEQ_SKIP_NOARP)) - break; - if (READ_ONCE(n->nud_state) & ~NUD_NOARP) - break; -next: - n = rcu_dereference(n->next); + while (++state->bucket < (1 << nht->hash_shift)) { + neigh_for_each_in_bucket(n, &nht->hash_heads[state->bucket]) { + tmp = neigh_get_valid(seq, n, NULL); + if (tmp) + return tmp; } - - if (n) - break; } - state->bucket = bucket; - return n; + return NULL; } static struct neighbour *neigh_get_next(struct seq_file *seq, @@ -3219,46 +3186,28 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, loff_t *pos) { struct neigh_seq_state *state = seq->private; - struct net *net = seq_file_net(seq); - struct neigh_hash_table *nht = state->nht; + struct neighbour *tmp; if (state->neigh_sub_iter) { void *v = state->neigh_sub_iter(state, n, pos); + if (v) return n; } - n = rcu_dereference(n->next); - while (1) { - while (n) { - if (!net_eq(dev_net(n->dev), net)) - goto next; - if (state->neigh_sub_iter) { - void *v = state->neigh_sub_iter(state, n, pos); - if (v) - return n; - goto next; - } - if (!(state->flags & NEIGH_SEQ_SKIP_NOARP)) - break; - - if (READ_ONCE(n->nud_state) & ~NUD_NOARP) - break; -next: - n = rcu_dereference(n->next); + hlist_for_each_entry_continue(n, hash) { + tmp = neigh_get_valid(seq, n, pos); + if (tmp) { + n = tmp; + goto out; } - - if (n) - break; - - if (++state->bucket >= (1 << nht->hash_shift)) - break; - - n = rcu_dereference(nht->hash_buckets[state->bucket]); } + n = neigh_get_first(seq); +out: if (n && pos) --(*pos); + return n; } @@ -3361,7 +3310,7 @@ void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl struct neigh_seq_state *state = seq->private; state->tbl = tbl; - state->bucket = 0; + state->bucket = -1; state->flags = (neigh_seq_flags & ~NEIGH_SEQ_IS_PNEIGH); rcu_read_lock(); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 809b48c0a528..157021ced442 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -56,7 +56,6 @@ static bool init_net_initialized; * outside. */ DECLARE_RWSEM(pernet_ops_rwsem); -EXPORT_SYMBOL_GPL(pernet_ops_rwsem); #define MIN_PERNET_OPS_ID \ ((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *)) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 21de7e10be16..a89cbd8d87c3 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -92,10 +92,11 @@ static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1] }; /* NETDEV_CMD_NAPI_SET - do */ -static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT + 1] = { +static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT + 1] = { [NETDEV_A_NAPI_ID] = { .type = NLA_U32, }, [NETDEV_A_NAPI_DEFER_HARD_IRQS] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_napi_defer_hard_irqs_range), [NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT] = { .type = NLA_UINT, }, + [NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, }, }; /* Ops table for netdev */ @@ -186,7 +187,7 @@ static const struct genl_split_ops netdev_nl_ops[] = { .cmd = NETDEV_CMD_NAPI_SET, .doit = netdev_nl_napi_set_doit, .policy = netdev_napi_set_nl_policy, - .maxattr = NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, + .maxattr = NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, }; diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index b49c3b4e5fbe..765ce7c9d73b 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -161,6 +161,7 @@ static int netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, const struct genl_info *info) { + unsigned long irq_suspend_timeout; unsigned long gro_flush_timeout; u32 napi_defer_hard_irqs; void *hdr; @@ -196,6 +197,11 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, napi_defer_hard_irqs)) goto nla_put_failure; + irq_suspend_timeout = napi_get_irq_suspend_timeout(napi); + if (nla_put_uint(rsp, NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, + irq_suspend_timeout)) + goto nla_put_failure; + gro_flush_timeout = napi_get_gro_flush_timeout(napi); if (nla_put_uint(rsp, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, gro_flush_timeout)) @@ -306,6 +312,7 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) static int netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info) { + u64 irq_suspend_timeout = 0; u64 gro_flush_timeout = 0; u32 defer = 0; @@ -314,6 +321,11 @@ netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info) napi_set_defer_hard_irqs(napi, defer); } + if (info->attrs[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT]) { + irq_suspend_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT]); + napi_set_irq_suspend_timeout(napi, irq_suspend_timeout); + } + if (info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]) { gro_flush_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]); napi_set_gro_flush_timeout(napi, gro_flush_timeout); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index a813d30d2135..f89cf93f6eb4 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -950,6 +950,7 @@ netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool, if (netmem && *offset + size > max_size) { netmem = page_pool_drain_frag(pool, netmem); if (netmem) { + recycle_stat_inc(pool, cached); alloc_stat_inc(pool, fast); goto frag_reset; } @@ -974,7 +975,6 @@ frag_reset: pool->frag_users++; pool->frag_offset = *offset + size; - alloc_stat_inc(pool, fast); return netmem; } EXPORT_SYMBOL(page_pool_alloc_frag_netmem); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b70f90b98714..327fa4957929 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -258,8 +258,87 @@ bool lockdep_rtnl_net_is_held(struct net *net) return lockdep_rtnl_is_held() && lockdep_is_held(&net->rtnl_mutex); } EXPORT_SYMBOL(lockdep_rtnl_net_is_held); +#else +static int rtnl_net_cmp_locks(const struct net *net_a, const struct net *net_b) +{ + /* No need to swap */ + return -1; +} #endif +struct rtnl_nets { + /* ->newlink() needs to freeze 3 netns at most; + * 2 for the new device, 1 for its peer. + */ + struct net *net[3]; + unsigned char len; +}; + +static void rtnl_nets_init(struct rtnl_nets *rtnl_nets) +{ + memset(rtnl_nets, 0, sizeof(*rtnl_nets)); +} + +static void rtnl_nets_destroy(struct rtnl_nets *rtnl_nets) +{ + int i; + + for (i = 0; i < rtnl_nets->len; i++) { + put_net(rtnl_nets->net[i]); + rtnl_nets->net[i] = NULL; + } + + rtnl_nets->len = 0; +} + +/** + * rtnl_nets_add - Add netns to be locked before ->newlink(). + * + * @rtnl_nets: rtnl_nets pointer passed to ->get_peer_net(). + * @net: netns pointer with an extra refcnt held. + * + * The extra refcnt is released in rtnl_nets_destroy(). + */ +static void rtnl_nets_add(struct rtnl_nets *rtnl_nets, struct net *net) +{ + int i; + + DEBUG_NET_WARN_ON_ONCE(rtnl_nets->len == ARRAY_SIZE(rtnl_nets->net)); + + for (i = 0; i < rtnl_nets->len; i++) { + switch (rtnl_net_cmp_locks(rtnl_nets->net[i], net)) { + case 0: + put_net(net); + return; + case 1: + swap(rtnl_nets->net[i], net); + } + } + + rtnl_nets->net[i] = net; + rtnl_nets->len++; +} + +static void rtnl_nets_lock(struct rtnl_nets *rtnl_nets) +{ + int i; + + rtnl_lock(); + + for (i = 0; i < rtnl_nets->len; i++) + __rtnl_net_lock(rtnl_nets->net[i]); +} + +static void rtnl_nets_unlock(struct rtnl_nets *rtnl_nets) +{ + int i; + + for (i = 0; i < rtnl_nets->len; i++) + __rtnl_net_unlock(rtnl_nets->net[i]); + + rtnl_unlock(); +} + static struct rtnl_link __rcu *__rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1]; static inline int rtm_msgindex(int msgtype) @@ -466,6 +545,7 @@ void __rtnl_unregister_many(const struct rtnl_msg_handler *handlers, int n) } EXPORT_SYMBOL_GPL(__rtnl_unregister_many); +static DEFINE_MUTEX(link_ops_mutex); static LIST_HEAD(link_ops); static struct rtnl_link_ops *rtnl_link_ops_get(const char *kind, int *srcu_index) @@ -494,27 +574,20 @@ static void rtnl_link_ops_put(struct rtnl_link_ops *ops, int srcu_index) } /** - * __rtnl_link_register - Register rtnl_link_ops with rtnetlink. + * rtnl_link_register - Register rtnl_link_ops with rtnetlink. * @ops: struct rtnl_link_ops * to register * - * The caller must hold the rtnl_mutex. This function should be used - * by drivers that create devices during module initialization. It - * must be called before registering the devices. - * * Returns 0 on success or a negative error code. */ -int __rtnl_link_register(struct rtnl_link_ops *ops) +int rtnl_link_register(struct rtnl_link_ops *ops) { struct rtnl_link_ops *tmp; int err; - /* When RTNL is removed, add lock for link_ops. */ - ASSERT_RTNL(); - - list_for_each_entry(tmp, &link_ops, list) { - if (!strcmp(ops->kind, tmp->kind)) - return -EEXIST; - } + /* Sanity-check max sizes to avoid stack buffer overflow. */ + if (WARN_ON(ops->maxtype > RTNL_MAX_TYPE || + ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE)) + return -EINVAL; /* The check for alloc/setup is here because if ops * does not have that filled up, it is not possible @@ -528,30 +601,19 @@ int __rtnl_link_register(struct rtnl_link_ops *ops) if (err) return err; - list_add_tail_rcu(&ops->list, &link_ops); - - return 0; -} -EXPORT_SYMBOL_GPL(__rtnl_link_register); + mutex_lock(&link_ops_mutex); -/** - * rtnl_link_register - Register rtnl_link_ops with rtnetlink. - * @ops: struct rtnl_link_ops * to register - * - * Returns 0 on success or a negative error code. - */ -int rtnl_link_register(struct rtnl_link_ops *ops) -{ - int err; + list_for_each_entry(tmp, &link_ops, list) { + if (!strcmp(ops->kind, tmp->kind)) { + err = -EEXIST; + goto unlock; + } + } - /* Sanity-check max sizes to avoid stack buffer overflow. */ - if (WARN_ON(ops->maxtype > RTNL_MAX_TYPE || - ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE)) - return -EINVAL; + list_add_tail_rcu(&ops->list, &link_ops); +unlock: + mutex_unlock(&link_ops_mutex); - rtnl_lock(); - err = __rtnl_link_register(ops); - rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(rtnl_link_register); @@ -568,27 +630,6 @@ static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) unregister_netdevice_many(&list_kill); } -/** - * __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. - * @ops: struct rtnl_link_ops * to unregister - * - * The caller must hold the rtnl_mutex and guarantee net_namespace_list - * integrity (hold pernet_ops_rwsem for writing to close the race - * with setup_net() and cleanup_net()). - */ -void __rtnl_link_unregister(struct rtnl_link_ops *ops) -{ - struct net *net; - - list_del_rcu(&ops->list); - synchronize_srcu(&ops->srcu); - cleanup_srcu_struct(&ops->srcu); - - for_each_net(net) - __rtnl_kill_links(net, ops); -} -EXPORT_SYMBOL_GPL(__rtnl_link_unregister); - /* Return with the rtnl_lock held when there are no network * devices unregistering in any network namespace. */ @@ -617,10 +658,22 @@ static void rtnl_lock_unregistering_all(void) */ void rtnl_link_unregister(struct rtnl_link_ops *ops) { + struct net *net; + + mutex_lock(&link_ops_mutex); + list_del_rcu(&ops->list); + mutex_unlock(&link_ops_mutex); + + synchronize_srcu(&ops->srcu); + cleanup_srcu_struct(&ops->srcu); + /* Close the race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); rtnl_lock_unregistering_all(); - __rtnl_link_unregister(ops); + + for_each_net(net) + __rtnl_kill_links(net, ops); + rtnl_unlock(); up_write(&pernet_ops_rwsem); } @@ -2140,7 +2193,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 }, [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 }, [IFLA_GSO_MAX_SEGS] = { .type = NLA_U32 }, - [IFLA_GSO_MAX_SIZE] = { .type = NLA_U32 }, + [IFLA_GSO_MAX_SIZE] = NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1), [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN }, [IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */ [IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN }, @@ -2165,7 +2218,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_TSO_MAX_SIZE] = { .type = NLA_REJECT }, [IFLA_TSO_MAX_SEGS] = { .type = NLA_REJECT }, [IFLA_ALLMULTI] = { .type = NLA_REJECT }, - [IFLA_GSO_IPV4_MAX_SIZE] = { .type = NLA_U32 }, + [IFLA_GSO_IPV4_MAX_SIZE] = NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1), [IFLA_GRO_IPV4_MAX_SIZE] = { .type = NLA_U32 }, }; @@ -2459,9 +2512,10 @@ int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, } EXPORT_SYMBOL(rtnl_nla_parse_ifinfomsg); -struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) +static struct net *rtnl_link_get_net_ifla(struct nlattr *tb[]) { - struct net *net; + struct net *net = NULL; + /* Examine the link attributes and figure out which * network namespace we are talking about. */ @@ -2469,8 +2523,17 @@ struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID])); else if (tb[IFLA_NET_NS_FD]) net = get_net_ns_by_fd(nla_get_u32(tb[IFLA_NET_NS_FD])); - else + + return net; +} + +struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) +{ + struct net *net = rtnl_link_get_net_ifla(tb); + + if (!net) net = get_net(src_net); + return net; } EXPORT_SYMBOL(rtnl_link_get_net); @@ -2940,10 +3003,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev, const char *pat = ifname[0] ? ifname : NULL; int new_ifindex; - if (tb[IFLA_NEW_IFINDEX]) - new_ifindex = nla_get_s32(tb[IFLA_NEW_IFINDEX]); - else - new_ifindex = 0; + new_ifindex = nla_get_s32_default(tb[IFLA_NEW_IFINDEX], 0); err = __dev_change_net_namespace(dev, tgt_net, pat, new_ifindex); if (err) @@ -3319,6 +3379,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct nlattr *tb[IFLA_MAX+1]; struct net_device *dev = NULL; + struct rtnl_nets rtnl_nets; struct net *tgt_net; int err; @@ -3337,6 +3398,12 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } + rtnl_nets_init(&rtnl_nets); + rtnl_nets_add(&rtnl_nets, get_net(net)); + rtnl_nets_add(&rtnl_nets, tgt_net); + + rtnl_nets_lock(&rtnl_nets); + if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) @@ -3349,7 +3416,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, else if (!err) err = -ENODEV; - put_net(tgt_net); + rtnl_nets_unlock(&rtnl_nets); errout: return err; } @@ -3434,6 +3501,8 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, return PTR_ERR(tgt_net); } + rtnl_net_lock(tgt_net); + if (ifm->ifi_index > 0) dev = __dev_get_by_index(tgt_net, ifm->ifi_index); else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) @@ -3448,6 +3517,8 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, else err = -EINVAL; + rtnl_net_unlock(tgt_net); + if (netnsid >= 0) put_net(tgt_net); @@ -3735,6 +3806,37 @@ out_unregister: goto out; } +static int rtnl_add_peer_net(struct rtnl_nets *rtnl_nets, + const struct rtnl_link_ops *ops, + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_MAX + 1]; + struct net *net; + int err; + + if (!data || !data[ops->peer_type]) + return 0; + + err = rtnl_nla_parse_ifinfomsg(tb, data[ops->peer_type], extack); + if (err < 0) + return err; + + if (ops->validate) { + err = ops->validate(tb, NULL, extack); + if (err < 0) + return err; + } + + net = rtnl_link_get_net_ifla(tb); + if (IS_ERR(net)) + return PTR_ERR(net); + if (net) + rtnl_nets_add(rtnl_nets, net); + + return 0; +} + static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, const struct rtnl_link_ops *ops, struct net *tgt_net, struct net *link_net, @@ -3796,6 +3898,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *tgt_net, *link_net = NULL; struct rtnl_link_ops *ops = NULL; struct rtnl_newlink_tbs *tbs; + struct rtnl_nets rtnl_nets; int ops_srcu_index; int ret; @@ -3831,17 +3934,19 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, ops = rtnl_link_ops_get(kind, &ops_srcu_index); #ifdef CONFIG_MODULES if (!ops) { - __rtnl_unlock(); request_module("rtnl-link-%s", kind); - rtnl_lock(); ops = rtnl_link_ops_get(kind, &ops_srcu_index); } #endif } + rtnl_nets_init(&rtnl_nets); + if (ops) { - if (ops->maxtype > RTNL_MAX_TYPE) - return -EINVAL; + if (ops->maxtype > RTNL_MAX_TYPE) { + ret = -EINVAL; + goto put_ops; + } if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) { ret = nla_parse_nested_deprecated(tbs->attr, ops->maxtype, @@ -3858,14 +3963,22 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (ret < 0) goto put_ops; } + + if (ops->peer_type) { + ret = rtnl_add_peer_net(&rtnl_nets, ops, data, extack); + if (ret < 0) + goto put_ops; + } } tgt_net = rtnl_link_get_net_capable(skb, sock_net(skb->sk), tb, CAP_NET_ADMIN); if (IS_ERR(tgt_net)) { ret = PTR_ERR(tgt_net); - goto put_ops; + goto put_net; } + rtnl_nets_add(&rtnl_nets, tgt_net); + if (tb[IFLA_LINK_NETNSID]) { int id = nla_get_s32(tb[IFLA_LINK_NETNSID]); @@ -3876,18 +3989,20 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, goto put_net; } + rtnl_nets_add(&rtnl_nets, link_net); + if (!netlink_ns_capable(skb, link_net->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; goto put_net; } } + rtnl_nets_lock(&rtnl_nets); ret = __rtnl_newlink(skb, nlh, ops, tgt_net, link_net, tbs, data, extack); + rtnl_nets_unlock(&rtnl_nets); put_net: - if (link_net) - put_net(link_net); - put_net(tgt_net); + rtnl_nets_destroy(&rtnl_nets); put_ops: if (ops) rtnl_link_ops_put(ops, ops_srcu_index); @@ -6888,11 +7003,14 @@ static struct pernet_operations rtnetlink_net_ops = { }; static const struct rtnl_msg_handler rtnetlink_rtnl_msg_handlers[] __initconst = { - {.msgtype = RTM_NEWLINK, .doit = rtnl_newlink}, - {.msgtype = RTM_DELLINK, .doit = rtnl_dellink}, + {.msgtype = RTM_NEWLINK, .doit = rtnl_newlink, + .flags = RTNL_FLAG_DOIT_PERNET}, + {.msgtype = RTM_DELLINK, .doit = rtnl_dellink, + .flags = RTNL_FLAG_DOIT_PERNET_WIP}, {.msgtype = RTM_GETLINK, .doit = rtnl_getlink, .dumpit = rtnl_dump_ifinfo, .flags = RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, - {.msgtype = RTM_SETLINK, .doit = rtnl_setlink}, + {.msgtype = RTM_SETLINK, .doit = rtnl_setlink, + .flags = RTNL_FLAG_DOIT_PERNET_WIP}, {.msgtype = RTM_GETADDR, .dumpit = rtnl_dump_all}, {.msgtype = RTM_GETROUTE, .dumpit = rtnl_dump_all}, {.msgtype = RTM_GETNETCONF, .dumpit = rtnl_dump_all}, diff --git a/net/core/skb_fault_injection.c b/net/core/skb_fault_injection.c new file mode 100644 index 000000000000..4235db6bdfad --- /dev/null +++ b/net/core/skb_fault_injection.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/debugfs.h> +#include <linux/fault-inject.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> + +static struct { + struct fault_attr attr; + char devname[IFNAMSIZ]; + bool filtered; +} skb_realloc = { + .attr = FAULT_ATTR_INITIALIZER, + .filtered = false, +}; + +static bool should_fail_net_realloc_skb(struct sk_buff *skb) +{ + struct net_device *net = skb->dev; + + if (skb_realloc.filtered && + strncmp(net->name, skb_realloc.devname, IFNAMSIZ)) + /* device name filter set, but names do not match */ + return false; + + if (!should_fail(&skb_realloc.attr, 1)) + return false; + + return true; +} +ALLOW_ERROR_INJECTION(should_fail_net_realloc_skb, TRUE); + +void skb_might_realloc(struct sk_buff *skb) +{ + if (!should_fail_net_realloc_skb(skb)) + return; + + pskb_expand_head(skb, 0, 0, GFP_ATOMIC); +} +EXPORT_SYMBOL(skb_might_realloc); + +static int __init fail_skb_realloc_setup(char *str) +{ + return setup_fault_attr(&skb_realloc.attr, str); +} +__setup("fail_skb_realloc=", fail_skb_realloc_setup); + +static void reset_settings(void) +{ + skb_realloc.filtered = false; + memset(&skb_realloc.devname, 0, IFNAMSIZ); +} + +static ssize_t devname_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + ssize_t ret; + + reset_settings(); + ret = simple_write_to_buffer(&skb_realloc.devname, IFNAMSIZ, + ppos, buffer, count); + if (ret < 0) + return ret; + + skb_realloc.devname[IFNAMSIZ - 1] = '\0'; + /* Remove a possible \n at the end of devname */ + strim(skb_realloc.devname); + + if (strnlen(skb_realloc.devname, IFNAMSIZ)) + skb_realloc.filtered = true; + + return count; +} + +static ssize_t devname_read(struct file *file, + char __user *buffer, + size_t size, loff_t *ppos) +{ + if (!skb_realloc.filtered) + return 0; + + return simple_read_from_buffer(buffer, size, ppos, &skb_realloc.devname, + strlen(skb_realloc.devname)); +} + +static const struct file_operations devname_ops = { + .write = devname_write, + .read = devname_read, +}; + +static int __init fail_skb_realloc_debugfs(void) +{ + umode_t mode = S_IFREG | 0600; + struct dentry *dir; + + dir = fault_create_debugfs_attr("fail_skb_realloc", NULL, + &skb_realloc.attr); + if (IS_ERR(dir)) + return PTR_ERR(dir); + + debugfs_create_file("devname", mode, dir, NULL, &devname_ops); + + return 0; +} + +late_initcall(fail_skb_realloc_debugfs); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 00afeb90c23a..6841e61a6bd0 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -753,14 +753,14 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); data = page_frag_alloc(nc, len, gfp_mask); - pfmemalloc = nc->pfmemalloc; + pfmemalloc = page_frag_cache_is_pfmemalloc(nc); } else { local_bh_disable(); local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache.page); data = page_frag_alloc(nc, len, gfp_mask); - pfmemalloc = nc->pfmemalloc; + pfmemalloc = page_frag_cache_is_pfmemalloc(nc); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); local_bh_enable(); @@ -850,7 +850,7 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) len = SKB_HEAD_ALIGN(len); data = page_frag_alloc(&nc->page, len, gfp_mask); - pfmemalloc = nc->page.pfmemalloc; + pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); } local_unlock_nested_bh(&napi_alloc_cache.bh_lock); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 07d6aa4e39ef..78347d7d25ef 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1760,6 +1760,10 @@ static int sock_map_link_update_prog(struct bpf_link *link, ret = -EINVAL; goto out; } + if (!sockmap_link->map) { + ret = -ENOLINK; + goto out; + } ret = sock_map_prog_link_lookup(sockmap_link->map, &pprog, &plink, sockmap_link->attach_type); diff --git a/net/devlink/dev.c b/net/devlink/dev.c index 9264bbc90d0c..d6e3db300acb 100644 --- a/net/devlink/dev.c +++ b/net/devlink/dev.c @@ -531,10 +531,8 @@ int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info) return err; } - if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) - action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); - else - action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT; + action = nla_get_u8_default(info->attrs[DEVLINK_ATTR_RELOAD_ACTION], + DEVLINK_RELOAD_ACTION_DRIVER_REINIT); if (!devlink_reload_action_is_supported(devlink, action)) { NL_SET_ERR_MSG(info->extack, "Requested reload action is not supported by the driver"); diff --git a/net/dsa/user.c b/net/dsa/user.c index 91a1fa5f8ab0..06c30a9e29ff 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -1042,15 +1042,12 @@ static void dsa_user_get_strings(struct net_device *dev, struct dsa_switch *ds = dp->ds; if (stringset == ETH_SS_STATS) { - int len = ETH_GSTRING_LEN; - - strscpy_pad(data, "tx_packets", len); - strscpy_pad(data + len, "tx_bytes", len); - strscpy_pad(data + 2 * len, "rx_packets", len); - strscpy_pad(data + 3 * len, "rx_bytes", len); + ethtool_puts(&data, "tx_packets"); + ethtool_puts(&data, "tx_bytes"); + ethtool_puts(&data, "rx_packets"); + ethtool_puts(&data, "rx_bytes"); if (ds->ops->get_strings) - ds->ops->get_strings(ds, dp->index, stringset, - data + 4 * len); + ds->ops->get_strings(ds, dp->index, stringset, data); } else if (stringset == ETH_SS_TEST) { net_selftest_get_strings(data); } @@ -1364,7 +1361,7 @@ dsa_user_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) static int dsa_user_add_cls_matchall_mirred(struct net_device *dev, struct tc_cls_matchall_offload *cls, - bool ingress) + bool ingress, bool ingress_target) { struct netlink_ext_ack *extack = cls->common.extack; struct dsa_port *dp = dsa_user_to_port(dev); @@ -1376,11 +1373,19 @@ dsa_user_add_cls_matchall_mirred(struct net_device *dev, struct dsa_port *to_dp; int err; - if (!ds->ops->port_mirror_add) + if (cls->common.protocol != htons(ETH_P_ALL)) { + NL_SET_ERR_MSG_MOD(extack, + "Can only offload \"protocol all\" matchall filter"); + return -EOPNOTSUPP; + } + + if (!ds->ops->port_mirror_add) { + NL_SET_ERR_MSG_MOD(extack, + "Switch does not support mirroring operation"); return -EOPNOTSUPP; + } - if (!flow_action_basic_hw_stats_check(&cls->rule->action, - cls->common.extack)) + if (!flow_action_basic_hw_stats_check(&cls->rule->action, extack)) return -EOPNOTSUPP; act = &cls->rule->action.entries[0]; @@ -1388,10 +1393,30 @@ dsa_user_add_cls_matchall_mirred(struct net_device *dev, if (!act->dev) return -EINVAL; - if (!dsa_user_dev_check(act->dev)) - return -EOPNOTSUPP; - - to_dp = dsa_user_to_port(act->dev); + if (dsa_user_dev_check(act->dev)) { + if (ingress_target) { + /* We can only fulfill this using software assist */ + if (cls->common.skip_sw) { + NL_SET_ERR_MSG_MOD(extack, + "Can only mirred to ingress of DSA user port if filter also runs in software"); + return -EOPNOTSUPP; + } + to_dp = dp->cpu_dp; + } else { + to_dp = dsa_user_to_port(act->dev); + } + } else { + /* Handle mirroring to foreign target ports as a mirror towards + * the CPU. The software tc rule will take the packets from + * there. + */ + if (cls->common.skip_sw) { + NL_SET_ERR_MSG_MOD(extack, + "Can only mirred to CPU if filter also runs in software"); + return -EOPNOTSUPP; + } + to_dp = dp->cpu_dp; + } if (dp->ds != to_dp->ds) { NL_SET_ERR_MSG_MOD(extack, @@ -1446,8 +1471,7 @@ dsa_user_add_cls_matchall_police(struct net_device *dev, return -EOPNOTSUPP; } - if (!flow_action_basic_hw_stats_check(&cls->rule->action, - cls->common.extack)) + if (!flow_action_basic_hw_stats_check(&cls->rule->action, extack)) return -EOPNOTSUPP; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) { @@ -1485,17 +1509,30 @@ static int dsa_user_add_cls_matchall(struct net_device *dev, struct tc_cls_matchall_offload *cls, bool ingress) { - int err = -EOPNOTSUPP; + const struct flow_action *action = &cls->rule->action; + struct netlink_ext_ack *extack = cls->common.extack; - if (cls->common.protocol == htons(ETH_P_ALL) && - flow_offload_has_one_action(&cls->rule->action) && - cls->rule->action.entries[0].id == FLOW_ACTION_MIRRED) - err = dsa_user_add_cls_matchall_mirred(dev, cls, ingress); - else if (flow_offload_has_one_action(&cls->rule->action) && - cls->rule->action.entries[0].id == FLOW_ACTION_POLICE) - err = dsa_user_add_cls_matchall_police(dev, cls, ingress); + if (!flow_offload_has_one_action(action)) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload matchall filter with more than one action"); + return -EOPNOTSUPP; + } - return err; + switch (action->entries[0].id) { + case FLOW_ACTION_MIRRED: + return dsa_user_add_cls_matchall_mirred(dev, cls, ingress, + false); + case FLOW_ACTION_MIRRED_INGRESS: + return dsa_user_add_cls_matchall_mirred(dev, cls, ingress, + true); + case FLOW_ACTION_POLICE: + return dsa_user_add_cls_matchall_police(dev, cls, ingress); + default: + NL_SET_ERR_MSG_MOD(extack, "Unknown action"); + break; + } + + return -EOPNOTSUPP; } static void dsa_user_del_cls_matchall(struct net_device *dev, diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 5cc131cdb1bc..7da94e26ced6 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -425,7 +425,7 @@ convert_link_ksettings_to_legacy_settings( /* layout of the struct passed from/to userland */ struct ethtool_link_usettings { - struct ethtool_link_settings base; + struct ethtool_link_settings_hdr base; struct { __u32 supported[__ETHTOOL_LINK_MODE_MASK_NU32]; __u32 advertising[__ETHTOOL_LINK_MODE_MASK_NU32]; diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c index 30b8ce275159..2d5bc57160be 100644 --- a/net/ethtool/linkinfo.c +++ b/net/ethtool/linkinfo.c @@ -8,9 +8,9 @@ struct linkinfo_req_info { }; struct linkinfo_reply_data { - struct ethnl_reply_data base; - struct ethtool_link_ksettings ksettings; - struct ethtool_link_settings *lsettings; + struct ethnl_reply_data base; + struct ethtool_link_ksettings ksettings; + struct ethtool_link_settings_hdr *lsettings; }; #define LINKINFO_REPDATA(__reply_base) \ @@ -98,7 +98,7 @@ static int ethnl_set_linkinfo(struct ethnl_req_info *req_info, struct genl_info *info) { struct ethtool_link_ksettings ksettings = {}; - struct ethtool_link_settings *lsettings; + struct ethtool_link_settings_hdr *lsettings; struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; bool mod = false; diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index 259cd9ef1f2a..17e49cf89f03 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -11,10 +11,10 @@ struct linkmodes_req_info { }; struct linkmodes_reply_data { - struct ethnl_reply_data base; - struct ethtool_link_ksettings ksettings; - struct ethtool_link_settings *lsettings; - bool peer_empty; + struct ethnl_reply_data base; + struct ethtool_link_ksettings ksettings; + struct ethtool_link_settings_hdr *lsettings; + bool peer_empty; }; #define LINKMODES_REPDATA(__reply_base) \ @@ -62,10 +62,12 @@ static int linkmodes_reply_size(const struct ethnl_req_info *req_base, { const struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); const struct ethtool_link_ksettings *ksettings = &data->ksettings; - const struct ethtool_link_settings *lsettings = &ksettings->base; bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const struct ethtool_link_settings_hdr *lsettings; int len, ret; + lsettings = &ksettings->base; + len = nla_total_size(sizeof(u8)) /* LINKMODES_AUTONEG */ + nla_total_size(sizeof(u32)) /* LINKMODES_SPEED */ + nla_total_size(sizeof(u32)) /* LINKMODES_LANES */ @@ -103,10 +105,12 @@ static int linkmodes_fill_reply(struct sk_buff *skb, { const struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); const struct ethtool_link_ksettings *ksettings = &data->ksettings; - const struct ethtool_link_settings *lsettings = &ksettings->base; bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const struct ethtool_link_settings_hdr *lsettings; int ret; + lsettings = &ksettings->base; + if (nla_put_u8(skb, ETHTOOL_A_LINKMODES_AUTONEG, lsettings->autoneg)) return -EMSGSIZE; @@ -237,7 +241,7 @@ static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, struct ethtool_link_ksettings *ksettings, bool *mod, const struct net_device *dev) { - struct ethtool_link_settings *lsettings = &ksettings->base; + struct ethtool_link_settings_hdr *lsettings = &ksettings->base; bool req_speed, req_lanes, req_duplex; const struct nlattr *master_slave_cfg, *lanes_cfg; int ret; diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index ebdfd5b64e17..9e64496a5c1c 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -515,6 +515,77 @@ static void hsr_change_rx_flags(struct net_device *dev, int change) } } +static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, + __be16 proto, u16 vid) +{ + bool is_slave_a_added = false; + bool is_slave_b_added = false; + struct hsr_port *port; + struct hsr_priv *hsr; + int ret = 0; + + hsr = netdev_priv(dev); + + hsr_for_each_port(hsr, port) { + if (port->type == HSR_PT_MASTER || + port->type == HSR_PT_INTERLINK) + continue; + + ret = vlan_vid_add(port->dev, proto, vid); + switch (port->type) { + case HSR_PT_SLAVE_A: + if (ret) { + /* clean up Slave-B */ + netdev_err(dev, "add vid failed for Slave-A\n"); + if (is_slave_b_added) + vlan_vid_del(port->dev, proto, vid); + return ret; + } + + is_slave_a_added = true; + break; + + case HSR_PT_SLAVE_B: + if (ret) { + /* clean up Slave-A */ + netdev_err(dev, "add vid failed for Slave-B\n"); + if (is_slave_a_added) + vlan_vid_del(port->dev, proto, vid); + return ret; + } + + is_slave_b_added = true; + break; + default: + break; + } + } + + return 0; +} + +static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, + __be16 proto, u16 vid) +{ + struct hsr_port *port; + struct hsr_priv *hsr; + + hsr = netdev_priv(dev); + + hsr_for_each_port(hsr, port) { + switch (port->type) { + case HSR_PT_SLAVE_A: + case HSR_PT_SLAVE_B: + vlan_vid_del(port->dev, proto, vid); + break; + default: + break; + } + } + + return 0; +} + static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, @@ -523,6 +594,8 @@ static const struct net_device_ops hsr_device_ops = { .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, .ndo_set_rx_mode = hsr_set_rx_mode, + .ndo_vlan_rx_add_vid = hsr_ndo_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = hsr_ndo_vlan_rx_kill_vid, }; static const struct device_type hsr_type = { @@ -569,14 +642,10 @@ void hsr_dev_setup(struct net_device *dev) dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | - NETIF_F_HW_VLAN_CTAG_TX; + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_FILTER; dev->features = dev->hw_features; - - /* VLAN on top of HSR needs testing and probably some work on - * hsr_header_create() etc. - */ - dev->features |= NETIF_F_VLAN_CHALLENGED; } /* Return true if dev is a HSR master; return false otherwise. @@ -652,6 +721,10 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true; + if ((slave[0]->features & NETIF_F_HW_VLAN_CTAG_FILTER) && + (slave[1]->features & NETIF_F_HW_VLAN_CTAG_FILTER)) + hsr_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + res = register_netdevice(hsr_dev); if (res) goto err_unregister; diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index b38060246e62..aa6acebc7c1e 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -280,6 +280,7 @@ static struct sk_buff *hsr_fill_tag(struct sk_buff *skb, struct hsr_port *port, u8 proto_version) { struct hsr_ethhdr *hsr_ethhdr; + unsigned char *pc; int lsdu_size; /* pad to minimum packet size which is 60 + 6 (HSR tag) */ @@ -290,7 +291,18 @@ static struct sk_buff *hsr_fill_tag(struct sk_buff *skb, if (frame->is_vlan) lsdu_size -= 4; - hsr_ethhdr = (struct hsr_ethhdr *)skb_mac_header(skb); + pc = skb_mac_header(skb); + if (frame->is_vlan) + /* This 4-byte shift (size of a vlan tag) does not + * mean that the ethhdr starts there. But rather it + * provides the proper environment for accessing + * the fields, such as hsr_tag etc., just like + * when the vlan tag is not there. This is because + * the hsr tag is after the vlan tag. + */ + hsr_ethhdr = (struct hsr_ethhdr *)(pc + VLAN_HLEN); + else + hsr_ethhdr = (struct hsr_ethhdr *)pc; hsr_set_path_id(hsr_ethhdr, port); set_hsr_tag_LSDU_size(&hsr_ethhdr->hsr_tag, lsdu_size); @@ -368,7 +380,7 @@ struct sk_buff *prp_create_tagged_frame(struct hsr_frame_info *frame, return skb_clone(frame->skb_std, GFP_ATOMIC); } - skb = skb_copy_expand(frame->skb_std, 0, + skb = skb_copy_expand(frame->skb_std, skb_headroom(frame->skb_std), skb_tailroom(frame->skb_std) + HSR_HLEN, GFP_ATOMIC); return prp_fill_rct(skb, frame, port); @@ -690,9 +702,6 @@ static int fill_frame_info(struct hsr_frame_info *frame, if (frame->is_vlan) { vlan_hdr = (struct hsr_vlan_ethhdr *)ethhdr; proto = vlan_hdr->vlanhdr.h_vlan_encapsulated_proto; - /* FIXME: */ - netdev_warn_once(skb->dev, "VLAN not yet supported"); - return -EINVAL; } frame->is_from_san = false; diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 6f09b9512484..b68f2f71d0e1 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -82,10 +82,7 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, return -EINVAL; } - if (!data[IFLA_HSR_MULTICAST_SPEC]) - multicast_spec = 0; - else - multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]); + multicast_spec = nla_get_u8_default(data[IFLA_HSR_MULTICAST_SPEC], 0); if (data[IFLA_HSR_PROTOCOL]) proto = nla_get_u8(data[IFLA_HSR_PROTOCOL]); diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index 29bf97640166..74ef0a310afb 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -202,10 +202,7 @@ int ieee802154_associate_req(struct sk_buff *skb, struct genl_info *info) addr.pan_id = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); - if (info->attrs[IEEE802154_ATTR_PAGE]) - page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); - else - page = 0; + page = nla_get_u8_default(info->attrs[IEEE802154_ATTR_PAGE], 0); ret = ieee802154_mlme_ops(dev)->assoc_req(dev, &addr, nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]), @@ -338,10 +335,7 @@ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info) blx = nla_get_u8(info->attrs[IEEE802154_ATTR_BAT_EXT]); coord_realign = nla_get_u8(info->attrs[IEEE802154_ATTR_COORD_REALIGN]); - if (info->attrs[IEEE802154_ATTR_PAGE]) - page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); - else - page = 0; + page = nla_get_u8_default(info->attrs[IEEE802154_ATTR_PAGE], 0); if (addr.short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) { ieee802154_nl_start_confirm(dev, IEEE802154_NO_SHORT_ADDRESS); @@ -388,10 +382,7 @@ int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info) channels = nla_get_u32(info->attrs[IEEE802154_ATTR_CHANNELS]); duration = nla_get_u8(info->attrs[IEEE802154_ATTR_DURATION]); - if (info->attrs[IEEE802154_ATTR_PAGE]) - page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); - else - page = 0; + page = nla_get_u8_default(info->attrs[IEEE802154_ATTR_PAGE], 0); ret = ieee802154_mlme_ops(dev)->scan_req(dev, type, channels, page, duration); diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 7eb37de3add2..5a024ca60d35 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -1438,22 +1438,18 @@ static int nl802154_trigger_scan(struct sk_buff *skb, struct genl_info *info) } /* Use current page by default */ - if (info->attrs[NL802154_ATTR_PAGE]) - request->page = nla_get_u8(info->attrs[NL802154_ATTR_PAGE]); - else - request->page = wpan_phy->current_page; + request->page = nla_get_u8_default(info->attrs[NL802154_ATTR_PAGE], + wpan_phy->current_page); /* Scan all supported channels by default */ - if (info->attrs[NL802154_ATTR_SCAN_CHANNELS]) - request->channels = nla_get_u32(info->attrs[NL802154_ATTR_SCAN_CHANNELS]); - else - request->channels = wpan_phy->supported.channels[request->page]; + request->channels = + nla_get_u32_default(info->attrs[NL802154_ATTR_SCAN_CHANNELS], + wpan_phy->supported.channels[request->page]); /* Use maximum duration order by default */ - if (info->attrs[NL802154_ATTR_SCAN_DURATION]) - request->duration = nla_get_u8(info->attrs[NL802154_ATTR_SCAN_DURATION]); - else - request->duration = IEEE802154_MAX_SCAN_DURATION; + request->duration = + nla_get_u8_default(info->attrs[NL802154_ATTR_SCAN_DURATION], + IEEE802154_MAX_SCAN_DURATION); err = rdev_trigger_scan(rdev, request); if (err) { @@ -1598,10 +1594,8 @@ nl802154_send_beacons(struct sk_buff *skb, struct genl_info *info) request->wpan_phy = wpan_phy; /* Use maximum duration order by default */ - if (info->attrs[NL802154_ATTR_BEACON_INTERVAL]) - request->interval = nla_get_u8(info->attrs[NL802154_ATTR_BEACON_INTERVAL]); - else - request->interval = IEEE802154_MAX_SCAN_DURATION; + request->interval = nla_get_u8_default(info->attrs[NL802154_ATTR_BEACON_INTERVAL], + IEEE802154_MAX_SCAN_DURATION); err = rdev_send_beacons(rdev, request); if (err) { diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 11c1519b3699..cb9a7ed8abd3 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1215,7 +1215,7 @@ int arp_invalidate(struct net_device *dev, __be32 ip, bool force) NEIGH_UPDATE_F_ADMIN, 0); write_lock_bh(&tbl->lock); neigh_release(neigh); - neigh_remove_one(neigh, tbl); + neigh_remove_one(neigh); write_unlock_bh(&tbl->lock); } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index f58f39a9ee87..c8b3cf5fba4c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -926,8 +926,7 @@ static struct in_ifaddr *inet_rtm_to_ifa(struct net *net, struct nlmsghdr *nlh, ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); - ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : - ifm->ifa_flags; + ifa->ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags); ifa->ifa_scope = ifm->ifa_scope; ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]); ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 0c9ce934b490..87bb36a5bdec 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -346,6 +346,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, int rpf, struct in_device *idev, u32 *itag) { struct net *net = dev_net(dev); + enum skb_drop_reason reason; struct flow_keys flkeys; int ret, no_addr; struct fib_result res; @@ -377,9 +378,15 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; - if (res.type != RTN_UNICAST && - (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev))) - goto e_inval; + if (res.type != RTN_UNICAST) { + if (res.type != RTN_LOCAL) { + reason = SKB_DROP_REASON_IP_INVALID_SOURCE; + goto e_inval; + } else if (!IN_DEV_ACCEPT_LOCAL(idev)) { + reason = SKB_DROP_REASON_IP_LOCAL_SOURCE; + goto e_inval; + } + } fib_combine_itag(itag, &res); dev_match = fib_info_nh_uses_dev(res.fi, dev); @@ -412,9 +419,9 @@ last_resort: return 0; e_inval: - return -EINVAL; + return -reason; e_rpf: - return -EXDEV; + return -SKB_DROP_REASON_IP_RPFILTER; } /* Ignore rp_filter for packets protected by IPsec. */ diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 33eec844a5a0..4f088fa1c2f2 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -545,7 +545,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, orefdst = skb_in->_skb_refdst; /* save old refdst */ skb_dst_set(skb_in, NULL); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, - dscp, rt2->dst.dev); + dscp, rt2->dst.dev) ? -EINVAL : 0; dst_release(&rt2->dst); rt2 = skb_rtable(skb_in); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 48e2810f1f27..07036a2943c1 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -132,12 +132,12 @@ static bool frag_expire_skip_icmp(u32 user) */ static void ip_expire(struct timer_list *t) { + enum skb_drop_reason reason = SKB_DROP_REASON_FRAG_REASM_TIMEOUT; struct inet_frag_queue *frag = from_timer(frag, t, timer); const struct iphdr *iph; struct sk_buff *head = NULL; struct net *net; struct ipq *qp; - int err; qp = container_of(frag, struct ipq, q); net = qp->q.fqdir->net; @@ -175,14 +175,15 @@ static void ip_expire(struct timer_list *t) /* skb has no dst, perform route lookup again */ iph = ip_hdr(head); - err = ip_route_input_noref(head, iph->daddr, iph->saddr, ip4h_dscp(iph), - head->dev); - if (err) + reason = ip_route_input_noref(head, iph->daddr, iph->saddr, + ip4h_dscp(iph), head->dev); + if (reason) goto out; /* Only an end host needs to send an ICMP * "Fragment Reassembly Timeout" message, per RFC792. */ + reason = SKB_DROP_REASON_FRAG_REASM_TIMEOUT; if (frag_expire_skip_icmp(qp->q.key.v4.user) && (skb_rtable(head)->rt_type != RTN_LOCAL)) goto out; @@ -195,7 +196,7 @@ out: spin_unlock(&qp->q.lock); out_rcu_unlock: rcu_read_unlock(); - kfree_skb_reason(head, SKB_DROP_REASON_FRAG_REASM_TIMEOUT); + kfree_skb_reason(head, reason); ipq_put(qp); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 89bb63da6852..f0a4dda246ab 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -322,15 +322,14 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, int err, drop_reason; struct rtable *rt; - drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; - if (ip_can_use_hint(skb, iph, hint)) { - err = ip_route_use_hint(skb, iph->daddr, iph->saddr, - ip4h_dscp(iph), dev, hint); - if (unlikely(err)) + drop_reason = ip_route_use_hint(skb, iph->daddr, iph->saddr, + ip4h_dscp(iph), dev, hint); + if (unlikely(drop_reason)) goto drop_error; } + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && !skb_dst(skb) && !skb->sk && @@ -362,10 +361,11 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, * how the packet travels inside Linux networking. */ if (!skb_valid_dst(skb)) { - err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - ip4h_dscp(iph), dev); - if (unlikely(err)) + drop_reason = ip_route_input_noref(skb, iph->daddr, iph->saddr, + ip4h_dscp(iph), dev); + if (unlikely(drop_reason)) goto drop_error; + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; } else { struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -425,10 +425,8 @@ drop: return NET_RX_DROP; drop_error: - if (err == -EXDEV) { - drop_reason = SKB_DROP_REASON_IP_RPFILTER; + if (drop_reason == SKB_DROP_REASON_IP_RPFILTER) __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); - } goto drop; } diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 81e86e5defee..e3321932bec0 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -618,7 +618,7 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev) orefdst = skb->_skb_refdst; skb_dst_set(skb, NULL); err = ip_route_input(skb, nexthop, iph->saddr, ip4h_dscp(iph), - dev); + dev) ? -EINVAL : 0; rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { skb_dst_drop(skb); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index d591c73e2c0e..25505f9b724c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -218,7 +218,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, ip_tunnel_flags_copy(flags, parms->i_flags); - hlist_for_each_entry_rcu(t, head, hash_node) { + hlist_for_each_entry_rcu(t, head, hash_node, lockdep_rtnl_is_held()) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && link == READ_ONCE(t->parms.link) && diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 99e7cd0531d9..c58dd78509a2 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2546,9 +2546,9 @@ static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (err < 0) goto errout; - src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; - grp = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0; - tableid = tb[RTA_TABLE] ? nla_get_u32(tb[RTA_TABLE]) : 0; + src = nla_get_in_addr_default(tb[RTA_SRC], 0); + grp = nla_get_in_addr_default(tb[RTA_DST], 0); + tableid = nla_get_u32_default(tb[RTA_TABLE], 0); mrt = ipmr_get_table(net, tableid ? tableid : RT_TABLE_DEFAULT); if (!mrt) { diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 1b991b889506..ef8009281da5 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -12,7 +12,13 @@ config NF_DEFRAG_IPV4 # old sockopt interface and eval loop config IP_NF_IPTABLES_LEGACY - tristate + tristate "Legacy IP tables support" + default n + select NETFILTER_XTABLES + help + iptables is a legacy packet classifier. + This is not needed if you are using iptables over nftables + (iptables-nft). config NF_SOCKET_IPV4 tristate "IPv4 socket lookup support" @@ -318,7 +324,13 @@ endif # IP_NF_IPTABLES # ARP tables config IP_NF_ARPTABLES - tristate + tristate "Legacy ARPTABLES support" + depends on NETFILTER_XTABLES + default n + help + arptables is a legacy packet classifier. + This is not needed if you are using arptables over nftables + (iptables-nft). config NFT_COMPAT_ARP tristate diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 570e450e008c..09a3d73b45ba 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3247,12 +3247,8 @@ static int nh_valid_get_del_req(const struct nlmsghdr *nlh, return -EINVAL; } - if (op_flags) { - if (tb[NHA_OP_FLAGS]) - *op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); - else - *op_flags = 0; - } + if (op_flags) + *op_flags = nla_get_u32_default(tb[NHA_OP_FLAGS], 0); return 0; } @@ -3433,10 +3429,7 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, if (err < 0) return err; - if (tb[NHA_OP_FLAGS]) - filter->op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); - else - filter->op_flags = 0; + filter->op_flags = nla_get_u32_default(tb[NHA_OP_FLAGS], 0); return __nh_valid_dump_req(nlh, tb, filter, cb->extack); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 763398e08b7d..e5603e84b20d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1027,6 +1027,19 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); +#ifdef CONFIG_IP_ROUTE_MULTIPATH + if (fib_info_num_path(res.fi) > 1) { + int nhsel; + + for (nhsel = 0; nhsel < fib_info_num_path(res.fi); nhsel++) { + nhc = fib_info_nhc(res.fi, nhsel); + update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, + jiffies + net->ipv4.ip_rt_mtu_expires); + } + rcu_read_unlock(); + return; + } +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); @@ -1665,50 +1678,54 @@ struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt) EXPORT_SYMBOL(rt_dst_clone); /* called in rcu_read_lock() section */ -int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, - dscp_t dscp, struct net_device *dev, - struct in_device *in_dev, u32 *itag) +enum skb_drop_reason +ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev, + struct in_device *in_dev, u32 *itag) { - int err; + enum skb_drop_reason reason; /* Primary sanity checks. */ if (!in_dev) - return -EINVAL; + return SKB_DROP_REASON_NOT_SPECIFIED; - if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || - skb->protocol != htons(ETH_P_IP)) - return -EINVAL; + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) + return SKB_DROP_REASON_IP_INVALID_SOURCE; + + if (skb->protocol != htons(ETH_P_IP)) + return SKB_DROP_REASON_INVALID_PROTO; if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) - return -EINVAL; + return SKB_DROP_REASON_IP_LOCALNET; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr) && ip_hdr(skb)->protocol != IPPROTO_IGMP) - return -EINVAL; + return SKB_DROP_REASON_IP_INVALID_SOURCE; } else { - err = fib_validate_source(skb, saddr, 0, dscp, 0, dev, in_dev, - itag); - if (err < 0) - return err; + reason = fib_validate_source_reason(skb, saddr, 0, dscp, 0, + dev, in_dev, itag); + if (reason) + return reason; } - return 0; + return SKB_NOT_DROPPED_YET; } /* called in rcu_read_lock() section */ -static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, - dscp_t dscp, struct net_device *dev, int our) +static enum skb_drop_reason +ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev, int our) { struct in_device *in_dev = __in_dev_get_rcu(dev); unsigned int flags = RTCF_MULTICAST; + enum skb_drop_reason reason; struct rtable *rth; u32 itag = 0; - int err; - err = ip_mc_validate_source(skb, daddr, saddr, dscp, dev, in_dev, - &itag); - if (err) - return err; + reason = ip_mc_validate_source(skb, daddr, saddr, dscp, dev, in_dev, + &itag); + if (reason) + return reason; if (our) flags |= RTCF_LOCAL; @@ -1719,7 +1736,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, false); if (!rth) - return -ENOBUFS; + return SKB_DROP_REASON_NOMEM; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; @@ -1735,7 +1752,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, skb_dst_drop(skb); skb_dst_set(skb, &rth->dst); - return 0; + return SKB_NOT_DROPPED_YET; } @@ -1765,10 +1782,12 @@ static void ip_handle_martian_source(struct net_device *dev, } /* called in rcu_read_lock() section */ -static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, - struct in_device *in_dev, __be32 daddr, - __be32 saddr, dscp_t dscp) +static enum skb_drop_reason +__mkroute_input(struct sk_buff *skb, const struct fib_result *res, + struct in_device *in_dev, __be32 daddr, + __be32 saddr, dscp_t dscp) { + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct fib_nh_common *nhc = FIB_RES_NHC(*res); struct net_device *dev = nhc->nhc_dev; struct fib_nh_exception *fnhe; @@ -1782,12 +1801,13 @@ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, out_dev = __in_dev_get_rcu(dev); if (!out_dev) { net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n"); - return -EINVAL; + return reason; } err = fib_validate_source(skb, saddr, daddr, dscp, FIB_RES_OIF(*res), in_dev->dev, in_dev, &itag); if (err < 0) { + reason = -err; ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); @@ -1815,7 +1835,7 @@ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, */ if (out_dev == in_dev && IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) { - err = -EINVAL; + reason = SKB_DROP_REASON_ARP_PVLAN_DISABLE; goto cleanup; } } @@ -1838,7 +1858,7 @@ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, rth = rt_dst_alloc(out_dev->dev, 0, res->type, IN_DEV_ORCONF(out_dev, NOXFRM)); if (!rth) { - err = -ENOBUFS; + reason = SKB_DROP_REASON_NOMEM; goto cleanup; } @@ -1852,9 +1872,9 @@ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, lwtunnel_set_redirect(&rth->dst); skb_dst_set(skb, &rth->dst); out: - err = 0; - cleanup: - return err; + reason = SKB_NOT_DROPPED_YET; +cleanup: + return reason; } #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -2112,9 +2132,10 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, } #endif /* CONFIG_IP_ROUTE_MULTIPATH */ -static int ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, - struct in_device *in_dev, __be32 daddr, - __be32 saddr, dscp_t dscp, struct flow_keys *hkeys) +static enum skb_drop_reason +ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, + struct in_device *in_dev, __be32 daddr, + __be32 saddr, dscp_t dscp, struct flow_keys *hkeys) { #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && fib_info_num_path(res->fi) > 1) { @@ -2133,43 +2154,50 @@ static int ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, * assuming daddr is valid and the destination is not a local broadcast one. * Uses the provided hint instead of performing a route lookup. */ -int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, - dscp_t dscp, struct net_device *dev, - const struct sk_buff *hint) +enum skb_drop_reason +ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev, + const struct sk_buff *hint) { + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct in_device *in_dev = __in_dev_get_rcu(dev); struct rtable *rt = skb_rtable(hint); struct net *net = dev_net(dev); - int err = -EINVAL; u32 tag = 0; if (!in_dev) - return -EINVAL; + return reason; - if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) { + reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; + } - if (ipv4_is_zeronet(saddr)) + if (ipv4_is_zeronet(saddr)) { + reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; + } - if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) + if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) { + reason = SKB_DROP_REASON_IP_LOCALNET; goto martian_source; + } if (rt->rt_type != RTN_LOCAL) goto skip_validate_source; - err = fib_validate_source(skb, saddr, daddr, dscp, 0, dev, in_dev, - &tag); - if (err < 0) + reason = fib_validate_source_reason(skb, saddr, daddr, dscp, 0, dev, + in_dev, &tag); + if (reason) goto martian_source; skip_validate_source: skb_dst_copy(skb, hint); - return 0; + return SKB_NOT_DROPPED_YET; martian_source: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); - return err; + return reason; } /* get device for dst_alloc with local routes */ @@ -2198,10 +2226,12 @@ static struct net_device *ip_rt_get_dev(struct net *net, * called with rcu_read_lock() */ -static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, - dscp_t dscp, struct net_device *dev, - struct fib_result *res) +static enum skb_drop_reason +ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev, + struct fib_result *res) { + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct in_device *in_dev = __in_dev_get_rcu(dev); struct flow_keys *flkeys = NULL, _flkeys; struct net *net = dev_net(dev); @@ -2229,8 +2259,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.flowi4_tun_key.tun_id = 0; skb_dst_drop(skb); - if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) { + reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; + } res->fi = NULL; res->table = NULL; @@ -2240,21 +2272,29 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, /* Accept zero addresses only to limited broadcast; * I even do not know to fix it or not. Waiting for complains :-) */ - if (ipv4_is_zeronet(saddr)) + if (ipv4_is_zeronet(saddr)) { + reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto martian_source; + } - if (ipv4_is_zeronet(daddr)) + if (ipv4_is_zeronet(daddr)) { + reason = SKB_DROP_REASON_IP_INVALID_DEST; goto martian_destination; + } /* Following code try to avoid calling IN_DEV_NET_ROUTE_LOCALNET(), * and call it once if daddr or/and saddr are loopback addresses */ if (ipv4_is_loopback(daddr)) { - if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) + if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) { + reason = SKB_DROP_REASON_IP_LOCALNET; goto martian_destination; + } } else if (ipv4_is_loopback(saddr)) { - if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) + if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) { + reason = SKB_DROP_REASON_IP_LOCALNET; goto martian_source; + } } /* @@ -2296,10 +2336,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto brd_input; } + err = -EINVAL; if (res->type == RTN_LOCAL) { - err = fib_validate_source(skb, saddr, daddr, dscp, 0, dev, - in_dev, &itag); - if (err < 0) + reason = fib_validate_source_reason(skb, saddr, daddr, dscp, + 0, dev, in_dev, &itag); + if (reason) goto martian_source; goto local_input; } @@ -2308,21 +2349,28 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, err = -EHOSTUNREACH; goto no_route; } - if (res->type != RTN_UNICAST) + if (res->type != RTN_UNICAST) { + reason = SKB_DROP_REASON_IP_INVALID_DEST; goto martian_destination; + } make_route: - err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, dscp, flkeys); -out: return err; + reason = ip_mkroute_input(skb, res, in_dev, daddr, saddr, dscp, + flkeys); + +out: + return reason; brd_input: - if (skb->protocol != htons(ETH_P_IP)) - goto e_inval; + if (skb->protocol != htons(ETH_P_IP)) { + reason = SKB_DROP_REASON_INVALID_PROTO; + goto out; + } if (!ipv4_is_zeronet(saddr)) { - err = fib_validate_source(skb, saddr, 0, dscp, 0, dev, in_dev, - &itag); - if (err < 0) + reason = fib_validate_source_reason(skb, saddr, 0, dscp, 0, + dev, in_dev, &itag); + if (reason) goto martian_source; } flags |= RTCF_BROADCAST; @@ -2340,7 +2388,7 @@ local_input: rth = rcu_dereference(nhc->nhc_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); - err = 0; + reason = SKB_NOT_DROPPED_YET; goto out; } } @@ -2377,7 +2425,7 @@ local_input: rt_add_uncached_list(rth); } skb_dst_set(skb, &rth->dst); - err = 0; + reason = SKB_NOT_DROPPED_YET; goto out; no_route: @@ -2398,12 +2446,8 @@ martian_destination: &daddr, &saddr, dev->name); #endif -e_inval: - err = -EINVAL; - goto out; - e_nobufs: - err = -ENOBUFS; + reason = SKB_DROP_REASON_NOMEM; goto out; martian_source: @@ -2412,9 +2456,10 @@ martian_source: } /* called with rcu_read_lock held */ -static int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, - dscp_t dscp, struct net_device *dev, - struct fib_result *res) +static enum skb_drop_reason +ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, + dscp_t dscp, struct net_device *dev, + struct fib_result *res) { /* Multicast recognition logic is moved from route cache to here. * The problem was that too many Ethernet cards have broken/missing @@ -2428,12 +2473,12 @@ static int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, * route cache entry is created eventually. */ if (ipv4_is_multicast(daddr)) { + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct in_device *in_dev = __in_dev_get_rcu(dev); int our = 0; - int err = -EINVAL; if (!in_dev) - return err; + return -EINVAL; our = ip_check_mc_rcu(in_dev, daddr, saddr, ip_hdr(skb)->protocol); @@ -2454,26 +2499,27 @@ static int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, IN_DEV_MFORWARD(in_dev)) #endif ) { - err = ip_route_input_mc(skb, daddr, saddr, dscp, dev, - our); + reason = ip_route_input_mc(skb, daddr, saddr, dscp, + dev, our); } - return err; + return reason; } return ip_route_input_slow(skb, daddr, saddr, dscp, dev, res); } -int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, - dscp_t dscp, struct net_device *dev) +enum skb_drop_reason ip_route_input_noref(struct sk_buff *skb, __be32 daddr, + __be32 saddr, dscp_t dscp, + struct net_device *dev) { + enum skb_drop_reason reason; struct fib_result res; - int err; rcu_read_lock(); - err = ip_route_input_rcu(skb, daddr, saddr, dscp, dev, &res); + reason = ip_route_input_rcu(skb, daddr, saddr, dscp, dev, &res); rcu_read_unlock(); - return err; + return reason; } EXPORT_SYMBOL(ip_route_input_noref); @@ -3231,10 +3277,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, return err; rtm = nlmsg_data(nlh); - src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; - dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0; - iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; - mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0; + src = nla_get_in_addr_default(tb[RTA_SRC], 0); + dst = nla_get_in_addr_default(tb[RTA_DST], 0); + iif = nla_get_u32_default(tb[RTA_IIF], 0); + mark = nla_get_u32_default(tb[RTA_MARK], 0); if (tb[RTA_UID]) uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else @@ -3260,7 +3306,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.daddr = dst; fl4.saddr = src; fl4.flowi4_tos = rtm->rtm_tos & INET_DSCP_MASK; - fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; + fl4.flowi4_oif = nla_get_u32_default(tb[RTA_OIF], 0); fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; if (sport) @@ -3285,7 +3331,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, skb->mark = mark; err = ip_route_input_rcu(skb, dst, src, inet_dsfield_to_dscp(rtm->rtm_tos), - dev, &res); + dev, &res) ? -EINVAL : 0; rt = skb_rtable(skb); if (err == 0 && rt->dst.error) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 82cc4a5633ce..0d704bda6c41 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3336,7 +3336,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; - if (icsk->icsk_ca_ops->release) + if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); icsk->icsk_ca_initialized = 0; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index db6516092daf..bbb8d5f0eae7 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -109,12 +109,13 @@ bool tcp_ao_ignore_icmp(const struct sock *sk, int family, int type, int code) * it's known that the keys in ao_info are matching peer's * family/address/VRF/etc. */ -struct tcp_ao_key *tcp_ao_established_key(struct tcp_ao_info *ao, +struct tcp_ao_key *tcp_ao_established_key(const struct sock *sk, + struct tcp_ao_info *ao, int sndid, int rcvid) { struct tcp_ao_key *key; - hlist_for_each_entry_rcu(key, &ao->head, node) { + hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) { if ((sndid >= 0 && key->sndid != sndid) || (rcvid >= 0 && key->rcvid != rcvid)) continue; @@ -205,7 +206,7 @@ static struct tcp_ao_key *__tcp_ao_do_lookup(const struct sock *sk, int l3index, if (!ao) return NULL; - hlist_for_each_entry_rcu(key, &ao->head, node) { + hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) { u8 prefixlen = min(prefix, key->prefixlen); if (!tcp_ao_key_cmp(key, l3index, addr, prefixlen, @@ -793,7 +794,7 @@ int tcp_ao_prepare_reset(const struct sock *sk, struct sk_buff *skb, if (!ao_info) return -ENOENT; - *key = tcp_ao_established_key(ao_info, aoh->rnext_keyid, -1); + *key = tcp_ao_established_key(sk, ao_info, aoh->rnext_keyid, -1); if (!*key) return -ENOENT; *traffic_key = snd_other_key(*key); @@ -979,7 +980,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, */ key = READ_ONCE(info->rnext_key); if (key->rcvid != aoh->keyid) { - key = tcp_ao_established_key(info, -1, aoh->keyid); + key = tcp_ao_established_key(sk, info, -1, aoh->keyid); if (!key) goto key_not_found; } @@ -1003,7 +1004,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, aoh->rnext_keyid, tcp_ao_hdr_maclen(aoh)); /* If the key is not found we do nothing. */ - key = tcp_ao_established_key(info, aoh->rnext_keyid, -1); + key = tcp_ao_established_key(sk, info, aoh->rnext_keyid, -1); if (key) /* pairs with tcp_ao_del_cmd */ WRITE_ONCE(info->current_key, key); @@ -1163,7 +1164,7 @@ void tcp_ao_established(struct sock *sk) if (!ao) return; - hlist_for_each_entry_rcu(key, &ao->head, node) + hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) tcp_ao_cache_traffic_keys(sk, ao, key); } @@ -1180,7 +1181,7 @@ void tcp_ao_finish_connect(struct sock *sk, struct sk_buff *skb) WRITE_ONCE(ao->risn, tcp_hdr(skb)->seq); ao->rcv_sne = 0; - hlist_for_each_entry_rcu(key, &ao->head, node) + hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) tcp_ao_cache_traffic_keys(sk, ao, key); } @@ -1256,14 +1257,14 @@ int tcp_ao_copy_all_matching(const struct sock *sk, struct sock *newsk, key_head = rcu_dereference(hlist_first_rcu(&new_ao->head)); first_key = hlist_entry_safe(key_head, struct tcp_ao_key, node); - key = tcp_ao_established_key(new_ao, tcp_rsk(req)->ao_keyid, -1); + key = tcp_ao_established_key(req_to_sk(req), new_ao, tcp_rsk(req)->ao_keyid, -1); if (key) new_ao->current_key = key; else new_ao->current_key = first_key; /* set rnext_key */ - key = tcp_ao_established_key(new_ao, -1, tcp_rsk(req)->ao_rcv_next); + key = tcp_ao_established_key(req_to_sk(req), new_ao, -1, tcp_rsk(req)->ao_rcv_next); if (key) new_ao->rnext_key = key; else @@ -1857,12 +1858,12 @@ static int tcp_ao_del_cmd(struct sock *sk, unsigned short int family, * if there's any. */ if (cmd.set_current) { - new_current = tcp_ao_established_key(ao_info, cmd.current_key, -1); + new_current = tcp_ao_established_key(sk, ao_info, cmd.current_key, -1); if (!new_current) return -ENOENT; } if (cmd.set_rnext) { - new_rnext = tcp_ao_established_key(ao_info, -1, cmd.rnext); + new_rnext = tcp_ao_established_key(sk, ao_info, -1, cmd.rnext); if (!new_rnext) return -ENOENT; } @@ -1902,7 +1903,8 @@ static int tcp_ao_del_cmd(struct sock *sk, unsigned short int family, * "It is presumed that an MKT affecting a particular * connection cannot be destroyed during an active connection" */ - hlist_for_each_entry_rcu(key, &ao_info->head, node) { + hlist_for_each_entry_rcu(key, &ao_info->head, node, + lockdep_sock_is_held(sk)) { if (cmd.sndid != key->sndid || cmd.rcvid != key->rcvid) continue; @@ -2000,14 +2002,14 @@ static int tcp_ao_info_cmd(struct sock *sk, unsigned short int family, * if there's any. */ if (cmd.set_current) { - new_current = tcp_ao_established_key(ao_info, cmd.current_key, -1); + new_current = tcp_ao_established_key(sk, ao_info, cmd.current_key, -1); if (!new_current) { err = -ENOENT; goto out; } } if (cmd.set_rnext) { - new_rnext = tcp_ao_established_key(ao_info, -1, cmd.rnext); + new_rnext = tcp_ao_established_key(sk, ao_info, -1, cmd.rnext); if (!new_rnext) { err = -ENOENT; goto out; @@ -2101,7 +2103,8 @@ int tcp_v4_parse_ao(struct sock *sk, int cmd, sockptr_t optval, int optlen) * The layout of the fields in the user and kernel structures is expected to * be the same (including in the 32bit vs 64bit case). */ -static int tcp_ao_copy_mkts_to_user(struct tcp_ao_info *ao_info, +static int tcp_ao_copy_mkts_to_user(const struct sock *sk, + struct tcp_ao_info *ao_info, sockptr_t optval, sockptr_t optlen) { struct tcp_ao_getsockopt opt_in, opt_out; @@ -2229,7 +2232,8 @@ static int tcp_ao_copy_mkts_to_user(struct tcp_ao_info *ao_info, /* May change in RX, while we're dumping, pre-fetch it */ current_key = READ_ONCE(ao_info->current_key); - hlist_for_each_entry_rcu(key, &ao_info->head, node) { + hlist_for_each_entry_rcu(key, &ao_info->head, node, + lockdep_sock_is_held(sk)) { if (opt_in.get_all) goto match; @@ -2309,7 +2313,7 @@ int tcp_ao_get_mkts(struct sock *sk, sockptr_t optval, sockptr_t optlen) if (!ao_info) return -ENOENT; - return tcp_ao_copy_mkts_to_user(ao_info, optval, optlen); + return tcp_ao_copy_mkts_to_user(sk, ao_info, optval, optlen); } int tcp_ao_get_sock_info(struct sock *sk, sockptr_t optval, sockptr_t optlen) @@ -2396,7 +2400,7 @@ int tcp_ao_set_repair(struct sock *sk, sockptr_t optval, unsigned int optlen) WRITE_ONCE(ao->snd_sne, cmd.snd_sne); WRITE_ONCE(ao->rcv_sne, cmd.rcv_sne); - hlist_for_each_entry_rcu(key, &ao->head, node) + hlist_for_each_entry_rcu(key, &ao->head, node, lockdep_sock_is_held(sk)) tcp_ao_cache_traffic_keys(sk, ao, key); return 0; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index e7658c5d6b79..370993c03d31 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -221,11 +221,11 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, int flags, int *addr_len) { - struct tcp_sock *tcp = tcp_sk(sk); int peek = flags & MSG_PEEK; - u32 seq = tcp->copied_seq; struct sk_psock *psock; + struct tcp_sock *tcp; int copied = 0; + u32 seq; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); @@ -238,7 +238,8 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, return tcp_recvmsg(sk, msg, len, flags, addr_len); lock_sock(sk); - + tcp = tcp_sk(sk); + seq = tcp->copied_seq; /* We may have received data on the sk_receive_queue pre-accept and * then we can not use read_skb in this context because we haven't * assigned a sk_socket yet so have no link to the ops. The work-around diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 0306d257fa64..df758adbb445 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -270,8 +270,9 @@ void tcp_cleanup_congestion_control(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - if (icsk->icsk_ca_ops->release) + if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); + icsk->icsk_ca_initialized = 0; bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2d844e1f867f..5bdf13ac26ef 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4921,8 +4921,8 @@ static bool tcp_ooo_try_coalesce(struct sock *sk, return res; } -static void tcp_drop_reason(struct sock *sk, struct sk_buff *skb, - enum skb_drop_reason reason) +noinline_for_tracing static void +tcp_drop_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { sk_drops_add(sk, skb); sk_skb_reason_drop(sk, skb, reason); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9d3dd101ea71..a38c8b1f44db 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1053,7 +1053,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) } if (aoh) - key.ao_key = tcp_ao_established_key(ao_info, aoh->rnext_keyid, -1); + key.ao_key = tcp_ao_established_key(sk, ao_info, + aoh->rnext_keyid, -1); } } if (key.ao_key) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 054244ce5117..5485a70b5fe5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2954,9 +2954,7 @@ void tcp_send_loss_probe(struct sock *sk) } skb = skb_rb_last(&sk->tcp_rtx_queue); if (unlikely(!skb)) { - WARN_ONCE(tp->packets_out, - "invalid inflight: %u state %u cwnd %u mss %d\n", - tp->packets_out, sk->sk_state, tcp_snd_cwnd(tp), mss); + tcp_warn_once(sk, tp->packets_out, "invalid inflight: "); smp_store_release(&inet_csk(sk)->icsk_pending, 0); return; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d0a99710d65d..96b5b2b0d507 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4793,7 +4793,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, if (!pfx) return -EINVAL; - ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; + ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags); /* We ignore other flags so far. */ ifa_flags &= IFA_F_MANAGETEMPADDR; @@ -5018,10 +5018,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENODEV; } - if (tb[IFA_FLAGS]) - cfg.ifa_flags = nla_get_u32(tb[IFA_FLAGS]); - else - cfg.ifa_flags = ifm->ifa_flags; + cfg.ifa_flags = nla_get_u32_default(tb[IFA_FLAGS], ifm->ifa_flags); /* We ignore other flags so far. */ cfg.ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 534a4498e280..7646e401c630 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -105,16 +105,11 @@ static int parse_nl_config(struct genl_info *info, xp->ip.locator_match.v64 = (__force __be64)nla_get_u64( info->attrs[ILA_ATTR_LOCATOR_MATCH]); - if (info->attrs[ILA_ATTR_CSUM_MODE]) - xp->ip.csum_mode = nla_get_u8(info->attrs[ILA_ATTR_CSUM_MODE]); - else - xp->ip.csum_mode = ILA_CSUM_NO_ACTION; - - if (info->attrs[ILA_ATTR_IDENT_TYPE]) - xp->ip.ident_type = nla_get_u8( - info->attrs[ILA_ATTR_IDENT_TYPE]); - else - xp->ip.ident_type = ILA_ATYPE_USE_FORMAT; + xp->ip.csum_mode = nla_get_u8_default(info->attrs[ILA_ATTR_CSUM_MODE], + ILA_CSUM_NO_ACTION); + + xp->ip.ident_type = nla_get_u8_default(info->attrs[ILA_ATTR_IDENT_TYPE], + ILA_ATYPE_USE_FORMAT); if (info->attrs[ILA_ATTR_IFINDEX]) xp->ifindex = nla_get_s32(info->attrs[ILA_ATTR_IFINDEX]); diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c index 08c929513065..a84d332f952f 100644 --- a/net/ipv6/ioam6.c +++ b/net/ipv6/ioam6.c @@ -135,15 +135,11 @@ static int ioam6_genl_addns(struct sk_buff *skb, struct genl_info *info) ns->id = id; - if (!info->attrs[IOAM6_ATTR_NS_DATA]) - data32 = IOAM6_U32_UNAVAILABLE; - else - data32 = nla_get_u32(info->attrs[IOAM6_ATTR_NS_DATA]); - - if (!info->attrs[IOAM6_ATTR_NS_DATA_WIDE]) - data64 = IOAM6_U64_UNAVAILABLE; - else - data64 = nla_get_u64(info->attrs[IOAM6_ATTR_NS_DATA_WIDE]); + data32 = nla_get_u32_default(info->attrs[IOAM6_ATTR_NS_DATA], + IOAM6_U32_UNAVAILABLE); + + data64 = nla_get_u64_default(info->attrs[IOAM6_ATTR_NS_DATA_WIDE], + IOAM6_U64_UNAVAILABLE); ns->data = cpu_to_be32(data32); ns->data_wide = cpu_to_be64(data64); diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index beb6b4cfc551..9d8422e350f8 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -142,10 +142,8 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, } } - if (!tb[IOAM6_IPTUNNEL_MODE]) - mode = IOAM6_IPTUNNEL_MODE_INLINE; - else - mode = nla_get_u8(tb[IOAM6_IPTUNNEL_MODE]); + mode = nla_get_u8_default(tb[IOAM6_IPTUNNEL_MODE], + IOAM6_IPTUNNEL_MODE_INLINE); if (tb[IOAM6_IPTUNNEL_SRC] && mode == IOAM6_IPTUNNEL_MODE_INLINE) { NL_SET_ERR_MSG(extack, "no tunnel src expected with this mode"); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 6383263bfd04..c134ba202c4c 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1183,8 +1183,8 @@ next_iter: while (sibling) { if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { - list_add_tail(&rt->fib6_siblings, - &sibling->fib6_siblings); + list_add_tail_rcu(&rt->fib6_siblings, + &sibling->fib6_siblings); break; } sibling = rcu_dereference_protected(sibling->fib6_next, @@ -1245,7 +1245,7 @@ add: fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; - list_del_init(&rt->fib6_siblings); + list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); return err; } @@ -1963,7 +1963,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; - list_del_init(&rt->fib6_siblings); + list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 8add0f45aa52..d66f58932a79 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2560,7 +2560,7 @@ static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, src = nla_get_in6_addr(tb[RTA_SRC]); if (tb[RTA_DST]) grp = nla_get_in6_addr(tb[RTA_DST]); - tableid = tb[RTA_TABLE] ? nla_get_u32(tb[RTA_TABLE]) : 0; + tableid = nla_get_u32_default(tb[RTA_TABLE], 0); mrt = ip6mr_get_table(net, tableid ?: RT_TABLE_DEFAULT); if (!mrt) { diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index f3c8e2d918e1..e087a8e97ba7 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -8,7 +8,14 @@ menu "IPv6: Netfilter Configuration" # old sockopt interface and eval loop config IP6_NF_IPTABLES_LEGACY - tristate + tristate "Legacy IP6 tables support" + depends on INET && IPV6 + select NETFILTER_XTABLES + default n + help + ip6tables is a legacy packet classifier. + This is not needed if you are using iptables over nftables + (iptables-nft). config NF_SOCKET_IPV6 tristate "IPv6 socket lookup support" diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 7db0437140bf..9ae2b2725bf9 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -268,12 +268,12 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in) void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { - struct sk_buff *nskb; - struct tcphdr _otcph; - const struct tcphdr *otcph; - unsigned int otcplen, hh_len; const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); struct dst_entry *dst = NULL; + const struct tcphdr *otcph; + struct sk_buff *nskb; + struct tcphdr _otcph; + unsigned int otcplen; struct flowi6 fl6; if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) || @@ -312,9 +312,8 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, if (IS_ERR(dst)) return; - hh_len = (dst->dev->hard_header_len + 15)&~15; - nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr) - + sizeof(struct tcphdr) + dst->trailer_len, + nskb = alloc_skb(LL_MAX_HEADER + sizeof(struct ipv6hdr) + + sizeof(struct tcphdr) + dst->trailer_len, GFP_ATOMIC); if (!nskb) { @@ -327,7 +326,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, nskb->mark = fl6.flowi6_mark; - skb_reserve(nskb, hh_len + dst->header_len); + skb_reserve(nskb, LL_MAX_HEADER); nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, ip6_dst_hoplimit(dst)); nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d7ce5cf2017a..63d7681c929f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -374,6 +374,7 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { struct rt6_info *rt = dst_rt6_info(dst); struct inet6_dev *idev = rt->rt6i_idev; + struct fib6_info *from; if (idev && idev->dev != blackhole_netdev) { struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev); @@ -383,6 +384,8 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) in6_dev_put(idev); } } + from = unrcu_pointer(xchg(&rt->from, NULL)); + fib6_info_release(from); } static bool __rt6_check_expired(const struct rt6_info *rt) @@ -413,8 +416,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { - struct fib6_info *sibling, *next_sibling; struct fib6_info *match = res->f6i; + struct fib6_info *sibling; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; @@ -440,8 +443,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound)) goto out; - list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings, - fib6_siblings) { + list_for_each_entry_rcu(sibling, &match->fib6_siblings, + fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; @@ -1455,7 +1458,6 @@ static DEFINE_SPINLOCK(rt6_exception_lock); static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { - struct fib6_info *from; struct net *net; if (!bucket || !rt6_ex) @@ -1467,8 +1469,6 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket, /* purge completely the exception to allow releasing the held resources: * some [sk] cache may keep the dst around for unlimited time */ - from = unrcu_pointer(xchg(&rt6_ex->rt6i->from, NULL)); - fib6_info_release(from); dst_dev_put(&rt6_ex->rt6i->dst); hlist_del_rcu(&rt6_ex->hlist); @@ -5195,14 +5195,18 @@ static void ip6_route_mpath_notify(struct fib6_info *rt, * nexthop. Since sibling routes are always added at the end of * the list, find the first sibling of the last route appended */ + rcu_read_lock(); + if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) { - rt = list_first_entry(&rt_last->fib6_siblings, - struct fib6_info, - fib6_siblings); + rt = list_first_or_null_rcu(&rt_last->fib6_siblings, + struct fib6_info, + fib6_siblings); } if (rt) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); + + rcu_read_unlock(); } static bool ip6_route_mpath_should_notify(const struct fib6_info *rt) @@ -5547,17 +5551,21 @@ static size_t rt6_nlmsg_size(struct fib6_info *f6i) nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); } else { - struct fib6_info *sibling, *next_sibling; struct fib6_nh *nh = f6i->fib6_nh; + struct fib6_info *sibling; nexthop_len = 0; if (f6i->fib6_nsiblings) { rt6_nh_nlmsg_size(nh, &nexthop_len); - list_for_each_entry_safe(sibling, next_sibling, - &f6i->fib6_siblings, fib6_siblings) { + rcu_read_lock(); + + list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, + fib6_siblings) { rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); } + + rcu_read_unlock(); } nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); } @@ -5721,7 +5729,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; } else if (rt->fib6_nsiblings) { - struct fib6_info *sibling, *next_sibling; + struct fib6_info *sibling; struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); @@ -5733,14 +5741,21 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, 0) < 0) goto nla_put_failure; - list_for_each_entry_safe(sibling, next_sibling, - &rt->fib6_siblings, fib6_siblings) { + rcu_read_lock(); + + list_for_each_entry_rcu(sibling, &rt->fib6_siblings, + fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, - AF_INET6, 0) < 0) + AF_INET6, 0) < 0) { + rcu_read_unlock(); + goto nla_put_failure; + } } + rcu_read_unlock(); + nla_nest_end(skb, mp); } else if (rt->nh) { if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id)) @@ -6177,7 +6192,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; - skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); + skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC); if (!skb) goto errout; @@ -6190,7 +6205,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, - info->nlh, gfp_any()); + info->nlh, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index c74705ead984..ac1dbd492c22 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -954,10 +954,10 @@ static int input_action_end_dx4_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); + enum skb_drop_reason reason; struct seg6_local_lwt *slwt; struct iphdr *iph; __be32 nhaddr; - int err; slwt = seg6_local_lwtunnel(orig_dst->lwtstate); @@ -967,9 +967,9 @@ static int input_action_end_dx4_finish(struct net *net, struct sock *sk, skb_dst_drop(skb); - err = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev); - if (err) { - kfree_skb(skb); + reason = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev); + if (reason) { + kfree_skb_reason(skb, reason); return -EINVAL; } @@ -1174,8 +1174,8 @@ drop: static int input_action_end_dt4(struct sk_buff *skb, struct seg6_local_lwt *slwt) { + enum skb_drop_reason reason; struct iphdr *iph; - int err; if (!decap_and_validate(skb, IPPROTO_IPIP)) goto drop; @@ -1193,8 +1193,8 @@ static int input_action_end_dt4(struct sk_buff *skb, iph = ip_hdr(skb); - err = ip_route_input(skb, iph->daddr, iph->saddr, 0, skb->dev); - if (unlikely(err)) + reason = ip_route_input(skb, iph->daddr, iph->saddr, 0, skb->dev); + if (unlikely(reason)) goto drop; return dst_input(skb); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 597920061a3a..c748eeae1453 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1172,8 +1172,8 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) goto out; if (aoh) - key.ao_key = tcp_ao_established_key(ao_info, - aoh->rnext_keyid, -1); + key.ao_key = tcp_ao_established_key(sk, ao_info, + aoh->rnext_keyid, -1); } } if (key.ao_key) { diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 13438cc0a6b1..cf0f7780fb10 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -96,7 +96,7 @@ config MAC80211_DEBUGFS config MAC80211_MESSAGE_TRACING bool "Trace all mac80211 debug messages" - depends on MAC80211 + depends on MAC80211 && TRACING help Select this option to have mac80211 register the mac80211_msg trace subsystem with tracepoints to diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 132e194c8d72..61a824ec33da 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -3071,6 +3071,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, bool update_txp_type = false; bool has_monitor = false; int user_power_level; + int old_power = local->user_power_level; lockdep_assert_wiphy(local->hw.wiphy); @@ -3180,6 +3181,10 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, } } + if (local->emulate_chanctx && + (old_power != local->user_power_level)) + ieee80211_hw_conf_chan(local); + return 0; } @@ -3190,7 +3195,8 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy, struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); - if (local->ops->get_txpower) + if (local->ops->get_txpower && + (sdata->flags & IEEE80211_SDATA_IN_DRIVER)) return drv_get_txpower(local, sdata, dbm); if (local->emulate_chanctx) @@ -4879,12 +4885,12 @@ void ieee80211_color_change_finalize_work(struct wiphy *wiphy, ieee80211_color_change_finalize(link); } -void ieee80211_color_collision_detection_work(struct work_struct *work) +void ieee80211_color_collision_detection_work(struct wiphy *wiphy, + struct wiphy_work *work) { - struct delayed_work *delayed_work = to_delayed_work(work); struct ieee80211_link_data *link = - container_of(delayed_work, struct ieee80211_link_data, - color_collision_detect_work); + container_of(work, struct ieee80211_link_data, + color_collision_detect_work.work); struct ieee80211_sub_if_data *sdata = link->sdata; cfg80211_obss_color_collision_notify(sdata->dev, link->color_bitmap, @@ -4937,7 +4943,8 @@ ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, return; } - if (delayed_work_pending(&link->color_collision_detect_work)) { + if (wiphy_delayed_work_pending(sdata->local->hw.wiphy, + &link->color_collision_detect_work)) { rcu_read_unlock(); return; } @@ -4946,9 +4953,9 @@ ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, /* queue the color collision detection event every 500 ms in order to * avoid sending too much netlink messages to userspace. */ - ieee80211_queue_delayed_work(&sdata->local->hw, - &link->color_collision_detect_work, - msecs_to_jiffies(500)); + wiphy_delayed_work_queue(sdata->local->hw.wiphy, + &link->color_collision_detect_work, + msecs_to_jiffies(500)); rcu_read_unlock(); } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 752297bcde76..a00096dd787b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -892,9 +892,10 @@ struct ieee80211_chanctx { /* temporary data for search algorithm etc. */ struct ieee80211_chan_req req; - struct ieee80211_chanctx_conf conf; - bool radar_detected; + + /* MUST be last - ends in a flexible-array member. */ + struct ieee80211_chanctx_conf conf; }; struct mac80211_qos_map { @@ -1051,7 +1052,7 @@ struct ieee80211_link_data { } csa; struct wiphy_work color_change_finalize_work; - struct delayed_work color_collision_detect_work; + struct wiphy_delayed_work color_collision_detect_work; u64 color_bitmap; /* context reservation -- protected with wiphy mutex */ @@ -2003,7 +2004,8 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, /* color change handling */ void ieee80211_color_change_finalize_work(struct wiphy *wiphy, struct wiphy_work *work); -void ieee80211_color_collision_detection_work(struct work_struct *work); +void ieee80211_color_collision_detection_work(struct wiphy *wiphy, + struct wiphy_work *work); /* interface handling */ #define MAC80211_SUPPORTED_FEATURES_TX (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \ diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 6fac3ba00d88..67ecfea22982 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -987,6 +987,26 @@ void ieee80211_reenable_keys(struct ieee80211_sub_if_data *sdata) } } +static void +ieee80211_key_iter(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_key *key, + void (*iter)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key, + void *data), + void *iter_data) +{ + /* skip keys of station in removal process */ + if (key->sta && key->sta->removed) + return; + if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) + return; + iter(hw, vif, key->sta ? &key->sta->sta : NULL, + &key->conf, iter_data); +} + void ieee80211_iter_keys(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void (*iter)(struct ieee80211_hw *hw, @@ -1005,16 +1025,13 @@ void ieee80211_iter_keys(struct ieee80211_hw *hw, if (vif) { sdata = vif_to_sdata(vif); list_for_each_entry_safe(key, tmp, &sdata->key_list, list) - iter(hw, &sdata->vif, - key->sta ? &key->sta->sta : NULL, - &key->conf, iter_data); + ieee80211_key_iter(hw, vif, key, iter, iter_data); } else { list_for_each_entry(sdata, &local->interfaces, list) list_for_each_entry_safe(key, tmp, &sdata->key_list, list) - iter(hw, &sdata->vif, - key->sta ? &key->sta->sta : NULL, - &key->conf, iter_data); + ieee80211_key_iter(hw, &sdata->vif, key, + iter, iter_data); } } EXPORT_SYMBOL(ieee80211_iter_keys); @@ -1031,17 +1048,8 @@ _ieee80211_iter_keys_rcu(struct ieee80211_hw *hw, { struct ieee80211_key *key; - list_for_each_entry_rcu(key, &sdata->key_list, list) { - /* skip keys of station in removal process */ - if (key->sta && key->sta->removed) - continue; - if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) - continue; - - iter(hw, &sdata->vif, - key->sta ? &key->sta->sta : NULL, - &key->conf, iter_data); - } + list_for_each_entry_rcu(key, &sdata->key_list, list) + ieee80211_key_iter(hw, &sdata->vif, key, iter, iter_data); } void ieee80211_iter_keys_rcu(struct ieee80211_hw *hw, diff --git a/net/mac80211/link.c b/net/mac80211/link.c index e8def387d0f8..58a76bcd6ae6 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -44,8 +44,8 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata, ieee80211_csa_finalize_work); wiphy_work_init(&link->color_change_finalize_work, ieee80211_color_change_finalize_work); - INIT_DELAYED_WORK(&link->color_collision_detect_work, - ieee80211_color_collision_detection_work); + wiphy_delayed_work_init(&link->color_collision_detect_work, + ieee80211_color_collision_detection_work); INIT_LIST_HEAD(&link->assigned_chanctx_list); INIT_LIST_HEAD(&link->reserved_chanctx_list); wiphy_delayed_work_init(&link->dfs_cac_timer_work, @@ -75,7 +75,8 @@ void ieee80211_link_stop(struct ieee80211_link_data *link) if (link->sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_mgd_stop_link(link); - cancel_delayed_work_sync(&link->color_collision_detect_work); + wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy, + &link->color_collision_detect_work); wiphy_work_cancel(link->sdata->local->hw.wiphy, &link->color_change_finalize_work); wiphy_work_cancel(link->sdata->local->hw.wiphy, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 89084690350f..ee1211a213d7 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -167,6 +167,8 @@ static u32 ieee80211_calc_hw_conf_chan(struct ieee80211_local *local, } power = ieee80211_chandef_max_power(&chandef); + if (local->user_power_level != IEEE80211_UNSET_POWER_LEVEL) + power = min(local->user_power_level, power); rcu_read_lock(); list_for_each_entry_rcu(sdata, &local->interfaces, list) { diff --git a/net/mctp/device.c b/net/mctp/device.c index 3d75b919995d..26ce34b7e88e 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -371,6 +371,8 @@ static int mctp_fill_link_af(struct sk_buff *skb, return -ENODATA; if (nla_put_u32(skb, IFLA_MCTP_NET, mdev->net)) return -EMSGSIZE; + if (nla_put_u8(skb, IFLA_MCTP_PHYS_BINDING, mdev->binding)) + return -EMSGSIZE; return 0; } @@ -385,6 +387,7 @@ static size_t mctp_get_link_af_size(const struct net_device *dev, if (!mdev) return 0; ret = nla_total_size(4); /* IFLA_MCTP_NET */ + ret += nla_total_size(1); /* IFLA_MCTP_PHYS_BINDING */ mctp_dev_put(mdev); return ret; } @@ -480,7 +483,8 @@ static int mctp_dev_notify(struct notifier_block *this, unsigned long event, } static int mctp_register_netdevice(struct net_device *dev, - const struct mctp_netdev_ops *ops) + const struct mctp_netdev_ops *ops, + enum mctp_phys_binding binding) { struct mctp_dev *mdev; @@ -489,17 +493,19 @@ static int mctp_register_netdevice(struct net_device *dev, return PTR_ERR(mdev); mdev->ops = ops; + mdev->binding = binding; return register_netdevice(dev); } int mctp_register_netdev(struct net_device *dev, - const struct mctp_netdev_ops *ops) + const struct mctp_netdev_ops *ops, + enum mctp_phys_binding binding) { int rc; rtnl_lock(); - rc = mctp_register_netdevice(dev, ops); + rc = mctp_register_netdevice(dev, ops, binding); rtnl_unlock(); return rc; diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c index 5a6b2b4510d3..dcffd847af33 100644 --- a/net/mptcp/mptcp_pm_gen.c +++ b/net/mptcp/mptcp_pm_gen.c @@ -112,7 +112,6 @@ const struct genl_ops mptcp_pm_nl_ops[11] = { .dumpit = mptcp_pm_nl_get_addr_dumpit, .policy = mptcp_pm_get_addr_nl_policy, .maxattr = MPTCP_PM_ATTR_TOKEN, - .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = MPTCP_PM_CMD_FLUSH_ADDRS, diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 2cceded3a83a..56dfea9862b7 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -91,6 +91,7 @@ static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk, struct mptcp_pm_addr_entry *addr) { struct mptcp_pm_addr_entry *entry, *tmp; + struct sock *sk = (struct sock *)msk; list_for_each_entry_safe(entry, tmp, &msk->pm.userspace_pm_local_addr_list, list) { if (mptcp_addresses_equal(&entry->addr, &addr->addr, false)) { @@ -98,7 +99,7 @@ static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk, * be used multiple times (e.g. fullmesh mode). */ list_del_rcu(&entry->list); - kfree(entry); + sock_kfree_s(sk, entry, sizeof(*entry)); msk->pm.local_addr_used--; return 0; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e978e05ec8d1..a6f2a25edb11 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2722,8 +2722,8 @@ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) if (!fail_tout && !inet_csk(sk)->icsk_mtup.probe_timestamp) return; - close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + - mptcp_close_timeout(sk); + close_timeout = (unsigned long)inet_csk(sk)->icsk_mtup.probe_timestamp - + tcp_jiffies32 + jiffies + mptcp_close_timeout(sk); /* the close timeout takes precedence on the fail one, and here at least one of * them is active @@ -2864,8 +2864,10 @@ static int mptcp_init_sock(struct sock *sk) if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net)) return -ENOMEM; + rcu_read_lock(); ret = mptcp_init_sched(mptcp_sk(sk), mptcp_sched_find(mptcp_get_scheduler(net))); + rcu_read_unlock(); if (ret) return ret; diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c index 78ed508ebc1b..df7dbcfa3b71 100644 --- a/net/mptcp/sched.c +++ b/net/mptcp/sched.c @@ -60,7 +60,6 @@ void mptcp_get_available_schedulers(char *buf, size_t maxlen) size_t offs = 0; rcu_read_lock(); - spin_lock(&mptcp_sched_list_lock); list_for_each_entry_rcu(sched, &mptcp_sched_list, list) { offs += snprintf(buf + offs, maxlen - offs, "%s%s", @@ -69,7 +68,6 @@ void mptcp_get_available_schedulers(char *buf, size_t maxlen) if (WARN_ON_ONCE(offs >= maxlen)) break; } - spin_unlock(&mptcp_sched_list_lock); rcu_read_unlock(); } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 07352b15f145..fd021cf8286e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -2049,7 +2049,6 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->tcp_state_change = old_ctx->tcp_state_change; new_ctx->tcp_error_report = old_ctx->tcp_error_report; new_ctx->rel_write_seq = 1; - new_ctx->tcp_sock = newsk; if (subflow_req->mp_capable) { /* see comments in subflow_syn_recv_sock(), MPTCP connection diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index dc6ddc4abbe2..7d13110ce188 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3662,10 +3662,7 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest, nla_memcpy(&udest->addr, nla_addr, sizeof(udest->addr)); udest->port = nla_get_be16(nla_port); - if (nla_addr_family) - udest->af = nla_get_u16(nla_addr_family); - else - udest->af = 0; + udest->af = nla_get_u16_default(nla_addr_family, 0); /* If a full entry was requested, check for the additional fields */ if (full_entry) { diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 4085c436e306..aad84aabd7f1 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -1090,10 +1090,8 @@ static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[], range->flags |= NF_NAT_RANGE_MAP_IPS; } - if (tb[CTA_NAT_V4_MAXIP]) - range->max_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MAXIP]); - else - range->max_addr.ip = range->min_addr.ip; + range->max_addr.ip = nla_get_be32_default(tb[CTA_NAT_V4_MAXIP], + range->min_addr.ip); return 0; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a24fe62650a7..6090ba9f1bb2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1495,6 +1495,7 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, INIT_LIST_HEAD(&table->sets); INIT_LIST_HEAD(&table->objects); INIT_LIST_HEAD(&table->flowtables); + write_pnet(&table->net, net); table->family = family; table->flags = flags; table->handle = ++nft_net->table_handle; @@ -1824,7 +1825,8 @@ nla_put_failure: return -ENOSPC; } -static int nft_dump_basechain_hook(struct sk_buff *skb, int family, +static int nft_dump_basechain_hook(struct sk_buff *skb, + const struct net *net, int family, const struct nft_base_chain *basechain, const struct list_head *hook_list) { @@ -1849,7 +1851,8 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family, if (!hook_list) hook_list = &basechain->hook_list; - list_for_each_entry_rcu(hook, hook_list, list) { + list_for_each_entry_rcu(hook, hook_list, list, + lockdep_commit_lock_is_held(net)) { if (!first) first = hook; @@ -1900,7 +1903,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, const struct nft_base_chain *basechain = nft_base_chain(chain); struct nft_stats __percpu *stats; - if (nft_dump_basechain_hook(skb, family, basechain, hook_list)) + if (nft_dump_basechain_hook(skb, net, family, basechain, hook_list)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CHAIN_POLICY, @@ -2082,14 +2085,14 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) err = nla_parse_nested_deprecated(tb, NFTA_COUNTER_MAX, attr, nft_counter_policy, NULL); if (err < 0) - return ERR_PTR(err); + return ERR_PTR_PCPU(err); if (!tb[NFTA_COUNTER_BYTES] || !tb[NFTA_COUNTER_PACKETS]) - return ERR_PTR(-EINVAL); + return ERR_PTR_PCPU(-EINVAL); newstats = netdev_alloc_pcpu_stats(struct nft_stats); if (newstats == NULL) - return ERR_PTR(-ENOMEM); + return ERR_PTR_PCPU(-ENOMEM); /* Restore old counters on this cpu, no problem. Per-cpu statistics * are not exposed to userspace. @@ -2533,10 +2536,10 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (nla[NFTA_CHAIN_COUNTERS]) { stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); - if (IS_ERR(stats)) { + if (IS_ERR_PCPU(stats)) { nft_chain_release_hook(&hook); kfree(basechain); - return PTR_ERR(stats); + return PTR_ERR_PCPU(stats); } rcu_assign_pointer(basechain->stats, stats); } @@ -2650,7 +2653,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, struct nft_table *table = ctx->table; struct nft_chain *chain = ctx->chain; struct nft_chain_hook hook = {}; - struct nft_stats *stats = NULL; + struct nft_stats __percpu *stats = NULL; struct nft_hook *h, *next; struct nf_hook_ops *ops; struct nft_trans *trans; @@ -2746,8 +2749,8 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, } stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); - if (IS_ERR(stats)) { - err = PTR_ERR(stats); + if (IS_ERR_PCPU(stats)) { + err = PTR_ERR_PCPU(stats); goto err_hooks; } } @@ -3294,25 +3297,37 @@ int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, if (!tb[NFTA_EXPR_DATA] || !tb[NFTA_EXPR_NAME]) return -EINVAL; + rcu_read_lock(); + type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]); - if (!type) - return -ENOENT; + if (!type) { + err = -ENOENT; + goto out_unlock; + } - if (!type->inner_ops) - return -EOPNOTSUPP; + if (!type->inner_ops) { + err = -EOPNOTSUPP; + goto out_unlock; + } err = nla_parse_nested_deprecated(info->tb, type->maxattr, tb[NFTA_EXPR_DATA], type->policy, NULL); if (err < 0) - goto err_nla_parse; + goto out_unlock; info->attr = nla; info->ops = type->inner_ops; + /* No module reference will be taken on type->owner. + * Presence of type->inner_ops implies that the expression + * is builtin, so it cannot go away. + */ + rcu_read_unlock(); return 0; -err_nla_parse: +out_unlock: + rcu_read_unlock(); return err; } @@ -3411,13 +3426,15 @@ void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) * Rules */ -static struct nft_rule *__nft_rule_lookup(const struct nft_chain *chain, +static struct nft_rule *__nft_rule_lookup(const struct net *net, + const struct nft_chain *chain, u64 handle) { struct nft_rule *rule; // FIXME: this sucks - list_for_each_entry_rcu(rule, &chain->rules, list) { + list_for_each_entry_rcu(rule, &chain->rules, list, + lockdep_commit_lock_is_held(net)) { if (handle == rule->handle) return rule; } @@ -3425,13 +3442,14 @@ static struct nft_rule *__nft_rule_lookup(const struct nft_chain *chain, return ERR_PTR(-ENOENT); } -static struct nft_rule *nft_rule_lookup(const struct nft_chain *chain, +static struct nft_rule *nft_rule_lookup(const struct net *net, + const struct nft_chain *chain, const struct nlattr *nla) { if (nla == NULL) return ERR_PTR(-EINVAL); - return __nft_rule_lookup(chain, be64_to_cpu(nla_get_be64(nla))); + return __nft_rule_lookup(net, chain, be64_to_cpu(nla_get_be64(nla))); } static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = { @@ -3732,7 +3750,7 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) return 0; } -/* called with rcu_read_lock held */ +/* Caller must hold rcu read lock or transaction mutex */ static struct sk_buff * nf_tables_getrule_single(u32 portid, const struct nfnl_info *info, const struct nlattr * const nla[], bool reset) @@ -3759,7 +3777,7 @@ nf_tables_getrule_single(u32 portid, const struct nfnl_info *info, return ERR_CAST(chain); } - rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); + rule = nft_rule_lookup(net, chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return ERR_CAST(rule); @@ -3983,7 +4001,8 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) struct nft_set_ext *ext; int ret = 0; - list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + list_for_each_entry_rcu(catchall, &set->catchall_list, list, + lockdep_commit_lock_is_held(ctx->net)) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, dummy_iter.genmask)) continue; @@ -4057,7 +4076,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_RULE_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE])); - rule = __nft_rule_lookup(chain, handle); + rule = __nft_rule_lookup(net, chain, handle); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); @@ -4079,7 +4098,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_RULE_POSITION]) { pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); - old_rule = __nft_rule_lookup(chain, pos_handle); + old_rule = __nft_rule_lookup(net, chain, pos_handle); if (IS_ERR(old_rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]); return PTR_ERR(old_rule); @@ -4296,7 +4315,7 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, if (chain) { if (nla[NFTA_RULE_HANDLE]) { - rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); + rule = nft_rule_lookup(info->net, chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) { if (PTR_ERR(rule) == -ENOENT && NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYRULE) @@ -4456,7 +4475,8 @@ static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { [NFTA_SET_DESC_CONCAT] = NLA_POLICY_NESTED_ARRAY(nft_concat_policy), }; -static struct nft_set *nft_set_lookup(const struct nft_table *table, +static struct nft_set *nft_set_lookup(const struct net *net, + const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nft_set *set; @@ -4464,7 +4484,8 @@ static struct nft_set *nft_set_lookup(const struct nft_table *table, if (nla == NULL) return ERR_PTR(-EINVAL); - list_for_each_entry_rcu(set, &table->sets, list) { + list_for_each_entry_rcu(set, &table->sets, list, + lockdep_commit_lock_is_held(net)) { if (!nla_strcmp(nla, set->name) && nft_active_genmask(set, genmask)) return set; @@ -4514,7 +4535,7 @@ struct nft_set *nft_set_lookup_global(const struct net *net, { struct nft_set *set; - set = nft_set_lookup(table, nla_set_name, genmask); + set = nft_set_lookup(net, table, nla_set_name, genmask); if (IS_ERR(set)) { if (!nla_set_id) return set; @@ -4890,7 +4911,7 @@ static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info, if (!nla[NFTA_SET_TABLE]) return -EINVAL; - set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask); + set = nft_set_lookup(net, table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return PTR_ERR(set); @@ -5226,7 +5247,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); - set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask); + set = nft_set_lookup(net, table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) { if (PTR_ERR(set) != -ENOENT) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); @@ -5428,7 +5449,7 @@ static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, set = nft_set_lookup_byhandle(table, attr, genmask); } else { attr = nla[NFTA_SET_NAME]; - set = nft_set_lookup(table, attr, genmask); + set = nft_set_lookup(net, table, attr, genmask); } if (IS_ERR(set)) { @@ -5492,7 +5513,8 @@ static int nft_set_catchall_bind_check(const struct nft_ctx *ctx, struct nft_set_ext *ext; int ret = 0; - list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + list_for_each_entry_rcu(catchall, &set->catchall_list, list, + lockdep_commit_lock_is_held(ctx->net)) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask)) continue; @@ -6258,7 +6280,7 @@ static int nft_set_dump_ctx_init(struct nft_set_dump_ctx *dump_ctx, return PTR_ERR(table); } - set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask); + set = nft_set_lookup(net, table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_SET]); return PTR_ERR(set); @@ -6409,7 +6431,7 @@ err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); } -static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx, +static struct nft_trans *nft_trans_elem_alloc(const struct nft_ctx *ctx, int msg_type, struct nft_set *set) { @@ -7471,13 +7493,11 @@ static int __nft_set_catchall_flush(const struct nft_ctx *ctx, { struct nft_trans *trans; - trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, - sizeof(struct nft_trans_elem), GFP_KERNEL); + trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set); if (!trans) return -ENOMEM; nft_setelem_data_deactivate(ctx->net, set, elem_priv); - nft_trans_elem_set(trans) = set; nft_trans_elem_priv(trans) = elem_priv; nft_trans_commit_list_add_tail(ctx->net, trans); @@ -7492,7 +7512,8 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, struct nft_set_ext *ext; int ret = 0; - list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + list_for_each_entry_rcu(catchall, &set->catchall_list, list, + lockdep_commit_lock_is_held(ctx->net)) { ext = nft_set_elem_ext(set, catchall->elem); if (!nft_set_elem_active(ext, genmask)) continue; @@ -7542,7 +7563,7 @@ static int nf_tables_delsetelem(struct sk_buff *skb, return PTR_ERR(table); } - set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask); + set = nft_set_lookup(net, table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_SET]); return PTR_ERR(set); @@ -7789,9 +7810,7 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, struct nft_trans *trans; int err = -ENOMEM; - if (!try_module_get(type->owner)) - return -ENOENT; - + /* caller must have obtained type->owner reference. */ trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ, sizeof(struct nft_trans_obj)); if (!trans) @@ -7859,15 +7878,16 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, if (info->nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; - type = __nft_obj_type_get(objtype, family); - if (WARN_ON_ONCE(!type)) - return -ENOENT; - if (!obj->ops->update) return 0; + type = nft_obj_type_get(net, objtype, family); + if (WARN_ON_ONCE(IS_ERR(type))) + return PTR_ERR(type); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + /* type->owner reference is put when transaction object is released. */ return nf_tables_updobj(&ctx, type, nla[NFTA_OBJ_DATA], obj); } @@ -8103,7 +8123,7 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) return 0; } -/* called with rcu_read_lock held */ +/* Caller must hold rcu read lock or transaction mutex */ static struct sk_buff * nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, const struct nlattr * const nla[], bool reset) @@ -8372,12 +8392,14 @@ static const struct nla_policy nft_flowtable_policy[NFTA_FLOWTABLE_MAX + 1] = { [NFTA_FLOWTABLE_FLAGS] = { .type = NLA_U32 }, }; -struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table, +struct nft_flowtable *nft_flowtable_lookup(const struct net *net, + const struct nft_table *table, const struct nlattr *nla, u8 genmask) { struct nft_flowtable *flowtable; - list_for_each_entry_rcu(flowtable, &table->flowtables, list) { + list_for_each_entry_rcu(flowtable, &table->flowtables, list, + lockdep_commit_lock_is_held(net)) { if (!nla_strcmp(nla, flowtable->name) && nft_active_genmask(flowtable, genmask)) return flowtable; @@ -8733,7 +8755,7 @@ static int nf_tables_newflowtable(struct sk_buff *skb, return PTR_ERR(table); } - flowtable = nft_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], + flowtable = nft_flowtable_lookup(net, table, nla[NFTA_FLOWTABLE_NAME], genmask); if (IS_ERR(flowtable)) { err = PTR_ERR(flowtable); @@ -8927,7 +8949,7 @@ static int nf_tables_delflowtable(struct sk_buff *skb, flowtable = nft_flowtable_lookup_byhandle(table, attr, genmask); } else { attr = nla[NFTA_FLOWTABLE_NAME]; - flowtable = nft_flowtable_lookup(table, attr, genmask); + flowtable = nft_flowtable_lookup(net, table, attr, genmask); } if (IS_ERR(flowtable)) { @@ -8997,7 +9019,8 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, if (!hook_list) hook_list = &flowtable->hook_list; - list_for_each_entry_rcu(hook, hook_list, list) { + list_for_each_entry_rcu(hook, hook_list, list, + lockdep_commit_lock_is_held(net)) { if (nla_put_string(skb, NFTA_DEVICE_NAME, hook->ops.dev->name)) goto nla_put_failure; } @@ -9139,7 +9162,7 @@ static int nf_tables_getflowtable(struct sk_buff *skb, return PTR_ERR(table); } - flowtable = nft_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], + flowtable = nft_flowtable_lookup(net, table, nla[NFTA_FLOWTABLE_NAME], genmask); if (IS_ERR(flowtable)) { NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); @@ -11430,22 +11453,48 @@ int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, } EXPORT_SYMBOL_GPL(nft_data_dump); -int __nft_release_basechain(struct nft_ctx *ctx) +static void __nft_release_basechain_now(struct nft_ctx *ctx) { struct nft_rule *rule, *nr; - if (WARN_ON(!nft_is_base_chain(ctx->chain))) - return 0; - - nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { list_del(&rule->list); - nft_use_dec(&ctx->chain->use); nf_tables_rule_release(ctx, rule); } + nf_tables_chain_destroy(ctx->chain); +} + +static void nft_release_basechain_rcu(struct rcu_head *head) +{ + struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head); + struct nft_ctx ctx = { + .family = chain->table->family, + .chain = chain, + .net = read_pnet(&chain->table->net), + }; + + __nft_release_basechain_now(&ctx); + put_net(ctx.net); +} + +int __nft_release_basechain(struct nft_ctx *ctx) +{ + struct nft_rule *rule; + + if (WARN_ON_ONCE(!nft_is_base_chain(ctx->chain))) + return 0; + + nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); + list_for_each_entry(rule, &ctx->chain->rules, list) + nft_use_dec(&ctx->chain->use); + nft_chain_del(ctx->chain); nft_use_dec(&ctx->table->use); - nf_tables_chain_destroy(ctx->chain); + + if (maybe_get_net(ctx->net)) + call_rcu(&ctx->chain->rcu_head, nft_release_basechain_rcu); + else + __nft_release_basechain_now(ctx); return 0; } diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 2f732fae5a83..65199c23c75c 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -409,8 +409,8 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx, if (!tb[NFTA_FLOW_TABLE_NAME]) return -EINVAL; - flowtable = nft_flowtable_lookup(ctx->table, tb[NFTA_FLOW_TABLE_NAME], - genmask); + flowtable = nft_flowtable_lookup(ctx->net, ctx->table, + tb[NFTA_FLOW_TABLE_NAME], genmask); if (IS_ERR(flowtable)) return PTR_ERR(flowtable); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 330609a76fb2..7dfc5343dae4 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -904,6 +904,9 @@ static void nft_payload_set_eval(const struct nft_expr *expr, ((priv->base != NFT_PAYLOAD_TRANSPORT_HEADER && priv->base != NFT_PAYLOAD_INNER_HEADER) || skb->ip_summed != CHECKSUM_PARTIAL)) { + if (offset + priv->len > skb->len) + goto err; + fsum = skb_checksum(skb, offset, priv->len, 0); tsum = csum_partial(src, priv->len, 0); diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 1caa04619dc6..12390d2e994f 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -88,13 +88,15 @@ bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, } static struct nft_bitmap_elem * -nft_bitmap_elem_find(const struct nft_set *set, struct nft_bitmap_elem *this, +nft_bitmap_elem_find(const struct net *net, + const struct nft_set *set, struct nft_bitmap_elem *this, u8 genmask) { const struct nft_bitmap *priv = nft_set_priv(set); struct nft_bitmap_elem *be; - list_for_each_entry_rcu(be, &priv->list, head) { + list_for_each_entry_rcu(be, &priv->list, head, + lockdep_is_held(&nft_pernet(net)->commit_mutex)) { if (memcmp(nft_set_ext_key(&be->ext), nft_set_ext_key(&this->ext), set->klen) || !nft_set_elem_active(&be->ext, genmask)) @@ -132,7 +134,7 @@ static int nft_bitmap_insert(const struct net *net, const struct nft_set *set, u8 genmask = nft_genmask_next(net); u32 idx, off; - be = nft_bitmap_elem_find(set, new, genmask); + be = nft_bitmap_elem_find(net, set, new, genmask); if (be) { *elem_priv = &be->priv; return -EEXIST; @@ -201,7 +203,7 @@ nft_bitmap_deactivate(const struct net *net, const struct nft_set *set, nft_bitmap_location(set, elem->key.val.data, &idx, &off); - be = nft_bitmap_elem_find(set, this, genmask); + be = nft_bitmap_elem_find(net, set, this, genmask); if (!be) return NULL; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index daa56dda737a..65bd291318f2 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -647,7 +647,8 @@ static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, int i; for (i = 0; i < priv->buckets; i++) { - hlist_for_each_entry_rcu(he, &priv->table[i], node) { + hlist_for_each_entry_rcu(he, &priv->table[i], node, + lockdep_is_held(&nft_pernet(ctx->net)->commit_mutex)) { if (iter->count < iter->skip) goto cont; diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 5c6ed68cc6e0..681301b46aa4 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -497,10 +497,7 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx, } if (tb[NFTA_TUNNEL_KEY_TOS]) info.key.tos = nla_get_u8(tb[NFTA_TUNNEL_KEY_TOS]); - if (tb[NFTA_TUNNEL_KEY_TTL]) - info.key.ttl = nla_get_u8(tb[NFTA_TUNNEL_KEY_TTL]); - else - info.key.ttl = U8_MAX; + info.key.ttl = nla_get_u8_default(tb[NFTA_TUNNEL_KEY_TTL], U8_MAX); if (tb[NFTA_TUNNEL_KEY_OPTS]) { err = nft_tunnel_obj_opts_init(ctx, tb[NFTA_TUNNEL_KEY_OPTS], diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index da5d929c7c85..709840612f0d 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1269,7 +1269,7 @@ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, /* and once again: */ list_for_each_entry(t, &xt_net->tables[af], list) - if (strcmp(t->name, name) == 0) + if (strcmp(t->name, name) == 0 && owner == t->me) return t; module_put(owner); diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 689eaa2afbec..079fe72a6384 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -107,11 +107,9 @@ static int netlbl_mgmt_add_common(struct genl_info *info, switch (entry->def.type) { case NETLBL_NLTYPE_UNLABELED: - if (info->attrs[NLBL_MGMT_A_FAMILY]) - entry->family = - nla_get_u16(info->attrs[NLBL_MGMT_A_FAMILY]); - else - entry->family = AF_UNSPEC; + entry->family = + nla_get_u16_default(info->attrs[NLBL_MGMT_A_FAMILY], + AF_UNSPEC); break; case NETLBL_NLTYPE_CIPSOV4: if (!info->attrs[NLBL_MGMT_A_CV4DOI]) @@ -601,10 +599,7 @@ static int netlbl_mgmt_listdef(struct sk_buff *skb, struct genl_info *info) struct netlbl_dom_map *entry; u16 family; - if (info->attrs[NLBL_MGMT_A_FAMILY]) - family = nla_get_u16(info->attrs[NLBL_MGMT_A_FAMILY]); - else - family = AF_INET; + family = nla_get_u16_default(info->attrs[NLBL_MGMT_A_FAMILY], AF_INET); ans_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (ans_skb == NULL) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 0a9287fadb47..52a7c7233cab 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2935,12 +2935,8 @@ static int __init netlink_proto_init(void) for (i = 0; i < MAX_LINKS; i++) { if (rhashtable_init(&nl_table[i].hash, - &netlink_rhashtable_params) < 0) { - while (--i > 0) - rhashtable_destroy(&nl_table[i].hash); - kfree(nl_table); + &netlink_rhashtable_params) < 0) goto panic; - } } netlink_add_usersock_entry(); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index f456a5911e7d..1ec5955fe469 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -757,6 +757,14 @@ int nci_core_conn_close(struct nci_dev *ndev, u8 conn_id) } EXPORT_SYMBOL(nci_core_conn_close); +static void nci_set_target_ats(struct nfc_target *target, struct nci_dev *ndev) +{ + if (ndev->target_ats_len > 0) { + target->ats_len = ndev->target_ats_len; + memcpy(target->ats, ndev->target_ats, target->ats_len); + } +} + static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev) { struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); @@ -939,8 +947,11 @@ static int nci_activate_target(struct nfc_dev *nfc_dev, msecs_to_jiffies(NCI_RF_DISC_SELECT_TIMEOUT)); } - if (!rc) + if (!rc) { ndev->target_active_prot = protocol; + if (protocol == NFC_PROTO_ISO14443) + nci_set_target_ats(target, ndev); + } return rc; } diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index 994a0a1efb58..a818eff27e6b 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -402,7 +402,7 @@ static int nci_extract_activation_params_iso_dep(struct nci_dev *ndev, switch (ntf->activation_rf_tech_and_mode) { case NCI_NFC_A_PASSIVE_POLL_MODE: nfca_poll = &ntf->activation_params.nfca_poll_iso_dep; - nfca_poll->rats_res_len = min_t(__u8, *data++, 20); + nfca_poll->rats_res_len = min_t(__u8, *data++, NFC_ATS_MAXSIZE); pr_debug("rats_res_len %d\n", nfca_poll->rats_res_len); if (nfca_poll->rats_res_len > 0) { memcpy(nfca_poll->rats_res, @@ -531,6 +531,28 @@ static int nci_store_general_bytes_nfc_dep(struct nci_dev *ndev, return NCI_STATUS_OK; } +static int nci_store_ats_nfc_iso_dep(struct nci_dev *ndev, + const struct nci_rf_intf_activated_ntf *ntf) +{ + ndev->target_ats_len = 0; + + if (ntf->activation_params_len <= 0) + return NCI_STATUS_OK; + + if (ntf->activation_params.nfca_poll_iso_dep.rats_res_len > NFC_ATS_MAXSIZE) { + pr_debug("ATS too long\n"); + return NCI_STATUS_RF_PROTOCOL_ERROR; + } + + if (ntf->activation_params.nfca_poll_iso_dep.rats_res_len > 0) { + ndev->target_ats_len = ntf->activation_params.nfca_poll_iso_dep.rats_res_len; + memcpy(ndev->target_ats, ntf->activation_params.nfca_poll_iso_dep.rats_res, + ndev->target_ats_len); + } + + return NCI_STATUS_OK; +} + static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev, const struct sk_buff *skb) { @@ -660,6 +682,14 @@ exit: if (err != NCI_STATUS_OK) pr_err("unable to store general bytes\n"); } + + /* store ATS to be reported later in nci_activate_target */ + if (ntf.rf_interface == NCI_RF_INTERFACE_ISO_DEP && + ntf.activation_rf_tech_and_mode == NCI_NFC_A_PASSIVE_POLL_MODE) { + err = nci_store_ats_nfc_iso_dep(ndev, &ntf); + if (err != NCI_STATUS_OK) + pr_err("unable to store ATS\n"); + } } if (!(ntf.activation_rf_tech_and_mode & NCI_RF_TECH_MODE_LISTEN_MASK)) { diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index dd2ce73a24fb..6a40b8d0350d 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -96,6 +96,11 @@ static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, goto nla_put_failure; } + if (target->ats_len > 0 && + nla_put(msg, NFC_ATTR_TARGET_ATS, target->ats_len, + target->ats)) + goto nla_put_failure; + genlmsg_end(msg, hdr); return 0; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 78d9961fcd44..225f6048867f 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1828,8 +1828,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.dp = dp; parms.port_no = OVSP_LOCAL; parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID]; - parms.desired_ifindex = a[OVS_DP_ATTR_IFINDEX] - ? nla_get_s32(a[OVS_DP_ATTR_IFINDEX]) : 0; + parms.desired_ifindex = nla_get_s32_default(a[OVS_DP_ATTR_IFINDEX], 0); /* So far only local changes have been made, now need the lock. */ ovs_lock(); @@ -2266,8 +2265,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) if (a[OVS_VPORT_ATTR_IFINDEX] && parms.type != OVS_VPORT_TYPE_INTERNAL) return -EOPNOTSUPP; - port_no = a[OVS_VPORT_ATTR_PORT_NO] - ? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0; + port_no = nla_get_u32_default(a[OVS_VPORT_ATTR_PORT_NO], 0); if (port_no >= DP_MAX_PORTS) return -EFBIG; @@ -2304,8 +2302,8 @@ restart: parms.dp = dp; parms.port_no = port_no; parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID]; - parms.desired_ifindex = a[OVS_VPORT_ATTR_IFINDEX] - ? nla_get_s32(a[OVS_VPORT_ATTR_IFINDEX]) : 0; + parms.desired_ifindex = nla_get_s32_default(a[OVS_VPORT_ATTR_IFINDEX], + 0); vport = new_vport(&parms); err = PTR_ERR(vport); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 729ef582a3a8..881ddd3696d5 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1938,7 +1938,7 @@ int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid, u32 ovs_nla_get_ufid_flags(const struct nlattr *attr) { - return attr ? nla_get_u32(attr) : 0; + return nla_get_u32_default(attr, 0); } /** diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 5858d65ea1a9..2412d7813d24 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -195,7 +195,6 @@ static int internal_dev_recv(struct sk_buff *skb) skb_dst_drop(skb); nf_reset_ct(skb); - secpath_reset(skb); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, netdev); diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c index 19234d664c4f..5c36bae37b8f 100644 --- a/net/phonet/pn_dev.c +++ b/net/phonet/pn_dev.c @@ -406,8 +406,9 @@ int phonet_route_del(struct net_device *dev, u8 daddr) if (!dev) return -ENOENT; - synchronize_rcu(); - dev_put(dev); + + /* Note : our caller must call synchronize_rcu() and dev_put(dev) */ + return 0; } diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index ca1f04e4a2d9..b9043c92dc24 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -233,6 +233,7 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh, { struct net *net = sock_net(skb->sk); struct nlattr *tb[RTA_MAX+1]; + bool sync_needed = false; struct net_device *dev; struct rtmsg *rtm; u32 ifindex; @@ -269,13 +270,20 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENODEV; } - if (nlh->nlmsg_type == RTM_NEWROUTE) + if (nlh->nlmsg_type == RTM_NEWROUTE) { err = phonet_route_add(dev, dst); - else + } else { err = phonet_route_del(dev, dst); + if (!err) + sync_needed = true; + } rcu_read_unlock(); + if (sync_needed) { + synchronize_rcu(); + dev_put(dev); + } if (!err) rtm_phonet_notify(net, nlh->nlmsg_type, ifindex, dst); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index d25bf1cf3670..bb11e8289d6d 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -516,6 +516,7 @@ void rxrpc_connect_client_calls(struct rxrpc_local *local) spin_lock(&local->client_call_lock); list_move_tail(&call->wait_link, &bundle->waiting_calls); + rxrpc_see_call(call, rxrpc_call_see_waiting_call); spin_unlock(&local->client_call_lock); if (rxrpc_bundle_has_space(bundle)) @@ -586,7 +587,10 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call _debug("call is waiting"); ASSERTCMP(call->call_id, ==, 0); ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags)); + /* May still be on ->new_client_calls. */ + spin_lock(&local->client_call_lock); list_del_init(&call->wait_link); + spin_unlock(&local->client_call_lock); return; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 1539d315afe7..694c4df7a1a3 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -337,9 +337,7 @@ static void rxrpc_clean_up_connection(struct work_struct *work) */ rxrpc_purge_queue(&conn->rx_queue); - if (conn->tx_data_alloc.va) - __page_frag_cache_drain(virt_to_page(conn->tx_data_alloc.va), - conn->tx_data_alloc.pagecnt_bias); + page_frag_cache_drain(&conn->tx_data_alloc); call_rcu(&conn->rcu, rxrpc_rcu_free_connection); } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index f9623ace2201..2792d2304605 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -452,9 +452,7 @@ void rxrpc_destroy_local(struct rxrpc_local *local) #endif rxrpc_purge_queue(&local->rx_queue); rxrpc_purge_client_connections(local); - if (local->tx_alloc.va) - __page_frag_cache_drain(virt_to_page(local->tx_alloc.va), - local->tx_alloc.pagecnt_bias); + page_frag_cache_drain(&local->tx_alloc); } /* diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 23d18fe5de9f..6abb8eec1b2b 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -29,6 +29,7 @@ bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error, call->send_abort_why = why; call->send_abort_err = error; call->send_abort_seq = 0; + trace_rxrpc_abort_call(call, abort_code); /* Request abort locklessly vs rxrpc_input_call_event(). */ smp_store_release(&call->send_abort, abort_code); rxrpc_poke_call(call, rxrpc_call_poke_abort); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 2197eb625658..c02f39efc6ef 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1183,9 +1183,8 @@ static int tcf_ct_fill_params_nat(struct tcf_ct_params *p, range->min_addr.ip = nla_get_in_addr(tb[TCA_CT_NAT_IPV4_MIN]); - range->max_addr.ip = max_attr ? - nla_get_in_addr(max_attr) : - range->min_addr.ip; + range->max_addr.ip = + nla_get_in_addr_default(max_attr, range->min_addr.ip); } else if (tb[TCA_CT_NAT_IPV6_MIN]) { struct nlattr *max_attr = tb[TCA_CT_NAT_IPV6_MAX]; @@ -1314,8 +1313,9 @@ static int tcf_ct_fill_params(struct net *net, err = -EINVAL; goto err; } - family = tb[TCA_CT_HELPER_FAMILY] ? nla_get_u8(tb[TCA_CT_HELPER_FAMILY]) : AF_INET; - proto = tb[TCA_CT_HELPER_PROTO] ? nla_get_u8(tb[TCA_CT_HELPER_PROTO]) : IPPROTO_TCP; + family = nla_get_u8_default(tb[TCA_CT_HELPER_FAMILY], AF_INET); + proto = nla_get_u8_default(tb[TCA_CT_HELPER_PROTO], + IPPROTO_TCP); err = nf_ct_add_helper(tmpl, name, family, proto, p->ct_action & TCA_CT_ACT_NAT, &p->helper); if (err) { diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 5dd41a012110..5b1241ddc758 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -197,8 +197,9 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, "dscp mask must be 6 contiguous bits"); return -EINVAL; } - dscpstatemask = tb[TCA_CTINFO_PARMS_DSCP_STATEMASK] ? - nla_get_u32(tb[TCA_CTINFO_PARMS_DSCP_STATEMASK]) : 0; + dscpstatemask = + nla_get_u32_default(tb[TCA_CTINFO_PARMS_DSCP_STATEMASK], + 0); /* mask & statemask must not overlap */ if (dscpmask & dscpstatemask) { NL_SET_ERR_MSG_ATTR(extack, @@ -243,8 +244,7 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, } cp_new->net = net; - cp_new->zone = tb[TCA_CTINFO_ZONE] ? - nla_get_u16(tb[TCA_CTINFO_ZONE]) : 0; + cp_new->zone = nla_get_u16_default(tb[TCA_CTINFO_ZONE], 0); if (dscpmask) { cp_new->dscpmask = dscpmask; cp_new->dscpmaskshift = dscpmaskshift; diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 1dd74125398a..91c0ec729823 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -190,15 +190,10 @@ static int fill_gate_entry(struct nlattr **tb, struct tcfg_gate_entry *entry, entry->interval = interval; - if (tb[TCA_GATE_ENTRY_IPV]) - entry->ipv = nla_get_s32(tb[TCA_GATE_ENTRY_IPV]); - else - entry->ipv = -1; + entry->ipv = nla_get_s32_default(tb[TCA_GATE_ENTRY_IPV], -1); - if (tb[TCA_GATE_ENTRY_MAX_OCTETS]) - entry->maxoctets = nla_get_s32(tb[TCA_GATE_ENTRY_MAX_OCTETS]); - else - entry->maxoctets = -1; + entry->maxoctets = nla_get_s32_default(tb[TCA_GATE_ENTRY_MAX_OCTETS], + -1); return 0; } diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 44a37a71ae92..9f86f4e666d3 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -288,16 +288,14 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, } p->tcfm_action = parm->m_action; - p->tcfm_label = tb[TCA_MPLS_LABEL] ? nla_get_u32(tb[TCA_MPLS_LABEL]) : - ACT_MPLS_LABEL_NOT_SET; - p->tcfm_tc = tb[TCA_MPLS_TC] ? nla_get_u8(tb[TCA_MPLS_TC]) : - ACT_MPLS_TC_NOT_SET; - p->tcfm_ttl = tb[TCA_MPLS_TTL] ? nla_get_u8(tb[TCA_MPLS_TTL]) : - mpls_ttl; - p->tcfm_bos = tb[TCA_MPLS_BOS] ? nla_get_u8(tb[TCA_MPLS_BOS]) : - ACT_MPLS_BOS_NOT_SET; - p->tcfm_proto = tb[TCA_MPLS_PROTO] ? nla_get_be16(tb[TCA_MPLS_PROTO]) : - htons(ETH_P_MPLS_UC); + p->tcfm_label = nla_get_u32_default(tb[TCA_MPLS_LABEL], + ACT_MPLS_LABEL_NOT_SET); + p->tcfm_tc = nla_get_u8_default(tb[TCA_MPLS_TC], ACT_MPLS_TC_NOT_SET); + p->tcfm_ttl = nla_get_u8_default(tb[TCA_MPLS_TTL], mpls_ttl); + p->tcfm_bos = nla_get_u8_default(tb[TCA_MPLS_BOS], + ACT_MPLS_BOS_NOT_SET); + p->tcfm_proto = nla_get_be16_default(tb[TCA_MPLS_PROTO], + htons(ETH_P_MPLS_UC)); spin_lock_bh(&m->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 8555125ed34d..a214ed681142 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -167,8 +167,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, } if (R_tab) { new->rate_present = true; - rate64 = tb[TCA_POLICE_RATE64] ? - nla_get_u64(tb[TCA_POLICE_RATE64]) : 0; + rate64 = nla_get_u64_default(tb[TCA_POLICE_RATE64], 0); psched_ratecfg_precompute(&new->rate, &R_tab->rate, rate64); qdisc_put_rtab(R_tab); } else { @@ -176,8 +175,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, } if (P_tab) { new->peak_present = true; - prate64 = tb[TCA_POLICE_PEAKRATE64] ? - nla_get_u64(tb[TCA_POLICE_PEAKRATE64]) : 0; + prate64 = nla_get_u64_default(tb[TCA_POLICE_PEAKRATE64], 0); psched_ratecfg_precompute(&new->peak, &P_tab->rate, prate64); qdisc_put_rtab(P_tab); } else { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 7637f979d689..7578e27260c9 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1518,6 +1518,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, return 0; err_dev_insert: + tcf_block_offload_unbind(block, q, ei); err_block_offload_bind: tcf_chain0_head_change_cb_del(block, ei); err_chain0_head_change_cb_add: @@ -1932,7 +1933,8 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain, static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, struct tcf_chain_info *chain_info, u32 protocol, u32 prio, - bool prio_allocate); + bool prio_allocate, + struct netlink_ext_ack *extack); /* Try to insert new proto. * If proto with specified priority already exists, free new proto @@ -1956,8 +1958,7 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, return ERR_PTR(-EAGAIN); } - tp = tcf_chain_tp_find(chain, &chain_info, - protocol, prio, false); + tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false, NULL); if (!tp) err = tcf_chain_tp_insert(chain, &chain_info, tp_new); mutex_unlock(&chain->filter_chain_lock); @@ -2017,7 +2018,8 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, struct tcf_chain_info *chain_info, u32 protocol, u32 prio, - bool prio_allocate) + bool prio_allocate, + struct netlink_ext_ack *extack) { struct tcf_proto **pprev; struct tcf_proto *tp; @@ -2028,9 +2030,14 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, pprev = &tp->next) { if (tp->prio >= prio) { if (tp->prio == prio) { - if (prio_allocate || - (tp->protocol != protocol && protocol)) + if (prio_allocate) { + NL_SET_ERR_MSG(extack, "Lowest ID from auto-alloc range already in use"); + return ERR_PTR(-ENOSPC); + } + if (tp->protocol != protocol && protocol) { + NL_SET_ERR_MSG(extack, "Protocol mismatch for filter with specified priority"); return ERR_PTR(-EINVAL); + } } else { tp = NULL; } @@ -2296,7 +2303,7 @@ replay: } block->classid = parent; - chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); if (chain_index > TC_ACT_EXT_VAL_MASK) { NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); err = -EINVAL; @@ -2311,9 +2318,8 @@ replay: mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, - prio, prio_allocate); + prio, prio_allocate, extack); if (IS_ERR(tp)) { - NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); err = PTR_ERR(tp); goto errout_locked; } @@ -2508,7 +2514,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, goto errout; } - chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); if (chain_index > TC_ACT_EXT_VAL_MASK) { NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); err = -EINVAL; @@ -2538,10 +2544,13 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, - prio, false); - if (!tp || IS_ERR(tp)) { + prio, false, extack); + if (!tp) { + err = -ENOENT; NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); - err = tp ? PTR_ERR(tp) : -ENOENT; + goto errout_locked; + } else if (IS_ERR(tp)) { + err = PTR_ERR(tp); goto errout_locked; } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); @@ -2663,7 +2672,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, goto errout; } - chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); if (chain_index > TC_ACT_EXT_VAL_MASK) { NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); err = -EINVAL; @@ -2678,11 +2687,14 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, - prio, false); + prio, false, extack); mutex_unlock(&chain->filter_chain_lock); - if (!tp || IS_ERR(tp)) { + if (!tp) { + err = -ENOENT; NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); - err = tp ? PTR_ERR(tp) : -ENOENT; + goto errout; + } else if (IS_ERR(tp)) { + err = PTR_ERR(tp); goto errout; } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); @@ -3103,7 +3115,7 @@ replay: if (IS_ERR(block)) return PTR_ERR(block); - chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + chain_index = nla_get_u32_default(tca[TCA_CHAIN], 0); if (chain_index > TC_ACT_EXT_VAL_MASK) { NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); err = -EINVAL; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index da2da2ab858b..300430b8c4d2 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -791,7 +791,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) drops = max_t(int, n, 0); rcu_read_lock(); while ((parentid = sch->parent)) { - if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS)) + if (parentid == TC_H_ROOT) break; if (sch->flags & TCQ_F_NOPARENT) diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 91072010923d..1e940ad0d2fa 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -356,7 +356,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, tb[TCA_CHOKE_STAB] == NULL) return -EINVAL; - max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0; + max_P = nla_get_u32_default(tb[TCA_CHOKE_MAX_P], 0); ctl = nla_data(tb[TCA_CHOKE_PARMS]); stab = nla_data(tb[TCA_CHOKE_STAB]); diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 79ba9dc70254..7d2151c62c4a 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -668,7 +668,7 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt, return -EINVAL; } - max_P = tb[TCA_GRED_MAX_P] ? nla_get_u32(tb[TCA_GRED_MAX_P]) : 0; + max_P = nla_get_u32_default(tb[TCA_GRED_MAX_P], 0); ctl = nla_data(tb[TCA_GRED_PARMS]); stab = nla_data(tb[TCA_GRED_STAB]); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index ff3de37874e4..c31bc5489bdd 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1810,8 +1810,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_put_rtab(qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB], NULL)); - rate64 = tb[TCA_HTB_RATE64] ? nla_get_u64(tb[TCA_HTB_RATE64]) : 0; - ceil64 = tb[TCA_HTB_CEIL64] ? nla_get_u64(tb[TCA_HTB_CEIL64]) : 0; + rate64 = nla_get_u64_default(tb[TCA_HTB_RATE64], 0); + ceil64 = nla_get_u64_default(tb[TCA_HTB_CEIL64], 0); if (!cl) { /* new class */ struct net_device *dev = qdisc_dev(sch); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index d584c0c25899..6a07cdbdb9e1 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -421,10 +421,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (err < 0) return err; - if (tb[TCA_QFQ_WEIGHT]) - weight = nla_get_u32(tb[TCA_QFQ_WEIGHT]); - else - weight = 1; + weight = nla_get_u32_default(tb[TCA_QFQ_WEIGHT], 1); if (tb[TCA_QFQ_LMAX]) { lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index b5f096588fae..6029bc29b51e 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -248,7 +248,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, tb[TCA_RED_STAB] == NULL) return -EINVAL; - max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0; + max_P = nla_get_u32_default(tb[TCA_RED_MAX_P], 0); ctl = nla_data(tb[TCA_RED_PARMS]); stab = nla_data(tb[TCA_RED_STAB]); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 8623dc0bafc0..a68e17891b0b 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1828,7 +1828,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, * zero; (2) the 'flags' of a "running" taprio instance cannot be * changed. */ - taprio_flags = tb[TCA_TAPRIO_ATTR_FLAGS] ? nla_get_u32(tb[TCA_TAPRIO_ATTR_FLAGS]) : 0; + taprio_flags = nla_get_u32_default(tb[TCA_TAPRIO_ATTR_FLAGS], 0); /* txtime-assist and full offload are mutually exclusive */ if ((taprio_flags & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) && diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index f7b809c0d142..b96c849545ae 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -103,10 +103,10 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, ipv6_addr_equal(&addr->a.v6.sin6_addr, &ifa->addr) && addr->a.v6.sin6_scope_id == ifa->idev->dev->ifindex) { - sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); found = 1; addr->valid = 0; list_del_rcu(&addr->list); + sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); break; } } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 39ca5403d4d7..8b9a1b96695e 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -738,6 +738,20 @@ void sctp_addr_wq_mgmt(struct net *net, struct sctp_sockaddr_entry *addr, int cm */ spin_lock_bh(&net->sctp.addr_wq_lock); + + /* Avoid searching the queue or modifying it if there are no consumers, + * as it can lead to performance degradation if addresses are modified + * en-masse. + * + * If the queue already contains some events, update it anyway to avoid + * ugly races between new sessions and new address events. + */ + if (list_empty(&net->sctp.auto_asconf_splist) && + list_empty(&net->sctp.addr_waitq)) { + spin_unlock_bh(&net->sctp.addr_wq_lock); + return; + } + /* Offsets existing events in addr_wq */ addrw = sctp_addr_wq_lookup(net, addr); if (addrw) { @@ -808,10 +822,10 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, if (addr->a.sa.sa_family == AF_INET && addr->a.v4.sin_addr.s_addr == ifa->ifa_local) { - sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); found = 1; addr->valid = 0; list_del_rcu(&addr->list); + sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); break; } } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 7d315a18612b..a0524ba8d787 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3751,7 +3751,7 @@ enum sctp_disposition sctp_sf_ootb(struct net *net, } ch = (struct sctp_chunkhdr *)ch_end; - } while (ch_end < skb_tail_pointer(skb)); + } while (ch_end + sizeof(*ch) < skb_tail_pointer(skb)); if (ootb_shut_ack) return sctp_sf_shut_8_4_5(net, ep, asoc, type, arg, commands); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 0316217b7687..9d76e902fd77 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3359,8 +3359,10 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, else rc = smc_create_clcsk(net, sk, family); - if (rc) + if (rc) { sk_common_release(sk); + sock->sk = NULL; + } out: return rc; } diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 9297dc20bfe2..9c563cdbea90 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -899,9 +899,7 @@ static void smc_copy_netdev_ifindex(struct smc_ib_device *smcibdev, int port) struct ib_device *ibdev = smcibdev->ibdev; struct net_device *ndev; - if (!ibdev->ops.get_netdev) - return; - ndev = ibdev->ops.get_netdev(ibdev, port + 1); + ndev = ib_device_get_netdev(ibdev, port + 1); if (ndev) { smcibdev->ndev_ifidx[port] = ndev->ifindex; dev_put(ndev); @@ -921,9 +919,7 @@ void smc_ib_ndev_change(struct net_device *ndev, unsigned long event) port_cnt = smcibdev->ibdev->phys_port_cnt; for (i = 0; i < min_t(size_t, port_cnt, SMC_MAX_PORTS); i++) { libdev = smcibdev->ibdev; - if (!libdev->ops.get_netdev) - continue; - lndev = libdev->ops.get_netdev(libdev, i + 1); + lndev = ib_device_get_netdev(libdev, i + 1); dev_put(lndev); if (lndev != ndev) continue; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index a04aa0e882f8..716808f374a8 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -1054,9 +1054,7 @@ static void smc_pnet_find_rdma_dev(struct net_device *netdev, for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; - if (!ibdev->ibdev->ops.get_netdev) - continue; - ndev = ibdev->ibdev->ops.get_netdev(ibdev->ibdev, i); + ndev = ib_device_get_netdev(ibdev->ibdev, i); if (!ndev) continue; dev_put(ndev); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 825ec5357691..b785425c3315 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1608,7 +1608,6 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt) static void svc_sock_free(struct svc_xprt *xprt) { struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); - struct page_frag_cache *pfc = &svsk->sk_frag_cache; struct socket *sock = svsk->sk_sock; trace_svcsock_free(svsk, sock); @@ -1618,8 +1617,7 @@ static void svc_sock_free(struct svc_xprt *xprt) sockfd_put(sock); else sock_release(sock); - if (pfc->va) - __page_frag_cache_drain(virt_to_head_page(pfc->va), - pfc->pagecnt_bias); + + page_frag_cache_drain(&svsk->sk_frag_cache); kfree(svsk); } diff --git a/net/sunrpc/xprtrdma/ib_client.c b/net/sunrpc/xprtrdma/ib_client.c index 8507cd4d8921..28c68b5f6823 100644 --- a/net/sunrpc/xprtrdma/ib_client.c +++ b/net/sunrpc/xprtrdma/ib_client.c @@ -153,6 +153,7 @@ static void rpcrdma_remove_one(struct ib_device *device, } trace_rpcrdma_client_remove_one_done(device); + xa_destroy(&rd->rd_xa); kfree(rd); } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 0e1691316f42..1326fbf45a34 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2459,6 +2459,7 @@ static void xs_tcp_setup_socket(struct work_struct *work) case -EHOSTUNREACH: case -EADDRINUSE: case -ENOBUFS: + case -ENOTCONN: break; default: printk("%s: connect returned unhandled error %d\n", diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index e2157e387217..56c232cf5b0f 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -549,6 +549,7 @@ static void hvs_destruct(struct vsock_sock *vsk) vmbus_hvsock_device_unregister(chan); kfree(hvs); + vsk->trans = NULL; } static int hvs_dgram_bind(struct vsock_sock *vsk, struct sockaddr_vm *addr) diff --git a/net/wireless/core.c b/net/wireless/core.c index 93d62a1d3a45..afbdc549fb4a 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1280,6 +1280,7 @@ static void _cfg80211_unregister_wdev(struct wireless_dev *wdev, /* deleted from the list, so can't be found from nl80211 any more */ cqm_config = rcu_access_pointer(wdev->cqm_config); kfree_rcu(cqm_config, rcu_head); + RCU_INIT_POINTER(wdev->cqm_config, NULL); /* * Ensure that all events have been processed and @@ -1750,6 +1751,13 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy, } EXPORT_SYMBOL_GPL(wiphy_delayed_work_flush); +bool wiphy_delayed_work_pending(struct wiphy *wiphy, + struct wiphy_delayed_work *dwork) +{ + return timer_pending(&dwork->timer); +} +EXPORT_SYMBOL_GPL(wiphy_delayed_work_pending); + static int __init cfg80211_init(void) { int err; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b8cdd844f0e6..9d2edb71f981 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1286,10 +1286,7 @@ static unsigned int nl80211_link_id(struct nlattr **attrs) { struct nlattr *linkid = attrs[NL80211_ATTR_MLO_LINK_ID]; - if (!linkid) - return 0; - - return nla_get_u8(linkid); + return nla_get_u8_default(linkid, 0); } static int nl80211_link_id_or_invalid(struct nlattr **attrs) @@ -3414,11 +3411,9 @@ static int _nl80211_parse_chandef(struct cfg80211_registered_device *rdev, if (attrs[NL80211_ATTR_CENTER_FREQ1]) { chandef->center_freq1 = nla_get_u32(attrs[NL80211_ATTR_CENTER_FREQ1]); - if (attrs[NL80211_ATTR_CENTER_FREQ1_OFFSET]) - chandef->freq1_offset = nla_get_u32( - attrs[NL80211_ATTR_CENTER_FREQ1_OFFSET]); - else - chandef->freq1_offset = 0; + chandef->freq1_offset = + nla_get_u32_default(attrs[NL80211_ATTR_CENTER_FREQ1_OFFSET], + 0); } if (attrs[NL80211_ATTR_CENTER_FREQ2]) chandef->center_freq2 = @@ -8265,11 +8260,9 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) if (unlikely(!rcu_access_pointer(cfg80211_regdomain))) return -EINPROGRESS; - if (info->attrs[NL80211_ATTR_USER_REG_HINT_TYPE]) - user_reg_hint_type = - nla_get_u32(info->attrs[NL80211_ATTR_USER_REG_HINT_TYPE]); - else - user_reg_hint_type = NL80211_USER_REG_HINT_USER; + user_reg_hint_type = + nla_get_u32_default(info->attrs[NL80211_ATTR_USER_REG_HINT_TYPE], + NL80211_USER_REG_HINT_USER); switch (user_reg_hint_type) { case NL80211_USER_REG_HINT_USER: @@ -11088,11 +11081,9 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, nla_len(info->attrs[NL80211_ATTR_SAE_PASSWORD]); } - if (info->attrs[NL80211_ATTR_SAE_PWE]) - settings->sae_pwe = - nla_get_u8(info->attrs[NL80211_ATTR_SAE_PWE]); - else - settings->sae_pwe = NL80211_SAE_PWE_UNSPECIFIED; + settings->sae_pwe = + nla_get_u8_default(info->attrs[NL80211_ATTR_SAE_PWE], + NL80211_SAE_PWE_UNSPECIFIED); return 0; } @@ -12348,10 +12339,8 @@ static int nl80211_disconnect(struct sk_buff *skb, struct genl_info *info) dev->ieee80211_ptr->conn_owner_nlportid != info->snd_portid) return -EPERM; - if (!info->attrs[NL80211_ATTR_REASON_CODE]) - reason = WLAN_REASON_DEAUTH_LEAVING; - else - reason = nla_get_u16(info->attrs[NL80211_ATTR_REASON_CODE]); + reason = nla_get_u16_default(info->attrs[NL80211_ATTR_REASON_CODE], + WLAN_REASON_DEAUTH_LEAVING); if (reason == 0) return -EINVAL; @@ -13697,10 +13686,7 @@ static int nl80211_parse_wowlan_tcp(struct cfg80211_registered_device *rdev, cfg->dst = nla_get_in_addr(tb[NL80211_WOWLAN_TCP_DST_IPV4]); memcpy(cfg->dst_mac, nla_data(tb[NL80211_WOWLAN_TCP_DST_MAC]), ETH_ALEN); - if (tb[NL80211_WOWLAN_TCP_SRC_PORT]) - port = nla_get_u16(tb[NL80211_WOWLAN_TCP_SRC_PORT]); - else - port = 0; + port = nla_get_u16_default(tb[NL80211_WOWLAN_TCP_SRC_PORT], 0); #ifdef CONFIG_INET /* allocate a socket and port for it and use it */ err = __sock_create(wiphy_net(&rdev->wiphy), PF_INET, SOCK_STREAM, @@ -13911,11 +13897,9 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) pat_len < wowlan->pattern_min_len) goto error; - if (!pat_tb[NL80211_PKTPAT_OFFSET]) - pkt_offset = 0; - else - pkt_offset = nla_get_u32( - pat_tb[NL80211_PKTPAT_OFFSET]); + pkt_offset = + nla_get_u32_default(pat_tb[NL80211_PKTPAT_OFFSET], + 0); if (pkt_offset > wowlan->max_pkt_offset) goto error; new_triggers.patterns[i].pkt_offset = pkt_offset; @@ -14159,10 +14143,8 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev, pat_len < coalesce->pattern_min_len) return -EINVAL; - if (!pat_tb[NL80211_PKTPAT_OFFSET]) - pkt_offset = 0; - else - pkt_offset = nla_get_u32(pat_tb[NL80211_PKTPAT_OFFSET]); + pkt_offset = nla_get_u32_default(pat_tb[NL80211_PKTPAT_OFFSET], + 0); if (pkt_offset > coalesce->max_pkt_offset) return -EINVAL; new_rule->patterns[i].pkt_offset = pkt_offset; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 8e3d46bf4836..1c6fd45aa809 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -3051,6 +3051,10 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, freq = ieee80211_channel_to_freq_khz(ap_info->channel, band); data.channel = ieee80211_get_channel_khz(wiphy, freq); + /* Skip if RNR element specifies an unsupported channel */ + if (!data.channel) + continue; + /* Skip if BSS entry generated from MBSSID or DIRECT source * frame data available already. */ diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e3b8ce89831a..e0dd9dfd71c2 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -200,7 +200,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, struct netlink_ext_ack *extack) { int err; - u8 sa_dir = attrs[XFRMA_SA_DIR] ? nla_get_u8(attrs[XFRMA_SA_DIR]) : 0; + u8 sa_dir = nla_get_u8_default(attrs[XFRMA_SA_DIR], 0); u16 family = p->sel.family; err = -EINVAL; @@ -767,10 +767,8 @@ static void xfrm_smark_init(struct nlattr **attrs, struct xfrm_mark *m) { if (attrs[XFRMA_SET_MARK]) { m->v = nla_get_u32(attrs[XFRMA_SET_MARK]); - if (attrs[XFRMA_SET_MARK_MASK]) - m->m = nla_get_u32(attrs[XFRMA_SET_MARK_MASK]); - else - m->m = 0xffffffff; + m->m = nla_get_u32_default(attrs[XFRMA_SET_MARK_MASK], + 0xffffffff); } else { m->v = m->m = 0; } diff --git a/scripts/Makefile.package b/scripts/Makefile.package index 11d53f240a2b..74bcb9e7f7a4 100644 --- a/scripts/Makefile.package +++ b/scripts/Makefile.package @@ -62,6 +62,10 @@ rpm-sources: linux.tar.gz PHONY += rpm-pkg srcrpm-pkg binrpm-pkg +ifneq ($(CC),$(HOSTCC)) +rpm-no-devel = --without=devel +endif + rpm-pkg: private build-type := a srcrpm-pkg: private build-type := s binrpm-pkg: private build-type := b @@ -72,7 +76,8 @@ rpm-pkg srcrpm-pkg binrpm-pkg: rpmbuild/SPECS/kernel.spec --define='_topdir $(abspath rpmbuild)' \ $(if $(filter a b, $(build-type)), \ --target $(UTS_MACHINE)-linux --build-in-place --noprep --define='_smp_mflags %{nil}' \ - $$(rpm -q rpm >/dev/null 2>&1 || echo --nodeps)) \ + $$(rpm -q rpm >/dev/null 2>&1 || echo --nodeps) \ + $(rpm-no-devel)) \ $(RPMOPTS)) # deb-pkg srcdeb-pkg bindeb-pkg diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index 4addd33749bb..6587ac86d0d5 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -533,6 +533,7 @@ bool menu_is_empty(struct menu *menu) bool menu_is_visible(struct menu *menu) { + struct menu *child; struct symbol *sym; tristate visible; @@ -551,7 +552,17 @@ bool menu_is_visible(struct menu *menu) } else visible = menu->prompt->visible.tri = expr_calc_value(menu->prompt->visible.expr); - return visible != no; + if (visible != no) + return true; + + if (!sym || sym_get_tristate_value(menu->sym) == no) + return false; + + for (child = menu->list; child; child = child->next) + if (menu_is_visible(child)) + return true; + + return false; } const char *menu_get_prompt(const struct menu *menu) diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 99dce93a4188..c4cc11aa558f 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -567,12 +567,12 @@ static int do_acpi_entry(const char *filename, void *symval, char *alias) { DEF_FIELD_ADDR(symval, acpi_device_id, id); - DEF_FIELD_ADDR(symval, acpi_device_id, cls); - DEF_FIELD_ADDR(symval, acpi_device_id, cls_msk); + DEF_FIELD(symval, acpi_device_id, cls); + DEF_FIELD(symval, acpi_device_id, cls_msk); if (id && strlen((const char *)*id)) sprintf(alias, "acpi*:%s:*", *id); - else if (cls) { + else { int i, byte_shift, cnt = 0; unsigned int msk; @@ -580,10 +580,10 @@ static int do_acpi_entry(const char *filename, cnt = 6; for (i = 1; i <= 3; i++) { byte_shift = 8 * (3-i); - msk = (*cls_msk >> byte_shift) & 0xFF; + msk = (cls_msk >> byte_shift) & 0xFF; if (msk) sprintf(&alias[cnt], "%02x", - (*cls >> byte_shift) & 0xFF); + (cls >> byte_shift) & 0xFF); else sprintf(&alias[cnt], "??"); cnt += 2; @@ -743,7 +743,7 @@ static void do_input(char *alias, for (i = min / BITS_PER_LONG; i < max / BITS_PER_LONG + 1; i++) arr[i] = TO_NATIVE(arr[i]); for (i = min; i < max; i++) - if (arr[i / BITS_PER_LONG] & (1L << (i%BITS_PER_LONG))) + if (arr[i / BITS_PER_LONG] & (1ULL << (i%BITS_PER_LONG))) sprintf(alias + strlen(alias), "%X,*", i); } diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c index e7d2da45b0df..6de9af17599d 100644 --- a/scripts/mod/sumversion.c +++ b/scripts/mod/sumversion.c @@ -392,7 +392,7 @@ out_file: /* Calc and record src checksum. */ void get_src_version(const char *modname, char sum[], unsigned sumlen) { - char *buf; + char *buf, *pos; struct md4_ctx md; char *fname; char filelist[PATH_MAX + 1]; @@ -401,9 +401,10 @@ void get_src_version(const char *modname, char sum[], unsigned sumlen) snprintf(filelist, sizeof(filelist), "%s.mod", modname); buf = read_text_file(filelist); + pos = buf; md4_init(&md); - while ((fname = strsep(&buf, "\n"))) { + while ((fname = strsep(&pos, "\n"))) { if (!*fname) continue; if (!(is_static_library(fname)) && diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 404587fc71fe..441b0bb66e0d 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -123,7 +123,7 @@ install_kernel_headers () { pdir=debian/$1 version=${1#linux-headers-} - "${srctree}/scripts/package/install-extmod-build" "${pdir}/usr/src/linux-headers-${version}" + CC="${DEB_HOST_GNU_TYPE}-gcc" "${srctree}/scripts/package/install-extmod-build" "${pdir}/usr/src/linux-headers-${version}" mkdir -p $pdir/lib/modules/$version/ ln -s /usr/src/linux-headers-$version $pdir/lib/modules/$version/build diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build index d2c9cacecc0c..7ec1f061a519 100755 --- a/scripts/package/install-extmod-build +++ b/scripts/package/install-extmod-build @@ -44,13 +44,11 @@ mkdir -p "${destdir}" fi } | tar -c -f - -T - | tar -xf - -C "${destdir}" -# When ${CC} and ${HOSTCC} differ, we are likely cross-compiling. Rebuild host -# programs using ${CC}. This assumes CC=${CROSS_COMPILE}gcc, which is usually -# the case for package building. It does not cross-compile when CC=clang. +# When ${CC} and ${HOSTCC} differ, rebuild host programs using ${CC}. # # This caters to host programs that participate in Kbuild. objtool and # resolve_btfids are out of scope. -if [ "${CC}" != "${HOSTCC}" ] && is_enabled CONFIG_CC_CAN_LINK; then +if [ "${CC}" != "${HOSTCC}" ]; then echo "Rebuilding host programs with ${CC}..." cat <<-'EOF' > "${destdir}/Kbuild" diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 10637d403777..fc3b7fa709fc 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -179,6 +179,8 @@ fi echo $debarch > debian/arch +host_gnu=$(dpkg-architecture -a "${debarch}" -q DEB_HOST_GNU_TYPE | sed 's/_/-/g') + # Generate a simple changelog template cat <<EOF > debian/changelog $sourcename ($packageversion) $distribution; urgency=low @@ -196,7 +198,11 @@ Priority: optional Maintainer: $maintainer Rules-Requires-Root: no Build-Depends: debhelper-compat (= 12) -Build-Depends-Arch: bc, bison, cpio, flex, kmod, libelf-dev:native, libssl-dev:native, rsync +Build-Depends-Arch: bc, bison, cpio, flex, + gcc-${host_gnu} <!pkg.${sourcename}.nokernelheaders>, + kmod, libelf-dev:native, + libssl-dev:native, libssl-dev <!pkg.${sourcename}.nokernelheaders>, + rsync Homepage: https://www.kernel.org/ Package: $packagename-$version @@ -224,6 +230,7 @@ cat <<EOF >> debian/control Package: linux-headers-$version Architecture: $debarch +Build-Profiles: <!pkg.${sourcename}.nokernelheaders> Description: Linux kernel headers for $version on $debarch This package provides kernel header files for $version on $debarch . @@ -238,6 +245,7 @@ cat <<EOF >> debian/control Package: linux-image-$version-dbg Section: debug Architecture: $debarch +Build-Profiles: <!pkg.${sourcename}.nokerneldbg> Description: Linux kernel debugging symbols for $version This package will come in handy if you need to debug the kernel. It provides all the necessary debug symbols for the kernel and its modules. diff --git a/scripts/rustc-llvm-version.sh b/scripts/rustc-llvm-version.sh index b6063cbe5bdc..a500d1ae3101 100755 --- a/scripts/rustc-llvm-version.sh +++ b/scripts/rustc-llvm-version.sh @@ -13,7 +13,7 @@ get_canonical_version() echo $((10000 * $1 + 100 * $2 + $3)) } -if output=$("$@" --version --verbose 2>/dev/null | grep LLVM); then +if output=$("$@" --version --verbose 2>/dev/null | grep -E 'LLVM.*[0-9]+\.[0-9]+\.[0-9]+'); then set -- $output get_canonical_version $3 else diff --git a/security/keys/keyring.c b/security/keys/keyring.c index 4448758f643a..f331725d5a37 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -772,8 +772,11 @@ ascend_to_node: for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { ptr = READ_ONCE(node->slots[slot]); - if (assoc_array_ptr_is_meta(ptr) && node->back_pointer) - goto descend_to_node; + if (assoc_array_ptr_is_meta(ptr)) { + if (node->back_pointer || + assoc_array_ptr_is_shortcut(ptr)) + goto descend_to_node; + } if (!keyring_ptr_is_keyring(ptr)) continue; diff --git a/security/keys/trusted-keys/trusted_dcp.c b/security/keys/trusted-keys/trusted_dcp.c index 4edc5bbbcda3..e908c53a803c 100644 --- a/security/keys/trusted-keys/trusted_dcp.c +++ b/security/keys/trusted-keys/trusted_dcp.c @@ -133,6 +133,7 @@ static int do_aead_crypto(u8 *in, u8 *out, size_t len, u8 *key, u8 *nonce, struct scatterlist src_sg, dst_sg; struct crypto_aead *aead; int ret; + DECLARE_CRYPTO_WAIT(wait); aead = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(aead)) { @@ -163,8 +164,8 @@ static int do_aead_crypto(u8 *in, u8 *out, size_t len, u8 *key, u8 *nonce, } aead_request_set_crypt(aead_req, &src_sg, &dst_sg, len, nonce); - aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, - NULL); + aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_SLEEP, + crypto_req_done, &wait); aead_request_set_ad(aead_req, 0); if (crypto_aead_setkey(aead, key, AES_KEYSIZE_128)) { @@ -174,9 +175,9 @@ static int do_aead_crypto(u8 *in, u8 *out, size_t len, u8 *key, u8 *nonce, } if (do_encrypt) - ret = crypto_aead_encrypt(aead_req); + ret = crypto_wait_req(crypto_aead_encrypt(aead_req), &wait); else - ret = crypto_aead_decrypt(aead_req); + ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &wait); free_req: aead_request_free(aead_req); diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index c72b2a754775..7fc51f829ecc 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -172,6 +172,9 @@ static int apply_constraint_to_size(struct snd_pcm_hw_params *params, step = max(step, amdtp_syt_intervals[i]); } + if (step == 0) + return -EINVAL; + t.min = roundup(s->min, step); t.max = rounddown(s->max, step); t.integer = 1; diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index f018bd779862..9f849e05ce79 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -723,6 +723,10 @@ static const struct config_entry acpi_config_table[] = { /* BayTrail */ { .flags = FLAG_SST_OR_SOF_BYT, + .acpi_hid = "LPE0F28", + }, + { + .flags = FLAG_SST_OR_SOF_BYT, .acpi_hid = "80860F28", }, /* CherryTrail */ diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig index bb15a0248250..68f1eee9e5c9 100644 --- a/sound/pci/hda/Kconfig +++ b/sound/pci/hda/Kconfig @@ -198,7 +198,7 @@ config SND_HDA_SCODEC_TAS2781_I2C depends on SND_SOC select SND_SOC_TAS2781_COMLIB select SND_SOC_TAS2781_FMWLIB - select CRC32_SARWATE + select CRC32 help Say Y or M here to include TAS2781 I2C HD-audio side codec support in snd-hda-intel driver, such as ALC287. diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 3bbf5fab2881..571fa8a6c9e1 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3868,20 +3868,18 @@ static void alc_default_init(struct hda_codec *codec) hp_pin_sense = snd_hda_jack_detect(codec, hp_pin); - if (hp_pin_sense) + if (hp_pin_sense) { msleep(2); - snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); - - if (hp_pin_sense) - msleep(85); + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT); - snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT); + msleep(75); - if (hp_pin_sense) - msleep(100); + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE); + msleep(75); + } } static void alc_default_shutup(struct hda_codec *codec) @@ -3897,22 +3895,20 @@ static void alc_default_shutup(struct hda_codec *codec) hp_pin_sense = snd_hda_jack_detect(codec, hp_pin); - if (hp_pin_sense) + if (hp_pin_sense) { msleep(2); - snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); - - if (hp_pin_sense) - msleep(85); - - if (!spec->no_shutup_pins) snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0); + AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); - if (hp_pin_sense) - msleep(100); + msleep(75); + + if (!spec->no_shutup_pins) + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0); + msleep(75); + } alc_auto_setup_eapd(codec, false); alc_shutup_pins(codec); } @@ -7525,6 +7521,7 @@ enum { ALC286_FIXUP_SONY_MIC_NO_PRESENCE, ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT, ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC269_FIXUP_DELL1_LIMIT_INT_MIC_BOOST, ALC269_FIXUP_DELL2_MIC_NO_PRESENCE, ALC269_FIXUP_DELL3_MIC_NO_PRESENCE, ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, @@ -7555,10 +7552,12 @@ enum { ALC290_FIXUP_SUBWOOFER_HSJACK, ALC269_FIXUP_THINKPAD_ACPI, ALC269_FIXUP_DMIC_THINKPAD_ACPI, + ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13, ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO, ALC255_FIXUP_ACER_MIC_NO_PRESENCE, ALC255_FIXUP_ASUS_MIC_NO_PRESENCE, ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC255_FIXUP_DELL1_LIMIT_INT_MIC_BOOST, ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, ALC255_FIXUP_HEADSET_MODE, ALC255_FIXUP_HEADSET_MODE_NO_HP_MIC, @@ -7649,6 +7648,7 @@ enum { ALC286_FIXUP_ACER_AIO_HEADSET_MIC, ALC256_FIXUP_ASUS_HEADSET_MIC, ALC256_FIXUP_ASUS_MIC_NO_PRESENCE, + ALC255_FIXUP_PREDATOR_SUBWOOFER, ALC299_FIXUP_PREDATOR_SPK, ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, ALC289_FIXUP_DELL_SPK1, @@ -7999,6 +7999,16 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc269_fixup_pincfg_U7x7_headset_mic, }, + [ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x14, 0x90170151 }, /* use as internal speaker (LFE) */ + { 0x1b, 0x90170152 }, /* use as internal speaker (back) */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST + }, [ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -8117,6 +8127,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE }, + [ALC269_FIXUP_DELL1_LIMIT_INT_MIC_BOOST] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269_fixup_limit_int_mic_boost, + .chained = true, + .chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE + }, [ALC269_FIXUP_DELL2_MIC_NO_PRESENCE] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -8397,6 +8413,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC255_FIXUP_HEADSET_MODE }, + [ALC255_FIXUP_DELL1_LIMIT_INT_MIC_BOOST] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269_fixup_limit_int_mic_boost, + .chained = true, + .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE + }, [ALC255_FIXUP_DELL2_MIC_NO_PRESENCE] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -9063,6 +9085,13 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE }, + [ALC255_FIXUP_PREDATOR_SUBWOOFER] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x17, 0x90170151 }, /* use as internal speaker (LFE) */ + { 0x1b, 0x90170152 } /* use as internal speaker (back) */ + } + }, [ALC299_FIXUP_PREDATOR_SPK] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -10150,6 +10179,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x110e, "Acer Aspire ES1-432", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1166, "Acer Veriton N4640G", ALC269_FIXUP_LIFEBOOK), SND_PCI_QUIRK(0x1025, 0x1167, "Acer Veriton N6640G", ALC269_FIXUP_LIFEBOOK), + SND_PCI_QUIRK(0x1025, 0x1177, "Acer Predator G9-593", ALC255_FIXUP_PREDATOR_SUBWOOFER), + SND_PCI_QUIRK(0x1025, 0x1178, "Acer Predator G9-593", ALC255_FIXUP_PREDATOR_SUBWOOFER), SND_PCI_QUIRK(0x1025, 0x1246, "Acer Predator Helios 500", ALC299_FIXUP_PREDATOR_SPK), SND_PCI_QUIRK(0x1025, 0x1247, "Acer vCopperbox", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1025, 0x1248, "Acer Veriton N4660G", ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE), @@ -10719,6 +10750,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x1404, "Clevo N150CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), 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, 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), @@ -10976,6 +11008,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1d05, 0x1409, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), @@ -10983,6 +11016,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13), SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), @@ -11070,6 +11104,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC269_FIXUP_DELL2_MIC_NO_PRESENCE, .name = "dell-headset-dock"}, {.id = ALC269_FIXUP_DELL3_MIC_NO_PRESENCE, .name = "dell-headset3"}, {.id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, .name = "dell-headset4"}, + {.id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET, .name = "dell-headset4-quiet"}, {.id = ALC283_FIXUP_CHROME_BOOK, .name = "alc283-dac-wcaps"}, {.id = ALC283_FIXUP_SENSE_COMBO_JACK, .name = "alc283-sense-combo"}, {.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"}, @@ -11624,16 +11659,16 @@ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = { SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, {0x19, 0x40000000}, {0x1b, 0x40000000}), - SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET, {0x19, 0x40000000}, {0x1b, 0x40000000}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, {0x19, 0x40000000}, {0x1a, 0x40000000}), - SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_LIMIT_INT_MIC_BOOST, {0x19, 0x40000000}, {0x1a, 0x40000000}), - SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, + SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC269_FIXUP_DELL1_LIMIT_INT_MIC_BOOST, {0x19, 0x40000000}, {0x1a, 0x40000000}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC2XX_FIXUP_HEADSET_MIC, diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index ace6328e91e3..438865d5e376 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -329,6 +329,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "E1404FA"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "E1504FA"), } }, @@ -342,6 +349,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M3502RA"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."), DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 B7ED"), } diff --git a/sound/soc/codecs/aw88399.c b/sound/soc/codecs/aw88399.c index 8dc2b8aa6832..bba59885242d 100644 --- a/sound/soc/codecs/aw88399.c +++ b/sound/soc/codecs/aw88399.c @@ -656,7 +656,7 @@ static int aw_dev_get_dsp_status(struct aw_device *aw_dev) if (ret) return ret; if (!(reg_val & (~AW88399_WDT_CNT_MASK))) - ret = -EPERM; + return -EPERM; return 0; } diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c index e4827b8c2bde..6e51954bdb1e 100644 --- a/sound/soc/codecs/cs42l51.c +++ b/sound/soc/codecs/cs42l51.c @@ -747,8 +747,10 @@ int cs42l51_probe(struct device *dev, struct regmap *regmap) cs42l51->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); - if (IS_ERR(cs42l51->reset_gpio)) - return PTR_ERR(cs42l51->reset_gpio); + if (IS_ERR(cs42l51->reset_gpio)) { + ret = PTR_ERR(cs42l51->reset_gpio); + goto error; + } if (cs42l51->reset_gpio) { dev_dbg(dev, "Release reset gpio\n"); @@ -780,6 +782,7 @@ int cs42l51_probe(struct device *dev, struct regmap *regmap) return 0; error: + gpiod_set_value_cansleep(cs42l51->reset_gpio, 1); regulator_bulk_disable(ARRAY_SIZE(cs42l51->supplies), cs42l51->supplies); return ret; diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index ef7a70fa6966..febbbe073962 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -202,12 +202,14 @@ #define CDC_RX_RXn_RX_PATH_SEC3(rx, n) (0x042c + rx->rxn_reg_stride * n) #define CDC_RX_RX0_RX_PATH_SEC4 (0x0430) #define CDC_RX_RX0_RX_PATH_SEC7 (0x0434) -#define CDC_RX_RXn_RX_PATH_SEC7(rx, n) (0x0434 + rx->rxn_reg_stride * n) +#define CDC_RX_RXn_RX_PATH_SEC7(rx, n) \ + (0x0434 + (rx->rxn_reg_stride * n) + ((n > 1) ? rx->rxn_reg_stride2 : 0)) #define CDC_RX_DSM_OUT_DELAY_SEL_MASK GENMASK(2, 0) #define CDC_RX_DSM_OUT_DELAY_TWO_SAMPLE 0x2 #define CDC_RX_RX0_RX_PATH_MIX_SEC0 (0x0438) #define CDC_RX_RX0_RX_PATH_MIX_SEC1 (0x043C) -#define CDC_RX_RXn_RX_PATH_DSM_CTL(rx, n) (0x0440 + rx->rxn_reg_stride * n) +#define CDC_RX_RXn_RX_PATH_DSM_CTL(rx, n) \ + (0x0440 + (rx->rxn_reg_stride * n) + ((n > 1) ? rx->rxn_reg_stride2 : 0)) #define CDC_RX_RXn_DSM_CLK_EN_MASK BIT(0) #define CDC_RX_RX0_RX_PATH_DSM_CTL (0x0440) #define CDC_RX_RX0_RX_PATH_DSM_DATA1 (0x0444) @@ -645,6 +647,7 @@ struct rx_macro { int rx_mclk_cnt; enum lpass_codec_version codec_version; int rxn_reg_stride; + int rxn_reg_stride2; bool is_ear_mode_on; bool hph_pwr_mode; bool hph_hd2_mode; @@ -1929,9 +1932,6 @@ static int rx_macro_digital_mute(struct snd_soc_dai *dai, int mute, int stream) CDC_RX_PATH_PGA_MUTE_MASK, 0x0); } - if (j == INTERP_AUX) - dsm_reg = CDC_RX_RXn_RX_PATH_DSM_CTL(rx, 2); - int_mux_cfg0 = CDC_RX_INP_MUX_RX_INT0_CFG0 + j * 8; int_mux_cfg1 = int_mux_cfg0 + 4; int_mux_cfg0_val = snd_soc_component_read(component, int_mux_cfg0); @@ -2702,9 +2702,6 @@ static int rx_macro_enable_interp_clk(struct snd_soc_component *component, main_reg = CDC_RX_RXn_RX_PATH_CTL(rx, interp_idx); dsm_reg = CDC_RX_RXn_RX_PATH_DSM_CTL(rx, interp_idx); - if (interp_idx == INTERP_AUX) - dsm_reg = CDC_RX_RXn_RX_PATH_DSM_CTL(rx, 2); - rx_cfg2_reg = CDC_RX_RXn_RX_PATH_CFG2(rx, interp_idx); if (SND_SOC_DAPM_EVENT_ON(event)) { @@ -3821,6 +3818,7 @@ static int rx_macro_probe(struct platform_device *pdev) case LPASS_CODEC_VERSION_2_0: case LPASS_CODEC_VERSION_2_1: rx->rxn_reg_stride = 0x80; + rx->rxn_reg_stride2 = 0xc; def_count = ARRAY_SIZE(rx_defaults) + ARRAY_SIZE(rx_pre_2_5_defaults); reg_defaults = kmalloc_array(def_count, sizeof(struct reg_default), GFP_KERNEL); if (!reg_defaults) @@ -3834,6 +3832,7 @@ static int rx_macro_probe(struct platform_device *pdev) case LPASS_CODEC_VERSION_2_7: case LPASS_CODEC_VERSION_2_8: rx->rxn_reg_stride = 0xc0; + rx->rxn_reg_stride2 = 0x0; def_count = ARRAY_SIZE(rx_defaults) + ARRAY_SIZE(rx_2_5_defaults); reg_defaults = kmalloc_array(def_count, sizeof(struct reg_default), GFP_KERNEL); if (!reg_defaults) diff --git a/sound/soc/codecs/max98388.c b/sound/soc/codecs/max98388.c index b847d7c59ec0..99986090b4a6 100644 --- a/sound/soc/codecs/max98388.c +++ b/sound/soc/codecs/max98388.c @@ -763,6 +763,7 @@ static int max98388_dai_tdm_slot(struct snd_soc_dai *dai, addr = MAX98388_R2044_PCM_TX_CTRL1 + (cnt / 8); bits = cnt % 8; regmap_update_bits(max98388->regmap, addr, bits, bits); + slot_found++; if (slot_found >= MAX_NUM_CH) break; } diff --git a/sound/soc/codecs/pcm3060-i2c.c b/sound/soc/codecs/pcm3060-i2c.c index 5330cf46b127..3816b25a8ead 100644 --- a/sound/soc/codecs/pcm3060-i2c.c +++ b/sound/soc/codecs/pcm3060-i2c.c @@ -2,7 +2,7 @@ // // PCM3060 I2C driver // -// Copyright (C) 2018 Kirill Marinushkin <[email protected]> +// Copyright (C) 2018 Kirill Marinushkin <[email protected]> #include <linux/i2c.h> #include <linux/module.h> @@ -55,5 +55,5 @@ static struct i2c_driver pcm3060_i2c_driver = { module_i2c_driver(pcm3060_i2c_driver); MODULE_DESCRIPTION("PCM3060 I2C driver"); -MODULE_AUTHOR("Kirill Marinushkin <[email protected]>"); +MODULE_AUTHOR("Kirill Marinushkin <[email protected]>"); MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/codecs/pcm3060-spi.c b/sound/soc/codecs/pcm3060-spi.c index 3b79734b832b..6095841f2f56 100644 --- a/sound/soc/codecs/pcm3060-spi.c +++ b/sound/soc/codecs/pcm3060-spi.c @@ -2,7 +2,7 @@ // // PCM3060 SPI driver // -// Copyright (C) 2018 Kirill Marinushkin <[email protected]> +// Copyright (C) 2018 Kirill Marinushkin <[email protected]> #include <linux/module.h> #include <linux/spi/spi.h> @@ -55,5 +55,5 @@ static struct spi_driver pcm3060_spi_driver = { module_spi_driver(pcm3060_spi_driver); MODULE_DESCRIPTION("PCM3060 SPI driver"); -MODULE_AUTHOR("Kirill Marinushkin <[email protected]>"); +MODULE_AUTHOR("Kirill Marinushkin <[email protected]>"); MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/codecs/pcm3060.c b/sound/soc/codecs/pcm3060.c index 586ec8c7246c..8974200652e7 100644 --- a/sound/soc/codecs/pcm3060.c +++ b/sound/soc/codecs/pcm3060.c @@ -2,7 +2,7 @@ // // PCM3060 codec driver // -// Copyright (C) 2018 Kirill Marinushkin <[email protected]> +// Copyright (C) 2018 Kirill Marinushkin <[email protected]> #include <linux/module.h> #include <sound/pcm_params.h> @@ -343,5 +343,5 @@ int pcm3060_probe(struct device *dev) EXPORT_SYMBOL(pcm3060_probe); MODULE_DESCRIPTION("PCM3060 codec driver"); -MODULE_AUTHOR("Kirill Marinushkin <[email protected]>"); +MODULE_AUTHOR("Kirill Marinushkin <[email protected]>"); MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/codecs/pcm3060.h b/sound/soc/codecs/pcm3060.h index 5e1185e7b03d..1b96835600b4 100644 --- a/sound/soc/codecs/pcm3060.h +++ b/sound/soc/codecs/pcm3060.h @@ -2,7 +2,7 @@ /* * PCM3060 codec driver * - * Copyright (C) 2018 Kirill Marinushkin <[email protected]> + * Copyright (C) 2018 Kirill Marinushkin <[email protected]> */ #ifndef _SND_SOC_PCM3060_H diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index 16f3425a3e35..855139348edb 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -2419,10 +2419,20 @@ static irqreturn_t rt5640_jd_gpio_irq(int irq, void *data) return IRQ_HANDLED; } -static void rt5640_cancel_work(void *data) +static void rt5640_disable_irq_and_cancel_work(void *data) { struct rt5640_priv *rt5640 = data; + if (rt5640->jd_gpio_irq_requested) { + free_irq(rt5640->jd_gpio_irq, rt5640); + rt5640->jd_gpio_irq_requested = false; + } + + if (rt5640->irq_requested) { + free_irq(rt5640->irq, rt5640); + rt5640->irq_requested = false; + } + cancel_delayed_work_sync(&rt5640->jack_work); cancel_delayed_work_sync(&rt5640->bp_work); } @@ -2463,13 +2473,7 @@ static void rt5640_disable_jack_detect(struct snd_soc_component *component) if (!rt5640->jack) return; - if (rt5640->jd_gpio_irq_requested) - free_irq(rt5640->jd_gpio_irq, rt5640); - - if (rt5640->irq_requested) - free_irq(rt5640->irq, rt5640); - - rt5640_cancel_work(rt5640); + rt5640_disable_irq_and_cancel_work(rt5640); if (rt5640->jack->status & SND_JACK_MICROPHONE) { rt5640_disable_micbias1_ovcd_irq(component); @@ -2477,8 +2481,6 @@ static void rt5640_disable_jack_detect(struct snd_soc_component *component) snd_soc_jack_report(rt5640->jack, 0, SND_JACK_BTN_0); } - rt5640->jd_gpio_irq_requested = false; - rt5640->irq_requested = false; rt5640->jd_gpio = NULL; rt5640->jack = NULL; } @@ -2798,7 +2800,8 @@ static int rt5640_suspend(struct snd_soc_component *component) if (rt5640->jack) { /* disable jack interrupts during system suspend */ disable_irq(rt5640->irq); - rt5640_cancel_work(rt5640); + cancel_delayed_work_sync(&rt5640->jack_work); + cancel_delayed_work_sync(&rt5640->bp_work); } snd_soc_component_force_bias_level(component, SND_SOC_BIAS_OFF); @@ -3032,7 +3035,7 @@ static int rt5640_i2c_probe(struct i2c_client *i2c) INIT_DELAYED_WORK(&rt5640->jack_work, rt5640_jack_work); /* Make sure work is stopped on probe-error / remove */ - ret = devm_add_action_or_reset(&i2c->dev, rt5640_cancel_work, rt5640); + ret = devm_add_action_or_reset(&i2c->dev, rt5640_disable_irq_and_cancel_work, rt5640); if (ret) return ret; diff --git a/sound/soc/codecs/rt722-sdca-sdw.c b/sound/soc/codecs/rt722-sdca-sdw.c index 87354bb1564e..d5c985ff5ac5 100644 --- a/sound/soc/codecs/rt722-sdca-sdw.c +++ b/sound/soc/codecs/rt722-sdca-sdw.c @@ -253,7 +253,7 @@ static int rt722_sdca_read_prop(struct sdw_slave *slave) } /* set the timeout values */ - prop->clk_stop_timeout = 200; + prop->clk_stop_timeout = 900; /* wake-up event */ prop->wake_capable = 1; diff --git a/sound/soc/codecs/wcd937x.c b/sound/soc/codecs/wcd937x.c index 45f32d281908..08fb13a334a4 100644 --- a/sound/soc/codecs/wcd937x.c +++ b/sound/soc/codecs/wcd937x.c @@ -715,12 +715,17 @@ static int wcd937x_codec_enable_aux_pa(struct snd_soc_dapm_widget *w, struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); struct wcd937x_priv *wcd937x = snd_soc_component_get_drvdata(component); int hph_mode = wcd937x->hph_mode; + u8 val; switch (event) { case SND_SOC_DAPM_PRE_PMU: + val = WCD937X_DIGITAL_PDM_WD_CTL2_EN | + WCD937X_DIGITAL_PDM_WD_CTL2_TIMEOUT_SEL | + WCD937X_DIGITAL_PDM_WD_CTL2_HOLD_OFF; snd_soc_component_update_bits(component, WCD937X_DIGITAL_PDM_WD_CTL2, - BIT(0), BIT(0)); + WCD937X_DIGITAL_PDM_WD_CTL2_MASK, + val); break; case SND_SOC_DAPM_POST_PMU: usleep_range(1000, 1010); @@ -741,7 +746,8 @@ static int wcd937x_codec_enable_aux_pa(struct snd_soc_dapm_widget *w, hph_mode); snd_soc_component_update_bits(component, WCD937X_DIGITAL_PDM_WD_CTL2, - BIT(0), 0x00); + WCD937X_DIGITAL_PDM_WD_CTL2_MASK, + 0x00); break; } @@ -2049,6 +2055,8 @@ static const struct snd_kcontrol_new wcd937x_snd_controls[] = { wcd937x_get_swr_port, wcd937x_set_swr_port), SOC_SINGLE_EXT("HPHR Switch", WCD937X_HPH_R, 0, 1, 0, wcd937x_get_swr_port, wcd937x_set_swr_port), + SOC_SINGLE_EXT("LO Switch", WCD937X_LO, 0, 1, 0, + wcd937x_get_swr_port, wcd937x_set_swr_port), SOC_SINGLE_EXT("ADC1 Switch", WCD937X_ADC1, 1, 1, 0, wcd937x_get_swr_port, wcd937x_set_swr_port), diff --git a/sound/soc/codecs/wcd937x.h b/sound/soc/codecs/wcd937x.h index 35f3d48bd7dd..4afa48dcaf74 100644 --- a/sound/soc/codecs/wcd937x.h +++ b/sound/soc/codecs/wcd937x.h @@ -391,6 +391,10 @@ #define WCD937X_DIGITAL_PDM_WD_CTL0 0x3465 #define WCD937X_DIGITAL_PDM_WD_CTL1 0x3466 #define WCD937X_DIGITAL_PDM_WD_CTL2 0x3467 +#define WCD937X_DIGITAL_PDM_WD_CTL2_HOLD_OFF BIT(2) +#define WCD937X_DIGITAL_PDM_WD_CTL2_TIMEOUT_SEL BIT(1) +#define WCD937X_DIGITAL_PDM_WD_CTL2_EN BIT(0) +#define WCD937X_DIGITAL_PDM_WD_CTL2_MASK GENMASK(2, 0) #define WCD937X_DIGITAL_INTR_MODE 0x346A #define WCD937X_DIGITAL_INTR_MASK_0 0x346B #define WCD937X_DIGITAL_INTR_MASK_1 0x346C diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c index a65f5b9935a2..0b247f16a163 100644 --- a/sound/soc/fsl/fsl_esai.c +++ b/sound/soc/fsl/fsl_esai.c @@ -119,10 +119,10 @@ static irqreturn_t esai_isr(int irq, void *devid) dev_dbg(&pdev->dev, "isr: Transmission Initialized\n"); if (esr & ESAI_ESR_RFF_MASK) - dev_warn(&pdev->dev, "isr: Receiving overrun\n"); + dev_dbg(&pdev->dev, "isr: Receiving overrun\n"); if (esr & ESAI_ESR_TFE_MASK) - dev_warn(&pdev->dev, "isr: Transmission underrun\n"); + dev_dbg(&pdev->dev, "isr: Transmission underrun\n"); if (esr & ESAI_ESR_TLS_MASK) dev_dbg(&pdev->dev, "isr: Just transmitted the last slot\n"); diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 193be098fa5e..0c71a73476df 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -28,6 +28,13 @@ #define MICFIL_OSR_DEFAULT 16 +#define MICFIL_NUM_RATES 7 +#define MICFIL_CLK_SRC_NUM 3 +/* clock source ids */ +#define MICFIL_AUDIO_PLL1 0 +#define MICFIL_AUDIO_PLL2 1 +#define MICFIL_CLK_EXT3 2 + enum quality { QUALITY_HIGH, QUALITY_MEDIUM, @@ -45,9 +52,12 @@ struct fsl_micfil { struct clk *mclk; struct clk *pll8k_clk; struct clk *pll11k_clk; + struct clk *clk_src[MICFIL_CLK_SRC_NUM]; struct snd_dmaengine_dai_dma_data dma_params_rx; struct sdma_peripheral_config sdmacfg; struct snd_soc_card *card; + struct snd_pcm_hw_constraint_list constraint_rates; + unsigned int constraint_rates_list[MICFIL_NUM_RATES]; unsigned int dataline; char name[32]; int irq[MICFIL_IRQ_LINES]; @@ -67,6 +77,7 @@ struct fsl_micfil_soc_data { bool imx; bool use_edma; bool use_verid; + bool volume_sx; u64 formats; }; @@ -76,6 +87,7 @@ static struct fsl_micfil_soc_data fsl_micfil_imx8mm = { .fifo_depth = 8, .dataline = 0xf, .formats = SNDRV_PCM_FMTBIT_S16_LE, + .volume_sx = true, }; static struct fsl_micfil_soc_data fsl_micfil_imx8mp = { @@ -84,6 +96,7 @@ static struct fsl_micfil_soc_data fsl_micfil_imx8mp = { .fifo_depth = 32, .dataline = 0xf, .formats = SNDRV_PCM_FMTBIT_S32_LE, + .volume_sx = false, }; static struct fsl_micfil_soc_data fsl_micfil_imx93 = { @@ -94,6 +107,7 @@ static struct fsl_micfil_soc_data fsl_micfil_imx93 = { .formats = SNDRV_PCM_FMTBIT_S32_LE, .use_edma = true, .use_verid = true, + .volume_sx = false, }; static const struct of_device_id fsl_micfil_dt_ids[] = { @@ -317,7 +331,26 @@ static int hwvad_detected(struct snd_kcontrol *kcontrol, return 0; } -static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = { +static const struct snd_kcontrol_new fsl_micfil_volume_controls[] = { + SOC_SINGLE_TLV("CH0 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(0), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH1 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(1), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH2 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(2), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH3 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(3), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH4 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(4), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH5 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(5), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH6 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(6), 0xF, 0, gain_tlv), + SOC_SINGLE_TLV("CH7 Volume", REG_MICFIL_OUT_CTRL, + MICFIL_OUTGAIN_CHX_SHIFT(7), 0xF, 0, gain_tlv), +}; + +static const struct snd_kcontrol_new fsl_micfil_volume_sx_controls[] = { SOC_SINGLE_SX_TLV("CH0 Volume", REG_MICFIL_OUT_CTRL, MICFIL_OUTGAIN_CHX_SHIFT(0), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH1 Volume", REG_MICFIL_OUT_CTRL, @@ -334,6 +367,9 @@ static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = { MICFIL_OUTGAIN_CHX_SHIFT(6), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH7 Volume", REG_MICFIL_OUT_CTRL, MICFIL_OUTGAIN_CHX_SHIFT(7), 0x8, 0xF, gain_tlv), +}; + +static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = { SOC_ENUM_EXT("MICFIL Quality Select", fsl_micfil_quality_enum, micfil_quality_get, micfil_quality_set), @@ -449,12 +485,34 @@ static int fsl_micfil_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct fsl_micfil *micfil = snd_soc_dai_get_drvdata(dai); + unsigned int rates[MICFIL_NUM_RATES] = {8000, 11025, 16000, 22050, 32000, 44100, 48000}; + int i, j, k = 0; + u64 clk_rate; if (!micfil) { dev_err(dai->dev, "micfil dai priv_data not set\n"); return -EINVAL; } + micfil->constraint_rates.list = micfil->constraint_rates_list; + micfil->constraint_rates.count = 0; + + for (j = 0; j < MICFIL_NUM_RATES; j++) { + for (i = 0; i < MICFIL_CLK_SRC_NUM; i++) { + clk_rate = clk_get_rate(micfil->clk_src[i]); + if (clk_rate != 0 && do_div(clk_rate, rates[j]) == 0) { + micfil->constraint_rates_list[k++] = rates[j]; + micfil->constraint_rates.count++; + break; + } + } + } + + if (micfil->constraint_rates.count > 0) + snd_pcm_hw_constraint_list(substream->runtime, 0, + SNDRV_PCM_HW_PARAM_RATE, + &micfil->constraint_rates); + return 0; } @@ -801,6 +859,20 @@ static int fsl_micfil_dai_probe(struct snd_soc_dai *cpu_dai) return 0; } +static int fsl_micfil_component_probe(struct snd_soc_component *component) +{ + struct fsl_micfil *micfil = snd_soc_component_get_drvdata(component); + + if (micfil->soc->volume_sx) + snd_soc_add_component_controls(component, fsl_micfil_volume_sx_controls, + ARRAY_SIZE(fsl_micfil_volume_sx_controls)); + else + snd_soc_add_component_controls(component, fsl_micfil_volume_controls, + ARRAY_SIZE(fsl_micfil_volume_controls)); + + return 0; +} + static const struct snd_soc_dai_ops fsl_micfil_dai_ops = { .probe = fsl_micfil_dai_probe, .startup = fsl_micfil_startup, @@ -821,6 +893,7 @@ static struct snd_soc_dai_driver fsl_micfil_dai = { static const struct snd_soc_component_driver fsl_micfil_component = { .name = "fsl-micfil-dai", + .probe = fsl_micfil_component_probe, .controls = fsl_micfil_snd_controls, .num_controls = ARRAY_SIZE(fsl_micfil_snd_controls), .legacy_dai_naming = 1, @@ -1134,6 +1207,12 @@ static int fsl_micfil_probe(struct platform_device *pdev) fsl_asoc_get_pll_clocks(&pdev->dev, &micfil->pll8k_clk, &micfil->pll11k_clk); + micfil->clk_src[MICFIL_AUDIO_PLL1] = micfil->pll8k_clk; + micfil->clk_src[MICFIL_AUDIO_PLL2] = micfil->pll11k_clk; + micfil->clk_src[MICFIL_CLK_EXT3] = devm_clk_get(&pdev->dev, "clkext3"); + if (IS_ERR(micfil->clk_src[MICFIL_CLK_EXT3])) + micfil->clk_src[MICFIL_CLK_EXT3] = NULL; + /* init regmap */ regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(regs)) diff --git a/sound/soc/intel/atom/sst/sst_acpi.c b/sound/soc/intel/atom/sst/sst_acpi.c index 9956dc63db74..257180630475 100644 --- a/sound/soc/intel/atom/sst/sst_acpi.c +++ b/sound/soc/intel/atom/sst/sst_acpi.c @@ -125,6 +125,28 @@ static const struct sst_res_info bytcr_res_info = { .acpi_ipc_irq_index = 0 }; +/* For "LPE0F28" ACPI device found on some Android factory OS models */ +static const struct sst_res_info lpe8086_res_info = { + .shim_offset = 0x140000, + .shim_size = 0x000100, + .shim_phy_addr = SST_BYT_SHIM_PHY_ADDR, + .ssp0_offset = 0xa0000, + .ssp0_size = 0x1000, + .dma0_offset = 0x98000, + .dma0_size = 0x4000, + .dma1_offset = 0x9c000, + .dma1_size = 0x4000, + .iram_offset = 0x0c0000, + .iram_size = 0x14000, + .dram_offset = 0x100000, + .dram_size = 0x28000, + .mbox_offset = 0x144000, + .mbox_size = 0x1000, + .acpi_lpe_res_index = 1, + .acpi_ddr_index = 0, + .acpi_ipc_irq_index = 0 +}; + static struct sst_platform_info byt_rvp_platform_data = { .probe_data = &byt_fwparse_info, .ipc_info = &byt_ipc_info, @@ -268,10 +290,38 @@ static int sst_acpi_probe(struct platform_device *pdev) mach->pdata = &chv_platform_data; pdata = mach->pdata; - ret = kstrtouint(id->id, 16, &dev_id); - if (ret < 0) { - dev_err(dev, "Unique device id conversion error: %d\n", ret); - return ret; + if (!strcmp(id->id, "LPE0F28")) { + struct resource *rsrc; + + /* Use regular BYT SST PCI VID:PID */ + dev_id = 0x80860F28; + byt_rvp_platform_data.res_info = &lpe8086_res_info; + + /* + * The "LPE0F28" ACPI device has separate IO-mem resources for: + * DDR, SHIM, MBOX, IRAM, DRAM, CFG + * None of which covers the entire LPE base address range. + * lpe8086_res_info.acpi_lpe_res_index points to the SHIM. + * Patch this to cover the entire base address range as expected + * by sst_platform_get_resources(). + */ + rsrc = platform_get_resource(pdev, IORESOURCE_MEM, + pdata->res_info->acpi_lpe_res_index); + if (!rsrc) { + dev_err(dev, "Invalid SHIM base\n"); + return -EIO; + } + rsrc->start -= pdata->res_info->shim_offset; + rsrc->end = rsrc->start + 0x200000 - 1; + } else { + ret = kstrtouint(id->id, 16, &dev_id); + if (ret < 0) { + dev_err(dev, "Unique device id conversion error: %d\n", ret); + return ret; + } + + if (soc_intel_is_byt_cr(pdev)) + byt_rvp_platform_data.res_info = &bytcr_res_info; } dev_dbg(dev, "ACPI device id: %x\n", dev_id); @@ -280,11 +330,6 @@ static int sst_acpi_probe(struct platform_device *pdev) if (ret < 0) return ret; - if (soc_intel_is_byt_cr(pdev)) { - /* override resource info */ - byt_rvp_platform_data.res_info = &bytcr_res_info; - } - /* update machine parameters */ mach->mach_params.acpi_ipc_irq_index = pdata->res_info->acpi_ipc_irq_index; @@ -344,6 +389,7 @@ static void sst_acpi_remove(struct platform_device *pdev) } static const struct acpi_device_id sst_acpi_ids[] = { + { "LPE0F28", (unsigned long)&snd_soc_acpi_intel_baytrail_machines}, { "80860F28", (unsigned long)&snd_soc_acpi_intel_baytrail_machines}, { "808622A8", (unsigned long)&snd_soc_acpi_intel_cherrytrail_machines}, { }, diff --git a/sound/soc/intel/avs/core.c b/sound/soc/intel/avs/core.c index da7bac09acb4..73d4bde9b2f7 100644 --- a/sound/soc/intel/avs/core.c +++ b/sound/soc/intel/avs/core.c @@ -28,6 +28,7 @@ #include "avs.h" #include "cldma.h" #include "messages.h" +#include "pcm.h" static u32 pgctl_mask = AZX_PGCTL_LSRMD_MASK; module_param(pgctl_mask, uint, 0444); @@ -247,7 +248,7 @@ static void hdac_stream_update_pos(struct hdac_stream *stream, u64 buffer_size) static void hdac_update_stream(struct hdac_bus *bus, struct hdac_stream *stream) { if (stream->substream) { - snd_pcm_period_elapsed(stream->substream); + avs_period_elapsed(stream->substream); } else if (stream->cstream) { u64 buffer_size = stream->cstream->runtime->buffer_size; diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c index afc0fc74cf94..4af811580356 100644 --- a/sound/soc/intel/avs/pcm.c +++ b/sound/soc/intel/avs/pcm.c @@ -16,6 +16,7 @@ #include <sound/soc-component.h> #include "avs.h" #include "path.h" +#include "pcm.h" #include "topology.h" #include "../../codecs/hda.h" @@ -30,6 +31,7 @@ struct avs_dma_data { struct hdac_ext_stream *host_stream; }; + struct work_struct period_elapsed_work; struct snd_pcm_substream *substream; }; @@ -56,6 +58,22 @@ avs_dai_find_path_template(struct snd_soc_dai *dai, bool is_fe, int direction) return dw->priv; } +static void avs_period_elapsed_work(struct work_struct *work) +{ + struct avs_dma_data *data = container_of(work, struct avs_dma_data, period_elapsed_work); + + snd_pcm_period_elapsed(data->substream); +} + +void avs_period_elapsed(struct snd_pcm_substream *substream) +{ + struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); + struct snd_soc_dai *dai = snd_soc_rtd_to_cpu(rtd, 0); + struct avs_dma_data *data = snd_soc_dai_get_dma_data(dai, substream); + + schedule_work(&data->period_elapsed_work); +} + static int avs_dai_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); @@ -77,6 +95,7 @@ static int avs_dai_startup(struct snd_pcm_substream *substream, struct snd_soc_d data->substream = substream; data->template = template; data->adev = adev; + INIT_WORK(&data->period_elapsed_work, avs_period_elapsed_work); snd_soc_dai_set_dma_data(dai, substream, data); if (rtd->dai_link->ignore_suspend) diff --git a/sound/soc/intel/avs/pcm.h b/sound/soc/intel/avs/pcm.h new file mode 100644 index 000000000000..0f3615c90398 --- /dev/null +++ b/sound/soc/intel/avs/pcm.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright(c) 2024 Intel Corporation + * + * Authors: Cezary Rojewski <[email protected]> + * Amadeusz Slawinski <[email protected]> + */ + +#ifndef __SOUND_SOC_INTEL_AVS_PCM_H +#define __SOUND_SOC_INTEL_AVS_PCM_H + +#include <sound/pcm.h> + +void avs_period_elapsed(struct snd_pcm_substream *substream); + +#endif diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 2ed49acb4e36..54f77f57ec8e 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -17,6 +17,7 @@ #include <linux/acpi.h> #include <linux/clk.h> #include <linux/device.h> +#include <linux/device/bus.h> #include <linux/dmi.h> #include <linux/gpio/consumer.h> #include <linux/gpio/machine.h> @@ -32,6 +33,8 @@ #include "../atom/sst-atom-controls.h" #include "../common/soc-intel-quirks.h" +#define BYT_RT5640_FALLBACK_CODEC_DEV_NAME "i2c-rt5640" + enum { BYT_RT5640_DMIC1_MAP, BYT_RT5640_DMIC2_MAP, @@ -1129,6 +1132,21 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, + { /* Vexia Edu Atla 10 tablet */ + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"), + /* Above strings are too generic, also match on BIOS date */ + DMI_MATCH(DMI_BIOS_DATE, "08/25/2014"), + }, + .driver_data = (void *)(BYT_RT5640_IN1_MAP | + BYT_RT5640_JD_SRC_JD2_IN4N | + BYT_RT5640_OVCD_TH_2000UA | + BYT_RT5640_OVCD_SF_0P75 | + BYT_RT5640_DIFF_MIC | + BYT_RT5640_SSP0_AIF2 | + BYT_RT5640_MCLK_EN), + }, { /* Voyo Winpad A15 */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), @@ -1698,9 +1716,33 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) codec_dev = acpi_get_first_physical_node(adev); acpi_dev_put(adev); - if (!codec_dev) - return -EPROBE_DEFER; - priv->codec_dev = get_device(codec_dev); + + if (codec_dev) { + priv->codec_dev = get_device(codec_dev); + } else { + /* + * Special case for Android tablets where the codec i2c_client + * has been manually instantiated by x86_android_tablets.ko due + * to a broken DSDT. + */ + codec_dev = bus_find_device_by_name(&i2c_bus_type, NULL, + BYT_RT5640_FALLBACK_CODEC_DEV_NAME); + if (!codec_dev) + return -EPROBE_DEFER; + + if (!i2c_verify_client(codec_dev)) { + dev_err(dev, "Error '%s' is not an i2c_client\n", + BYT_RT5640_FALLBACK_CODEC_DEV_NAME); + put_device(codec_dev); + } + + /* fixup codec name */ + strscpy(byt_rt5640_codec_name, BYT_RT5640_FALLBACK_CODEC_DEV_NAME, + sizeof(byt_rt5640_codec_name)); + + /* bus_find_device() returns a reference no need to get() */ + priv->codec_dev = codec_dev; + } /* * swap SSP0 if bytcr is detected diff --git a/sound/soc/intel/common/soc-acpi-intel-lnl-match.c b/sound/soc/intel/common/soc-acpi-intel-lnl-match.c index 3c4e0c7ca8ee..094ed4b27cb0 100644 --- a/sound/soc/intel/common/soc-acpi-intel-lnl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-lnl-match.c @@ -225,6 +225,15 @@ static const struct snd_soc_acpi_adr_device rt1316_3_group1_adr[] = { } }; +static const struct snd_soc_acpi_adr_device rt1318_1_adr[] = { + { + .adr = 0x000133025D131801ull, + .num_endpoints = 1, + .endpoints = &single_endpoint, + .name_prefix = "rt1318-1" + } +}; + static const struct snd_soc_acpi_adr_device rt1318_1_group1_adr[] = { { .adr = 0x000130025D131801ull, @@ -243,6 +252,15 @@ static const struct snd_soc_acpi_adr_device rt1318_2_group1_adr[] = { } }; +static const struct snd_soc_acpi_adr_device rt713_0_adr[] = { + { + .adr = 0x000031025D071301ull, + .num_endpoints = 1, + .endpoints = &single_endpoint, + .name_prefix = "rt713" + } +}; + static const struct snd_soc_acpi_adr_device rt714_0_adr[] = { { .adr = 0x000030025D071401ull, @@ -378,6 +396,20 @@ static const struct snd_soc_acpi_link_adr lnl_sdw_rt1318_l12_rt714_l0[] = { {} }; +static const struct snd_soc_acpi_link_adr lnl_sdw_rt713_l0_rt1318_l1[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(rt713_0_adr), + .adr_d = rt713_0_adr, + }, + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(rt1318_1_adr), + .adr_d = rt1318_1_adr, + }, + {} +}; + /* this table is used when there is no I2S codec present */ struct snd_soc_acpi_mach snd_soc_acpi_intel_lnl_sdw_machines[] = { /* mockup tests need to be first */ @@ -447,6 +479,12 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_lnl_sdw_machines[] = { .drv_name = "sof_sdw", .sof_tplg_filename = "sof-lnl-rt1318-l12-rt714-l0.tplg" }, + { + .link_mask = BIT(0) | BIT(1), + .links = lnl_sdw_rt713_l0_rt1318_l1, + .drv_name = "sof_sdw", + .sof_tplg_filename = "sof-lnl-rt713-l0-rt1318-l1.tplg" + }, {}, }; EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_lnl_sdw_machines); diff --git a/sound/soc/loongson/loongson_card.c b/sound/soc/loongson/loongson_card.c index 7379f24d385c..7910d5d9ac4f 100644 --- a/sound/soc/loongson/loongson_card.c +++ b/sound/soc/loongson/loongson_card.c @@ -144,6 +144,7 @@ static int loongson_card_parse_of(struct loongson_card_data *data) dev_err(dev, "getting cpu dlc error (%d)\n", ret); goto err; } + loongson_dai_links[i].platforms->of_node = loongson_dai_links[i].cpus->of_node; ret = snd_soc_of_get_dlc(codec, NULL, loongson_dai_links[i].codecs, 0); if (ret < 0) { diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig index 762491d6f2f2..ca7a30ebd26a 100644 --- a/sound/soc/qcom/Kconfig +++ b/sound/soc/qcom/Kconfig @@ -157,6 +157,7 @@ config SND_SOC_SDM845 depends on COMMON_CLK select SND_SOC_QDSP6 select SND_SOC_QCOM_COMMON + select SND_SOC_QCOM_SDW select SND_SOC_RT5663 select SND_SOC_MAX98927 imply SND_SOC_CROS_EC_CODEC @@ -208,6 +209,7 @@ config SND_SOC_SC7280 tristate "SoC Machine driver for SC7280 boards" depends on I2C && SOUNDWIRE select SND_SOC_QCOM_COMMON + select SND_SOC_QCOM_SDW select SND_SOC_LPASS_SC7280 select SND_SOC_MAX98357A select SND_SOC_WCD938X_SDW diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index 5a47f661e0c6..242bc16da36d 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -1242,6 +1242,8 @@ int asoc_qcom_lpass_cpu_platform_probe(struct platform_device *pdev) /* Allocation for i2sctl regmap fields */ drvdata->i2sctl = devm_kzalloc(&pdev->dev, sizeof(struct lpaif_i2sctl), GFP_KERNEL); + if (!drvdata->i2sctl) + return -ENOMEM; /* Initialize bitfields for dai I2SCTL register */ ret = lpass_cpu_init_i2sctl_bitfields(dev, drvdata->i2sctl, diff --git a/sound/soc/qcom/sc7280.c b/sound/soc/qcom/sc7280.c index 207ac5da4dd4..230af8d7b205 100644 --- a/sound/soc/qcom/sc7280.c +++ b/sound/soc/qcom/sc7280.c @@ -23,6 +23,7 @@ #include "common.h" #include "lpass.h" #include "qdsp6/q6afe.h" +#include "sdw.h" #define DEFAULT_MCLK_RATE 19200000 #define RT5682_PLL_FREQ (48000 * 512) @@ -316,6 +317,7 @@ static void sc7280_snd_shutdown(struct snd_pcm_substream *substream) struct snd_soc_card *card = rtd->card; struct sc7280_snd_data *data = snd_soc_card_get_drvdata(card); struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0); + struct sdw_stream_runtime *sruntime = data->sruntime[cpu_dai->id]; switch (cpu_dai->id) { case MI2S_PRIMARY: @@ -333,6 +335,9 @@ static void sc7280_snd_shutdown(struct snd_pcm_substream *substream) default: break; } + + data->sruntime[cpu_dai->id] = NULL; + sdw_release_stream(sruntime); } static int sc7280_snd_startup(struct snd_pcm_substream *substream) @@ -347,6 +352,8 @@ static int sc7280_snd_startup(struct snd_pcm_substream *substream) switch (cpu_dai->id) { case MI2S_PRIMARY: ret = sc7280_rt5682_init(rtd); + if (ret) + return ret; break; case SECONDARY_MI2S_RX: codec_dai_fmt |= SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_I2S; @@ -360,7 +367,8 @@ static int sc7280_snd_startup(struct snd_pcm_substream *substream) default: break; } - return ret; + + return qcom_snd_sdw_startup(substream); } static const struct snd_soc_ops sc7280_ops = { diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c index 75701546b6ea..a479d7e5b7fb 100644 --- a/sound/soc/qcom/sdm845.c +++ b/sound/soc/qcom/sdm845.c @@ -15,6 +15,7 @@ #include <uapi/linux/input-event-codes.h> #include "common.h" #include "qdsp6/q6afe.h" +#include "sdw.h" #include "../codecs/rt5663.h" #define DRIVER_NAME "sdm845" @@ -416,7 +417,7 @@ static int sdm845_snd_startup(struct snd_pcm_substream *substream) pr_err("%s: invalid dai id 0x%x\n", __func__, cpu_dai->id); break; } - return 0; + return qcom_snd_sdw_startup(substream); } static void sdm845_snd_shutdown(struct snd_pcm_substream *substream) @@ -425,6 +426,7 @@ static void sdm845_snd_shutdown(struct snd_pcm_substream *substream) struct snd_soc_card *card = rtd->card; struct sdm845_snd_data *data = snd_soc_card_get_drvdata(card); struct snd_soc_dai *cpu_dai = snd_soc_rtd_to_cpu(rtd, 0); + struct sdw_stream_runtime *sruntime = data->sruntime[cpu_dai->id]; switch (cpu_dai->id) { case PRIMARY_MI2S_RX: @@ -463,6 +465,9 @@ static void sdm845_snd_shutdown(struct snd_pcm_substream *substream) pr_err("%s: invalid dai id 0x%x\n", __func__, cpu_dai->id); break; } + + data->sruntime[cpu_dai->id] = NULL; + sdw_release_stream(sruntime); } static int sdm845_snd_prepare(struct snd_pcm_substream *substream) diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index 9784718a2b6f..eca5ce096e54 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -1281,7 +1281,9 @@ audio_graph: if (!of_node_name_eq(ports, "ports") && !of_node_name_eq(ports, "port")) continue; - priv->component_dais[i] = of_graph_get_endpoint_count(ports); + priv->component_dais[i] = + of_graph_get_endpoint_count(of_node_name_eq(ports, "ports") ? + ports : np); nr += priv->component_dais[i]; i++; if (i >= RSND_MAX_COMPONENT) { @@ -1493,7 +1495,8 @@ static int rsnd_dai_probe(struct rsnd_priv *priv) if (!of_node_name_eq(ports, "ports") && !of_node_name_eq(ports, "port")) continue; - for_each_endpoint_of_node(ports, dai_np) { + for_each_endpoint_of_node(of_node_name_eq(ports, "ports") ? + ports : np, dai_np) { __rsnd_dai_probe(priv, dai_np, dai_np, 0, dai_i); if (!rsnd_is_gen1(priv) && !rsnd_is_gen2(priv)) { rdai = rsnd_rdai_get(priv, dai_i); diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 9330f1a3f758..99521c784a9b 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1147,6 +1147,8 @@ static int dapm_widget_list_create(struct snd_soc_dapm_widget_list **list, if (*list == NULL) return -ENOMEM; + (*list)->num_widgets = size; + list_for_each_entry(w, widgets, work_list) (*list)->widgets[i++] = w; @@ -2785,10 +2787,10 @@ EXPORT_SYMBOL_GPL(snd_soc_dapm_update_dai); int snd_soc_dapm_widget_name_cmp(struct snd_soc_dapm_widget *widget, const char *s) { - struct snd_soc_component *component = snd_soc_dapm_to_component(widget->dapm); + struct snd_soc_component *component = widget->dapm->component; const char *wname = widget->name; - if (component->name_prefix) + if (component && component->name_prefix) wname += strlen(component->name_prefix) + 1; /* plus space */ return strcmp(wname, s); diff --git a/sound/soc/sof/amd/acp-loader.c b/sound/soc/sof/amd/acp-loader.c index 19f10dd77e4b..077af9e2af8d 100644 --- a/sound/soc/sof/amd/acp-loader.c +++ b/sound/soc/sof/amd/acp-loader.c @@ -206,7 +206,10 @@ int acp_dsp_pre_fw_run(struct snd_sof_dev *sdev) configure_pte_for_fw_loading(FW_SRAM_DATA_BIN, ACP_SRAM_PAGE_COUNT, adata); src_addr = ACP_SYSTEM_MEMORY_WINDOW + ACP_DEFAULT_SRAM_LENGTH + (page_count * ACP_PAGE_SIZE); - dest_addr = ACP_SRAM_BASE_ADDRESS; + if (adata->pci_rev > ACP63_PCI_ID) + dest_addr = ACP7X_SRAM_BASE_ADDRESS; + else + dest_addr = ACP_SRAM_BASE_ADDRESS; ret = configure_and_run_dma(adata, src_addr, dest_addr, adata->fw_sram_data_bin_size); diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c index d579c3849392..de3001f5b9bb 100644 --- a/sound/soc/sof/amd/acp.c +++ b/sound/soc/sof/amd/acp.c @@ -329,7 +329,9 @@ int configure_and_run_sha_dma(struct acp_dev_data *adata, void *image_addr, fw_qualifier, fw_qualifier & DSP_FW_RUN_ENABLE, ACP_REG_POLL_INTERVAL, ACP_DMA_COMPLETE_TIMEOUT_US); if (ret < 0) { - dev_err(sdev->dev, "PSP validation failed\n"); + val = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_SHA_PSP_ACK); + dev_err(sdev->dev, "PSP validation failed: fw_qualifier = %#x, ACP_SHA_PSP_ACK = %#x\n", + fw_qualifier, val); return ret; } diff --git a/sound/soc/sof/intel/hda-dai-ops.c b/sound/soc/sof/intel/hda-dai-ops.c index 484c76147885..92681ca7f24d 100644 --- a/sound/soc/sof/intel/hda-dai-ops.c +++ b/sound/soc/sof/intel/hda-dai-ops.c @@ -346,20 +346,21 @@ static int hda_trigger(struct snd_sof_dev *sdev, struct snd_soc_dai *cpu_dai, case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: snd_hdac_ext_stream_start(hext_stream); break; - case SNDRV_PCM_TRIGGER_SUSPEND: - case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - snd_hdac_ext_stream_clear(hext_stream); - /* - * Save the LLP registers in case the stream is - * restarting due PAUSE_RELEASE, or START without a pcm - * close/open since in this case the LLP register is not reset - * to 0 and the delay calculation will return with invalid - * results. + * Save the LLP registers since in case of PAUSE the LLP + * register are not reset to 0, the delay calculation will use + * the saved offsets for compensating the delay calculation. */ hext_stream->pplcllpl = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPL); hext_stream->pplcllpu = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPU); + snd_hdac_ext_stream_clear(hext_stream); + break; + case SNDRV_PCM_TRIGGER_SUSPEND: + case SNDRV_PCM_TRIGGER_STOP: + hext_stream->pplcllpl = 0; + hext_stream->pplcllpu = 0; + snd_hdac_ext_stream_clear(hext_stream); break; default: dev_err(sdev->dev, "unknown trigger command %d\n", cmd); @@ -512,7 +513,6 @@ static const struct hda_dai_widget_dma_ops sdw_ipc4_chain_dma_ops = { static int hda_ipc3_post_trigger(struct snd_sof_dev *sdev, struct snd_soc_dai *cpu_dai, struct snd_pcm_substream *substream, int cmd) { - struct hdac_ext_stream *hext_stream = hda_get_hext_stream(sdev, cpu_dai, substream); struct snd_soc_dapm_widget *w = snd_soc_dai_get_widget(cpu_dai, substream->stream); switch (cmd) { @@ -527,9 +527,6 @@ static int hda_ipc3_post_trigger(struct snd_sof_dev *sdev, struct snd_soc_dai *c if (ret < 0) return ret; - if (cmd == SNDRV_PCM_TRIGGER_STOP) - return hda_link_dma_cleanup(substream, hext_stream, cpu_dai); - break; } case SNDRV_PCM_TRIGGER_PAUSE_PUSH: diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index 1c823f9eea57..ac505c7ad342 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -302,6 +302,7 @@ static int __maybe_unused hda_dai_trigger(struct snd_pcm_substream *substream, i } switch (cmd) { + case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: ret = hda_link_dma_cleanup(substream, hext_stream, dai); if (ret < 0) { @@ -370,6 +371,13 @@ static int non_hda_dai_hw_params_data(struct snd_pcm_substream *substream, return -EINVAL; } + sdev = widget_to_sdev(w); + hext_stream = ops->get_hext_stream(sdev, cpu_dai, substream); + + /* nothing more to do if the link is already prepared */ + if (hext_stream && hext_stream->link_prepared) + return 0; + /* use HDaudio stream handling */ ret = hda_dai_hw_params_data(substream, params, cpu_dai, data, flags); if (ret < 0) { @@ -377,7 +385,6 @@ static int non_hda_dai_hw_params_data(struct snd_pcm_substream *substream, return ret; } - sdev = widget_to_sdev(w); if (sdev->dspless_mode_selected) return 0; @@ -482,6 +489,31 @@ int sdw_hda_dai_hw_params(struct snd_pcm_substream *substream, int ret; int i; + ops = hda_dai_get_ops(substream, cpu_dai); + if (!ops) { + dev_err(cpu_dai->dev, "DAI widget ops not set\n"); + return -EINVAL; + } + + sdev = widget_to_sdev(w); + hext_stream = ops->get_hext_stream(sdev, cpu_dai, substream); + + /* nothing more to do if the link is already prepared */ + if (hext_stream && hext_stream->link_prepared) + return 0; + + /* + * reset the PCMSyCM registers to handle a prepare callback when the PCM is restarted + * due to xruns or after a call to snd_pcm_drain/drop() + */ + ret = hdac_bus_eml_sdw_map_stream_ch(sof_to_bus(sdev), link_id, cpu_dai->id, + 0, 0, substream->stream); + if (ret < 0) { + dev_err(cpu_dai->dev, "%s: hdac_bus_eml_sdw_map_stream_ch failed %d\n", + __func__, ret); + return ret; + } + data.dai_index = (link_id << 8) | cpu_dai->id; data.dai_node_id = intel_alh_id; ret = non_hda_dai_hw_params_data(substream, params, cpu_dai, &data, flags); @@ -490,10 +522,7 @@ int sdw_hda_dai_hw_params(struct snd_pcm_substream *substream, return ret; } - ops = hda_dai_get_ops(substream, cpu_dai); - sdev = widget_to_sdev(w); hext_stream = ops->get_hext_stream(sdev, cpu_dai, substream); - if (!hext_stream) return -ENODEV; diff --git a/sound/soc/sof/intel/hda-loader.c b/sound/soc/sof/intel/hda-loader.c index 75f6240cf3e1..9d8ebb7c6a10 100644 --- a/sound/soc/sof/intel/hda-loader.c +++ b/sound/soc/sof/intel/hda-loader.c @@ -294,14 +294,9 @@ int hda_cl_copy_fw(struct snd_sof_dev *sdev, struct hdac_ext_stream *hext_stream { struct sof_intel_hda_dev *hda = sdev->pdata->hw_pdata; const struct sof_intel_dsp_desc *chip = hda->desc; - struct sof_intel_hda_stream *hda_stream; - unsigned long time_left; unsigned int reg; int ret, status; - hda_stream = container_of(hext_stream, struct sof_intel_hda_stream, - hext_stream); - dev_dbg(sdev->dev, "Code loader DMA starting\n"); ret = hda_cl_trigger(sdev->dev, hext_stream, SNDRV_PCM_TRIGGER_START); @@ -310,18 +305,6 @@ int hda_cl_copy_fw(struct snd_sof_dev *sdev, struct hdac_ext_stream *hext_stream return ret; } - if (sdev->pdata->ipc_type == SOF_IPC_TYPE_4) { - /* Wait for completion of transfer */ - time_left = wait_for_completion_timeout(&hda_stream->ioc, - msecs_to_jiffies(HDA_CL_DMA_IOC_TIMEOUT_MS)); - - if (!time_left) { - dev_err(sdev->dev, "Code loader DMA did not complete\n"); - return -ETIMEDOUT; - } - dev_dbg(sdev->dev, "Code loader DMA done\n"); - } - dev_dbg(sdev->dev, "waiting for FW_ENTERED status\n"); status = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR, diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index 87be7f16e8c2..240fee2166d1 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -3129,9 +3129,20 @@ static int sof_ipc4_dai_config(struct snd_sof_dev *sdev, struct snd_sof_widget * * group_id during copier's ipc_prepare op. */ if (flags & SOF_DAI_CONFIG_FLAGS_HW_PARAMS) { + struct sof_ipc4_alh_configuration_blob *blob; + + blob = (struct sof_ipc4_alh_configuration_blob *)ipc4_copier->copier_config; ipc4_copier->dai_index = data->dai_node_id; - copier_data->gtw_cfg.node_id &= ~SOF_IPC4_NODE_INDEX_MASK; - copier_data->gtw_cfg.node_id |= SOF_IPC4_NODE_INDEX(data->dai_node_id); + + /* + * no need to set the node_id for aggregated DAI's. These will be assigned + * a group_id during widget ipc_prepare + */ + if (blob->alh_cfg.device_count == 1) { + copier_data->gtw_cfg.node_id &= ~SOF_IPC4_NODE_INDEX_MASK; + copier_data->gtw_cfg.node_id |= + SOF_IPC4_NODE_INDEX(data->dai_node_id); + } } break; diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 2a9594f34dac..6456e87e2f39 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -4042,6 +4042,9 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer) break; err = dell_dock_mixer_init(mixer); break; + case USB_ID(0x0bda, 0x402e): /* Dell WD19 dock */ + err = dell_dock_mixer_create(mixer); + break; case USB_ID(0x2a39, 0x3fd2): /* RME ADI-2 Pro */ case USB_ID(0x2a39, 0x3fd3): /* RME ADI-2 DAC */ diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 5a7dfeb8e8eb..488f8e751349 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -94,6 +94,7 @@ #define ARM_CPU_PART_NEOVERSE_V3 0xD84 #define ARM_CPU_PART_CORTEX_X925 0xD85 #define ARM_CPU_PART_CORTEX_A725 0xD87 +#define ARM_CPU_PART_NEOVERSE_N3 0xD8E #define APM_CPU_PART_XGENE 0x000 #define APM_CPU_VAR_POTENZA 0x00 @@ -176,6 +177,7 @@ #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) #define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725) +#define MIDR_NEOVERSE_N3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N3) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index a7c06a46fb76..3ae84c3b8e6d 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -36,6 +36,20 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) #define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) +/* + * Architectural memory types that are common to MTRRs, PAT, VMX MSRs, etc. + * Most MSRs support/allow only a subset of memory types, but the values + * themselves are common across all relevant MSRs. + */ +#define X86_MEMTYPE_UC 0ull /* Uncacheable, a.k.a. Strong Uncacheable */ +#define X86_MEMTYPE_WC 1ull /* Write Combining */ +/* RESERVED 2 */ +/* RESERVED 3 */ +#define X86_MEMTYPE_WT 4ull /* Write Through */ +#define X86_MEMTYPE_WP 5ull /* Write Protected */ +#define X86_MEMTYPE_WB 6ull /* Write Back */ +#define X86_MEMTYPE_UC_MINUS 7ull /* Weak Uncacheabled (PAT only) */ + /* FRED MSRs */ #define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */ #define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */ @@ -365,6 +379,12 @@ #define MSR_IA32_CR_PAT 0x00000277 +#define PAT_VALUE(p0, p1, p2, p3, p4, p5, p6, p7) \ + ((X86_MEMTYPE_ ## p0) | (X86_MEMTYPE_ ## p1 << 8) | \ + (X86_MEMTYPE_ ## p2 << 16) | (X86_MEMTYPE_ ## p3 << 24) | \ + (X86_MEMTYPE_ ## p4 << 32) | (X86_MEMTYPE_ ## p5 << 40) | \ + (X86_MEMTYPE_ ## p6 << 48) | (X86_MEMTYPE_ ## p7 << 56)) + #define MSR_IA32_DEBUGCTLMSR 0x000001d9 #define MSR_IA32_LASTBRANCHFROMIP 0x000001db #define MSR_IA32_LASTBRANCHTOIP 0x000001dc @@ -1159,15 +1179,6 @@ #define MSR_IA32_VMX_VMFUNC 0x00000491 #define MSR_IA32_VMX_PROCBASED_CTLS3 0x00000492 -/* VMX_BASIC bits and bitmasks */ -#define VMX_BASIC_VMCS_SIZE_SHIFT 32 -#define VMX_BASIC_TRUE_CTLS (1ULL << 55) -#define VMX_BASIC_64 0x0001000000000000LLU -#define VMX_BASIC_MEM_TYPE_SHIFT 50 -#define VMX_BASIC_MEM_TYPE_MASK 0x003c000000000000LLU -#define VMX_BASIC_MEM_TYPE_WB 6LLU -#define VMX_BASIC_INOUT 0x0040000000000000LLU - /* Resctrl MSRs: */ /* - Intel: */ #define MSR_IA32_L3_QOS_CFG 0xc81 @@ -1185,11 +1196,6 @@ #define MSR_IA32_SMBA_BW_BASE 0xc0000280 #define MSR_IA32_EVT_CFG_BASE 0xc0000400 -/* MSR_IA32_VMX_MISC bits */ -#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) -#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) -#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F - /* AMD-V MSRs */ #define MSR_VM_CR 0xc0010114 #define MSR_VM_IGNNE 0xc0010115 diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index bf57a824f722..a8debbf2f702 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -439,6 +439,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5) #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6) +#define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index 9de35df1afc3..63182a023e9d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -11,6 +11,9 @@ #ifndef __NR_getpgid #define __NR_getpgid 132 #endif +#ifndef __NR_capget +#define __NR_capget 184 +#endif #ifndef __NR_gettid #define __NR_gettid 224 #endif diff --git a/tools/arch/x86/include/uapi/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h index d0f2043d7132..77311e8d1b5d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_64.h +++ b/tools/arch/x86/include/uapi/asm/unistd_64.h @@ -11,6 +11,9 @@ #ifndef __NR_getpgid #define __NR_getpgid 121 #endif +#ifndef __NR_capget +#define __NR_capget 125 +#endif #ifndef __NR_gettid #define __NR_gettid 186 #endif diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 0eb24d21aac2..60044b608817 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -36,4 +36,19 @@ #define GENMASK_ULL(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __GENMASK_U128() depends on _BIT128() which would not work + * in the asm code, as it shifts an 'unsigned __init128' data + * type instead of direct representation of 128 bit constants + * such as long and unsigned long. The fundamental problem is + * that a 128 bit constant will get silently truncated by the + * gcc compiler. + */ +#define GENMASK_U128(h, l) \ + (GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l)) +#endif + #endif /* __LINUX_BITS_H */ diff --git a/tools/include/linux/unaligned.h b/tools/include/linux/unaligned.h index bc0633bc4650..395a4464fe73 100644 --- a/tools/include/linux/unaligned.h +++ b/tools/include/linux/unaligned.h @@ -9,16 +9,7 @@ #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wpacked" #pragma GCC diagnostic ignored "-Wattributes" - -#define __get_unaligned_t(type, ptr) ({ \ - const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ - __pptr->x; \ -}) - -#define __put_unaligned_t(type, val, ptr) do { \ - struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ - __pptr->x = (val); \ -} while (0) +#include <vdso/unaligned.h> #define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) #define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr)) diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h index 3c2a101986a3..5ee30f882736 100644 --- a/tools/include/uapi/linux/bits.h +++ b/tools/include/uapi/linux/bits.h @@ -12,4 +12,7 @@ (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \ (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_U128(h, l) \ + ((_BIT128((h)) << 1) - (_BIT128(l))) + #endif /* _UAPI_LINUX_BITS_H */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e8241b320c6d..4a939c90dc2e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1121,6 +1121,9 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[] + * in sync with the definitions below. + */ enum bpf_link_type { BPF_LINK_TYPE_UNSPEC = 0, BPF_LINK_TYPE_RAW_TRACEPOINT = 1, diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index a429381e7ca5..e16be0d37746 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,6 +28,23 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __BIT128() would not work in the asm code, as it shifts an + * 'unsigned __init128' data type as direct representation of + * 128 bit constants is not supported in the gcc compiler, as + * they get silently truncated. + * + * TODO: Please revisit this implementation when gcc compiler + * starts representing 128 bit constants directly like long + * and unsigned long etc. Subsequently drop the comment for + * GENMASK_U128() which would then start supporting asm code. + */ +#define _BIT128(x) ((unsigned __int128)(1) << (x)) +#endif + #define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index e3ebb49f60d2..e4be227d3ad6 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -124,6 +124,7 @@ enum { NETDEV_A_NAPI_PID, NETDEV_A_NAPI_DEFER_HARD_IRQS, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, + NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) diff --git a/tools/include/vdso/unaligned.h b/tools/include/vdso/unaligned.h new file mode 100644 index 000000000000..eee3d2a4dbe4 --- /dev/null +++ b/tools/include/vdso/unaligned.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_UNALIGNED_H +#define __VDSO_UNALIGNED_H + +#define __get_unaligned_t(type, ptr) ({ \ + const struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ + __pptr->x; \ +}) + +#define __put_unaligned_t(type, val, ptr) do { \ + struct { type x; } __packed *__pptr = (typeof(__pptr))(ptr); \ + __pptr->x = (val); \ +} while (0) + +#endif /* __VDSO_UNALIGNED_H */ diff --git a/tools/mm/page-types.c b/tools/mm/page-types.c index fa050d5a48cd..6eb17cc1a06c 100644 --- a/tools/mm/page-types.c +++ b/tools/mm/page-types.c @@ -22,6 +22,7 @@ #include <time.h> #include <setjmp.h> #include <signal.h> +#include <inttypes.h> #include <sys/types.h> #include <sys/errno.h> #include <sys/fcntl.h> @@ -391,9 +392,9 @@ static void show_page_range(unsigned long voffset, unsigned long offset, if (opt_file) printf("%lx\t", voff); if (opt_list_cgroup) - printf("@%llu\t", (unsigned long long)cgroup0); + printf("@%" PRIu64 "\t", cgroup0); if (opt_list_mapcnt) - printf("%lu\t", mapcnt0); + printf("%" PRIu64 "\t", mapcnt0); printf("%lx\t%lx\t%s\n", index, count, page_flag_name(flags0)); } @@ -419,9 +420,9 @@ static void show_page(unsigned long voffset, unsigned long offset, if (opt_file) printf("%lx\t", voffset); if (opt_list_cgroup) - printf("@%llu\t", (unsigned long long)cgroup); + printf("@%" PRIu64 "\t", cgroup) if (opt_list_mapcnt) - printf("%lu\t", mapcnt); + printf("%" PRIu64 "\t", mapcnt); printf("%lx\t%s\n", offset, page_flag_name(flags)); } diff --git a/tools/mm/slabinfo.c b/tools/mm/slabinfo.c index cfaeaea71042..04e9e6ba86ea 100644 --- a/tools/mm/slabinfo.c +++ b/tools/mm/slabinfo.c @@ -1297,7 +1297,9 @@ static void read_slab_dir(void) slab->cpu_partial_free = get_obj("cpu_partial_free"); slab->alloc_node_mismatch = get_obj("alloc_node_mismatch"); slab->deactivate_bypass = get_obj("deactivate_bypass"); - chdir(".."); + if (chdir("..")) + fatal("Unable to chdir from slab ../%s\n", + slab->name); if (slab->name[0] == ':') alias_targets++; slab++; diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py index b6d6f8aef423..a745739655ad 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/lib/nlspec.py @@ -131,6 +131,9 @@ class SpecEnumSet(SpecElement): def has_doc(self): if 'doc' in self.yaml: return True + return self.has_entry_doc() + + def has_entry_doc(self): for entry in self.entries.values(): if entry.has_doc(): return True diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 1a825b4081b2..c48b69071111 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -481,7 +481,7 @@ class TypeBinary(Type): pass elif len(self.checks) == 1: check_name = list(self.checks)[0] - if check_name not in {'exact-len', 'min-len'}: + if check_name not in {'exact-len', 'min-len', 'max-len'}: raise Exception('Unsupported check for binary type: ' + check_name) else: raise Exception('More than one check for binary type not implemented, yet') @@ -492,6 +492,8 @@ class TypeBinary(Type): mem = 'NLA_POLICY_EXACT_LEN(' + self.get_limit_str('exact-len') + ')' elif 'min-len' in self.checks: mem = '{ .len = ' + self.get_limit_str('min-len') + ', }' + elif 'max-len' in self.checks: + mem = 'NLA_POLICY_MAX_LEN(' + self.get_limit_str('max-len') + ')' return mem @@ -2435,11 +2437,15 @@ def render_uapi(family, cw): enum = family.consts[const['name']] if enum.has_doc(): - cw.p('/**') - doc = '' - if 'doc' in enum: - doc = ' - ' + enum['doc'] - cw.write_doc_line(enum.enum_name + doc) + if enum.has_entry_doc(): + cw.p('/**') + doc = '' + if 'doc' in enum: + doc = ' - ' + enum['doc'] + cw.write_doc_line(enum.enum_name + doc) + else: + cw.p('/*') + cw.write_doc_line(enum['doc'], indent=False) for entry in enum.entries.values(): if entry.has_doc(): doc = '@' + entry.c_name + ': ' + entry['doc'] diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 4ddb27a48eed..d4332675babb 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -704,8 +704,8 @@ ifeq ($(BUILD_BPF_SKEL),1) BUILD_BPF_SKEL := 0 else CLANG_VERSION := $(shell $(CLANG) --version | head -1 | sed 's/.*clang version \([[:digit:]]\+.[[:digit:]]\+.[[:digit:]]\+\).*/\1/g') - ifeq ($(call version-lt3,$(CLANG_VERSION),16.0.6),1) - $(warning Warning: Disabled BPF skeletons as at least $(CLANG) version 16.0.6 is reported to be a working setup with the current of BPF based perf features) + ifeq ($(call version-lt3,$(CLANG_VERSION),12.0.1),1) + $(warning Warning: Disabled BPF skeletons as reliable BTF generation needs at least $(CLANG) version 12.0.1) BUILD_BPF_SKEL := 0 endif endif diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index f6e847529073..d3f11b90d025 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -1399,7 +1399,7 @@ static const struct syscall_fmt syscall_fmts[] = { .arg = { [2] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, }, { .name = "waitid", .errpid = true, .arg = { [3] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, }, - { .name = "write", .errpid = true, + { .name = "write", .arg = { [1] = { .scnprintf = SCA_BUF /* buf */, .from_user = true, }, }, }, }; diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 29adbb423327..a05c1c105c51 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -22,6 +22,7 @@ FILES=( "include/vdso/bits.h" "include/linux/const.h" "include/vdso/const.h" + "include/vdso/unaligned.h" "include/linux/hash.h" "include/linux/list-sort.h" "include/uapi/linux/hw_breakpoint.h" diff --git a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh index b5dc10b2a738..bead723e34af 100755 --- a/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh +++ b/tools/perf/tests/shell/base_probe/test_adding_blacklisted.sh @@ -19,35 +19,74 @@ TEST_RESULT=0 # skip if not supported -BLACKFUNC=`head -n 1 /sys/kernel/debug/kprobes/blacklist 2> /dev/null | cut -f2` -if [ -z "$BLACKFUNC" ]; then +BLACKFUNC_LIST=`head -n 5 /sys/kernel/debug/kprobes/blacklist 2> /dev/null | cut -f2` +if [ -z "$BLACKFUNC_LIST" ]; then print_overall_skipped exit 0 fi +# try to find vmlinux with DWARF debug info +VMLINUX_FILE=$(perf probe -v random_probe |& grep "Using.*for symbols" | sed -r 's/^Using (.*) for symbols$/\1/') + # remove all previously added probes clear_all_probes ### adding blacklisted function - -# functions from blacklist should be skipped by perf probe -! $CMD_PERF probe $BLACKFUNC > $LOGS_DIR/adding_blacklisted.log 2> $LOGS_DIR/adding_blacklisted.err -PERF_EXIT_CODE=$? - REGEX_SCOPE_FAIL="Failed to find scope of probe point" REGEX_SKIP_MESSAGE=" is blacklisted function, skip it\." -REGEX_NOT_FOUND_MESSAGE="Probe point \'$BLACKFUNC\' not found." +REGEX_NOT_FOUND_MESSAGE="Probe point \'$RE_EVENT\' not found." REGEX_ERROR_MESSAGE="Error: Failed to add events." REGEX_INVALID_ARGUMENT="Failed to write event: Invalid argument" REGEX_SYMBOL_FAIL="Failed to find symbol at $RE_ADDRESS" -REGEX_OUT_SECTION="$BLACKFUNC is out of \.\w+, skip it" -../common/check_all_lines_matched.pl "$REGEX_SKIP_MESSAGE" "$REGEX_NOT_FOUND_MESSAGE" "$REGEX_ERROR_MESSAGE" "$REGEX_SCOPE_FAIL" "$REGEX_INVALID_ARGUMENT" "$REGEX_SYMBOL_FAIL" "$REGEX_OUT_SECTION" < $LOGS_DIR/adding_blacklisted.err -CHECK_EXIT_CODE=$? - -print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "adding blacklisted function $BLACKFUNC" -(( TEST_RESULT += $? )) - +REGEX_OUT_SECTION="$RE_EVENT is out of \.\w+, skip it" +REGEX_MISSING_DECL_LINE="A function DIE doesn't have decl_line. Maybe broken DWARF?" + +BLACKFUNC="" +SKIP_DWARF=0 + +for BLACKFUNC in $BLACKFUNC_LIST; do + echo "Probing $BLACKFUNC" + + # functions from blacklist should be skipped by perf probe + ! $CMD_PERF probe $BLACKFUNC > $LOGS_DIR/adding_blacklisted.log 2> $LOGS_DIR/adding_blacklisted.err + PERF_EXIT_CODE=$? + + # check for bad DWARF polluting the result + ../common/check_all_patterns_found.pl "$REGEX_MISSING_DECL_LINE" >/dev/null < $LOGS_DIR/adding_blacklisted.err + + if [ $? -eq 0 ]; then + SKIP_DWARF=1 + echo "Result polluted by broken DWARF, trying another probe" + + # confirm that the broken DWARF comes from assembler + if [ -n "$VMLINUX_FILE" ]; then + readelf -wi "$VMLINUX_FILE" | + awk -v probe="$BLACKFUNC" '/DW_AT_language/ { comp_lang = $0 } + $0 ~ probe { if (comp_lang) { print comp_lang }; exit }' | + grep -q "MIPS assembler" + + CHECK_EXIT_CODE=$? + if [ $CHECK_EXIT_CODE -ne 0 ]; then + SKIP_DWARF=0 # broken DWARF while available + break + fi + fi + else + ../common/check_all_lines_matched.pl "$REGEX_SKIP_MESSAGE" "$REGEX_NOT_FOUND_MESSAGE" "$REGEX_ERROR_MESSAGE" "$REGEX_SCOPE_FAIL" "$REGEX_INVALID_ARGUMENT" "$REGEX_SYMBOL_FAIL" "$REGEX_OUT_SECTION" < $LOGS_DIR/adding_blacklisted.err + CHECK_EXIT_CODE=$? + + SKIP_DWARF=0 + break + fi +done + +if [ $SKIP_DWARF -eq 1 ]; then + print_testcase_skipped "adding blacklisted function $BLACKFUNC" +else + print_results $PERF_EXIT_CODE $CHECK_EXIT_CODE "adding blacklisted function $BLACKFUNC" + (( TEST_RESULT += $? )) +fi ### listing not-added probe diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index b2f17cca014b..4a62ed593e84 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -288,6 +288,10 @@ int sys_enter_rename(struct syscall_enter_args *args) augmented_args->arg.size = PERF_ALIGN(oldpath_len + 1, sizeof(u64)); len += augmented_args->arg.size; + /* Every read from userspace is limited to value size */ + if (augmented_args->arg.size > sizeof(augmented_args->arg.value)) + return 1; /* Failure: don't filter */ + struct augmented_arg *arg2 = (void *)&augmented_args->arg.value + augmented_args->arg.size; newpath_len = augmented_arg__read_str(arg2, newpath_arg, sizeof(augmented_args->arg.value)); @@ -315,6 +319,10 @@ int sys_enter_renameat2(struct syscall_enter_args *args) augmented_args->arg.size = PERF_ALIGN(oldpath_len + 1, sizeof(u64)); len += augmented_args->arg.size; + /* Every read from userspace is limited to value size */ + if (augmented_args->arg.size > sizeof(augmented_args->arg.value)) + return 1; /* Failure: don't filter */ + struct augmented_arg *arg2 = (void *)&augmented_args->arg.value + augmented_args->arg.size; newpath_len = augmented_arg__read_str(arg2, newpath_arg, sizeof(augmented_args->arg.value)); @@ -423,8 +431,9 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid) static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) { bool augmented, do_output = false; - int zero = 0, size, aug_size, index, output = 0, + int zero = 0, size, aug_size, index, value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value); + u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */ unsigned int nr, *beauty_map; struct beauty_payload_enter *payload; void *arg, *payload_offset; @@ -477,6 +486,8 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) augmented = true; } else if (size < 0 && size >= -6) { /* buffer */ index = -(size + 1); + barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick. + index &= 7; // Satisfy the bounds checking with the verifier in some kernels. aug_size = args->args[index]; if (aug_size > TRACE_AUG_MAX_BUF) @@ -488,10 +499,17 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) } } + /* Augmented data size is limited to sizeof(augmented_arg->unnamed union with value field) */ + if (aug_size > value_size) + aug_size = value_size; + /* write data to payload */ if (augmented) { int written = offsetof(struct augmented_arg, value) + aug_size; + if (written < 0 || written > sizeof(struct augmented_arg)) + return 1; + ((struct augmented_arg *)payload_offset)->size = aug_size; output += written; payload_offset += written; @@ -499,7 +517,7 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) } } - if (!do_output) + if (!do_output || (sizeof(struct syscall_enter_args) + output) > sizeof(struct beauty_payload_enter)) return 1; return augmented__beauty_output(ctx, payload, sizeof(struct syscall_enter_args) + output); diff --git a/tools/perf/util/cap.c b/tools/perf/util/cap.c index 7574a67651bc..69d9a2bcd40b 100644 --- a/tools/perf/util/cap.c +++ b/tools/perf/util/cap.c @@ -7,13 +7,9 @@ #include "debug.h" #include <errno.h> #include <string.h> -#include <unistd.h> #include <linux/capability.h> #include <sys/syscall.h> - -#ifndef SYS_capget -#define SYS_capget 90 -#endif +#include <unistd.h> #define MAX_LINUX_CAPABILITY_U32S _LINUX_CAPABILITY_U32S_3 @@ -21,9 +17,9 @@ bool perf_cap__capable(int cap, bool *used_root) { struct __user_cap_header_struct header = { .version = _LINUX_CAPABILITY_VERSION_3, - .pid = getpid(), + .pid = 0, }; - struct __user_cap_data_struct data[MAX_LINUX_CAPABILITY_U32S]; + struct __user_cap_data_struct data[MAX_LINUX_CAPABILITY_U32S] = {}; __u32 cap_val; *used_root = false; diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 31a223eaf8e6..ee3d43a7ba45 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -19,6 +19,7 @@ #include "util/bpf-filter.h" #include "util/env.h" #include "util/kvm-stat.h" +#include "util/stat.h" #include "util/kwork.h" #include "util/sample.h" #include "util/lock-contention.h" @@ -1355,6 +1356,7 @@ error: unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; +#ifdef HAVE_KVM_STAT_SUPPORT bool kvm_entry_event(struct evsel *evsel __maybe_unused) { return false; @@ -1384,6 +1386,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, char *decode __maybe_unused) { } +#endif // HAVE_KVM_STAT_SUPPORT int find_scripts(char **scripts_array __maybe_unused, char **scripts_path_array __maybe_unused, int num __maybe_unused, int pathlen __maybe_unused) diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index 7c15dec6900d..6c45ded922b6 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -46,6 +46,11 @@ static const char *const *syscalltbl_native = syscalltbl_mips_n64; #include <asm/syscalls.c> const int syscalltbl_native_max_id = SYSCALLTBL_LOONGARCH_MAX_ID; static const char *const *syscalltbl_native = syscalltbl_loongarch; +#else +const int syscalltbl_native_max_id = 0; +static const char *const syscalltbl_native[] = { + [0] = "unknown", +}; #endif struct syscall { @@ -182,6 +187,11 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name) return audit_name_to_syscall(name, tbl->audit_machine); } +int syscalltbl__id_at_idx(struct syscalltbl *tbl __maybe_unused, int idx) +{ + return idx; +} + int syscalltbl__strglobmatch_next(struct syscalltbl *tbl __maybe_unused, const char *syscall_glob __maybe_unused, int *idx __maybe_unused) { diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 27749c51c3ec..248ab790d143 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -320,7 +320,7 @@ u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym; /* * Access a cpumask in read-only mode (typically to check bits). */ -const struct cpumask *cast_mask(struct bpf_cpumask *mask) +static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask) { return (const struct cpumask *)mask; } diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 90d5afd52dd0..050725afa45d 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -693,26 +693,22 @@ static int mock_decoder_commit(struct cxl_decoder *cxld) return 0; } -static int mock_decoder_reset(struct cxl_decoder *cxld) +static void mock_decoder_reset(struct cxl_decoder *cxld) { struct cxl_port *port = to_cxl_port(cxld->dev.parent); int id = cxld->id; if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0) - return 0; + return; dev_dbg(&port->dev, "%s reset\n", dev_name(&cxld->dev)); - if (port->commit_end != id) { + if (port->commit_end == id) + cxl_port_commit_reap(cxld); + else dev_dbg(&port->dev, "%s: out of order reset, expected decoder%d.%d\n", dev_name(&cxld->dev), port->id, port->commit_end); - return -EBUSY; - } - - port->commit_end--; cxld->flags &= ~CXL_DECODER_F_ENABLE; - - return 0; } static void default_mock_decoder(struct cxl_decoder *cxld) @@ -1062,7 +1058,7 @@ static void mock_companion(struct acpi_device *adev, struct device *dev) #define SZ_64G (SZ_32G * 2) #endif -static __init int cxl_rch_init(void) +static __init int cxl_rch_topo_init(void) { int rc, i; @@ -1090,30 +1086,8 @@ static __init int cxl_rch_init(void) goto err_bridge; } - for (i = 0; i < ARRAY_SIZE(cxl_rcd); i++) { - int idx = NR_MEM_MULTI + NR_MEM_SINGLE + i; - struct platform_device *rch = cxl_rch[i]; - struct platform_device *pdev; - - pdev = platform_device_alloc("cxl_rcd", idx); - if (!pdev) - goto err_mem; - pdev->dev.parent = &rch->dev; - set_dev_node(&pdev->dev, i % 2); - - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); - goto err_mem; - } - cxl_rcd[i] = pdev; - } - return 0; -err_mem: - for (i = ARRAY_SIZE(cxl_rcd) - 1; i >= 0; i--) - platform_device_unregister(cxl_rcd[i]); err_bridge: for (i = ARRAY_SIZE(cxl_rch) - 1; i >= 0; i--) { struct platform_device *pdev = cxl_rch[i]; @@ -1127,12 +1101,10 @@ err_bridge: return rc; } -static void cxl_rch_exit(void) +static void cxl_rch_topo_exit(void) { int i; - for (i = ARRAY_SIZE(cxl_rcd) - 1; i >= 0; i--) - platform_device_unregister(cxl_rcd[i]); for (i = ARRAY_SIZE(cxl_rch) - 1; i >= 0; i--) { struct platform_device *pdev = cxl_rch[i]; @@ -1143,7 +1115,7 @@ static void cxl_rch_exit(void) } } -static __init int cxl_single_init(void) +static __init int cxl_single_topo_init(void) { int i, rc; @@ -1228,29 +1200,8 @@ static __init int cxl_single_init(void) cxl_swd_single[i] = pdev; } - for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) { - struct platform_device *dport = cxl_swd_single[i]; - struct platform_device *pdev; - - pdev = platform_device_alloc("cxl_mem", NR_MEM_MULTI + i); - if (!pdev) - goto err_mem; - pdev->dev.parent = &dport->dev; - set_dev_node(&pdev->dev, i % 2); - - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); - goto err_mem; - } - cxl_mem_single[i] = pdev; - } - return 0; -err_mem: - for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) - platform_device_unregister(cxl_mem_single[i]); err_dport: for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--) platform_device_unregister(cxl_swd_single[i]); @@ -1273,12 +1224,10 @@ err_bridge: return rc; } -static void cxl_single_exit(void) +static void cxl_single_topo_exit(void) { int i; - for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) - platform_device_unregister(cxl_mem_single[i]); for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--) platform_device_unregister(cxl_swd_single[i]); for (i = ARRAY_SIZE(cxl_swu_single) - 1; i >= 0; i--) @@ -1295,6 +1244,91 @@ static void cxl_single_exit(void) } } +static void cxl_mem_exit(void) +{ + int i; + + for (i = ARRAY_SIZE(cxl_rcd) - 1; i >= 0; i--) + platform_device_unregister(cxl_rcd[i]); + for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem_single[i]); + for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem[i]); +} + +static int cxl_mem_init(void) +{ + int i, rc; + + for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) { + struct platform_device *dport = cxl_switch_dport[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_mem", i); + if (!pdev) + goto err_mem; + pdev->dev.parent = &dport->dev; + set_dev_node(&pdev->dev, i % 2); + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_mem; + } + cxl_mem[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) { + struct platform_device *dport = cxl_swd_single[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_mem", NR_MEM_MULTI + i); + if (!pdev) + goto err_single; + pdev->dev.parent = &dport->dev; + set_dev_node(&pdev->dev, i % 2); + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_single; + } + cxl_mem_single[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_rcd); i++) { + int idx = NR_MEM_MULTI + NR_MEM_SINGLE + i; + struct platform_device *rch = cxl_rch[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_rcd", idx); + if (!pdev) + goto err_rcd; + pdev->dev.parent = &rch->dev; + set_dev_node(&pdev->dev, i % 2); + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_rcd; + } + cxl_rcd[i] = pdev; + } + + return 0; + +err_rcd: + for (i = ARRAY_SIZE(cxl_rcd) - 1; i >= 0; i--) + platform_device_unregister(cxl_rcd[i]); +err_single: + for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem_single[i]); +err_mem: + for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem[i]); + return rc; +} + static __init int cxl_test_init(void) { int rc, i; @@ -1407,29 +1441,11 @@ static __init int cxl_test_init(void) cxl_switch_dport[i] = pdev; } - for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) { - struct platform_device *dport = cxl_switch_dport[i]; - struct platform_device *pdev; - - pdev = platform_device_alloc("cxl_mem", i); - if (!pdev) - goto err_mem; - pdev->dev.parent = &dport->dev; - set_dev_node(&pdev->dev, i % 2); - - rc = platform_device_add(pdev); - if (rc) { - platform_device_put(pdev); - goto err_mem; - } - cxl_mem[i] = pdev; - } - - rc = cxl_single_init(); + rc = cxl_single_topo_init(); if (rc) - goto err_mem; + goto err_dport; - rc = cxl_rch_init(); + rc = cxl_rch_topo_init(); if (rc) goto err_single; @@ -1442,19 +1458,20 @@ static __init int cxl_test_init(void) rc = platform_device_add(cxl_acpi); if (rc) - goto err_add; + goto err_root; + + rc = cxl_mem_init(); + if (rc) + goto err_root; return 0; -err_add: +err_root: platform_device_put(cxl_acpi); err_rch: - cxl_rch_exit(); + cxl_rch_topo_exit(); err_single: - cxl_single_exit(); -err_mem: - for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) - platform_device_unregister(cxl_mem[i]); + cxl_single_topo_exit(); err_dport: for (i = ARRAY_SIZE(cxl_switch_dport) - 1; i >= 0; i--) platform_device_unregister(cxl_switch_dport[i]); @@ -1486,11 +1503,10 @@ static __exit void cxl_test_exit(void) { int i; + cxl_mem_exit(); platform_device_unregister(cxl_acpi); - cxl_rch_exit(); - cxl_single_exit(); - for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) - platform_device_unregister(cxl_mem[i]); + cxl_rch_topo_exit(); + cxl_single_topo_exit(); for (i = ARRAY_SIZE(cxl_switch_dport) - 1; i >= 0; i--) platform_device_unregister(cxl_switch_dport[i]); for (i = ARRAY_SIZE(cxl_switch_uport) - 1; i >= 0; i--) diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index ad5c4c18c5c6..71916e0e1546 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -1673,6 +1673,7 @@ static struct platform_driver cxl_mock_mem_driver = { .name = KBUILD_MODNAME, .dev_groups = cxl_mock_mem_groups, .groups = cxl_mock_mem_core_groups, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, }; diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index e6533b3400de..7e88551f2d38 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -24,7 +24,6 @@ test_flow_dissector flow_dissector_load test_tcpnotify_user test_libbpf -test_tcp_check_syncookie_user test_sysctl xdping test_cpp diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 75016962f795..9ec53c858d8d 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -137,7 +137,6 @@ TEST_PROGS := test_kmod.sh \ test_xdp_vlan_mode_generic.sh \ test_xdp_vlan_mode_native.sh \ test_lwt_ip_encap.sh \ - test_tcp_check_syncookie.sh \ test_tc_tunnel.sh \ test_tc_edt.sh \ test_xdping.sh \ @@ -154,11 +153,23 @@ TEST_PROGS_EXTENDED := with_addr.sh \ # Compile but not part of 'make run_tests' TEST_GEN_PROGS_EXTENDED = \ - flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ - test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \ - xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ - xdp_features bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ - bpf_test_modorder_y.ko + bench \ + bpf_testmod.ko \ + bpf_test_modorder_x.ko \ + bpf_test_modorder_y.ko \ + bpf_test_no_cfi.ko \ + flow_dissector_load \ + runqslower \ + test_cpp \ + test_flow_dissector \ + test_lirc_mode2_user \ + veristat \ + xdp_features \ + xdp_hw_metadata \ + xdp_redirect_multi \ + xdp_synproxy \ + xdping \ + xskxceiver TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi @@ -361,7 +372,6 @@ $(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS) $(OUTPUT)/test_maps: $(TESTING_HELPERS) $(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS) $(UNPRIV_HELPERS) $(OUTPUT)/xsk.o: $(BPFOBJ) -$(OUTPUT)/test_tcp_check_syncookie_user: $(NETWORK_HELPERS) BPFTOOL ?= $(DEFAULT_BPFTOOL) $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c new file mode 100644 index 000000000000..0ba015686492 --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <linux/bpf.h> +#include <stdio.h> +#include <stdbool.h> +#include <unistd.h> +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include <pthread.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <test_maps.h> + +struct test_lpm_key { + __u32 prefix; + __u32 data; +}; + +struct get_next_key_ctx { + struct test_lpm_key key; + bool start; + bool stop; + int map_fd; + int loop; +}; + +static void *get_next_key_fn(void *arg) +{ + struct get_next_key_ctx *ctx = arg; + struct test_lpm_key next_key; + int i = 0; + + while (!ctx->start) + usleep(1); + + while (!ctx->stop && i++ < ctx->loop) + bpf_map_get_next_key(ctx->map_fd, &ctx->key, &next_key); + + return NULL; +} + +static void abort_get_next_key(struct get_next_key_ctx *ctx, pthread_t *tids, + unsigned int nr) +{ + unsigned int i; + + ctx->stop = true; + ctx->start = true; + for (i = 0; i < nr; i++) + pthread_join(tids[i], NULL); +} + +/* This test aims to prevent regression of future. As long as the kernel does + * not panic, it is considered as success. + */ +void test_lpm_trie_map_get_next_key(void) +{ +#define MAX_NR_THREADS 8 + LIBBPF_OPTS(bpf_map_create_opts, create_opts, + .map_flags = BPF_F_NO_PREALLOC); + struct test_lpm_key key = {}; + __u32 val = 0; + int map_fd; + const __u32 max_prefixlen = 8 * (sizeof(key) - sizeof(key.prefix)); + const __u32 max_entries = max_prefixlen + 1; + unsigned int i, nr = MAX_NR_THREADS, loop = 65536; + pthread_t tids[MAX_NR_THREADS]; + struct get_next_key_ctx ctx; + int err; + + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie_map", + sizeof(struct test_lpm_key), sizeof(__u32), + max_entries, &create_opts); + CHECK(map_fd == -1, "bpf_map_create()", "error:%s\n", + strerror(errno)); + + for (i = 0; i <= max_prefixlen; i++) { + key.prefix = i; + err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY); + CHECK(err, "bpf_map_update_elem()", "error:%s\n", + strerror(errno)); + } + + ctx.start = false; + ctx.stop = false; + ctx.map_fd = map_fd; + ctx.loop = loop; + memcpy(&ctx.key, &key, sizeof(key)); + + for (i = 0; i < nr; i++) { + err = pthread_create(&tids[i], NULL, get_next_key_fn, &ctx); + if (err) { + abort_get_next_key(&ctx, tids, i); + CHECK(err, "pthread_create", "error %d\n", err); + } + } + + ctx.start = true; + for (i = 0; i < nr; i++) + pthread_join(tids[i], NULL); + + printf("%s:PASS\n", __func__); + + close(map_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c index ef4d6a3ae423..cf15cc3be491 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c @@ -17,32 +17,37 @@ #include "test_progs.h" #include "test_btf_skc_cls_ingress.skel.h" -static struct test_btf_skc_cls_ingress *skel; -static struct sockaddr_in6 srv_sa6; -static __u32 duration; +#define TEST_NS "skc_cls_ingress" -static int prepare_netns(void) +#define BIT(n) (1 << (n)) +#define TEST_MODE_IPV4 BIT(0) +#define TEST_MODE_IPV6 BIT(1) +#define TEST_MODE_DUAL (TEST_MODE_IPV4 | TEST_MODE_IPV6) + +#define SERVER_ADDR_IPV4 "127.0.0.1" +#define SERVER_ADDR_IPV6 "::1" +#define SERVER_ADDR_DUAL "::0" +/* RFC791, 576 for minimal IPv4 datagram, minus 40 bytes of TCP header */ +#define MIN_IPV4_MSS 536 + +static struct netns_obj *prepare_netns(struct test_btf_skc_cls_ingress *skel) { LIBBPF_OPTS(bpf_tc_hook, qdisc_lo, .attach_point = BPF_TC_INGRESS); LIBBPF_OPTS(bpf_tc_opts, tc_attach, .prog_fd = bpf_program__fd(skel->progs.cls_ingress)); + struct netns_obj *ns = NULL; - if (CHECK(unshare(CLONE_NEWNET), "create netns", - "unshare(CLONE_NEWNET): %s (%d)", - strerror(errno), errno)) - return -1; - - if (CHECK(system("ip link set dev lo up"), - "ip link set dev lo up", "failed\n")) - return -1; + ns = netns_new(TEST_NS, true); + if (!ASSERT_OK_PTR(ns, "create and join netns")) + return ns; qdisc_lo.ifindex = if_nametoindex("lo"); if (!ASSERT_OK(bpf_tc_hook_create(&qdisc_lo), "qdisc add dev lo clsact")) - return -1; + goto free_ns; if (!ASSERT_OK(bpf_tc_attach(&qdisc_lo, &tc_attach), "filter add dev lo ingress")) - return -1; + goto free_ns; /* Ensure 20 bytes options (i.e. in total 40 bytes tcp header) for the * bpf_tcp_gen_syncookie() helper. @@ -50,71 +55,142 @@ static int prepare_netns(void) if (write_sysctl("/proc/sys/net/ipv4/tcp_window_scaling", "1") || write_sysctl("/proc/sys/net/ipv4/tcp_timestamps", "1") || write_sysctl("/proc/sys/net/ipv4/tcp_sack", "1")) - return -1; + goto free_ns; + + return ns; - return 0; +free_ns: + netns_free(ns); + return NULL; } -static void reset_test(void) +static void reset_test(struct test_btf_skc_cls_ingress *skel) { + memset(&skel->bss->srv_sa4, 0, sizeof(skel->bss->srv_sa4)); memset(&skel->bss->srv_sa6, 0, sizeof(skel->bss->srv_sa6)); skel->bss->listen_tp_sport = 0; skel->bss->req_sk_sport = 0; skel->bss->recv_cookie = 0; skel->bss->gen_cookie = 0; skel->bss->linum = 0; + skel->bss->mss = 0; } -static void print_err_line(void) +static void print_err_line(struct test_btf_skc_cls_ingress *skel) { if (skel->bss->linum) printf("bpf prog error at line %u\n", skel->bss->linum); } -static void test_conn(void) +static int v6only_true(int fd, void *opts) +{ + int mode = true; + + return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode)); +} + +static int v6only_false(int fd, void *opts) { + int mode = false; + + return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode)); +} + +static void run_test(struct test_btf_skc_cls_ingress *skel, bool gen_cookies, + int ip_mode) +{ + const char *tcp_syncookies = gen_cookies ? "2" : "1"; int listen_fd = -1, cli_fd = -1, srv_fd = -1, err; - socklen_t addrlen = sizeof(srv_sa6); + struct network_helper_opts opts = { 0 }; + struct sockaddr_storage *addr; + struct sockaddr_in6 srv_sa6; + struct sockaddr_in srv_sa4; + socklen_t addr_len; + int sock_family; + char *srv_addr; int srv_port; - if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "1")) + switch (ip_mode) { + case TEST_MODE_IPV4: + sock_family = AF_INET; + srv_addr = SERVER_ADDR_IPV4; + addr = (struct sockaddr_storage *)&srv_sa4; + addr_len = sizeof(srv_sa4); + break; + case TEST_MODE_IPV6: + opts.post_socket_cb = v6only_true; + sock_family = AF_INET6; + srv_addr = SERVER_ADDR_IPV6; + addr = (struct sockaddr_storage *)&srv_sa6; + addr_len = sizeof(srv_sa6); + break; + case TEST_MODE_DUAL: + opts.post_socket_cb = v6only_false; + sock_family = AF_INET6; + srv_addr = SERVER_ADDR_DUAL; + addr = (struct sockaddr_storage *)&srv_sa6; + addr_len = sizeof(srv_sa6); + break; + default: + PRINT_FAIL("Unknown IP mode %d", ip_mode); return; + } - listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); - if (CHECK_FAIL(listen_fd == -1)) + if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", tcp_syncookies)) return; - err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen); - if (CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d\n", err, - errno)) - goto done; - memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6)); - srv_port = ntohs(srv_sa6.sin6_port); + listen_fd = start_server_str(sock_family, SOCK_STREAM, srv_addr, 0, + &opts); + if (!ASSERT_OK_FD(listen_fd, "start server")) + return; - cli_fd = connect_to_fd(listen_fd, 0); - if (CHECK_FAIL(cli_fd == -1)) + err = getsockname(listen_fd, (struct sockaddr *)addr, &addr_len); + if (!ASSERT_OK(err, "getsockname(listen_fd)")) goto done; - srv_fd = accept(listen_fd, NULL, NULL); - if (CHECK_FAIL(srv_fd == -1)) + switch (ip_mode) { + case TEST_MODE_IPV4: + memcpy(&skel->bss->srv_sa4, &srv_sa4, sizeof(srv_sa4)); + srv_port = ntohs(srv_sa4.sin_port); + break; + case TEST_MODE_IPV6: + case TEST_MODE_DUAL: + memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6)); + srv_port = ntohs(srv_sa6.sin6_port); + break; + default: goto done; + } - if (CHECK(skel->bss->listen_tp_sport != srv_port || - skel->bss->req_sk_sport != srv_port, - "Unexpected sk src port", - "listen_tp_sport:%u req_sk_sport:%u expected:%u\n", - skel->bss->listen_tp_sport, skel->bss->req_sk_sport, - srv_port)) + cli_fd = connect_to_fd(listen_fd, 0); + if (!ASSERT_OK_FD(cli_fd, "connect client")) goto done; - if (CHECK(skel->bss->gen_cookie || skel->bss->recv_cookie, - "Unexpected syncookie states", - "gen_cookie:%u recv_cookie:%u\n", - skel->bss->gen_cookie, skel->bss->recv_cookie)) + srv_fd = accept(listen_fd, NULL, NULL); + if (!ASSERT_OK_FD(srv_fd, "accept connection")) goto done; - CHECK(skel->bss->linum, "bpf prog detected error", "at line %u\n", - skel->bss->linum); + ASSERT_EQ(skel->bss->listen_tp_sport, srv_port, "listen tp src port"); + + if (!gen_cookies) { + ASSERT_EQ(skel->bss->req_sk_sport, srv_port, + "request socket source port with syncookies disabled"); + ASSERT_EQ(skel->bss->gen_cookie, 0, + "generated syncookie with syncookies disabled"); + ASSERT_EQ(skel->bss->recv_cookie, 0, + "received syncookie with syncookies disabled"); + } else { + ASSERT_EQ(skel->bss->req_sk_sport, 0, + "request socket source port with syncookies enabled"); + ASSERT_NEQ(skel->bss->gen_cookie, 0, + "syncookie properly generated"); + ASSERT_EQ(skel->bss->gen_cookie, skel->bss->recv_cookie, + "matching syncookies on client and server"); + ASSERT_GT(skel->bss->mss, MIN_IPV4_MSS, + "MSS in cookie min value"); + ASSERT_LT(skel->bss->mss, USHRT_MAX, + "MSS in cookie max value"); + } done: if (listen_fd != -1) @@ -125,96 +201,74 @@ done: close(srv_fd); } -static void test_syncookie(void) +static void test_conn_ipv4(struct test_btf_skc_cls_ingress *skel) { - int listen_fd = -1, cli_fd = -1, srv_fd = -1, err; - socklen_t addrlen = sizeof(srv_sa6); - int srv_port; - - /* Enforce syncookie mode */ - if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "2")) - return; - - listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); - if (CHECK_FAIL(listen_fd == -1)) - return; - - err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen); - if (CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d\n", err, - errno)) - goto done; - memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6)); - srv_port = ntohs(srv_sa6.sin6_port); - - cli_fd = connect_to_fd(listen_fd, 0); - if (CHECK_FAIL(cli_fd == -1)) - goto done; - - srv_fd = accept(listen_fd, NULL, NULL); - if (CHECK_FAIL(srv_fd == -1)) - goto done; + run_test(skel, false, TEST_MODE_IPV4); +} - if (CHECK(skel->bss->listen_tp_sport != srv_port, - "Unexpected tp src port", - "listen_tp_sport:%u expected:%u\n", - skel->bss->listen_tp_sport, srv_port)) - goto done; +static void test_conn_ipv6(struct test_btf_skc_cls_ingress *skel) +{ + run_test(skel, false, TEST_MODE_IPV6); +} - if (CHECK(skel->bss->req_sk_sport, - "Unexpected req_sk src port", - "req_sk_sport:%u expected:0\n", - skel->bss->req_sk_sport)) - goto done; +static void test_conn_dual(struct test_btf_skc_cls_ingress *skel) +{ + run_test(skel, false, TEST_MODE_DUAL); +} - if (CHECK(!skel->bss->gen_cookie || - skel->bss->gen_cookie != skel->bss->recv_cookie, - "Unexpected syncookie states", - "gen_cookie:%u recv_cookie:%u\n", - skel->bss->gen_cookie, skel->bss->recv_cookie)) - goto done; +static void test_syncookie_ipv4(struct test_btf_skc_cls_ingress *skel) +{ + run_test(skel, true, TEST_MODE_IPV4); +} - CHECK(skel->bss->linum, "bpf prog detected error", "at line %u\n", - skel->bss->linum); +static void test_syncookie_ipv6(struct test_btf_skc_cls_ingress *skel) +{ + run_test(skel, true, TEST_MODE_IPV6); +} -done: - if (listen_fd != -1) - close(listen_fd); - if (cli_fd != -1) - close(cli_fd); - if (srv_fd != -1) - close(srv_fd); +static void test_syncookie_dual(struct test_btf_skc_cls_ingress *skel) +{ + run_test(skel, true, TEST_MODE_DUAL); } struct test { const char *desc; - void (*run)(void); + void (*run)(struct test_btf_skc_cls_ingress *skel); }; #define DEF_TEST(name) { #name, test_##name } static struct test tests[] = { - DEF_TEST(conn), - DEF_TEST(syncookie), + DEF_TEST(conn_ipv4), + DEF_TEST(conn_ipv6), + DEF_TEST(conn_dual), + DEF_TEST(syncookie_ipv4), + DEF_TEST(syncookie_ipv6), + DEF_TEST(syncookie_dual), }; void test_btf_skc_cls_ingress(void) { + struct test_btf_skc_cls_ingress *skel; + struct netns_obj *ns; int i; skel = test_btf_skc_cls_ingress__open_and_load(); - if (CHECK(!skel, "test_btf_skc_cls_ingress__open_and_load", "failed\n")) + if (!ASSERT_OK_PTR(skel, "test_btf_skc_cls_ingress__open_and_load")) return; for (i = 0; i < ARRAY_SIZE(tests); i++) { if (!test__start_subtest(tests[i].desc)) continue; - if (prepare_netns()) + ns = prepare_netns(skel); + if (!ns) break; - tests[i].run(); + tests[i].run(skel); - print_err_line(); - reset_test(); + print_err_line(skel); + reset_test(skel); + netns_free(ns); } test_btf_skc_cls_ingress__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/test_csum_diff.c b/tools/testing/selftests/bpf/prog_tests/test_csum_diff.c new file mode 100644 index 000000000000..107b20d43e83 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_csum_diff.c @@ -0,0 +1,408 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates */ +#include <test_progs.h> +#include "csum_diff_test.skel.h" + +#define BUFF_SZ 512 + +struct testcase { + unsigned long long to_buff[BUFF_SZ / 8]; + unsigned int to_buff_len; + unsigned long long from_buff[BUFF_SZ / 8]; + unsigned int from_buff_len; + unsigned short seed; + unsigned short result; +}; + +#define NUM_PUSH_TESTS 4 + +struct testcase push_tests[NUM_PUSH_TESTS] = { + { + .to_buff = { + 0xdeadbeefdeadbeef, + }, + .to_buff_len = 8, + .from_buff = {}, + .from_buff_len = 0, + .seed = 0, + .result = 0x3b3b + }, + { + .to_buff = { + 0xdeadbeefdeadbeef, + 0xbeefdeadbeefdead, + }, + .to_buff_len = 16, + .from_buff = {}, + .from_buff_len = 0, + .seed = 0x1234, + .result = 0x88aa + }, + { + .to_buff = { + 0xdeadbeefdeadbeef, + 0xbeefdeadbeefdead, + }, + .to_buff_len = 15, + .from_buff = {}, + .from_buff_len = 0, + .seed = 0x1234, +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + .result = 0xcaa9 +#else + .result = 0x87fd +#endif + }, + { + .to_buff = { + 0x327b23c66b8b4567, + 0x66334873643c9869, + 0x19495cff74b0dc51, + 0x625558ec2ae8944a, + 0x46e87ccd238e1f29, + 0x507ed7ab3d1b58ba, + 0x41b71efb2eb141f2, + 0x7545e14679e2a9e3, + 0x5bd062c2515f007c, + 0x4db127f812200854, + 0x1f16e9e80216231b, + 0x66ef438d1190cde7, + 0x3352255a140e0f76, + 0x0ded7263109cf92e, + 0x1befd79f7fdcc233, + 0x6b68079a41a7c4c9, + 0x25e45d324e6afb66, + 0x431bd7b7519b500d, + 0x7c83e4583f2dba31, + 0x62bbd95a257130a3, + 0x628c895d436c6125, + 0x721da317333ab105, + 0x2d1d5ae92443a858, + 0x75a2a8d46763845e, + 0x79838cb208edbdab, + 0x0b03e0c64353d0cd, + 0x54e49eb4189a769b, + 0x2ca8861171f32454, + 0x02901d820836c40e, + 0x081386413a95f874, + 0x7c3dbd3d1e7ff521, + 0x6ceaf087737b8ddc, + 0x4516dde922221a70, + 0x614fd4a13006c83e, + 0x5577f8e1419ac241, + 0x05072367440badfc, + 0x77465f013804823e, + 0x5c482a977724c67e, + 0x5e884adc2463b9ea, + 0x2d51779651ead36b, + 0x153ea438580bd78f, + 0x70a64e2a3855585c, + 0x2a487cb06a2342ec, + 0x725a06fb1d4ed43b, + 0x57e4ccaf2cd89a32, + 0x4b588f547a6d8d3c, + 0x6de91b18542289ec, + 0x7644a45c38437fdb, + 0x684a481a32fff902, + 0x749abb43579478fe, + 0x1ba026fa3dc240fb, + 0x75c6c33a79a1deaa, + 0x70c6a52912e685fb, + 0x374a3fe6520eedd1, + 0x23f9c13c4f4ef005, + 0x275ac794649bb77c, + 0x1cf10fd839386575, + 0x235ba861180115be, + 0x354fe9f947398c89, + 0x741226bb15b5af5c, + 0x10233c990d34b6a8, + 0x615740953f6ab60f, + 0x77ae35eb7e0c57b1, + 0x310c50b3579be4f1, + }, + .to_buff_len = 512, + .from_buff = {}, + .from_buff_len = 0, + .seed = 0xffff, + .result = 0xca45 + }, +}; + +#define NUM_PULL_TESTS 4 + +struct testcase pull_tests[NUM_PULL_TESTS] = { + { + .from_buff = { + 0xdeadbeefdeadbeef, + }, + .from_buff_len = 8, + .to_buff = {}, + .to_buff_len = 0, + .seed = 0, + .result = 0xc4c4 + }, + { + .from_buff = { + 0xdeadbeefdeadbeef, + 0xbeefdeadbeefdead, + }, + .from_buff_len = 16, + .to_buff = {}, + .to_buff_len = 0, + .seed = 0x1234, + .result = 0x9bbd + }, + { + .from_buff = { + 0xdeadbeefdeadbeef, + 0xbeefdeadbeefdead, + }, + .from_buff_len = 15, + .to_buff = {}, + .to_buff_len = 0, + .seed = 0x1234, +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + .result = 0x59be +#else + .result = 0x9c6a +#endif + }, + { + .from_buff = { + 0x327b23c66b8b4567, + 0x66334873643c9869, + 0x19495cff74b0dc51, + 0x625558ec2ae8944a, + 0x46e87ccd238e1f29, + 0x507ed7ab3d1b58ba, + 0x41b71efb2eb141f2, + 0x7545e14679e2a9e3, + 0x5bd062c2515f007c, + 0x4db127f812200854, + 0x1f16e9e80216231b, + 0x66ef438d1190cde7, + 0x3352255a140e0f76, + 0x0ded7263109cf92e, + 0x1befd79f7fdcc233, + 0x6b68079a41a7c4c9, + 0x25e45d324e6afb66, + 0x431bd7b7519b500d, + 0x7c83e4583f2dba31, + 0x62bbd95a257130a3, + 0x628c895d436c6125, + 0x721da317333ab105, + 0x2d1d5ae92443a858, + 0x75a2a8d46763845e, + 0x79838cb208edbdab, + 0x0b03e0c64353d0cd, + 0x54e49eb4189a769b, + 0x2ca8861171f32454, + 0x02901d820836c40e, + 0x081386413a95f874, + 0x7c3dbd3d1e7ff521, + 0x6ceaf087737b8ddc, + 0x4516dde922221a70, + 0x614fd4a13006c83e, + 0x5577f8e1419ac241, + 0x05072367440badfc, + 0x77465f013804823e, + 0x5c482a977724c67e, + 0x5e884adc2463b9ea, + 0x2d51779651ead36b, + 0x153ea438580bd78f, + 0x70a64e2a3855585c, + 0x2a487cb06a2342ec, + 0x725a06fb1d4ed43b, + 0x57e4ccaf2cd89a32, + 0x4b588f547a6d8d3c, + 0x6de91b18542289ec, + 0x7644a45c38437fdb, + 0x684a481a32fff902, + 0x749abb43579478fe, + 0x1ba026fa3dc240fb, + 0x75c6c33a79a1deaa, + 0x70c6a52912e685fb, + 0x374a3fe6520eedd1, + 0x23f9c13c4f4ef005, + 0x275ac794649bb77c, + 0x1cf10fd839386575, + 0x235ba861180115be, + 0x354fe9f947398c89, + 0x741226bb15b5af5c, + 0x10233c990d34b6a8, + 0x615740953f6ab60f, + 0x77ae35eb7e0c57b1, + 0x310c50b3579be4f1, + }, + .from_buff_len = 512, + .to_buff = {}, + .to_buff_len = 0, + .seed = 0xffff, + .result = 0x35ba + }, +}; + +#define NUM_DIFF_TESTS 4 + +struct testcase diff_tests[NUM_DIFF_TESTS] = { + { + .from_buff = { + 0xdeadbeefdeadbeef, + }, + .from_buff_len = 8, + .to_buff = { + 0xabababababababab, + }, + .to_buff_len = 8, + .seed = 0, + .result = 0x7373 + }, + { + .from_buff = { + 0xdeadbeefdeadbeef, + }, + .from_buff_len = 7, + .to_buff = { + 0xabababababababab, + }, + .to_buff_len = 7, + .seed = 0, +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + .result = 0xa673 +#else + .result = 0x73b7 +#endif + }, + { + .from_buff = { + 0, + }, + .from_buff_len = 8, + .to_buff = { + 0xabababababababab, + }, + .to_buff_len = 8, + .seed = 0, + .result = 0xaeae + }, + { + .from_buff = { + 0xdeadbeefdeadbeef + }, + .from_buff_len = 8, + .to_buff = { + 0, + }, + .to_buff_len = 8, + .seed = 0xffff, + .result = 0xc4c4 + }, +}; + +#define NUM_EDGE_TESTS 4 + +struct testcase edge_tests[NUM_EDGE_TESTS] = { + { + .from_buff = {}, + .from_buff_len = 0, + .to_buff = {}, + .to_buff_len = 0, + .seed = 0, + .result = 0 + }, + { + .from_buff = { + 0x1234 + }, + .from_buff_len = 0, + .to_buff = { + 0x1234 + }, + .to_buff_len = 0, + .seed = 0, + .result = 0 + }, + { + .from_buff = {}, + .from_buff_len = 0, + .to_buff = {}, + .to_buff_len = 0, + .seed = 0x1234, + .result = 0x1234 + }, + { + .from_buff = {}, + .from_buff_len = 512, + .to_buff = {}, + .to_buff_len = 0, + .seed = 0xffff, + .result = 0xffff + }, +}; + +static unsigned short trigger_csum_diff(const struct csum_diff_test *skel) +{ + u8 tmp_out[64 << 2] = {}; + u8 tmp_in[64] = {}; + int err; + int pfd; + + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = tmp_in, + .data_size_in = sizeof(tmp_in), + .data_out = tmp_out, + .data_size_out = sizeof(tmp_out), + .repeat = 1, + ); + pfd = bpf_program__fd(skel->progs.compute_checksum); + err = bpf_prog_test_run_opts(pfd, &topts); + if (err) + return -1; + + return skel->bss->result; +} + +static void test_csum_diff(struct testcase *tests, int num_tests) +{ + struct csum_diff_test *skel; + unsigned short got; + int err; + + for (int i = 0; i < num_tests; i++) { + skel = csum_diff_test__open(); + if (!ASSERT_OK_PTR(skel, "csum_diff_test open")) + return; + + skel->rodata->to_buff_len = tests[i].to_buff_len; + skel->rodata->from_buff_len = tests[i].from_buff_len; + + err = csum_diff_test__load(skel); + if (!ASSERT_EQ(err, 0, "csum_diff_test load")) + goto out; + + memcpy(skel->bss->to_buff, tests[i].to_buff, tests[i].to_buff_len); + memcpy(skel->bss->from_buff, tests[i].from_buff, tests[i].from_buff_len); + skel->bss->seed = tests[i].seed; + + got = trigger_csum_diff(skel); + ASSERT_EQ(got, tests[i].result, "csum_diff result"); + + csum_diff_test__destroy(skel); + } + + return; +out: + csum_diff_test__destroy(skel); +} + +void test_test_csum_diff(void) +{ + if (test__start_subtest("csum_diff_push")) + test_csum_diff(push_tests, NUM_PUSH_TESTS); + if (test__start_subtest("csum_diff_pull")) + test_csum_diff(pull_tests, NUM_PULL_TESTS); + if (test__start_subtest("csum_diff_diff")) + test_csum_diff(diff_tests, NUM_DIFF_TESTS); + if (test__start_subtest("csum_diff_edge")) + test_csum_diff(edge_tests, NUM_EDGE_TESTS); +} diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 5356f26bbb3f..75f7a2ce334b 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -54,6 +54,7 @@ #include "verifier_masking.skel.h" #include "verifier_meta_access.skel.h" #include "verifier_movsx.skel.h" +#include "verifier_mtu.skel.h" #include "verifier_netfilter_ctx.skel.h" #include "verifier_netfilter_retcode.skel.h" #include "verifier_bpf_fastcall.skel.h" @@ -223,6 +224,24 @@ void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_pack void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); } void test_verifier_lsm(void) { RUN(verifier_lsm); } +void test_verifier_mtu(void) +{ + __u64 caps = 0; + int ret; + + /* In case CAP_BPF and CAP_PERFMON is not set */ + ret = cap_enable_effective(1ULL << CAP_BPF | 1ULL << CAP_NET_ADMIN, &caps); + if (!ASSERT_OK(ret, "set_cap_bpf_cap_net_admin")) + return; + ret = cap_disable_effective(1ULL << CAP_SYS_ADMIN | 1ULL << CAP_PERFMON, NULL); + if (!ASSERT_OK(ret, "disable_cap_sys_admin")) + goto restore_cap; + RUN(verifier_mtu); +restore_cap: + if (caps) + cap_enable_effective(caps, NULL); +} + static int init_test_val_map(struct bpf_object *obj, char *map_name) { struct test_val value = { diff --git a/tools/testing/selftests/bpf/progs/csum_diff_test.c b/tools/testing/selftests/bpf/progs/csum_diff_test.c new file mode 100644 index 000000000000..9438f1773a58 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/csum_diff_test.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates */ +#include <linux/types.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define BUFF_SZ 512 + +/* Will be updated by benchmark before program loading */ +char to_buff[BUFF_SZ]; +const volatile unsigned int to_buff_len = 0; +char from_buff[BUFF_SZ]; +const volatile unsigned int from_buff_len = 0; +unsigned short seed = 0; + +short result; + +char _license[] SEC("license") = "GPL"; + +SEC("tc") +int compute_checksum(void *ctx) +{ + int to_len_half = to_buff_len / 2; + int from_len_half = from_buff_len / 2; + short result2; + + /* Calculate checksum in one go */ + result2 = bpf_csum_diff((void *)from_buff, from_buff_len, + (void *)to_buff, to_buff_len, seed); + + /* Calculate checksum by concatenating bpf_csum_diff()*/ + result = bpf_csum_diff((void *)from_buff, from_buff_len - from_len_half, + (void *)to_buff, to_buff_len - to_len_half, seed); + + result = bpf_csum_diff((void *)from_buff + (from_buff_len - from_len_half), from_len_half, + (void *)to_buff + (to_buff_len - to_len_half), to_len_half, result); + + result = (result == result2) ? result : 0; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c index f0759efff6ef..1cd1a1b72cb5 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c +++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c @@ -10,16 +10,18 @@ #endif struct sockaddr_in6 srv_sa6 = {}; +struct sockaddr_in srv_sa4 = {}; __u16 listen_tp_sport = 0; __u16 req_sk_sport = 0; __u32 recv_cookie = 0; __u32 gen_cookie = 0; +__u32 mss = 0; __u32 linum = 0; #define LOG() ({ if (!linum) linum = __LINE__; }) -static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th, - struct tcp_sock *tp, +static void test_syncookie_helper(void *iphdr, int iphdr_size, + struct tcphdr *th, struct tcp_sock *tp, struct __sk_buff *skb) { if (th->syn) { @@ -38,17 +40,18 @@ static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th, return; } - mss_cookie = bpf_tcp_gen_syncookie(tp, ip6h, sizeof(*ip6h), + mss_cookie = bpf_tcp_gen_syncookie(tp, iphdr, iphdr_size, th, 40); if (mss_cookie < 0) { if (mss_cookie != -ENOENT) LOG(); } else { gen_cookie = (__u32)mss_cookie; + mss = mss_cookie >> 32; } } else if (gen_cookie) { /* It was in cookie mode */ - int ret = bpf_tcp_check_syncookie(tp, ip6h, sizeof(*ip6h), + int ret = bpf_tcp_check_syncookie(tp, iphdr, iphdr_size, th, sizeof(*th)); if (ret < 0) { @@ -60,26 +63,58 @@ static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th, } } -static int handle_ip6_tcp(struct ipv6hdr *ip6h, struct __sk_buff *skb) +static int handle_ip_tcp(struct ethhdr *eth, struct __sk_buff *skb) { - struct bpf_sock_tuple *tuple; + struct bpf_sock_tuple *tuple = NULL; + unsigned int tuple_len = 0; struct bpf_sock *bpf_skc; - unsigned int tuple_len; + void *data_end, *iphdr; + struct ipv6hdr *ip6h; + struct iphdr *ip4h; struct tcphdr *th; - void *data_end; + int iphdr_size; data_end = (void *)(long)(skb->data_end); - th = (struct tcphdr *)(ip6h + 1); - if (th + 1 > data_end) - return TC_ACT_OK; - - /* Is it the testing traffic? */ - if (th->dest != srv_sa6.sin6_port) + switch (eth->h_proto) { + case bpf_htons(ETH_P_IP): + ip4h = (struct iphdr *)(eth + 1); + if (ip4h + 1 > data_end) + return TC_ACT_OK; + if (ip4h->protocol != IPPROTO_TCP) + return TC_ACT_OK; + th = (struct tcphdr *)(ip4h + 1); + if (th + 1 > data_end) + return TC_ACT_OK; + /* Is it the testing traffic? */ + if (th->dest != srv_sa4.sin_port) + return TC_ACT_OK; + tuple_len = sizeof(tuple->ipv4); + tuple = (struct bpf_sock_tuple *)&ip4h->saddr; + iphdr = ip4h; + iphdr_size = sizeof(*ip4h); + break; + case bpf_htons(ETH_P_IPV6): + ip6h = (struct ipv6hdr *)(eth + 1); + if (ip6h + 1 > data_end) + return TC_ACT_OK; + if (ip6h->nexthdr != IPPROTO_TCP) + return TC_ACT_OK; + th = (struct tcphdr *)(ip6h + 1); + if (th + 1 > data_end) + return TC_ACT_OK; + /* Is it the testing traffic? */ + if (th->dest != srv_sa6.sin6_port) + return TC_ACT_OK; + tuple_len = sizeof(tuple->ipv6); + tuple = (struct bpf_sock_tuple *)&ip6h->saddr; + iphdr = ip6h; + iphdr_size = sizeof(*ip6h); + break; + default: return TC_ACT_OK; + } - tuple_len = sizeof(tuple->ipv6); - tuple = (struct bpf_sock_tuple *)&ip6h->saddr; if ((void *)tuple + tuple_len > data_end) { LOG(); return TC_ACT_OK; @@ -126,7 +161,7 @@ static int handle_ip6_tcp(struct ipv6hdr *ip6h, struct __sk_buff *skb) listen_tp_sport = tp->inet_conn.icsk_inet.sk.__sk_common.skc_num; - test_syncookie_helper(ip6h, th, tp, skb); + test_syncookie_helper(iphdr, iphdr_size, th, tp, skb); bpf_sk_release(tp); return TC_ACT_OK; } @@ -142,7 +177,6 @@ release: SEC("tc") int cls_ingress(struct __sk_buff *skb) { - struct ipv6hdr *ip6h; struct ethhdr *eth; void *data_end; @@ -152,17 +186,11 @@ int cls_ingress(struct __sk_buff *skb) if (eth + 1 > data_end) return TC_ACT_OK; - if (eth->h_proto != bpf_htons(ETH_P_IPV6)) - return TC_ACT_OK; - - ip6h = (struct ipv6hdr *)(eth + 1); - if (ip6h + 1 > data_end) + if (eth->h_proto != bpf_htons(ETH_P_IP) && + eth->h_proto != bpf_htons(ETH_P_IPV6)) return TC_ACT_OK; - if (ip6h->nexthdr == IPPROTO_TCP) - return handle_ip6_tcp(ip6h, skb); - - return TC_ACT_OK; + return handle_ip_tcp(eth, skb); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c deleted file mode 100644 index 6edebce563b5..000000000000 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ /dev/null @@ -1,167 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (c) 2018 Facebook -// Copyright (c) 2019 Cloudflare - -#include <string.h> - -#include <linux/bpf.h> -#include <linux/pkt_cls.h> -#include <linux/if_ether.h> -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/ipv6.h> -#include <sys/socket.h> -#include <linux/tcp.h> - -#include <bpf/bpf_helpers.h> -#include <bpf/bpf_endian.h> - -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __type(key, __u32); - __type(value, __u32); - __uint(max_entries, 3); -} results SEC(".maps"); - -static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk, - void *iph, __u32 ip_size, - struct tcphdr *tcph) -{ - __u32 thlen = tcph->doff * 4; - - if (tcph->syn && !tcph->ack) { - // packet should only have an MSS option - if (thlen != 24) - return 0; - - if ((void *)tcph + thlen > data_end) - return 0; - - return bpf_tcp_gen_syncookie(sk, iph, ip_size, tcph, thlen); - } - return 0; -} - -static __always_inline void check_syncookie(void *ctx, void *data, - void *data_end) -{ - struct bpf_sock_tuple tup; - struct bpf_sock *sk; - struct ethhdr *ethh; - struct iphdr *ipv4h; - struct ipv6hdr *ipv6h; - struct tcphdr *tcph; - int ret; - __u32 key_mss = 2; - __u32 key_gen = 1; - __u32 key = 0; - __s64 seq_mss; - - ethh = data; - if (ethh + 1 > data_end) - return; - - switch (bpf_ntohs(ethh->h_proto)) { - case ETH_P_IP: - ipv4h = data + sizeof(struct ethhdr); - if (ipv4h + 1 > data_end) - return; - - if (ipv4h->ihl != 5) - return; - - tcph = data + sizeof(struct ethhdr) + sizeof(struct iphdr); - if (tcph + 1 > data_end) - return; - - tup.ipv4.saddr = ipv4h->saddr; - tup.ipv4.daddr = ipv4h->daddr; - tup.ipv4.sport = tcph->source; - tup.ipv4.dport = tcph->dest; - - sk = bpf_skc_lookup_tcp(ctx, &tup, sizeof(tup.ipv4), - BPF_F_CURRENT_NETNS, 0); - if (!sk) - return; - - if (sk->state != BPF_TCP_LISTEN) - goto release; - - seq_mss = gen_syncookie(data_end, sk, ipv4h, sizeof(*ipv4h), - tcph); - - ret = bpf_tcp_check_syncookie(sk, ipv4h, sizeof(*ipv4h), - tcph, sizeof(*tcph)); - break; - - case ETH_P_IPV6: - ipv6h = data + sizeof(struct ethhdr); - if (ipv6h + 1 > data_end) - return; - - if (ipv6h->nexthdr != IPPROTO_TCP) - return; - - tcph = data + sizeof(struct ethhdr) + sizeof(struct ipv6hdr); - if (tcph + 1 > data_end) - return; - - memcpy(tup.ipv6.saddr, &ipv6h->saddr, sizeof(tup.ipv6.saddr)); - memcpy(tup.ipv6.daddr, &ipv6h->daddr, sizeof(tup.ipv6.daddr)); - tup.ipv6.sport = tcph->source; - tup.ipv6.dport = tcph->dest; - - sk = bpf_skc_lookup_tcp(ctx, &tup, sizeof(tup.ipv6), - BPF_F_CURRENT_NETNS, 0); - if (!sk) - return; - - if (sk->state != BPF_TCP_LISTEN) - goto release; - - seq_mss = gen_syncookie(data_end, sk, ipv6h, sizeof(*ipv6h), - tcph); - - ret = bpf_tcp_check_syncookie(sk, ipv6h, sizeof(*ipv6h), - tcph, sizeof(*tcph)); - break; - - default: - return; - } - - if (seq_mss > 0) { - __u32 cookie = (__u32)seq_mss; - __u32 mss = seq_mss >> 32; - - bpf_map_update_elem(&results, &key_gen, &cookie, 0); - bpf_map_update_elem(&results, &key_mss, &mss, 0); - } - - if (ret == 0) { - __u32 cookie = bpf_ntohl(tcph->ack_seq) - 1; - - bpf_map_update_elem(&results, &key, &cookie, 0); - } - -release: - bpf_sk_release(sk); -} - -SEC("tc") -int check_syncookie_clsact(struct __sk_buff *skb) -{ - check_syncookie(skb, (void *)(long)skb->data, - (void *)(long)skb->data_end); - return TC_ACT_OK; -} - -SEC("xdp") -int check_syncookie_xdp(struct xdp_md *ctx) -{ - check_syncookie(ctx, (void *)(long)ctx->data, - (void *)(long)ctx->data_end); - return XDP_PASS; -} - -char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_array_access.c b/tools/testing/selftests/bpf/progs/verifier_array_access.c index 95d7ecc12963..4195aa824ba5 100644 --- a/tools/testing/selftests/bpf/progs/verifier_array_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_array_access.c @@ -368,8 +368,7 @@ __naked void a_read_only_array_2_1(void) r4 = 0; \ r5 = 0; \ call %[bpf_csum_diff]; \ -l0_%=: r0 &= 0xffff; \ - exit; \ +l0_%=: exit; \ " : : __imm(bpf_csum_diff), __imm(bpf_map_lookup_elem), diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c index f4da4d508ddb..156cc278e2fc 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c +++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c @@ -15,6 +15,8 @@ int bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign, int *bpf_iter_bits_next(struct bpf_iter_bits *it) __ksym __weak; void bpf_iter_bits_destroy(struct bpf_iter_bits *it) __ksym __weak; +u64 bits_array[511] = {}; + SEC("iter.s/cgroup") __description("bits iter without destroy") __failure __msg("Unreleased reference") @@ -110,16 +112,16 @@ int bit_index(void) } SEC("syscall") -__description("bits nomem") +__description("bits too big") __success __retval(0) -int bits_nomem(void) +int bits_too_big(void) { u64 data[4]; int nr = 0; int *bit; __builtin_memset(&data, 0xff, sizeof(data)); - bpf_for_each(bits, bit, &data[0], 513) /* Be greater than 512 */ + bpf_for_each(bits, bit, &data[0], 512) /* Be greater than 511 */ nr++; return nr; } @@ -151,3 +153,56 @@ int zero_words(void) nr++; return nr; } + +SEC("syscall") +__description("huge words") +__success __retval(0) +int huge_words(void) +{ + u64 data[8] = {0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1}; + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, &data[0], 67108865) + nr++; + return nr; +} + +SEC("syscall") +__description("max words") +__success __retval(4) +int max_words(void) +{ + volatile int nr = 0; + int *bit; + + bits_array[0] = (1ULL << 63) | 1U; + bits_array[510] = (1ULL << 33) | (1ULL << 32); + + bpf_for_each(bits, bit, bits_array, 511) { + if (nr == 0 && *bit != 0) + break; + if (nr == 2 && *bit != 32672) + break; + nr++; + } + return nr; +} + +SEC("syscall") +__description("bad words") +__success __retval(0) +int bad_words(void) +{ + void *bad_addr = (void *)(3UL << 30); + int nr = 0; + int *bit; + + bpf_for_each(bits, bit, bad_addr, 1) + nr++; + + bpf_for_each(bits, bit, bad_addr, 4) + nr++; + + return nr; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c index 9da97d2efcd9..5094c288cfd7 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c +++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c @@ -790,61 +790,6 @@ __naked static void cumulative_stack_depth_subprog(void) :: __imm(bpf_get_smp_processor_id) : __clobber_all); } -SEC("raw_tp") -__arch_x86_64 -__log_level(4) -__msg("stack depth 512") -__xlated("0: r1 = 42") -__xlated("1: *(u64 *)(r10 -512) = r1") -__xlated("2: w0 = ") -__xlated("3: r0 = &(void __percpu *)(r0)") -__xlated("4: r0 = *(u32 *)(r0 +0)") -__xlated("5: exit") -__success -__naked int bpf_fastcall_max_stack_ok(void) -{ - asm volatile( - "r1 = 42;" - "*(u64 *)(r10 - %[max_bpf_stack]) = r1;" - "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;" - "call %[bpf_get_smp_processor_id];" - "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);" - "exit;" - : - : __imm_const(max_bpf_stack, MAX_BPF_STACK), - __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8), - __imm(bpf_get_smp_processor_id) - : __clobber_all - ); -} - -SEC("raw_tp") -__arch_x86_64 -__log_level(4) -__msg("stack depth 520") -__failure -__naked int bpf_fastcall_max_stack_fail(void) -{ - asm volatile( - "r1 = 42;" - "*(u64 *)(r10 - %[max_bpf_stack]) = r1;" - "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;" - "call %[bpf_get_smp_processor_id];" - "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);" - /* call to prandom blocks bpf_fastcall rewrite */ - "*(u64 *)(r10 - %[max_bpf_stack_8]) = r1;" - "call %[bpf_get_prandom_u32];" - "r1 = *(u64 *)(r10 - %[max_bpf_stack_8]);" - "exit;" - : - : __imm_const(max_bpf_stack, MAX_BPF_STACK), - __imm_const(max_bpf_stack_8, MAX_BPF_STACK + 8), - __imm(bpf_get_smp_processor_id), - __imm(bpf_get_prandom_u32) - : __clobber_all - ); -} - SEC("cgroup/getsockname_unix") __xlated("0: r2 = 1") /* bpf_cast_to_kern_ctx is replaced by a single assignment */ diff --git a/tools/testing/selftests/bpf/progs/verifier_const.c b/tools/testing/selftests/bpf/progs/verifier_const.c index 2e533d7eec2f..e118dbb768bf 100644 --- a/tools/testing/selftests/bpf/progs/verifier_const.c +++ b/tools/testing/selftests/bpf/progs/verifier_const.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2024 Isovalent */ -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #include "bpf_misc.h" const volatile long foo = 42; @@ -66,4 +67,32 @@ int tcx6(struct __sk_buff *skb) return TCX_PASS; } +static inline void write_fixed(volatile void *p, __u32 val) +{ + *(volatile __u32 *)p = val; +} + +static inline void write_dyn(void *p, void *val, int len) +{ + bpf_copy_from_user(p, len, val); +} + +SEC("tc/ingress") +__description("rodata/mark: write with unknown reg rejected") +__failure __msg("write into map forbidden") +int tcx7(struct __sk_buff *skb) +{ + write_fixed((void *)&foo, skb->mark); + return TCX_PASS; +} + +SEC("lsm.s/bprm_committed_creds") +__description("rodata/mark: write with unknown reg rejected") +__failure __msg("write into map forbidden") +int BPF_PROG(bprm, struct linux_binprm *bprm) +{ + write_dyn((void *)&foo, &bart, bpf_get_prandom_u32() & 3); + return 0; +} + char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_mtu.c b/tools/testing/selftests/bpf/progs/verifier_mtu.c new file mode 100644 index 000000000000..70c7600a26a0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_mtu.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("tc/ingress") +__description("uninit/mtu: write rejected") +__failure __msg("invalid indirect read from stack") +int tc_uninit_mtu(struct __sk_buff *ctx) +{ + __u32 mtu; + + bpf_check_mtu(ctx, 0, &mtu, 0, 0); + return TCX_PASS; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_search_pruning.c b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c index 5a14498d352f..f40e57251e94 100644 --- a/tools/testing/selftests/bpf/progs/verifier_search_pruning.c +++ b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c @@ -2,6 +2,7 @@ /* Converted from tools/testing/selftests/bpf/verifier/search_pruning.c */ #include <linux/bpf.h> +#include <../../../include/linux/filter.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" @@ -336,4 +337,26 @@ l0_%=: r1 = 42; \ : __clobber_all); } +/* Without checkpoint forcibly inserted at the back-edge a loop this + * test would take a very long time to verify. + */ +SEC("kprobe") +__failure __log_level(4) +__msg("BPF program is too large.") +__naked void short_loop1(void) +{ + asm volatile ( + " r7 = *(u16 *)(r1 +0);" + "1: r7 += 0x1ab064b9;" + " .8byte %[jset];" /* same as 'if r7 & 0x702000 goto 1b;' */ + " r7 &= 0x1ee60e;" + " r7 += r1;" + " if r7 s> 0x37d2 goto +0;" + " r0 = 0;" + " exit;" + : + : __imm_insn(jset, BPF_JMP_IMM(BPF_JSET, BPF_REG_7, 0x702000, -2)) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c index f8f5dc9f72b8..62b8e29ced9f 100644 --- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c @@ -21,7 +21,6 @@ #define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3]) -#define IP_DF 0x4000 #define IP_MF 0x2000 #define IP_OFFSET 0x1fff @@ -442,7 +441,7 @@ static __always_inline int tcp_lookup(void *ctx, struct header_pointers *hdr, bo /* TCP doesn't normally use fragments, and XDP can't reassemble * them. */ - if ((hdr->ipv4->frag_off & bpf_htons(IP_DF | IP_MF | IP_OFFSET)) != bpf_htons(IP_DF)) + if ((hdr->ipv4->frag_off & bpf_htons(IP_MF | IP_OFFSET)) != 0) return XDP_DROP; tup.ipv4.saddr = hdr->ipv4->saddr; diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 3e02d7267de8..075c93ed143e 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -56,6 +56,8 @@ static void running_handler(int a); #define BPF_SOCKHASH_FILENAME "test_sockhash_kern.bpf.o" #define CG_PATH "/sockmap" +#define EDATAINTEGRITY 2001 + /* global sockets */ int s1, s2, c1, c2, p1, p2; int test_cnt; @@ -510,23 +512,25 @@ unwind_iov: return -ENOMEM; } -static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz) +/* TODO: Add verification logic for push, pull and pop data */ +static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz, + unsigned char *k_p, int *bytes_cnt_p) { - int i, j = 0, bytes_cnt = 0; - unsigned char k = 0; + int i, j, bytes_cnt = *bytes_cnt_p; + unsigned char k = *k_p; - for (i = 0; i < msg->msg_iovlen; i++) { + for (i = 0, j = 0; i < msg->msg_iovlen && size; i++, j = 0) { unsigned char *d = msg->msg_iov[i].iov_base; /* Special case test for skb ingress + ktls */ if (i == 0 && txmsg_ktls_skb) { if (msg->msg_iov[i].iov_len < 4) - return -EIO; + return -EDATAINTEGRITY; if (memcmp(d, "PASS", 4) != 0) { fprintf(stderr, "detected skb data error with skb ingress update @iov[%i]:%i \"%02x %02x %02x %02x\" != \"PASS\"\n", i, 0, d[0], d[1], d[2], d[3]); - return -EIO; + return -EDATAINTEGRITY; } j = 4; /* advance index past PASS header */ } @@ -536,7 +540,7 @@ static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz) fprintf(stderr, "detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n", i, j, d[j], k - 1, d[j+1], k); - return -EIO; + return -EDATAINTEGRITY; } bytes_cnt++; if (bytes_cnt == chunk_sz) { @@ -546,6 +550,8 @@ static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz) size--; } } + *k_p = k; + *bytes_cnt_p = bytes_cnt; return 0; } @@ -602,6 +608,8 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, float total_bytes, txmsg_pop_total; int fd_flags = O_NONBLOCK; struct timeval timeout; + unsigned char k = 0; + int bytes_cnt = 0; fd_set w; fcntl(fd, fd_flags); @@ -696,7 +704,7 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, iov_length * cnt : iov_length * iov_count; - errno = msg_verify_data(&msg, recv, chunk_sz); + errno = msg_verify_data(&msg, recv, chunk_sz, &k, &bytes_cnt); if (errno) { perror("data verify msg failed"); goto out_errno; @@ -704,7 +712,9 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, if (recvp) { errno = msg_verify_data(&msg_peek, recvp, - chunk_sz); + chunk_sz, + &k, + &bytes_cnt); if (errno) { perror("data verify msg_peek failed"); goto out_errno; @@ -812,7 +822,7 @@ static int sendmsg_test(struct sockmap_options *opt) s.bytes_sent, sent_Bps, sent_Bps/giga, s.bytes_recvd, recvd_Bps, recvd_Bps/giga, peek_flag ? "(peek_msg)" : ""); - if (err && txmsg_cork) + if (err && err != -EDATAINTEGRITY && txmsg_cork) err = 0; exit(err ? 1 : 0); } else if (rxpid == -1) { @@ -1596,7 +1606,7 @@ static void test_txmsg_pull(int cgrp, struct sockmap_options *opt) test_send_large(opt, cgrp); /* Test pull + redirect */ - txmsg_redir = 0; + txmsg_redir = 1; txmsg_start = 1; txmsg_end = 2; test_send(opt, cgrp); diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh deleted file mode 100755 index b42c24282c25..000000000000 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ /dev/null @@ -1,85 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# Copyright (c) 2018 Facebook -# Copyright (c) 2019 Cloudflare - -set -eu -readonly NS1="ns1-$(mktemp -u XXXXXX)" - -wait_for_ip() -{ - local _i - printf "Wait for IP %s to become available " "$1" - for _i in $(seq ${MAX_PING_TRIES}); do - printf "." - if ns1_exec ping -c 1 -W 1 "$1" >/dev/null 2>&1; then - echo " OK" - return - fi - sleep 1 - done - echo 1>&2 "ERROR: Timeout waiting for test IP to become available." - exit 1 -} - -get_prog_id() -{ - awk '/ id / {sub(/.* id /, "", $0); print($1)}' -} - -ns1_exec() -{ - ip netns exec ${NS1} "$@" -} - -setup() -{ - ip netns add ${NS1} - ns1_exec ip link set lo up - - ns1_exec sysctl -w net.ipv4.tcp_syncookies=2 - ns1_exec sysctl -w net.ipv4.tcp_window_scaling=0 - ns1_exec sysctl -w net.ipv4.tcp_timestamps=0 - ns1_exec sysctl -w net.ipv4.tcp_sack=0 - - wait_for_ip 127.0.0.1 - wait_for_ip ::1 -} - -cleanup() -{ - ip netns del ns1 2>/dev/null || : -} - -main() -{ - trap cleanup EXIT 2 3 6 15 - setup - - printf "Testing clsact..." - ns1_exec tc qdisc add dev "${TEST_IF}" clsact - ns1_exec tc filter add dev "${TEST_IF}" ingress \ - bpf obj "${BPF_PROG_OBJ}" sec "${CLSACT_SECTION}" da - - BPF_PROG_ID=$(ns1_exec tc filter show dev "${TEST_IF}" ingress | \ - get_prog_id) - ns1_exec "${PROG}" "${BPF_PROG_ID}" - ns1_exec tc qdisc del dev "${TEST_IF}" clsact - - printf "Testing XDP..." - ns1_exec ip link set "${TEST_IF}" xdp \ - object "${BPF_PROG_OBJ}" section "${XDP_SECTION}" - BPF_PROG_ID=$(ns1_exec ip link show "${TEST_IF}" | get_prog_id) - ns1_exec "${PROG}" "${BPF_PROG_ID}" -} - -DIR=$(dirname $0) -TEST_IF=lo -MAX_PING_TRIES=5 -BPF_PROG_OBJ="${DIR}/test_tcp_check_syncookie_kern.bpf.o" -CLSACT_SECTION="tc" -XDP_SECTION="xdp" -BPF_PROG_ID=0 -PROG="${DIR}/test_tcp_check_syncookie_user" - -main diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c deleted file mode 100644 index 3844f9b8232a..000000000000 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ /dev/null @@ -1,213 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (c) 2018 Facebook -// Copyright (c) 2019 Cloudflare - -#include <limits.h> -#include <string.h> -#include <stdlib.h> -#include <unistd.h> - -#include <arpa/inet.h> -#include <netinet/in.h> -#include <sys/types.h> -#include <sys/socket.h> - -#include <bpf/bpf.h> -#include <bpf/libbpf.h> - -#include "cgroup_helpers.h" -#include "network_helpers.h" - -static int get_map_fd_by_prog_id(int prog_id, bool *xdp) -{ - struct bpf_prog_info info = {}; - __u32 info_len = sizeof(info); - __u32 map_ids[1]; - int prog_fd = -1; - int map_fd = -1; - - prog_fd = bpf_prog_get_fd_by_id(prog_id); - if (prog_fd < 0) { - log_err("Failed to get fd by prog id %d", prog_id); - goto err; - } - - info.nr_map_ids = 1; - info.map_ids = (__u64)(unsigned long)map_ids; - - if (bpf_prog_get_info_by_fd(prog_fd, &info, &info_len)) { - log_err("Failed to get info by prog fd %d", prog_fd); - goto err; - } - - if (!info.nr_map_ids) { - log_err("No maps found for prog fd %d", prog_fd); - goto err; - } - - *xdp = info.type == BPF_PROG_TYPE_XDP; - - map_fd = bpf_map_get_fd_by_id(map_ids[0]); - if (map_fd < 0) - log_err("Failed to get fd by map id %d", map_ids[0]); -err: - if (prog_fd >= 0) - close(prog_fd); - return map_fd; -} - -static int run_test(int server_fd, int results_fd, bool xdp) -{ - int client = -1, srv_client = -1; - int ret = 0; - __u32 key = 0; - __u32 key_gen = 1; - __u32 key_mss = 2; - __u32 value = 0; - __u32 value_gen = 0; - __u32 value_mss = 0; - - if (bpf_map_update_elem(results_fd, &key, &value, 0) < 0) { - log_err("Can't clear results"); - goto err; - } - - if (bpf_map_update_elem(results_fd, &key_gen, &value_gen, 0) < 0) { - log_err("Can't clear results"); - goto err; - } - - if (bpf_map_update_elem(results_fd, &key_mss, &value_mss, 0) < 0) { - log_err("Can't clear results"); - goto err; - } - - client = connect_to_fd(server_fd, 0); - if (client == -1) - goto err; - - srv_client = accept(server_fd, NULL, 0); - if (srv_client == -1) { - log_err("Can't accept connection"); - goto err; - } - - if (bpf_map_lookup_elem(results_fd, &key, &value) < 0) { - log_err("Can't lookup result"); - goto err; - } - - if (value == 0) { - log_err("Didn't match syncookie: %u", value); - goto err; - } - - if (bpf_map_lookup_elem(results_fd, &key_gen, &value_gen) < 0) { - log_err("Can't lookup result"); - goto err; - } - - if (xdp && value_gen == 0) { - // SYN packets do not get passed through generic XDP, skip the - // rest of the test. - printf("Skipping XDP cookie check\n"); - goto out; - } - - if (bpf_map_lookup_elem(results_fd, &key_mss, &value_mss) < 0) { - log_err("Can't lookup result"); - goto err; - } - - if (value != value_gen) { - log_err("BPF generated cookie does not match kernel one"); - goto err; - } - - if (value_mss < 536 || value_mss > USHRT_MAX) { - log_err("Unexpected MSS retrieved"); - goto err; - } - - goto out; - -err: - ret = 1; -out: - close(client); - close(srv_client); - return ret; -} - -static int v6only_true(int fd, void *opts) -{ - int mode = true; - - return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode)); -} - -static int v6only_false(int fd, void *opts) -{ - int mode = false; - - return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode)); -} - -int main(int argc, char **argv) -{ - struct network_helper_opts opts = { 0 }; - int server = -1; - int server_v6 = -1; - int server_dual = -1; - int results = -1; - int err = 0; - bool xdp; - - if (argc < 2) { - fprintf(stderr, "Usage: %s prog_id\n", argv[0]); - exit(1); - } - - /* Use libbpf 1.0 API mode */ - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - - results = get_map_fd_by_prog_id(atoi(argv[1]), &xdp); - if (results < 0) { - log_err("Can't get map"); - goto err; - } - - server = start_server_str(AF_INET, SOCK_STREAM, "127.0.0.1", 0, NULL); - if (server == -1) - goto err; - - opts.post_socket_cb = v6only_true; - server_v6 = start_server_str(AF_INET6, SOCK_STREAM, "::1", 0, &opts); - if (server_v6 == -1) - goto err; - - opts.post_socket_cb = v6only_false; - server_dual = start_server_str(AF_INET6, SOCK_STREAM, "::0", 0, &opts); - if (server_dual == -1) - goto err; - - if (run_test(server, results, xdp)) - goto err; - - if (run_test(server_v6, results, xdp)) - goto err; - - if (run_test(server_dual, results, xdp)) - goto err; - - printf("ok\n"); - goto out; -err: - err = 1; -out: - close(server); - close(server_v6); - close(server_dual); - close(results); - return err; -} diff --git a/tools/testing/selftests/bpf/veristat.cfg b/tools/testing/selftests/bpf/veristat.cfg index 1a385061618d..e661ffdcaadf 100644 --- a/tools/testing/selftests/bpf/veristat.cfg +++ b/tools/testing/selftests/bpf/veristat.cfg @@ -15,3 +15,4 @@ test_usdt* test_verif_scale* test_xdp_noinline* xdp_synproxy* +verifier_search_pruning* diff --git a/tools/testing/selftests/drivers/net/hw/.gitignore b/tools/testing/selftests/drivers/net/hw/.gitignore new file mode 100644 index 000000000000..e9fe6ede681a --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/.gitignore @@ -0,0 +1 @@ +ncdevmem diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index c9f2f48fc30f..1c6a77480923 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -3,6 +3,7 @@ TEST_PROGS = \ csum.py \ devlink_port_split.py \ + devmem.py \ ethtool.sh \ ethtool_extended_state.sh \ ethtool_mm.sh \ @@ -26,4 +27,12 @@ TEST_INCLUDES := \ ../../../net/forwarding/tc_common.sh \ # +# YNL files, must be before "include ..lib.mk" +YNL_GEN_FILES := ncdevmem +TEST_GEN_FILES += $(YNL_GEN_FILES) + include ../../../lib.mk + +# YNL build +YNL_GENS := ethtool netdev +include ../../../net/ynl.mk diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py new file mode 100755 index 000000000000..1223f0f5c10c --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/devmem.py @@ -0,0 +1,45 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +from lib.py import ksft_run, ksft_exit +from lib.py import ksft_eq, KsftSkipEx +from lib.py import NetDrvEpEnv +from lib.py import bkg, cmd, rand_port, wait_port_listen +from lib.py import ksft_disruptive + + +def require_devmem(cfg): + if not hasattr(cfg, "_devmem_probed"): + port = rand_port() + probe_command = f"./ncdevmem -f {cfg.ifname}" + cfg._devmem_supported = cmd(probe_command, fail=False, shell=True).ret == 0 + cfg._devmem_probed = True + + if not cfg._devmem_supported: + raise KsftSkipEx("Test requires devmem support") + + +@ksft_disruptive +def check_rx(cfg) -> None: + cfg.require_v6() + require_devmem(cfg) + + port = rand_port() + listen_cmd = f"./ncdevmem -l -f {cfg.ifname} -s {cfg.v6} -p {port}" + + with bkg(listen_cmd) as socat: + wait_port_listen(port) + cmd(f"echo -e \"hello\\nworld\"| socat -u - TCP6:[{cfg.v6}]:{port}", host=cfg.remote, shell=True) + + ksft_eq(socat.stdout.strip(), "hello\nworld") + + +def main() -> None: + with NetDrvEpEnv(__file__) as cfg: + ksft_run([check_rx], + args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c new file mode 100644 index 000000000000..8e502a1f8f9b --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -0,0 +1,789 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * tcpdevmem netcat. Works similarly to netcat but does device memory TCP + * instead of regular TCP. Uses udmabuf to mock a dmabuf provider. + * + * Usage: + * + * On server: + * ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201 + * + * On client: + * echo -n "hello\nworld" | nc -s <server IP> 5201 -p 5201 + * + * Test data validation: + * + * On server: + * ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201 -v 7 + * + * On client: + * yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \ + * tr \\n \\0 | \ + * head -c 5G | \ + * nc <server IP> 5201 -p 5201 + * + * + * Note this is compatible with regular netcat. i.e. the sender or receiver can + * be replaced with regular netcat to test the RX or TX path in isolation. + */ +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + +#include <linux/uio.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <stdbool.h> +#include <string.h> +#include <errno.h> +#define __iovec_defined +#include <fcntl.h> +#include <malloc.h> +#include <error.h> + +#include <arpa/inet.h> +#include <sys/socket.h> +#include <sys/mman.h> +#include <sys/ioctl.h> +#include <sys/syscall.h> + +#include <linux/memfd.h> +#include <linux/dma-buf.h> +#include <linux/udmabuf.h> +#include <libmnl/libmnl.h> +#include <linux/types.h> +#include <linux/netlink.h> +#include <linux/genetlink.h> +#include <linux/netdev.h> +#include <linux/ethtool_netlink.h> +#include <time.h> +#include <net/if.h> + +#include "netdev-user.h" +#include "ethtool-user.h" +#include <ynl.h> + +#define PAGE_SHIFT 12 +#define TEST_PREFIX "ncdevmem" +#define NUM_PAGES 16000 + +#ifndef MSG_SOCK_DEVMEM +#define MSG_SOCK_DEVMEM 0x2000000 +#endif + +static char *server_ip; +static char *client_ip; +static char *port; +static size_t do_validation; +static int start_queue = -1; +static int num_queues = -1; +static char *ifname; +static unsigned int ifindex; +static unsigned int dmabuf_id; + +struct memory_buffer { + int fd; + size_t size; + + int devfd; + int memfd; + char *buf_mem; +}; + +struct memory_provider { + struct memory_buffer *(*alloc)(size_t size); + void (*free)(struct memory_buffer *ctx); + void (*memcpy_from_device)(void *dst, struct memory_buffer *src, + size_t off, int n); +}; + +static struct memory_buffer *udmabuf_alloc(size_t size) +{ + struct udmabuf_create create; + struct memory_buffer *ctx; + int ret; + + ctx = malloc(sizeof(*ctx)); + if (!ctx) + error(1, ENOMEM, "malloc failed"); + + ctx->size = size; + + ctx->devfd = open("/dev/udmabuf", O_RDWR); + if (ctx->devfd < 0) + error(1, errno, + "%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n", + TEST_PREFIX); + + ctx->memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING); + if (ctx->memfd < 0) + error(1, errno, "%s: [skip,no-memfd]\n", TEST_PREFIX); + + ret = fcntl(ctx->memfd, F_ADD_SEALS, F_SEAL_SHRINK); + if (ret < 0) + error(1, errno, "%s: [skip,fcntl-add-seals]\n", TEST_PREFIX); + + ret = ftruncate(ctx->memfd, size); + if (ret == -1) + error(1, errno, "%s: [FAIL,memfd-truncate]\n", TEST_PREFIX); + + memset(&create, 0, sizeof(create)); + + create.memfd = ctx->memfd; + create.offset = 0; + create.size = size; + ctx->fd = ioctl(ctx->devfd, UDMABUF_CREATE, &create); + if (ctx->fd < 0) + error(1, errno, "%s: [FAIL, create udmabuf]\n", TEST_PREFIX); + + ctx->buf_mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, + ctx->fd, 0); + if (ctx->buf_mem == MAP_FAILED) + error(1, errno, "%s: [FAIL, map udmabuf]\n", TEST_PREFIX); + + return ctx; +} + +static void udmabuf_free(struct memory_buffer *ctx) +{ + munmap(ctx->buf_mem, ctx->size); + close(ctx->fd); + close(ctx->memfd); + close(ctx->devfd); + free(ctx); +} + +static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src, + size_t off, int n) +{ + struct dma_buf_sync sync = {}; + + sync.flags = DMA_BUF_SYNC_START; + ioctl(src->fd, DMA_BUF_IOCTL_SYNC, &sync); + + memcpy(dst, src->buf_mem + off, n); + + sync.flags = DMA_BUF_SYNC_END; + ioctl(src->fd, DMA_BUF_IOCTL_SYNC, &sync); +} + +static struct memory_provider udmabuf_memory_provider = { + .alloc = udmabuf_alloc, + .free = udmabuf_free, + .memcpy_from_device = udmabuf_memcpy_from_device, +}; + +static struct memory_provider *provider = &udmabuf_memory_provider; + +static void print_nonzero_bytes(void *ptr, size_t size) +{ + unsigned char *p = ptr; + unsigned int i; + + for (i = 0; i < size; i++) + putchar(p[i]); +} + +void validate_buffer(void *line, size_t size) +{ + static unsigned char seed = 1; + unsigned char *ptr = line; + int errors = 0; + size_t i; + + for (i = 0; i < size; i++) { + if (ptr[i] != seed) { + fprintf(stderr, + "Failed validation: expected=%u, actual=%u, index=%lu\n", + seed, ptr[i], i); + errors++; + if (errors > 20) + error(1, 0, "validation failed."); + } + seed++; + if (seed == do_validation) + seed = 0; + } + + fprintf(stdout, "Validated buffer\n"); +} + +static int rxq_num(int ifindex) +{ + struct ethtool_channels_get_req *req; + struct ethtool_channels_get_rsp *rsp; + struct ynl_error yerr; + struct ynl_sock *ys; + int num = -1; + + ys = ynl_sock_create(&ynl_ethtool_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return -1; + } + + req = ethtool_channels_get_req_alloc(); + ethtool_channels_get_req_set_header_dev_index(req, ifindex); + rsp = ethtool_channels_get(ys, req); + if (rsp) + num = rsp->rx_count + rsp->combined_count; + ethtool_channels_get_req_free(req); + ethtool_channels_get_rsp_free(rsp); + + ynl_sock_destroy(ys); + + return num; +} + +#define run_command(cmd, ...) \ + ({ \ + char command[256]; \ + memset(command, 0, sizeof(command)); \ + snprintf(command, sizeof(command), cmd, ##__VA_ARGS__); \ + fprintf(stderr, "Running: %s\n", command); \ + system(command); \ + }) + +static int reset_flow_steering(void) +{ + /* Depending on the NIC, toggling ntuple off and on might not + * be allowed. Additionally, attempting to delete existing filters + * will fail if no filters are present. Therefore, do not enforce + * the exit status. + */ + + run_command("sudo ethtool -K %s ntuple off >&2", ifname); + run_command("sudo ethtool -K %s ntuple on >&2", ifname); + run_command( + "sudo ethtool -n %s | grep 'Filter:' | awk '{print $2}' | xargs -n1 ethtool -N %s delete >&2", + ifname, ifname); + return 0; +} + +static const char *tcp_data_split_str(int val) +{ + switch (val) { + case 0: + return "off"; + case 1: + return "auto"; + case 2: + return "on"; + default: + return "?"; + } +} + +static int configure_headersplit(bool on) +{ + struct ethtool_rings_get_req *get_req; + struct ethtool_rings_get_rsp *get_rsp; + struct ethtool_rings_set_req *req; + struct ynl_error yerr; + struct ynl_sock *ys; + int ret; + + ys = ynl_sock_create(&ynl_ethtool_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return -1; + } + + req = ethtool_rings_set_req_alloc(); + ethtool_rings_set_req_set_header_dev_index(req, ifindex); + /* 0 - off, 1 - auto, 2 - on */ + ethtool_rings_set_req_set_tcp_data_split(req, on ? 2 : 0); + ret = ethtool_rings_set(ys, req); + if (ret < 0) + fprintf(stderr, "YNL failed: %s\n", ys->err.msg); + ethtool_rings_set_req_free(req); + + if (ret == 0) { + get_req = ethtool_rings_get_req_alloc(); + ethtool_rings_get_req_set_header_dev_index(get_req, ifindex); + get_rsp = ethtool_rings_get(ys, get_req); + ethtool_rings_get_req_free(get_req); + if (get_rsp) + fprintf(stderr, "TCP header split: %s\n", + tcp_data_split_str(get_rsp->tcp_data_split)); + ethtool_rings_get_rsp_free(get_rsp); + } + + ynl_sock_destroy(ys); + + return ret; +} + +static int configure_rss(void) +{ + return run_command("sudo ethtool -X %s equal %d >&2", ifname, start_queue); +} + +static int configure_channels(unsigned int rx, unsigned int tx) +{ + return run_command("sudo ethtool -L %s rx %u tx %u", ifname, rx, tx); +} + +static int configure_flow_steering(struct sockaddr_in6 *server_sin) +{ + const char *type = "tcp6"; + const char *server_addr; + char buf[40]; + + inet_ntop(AF_INET6, &server_sin->sin6_addr, buf, sizeof(buf)); + server_addr = buf; + + if (IN6_IS_ADDR_V4MAPPED(&server_sin->sin6_addr)) { + type = "tcp4"; + server_addr = strrchr(server_addr, ':') + 1; + } + + return run_command("sudo ethtool -N %s flow-type %s %s %s dst-ip %s %s %s dst-port %s queue %d >&2", + ifname, + type, + client_ip ? "src-ip" : "", + client_ip ?: "", + server_addr, + client_ip ? "src-port" : "", + client_ip ? port : "", + port, start_queue); +} + +static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd, + struct netdev_queue_id *queues, + unsigned int n_queue_index, struct ynl_sock **ys) +{ + struct netdev_bind_rx_req *req = NULL; + struct netdev_bind_rx_rsp *rsp = NULL; + struct ynl_error yerr; + + *ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!*ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return -1; + } + + req = netdev_bind_rx_req_alloc(); + netdev_bind_rx_req_set_ifindex(req, ifindex); + netdev_bind_rx_req_set_fd(req, dmabuf_fd); + __netdev_bind_rx_req_set_queues(req, queues, n_queue_index); + + rsp = netdev_bind_rx(*ys, req); + if (!rsp) { + perror("netdev_bind_rx"); + goto err_close; + } + + if (!rsp->_present.id) { + perror("id not present"); + goto err_close; + } + + fprintf(stderr, "got dmabuf id=%d\n", rsp->id); + dmabuf_id = rsp->id; + + netdev_bind_rx_req_free(req); + netdev_bind_rx_rsp_free(rsp); + + return 0; + +err_close: + fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg); + netdev_bind_rx_req_free(req); + ynl_sock_destroy(*ys); + return -1; +} + +static void enable_reuseaddr(int fd) +{ + int opt = 1; + int ret; + + ret = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt)); + if (ret) + error(1, errno, "%s: [FAIL, SO_REUSEPORT]\n", TEST_PREFIX); + + ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt)); + if (ret) + error(1, errno, "%s: [FAIL, SO_REUSEADDR]\n", TEST_PREFIX); +} + +static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6) +{ + int ret; + + sin6->sin6_family = AF_INET6; + sin6->sin6_port = htons(port); + + ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr); + if (ret != 1) { + /* fallback to plain IPv4 */ + ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]); + if (ret != 1) + return -1; + + /* add ::ffff prefix */ + sin6->sin6_addr.s6_addr32[0] = 0; + sin6->sin6_addr.s6_addr32[1] = 0; + sin6->sin6_addr.s6_addr16[4] = 0; + sin6->sin6_addr.s6_addr16[5] = 0xffff; + } + + return 0; +} + +int do_server(struct memory_buffer *mem) +{ + char ctrl_data[sizeof(int) * 20000]; + struct netdev_queue_id *queues; + size_t non_page_aligned_frags = 0; + struct sockaddr_in6 client_addr; + struct sockaddr_in6 server_sin; + size_t page_aligned_frags = 0; + size_t total_received = 0; + socklen_t client_addr_len; + bool is_devmem = false; + char *tmp_mem = NULL; + struct ynl_sock *ys; + char iobuf[819200]; + char buffer[256]; + int socket_fd; + int client_fd; + size_t i = 0; + int ret; + + ret = parse_address(server_ip, atoi(port), &server_sin); + if (ret < 0) + error(1, 0, "parse server address"); + + if (reset_flow_steering()) + error(1, 0, "Failed to reset flow steering\n"); + + if (configure_headersplit(1)) + error(1, 0, "Failed to enable TCP header split\n"); + + /* Configure RSS to divert all traffic from our devmem queues */ + if (configure_rss()) + error(1, 0, "Failed to configure rss\n"); + + /* Flow steer our devmem flows to start_queue */ + if (configure_flow_steering(&server_sin)) + error(1, 0, "Failed to configure flow steering\n"); + + sleep(1); + + queues = malloc(sizeof(*queues) * num_queues); + + for (i = 0; i < num_queues; i++) { + queues[i]._present.type = 1; + queues[i]._present.id = 1; + queues[i].type = NETDEV_QUEUE_TYPE_RX; + queues[i].id = start_queue + i; + } + + if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) + error(1, 0, "Failed to bind\n"); + + tmp_mem = malloc(mem->size); + if (!tmp_mem) + error(1, ENOMEM, "malloc failed"); + + socket_fd = socket(AF_INET6, SOCK_STREAM, 0); + if (socket_fd < 0) + error(1, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX); + + enable_reuseaddr(socket_fd); + + fprintf(stderr, "binding to address %s:%d\n", server_ip, + ntohs(server_sin.sin6_port)); + + ret = bind(socket_fd, &server_sin, sizeof(server_sin)); + if (ret) + error(1, errno, "%s: [FAIL, bind]\n", TEST_PREFIX); + + ret = listen(socket_fd, 1); + if (ret) + error(1, errno, "%s: [FAIL, listen]\n", TEST_PREFIX); + + client_addr_len = sizeof(client_addr); + + inet_ntop(AF_INET6, &server_sin.sin6_addr, buffer, + sizeof(buffer)); + fprintf(stderr, "Waiting or connection on %s:%d\n", buffer, + ntohs(server_sin.sin6_port)); + client_fd = accept(socket_fd, &client_addr, &client_addr_len); + + inet_ntop(AF_INET6, &client_addr.sin6_addr, buffer, + sizeof(buffer)); + fprintf(stderr, "Got connection from %s:%d\n", buffer, + ntohs(client_addr.sin6_port)); + + while (1) { + struct iovec iov = { .iov_base = iobuf, + .iov_len = sizeof(iobuf) }; + struct dmabuf_cmsg *dmabuf_cmsg = NULL; + struct cmsghdr *cm = NULL; + struct msghdr msg = { 0 }; + struct dmabuf_token token; + ssize_t ret; + + is_devmem = false; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = ctrl_data; + msg.msg_controllen = sizeof(ctrl_data); + ret = recvmsg(client_fd, &msg, MSG_SOCK_DEVMEM); + fprintf(stderr, "recvmsg ret=%ld\n", ret); + if (ret < 0 && (errno == EAGAIN || errno == EWOULDBLOCK)) + continue; + if (ret < 0) { + perror("recvmsg"); + continue; + } + if (ret == 0) { + fprintf(stderr, "client exited\n"); + goto cleanup; + } + + i++; + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) { + if (cm->cmsg_level != SOL_SOCKET || + (cm->cmsg_type != SCM_DEVMEM_DMABUF && + cm->cmsg_type != SCM_DEVMEM_LINEAR)) { + fprintf(stderr, "skipping non-devmem cmsg\n"); + continue; + } + + dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm); + is_devmem = true; + + if (cm->cmsg_type == SCM_DEVMEM_LINEAR) { + /* TODO: process data copied from skb's linear + * buffer. + */ + fprintf(stderr, + "SCM_DEVMEM_LINEAR. dmabuf_cmsg->frag_size=%u\n", + dmabuf_cmsg->frag_size); + + continue; + } + + token.token_start = dmabuf_cmsg->frag_token; + token.token_count = 1; + + total_received += dmabuf_cmsg->frag_size; + fprintf(stderr, + "received frag_page=%llu, in_page_offset=%llu, frag_offset=%llu, frag_size=%u, token=%u, total_received=%lu, dmabuf_id=%u\n", + dmabuf_cmsg->frag_offset >> PAGE_SHIFT, + dmabuf_cmsg->frag_offset % getpagesize(), + dmabuf_cmsg->frag_offset, + dmabuf_cmsg->frag_size, dmabuf_cmsg->frag_token, + total_received, dmabuf_cmsg->dmabuf_id); + + if (dmabuf_cmsg->dmabuf_id != dmabuf_id) + error(1, 0, + "received on wrong dmabuf_id: flow steering error\n"); + + if (dmabuf_cmsg->frag_size % getpagesize()) + non_page_aligned_frags++; + else + page_aligned_frags++; + + provider->memcpy_from_device(tmp_mem, mem, + dmabuf_cmsg->frag_offset, + dmabuf_cmsg->frag_size); + + if (do_validation) + validate_buffer(tmp_mem, + dmabuf_cmsg->frag_size); + else + print_nonzero_bytes(tmp_mem, + dmabuf_cmsg->frag_size); + + ret = setsockopt(client_fd, SOL_SOCKET, + SO_DEVMEM_DONTNEED, &token, + sizeof(token)); + if (ret != 1) + error(1, 0, + "SO_DEVMEM_DONTNEED not enough tokens"); + } + if (!is_devmem) + error(1, 0, "flow steering error\n"); + + fprintf(stderr, "total_received=%lu\n", total_received); + } + + fprintf(stderr, "%s: ok\n", TEST_PREFIX); + + fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", + page_aligned_frags, non_page_aligned_frags); + + fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", + page_aligned_frags, non_page_aligned_frags); + +cleanup: + + free(tmp_mem); + close(client_fd); + close(socket_fd); + ynl_sock_destroy(ys); + + return 0; +} + +void run_devmem_tests(void) +{ + struct netdev_queue_id *queues; + struct memory_buffer *mem; + struct ynl_sock *ys; + size_t i = 0; + + mem = provider->alloc(getpagesize() * NUM_PAGES); + + /* Configure RSS to divert all traffic from our devmem queues */ + if (configure_rss()) + error(1, 0, "rss error\n"); + + queues = calloc(num_queues, sizeof(*queues)); + + if (configure_headersplit(1)) + error(1, 0, "Failed to configure header split\n"); + + if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) + error(1, 0, "Binding empty queues array should have failed\n"); + + for (i = 0; i < num_queues; i++) { + queues[i]._present.type = 1; + queues[i]._present.id = 1; + queues[i].type = NETDEV_QUEUE_TYPE_RX; + queues[i].id = start_queue + i; + } + + if (configure_headersplit(0)) + error(1, 0, "Failed to configure header split\n"); + + if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) + error(1, 0, "Configure dmabuf with header split off should have failed\n"); + + if (configure_headersplit(1)) + error(1, 0, "Failed to configure header split\n"); + + for (i = 0; i < num_queues; i++) { + queues[i]._present.type = 1; + queues[i]._present.id = 1; + queues[i].type = NETDEV_QUEUE_TYPE_RX; + queues[i].id = start_queue + i; + } + + if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) + error(1, 0, "Failed to bind\n"); + + /* Deactivating a bound queue should not be legal */ + if (!configure_channels(num_queues, num_queues - 1)) + error(1, 0, "Deactivating a bound queue should be illegal.\n"); + + /* Closing the netlink socket does an implicit unbind */ + ynl_sock_destroy(ys); + + provider->free(mem); +} + +int main(int argc, char *argv[]) +{ + struct memory_buffer *mem; + int is_server = 0, opt; + int ret; + + while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:")) != -1) { + switch (opt) { + case 'l': + is_server = 1; + break; + case 's': + server_ip = optarg; + break; + case 'c': + client_ip = optarg; + break; + case 'p': + port = optarg; + break; + case 'v': + do_validation = atoll(optarg); + break; + case 'q': + num_queues = atoi(optarg); + break; + case 't': + start_queue = atoi(optarg); + break; + case 'f': + ifname = optarg; + break; + case '?': + fprintf(stderr, "unknown option: %c\n", optopt); + break; + } + } + + if (!ifname) + error(1, 0, "Missing -f argument\n"); + + ifindex = if_nametoindex(ifname); + + if (!server_ip && !client_ip) { + if (start_queue < 0 && num_queues < 0) { + num_queues = rxq_num(ifindex); + if (num_queues < 0) + error(1, 0, "couldn't detect number of queues\n"); + if (num_queues < 2) + error(1, 0, + "number of device queues is too low\n"); + /* make sure can bind to multiple queues */ + start_queue = num_queues / 2; + num_queues /= 2; + } + + if (start_queue < 0 || num_queues < 0) + error(1, 0, "Both -t and -q are required\n"); + + run_devmem_tests(); + return 0; + } + + if (start_queue < 0 && num_queues < 0) { + num_queues = rxq_num(ifindex); + if (num_queues < 2) + error(1, 0, "number of device queues is too low\n"); + + num_queues = 1; + start_queue = rxq_num(ifindex) - num_queues; + + if (start_queue < 0) + error(1, 0, "couldn't detect number of queues\n"); + + fprintf(stderr, "using queues %d..%d\n", start_queue, start_queue + num_queues); + } + + for (; optind < argc; optind++) + fprintf(stderr, "extra arguments: %s\n", argv[optind]); + + if (start_queue < 0) + error(1, 0, "Missing -t argument\n"); + + if (num_queues < 0) + error(1, 0, "Missing -q argument\n"); + + if (!server_ip) + error(1, 0, "Missing -s argument\n"); + + if (!port) + error(1, 0, "Missing -p argument\n"); + + mem = provider->alloc(getpagesize() * NUM_PAGES); + ret = is_server ? do_server(mem) : 1; + provider->free(mem); + + return ret; +} diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh index 06021b2059b7..b175f4d966e5 100755 --- a/tools/testing/selftests/drivers/net/netcons_basic.sh +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -20,22 +20,26 @@ SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") # Simple script to test dynamic targets in netconsole SRCIF="" # to be populated later -SRCIP=192.168.1.1 +SRCIP=192.0.2.1 DSTIF="" # to be populated later -DSTIP=192.168.1.2 +DSTIP=192.0.2.2 PORT="6666" MSG="netconsole selftest" +USERDATA_KEY="key" +USERDATA_VALUE="value" TARGET=$(mktemp -u netcons_XXXXX) DEFAULT_PRINTK_VALUES=$(cat /proc/sys/kernel/printk) NETCONS_CONFIGFS="/sys/kernel/config/netconsole" NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" +KEY_PATH="${NETCONS_PATH}/userdata/${USERDATA_KEY}" # NAMESPACE will be populated by setup_ns with a random value NAMESPACE="" # IDs for netdevsim NSIM_DEV_1_ID=$((256 + RANDOM % 256)) NSIM_DEV_2_ID=$((512 + RANDOM % 256)) +NSIM_DEV_SYS_NEW="/sys/bus/netdevsim/new_device" # Used to create and delete namespaces source "${SCRIPTDIR}"/../../net/lib.sh @@ -43,7 +47,6 @@ source "${SCRIPTDIR}"/../../net/net_helper.sh # Create netdevsim interfaces create_ifaces() { - local NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" @@ -122,6 +125,8 @@ function cleanup() { # delete netconsole dynamic reconfiguration echo 0 > "${NETCONS_PATH}"/enabled + # Remove key + rmdir "${KEY_PATH}" # Remove the configfs entry rmdir "${NETCONS_PATH}" @@ -136,6 +141,18 @@ function cleanup() { echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk } +function set_user_data() { + if [[ ! -d "${NETCONS_PATH}""/userdata" ]] + then + echo "Userdata path not available in ${NETCONS_PATH}/userdata" + exit "${ksft_skip}" + fi + + mkdir -p "${KEY_PATH}" + VALUE_PATH="${KEY_PATH}""/value" + echo "${USERDATA_VALUE}" > "${VALUE_PATH}" +} + function listen_port_and_save_to() { local OUTPUT=${1} # Just wait for 2 seconds @@ -146,6 +163,10 @@ function listen_port_and_save_to() { function validate_result() { local TMPFILENAME="$1" + # TMPFILENAME will contain something like: + # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM + # key=value + # Check if the file exists if [ ! -f "$TMPFILENAME" ]; then echo "FAIL: File was not generated." >&2 @@ -158,6 +179,12 @@ function validate_result() { exit "${ksft_fail}" fi + if ! grep -q "${USERDATA_KEY}=${USERDATA_VALUE}" "${TMPFILENAME}"; then + echo "FAIL: ${USERDATA_KEY}=${USERDATA_VALUE} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + exit "${ksft_fail}" + fi + # Delete the file once it is validated, otherwise keep it # for debugging purposes rm "${TMPFILENAME}" @@ -185,6 +212,11 @@ function check_for_dependencies() { exit "${ksft_skip}" fi + if [ ! -f "${NSIM_DEV_SYS_NEW}" ]; then + echo "SKIP: file ${NSIM_DEV_SYS_NEW} does not exist. Check if CONFIG_NETDEVSIM is enabled" >&2 + exit "${ksft_skip}" + fi + if [ ! -d "${NETCONS_CONFIGFS}" ]; then echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2 exit "${ksft_skip}" @@ -220,6 +252,8 @@ trap cleanup EXIT set_network # Create a dynamic target for netconsole create_dynamic_target +# Set userdata "key" with the "value" value +set_user_data # Listed for netconsole port inside the namespace and destination interface listen_port_and_save_to "${OUTPUT_FILE}" & # Wait for socat to start and listen to the port. diff --git a/tools/testing/selftests/drivers/net/netdevsim/Makefile b/tools/testing/selftests/drivers/net/netdevsim/Makefile index 5bace0b7fb57..07b7c46d3311 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/Makefile +++ b/tools/testing/selftests/drivers/net/netdevsim/Makefile @@ -4,11 +4,14 @@ TEST_PROGS = devlink.sh \ devlink_in_netns.sh \ devlink_trap.sh \ ethtool-coalesce.sh \ + ethtool-features.sh \ ethtool-fec.sh \ ethtool-pause.sh \ ethtool-ring.sh \ fib.sh \ + fib_notifications.sh \ hw_stats_l3.sh \ + macsec-offload.sh \ nexthop.sh \ peer.sh \ psample.sh \ diff --git a/tools/testing/selftests/drivers/net/netdevsim/config b/tools/testing/selftests/drivers/net/netdevsim/config index adf45a3a78b4..5117c78ddf0a 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/config +++ b/tools/testing/selftests/drivers/net/netdevsim/config @@ -1,6 +1,7 @@ CONFIG_DUMMY=y CONFIG_GENEVE=m CONFIG_IPV6=y +CONFIG_MACSEC=m CONFIG_NETDEVSIM=m CONFIG_NET_SCH_MQPRIO=y CONFIG_NET_SCH_MULTIQ=y diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-features.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-features.sh new file mode 100644 index 000000000000..bc210dc6ad2d --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-features.sh @@ -0,0 +1,31 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only + +source ethtool-common.sh + +NSIM_NETDEV=$(make_netdev) + +set -o pipefail + +FEATS=" + tx-checksum-ip-generic + tx-scatter-gather + tx-tcp-segmentation + generic-segmentation-offload + generic-receive-offload" + +for feat in $FEATS ; do + s=$(ethtool --json -k $NSIM_NETDEV | jq ".[].\"$feat\".active" 2>/dev/null) + check $? "$s" true + + s=$(ethtool --json -k $NSIM_NETDEV | jq ".[].\"$feat\".fixed" 2>/dev/null) + check $? "$s" false +done + +if [ $num_errors -eq 0 ]; then + echo "PASSED all $((num_passes)) checks" + exit 0 +else + echo "FAILED $num_errors/$((num_errors+num_passes)) checks" + exit 1 +fi diff --git a/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh b/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh new file mode 100755 index 000000000000..98033e6667d2 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh @@ -0,0 +1,117 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only + +source ethtool-common.sh + +NSIM_NETDEV=$(make_netdev) +MACSEC_NETDEV=macsec_nsim + +set -o pipefail + +if ! ethtool -k $NSIM_NETDEV | grep -q 'macsec-hw-offload: on'; then + echo "SKIP: netdevsim doesn't support MACsec offload" + exit 4 +fi + +if ! ip link add link $NSIM_NETDEV $MACSEC_NETDEV type macsec offload mac 2>/dev/null; then + echo "SKIP: couldn't create macsec device" + exit 4 +fi +ip link del $MACSEC_NETDEV + +# +# test macsec offload API +# + +ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}" type macsec port 4 offload mac +check $? + +ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}2" type macsec address "aa:bb:cc:dd:ee:ff" port 5 offload mac +check $? + +ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}3" type macsec sci abbacdde01020304 offload mac +check $? + +ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}4" type macsec port 8 offload mac 2> /dev/null +check $? '' '' 1 + +ip macsec add "${MACSEC_NETDEV}" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012 +check $? + +ip macsec add "${MACSEC_NETDEV}" rx port 1234 address "1c:ed:de:ad:be:ef" +check $? + +ip macsec add "${MACSEC_NETDEV}" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on \ + key 00 0123456789abcdef0123456789abcdef +check $? + +ip macsec add "${MACSEC_NETDEV}" rx port 1235 address "1c:ed:de:ad:be:ef" 2> /dev/null +check $? '' '' 1 + +# can't disable macsec offload when SAs are configured +ip link set "${MACSEC_NETDEV}" type macsec offload off 2> /dev/null +check $? '' '' 1 + +ip macsec offload "${MACSEC_NETDEV}" off 2> /dev/null +check $? '' '' 1 + +# toggle macsec offload via rtnetlink +ip link set "${MACSEC_NETDEV}2" type macsec offload off +check $? + +ip link set "${MACSEC_NETDEV}2" type macsec offload mac +check $? + +# toggle macsec offload via genetlink +ip macsec offload "${MACSEC_NETDEV}2" off +check $? + +ip macsec offload "${MACSEC_NETDEV}2" mac +check $? + +for dev in ${MACSEC_NETDEV}{,2,3} ; do + ip link del $dev + check $? +done + + +# +# test ethtool features when toggling offload +# + +ip link add link $NSIM_NETDEV $MACSEC_NETDEV type macsec offload mac +TMP_FEATS_ON_1="$(ethtool -k $MACSEC_NETDEV)" + +ip link set $MACSEC_NETDEV type macsec offload off +TMP_FEATS_OFF_1="$(ethtool -k $MACSEC_NETDEV)" + +ip link set $MACSEC_NETDEV type macsec offload mac +TMP_FEATS_ON_2="$(ethtool -k $MACSEC_NETDEV)" + +[ "$TMP_FEATS_ON_1" = "$TMP_FEATS_ON_2" ] +check $? + +ip link del $MACSEC_NETDEV + +ip link add link $NSIM_NETDEV $MACSEC_NETDEV type macsec +check $? + +TMP_FEATS_OFF_2="$(ethtool -k $MACSEC_NETDEV)" +[ "$TMP_FEATS_OFF_1" = "$TMP_FEATS_OFF_2" ] +check $? + +ip link set $MACSEC_NETDEV type macsec offload mac +check $? + +TMP_FEATS_ON_3="$(ethtool -k $MACSEC_NETDEV)" +[ "$TMP_FEATS_ON_1" = "$TMP_FEATS_ON_3" ] +check $? + + +if [ $num_errors -eq 0 ]; then + echo "PASSED all $((num_passes)) checks" + exit 0 +else + echo "FAILED $num_errors/$((num_errors+num_passes)) checks" + exit 1 +fi diff --git a/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc b/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc new file mode 100644 index 000000000000..35e8d47d6072 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc @@ -0,0 +1,101 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Test tracefs GID mount option +# requires: "[gid=<gid>]":README + +fail() { + local msg="$1" + + echo "FAILED: $msg" + exit_fail +} + +find_alternate_gid() { + local original_gid="$1" + tac /etc/group | grep -v ":$original_gid:" | head -1 | cut -d: -f3 +} + +mount_tracefs_with_options() { + local mount_point="$1" + local options="$2" + + mount -t tracefs -o "$options" nodev "$mount_point" + + setup +} + +unmount_tracefs() { + local mount_point="$1" + + # Need to make sure the mount isn't busy so that we can umount it + (cd $mount_point; finish_ftrace;) + + cleanup +} + +create_instance() { + local mount_point="$1" + local instance="$mount_point/instances/$(mktemp -u test-XXXXXX)" + + mkdir "$instance" + echo "$instance" +} + +remove_instance() { + local instance="$1" + + rmdir "$instance" +} + +check_gid() { + local mount_point="$1" + local expected_gid="$2" + + echo "Checking permission group ..." + + cd "$mount_point" + + for file in "." "events" "events/sched" "events/sched/sched_switch" "events/sched/sched_switch/enable"; do + local gid=`stat -c "%g" $file` + if [ "$gid" -ne "$expected_gid" ]; then + cd - # Return to the previous working directory (tracefs root) + fail "$(realpath $file): Expected group $expected_gid; Got group $gid" + fi + done + + cd - # Return to the previous working directory (tracefs root) +} + +test_gid_mount_option() { + local mount_point=$(get_mount_point) + local mount_options=$(get_mnt_options "$mount_point") + local original_group=$(stat -c "%g" .) + local other_group=$(find_alternate_gid "$original_group") + + # Set up mount options with new GID for testing + local new_options=`echo "$mount_options" | sed -e "s/gid=[0-9]*/gid=$other_group/"` + if [ "$new_options" = "$mount_options" ]; then + new_options="$mount_options,gid=$other_group" + mount_options="$mount_options,gid=$original_group" + fi + + # Unmount existing tracefs instance and mount with new GID + unmount_tracefs "$mount_point" + mount_tracefs_with_options "$mount_point" "$new_options" + + check_gid "$mount_point" "$other_group" + + # Check that files created after the mount inherit the GID + local instance=$(create_instance "$mount_point") + check_gid "$instance" "$other_group" + remove_instance "$instance" + + # Unmount and remount with the original GID + unmount_tracefs "$mount_point" + mount_tracefs_with_options "$mount_point" "$mount_options" + check_gid "$mount_point" "$original_group" +} + +test_gid_mount_option + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc index 094419e190c2..e71cc3ad0bdf 100644 --- a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc +++ b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc @@ -1,24 +1,14 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: Test file and directory ownership changes for eventfs +# requires: "[gid=<gid>]":README original_group=`stat -c "%g" .` original_owner=`stat -c "%u" .` -mount_point=`stat -c '%m' .` +local mount_point=$(get_mount_point) -# If stat -c '%m' does not work (e.g. busybox) or failed, try to use the -# current working directory (which should be a tracefs) as the mount point. -if [ ! -d "$mount_point" ]; then - if mount | grep -qw $PWD ; then - mount_point=$PWD - else - # If PWD doesn't work, that is an environmental problem. - exit_unresolved - fi -fi - -mount_options=`mount | grep "$mount_point" | sed -e 's/.*(\(.*\)).*/\1/'` +mount_options=$(get_mnt_options "$mount_point") # find another owner and group that is not the original other_group=`tac /etc/group | grep -v ":$original_group:" | head -1 | cut -d: -f3` diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index 779f3e62ec90..84d6a9c7ad67 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -193,3 +193,28 @@ ftrace_errlog_check() { # err-prefix command-with-error-pos-by-^ command-file # " Command: " and "^\n" => 13 test $(expr 13 + $pos) -eq $N } + +# Helper to get the tracefs mount point +get_mount_point() { + local mount_point=`stat -c '%m' .` + + # If stat -c '%m' does not work (e.g. busybox) or failed, try to use the + # current working directory (which should be a tracefs) as the mount point. + if [ ! -d "$mount_point" ]; then + if mount | grep -qw "$PWD"; then + mount_point=$PWD + else + # If PWD doesn't work, that is an environmental problem. + exit_unresolved + fi + fi + echo "$mount_point" +} + +# Helper function to retrieve mount options for a given mount point +get_mnt_options() { + local mnt_point="$1" + local opts=$(mount | grep -m1 "$mnt_point" | sed -e 's/.*(\(.*\)).*/\1/') + + echo "$opts" +}
\ No newline at end of file diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh index e7008f614ad7..6a3b8503264e 100755 --- a/tools/testing/selftests/intel_pstate/run.sh +++ b/tools/testing/selftests/intel_pstate/run.sh @@ -44,6 +44,11 @@ if [ $UID != 0 ] && [ $EVALUATE_ONLY == 0 ]; then exit $ksft_skip fi +if ! command -v cpupower &> /dev/null; then + echo $msg cpupower could not be found, please install it >&2 + exit $ksft_skip +fi + max_cpus=$(($(nproc)-1)) function run_test () { @@ -87,9 +92,9 @@ mkt_freq=${_mkt_freq}0 # Get the ranges from cpupower _min_freq=$(cpupower frequency-info -l | tail -1 | awk ' { print $1 } ') -min_freq=$(($_min_freq / 1000)) +min_freq=$((_min_freq / 1000)) _max_freq=$(cpupower frequency-info -l | tail -1 | awk ' { print $2 } ') -max_freq=$(($_max_freq / 1000)) +max_freq=$((_max_freq / 1000)) [ $EVALUATE_ONLY -eq 0 ] && for freq in `seq $max_freq -100 $min_freq` diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 02e1204971b0..acec529baaca 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -36,6 +36,8 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +TEST_GEN_MODS_DIR := page_frag + TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test TEST_GEN_FILES += gup_longterm @@ -126,6 +128,7 @@ TEST_FILES += test_hmm.sh TEST_FILES += va_high_addr_switch.sh TEST_FILES += charge_reserved_hugetlb.sh TEST_FILES += hugetlb_reparenting_test.sh +TEST_FILES += test_page_frag.sh # required by charge_reserved_hugetlb.sh TEST_FILES += write_hugetlb_memory.sh diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile new file mode 100644 index 000000000000..58dda74d50a3 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/Makefile @@ -0,0 +1,18 @@ +PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = page_frag_test.ko + +obj-m += page_frag_test.o + +all: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) clean diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c new file mode 100644 index 000000000000..e806c1866e36 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Test module for page_frag cache + * + * Copyright (C) 2024 Yunsheng Lin <[email protected]> + */ + +#include <linux/module.h> +#include <linux/cpumask.h> +#include <linux/completion.h> +#include <linux/ptr_ring.h> +#include <linux/kthread.h> +#include <linux/page_frag_cache.h> + +#define TEST_FAILED_PREFIX "page_frag_test failed: " + +static struct ptr_ring ptr_ring; +static int nr_objs = 512; +static atomic_t nthreads; +static struct completion wait; +static struct page_frag_cache test_nc; +static int test_popped; +static int test_pushed; +static bool force_exit; + +static int nr_test = 2000000; +module_param(nr_test, int, 0); +MODULE_PARM_DESC(nr_test, "number of iterations to test"); + +static bool test_align; +module_param(test_align, bool, 0); +MODULE_PARM_DESC(test_align, "use align API for testing"); + +static int test_alloc_len = 2048; +module_param(test_alloc_len, int, 0); +MODULE_PARM_DESC(test_alloc_len, "alloc len for testing"); + +static int test_push_cpu; +module_param(test_push_cpu, int, 0); +MODULE_PARM_DESC(test_push_cpu, "test cpu for pushing fragment"); + +static int test_pop_cpu; +module_param(test_pop_cpu, int, 0); +MODULE_PARM_DESC(test_pop_cpu, "test cpu for popping fragment"); + +static int page_frag_pop_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_frag pop test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_popped < nr_test) { + void *obj = __ptr_ring_consume(ring); + + if (obj) { + test_popped++; + page_frag_free(obj); + } else { + if (force_exit) + break; + + cond_resched(); + } + } + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + pr_info("page_frag pop test thread exits on cpu %d\n", + smp_processor_id()); + + return 0; +} + +static int page_frag_push_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_frag push test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_pushed < nr_test && !force_exit) { + void *va; + int ret; + + if (test_align) { + va = page_frag_alloc_align(&test_nc, test_alloc_len, + GFP_KERNEL, SMP_CACHE_BYTES); + + if ((unsigned long)va & (SMP_CACHE_BYTES - 1)) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "unaligned va returned\n"); + } + } else { + va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + } + + if (!va) + continue; + + ret = __ptr_ring_produce(ring, va); + if (ret) { + page_frag_free(va); + cond_resched(); + } else { + test_pushed++; + } + } + + pr_info("page_frag push test thread exits on cpu %d\n", + smp_processor_id()); + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + return 0; +} + +static int __init page_frag_test_init(void) +{ + struct task_struct *tsk_push, *tsk_pop; + int last_pushed = 0, last_popped = 0; + ktime_t start; + u64 duration; + int ret; + + page_frag_cache_init(&test_nc); + atomic_set(&nthreads, 2); + init_completion(&wait); + + if (test_alloc_len > PAGE_SIZE || test_alloc_len <= 0 || + !cpu_active(test_push_cpu) || !cpu_active(test_pop_cpu)) + return -EINVAL; + + ret = ptr_ring_init(&ptr_ring, nr_objs, GFP_KERNEL); + if (ret) + return ret; + + tsk_push = kthread_create_on_cpu(page_frag_push_thread, &ptr_ring, + test_push_cpu, "page_frag_push"); + if (IS_ERR(tsk_push)) + return PTR_ERR(tsk_push); + + tsk_pop = kthread_create_on_cpu(page_frag_pop_thread, &ptr_ring, + test_pop_cpu, "page_frag_pop"); + if (IS_ERR(tsk_pop)) { + kthread_stop(tsk_push); + return PTR_ERR(tsk_pop); + } + + start = ktime_get(); + wake_up_process(tsk_push); + wake_up_process(tsk_pop); + + pr_info("waiting for test to complete\n"); + + while (!wait_for_completion_timeout(&wait, msecs_to_jiffies(10000))) { + /* exit if there is no progress for push or pop size */ + if (last_pushed == test_pushed || last_popped == test_popped) { + WARN_ONCE(true, TEST_FAILED_PREFIX "no progress\n"); + force_exit = true; + continue; + } + + last_pushed = test_pushed; + last_popped = test_popped; + pr_info("page_frag_test progress: pushed = %d, popped = %d\n", + test_pushed, test_popped); + } + + if (force_exit) { + pr_err(TEST_FAILED_PREFIX "exit with error\n"); + goto out; + } + + duration = (u64)ktime_us_delta(ktime_get(), start); + pr_info("%d of iterations for %s testing took: %lluus\n", nr_test, + test_align ? "aligned" : "non-aligned", duration); + +out: + ptr_ring_cleanup(&ptr_ring, NULL); + page_frag_cache_drain(&test_nc); + + return -EAGAIN; +} + +static void __exit page_frag_test_exit(void) +{ +} + +module_init(page_frag_test_init); +module_exit(page_frag_test_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yunsheng Lin <[email protected]>"); +MODULE_DESCRIPTION("Test module for page_frag"); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index c5797ad1d37b..2c5394584af4 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -75,6 +75,8 @@ separated by spaces: read-only VMAs - mdwe test prctl(PR_SET_MDWE, ...) +- page_frag + test handling of page fragment allocation and freeing example: ./run_vmtests.sh -t "hmm mmap ksm" EOF @@ -456,6 +458,12 @@ CATEGORY="mkdirty" run_test ./mkdirty CATEGORY="mdwe" run_test ./mdwe_test +CATEGORY="page_frag" run_test ./test_page_frag.sh smoke + +CATEGORY="page_frag" run_test ./test_page_frag.sh aligned + +CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned + echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix echo "1..${count_total}" | tap_output diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh new file mode 100755 index 000000000000..f55b105084cf --- /dev/null +++ b/tools/testing/selftests/mm/test_page_frag.sh @@ -0,0 +1,175 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2024 Yunsheng Lin <[email protected]> +# Copyright (C) 2018 Uladzislau Rezki (Sony) <[email protected]> +# +# This is a test script for the kernel test driver to test the +# correctness and performance of page_frag's implementation. +# Therefore it is just a kernel module loader. You can specify +# and pass different parameters in order to: +# a) analyse performance of page fragment allocations; +# b) stressing and stability check of page_frag subsystem. + +DRIVER="./page_frag/page_frag_test.ko" +CPU_LIST=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2) +TEST_CPU_0=$(echo $CPU_LIST | awk '{print $1}') + +if [ $(echo $CPU_LIST | wc -w) -gt 1 ]; then + TEST_CPU_1=$(echo $CPU_LIST | awk '{print $2}') + NR_TEST=100000000 +else + TEST_CPU_1=$TEST_CPU_0 + NR_TEST=1000000 +fi + +# 1 if fails +exitcode=1 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +check_test_failed_prefix() { + if dmesg | grep -q 'page_frag_test failed:';then + echo "page_frag_test failed, please check dmesg" + exit $exitcode + fi +} + +# +# Static templates for testing of page_frag APIs. +# Also it is possible to pass any supported parameters manually. +# +SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1" +NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST" +ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1" + +check_test_requirements() +{ + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit $ksft_skip + fi + + if ! which insmod > /dev/null 2>&1; then + echo "$0: You need insmod installed" + exit $ksft_skip + fi + + if [ ! -f $DRIVER ]; then + echo "$0: You need to compile page_frag_test module" + exit $ksft_skip + fi +} + +run_nonaligned_check() +{ + echo "Run performance tests to evaluate how fast nonaligned alloc API is." + + insmod $DRIVER $NONALIGNED_PARAM > /dev/null 2>&1 +} + +run_aligned_check() +{ + echo "Run performance tests to evaluate how fast aligned alloc API is." + + insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1 +} + +run_smoke_check() +{ + echo "Run smoke test." + + insmod $DRIVER $SMOKE_PARAM > /dev/null 2>&1 +} + +usage() +{ + echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | " + echo "manual parameters" + echo + echo "Valid tests and parameters:" + echo + modinfo $DRIVER + echo + echo "Example usage:" + echo + echo "# Shows help message" + echo "$0" + echo + echo "# Smoke testing" + echo "$0 smoke" + echo + echo "# Performance testing for nonaligned alloc API" + echo "$0 nonaligned" + echo + echo "# Performance testing for aligned alloc API" + echo "$0 aligned" + echo + exit 0 +} + +function validate_passed_args() +{ + VALID_ARGS=`modinfo $DRIVER | awk '/parm:/ {print $2}' | sed 's/:.*//'` + + # + # Something has been passed, check it. + # + for passed_arg in $@; do + key=${passed_arg//=*/} + valid=0 + + for valid_arg in $VALID_ARGS; do + if [[ $key = $valid_arg ]]; then + valid=1 + break + fi + done + + if [[ $valid -ne 1 ]]; then + echo "Error: key is not correct: ${key}" + exit $exitcode + fi + done +} + +function run_manual_check() +{ + # + # Validate passed parameters. If there is wrong one, + # the script exists and does not execute further. + # + validate_passed_args $@ + + echo "Run the test with following parameters: $@" + insmod $DRIVER $@ > /dev/null 2>&1 +} + +function run_test() +{ + if [ $# -eq 0 ]; then + usage + else + if [[ "$1" = "smoke" ]]; then + run_smoke_check + elif [[ "$1" = "nonaligned" ]]; then + run_nonaligned_check + elif [[ "$1" = "aligned" ]]; then + run_aligned_check + else + run_manual_check $@ + fi + fi + + check_test_failed_prefix + + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +check_test_requirements +run_test $@ + +exit 0 diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index 852e7281026e..717539eddf98 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -18,7 +18,7 @@ bool test_uffdio_wp = true; unsigned long long *count_verify; uffd_test_ops_t *uffd_test_ops; uffd_test_case_ops_t *uffd_test_case_ops; -pthread_barrier_t ready_for_fork; +atomic_bool ready_for_fork; static int uffd_mem_fd_create(off_t mem_size, bool hugetlb) { @@ -519,8 +519,7 @@ void *uffd_poll_thread(void *arg) pollfd[1].fd = pipefd[cpu*2]; pollfd[1].events = POLLIN; - /* Ready for parent thread to fork */ - pthread_barrier_wait(&ready_for_fork); + ready_for_fork = true; for (;;) { ret = poll(pollfd, 2, -1); diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 3e6228d8e0dc..a70ae10b5f62 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -33,6 +33,7 @@ #include <inttypes.h> #include <stdint.h> #include <sys/random.h> +#include <stdatomic.h> #include "../kselftest.h" #include "vm_util.h" @@ -104,7 +105,7 @@ extern bool map_shared; extern bool test_uffdio_wp; extern unsigned long long *count_verify; extern volatile bool test_uffdio_copy_eexist; -extern pthread_barrier_t ready_for_fork; +extern atomic_bool ready_for_fork; extern uffd_test_ops_t anon_uffd_test_ops; extern uffd_test_ops_t shmem_uffd_test_ops; diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index c8a3b1c7edff..a2e71b1636e7 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -241,8 +241,7 @@ static void *fork_event_consumer(void *data) fork_event_args *args = data; struct uffd_msg msg = { 0 }; - /* Ready for parent thread to fork */ - pthread_barrier_wait(&ready_for_fork); + ready_for_fork = true; /* Read until a full msg received */ while (uffd_read_msg(args->parent_uffd, &msg)); @@ -311,12 +310,11 @@ static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) /* Prepare a thread to resolve EVENT_FORK */ if (with_event) { - pthread_barrier_init(&ready_for_fork, NULL, 2); + ready_for_fork = false; if (pthread_create(&thread, NULL, fork_event_consumer, &args)) err("pthread_create()"); - /* Wait for child thread to start before forking */ - pthread_barrier_wait(&ready_for_fork); - pthread_barrier_destroy(&ready_for_fork); + while (!ready_for_fork) + ; /* Wait for the poll_thread to start executing before forking */ } child = fork(); @@ -781,7 +779,7 @@ static void uffd_sigbus_test_common(bool wp) char c; struct uffd_args args = { 0 }; - pthread_barrier_init(&ready_for_fork, NULL, 2); + ready_for_fork = false; fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); @@ -798,9 +796,8 @@ static void uffd_sigbus_test_common(bool wp) if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); - /* Wait for child thread to start before forking */ - pthread_barrier_wait(&ready_for_fork); - pthread_barrier_destroy(&ready_for_fork); + while (!ready_for_fork) + ; /* Wait for the poll_thread to start executing before forking */ pid = fork(); if (pid < 0) @@ -841,7 +838,7 @@ static void uffd_events_test_common(bool wp) char c; struct uffd_args args = { 0 }; - pthread_barrier_init(&ready_for_fork, NULL, 2); + ready_for_fork = false; fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); if (uffd_register(uffd, area_dst, nr_pages * page_size, @@ -852,9 +849,8 @@ static void uffd_events_test_common(bool wp) if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) err("uffd_poll_thread create"); - /* Wait for child thread to start before forking */ - pthread_barrier_wait(&ready_for_fork); - pthread_barrier_destroy(&ready_for_fork); + while (!ready_for_fork) + ; /* Wait for the poll_thread to start executing before forking */ pid = fork(); if (pid < 0) diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index c6a8c732b802..68801e1a9ec2 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -1414,6 +1414,13 @@ TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid) ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/b", 0, 0, 0), 0); ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/BB/b", 0, 0, 0), 0); + ASSERT_EQ(mount("testing", "/mnt/A", "ramfs", MS_NOATIME | MS_NODEV, + "size=100000,mode=700"), 0); + + ASSERT_EQ(mkdir("/mnt/A/AA", 0777), 0); + + ASSERT_EQ(mount("/tmp", "/mnt/A/AA", NULL, MS_BIND | MS_REC, NULL), 0); + open_tree_fd = sys_open_tree(-EBADF, "/mnt/A", AT_RECURSIVE | AT_EMPTY_PATH | @@ -1433,6 +1440,8 @@ TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid) ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/BB/b", 0, 0, 0), 0); ASSERT_EQ(expected_uid_gid(open_tree_fd, "B/b", 0, 0, 0), 0); ASSERT_EQ(expected_uid_gid(open_tree_fd, "B/BB/b", 0, 0, 0), 0); + + (void)umount2("/mnt/A", MNT_DETACH); } TEST_F(mount_setattr, mount_attr_nosymfollow) diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 217d8b7a7365..48973e78d46b 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -2,6 +2,7 @@ bind_bhash bind_timewait bind_wildcard +busy_poller cmsg_sender diag_uid epoll_busy_poll @@ -18,7 +19,6 @@ ipv6_flowlabel_mgr log.txt msg_oob msg_zerocopy -ncdevmem nettest psock_fanout psock_snd diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 26a4883a65c9..2b2a5ec7fa6a 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -96,9 +96,11 @@ TEST_PROGS += fdb_flush.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh TEST_PROGS += bpf_offload.py +TEST_PROGS += ipv6_route_update_soft_lockup.sh +TEST_PROGS += busy_poll_test.sh # YNL files, must be before "include ..lib.mk" -YNL_GEN_FILES := ncdevmem +YNL_GEN_FILES := busy_poller TEST_GEN_FILES += $(YNL_GEN_FILES) TEST_FILES := settings diff --git a/tools/testing/selftests/net/busy_poll_test.sh b/tools/testing/selftests/net/busy_poll_test.sh new file mode 100755 index 000000000000..7db292ec4884 --- /dev/null +++ b/tools/testing/selftests/net/busy_poll_test.sh @@ -0,0 +1,165 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +source net_helper.sh + +NSIM_SV_ID=$((256 + RANDOM % 256)) +NSIM_SV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_SV_ID +NSIM_CL_ID=$((512 + RANDOM % 256)) +NSIM_CL_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_CL_ID + +NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device +NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device +NSIM_DEV_SYS_LINK=/sys/bus/netdevsim/link_device +NSIM_DEV_SYS_UNLINK=/sys/bus/netdevsim/unlink_device + +SERVER_IP=192.168.1.1 +CLIENT_IP=192.168.1.2 +SERVER_PORT=48675 + +# busy poll config +MAX_EVENTS=8 +BUSY_POLL_USECS=0 +BUSY_POLL_BUDGET=16 +PREFER_BUSY_POLL=1 + +# IRQ deferral config +NAPI_DEFER_HARD_IRQS=100 +GRO_FLUSH_TIMEOUT=50000 +SUSPEND_TIMEOUT=20000000 + +setup_ns() +{ + set -e + ip netns add nssv + ip netns add nscl + + NSIM_SV_NAME=$(find $NSIM_SV_SYS/net -maxdepth 1 -type d ! \ + -path $NSIM_SV_SYS/net -exec basename {} \;) + NSIM_CL_NAME=$(find $NSIM_CL_SYS/net -maxdepth 1 -type d ! \ + -path $NSIM_CL_SYS/net -exec basename {} \;) + + # ensure the server has 1 queue + ethtool -L $NSIM_SV_NAME combined 1 2>/dev/null + + ip link set $NSIM_SV_NAME netns nssv + ip link set $NSIM_CL_NAME netns nscl + + ip netns exec nssv ip addr add "${SERVER_IP}/24" dev $NSIM_SV_NAME + ip netns exec nscl ip addr add "${CLIENT_IP}/24" dev $NSIM_CL_NAME + + ip netns exec nssv ip link set dev $NSIM_SV_NAME up + ip netns exec nscl ip link set dev $NSIM_CL_NAME up + + set +e +} + +cleanup_ns() +{ + ip netns del nscl + ip netns del nssv +} + +test_busypoll() +{ + suspend_value=${1:-0} + tmp_file=$(mktemp) + out_file=$(mktemp) + + # fill a test file with random data + dd if=/dev/urandom of=${tmp_file} bs=1M count=1 2> /dev/null + + timeout -k 1s 30s ip netns exec nssv ./busy_poller \ + -p${SERVER_PORT} \ + -b${SERVER_IP} \ + -m${MAX_EVENTS} \ + -u${BUSY_POLL_USECS} \ + -P${PREFER_BUSY_POLL} \ + -g${BUSY_POLL_BUDGET} \ + -i${NSIM_SV_IFIDX} \ + -s${suspend_value} \ + -o${out_file}& + + wait_local_port_listen nssv ${SERVER_PORT} tcp + + ip netns exec nscl socat -u $tmp_file TCP:${SERVER_IP}:${SERVER_PORT} + + wait + + tmp_file_md5sum=$(md5sum $tmp_file | cut -f1 -d' ') + out_file_md5sum=$(md5sum $out_file | cut -f1 -d' ') + + if [ "$tmp_file_md5sum" = "$out_file_md5sum" ]; then + res=0 + else + echo "md5sum mismatch" + echo "input file md5sum: ${tmp_file_md5sum}"; + echo "output file md5sum: ${out_file_md5sum}"; + res=1 + fi + + rm $out_file $tmp_file + + return $res +} + +test_busypoll_with_suspend() +{ + test_busypoll ${SUSPEND_TIMEOUT} + + return $? +} + +### +### Code start +### + +modprobe netdevsim + +# linking + +echo $NSIM_SV_ID > $NSIM_DEV_SYS_NEW +echo $NSIM_CL_ID > $NSIM_DEV_SYS_NEW +udevadm settle + +setup_ns + +NSIM_SV_FD=$((256 + RANDOM % 256)) +exec {NSIM_SV_FD}</var/run/netns/nssv +NSIM_SV_IFIDX=$(ip netns exec nssv cat /sys/class/net/$NSIM_SV_NAME/ifindex) + +NSIM_CL_FD=$((256 + RANDOM % 256)) +exec {NSIM_CL_FD}</var/run/netns/nscl +NSIM_CL_IFIDX=$(ip netns exec nscl cat /sys/class/net/$NSIM_CL_NAME/ifindex) + +echo "$NSIM_SV_FD:$NSIM_SV_IFIDX $NSIM_CL_FD:$NSIM_CL_IFIDX" > \ + $NSIM_DEV_SYS_LINK + +if [ $? -ne 0 ]; then + echo "linking netdevsim1 with netdevsim2 should succeed" + cleanup_ns + exit 1 +fi + +test_busypoll +if [ $? -ne 0 ]; then + echo "test_busypoll failed" + cleanup_ns + exit 1 +fi + +test_busypoll_with_suspend +if [ $? -ne 0 ]; then + echo "test_busypoll_with_suspend failed" + cleanup_ns + exit 1 +fi + +echo "$NSIM_SV_FD:$NSIM_SV_IFIDX" > $NSIM_DEV_SYS_UNLINK + +echo $NSIM_CL_ID > $NSIM_DEV_SYS_DEL + +cleanup_ns + +modprobe -r netdevsim + +exit 0 diff --git a/tools/testing/selftests/net/busy_poller.c b/tools/testing/selftests/net/busy_poller.c new file mode 100644 index 000000000000..99b0e8c17fca --- /dev/null +++ b/tools/testing/selftests/net/busy_poller.c @@ -0,0 +1,346 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <assert.h> +#include <errno.h> +#include <error.h> +#include <fcntl.h> +#include <inttypes.h> +#include <limits.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <ynl.h> + +#include <arpa/inet.h> +#include <netinet/in.h> + +#include <sys/epoll.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/types.h> + +#include <linux/genetlink.h> +#include <linux/netlink.h> + +#include "netdev-user.h" + +/* The below ifdef blob is required because: + * + * - sys/epoll.h does not (yet) have the ioctl definitions included. So, + * systems with older glibcs will not have them available. However, + * sys/epoll.h does include the type definition for epoll_data, which is + * needed by the user program (e.g. epoll_event.data.fd) + * + * - linux/eventpoll.h does not define the epoll_data type, it is simply an + * opaque __u64. It does, however, include the ioctl definition. + * + * Including both headers is impossible (types would be redefined), so I've + * opted instead to take sys/epoll.h, and include the blob below. + * + * Someday, when glibc is globally up to date, the blob below can be removed. + */ +#if !defined(EPOLL_IOC_TYPE) +struct epoll_params { + uint32_t busy_poll_usecs; + uint16_t busy_poll_budget; + uint8_t prefer_busy_poll; + + /* pad the struct to a multiple of 64bits */ + uint8_t __pad; +}; + +#define EPOLL_IOC_TYPE 0x8A +#define EPIOCSPARAMS _IOW(EPOLL_IOC_TYPE, 0x01, struct epoll_params) +#define EPIOCGPARAMS _IOR(EPOLL_IOC_TYPE, 0x02, struct epoll_params) +#endif + +static uint32_t cfg_port = 8000; +static struct in_addr cfg_bind_addr = { .s_addr = INADDR_ANY }; +static char *cfg_outfile; +static int cfg_max_events = 8; +static int cfg_ifindex; + +/* busy poll params */ +static uint32_t cfg_busy_poll_usecs; +static uint32_t cfg_busy_poll_budget; +static uint32_t cfg_prefer_busy_poll; + +/* IRQ params */ +static uint32_t cfg_defer_hard_irqs; +static uint64_t cfg_gro_flush_timeout; +static uint64_t cfg_irq_suspend_timeout; + +static void usage(const char *filepath) +{ + error(1, 0, + "Usage: %s -p<port> -b<addr> -m<max_events> -u<busy_poll_usecs> -P<prefer_busy_poll> -g<busy_poll_budget> -o<outfile> -d<defer_hard_irqs> -r<gro_flush_timeout> -s<irq_suspend_timeout> -i<ifindex>", + filepath); +} + +static void parse_opts(int argc, char **argv) +{ + int ret; + int c; + + if (argc <= 1) + usage(argv[0]); + + while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:")) != -1) { + switch (c) { + case 'u': + cfg_busy_poll_usecs = strtoul(optarg, NULL, 0); + if (cfg_busy_poll_usecs == ULONG_MAX || + cfg_busy_poll_usecs > UINT32_MAX) + error(1, ERANGE, "busy_poll_usecs too large"); + break; + case 'P': + cfg_prefer_busy_poll = strtoul(optarg, NULL, 0); + if (cfg_prefer_busy_poll == ULONG_MAX || + cfg_prefer_busy_poll > 1) + error(1, ERANGE, + "prefer busy poll should be 0 or 1"); + break; + case 'g': + cfg_busy_poll_budget = strtoul(optarg, NULL, 0); + if (cfg_busy_poll_budget == ULONG_MAX || + cfg_busy_poll_budget > UINT16_MAX) + error(1, ERANGE, + "busy poll budget must be [0, UINT16_MAX]"); + break; + case 'p': + cfg_port = strtoul(optarg, NULL, 0); + if (cfg_port > UINT16_MAX) + error(1, ERANGE, "port must be <= 65535"); + break; + case 'b': + ret = inet_aton(optarg, &cfg_bind_addr); + if (ret == 0) + error(1, errno, + "bind address %s invalid", optarg); + break; + case 'o': + cfg_outfile = strdup(optarg); + if (!cfg_outfile) + error(1, 0, "outfile invalid"); + break; + case 'm': + cfg_max_events = strtol(optarg, NULL, 0); + + if (cfg_max_events == LONG_MIN || + cfg_max_events == LONG_MAX || + cfg_max_events <= 0) + error(1, ERANGE, + "max events must be > 0 and < LONG_MAX"); + break; + case 'd': + cfg_defer_hard_irqs = strtoul(optarg, NULL, 0); + + if (cfg_defer_hard_irqs == ULONG_MAX || + cfg_defer_hard_irqs > INT32_MAX) + error(1, ERANGE, + "defer_hard_irqs must be <= INT32_MAX"); + break; + case 'r': + cfg_gro_flush_timeout = strtoull(optarg, NULL, 0); + + if (cfg_gro_flush_timeout == ULLONG_MAX) + error(1, ERANGE, + "gro_flush_timeout must be < ULLONG_MAX"); + break; + case 's': + cfg_irq_suspend_timeout = strtoull(optarg, NULL, 0); + + if (cfg_irq_suspend_timeout == ULLONG_MAX) + error(1, ERANGE, + "irq_suspend_timeout must be < ULLONG_MAX"); + break; + case 'i': + cfg_ifindex = strtoul(optarg, NULL, 0); + if (cfg_ifindex == ULONG_MAX) + error(1, ERANGE, + "ifindex must be < ULONG_MAX"); + break; + } + } + + if (!cfg_ifindex) + usage(argv[0]); + + if (optind != argc) + usage(argv[0]); +} + +static void epoll_ctl_add(int epfd, int fd, uint32_t events) +{ + struct epoll_event ev; + + ev.events = events; + ev.data.fd = fd; + if (epoll_ctl(epfd, EPOLL_CTL_ADD, fd, &ev) == -1) + error(1, errno, "epoll_ctl add fd: %d", fd); +} + +static void setnonblock(int sockfd) +{ + int flags; + + flags = fcntl(sockfd, F_GETFL, 0); + + if (fcntl(sockfd, F_SETFL, flags | O_NONBLOCK) == -1) + error(1, errno, "unable to set socket to nonblocking mode"); +} + +static void write_chunk(int fd, char *buf, ssize_t buflen) +{ + ssize_t remaining = buflen; + char *buf_offset = buf; + ssize_t writelen = 0; + ssize_t write_result; + + while (writelen < buflen) { + write_result = write(fd, buf_offset, remaining); + if (write_result == -1) + error(1, errno, "unable to write data to outfile"); + + writelen += write_result; + remaining -= write_result; + buf_offset += write_result; + } +} + +static void setup_queue(void) +{ + struct netdev_napi_get_list *napi_list = NULL; + struct netdev_napi_get_req_dump *req = NULL; + struct netdev_napi_set_req *set_req = NULL; + struct ynl_sock *ys; + struct ynl_error yerr; + uint32_t napi_id; + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) + error(1, 0, "YNL: %s", yerr.msg); + + req = netdev_napi_get_req_dump_alloc(); + netdev_napi_get_req_dump_set_ifindex(req, cfg_ifindex); + napi_list = netdev_napi_get_dump(ys, req); + + /* assume there is 1 NAPI configured and take the first */ + if (napi_list->obj._present.id) + napi_id = napi_list->obj.id; + else + error(1, 0, "napi ID not present?"); + + set_req = netdev_napi_set_req_alloc(); + netdev_napi_set_req_set_id(set_req, napi_id); + netdev_napi_set_req_set_defer_hard_irqs(set_req, cfg_defer_hard_irqs); + netdev_napi_set_req_set_gro_flush_timeout(set_req, + cfg_gro_flush_timeout); + netdev_napi_set_req_set_irq_suspend_timeout(set_req, + cfg_irq_suspend_timeout); + + if (netdev_napi_set(ys, set_req)) + error(1, 0, "can't set NAPI params: %s\n", yerr.msg); + + netdev_napi_get_list_free(napi_list); + netdev_napi_get_req_dump_free(req); + netdev_napi_set_req_free(set_req); + ynl_sock_destroy(ys); +} + +static void run_poller(void) +{ + struct epoll_event events[cfg_max_events]; + struct epoll_params epoll_params = {0}; + struct sockaddr_in server_addr; + int i, epfd, nfds; + ssize_t readlen; + int outfile_fd; + char buf[1024]; + int sockfd; + int conn; + int val; + + outfile_fd = open(cfg_outfile, O_WRONLY | O_CREAT, 0644); + if (outfile_fd == -1) + error(1, errno, "unable to open outfile: %s", cfg_outfile); + + sockfd = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + if (sockfd == -1) + error(1, errno, "unable to create listen socket"); + + server_addr.sin_family = AF_INET; + server_addr.sin_port = htons(cfg_port); + server_addr.sin_addr = cfg_bind_addr; + + /* these values are range checked during parse_opts, so casting is safe + * here + */ + epoll_params.busy_poll_usecs = cfg_busy_poll_usecs; + epoll_params.busy_poll_budget = (uint16_t)cfg_busy_poll_budget; + epoll_params.prefer_busy_poll = (uint8_t)cfg_prefer_busy_poll; + epoll_params.__pad = 0; + + val = 1; + if (setsockopt(sockfd, SOL_SOCKET, SO_REUSEADDR, &val, sizeof(val))) + error(1, errno, "poller setsockopt reuseaddr"); + + setnonblock(sockfd); + + if (bind(sockfd, (struct sockaddr *)&server_addr, + sizeof(struct sockaddr_in))) + error(0, errno, "poller bind to port: %d\n", cfg_port); + + if (listen(sockfd, 1)) + error(1, errno, "poller listen"); + + epfd = epoll_create1(0); + if (ioctl(epfd, EPIOCSPARAMS, &epoll_params) == -1) + error(1, errno, "unable to set busy poll params"); + + epoll_ctl_add(epfd, sockfd, EPOLLIN | EPOLLOUT | EPOLLET); + + for (;;) { + nfds = epoll_wait(epfd, events, cfg_max_events, -1); + for (i = 0; i < nfds; i++) { + if (events[i].data.fd == sockfd) { + conn = accept(sockfd, NULL, NULL); + if (conn == -1) + error(1, errno, + "accepting incoming connection failed"); + + setnonblock(conn); + epoll_ctl_add(epfd, conn, + EPOLLIN | EPOLLET | EPOLLRDHUP | + EPOLLHUP); + } else if (events[i].events & EPOLLIN) { + for (;;) { + readlen = read(events[i].data.fd, buf, + sizeof(buf)); + if (readlen > 0) + write_chunk(outfile_fd, buf, + readlen); + else + break; + } + } else { + /* spurious event ? */ + } + if (events[i].events & (EPOLLRDHUP | EPOLLHUP)) { + epoll_ctl(epfd, EPOLL_CTL_DEL, + events[i].data.fd, NULL); + close(events[i].data.fd); + close(outfile_fd); + return; + } + } + } +} + +int main(int argc, char *argv[]) +{ + parse_opts(argc, argv); + setup_queue(); + run_poller(); + return 0; +} diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 224346426ef2..7d885cff8d79 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -126,6 +126,7 @@ TEST_FILES := devlink_lib.sh \ tc_common.sh TEST_INCLUDES := \ - ../lib.sh + ../lib.sh \ + $(wildcard ../lib/sh/*.sh) include ../../lib.mk diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh index 96c97064f2d3..becc7c3fc809 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_flat gre_mtu_change + gre_flat_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change } +gre_flat_remote_change() +{ + flat_remote_change + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 (new remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 (new remote)" + + flat_remote_restore + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 (old remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh index ff9fb0db9bd1..e5335116a2fd 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_flat gre_mtu_change + gre_flat_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change } +gre_flat_remote_change() +{ + flat_remote_change + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key (new remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key (new remote)" + + flat_remote_restore + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key (old remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh index 12c138785242..7e0cbfdefab0 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_flat gre_mtu_change + gre_flat_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_flat_remote_change() +{ + flat_remote_change + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey (new remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey (new remote)" + + flat_remote_restore + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey (old remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh index 83b55c30a5c3..e0844495f3d1 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_hier gre_mtu_change + gre_hier_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_hier_remote_change() +{ + hier_remote_change + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 (new remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 (new remote)" + + hier_remote_restore + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 (old remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh index 256607916d92..741bc9c928eb 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_hier gre_mtu_change + gre_hier_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_hier_remote_change() +{ + hier_remote_change + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key (new remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key (new remote)" + + hier_remote_restore + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key (old remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh index ad1bcd6334a8..ad9eab4b1367 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_hier gre_mtu_change + gre_hier_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_hier_remote_change() +{ + hier_remote_change + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey (new remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey (new remote)" + + hier_remote_restore + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey (old remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh index 24f4ab328bd2..2d91281dc5b7 100644 --- a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh @@ -436,3 +436,83 @@ test_mtu_change() check_err $? log_test "ping GRE IPv6, packet size 1800 after MTU change" } + +topo_flat_remote_change() +{ + local old1=$1; shift + local new1=$1; shift + local old2=$1; shift + local new2=$1; shift + + ip link set dev g1a type ip6gre local $new1 remote $new2 + __addr_add_del g1a add "$new1/128" + __addr_add_del g1a del "$old1/128" + ip -6 route add $new2/128 via 2001:db8:10::2 + ip -6 route del $old2/128 + + ip link set dev g2a type ip6gre local $new2 remote $new1 + __addr_add_del g2a add "$new2/128" + __addr_add_del g2a del "$old2/128" + ip -6 route add vrf v$ol2 $new1/128 via 2001:db8:10::1 + ip -6 route del vrf v$ol2 $old1/128 +} + +flat_remote_change() +{ + local old1=2001:db8:3::1 + local new1=2001:db8:3::10 + local old2=2001:db8:3::2 + local new2=2001:db8:3::20 + + topo_flat_remote_change $old1 $new1 $old2 $new2 +} + +flat_remote_restore() +{ + local old1=2001:db8:3::10 + local new1=2001:db8:3::1 + local old2=2001:db8:3::20 + local new2=2001:db8:3::2 + + topo_flat_remote_change $old1 $new1 $old2 $new2 +} + +topo_hier_remote_change() +{ + local old1=$1; shift + local new1=$1; shift + local old2=$1; shift + local new2=$1; shift + + __addr_add_del dummy1 del "$old1/64" + __addr_add_del dummy1 add "$new1/64" + ip link set dev g1a type ip6gre local $new1 remote $new2 + ip -6 route add vrf v$ul1 $new2/128 via 2001:db8:10::2 + ip -6 route del vrf v$ul1 $old2/128 + + __addr_add_del dummy2 del "$old2/64" + __addr_add_del dummy2 add "$new2/64" + ip link set dev g2a type ip6gre local $new2 remote $new1 + ip -6 route add vrf v$ul2 $new1/128 via 2001:db8:10::1 + ip -6 route del vrf v$ul2 $old1/128 +} + +hier_remote_change() +{ + local old1=2001:db8:3::1 + local new1=2001:db8:3::10 + local old2=2001:db8:3::2 + local new2=2001:db8:3::20 + + topo_hier_remote_change $old1 $new1 $old2 $new2 +} + +hier_remote_restore() +{ + local old1=2001:db8:3::10 + local new1=2001:db8:3::1 + local old2=2001:db8:3::20 + local new2=2001:db8:3::2 + + topo_hier_remote_change $old1 $new1 $old2 $new2 +} diff --git a/tools/testing/selftests/net/hsr/config b/tools/testing/selftests/net/hsr/config index 241542441c51..555a868743f0 100644 --- a/tools/testing/selftests/net/hsr/config +++ b/tools/testing/selftests/net/hsr/config @@ -3,3 +3,4 @@ CONFIG_NET_SCH_NETEM=m CONFIG_HSR=y CONFIG_VETH=y CONFIG_BRIDGE=y +CONFIG_VLAN_8021Q=m diff --git a/tools/testing/selftests/net/hsr/hsr_common.sh b/tools/testing/selftests/net/hsr/hsr_common.sh index 8e97b1f2e7e5..1dc882ac1c74 100644 --- a/tools/testing/selftests/net/hsr/hsr_common.sh +++ b/tools/testing/selftests/net/hsr/hsr_common.sh @@ -15,7 +15,7 @@ do_ping() { local netns="$1" local connect_addr="$2" - local ping_args="-q -c 2" + local ping_args="-q -c 2 -i 0.1" if is_v6 "${connect_addr}"; then $ipv6 || return 0 @@ -36,7 +36,7 @@ do_ping_long() { local netns="$1" local connect_addr="$2" - local ping_args="-q -c 10" + local ping_args="-q -c 10 -i 0.1" if is_v6 "${connect_addr}"; then $ipv6 || return 0 diff --git a/tools/testing/selftests/net/hsr/hsr_ping.sh b/tools/testing/selftests/net/hsr/hsr_ping.sh index f5d207fc770a..5a65f4f836be 100755 --- a/tools/testing/selftests/net/hsr/hsr_ping.sh +++ b/tools/testing/selftests/net/hsr/hsr_ping.sh @@ -175,6 +175,100 @@ setup_hsr_interfaces() ip -net "$ns3" link set hsr3 up } +setup_vlan_interfaces() { + ip -net "$ns1" link add link hsr1 name hsr1.2 type vlan id 2 + ip -net "$ns1" link add link hsr1 name hsr1.3 type vlan id 3 + ip -net "$ns1" link add link hsr1 name hsr1.4 type vlan id 4 + ip -net "$ns1" link add link hsr1 name hsr1.5 type vlan id 5 + + ip -net "$ns2" link add link hsr2 name hsr2.2 type vlan id 2 + ip -net "$ns2" link add link hsr2 name hsr2.3 type vlan id 3 + ip -net "$ns2" link add link hsr2 name hsr2.4 type vlan id 4 + ip -net "$ns2" link add link hsr2 name hsr2.5 type vlan id 5 + + ip -net "$ns3" link add link hsr3 name hsr3.2 type vlan id 2 + ip -net "$ns3" link add link hsr3 name hsr3.3 type vlan id 3 + ip -net "$ns3" link add link hsr3 name hsr3.4 type vlan id 4 + ip -net "$ns3" link add link hsr3 name hsr3.5 type vlan id 5 + + ip -net "$ns1" addr add 100.64.2.1/24 dev hsr1.2 + ip -net "$ns1" addr add 100.64.3.1/24 dev hsr1.3 + ip -net "$ns1" addr add 100.64.4.1/24 dev hsr1.4 + ip -net "$ns1" addr add 100.64.5.1/24 dev hsr1.5 + + ip -net "$ns2" addr add 100.64.2.2/24 dev hsr2.2 + ip -net "$ns2" addr add 100.64.3.2/24 dev hsr2.3 + ip -net "$ns2" addr add 100.64.4.2/24 dev hsr2.4 + ip -net "$ns2" addr add 100.64.5.2/24 dev hsr2.5 + + ip -net "$ns3" addr add 100.64.2.3/24 dev hsr3.2 + ip -net "$ns3" addr add 100.64.3.3/24 dev hsr3.3 + ip -net "$ns3" addr add 100.64.4.3/24 dev hsr3.4 + ip -net "$ns3" addr add 100.64.5.3/24 dev hsr3.5 + + ip -net "$ns1" link set dev hsr1.2 up + ip -net "$ns1" link set dev hsr1.3 up + ip -net "$ns1" link set dev hsr1.4 up + ip -net "$ns1" link set dev hsr1.5 up + + ip -net "$ns2" link set dev hsr2.2 up + ip -net "$ns2" link set dev hsr2.3 up + ip -net "$ns2" link set dev hsr2.4 up + ip -net "$ns2" link set dev hsr2.5 up + + ip -net "$ns3" link set dev hsr3.2 up + ip -net "$ns3" link set dev hsr3.3 up + ip -net "$ns3" link set dev hsr3.4 up + ip -net "$ns3" link set dev hsr3.5 up + +} + +hsr_vlan_ping() { + do_ping "$ns1" 100.64.2.2 + do_ping "$ns1" 100.64.3.2 + do_ping "$ns1" 100.64.4.2 + do_ping "$ns1" 100.64.5.2 + + do_ping "$ns1" 100.64.2.3 + do_ping "$ns1" 100.64.3.3 + do_ping "$ns1" 100.64.4.3 + do_ping "$ns1" 100.64.5.3 + + do_ping "$ns2" 100.64.2.1 + do_ping "$ns2" 100.64.3.1 + do_ping "$ns2" 100.64.4.1 + do_ping "$ns2" 100.64.5.1 + + do_ping "$ns2" 100.64.2.3 + do_ping "$ns2" 100.64.3.3 + do_ping "$ns2" 100.64.4.3 + do_ping "$ns2" 100.64.5.3 + + do_ping "$ns3" 100.64.2.1 + do_ping "$ns3" 100.64.3.1 + do_ping "$ns3" 100.64.4.1 + do_ping "$ns3" 100.64.5.1 + + do_ping "$ns3" 100.64.2.2 + do_ping "$ns3" 100.64.3.2 + do_ping "$ns3" 100.64.4.2 + do_ping "$ns3" 100.64.5.2 +} + +run_vlan_tests() { + vlan_challenged_hsr1=$(ip net exec "$ns1" ethtool -k hsr1 | grep "vlan-challenged" | awk '{print $2}') + vlan_challenged_hsr2=$(ip net exec "$ns2" ethtool -k hsr2 | grep "vlan-challenged" | awk '{print $2}') + vlan_challenged_hsr3=$(ip net exec "$ns3" ethtool -k hsr3 | grep "vlan-challenged" | awk '{print $2}') + + if [[ "$vlan_challenged_hsr1" = "off" || "$vlan_challenged_hsr2" = "off" || "$vlan_challenged_hsr3" = "off" ]]; then + echo "INFO: Running VLAN tests" + setup_vlan_interfaces + hsr_vlan_ping + else + echo "INFO: Not Running VLAN tests as the device does not support VLAN" + fi +} + check_prerequisites setup_ns ns1 ns2 ns3 @@ -183,9 +277,13 @@ trap cleanup_all_ns EXIT setup_hsr_interfaces 0 do_complete_ping_test +run_vlan_tests + setup_ns ns1 ns2 ns3 setup_hsr_interfaces 1 do_complete_ping_test +run_vlan_tests + exit $ret diff --git a/tools/testing/selftests/net/hsr/settings b/tools/testing/selftests/net/hsr/settings new file mode 100644 index 000000000000..0fbc037f2aa8 --- /dev/null +++ b/tools/testing/selftests/net/hsr/settings @@ -0,0 +1 @@ +timeout=50 diff --git a/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh new file mode 100755 index 000000000000..a6b2b1f9c641 --- /dev/null +++ b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh @@ -0,0 +1,262 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Testing for potential kernel soft lockup during IPv6 routing table +# refresh under heavy outgoing IPv6 traffic. If a kernel soft lockup +# occurs, a kernel panic will be triggered to prevent associated issues. +# +# +# Test Environment Layout +# +# ┌----------------┐ ┌----------------┐ +# | SOURCE_NS | | SINK_NS | +# | NAMESPACE | | NAMESPACE | +# |(iperf3 clients)| |(iperf3 servers)| +# | | | | +# | | | | +# | ┌-----------| nexthops |---------┐ | +# | |veth_source|<--------------------------------------->|veth_sink|<┐ | +# | └-----------|2001:0DB8:1::0:1/96 2001:0DB8:1::1:1/96 |---------┘ | | +# | | ^ 2001:0DB8:1::1:2/96 | | | +# | | . . | fwd | | +# | ┌---------┐ | . . | | | +# | | IPv6 | | . . | V | +# | | routing | | . 2001:0DB8:1::1:80/96| ┌-----┐ | +# | | table | | . | | lo | | +# | | nexthop | | . └--------┴-----┴-┘ +# | | update | | ............................> 2001:0DB8:2::1:1/128 +# | └-------- ┘ | +# └----------------┘ +# +# The test script sets up two network namespaces, source_ns and sink_ns, +# connected via a veth link. Within source_ns, it continuously updates the +# IPv6 routing table by flushing and inserting IPV6_NEXTHOP_ADDR_COUNT nexthop +# IPs destined for SINK_LOOPBACK_IP_ADDR in sink_ns. This refresh occurs at a +# rate of 1/ROUTING_TABLE_REFRESH_PERIOD per second for TEST_DURATION seconds. +# +# Simultaneously, multiple iperf3 clients within source_ns generate heavy +# outgoing IPv6 traffic. Each client is assigned a unique port number starting +# at 5000 and incrementing sequentially. Each client targets a unique iperf3 +# server running in sink_ns, connected to the SINK_LOOPBACK_IFACE interface +# using the same port number. +# +# The number of iperf3 servers and clients is set to half of the total +# available cores on each machine. +# +# NOTE: We have tested this script on machines with various CPU specifications, +# ranging from lower to higher performance as listed below. The test script +# effectively triggered a kernel soft lockup on machines running an unpatched +# kernel in under a minute: +# +# - 1x Intel Xeon E-2278G 8-Core Processor @ 3.40GHz +# - 1x Intel Xeon E-2378G Processor 8-Core @ 2.80GHz +# - 1x AMD EPYC 7401P 24-Core Processor @ 2.00GHz +# - 1x AMD EPYC 7402P 24-Core Processor @ 2.80GHz +# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz +# - 1x Ampere Altra Q80-30 80-Core Processor @ 3.00GHz +# - 2x Intel Xeon Gold 5120 14-Core Processor @ 2.20GHz +# - 2x Intel Xeon Silver 4214 24-Core Processor @ 2.20GHz +# - 1x AMD EPYC 7502P 32-Core @ 2.50GHz +# - 1x Intel Xeon Gold 6314U 32-Core Processor @ 2.30GHz +# - 2x Intel Xeon Gold 6338 32-Core Processor @ 2.00GHz +# +# On less performant machines, you may need to increase the TEST_DURATION +# parameter to enhance the likelihood of encountering a race condition leading +# to a kernel soft lockup and avoid a false negative result. +# +# NOTE: The test may not produce the expected result in virtualized +# environments (e.g., qemu) due to differences in timing and CPU handling, +# which can affect the conditions needed to trigger a soft lockup. + +source lib.sh +source net_helper.sh + +TEST_DURATION=300 +ROUTING_TABLE_REFRESH_PERIOD=0.01 + +IPERF3_BITRATE="300m" + + +IPV6_NEXTHOP_ADDR_COUNT="128" +IPV6_NEXTHOP_ADDR_MASK="96" +IPV6_NEXTHOP_PREFIX="2001:0DB8:1" + + +SOURCE_TEST_IFACE="veth_source" +SOURCE_TEST_IP_ADDR="2001:0DB8:1::0:1/96" + +SINK_TEST_IFACE="veth_sink" +# ${SINK_TEST_IFACE} is populated with the following range of IPv6 addresses: +# 2001:0DB8:1::1:1 to 2001:0DB8:1::1:${IPV6_NEXTHOP_ADDR_COUNT} +SINK_LOOPBACK_IFACE="lo" +SINK_LOOPBACK_IP_MASK="128" +SINK_LOOPBACK_IP_ADDR="2001:0DB8:2::1:1" + +nexthop_ip_list="" +termination_signal="" +kernel_softlokup_panic_prev_val="" + +terminate_ns_processes_by_pattern() { + local ns=$1 + local pattern=$2 + + for pid in $(ip netns pids ${ns}); do + [ -e /proc/$pid/cmdline ] && grep -qe "${pattern}" /proc/$pid/cmdline && kill -9 $pid + done +} + +cleanup() { + echo "info: cleaning up namespaces and terminating all processes within them..." + + + # Terminate iperf3 instances running in the source_ns. To avoid race + # conditions, first iterate over the PIDs and terminate those + # associated with the bash shells running the + # `while true; do iperf3 -c ...; done` loops. In a second iteration, + # terminate the individual `iperf3 -c ...` instances. + terminate_ns_processes_by_pattern ${source_ns} while + terminate_ns_processes_by_pattern ${source_ns} iperf3 + + # Repeat the same process for sink_ns + terminate_ns_processes_by_pattern ${sink_ns} while + terminate_ns_processes_by_pattern ${sink_ns} iperf3 + + # Check if any iperf3 instances are still running. This could happen + # if a core has entered an infinite loop and the timeout for detecting + # the soft lockup has not expired, but either the test interval has + # already elapsed or the test was terminated manually (e.g., with ^C) + for pid in $(ip netns pids ${source_ns}); do + if [ -e /proc/$pid/cmdline ] && grep -qe 'iperf3' /proc/$pid/cmdline; then + echo "FAIL: unable to terminate some iperf3 instances. Soft lockup is underway. A kernel panic is on the way!" + exit ${ksft_fail} + fi + done + + if [ "$termination_signal" == "SIGINT" ]; then + echo "SKIP: Termination due to ^C (SIGINT)" + elif [ "$termination_signal" == "SIGALRM" ]; then + echo "PASS: No kernel soft lockup occurred during this ${TEST_DURATION} second test" + fi + + cleanup_ns ${source_ns} ${sink_ns} + + sysctl -qw kernel.softlockup_panic=${kernel_softlokup_panic_prev_val} +} + +setup_prepare() { + setup_ns source_ns sink_ns + + ip -n ${source_ns} link add name ${SOURCE_TEST_IFACE} type veth peer name ${SINK_TEST_IFACE} netns ${sink_ns} + + # Setting up the Source namespace + ip -n ${source_ns} addr add ${SOURCE_TEST_IP_ADDR} dev ${SOURCE_TEST_IFACE} + ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} qlen 10000 + ip -n ${source_ns} link set dev ${SOURCE_TEST_IFACE} up + ip netns exec ${source_ns} sysctl -qw net.ipv6.fib_multipath_hash_policy=1 + + # Setting up the Sink namespace + ip -n ${sink_ns} addr add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} dev ${SINK_LOOPBACK_IFACE} + ip -n ${sink_ns} link set dev ${SINK_LOOPBACK_IFACE} up + ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_LOOPBACK_IFACE}.forwarding=1 + + ip -n ${sink_ns} link set ${SINK_TEST_IFACE} up + ip netns exec ${sink_ns} sysctl -qw net.ipv6.conf.${SINK_TEST_IFACE}.forwarding=1 + + + # Populate nexthop IPv6 addresses on the test interface in the sink_ns + echo "info: populating ${IPV6_NEXTHOP_ADDR_COUNT} IPv6 addresses on the ${SINK_TEST_IFACE} interface ..." + for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do + ip -n ${sink_ns} addr add ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" "${IP}")/${IPV6_NEXTHOP_ADDR_MASK} dev ${SINK_TEST_IFACE}; + done + + # Preparing list of nexthops + for IP in $(seq 1 ${IPV6_NEXTHOP_ADDR_COUNT}); do + nexthop_ip_list=$nexthop_ip_list" nexthop via ${IPV6_NEXTHOP_PREFIX}::$(printf "1:%x" $IP) dev ${SOURCE_TEST_IFACE} weight 1" + done +} + + +test_soft_lockup_during_routing_table_refresh() { + # Start num_of_iperf_servers iperf3 servers in the sink_ns namespace, + # each listening on ports starting at 5001 and incrementing + # sequentially. Since iperf3 instances may terminate unexpectedly, a + # while loop is used to automatically restart them in such cases. + echo "info: starting ${num_of_iperf_servers} iperf3 servers in the sink_ns namespace ..." + for i in $(seq 1 ${num_of_iperf_servers}); do + cmd="iperf3 --bind ${SINK_LOOPBACK_IP_ADDR} -s -p $(printf '5%03d' ${i}) --rcv-timeout 200 &>/dev/null" + ip netns exec ${sink_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null + done + + # Wait for the iperf3 servers to be ready + for i in $(seq ${num_of_iperf_servers}); do + port=$(printf '5%03d' ${i}); + wait_local_port_listen ${sink_ns} ${port} tcp + done + + # Continuously refresh the routing table in the background within + # the source_ns namespace + ip netns exec ${source_ns} bash -c " + while \$(ip netns list | grep -q ${source_ns}); do + ip -6 route add ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK} ${nexthop_ip_list}; + sleep ${ROUTING_TABLE_REFRESH_PERIOD}; + ip -6 route delete ${SINK_LOOPBACK_IP_ADDR}/${SINK_LOOPBACK_IP_MASK}; + done &" + + # Start num_of_iperf_servers iperf3 clients in the source_ns namespace, + # each sending TCP traffic on sequential ports starting at 5001. + # Since iperf3 instances may terminate unexpectedly (e.g., if the route + # to the server is deleted in the background during a route refresh), a + # while loop is used to automatically restart them in such cases. + echo "info: starting ${num_of_iperf_servers} iperf3 clients in the source_ns namespace ..." + for i in $(seq 1 ${num_of_iperf_servers}); do + cmd="iperf3 -c ${SINK_LOOPBACK_IP_ADDR} -p $(printf '5%03d' ${i}) --length 64 --bitrate ${IPERF3_BITRATE} -t 0 --connect-timeout 150 &>/dev/null" + ip netns exec ${source_ns} bash -c "while true; do ${cmd}; done &" &>/dev/null + done + + echo "info: IPv6 routing table is being updated at the rate of $(echo "1/${ROUTING_TABLE_REFRESH_PERIOD}" | bc)/s for ${TEST_DURATION} seconds ..." + echo "info: A kernel soft lockup, if detected, results in a kernel panic!" + + wait +} + +# Make sure 'iperf3' is installed, skip the test otherwise +if [ ! -x "$(command -v "iperf3")" ]; then + echo "SKIP: 'iperf3' is not installed. Skipping the test." + exit ${ksft_skip} +fi + +# Determine the number of cores on the machine +num_of_iperf_servers=$(( $(nproc)/2 )) + +# Check if we are running on a multi-core machine, skip the test otherwise +if [ "${num_of_iperf_servers}" -eq 0 ]; then + echo "SKIP: This test is not valid on a single core machine!" + exit ${ksft_skip} +fi + +# Since the kernel soft lockup we're testing causes at least one core to enter +# an infinite loop, destabilizing the host and likely affecting subsequent +# tests, we trigger a kernel panic instead of reporting a failure and +# continuing +kernel_softlokup_panic_prev_val=$(sysctl -n kernel.softlockup_panic) +sysctl -qw kernel.softlockup_panic=1 + +handle_sigint() { + termination_signal="SIGINT" + cleanup + exit ${ksft_skip} +} + +handle_sigalrm() { + termination_signal="SIGALRM" + cleanup + exit ${ksft_pass} +} + +trap handle_sigint SIGINT +trap handle_sigalrm SIGALRM + +(sleep ${TEST_DURATION} && kill -s SIGALRM $$)& + +setup_prepare +test_soft_lockup_during_routing_table_refresh diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 5d796622e730..8e3fc05a5397 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -11,7 +11,7 @@ TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq TEST_FILES := mptcp_lib.sh settings -TEST_INCLUDES := ../lib.sh ../net_helper.sh +TEST_INCLUDES := ../lib.sh $(wildcard ../lib/sh/*.sh) ../net_helper.sh EXTRA_CLEAN := *.pcap diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 57325d57e4c6..b48b4e56826a 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -259,6 +259,15 @@ check_mptcp_disabled() mptcp_lib_ns_init disabled_ns print_larger_title "New MPTCP socket can be blocked via sysctl" + + # mainly to cover more code + if ! ip netns exec ${disabled_ns} sysctl net.mptcp >/dev/null; then + mptcp_lib_pr_fail "not able to list net.mptcp sysctl knobs" + mptcp_lib_result_fail "not able to list net.mptcp sysctl knobs" + ret=${KSFT_FAIL} + return 1 + fi + # net.mptcp.enabled should be enabled by default if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then mptcp_lib_pr_fail "net.mptcp.enabled sysctl is not 1 by default" diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c deleted file mode 100644 index 64d6805381c5..000000000000 --- a/tools/testing/selftests/net/ncdevmem.c +++ /dev/null @@ -1,570 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE -#define __EXPORTED_HEADERS__ - -#include <linux/uio.h> -#include <stdio.h> -#include <stdlib.h> -#include <unistd.h> -#include <stdbool.h> -#include <string.h> -#include <errno.h> -#define __iovec_defined -#include <fcntl.h> -#include <malloc.h> -#include <error.h> - -#include <arpa/inet.h> -#include <sys/socket.h> -#include <sys/mman.h> -#include <sys/ioctl.h> -#include <sys/syscall.h> - -#include <linux/memfd.h> -#include <linux/dma-buf.h> -#include <linux/udmabuf.h> -#include <libmnl/libmnl.h> -#include <linux/types.h> -#include <linux/netlink.h> -#include <linux/genetlink.h> -#include <linux/netdev.h> -#include <time.h> -#include <net/if.h> - -#include "netdev-user.h" -#include <ynl.h> - -#define PAGE_SHIFT 12 -#define TEST_PREFIX "ncdevmem" -#define NUM_PAGES 16000 - -#ifndef MSG_SOCK_DEVMEM -#define MSG_SOCK_DEVMEM 0x2000000 -#endif - -/* - * tcpdevmem netcat. Works similarly to netcat but does device memory TCP - * instead of regular TCP. Uses udmabuf to mock a dmabuf provider. - * - * Usage: - * - * On server: - * ncdevmem -s <server IP> -c <client IP> -f eth1 -l -p 5201 -v 7 - * - * On client: - * yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \ - * tr \\n \\0 | \ - * head -c 5G | \ - * nc <server IP> 5201 -p 5201 - * - * Note this is compatible with regular netcat. i.e. the sender or receiver can - * be replaced with regular netcat to test the RX or TX path in isolation. - */ - -static char *server_ip = "192.168.1.4"; -static char *client_ip = "192.168.1.2"; -static char *port = "5201"; -static size_t do_validation; -static int start_queue = 8; -static int num_queues = 8; -static char *ifname = "eth1"; -static unsigned int ifindex; -static unsigned int dmabuf_id; - -void print_bytes(void *ptr, size_t size) -{ - unsigned char *p = ptr; - int i; - - for (i = 0; i < size; i++) - printf("%02hhX ", p[i]); - printf("\n"); -} - -void print_nonzero_bytes(void *ptr, size_t size) -{ - unsigned char *p = ptr; - unsigned int i; - - for (i = 0; i < size; i++) - putchar(p[i]); - printf("\n"); -} - -void validate_buffer(void *line, size_t size) -{ - static unsigned char seed = 1; - unsigned char *ptr = line; - int errors = 0; - size_t i; - - for (i = 0; i < size; i++) { - if (ptr[i] != seed) { - fprintf(stderr, - "Failed validation: expected=%u, actual=%u, index=%lu\n", - seed, ptr[i], i); - errors++; - if (errors > 20) - error(1, 0, "validation failed."); - } - seed++; - if (seed == do_validation) - seed = 0; - } - - fprintf(stdout, "Validated buffer\n"); -} - -#define run_command(cmd, ...) \ - ({ \ - char command[256]; \ - memset(command, 0, sizeof(command)); \ - snprintf(command, sizeof(command), cmd, ##__VA_ARGS__); \ - printf("Running: %s\n", command); \ - system(command); \ - }) - -static int reset_flow_steering(void) -{ - int ret = 0; - - ret = run_command("sudo ethtool -K %s ntuple off", ifname); - if (ret) - return ret; - - return run_command("sudo ethtool -K %s ntuple on", ifname); -} - -static int configure_headersplit(bool on) -{ - return run_command("sudo ethtool -G %s tcp-data-split %s", ifname, - on ? "on" : "off"); -} - -static int configure_rss(void) -{ - return run_command("sudo ethtool -X %s equal %d", ifname, start_queue); -} - -static int configure_channels(unsigned int rx, unsigned int tx) -{ - return run_command("sudo ethtool -L %s rx %u tx %u", ifname, rx, tx); -} - -static int configure_flow_steering(void) -{ - return run_command("sudo ethtool -N %s flow-type tcp4 src-ip %s dst-ip %s src-port %s dst-port %s queue %d", - ifname, client_ip, server_ip, port, port, start_queue); -} - -static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd, - struct netdev_queue_id *queues, - unsigned int n_queue_index, struct ynl_sock **ys) -{ - struct netdev_bind_rx_req *req = NULL; - struct netdev_bind_rx_rsp *rsp = NULL; - struct ynl_error yerr; - - *ys = ynl_sock_create(&ynl_netdev_family, &yerr); - if (!*ys) { - fprintf(stderr, "YNL: %s\n", yerr.msg); - return -1; - } - - req = netdev_bind_rx_req_alloc(); - netdev_bind_rx_req_set_ifindex(req, ifindex); - netdev_bind_rx_req_set_fd(req, dmabuf_fd); - __netdev_bind_rx_req_set_queues(req, queues, n_queue_index); - - rsp = netdev_bind_rx(*ys, req); - if (!rsp) { - perror("netdev_bind_rx"); - goto err_close; - } - - if (!rsp->_present.id) { - perror("id not present"); - goto err_close; - } - - printf("got dmabuf id=%d\n", rsp->id); - dmabuf_id = rsp->id; - - netdev_bind_rx_req_free(req); - netdev_bind_rx_rsp_free(rsp); - - return 0; - -err_close: - fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg); - netdev_bind_rx_req_free(req); - ynl_sock_destroy(*ys); - return -1; -} - -static void create_udmabuf(int *devfd, int *memfd, int *buf, size_t dmabuf_size) -{ - struct udmabuf_create create; - int ret; - - *devfd = open("/dev/udmabuf", O_RDWR); - if (*devfd < 0) { - error(70, 0, - "%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n", - TEST_PREFIX); - } - - *memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING); - if (*memfd < 0) - error(70, 0, "%s: [skip,no-memfd]\n", TEST_PREFIX); - - /* Required for udmabuf */ - ret = fcntl(*memfd, F_ADD_SEALS, F_SEAL_SHRINK); - if (ret < 0) - error(73, 0, "%s: [skip,fcntl-add-seals]\n", TEST_PREFIX); - - ret = ftruncate(*memfd, dmabuf_size); - if (ret == -1) - error(74, 0, "%s: [FAIL,memfd-truncate]\n", TEST_PREFIX); - - memset(&create, 0, sizeof(create)); - - create.memfd = *memfd; - create.offset = 0; - create.size = dmabuf_size; - *buf = ioctl(*devfd, UDMABUF_CREATE, &create); - if (*buf < 0) - error(75, 0, "%s: [FAIL, create udmabuf]\n", TEST_PREFIX); -} - -int do_server(void) -{ - char ctrl_data[sizeof(int) * 20000]; - struct netdev_queue_id *queues; - size_t non_page_aligned_frags = 0; - struct sockaddr_in client_addr; - struct sockaddr_in server_sin; - size_t page_aligned_frags = 0; - int devfd, memfd, buf, ret; - size_t total_received = 0; - socklen_t client_addr_len; - bool is_devmem = false; - char *buf_mem = NULL; - struct ynl_sock *ys; - size_t dmabuf_size; - char iobuf[819200]; - char buffer[256]; - int socket_fd; - int client_fd; - size_t i = 0; - int opt = 1; - - dmabuf_size = getpagesize() * NUM_PAGES; - - create_udmabuf(&devfd, &memfd, &buf, dmabuf_size); - - if (reset_flow_steering()) - error(1, 0, "Failed to reset flow steering\n"); - - /* Configure RSS to divert all traffic from our devmem queues */ - if (configure_rss()) - error(1, 0, "Failed to configure rss\n"); - - /* Flow steer our devmem flows to start_queue */ - if (configure_flow_steering()) - error(1, 0, "Failed to configure flow steering\n"); - - sleep(1); - - queues = malloc(sizeof(*queues) * num_queues); - - for (i = 0; i < num_queues; i++) { - queues[i]._present.type = 1; - queues[i]._present.id = 1; - queues[i].type = NETDEV_QUEUE_TYPE_RX; - queues[i].id = start_queue + i; - } - - if (bind_rx_queue(ifindex, buf, queues, num_queues, &ys)) - error(1, 0, "Failed to bind\n"); - - buf_mem = mmap(NULL, dmabuf_size, PROT_READ | PROT_WRITE, MAP_SHARED, - buf, 0); - if (buf_mem == MAP_FAILED) - error(1, 0, "mmap()"); - - server_sin.sin_family = AF_INET; - server_sin.sin_port = htons(atoi(port)); - - ret = inet_pton(server_sin.sin_family, server_ip, &server_sin.sin_addr); - if (socket < 0) - error(79, 0, "%s: [FAIL, create socket]\n", TEST_PREFIX); - - socket_fd = socket(server_sin.sin_family, SOCK_STREAM, 0); - if (socket < 0) - error(errno, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX); - - ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEPORT, &opt, - sizeof(opt)); - if (ret) - error(errno, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX); - - ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEADDR, &opt, - sizeof(opt)); - if (ret) - error(errno, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX); - - printf("binding to address %s:%d\n", server_ip, - ntohs(server_sin.sin_port)); - - ret = bind(socket_fd, &server_sin, sizeof(server_sin)); - if (ret) - error(errno, errno, "%s: [FAIL, bind]\n", TEST_PREFIX); - - ret = listen(socket_fd, 1); - if (ret) - error(errno, errno, "%s: [FAIL, listen]\n", TEST_PREFIX); - - client_addr_len = sizeof(client_addr); - - inet_ntop(server_sin.sin_family, &server_sin.sin_addr, buffer, - sizeof(buffer)); - printf("Waiting or connection on %s:%d\n", buffer, - ntohs(server_sin.sin_port)); - client_fd = accept(socket_fd, &client_addr, &client_addr_len); - - inet_ntop(client_addr.sin_family, &client_addr.sin_addr, buffer, - sizeof(buffer)); - printf("Got connection from %s:%d\n", buffer, - ntohs(client_addr.sin_port)); - - while (1) { - struct iovec iov = { .iov_base = iobuf, - .iov_len = sizeof(iobuf) }; - struct dmabuf_cmsg *dmabuf_cmsg = NULL; - struct dma_buf_sync sync = { 0 }; - struct cmsghdr *cm = NULL; - struct msghdr msg = { 0 }; - struct dmabuf_token token; - ssize_t ret; - - is_devmem = false; - printf("\n\n"); - - msg.msg_iov = &iov; - msg.msg_iovlen = 1; - msg.msg_control = ctrl_data; - msg.msg_controllen = sizeof(ctrl_data); - ret = recvmsg(client_fd, &msg, MSG_SOCK_DEVMEM); - printf("recvmsg ret=%ld\n", ret); - if (ret < 0 && (errno == EAGAIN || errno == EWOULDBLOCK)) - continue; - if (ret < 0) { - perror("recvmsg"); - continue; - } - if (ret == 0) { - printf("client exited\n"); - goto cleanup; - } - - i++; - for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) { - if (cm->cmsg_level != SOL_SOCKET || - (cm->cmsg_type != SCM_DEVMEM_DMABUF && - cm->cmsg_type != SCM_DEVMEM_LINEAR)) { - fprintf(stdout, "skipping non-devmem cmsg\n"); - continue; - } - - dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm); - is_devmem = true; - - if (cm->cmsg_type == SCM_DEVMEM_LINEAR) { - /* TODO: process data copied from skb's linear - * buffer. - */ - fprintf(stdout, - "SCM_DEVMEM_LINEAR. dmabuf_cmsg->frag_size=%u\n", - dmabuf_cmsg->frag_size); - - continue; - } - - token.token_start = dmabuf_cmsg->frag_token; - token.token_count = 1; - - total_received += dmabuf_cmsg->frag_size; - printf("received frag_page=%llu, in_page_offset=%llu, frag_offset=%llu, frag_size=%u, token=%u, total_received=%lu, dmabuf_id=%u\n", - dmabuf_cmsg->frag_offset >> PAGE_SHIFT, - dmabuf_cmsg->frag_offset % getpagesize(), - dmabuf_cmsg->frag_offset, dmabuf_cmsg->frag_size, - dmabuf_cmsg->frag_token, total_received, - dmabuf_cmsg->dmabuf_id); - - if (dmabuf_cmsg->dmabuf_id != dmabuf_id) - error(1, 0, - "received on wrong dmabuf_id: flow steering error\n"); - - if (dmabuf_cmsg->frag_size % getpagesize()) - non_page_aligned_frags++; - else - page_aligned_frags++; - - sync.flags = DMA_BUF_SYNC_READ | DMA_BUF_SYNC_START; - ioctl(buf, DMA_BUF_IOCTL_SYNC, &sync); - - if (do_validation) - validate_buffer( - ((unsigned char *)buf_mem) + - dmabuf_cmsg->frag_offset, - dmabuf_cmsg->frag_size); - else - print_nonzero_bytes( - ((unsigned char *)buf_mem) + - dmabuf_cmsg->frag_offset, - dmabuf_cmsg->frag_size); - - sync.flags = DMA_BUF_SYNC_READ | DMA_BUF_SYNC_END; - ioctl(buf, DMA_BUF_IOCTL_SYNC, &sync); - - ret = setsockopt(client_fd, SOL_SOCKET, - SO_DEVMEM_DONTNEED, &token, - sizeof(token)); - if (ret != 1) - error(1, 0, - "SO_DEVMEM_DONTNEED not enough tokens"); - } - if (!is_devmem) - error(1, 0, "flow steering error\n"); - - printf("total_received=%lu\n", total_received); - } - - fprintf(stdout, "%s: ok\n", TEST_PREFIX); - - fprintf(stdout, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", - page_aligned_frags, non_page_aligned_frags); - - fprintf(stdout, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n", - page_aligned_frags, non_page_aligned_frags); - -cleanup: - - munmap(buf_mem, dmabuf_size); - close(client_fd); - close(socket_fd); - close(buf); - close(memfd); - close(devfd); - ynl_sock_destroy(ys); - - return 0; -} - -void run_devmem_tests(void) -{ - struct netdev_queue_id *queues; - int devfd, memfd, buf; - struct ynl_sock *ys; - size_t dmabuf_size; - size_t i = 0; - - dmabuf_size = getpagesize() * NUM_PAGES; - - create_udmabuf(&devfd, &memfd, &buf, dmabuf_size); - - /* Configure RSS to divert all traffic from our devmem queues */ - if (configure_rss()) - error(1, 0, "rss error\n"); - - queues = calloc(num_queues, sizeof(*queues)); - - if (configure_headersplit(1)) - error(1, 0, "Failed to configure header split\n"); - - if (!bind_rx_queue(ifindex, buf, queues, num_queues, &ys)) - error(1, 0, "Binding empty queues array should have failed\n"); - - for (i = 0; i < num_queues; i++) { - queues[i]._present.type = 1; - queues[i]._present.id = 1; - queues[i].type = NETDEV_QUEUE_TYPE_RX; - queues[i].id = start_queue + i; - } - - if (configure_headersplit(0)) - error(1, 0, "Failed to configure header split\n"); - - if (!bind_rx_queue(ifindex, buf, queues, num_queues, &ys)) - error(1, 0, "Configure dmabuf with header split off should have failed\n"); - - if (configure_headersplit(1)) - error(1, 0, "Failed to configure header split\n"); - - for (i = 0; i < num_queues; i++) { - queues[i]._present.type = 1; - queues[i]._present.id = 1; - queues[i].type = NETDEV_QUEUE_TYPE_RX; - queues[i].id = start_queue + i; - } - - if (bind_rx_queue(ifindex, buf, queues, num_queues, &ys)) - error(1, 0, "Failed to bind\n"); - - /* Deactivating a bound queue should not be legal */ - if (!configure_channels(num_queues, num_queues - 1)) - error(1, 0, "Deactivating a bound queue should be illegal.\n"); - - /* Closing the netlink socket does an implicit unbind */ - ynl_sock_destroy(ys); -} - -int main(int argc, char *argv[]) -{ - int is_server = 0, opt; - - while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:")) != -1) { - switch (opt) { - case 'l': - is_server = 1; - break; - case 's': - server_ip = optarg; - break; - case 'c': - client_ip = optarg; - break; - case 'p': - port = optarg; - break; - case 'v': - do_validation = atoll(optarg); - break; - case 'q': - num_queues = atoi(optarg); - break; - case 't': - start_queue = atoi(optarg); - break; - case 'f': - ifname = optarg; - break; - case '?': - printf("unknown option: %c\n", optopt); - break; - } - } - - ifindex = if_nametoindex(ifname); - - for (; optind < argc; optind++) - printf("extra arguments: %s\n", argv[optind]); - - run_devmem_tests(); - - if (is_server) - return do_server(); - - return 0; -} diff --git a/tools/testing/selftests/net/netfilter/Makefile b/tools/testing/selftests/net/netfilter/Makefile index 542f7886a0bc..ffe161fac8b5 100644 --- a/tools/testing/selftests/net/netfilter/Makefile +++ b/tools/testing/selftests/net/netfilter/Makefile @@ -8,6 +8,7 @@ MNL_LDLIBS := $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) TEST_PROGS := br_netfilter.sh bridge_brouter.sh TEST_PROGS += br_netfilter_queue.sh +TEST_PROGS += conntrack_dump_flush.sh TEST_PROGS += conntrack_icmp_related.sh TEST_PROGS += conntrack_ipip_mtu.sh TEST_PROGS += conntrack_tcp_unreplied.sh @@ -36,10 +37,9 @@ TEST_PROGS += xt_string.sh TEST_PROGS_EXTENDED = nft_concat_range_perf.sh -TEST_GEN_PROGS = conntrack_dump_flush - TEST_GEN_FILES = audit_logread TEST_GEN_FILES += connect_close nf_queue +TEST_GEN_FILES += conntrack_dump_flush TEST_GEN_FILES += conntrack_reverse_clash TEST_GEN_FILES += sctp_collision @@ -55,4 +55,5 @@ TEST_FILES := lib.sh TEST_FILES += packetdrill TEST_INCLUDES := \ - ../lib.sh + ../lib.sh \ + $(wildcard ../lib/sh/*.sh) diff --git a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c index dc056fec993b..254ff03297f0 100644 --- a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c +++ b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c @@ -98,7 +98,7 @@ static int conntrack_data_insert(struct mnl_socket *sock, struct nlmsghdr *nlh, char buf[MNL_SOCKET_BUFFER_SIZE]; struct nlmsghdr *rplnlh; unsigned int portid; - int err, ret; + int ret; portid = mnl_socket_get_portid(sock); @@ -217,7 +217,7 @@ static int conntracK_count_zone(struct mnl_socket *sock, uint16_t zone) struct nfgenmsg *nfh; struct nlattr *nest; unsigned int portid; - int err, ret; + int ret; portid = mnl_socket_get_portid(sock); @@ -264,7 +264,7 @@ static int conntrack_flush_zone(struct mnl_socket *sock, uint16_t zone) struct nfgenmsg *nfh; struct nlattr *nest; unsigned int portid; - int err, ret; + int ret; portid = mnl_socket_get_portid(sock); diff --git a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.sh b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.sh new file mode 100755 index 000000000000..8b0935385849 --- /dev/null +++ b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.sh @@ -0,0 +1,3 @@ +#!/bin/bash + +exec unshare -n ./conntrack_dump_flush diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh index b3995550856a..a4ee5496f2a1 100755 --- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh @@ -71,6 +71,8 @@ omtu=9000 lmtu=1500 rmtu=2000 +filesize=$((2 * 1024 * 1024)) + usage(){ echo "nft_flowtable.sh [OPTIONS]" echo @@ -81,12 +83,13 @@ usage(){ exit 1 } -while getopts "o:l:r:" o +while getopts "o:l:r:s:" o do case $o in o) omtu=$OPTARG;; l) lmtu=$OPTARG;; r) rmtu=$OPTARG;; + s) filesize=$OPTARG;; *) usage;; esac done @@ -217,18 +220,10 @@ ns2out=$(mktemp) make_file() { - name=$1 - - SIZE=$((RANDOM % (1024 * 128))) - SIZE=$((SIZE + (1024 * 8))) - TSIZE=$((SIZE * 1024)) - - dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null + name="$1" + sz="$2" - SIZE=$((RANDOM % 1024)) - SIZE=$((SIZE + 128)) - TSIZE=$((TSIZE + SIZE)) - dd if=/dev/urandom conf=notrunc of="$name" bs=1 count=$SIZE 2> /dev/null + head -c "$sz" < /dev/urandom > "$name" } check_counters() @@ -246,18 +241,18 @@ check_counters() local fs fs=$(du -sb "$nsin") local max_orig=${fs%%/*} - local max_repl=$((max_orig/4)) + local max_repl=$((max_orig)) # flowtable fastpath should bypass normal routing one, i.e. the counters in forward hook # should always be lower than the size of the transmitted file (max_orig). if [ "$orig_cnt" -gt "$max_orig" ];then - echo "FAIL: $what: original counter $orig_cnt exceeds expected value $max_orig" 1>&2 + echo "FAIL: $what: original counter $orig_cnt exceeds expected value $max_orig, reply counter $repl_cnt" 1>&2 ret=1 ok=0 fi if [ "$repl_cnt" -gt $max_repl ];then - echo "FAIL: $what: reply counter $repl_cnt exceeds expected value $max_repl" 1>&2 + echo "FAIL: $what: reply counter $repl_cnt exceeds expected value $max_repl, original counter $orig_cnt" 1>&2 ret=1 ok=0 fi @@ -455,7 +450,7 @@ test_tcp_forwarding_nat() return $lret } -make_file "$nsin" +make_file "$nsin" "$filesize" # First test: # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed. @@ -664,8 +659,16 @@ if [ "$1" = "" ]; then l=$(((RANDOM%mtu) + low)) r=$(((RANDOM%mtu) + low)) - echo "re-run with random mtus: -o $o -l $l -r $r" - $0 -o "$o" -l "$l" -r "$r" + MINSIZE=$((2 * 1000 * 1000)) + MAXSIZE=$((64 * 1000 * 1000)) + + filesize=$(((RANDOM * RANDOM) % MAXSIZE)) + if [ "$filesize" -lt "$MINSIZE" ]; then + filesize=$((filesize+MINSIZE)) + fi + + echo "re-run with random mtus and file size: -o $o -l $l -r $r -s $filesize" + $0 -o "$o" -l "$l" -r "$r" -s "$filesize" fi exit $ret diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh index a9d109fcc15c..785e3875a6da 100755 --- a/tools/testing/selftests/net/netfilter/nft_queue.sh +++ b/tools/testing/selftests/net/netfilter/nft_queue.sh @@ -512,10 +512,10 @@ EOF :> "$TMPFILE1" :> "$TMPFILE2" - timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12345,fork OPEN:"$TMPFILE1",trunc & + timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12345,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc & local rpid1=$! - timeout 10 ip netns exec "$ns3" socat UDP-LISTEN:12345,fork OPEN:"$TMPFILE2",trunc & + timeout 10 ip netns exec "$ns3" socat UDP-LISTEN:12345,fork,pf=ipv4 OPEN:"$TMPFILE2",trunc & local rpid2=$! ip netns exec "$nsrouter" ./nf_queue -q 12 -d 1000 & @@ -528,8 +528,8 @@ EOF # Send two packets, one should end up in ns1, other in ns2. # This is because nfqueue will delay packet for long enough so that # second packet will not find existing conntrack entry. - echo "Packet 1" | ip netns exec "$ns1" socat STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221 - echo "Packet 2" | ip netns exec "$ns1" socat STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221 + echo "Packet 1" | ip netns exec "$ns1" socat -u STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221 + echo "Packet 2" | ip netns exec "$ns1" socat -u STDIN UDP-DATAGRAM:10.6.6.6:12345,bind=0.0.0.0:55221 busywait 10000 output_files_written "$TMPFILE1" "$TMPFILE2" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 569bce8b6383..66be7699c72c 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -197,6 +197,12 @@ # # - pmtu_ipv6_route_change # Same as above but with IPv6 +# +# - pmtu_ipv4_mp_exceptions +# Use the same topology as in pmtu_ipv4, but add routeable addresses +# on host A and B on lo reachable via both routers. Host A and B +# addresses have multipath routes to each other, b_r1 mtu = 1500. +# Check that PMTU exceptions are created for both paths. source lib.sh source net_helper.sh @@ -266,7 +272,8 @@ tests=" list_flush_ipv4_exception ipv4: list and flush cached exceptions 1 list_flush_ipv6_exception ipv6: list and flush cached exceptions 1 pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1 - pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1" + pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1 + pmtu_ipv4_mp_exceptions ipv4: PMTU multipath nh exceptions 1" # Addressing and routing for tests with routers: four network segments, with # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an @@ -343,6 +350,9 @@ tunnel6_a_addr="fd00:2::a" tunnel6_b_addr="fd00:2::b" tunnel6_mask="64" +host4_a_addr="192.168.99.99" +host4_b_addr="192.168.88.88" + dummy6_0_prefix="fc00:1000::" dummy6_1_prefix="fc00:1001::" dummy6_mask="64" @@ -984,6 +994,52 @@ setup_ovs_bridge() { run_cmd ip route add ${prefix6}:${b_r1}::1 via ${prefix6}:${a_r1}::2 } +setup_multipath_new() { + # Set up host A with multipath routes to host B host4_b_addr + run_cmd ${ns_a} ip addr add ${host4_a_addr} dev lo + run_cmd ${ns_a} ip nexthop add id 401 via ${prefix4}.${a_r1}.2 dev veth_A-R1 + run_cmd ${ns_a} ip nexthop add id 402 via ${prefix4}.${a_r2}.2 dev veth_A-R2 + run_cmd ${ns_a} ip nexthop add id 403 group 401/402 + run_cmd ${ns_a} ip route add ${host4_b_addr} src ${host4_a_addr} nhid 403 + + # Set up host B with multipath routes to host A host4_a_addr + run_cmd ${ns_b} ip addr add ${host4_b_addr} dev lo + run_cmd ${ns_b} ip nexthop add id 401 via ${prefix4}.${b_r1}.2 dev veth_B-R1 + run_cmd ${ns_b} ip nexthop add id 402 via ${prefix4}.${b_r2}.2 dev veth_B-R2 + run_cmd ${ns_b} ip nexthop add id 403 group 401/402 + run_cmd ${ns_b} ip route add ${host4_a_addr} src ${host4_b_addr} nhid 403 +} + +setup_multipath_old() { + # Set up host A with multipath routes to host B host4_b_addr + run_cmd ${ns_a} ip addr add ${host4_a_addr} dev lo + run_cmd ${ns_a} ip route add ${host4_b_addr} \ + src ${host4_a_addr} \ + nexthop via ${prefix4}.${a_r1}.2 weight 1 \ + nexthop via ${prefix4}.${a_r2}.2 weight 1 + + # Set up host B with multipath routes to host A host4_a_addr + run_cmd ${ns_b} ip addr add ${host4_b_addr} dev lo + run_cmd ${ns_b} ip route add ${host4_a_addr} \ + src ${host4_b_addr} \ + nexthop via ${prefix4}.${b_r1}.2 weight 1 \ + nexthop via ${prefix4}.${b_r2}.2 weight 1 +} + +setup_multipath() { + if [ "$USE_NH" = "yes" ]; then + setup_multipath_new + else + setup_multipath_old + fi + + # Set up routers with routes to dummies + run_cmd ${ns_r1} ip route add ${host4_a_addr} via ${prefix4}.${a_r1}.1 + run_cmd ${ns_r2} ip route add ${host4_a_addr} via ${prefix4}.${a_r2}.1 + run_cmd ${ns_r1} ip route add ${host4_b_addr} via ${prefix4}.${b_r1}.1 + run_cmd ${ns_r2} ip route add ${host4_b_addr} via ${prefix4}.${b_r2}.1 +} + setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip @@ -1076,23 +1132,15 @@ link_get_mtu() { } route_get_dst_exception() { - ns_cmd="${1}" - dst="${2}" - dsfield="${3}" + ns_cmd="${1}"; shift - if [ -z "${dsfield}" ]; then - dsfield=0 - fi - - ${ns_cmd} ip route get "${dst}" dsfield "${dsfield}" + ${ns_cmd} ip route get "$@" } route_get_dst_pmtu_from_exception() { - ns_cmd="${1}" - dst="${2}" - dsfield="${3}" + ns_cmd="${1}"; shift - mtu_parse "$(route_get_dst_exception "${ns_cmd}" "${dst}" "${dsfield}")" + mtu_parse "$(route_get_dst_exception "${ns_cmd}" "$@")" } check_pmtu_value() { @@ -1235,10 +1283,10 @@ test_pmtu_ipv4_dscp_icmp_exception() { run_cmd "${ns_a}" ping -q -M want -Q "${dsfield}" -c 1 -w 1 -s "${len}" "${dst2}" # Check that exceptions have been created with the correct PMTU - pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" dsfield "${policy_mark}")" check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 - pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" dsfield "${policy_mark}")" check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 } @@ -1285,9 +1333,9 @@ test_pmtu_ipv4_dscp_udp_exception() { UDP:"${dst2}":50000,tos="${dsfield}" # Check that exceptions have been created with the correct PMTU - pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" dsfield "${policy_mark}")" check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 - pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" dsfield "${policy_mark}")" check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 } @@ -2056,7 +2104,7 @@ check_running() { pid=${1} cmd=${2} - [ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "{cmd}" ] + [ "$(cat /proc/${pid}/cmdline 2>/dev/null | tr -d '\0')" = "${cmd}" ] } test_cleanup_vxlanX_exception() { @@ -2329,6 +2377,36 @@ test_pmtu_ipv6_route_change() { test_pmtu_ipvX_route_change 6 } +test_pmtu_ipv4_mp_exceptions() { + setup namespaces routing multipath || return $ksft_skip + + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1500 + mtu "${ns_b}" veth_B-R1 1500 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + # Ping and expect two nexthop exceptions for two routes + run_cmd ${ns_a} ping -q -M want -i 0.1 -c 1 -s 1800 "${host4_b_addr}" + + # Check that exceptions have been created with the correct PMTU + pmtu_a_R1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${host4_b_addr}" oif veth_A-R1)" + pmtu_a_R2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${host4_b_addr}" oif veth_A-R2)" + + check_pmtu_value "1500" "${pmtu_a_R1}" "exceeding MTU (veth_A-R1)" || return 1 + check_pmtu_value "1500" "${pmtu_a_R2}" "exceeding MTU (veth_A-R2)" || return 1 +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 87dce3efe31e..7f05b5f9b76f 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -21,10 +21,10 @@ ALL_TESTS=" kci_test_vrf kci_test_encap kci_test_macsec - kci_test_macsec_offload kci_test_ipsec kci_test_ipsec_offload kci_test_fdb_get + kci_test_fdb_del kci_test_neigh_get kci_test_bridge_parent_id kci_test_address_proto @@ -559,73 +559,6 @@ kci_test_macsec() end_test "PASS: macsec" } -kci_test_macsec_offload() -{ - sysfsd=/sys/kernel/debug/netdevsim/netdevsim0/ports/0/ - sysfsnet=/sys/bus/netdevsim/devices/netdevsim0/net/ - probed=false - local ret=0 - run_cmd_grep "^Usage: ip macsec" ip macsec help - if [ $? -ne 0 ]; then - end_test "SKIP: macsec: iproute2 too old" - return $ksft_skip - fi - - if ! mount | grep -q debugfs; then - mount -t debugfs none /sys/kernel/debug/ &> /dev/null - fi - - # setup netdevsim since dummydev doesn't have offload support - if [ ! -w /sys/bus/netdevsim/new_device ] ; then - run_cmd modprobe -q netdevsim - - if [ $ret -ne 0 ]; then - end_test "SKIP: macsec_offload can't load netdevsim" - return $ksft_skip - fi - probed=true - fi - - echo "0" > /sys/bus/netdevsim/new_device - while [ ! -d $sysfsnet ] ; do :; done - udevadm settle - dev=`ls $sysfsnet` - - ip link set $dev up - if [ ! -d $sysfsd ] ; then - end_test "FAIL: macsec_offload can't create device $dev" - return 1 - fi - run_cmd_grep 'macsec-hw-offload: on' ethtool -k $dev - if [ $? -eq 1 ] ; then - end_test "FAIL: macsec_offload netdevsim doesn't support MACsec offload" - return 1 - fi - run_cmd ip link add link $dev kci_macsec1 type macsec port 4 offload mac - run_cmd ip link add link $dev kci_macsec2 type macsec address "aa:bb:cc:dd:ee:ff" port 5 offload mac - run_cmd ip link add link $dev kci_macsec3 type macsec sci abbacdde01020304 offload mac - run_cmd_fail ip link add link $dev kci_macsec4 type macsec port 8 offload mac - - msname=kci_macsec1 - run_cmd ip macsec add "$msname" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012 - run_cmd ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" - run_cmd ip macsec add "$msname" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on \ - key 00 0123456789abcdef0123456789abcdef - run_cmd_fail ip macsec add "$msname" rx port 1235 address "1c:ed:de:ad:be:ef" - # clean up any leftovers - for msdev in kci_macsec{1,2,3,4} ; do - ip link del $msdev 2> /dev/null - done - echo 0 > /sys/bus/netdevsim/del_device - $probed && rmmod netdevsim - - if [ $ret -ne 0 ]; then - end_test "FAIL: macsec_offload" - return 1 - fi - end_test "PASS: macsec_offload" -} - #------------------------------------------------------------------- # Example commands # ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \ @@ -1065,6 +998,45 @@ kci_test_fdb_get() end_test "PASS: bridge fdb get" } +kci_test_fdb_del() +{ + local test_mac=de:ad:be:ef:13:37 + local dummydev="dummy1" + local brdev="test-br0" + local ret=0 + + run_cmd_grep 'bridge fdb get' bridge fdb help + if [ $? -ne 0 ]; then + end_test "SKIP: fdb del tests: iproute2 too old" + return $ksft_skip + fi + + setup_ns testns + if [ $? -ne 0 ]; then + end_test "SKIP fdb del tests: cannot add net namespace $testns" + return $ksft_skip + fi + IP="ip -netns $testns" + BRIDGE="bridge -netns $testns" + run_cmd $IP link add $dummydev type dummy + run_cmd $IP link add name $brdev type bridge vlan_filtering 1 + run_cmd $IP link set dev $dummydev master $brdev + run_cmd $BRIDGE fdb add $test_mac dev $dummydev master static vlan 1 + run_cmd $BRIDGE vlan del vid 1 dev $dummydev + run_cmd $BRIDGE fdb get $test_mac br $brdev vlan 1 + run_cmd $BRIDGE fdb del $test_mac dev $dummydev master vlan 1 + run_cmd_fail $BRIDGE fdb get $test_mac br $brdev vlan 1 + + ip netns del $testns &>/dev/null + + if [ $ret -ne 0 ]; then + end_test "FAIL: bridge fdb del" + return 1 + fi + + end_test "PASS: bridge fdb del" +} + kci_test_neigh_get() { dstmac=de:ad:be:ef:13:37 diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh index 4f1edbafb946..6bb7dfaa30b6 100755 --- a/tools/testing/selftests/net/veth.sh +++ b/tools/testing/selftests/net/veth.sh @@ -46,8 +46,6 @@ create_ns() { ip -n $BASE$ns addr add dev veth$ns $BM_NET_V4$ns/24 ip -n $BASE$ns addr add dev veth$ns $BM_NET_V6$ns/64 nodad done - echo "#kernel" > $BASE - chmod go-rw $BASE } __chk_flag() { diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 06ae9c107049..011762224600 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -184,7 +184,7 @@ auto-test-targets := \ testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets))) -$(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR) +$(SCXOBJ_DIR)/runner.o: runner.c | $(SCXOBJ_DIR) $(BPFOBJ) $(CC) $(CFLAGS) -c $< -o $@ # Create all of the test targets object files, whose testcase objects will be diff --git a/tools/testing/selftests/sched_ext/create_dsq.bpf.c b/tools/testing/selftests/sched_ext/create_dsq.bpf.c index 23f79ed343f0..2cfc4ffd60e2 100644 --- a/tools/testing/selftests/sched_ext/create_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/create_dsq.bpf.c @@ -51,8 +51,8 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(create_dsq_init) SEC(".struct_ops.link") struct sched_ext_ops create_dsq_ops = { - .init_task = create_dsq_init_task, - .exit_task = create_dsq_exit_task, - .init = create_dsq_init, + .init_task = (void *) create_dsq_init_task, + .exit_task = (void *) create_dsq_exit_task, + .init = (void *) create_dsq_init, .name = "create_dsq", }; diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c index e97ad41d354a..37d9bf6fb745 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c @@ -35,8 +35,8 @@ void BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops ddsp_bogus_dsq_fail_ops = { - .select_cpu = ddsp_bogus_dsq_fail_select_cpu, - .exit = ddsp_bogus_dsq_fail_exit, + .select_cpu = (void *) ddsp_bogus_dsq_fail_select_cpu, + .exit = (void *) ddsp_bogus_dsq_fail_exit, .name = "ddsp_bogus_dsq_fail", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c index dde7e7dafbfb..dffc97d9cdf1 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -32,8 +32,8 @@ void BPF_STRUCT_OPS(ddsp_vtimelocal_fail_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops ddsp_vtimelocal_fail_ops = { - .select_cpu = ddsp_vtimelocal_fail_select_cpu, - .exit = ddsp_vtimelocal_fail_exit, + .select_cpu = (void *) ddsp_vtimelocal_fail_select_cpu, + .exit = (void *) ddsp_vtimelocal_fail_exit, .name = "ddsp_vtimelocal_fail", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index efb4672decb4..6a7db1502c29 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -56,10 +56,10 @@ void BPF_STRUCT_OPS(dsp_local_on_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops dsp_local_on_ops = { - .select_cpu = dsp_local_on_select_cpu, - .enqueue = dsp_local_on_enqueue, - .dispatch = dsp_local_on_dispatch, - .exit = dsp_local_on_exit, + .select_cpu = (void *) dsp_local_on_select_cpu, + .enqueue = (void *) dsp_local_on_enqueue, + .dispatch = (void *) dsp_local_on_dispatch, + .exit = (void *) dsp_local_on_exit, .name = "dsp_local_on", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c index b0b99531d5d5..e1bd13e48889 100644 --- a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c +++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.bpf.c @@ -12,10 +12,18 @@ char _license[] SEC("license") = "GPL"; +u32 exit_kind; + +void BPF_STRUCT_OPS_SLEEPABLE(enq_last_no_enq_fails_exit, struct scx_exit_info *info) +{ + exit_kind = info->kind; +} + SEC(".struct_ops.link") struct sched_ext_ops enq_last_no_enq_fails_ops = { .name = "enq_last_no_enq_fails", /* Need to define ops.enqueue() with SCX_OPS_ENQ_LAST */ .flags = SCX_OPS_ENQ_LAST, + .exit = (void *) enq_last_no_enq_fails_exit, .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c index 2a3eda5e2c0b..73e679953e27 100644 --- a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c +++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c @@ -31,8 +31,12 @@ static enum scx_test_status run(void *ctx) struct bpf_link *link; link = bpf_map__attach_struct_ops(skel->maps.enq_last_no_enq_fails_ops); - if (link) { - SCX_ERR("Incorrectly succeeded in to attaching scheduler"); + if (!link) { + SCX_ERR("Incorrectly failed at attaching scheduler"); + return SCX_TEST_FAIL; + } + if (!skel->bss->exit_kind) { + SCX_ERR("Incorrectly stayed loaded"); return SCX_TEST_FAIL; } @@ -50,7 +54,7 @@ static void cleanup(void *ctx) struct scx_test enq_last_no_enq_fails = { .name = "enq_last_no_enq_fails", - .description = "Verify we fail to load a scheduler if we specify " + .description = "Verify we eject a scheduler if we specify " "the SCX_OPS_ENQ_LAST flag without defining " "ops.enqueue()", .setup = setup, diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c index b3dfc1033cd6..1efb50d61040 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c @@ -36,8 +36,8 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p, SEC(".struct_ops.link") struct sched_ext_ops enq_select_cpu_fails_ops = { - .select_cpu = enq_select_cpu_fails_select_cpu, - .enqueue = enq_select_cpu_fails_enqueue, + .select_cpu = (void *) enq_select_cpu_fails_select_cpu, + .enqueue = (void *) enq_select_cpu_fails_enqueue, .name = "enq_select_cpu_fails", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c index ae12ddaac921..d75d4faf07f6 100644 --- a/tools/testing/selftests/sched_ext/exit.bpf.c +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -15,6 +15,8 @@ UEI_DEFINE(uei); #define EXIT_CLEANLY() scx_bpf_exit(exit_point, "%d", exit_point) +#define DSQ_ID 0 + s32 BPF_STRUCT_OPS(exit_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { @@ -31,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags) if (exit_point == EXIT_ENQUEUE) EXIT_CLEANLY(); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) @@ -39,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) if (exit_point == EXIT_DISPATCH) EXIT_CLEANLY(); - scx_bpf_consume(SCX_DSQ_GLOBAL); + scx_bpf_consume(DSQ_ID); } void BPF_STRUCT_OPS(exit_enable, struct task_struct *p) @@ -67,18 +69,18 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(exit_init) if (exit_point == EXIT_INIT) EXIT_CLEANLY(); - return 0; + return scx_bpf_create_dsq(DSQ_ID, -1); } SEC(".struct_ops.link") struct sched_ext_ops exit_ops = { - .select_cpu = exit_select_cpu, - .enqueue = exit_enqueue, - .dispatch = exit_dispatch, - .init_task = exit_init_task, - .enable = exit_enable, - .exit = exit_exit, - .init = exit_init, + .select_cpu = (void *) exit_select_cpu, + .enqueue = (void *) exit_enqueue, + .dispatch = (void *) exit_dispatch, + .init_task = (void *) exit_init_task, + .enable = (void *) exit_enable, + .exit = (void *) exit_exit, + .init = (void *) exit_init, .name = "exit", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/hotplug.bpf.c b/tools/testing/selftests/sched_ext/hotplug.bpf.c index 8f2601db39f3..6c9f25c9bf53 100644 --- a/tools/testing/selftests/sched_ext/hotplug.bpf.c +++ b/tools/testing/selftests/sched_ext/hotplug.bpf.c @@ -46,16 +46,16 @@ void BPF_STRUCT_OPS_SLEEPABLE(hotplug_cpu_offline, s32 cpu) SEC(".struct_ops.link") struct sched_ext_ops hotplug_cb_ops = { - .cpu_online = hotplug_cpu_online, - .cpu_offline = hotplug_cpu_offline, - .exit = hotplug_exit, + .cpu_online = (void *) hotplug_cpu_online, + .cpu_offline = (void *) hotplug_cpu_offline, + .exit = (void *) hotplug_exit, .name = "hotplug_cbs", .timeout_ms = 1000U, }; SEC(".struct_ops.link") struct sched_ext_ops hotplug_nocb_ops = { - .exit = hotplug_exit, + .exit = (void *) hotplug_exit, .name = "hotplug_nocbs", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/init_enable_count.bpf.c b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c index 47ea89a626c3..5eb9edb1837d 100644 --- a/tools/testing/selftests/sched_ext/init_enable_count.bpf.c +++ b/tools/testing/selftests/sched_ext/init_enable_count.bpf.c @@ -45,9 +45,9 @@ void BPF_STRUCT_OPS(cnt_disable, struct task_struct *p) SEC(".struct_ops.link") struct sched_ext_ops init_enable_count_ops = { - .init_task = cnt_init_task, - .exit_task = cnt_exit_task, - .enable = cnt_enable, - .disable = cnt_disable, + .init_task = (void *) cnt_init_task, + .exit_task = (void *) cnt_exit_task, + .enable = (void *) cnt_enable, + .disable = (void *) cnt_disable, .name = "init_enable_count", }; diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 00bfa9cb95d3..4d4cd8d966db 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -131,34 +131,34 @@ void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info) SEC(".struct_ops.link") struct sched_ext_ops maximal_ops = { - .select_cpu = maximal_select_cpu, - .enqueue = maximal_enqueue, - .dequeue = maximal_dequeue, - .dispatch = maximal_dispatch, - .runnable = maximal_runnable, - .running = maximal_running, - .stopping = maximal_stopping, - .quiescent = maximal_quiescent, - .yield = maximal_yield, - .core_sched_before = maximal_core_sched_before, - .set_weight = maximal_set_weight, - .set_cpumask = maximal_set_cpumask, - .update_idle = maximal_update_idle, - .cpu_acquire = maximal_cpu_acquire, - .cpu_release = maximal_cpu_release, - .cpu_online = maximal_cpu_online, - .cpu_offline = maximal_cpu_offline, - .init_task = maximal_init_task, - .enable = maximal_enable, - .exit_task = maximal_exit_task, - .disable = maximal_disable, - .cgroup_init = maximal_cgroup_init, - .cgroup_exit = maximal_cgroup_exit, - .cgroup_prep_move = maximal_cgroup_prep_move, - .cgroup_move = maximal_cgroup_move, - .cgroup_cancel_move = maximal_cgroup_cancel_move, - .cgroup_set_weight = maximal_cgroup_set_weight, - .init = maximal_init, - .exit = maximal_exit, + .select_cpu = (void *) maximal_select_cpu, + .enqueue = (void *) maximal_enqueue, + .dequeue = (void *) maximal_dequeue, + .dispatch = (void *) maximal_dispatch, + .runnable = (void *) maximal_runnable, + .running = (void *) maximal_running, + .stopping = (void *) maximal_stopping, + .quiescent = (void *) maximal_quiescent, + .yield = (void *) maximal_yield, + .core_sched_before = (void *) maximal_core_sched_before, + .set_weight = (void *) maximal_set_weight, + .set_cpumask = (void *) maximal_set_cpumask, + .update_idle = (void *) maximal_update_idle, + .cpu_acquire = (void *) maximal_cpu_acquire, + .cpu_release = (void *) maximal_cpu_release, + .cpu_online = (void *) maximal_cpu_online, + .cpu_offline = (void *) maximal_cpu_offline, + .init_task = (void *) maximal_init_task, + .enable = (void *) maximal_enable, + .exit_task = (void *) maximal_exit_task, + .disable = (void *) maximal_disable, + .cgroup_init = (void *) maximal_cgroup_init, + .cgroup_exit = (void *) maximal_cgroup_exit, + .cgroup_prep_move = (void *) maximal_cgroup_prep_move, + .cgroup_move = (void *) maximal_cgroup_move, + .cgroup_cancel_move = (void *) maximal_cgroup_cancel_move, + .cgroup_set_weight = (void *) maximal_cgroup_set_weight, + .init = (void *) maximal_init, + .exit = (void *) maximal_exit, .name = "maximal", }; diff --git a/tools/testing/selftests/sched_ext/maybe_null.bpf.c b/tools/testing/selftests/sched_ext/maybe_null.bpf.c index 27d0f386acfb..cf4ae870cd4e 100644 --- a/tools/testing/selftests/sched_ext/maybe_null.bpf.c +++ b/tools/testing/selftests/sched_ext/maybe_null.bpf.c @@ -29,8 +29,8 @@ bool BPF_STRUCT_OPS(maybe_null_success_yield, struct task_struct *from, SEC(".struct_ops.link") struct sched_ext_ops maybe_null_success = { - .dispatch = maybe_null_success_dispatch, - .yield = maybe_null_success_yield, - .enable = maybe_null_running, + .dispatch = (void *) maybe_null_success_dispatch, + .yield = (void *) maybe_null_success_yield, + .enable = (void *) maybe_null_running, .name = "minimal", }; diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c index c0641050271d..ec724d7b33d1 100644 --- a/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/maybe_null_fail_dsp.bpf.c @@ -19,7 +19,7 @@ void BPF_STRUCT_OPS(maybe_null_fail_dispatch, s32 cpu, struct task_struct *p) SEC(".struct_ops.link") struct sched_ext_ops maybe_null_fail = { - .dispatch = maybe_null_fail_dispatch, - .enable = maybe_null_running, + .dispatch = (void *) maybe_null_fail_dispatch, + .enable = (void *) maybe_null_running, .name = "maybe_null_fail_dispatch", }; diff --git a/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c index 3c1740028e3b..e6552cace020 100644 --- a/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c +++ b/tools/testing/selftests/sched_ext/maybe_null_fail_yld.bpf.c @@ -22,7 +22,7 @@ bool BPF_STRUCT_OPS(maybe_null_fail_yield, struct task_struct *from, SEC(".struct_ops.link") struct sched_ext_ops maybe_null_fail = { - .yield = maybe_null_fail_yield, - .enable = maybe_null_running, + .yield = (void *) maybe_null_fail_yield, + .enable = (void *) maybe_null_running, .name = "maybe_null_fail_yield", }; diff --git a/tools/testing/selftests/sched_ext/prog_run.bpf.c b/tools/testing/selftests/sched_ext/prog_run.bpf.c index 6a4d7c48e3f2..00c267626a68 100644 --- a/tools/testing/selftests/sched_ext/prog_run.bpf.c +++ b/tools/testing/selftests/sched_ext/prog_run.bpf.c @@ -28,6 +28,6 @@ void BPF_STRUCT_OPS(prog_run_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops prog_run_ops = { - .exit = prog_run_exit, + .exit = (void *) prog_run_exit, .name = "prog_run", }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c index 2ed2991afafe..f171ac470970 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c @@ -35,6 +35,6 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p, SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dfl_ops = { - .enqueue = select_cpu_dfl_enqueue, + .enqueue = (void *) select_cpu_dfl_enqueue, .name = "select_cpu_dfl", }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c index 4bb5abb2d369..9efdbb7da928 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c @@ -82,8 +82,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task, SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dfl_nodispatch_ops = { - .select_cpu = select_cpu_dfl_nodispatch_select_cpu, - .enqueue = select_cpu_dfl_nodispatch_enqueue, - .init_task = select_cpu_dfl_nodispatch_init_task, + .select_cpu = (void *) select_cpu_dfl_nodispatch_select_cpu, + .enqueue = (void *) select_cpu_dfl_nodispatch_enqueue, + .init_task = (void *) select_cpu_dfl_nodispatch_init_task, .name = "select_cpu_dfl_nodispatch", }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c index f0b96a4a04b2..59bfc4f36167 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c @@ -35,7 +35,7 @@ dispatch: SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dispatch_ops = { - .select_cpu = select_cpu_dispatch_select_cpu, + .select_cpu = (void *) select_cpu_dispatch_select_cpu, .name = "select_cpu_dispatch", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c index 7b42ddce0f56..3bbd5fcdfb18 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c @@ -30,8 +30,8 @@ void BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dispatch_bad_dsq_ops = { - .select_cpu = select_cpu_dispatch_bad_dsq_select_cpu, - .exit = select_cpu_dispatch_bad_dsq_exit, + .select_cpu = (void *) select_cpu_dispatch_bad_dsq_select_cpu, + .exit = (void *) select_cpu_dispatch_bad_dsq_exit, .name = "select_cpu_dispatch_bad_dsq", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c index 653e3dc0b4dc..0fda57fe0ecf 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c @@ -31,8 +31,8 @@ void BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_exit, struct scx_exit_info *ei) SEC(".struct_ops.link") struct sched_ext_ops select_cpu_dispatch_dbl_dsp_ops = { - .select_cpu = select_cpu_dispatch_dbl_dsp_select_cpu, - .exit = select_cpu_dispatch_dbl_dsp_exit, + .select_cpu = (void *) select_cpu_dispatch_dbl_dsp_select_cpu, + .exit = (void *) select_cpu_dispatch_dbl_dsp_exit, .name = "select_cpu_dispatch_dbl_dsp", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c index 7f3ebf4fc2ea..e6c67bcf5e6e 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -81,12 +81,12 @@ s32 BPF_STRUCT_OPS_SLEEPABLE(select_cpu_vtime_init) SEC(".struct_ops.link") struct sched_ext_ops select_cpu_vtime_ops = { - .select_cpu = select_cpu_vtime_select_cpu, - .dispatch = select_cpu_vtime_dispatch, - .running = select_cpu_vtime_running, - .stopping = select_cpu_vtime_stopping, - .enable = select_cpu_vtime_enable, - .init = select_cpu_vtime_init, + .select_cpu = (void *) select_cpu_vtime_select_cpu, + .dispatch = (void *) select_cpu_vtime_dispatch, + .running = (void *) select_cpu_vtime_running, + .stopping = (void *) select_cpu_vtime_stopping, + .enable = (void *) select_cpu_vtime_enable, + .init = (void *) select_cpu_vtime_init, .name = "select_cpu_vtime", .timeout_ms = 1000U, }; diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json new file mode 100644 index 000000000000..d3dd65b05b5f --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -0,0 +1,98 @@ +[ + { + "id": "ca5e", + "name": "Check class delete notification for ffff:", + "category": [ + "qdisc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: drr", + "$TC filter add dev $DUMMY parent 1: basic classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr", + "$TC qdisc add dev $DUMMY parent 1:1 handle ffff: drr", + "$TC filter add dev $DUMMY parent ffff: basic classid ffff:1", + "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr", + "$TC qdisc add dev $DUMMY parent ffff:1 netem delay 1s", + "ping -c1 -W0.01 -I $DUMMY 10.10.10.1 || true", + "$TC class del dev $DUMMY classid ffff:1", + "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC -s qdisc ls dev $DUMMY", + "matchPattern": "drr 1: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: drr", + "$IP addr del 10.10.10.10/24 dev $DUMMY" + ] + }, + { + "id": "e4b7", + "name": "Check class delete notification for root ffff:", + "category": [ + "qdisc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle ffff: drr", + "$TC filter add dev $DUMMY parent ffff: basic classid ffff:1", + "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr", + "$TC qdisc add dev $DUMMY parent ffff:1 netem delay 1s", + "ping -c1 -W0.01 -I $DUMMY 10.10.10.1 || true", + "$TC class del dev $DUMMY classid ffff:1", + "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC qdisc ls dev $DUMMY", + "matchPattern": "drr ffff: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle ffff: drr", + "$IP addr del 10.10.10.10/24 dev $DUMMY" + ] + }, + { + "id": "33a9", + "name": "Check ingress is not searchable on backlog update", + "category": [ + "qdisc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY ingress", + "$TC qdisc add dev $DUMMY root handle 1: drr", + "$TC filter add dev $DUMMY parent 1: basic classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: drr", + "$TC filter add dev $DUMMY parent 2: basic classid 2:1", + "$TC class add dev $DUMMY parent 2: classid 2:1 drr", + "$TC qdisc add dev $DUMMY parent 2:1 netem delay 1s", + "ping -c1 -W0.01 -I $DUMMY 10.10.10.1 || true" + ], + "cmdUnderTest": "$TC class del dev $DUMMY classid 2:1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc ls dev $DUMMY", + "matchPattern": "drr 1: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: drr", + "$TC qdisc del dev $DUMMY ingress", + "$IP addr del 10.10.10.10/24 dev $DUMMY" + ] + } +] diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c index bc71cbca0dde..a1f506ba5578 100644 --- a/tools/testing/selftests/watchdog/watchdog-test.c +++ b/tools/testing/selftests/watchdog/watchdog-test.c @@ -334,7 +334,13 @@ int main(int argc, char *argv[]) printf("Watchdog Ticking Away!\n"); + /* + * Register the signals + */ signal(SIGINT, term); + signal(SIGTERM, term); + signal(SIGKILL, term); + signal(SIGQUIT, term); while (1) { keep_alive(); diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c index c53f220eb6cc..b33b47342d41 100644 --- a/tools/testing/vma/vma.c +++ b/tools/testing/vma/vma.c @@ -1522,6 +1522,45 @@ static bool test_copy_vma(void) return true; } +static bool test_expand_only_mode(void) +{ + unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE; + struct mm_struct mm = {}; + VMA_ITERATOR(vmi, &mm, 0); + struct vm_area_struct *vma_prev, *vma; + VMG_STATE(vmg, &mm, &vmi, 0x5000, 0x9000, flags, 5); + + /* + * Place a VMA prior to the one we're expanding so we assert that we do + * not erroneously try to traverse to the previous VMA even though we + * have, through the use of VMG_FLAG_JUST_EXPAND, indicated we do not + * need to do so. + */ + alloc_and_link_vma(&mm, 0, 0x2000, 0, flags); + + /* + * We will be positioned at the prev VMA, but looking to expand to + * 0x9000. + */ + vma_iter_set(&vmi, 0x3000); + vma_prev = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags); + vmg.prev = vma_prev; + vmg.merge_flags = VMG_FLAG_JUST_EXPAND; + + vma = vma_merge_new_range(&vmg); + ASSERT_NE(vma, NULL); + ASSERT_EQ(vma, vma_prev); + ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS); + ASSERT_EQ(vma->vm_start, 0x3000); + ASSERT_EQ(vma->vm_end, 0x9000); + ASSERT_EQ(vma->vm_pgoff, 3); + ASSERT_TRUE(vma_write_started(vma)); + ASSERT_EQ(vma_iter_addr(&vmi), 0x3000); + + cleanup_mm(&mm, &vmi); + return true; +} + int main(void) { int num_tests = 0, num_fail = 0; @@ -1553,6 +1592,7 @@ int main(void) TEST(vmi_prealloc_fail); TEST(merge_extend); TEST(copy_vma); + TEST(expand_only_mode); #undef TEST diff --git a/tools/usb/usbip/src/usbip_detach.c b/tools/usb/usbip/src/usbip_detach.c index b29101986b5a..6b78d4a81e95 100644 --- a/tools/usb/usbip/src/usbip_detach.c +++ b/tools/usb/usbip/src/usbip_detach.c @@ -68,6 +68,7 @@ static int detach_port(char *port) } if (!found) { + ret = -1; err("Invalid port %s > maxports %d", port, vhci_driver->nports); goto call_driver_close; |