diff options
1120 files changed, 24052 insertions, 6837 deletions
@@ -971,6 +971,7 @@ D: PowerPC N: Daniel Drake E: dsd@gentoo.org D: USBAT02 CompactFlash support in usb-storage +D: ZD1211RW wireless driver S: UK N: Oleg Drokin diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index babbe04c8d37..4d8c27eca96b 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1226,7 +1226,7 @@ PAGE_SIZE multiple when read back. Note that all fields in this file are hierarchical and the file modified event can be generated due to an event down the - hierarchy. For for the local events at the cgroup level see + hierarchy. For the local events at the cgroup level see memory.events.local. low @@ -2170,19 +2170,19 @@ existing device files. Cgroup v2 device controller has no interface files and is implemented on top of cgroup BPF. To control access to device files, a user may -create bpf programs of the BPF_CGROUP_DEVICE type and attach them -to cgroups. On an attempt to access a device file, corresponding -BPF programs will be executed, and depending on the return value -the attempt will succeed or fail with -EPERM. - -A BPF_CGROUP_DEVICE program takes a pointer to the bpf_cgroup_dev_ctx -structure, which describes the device access attempt: access type -(mknod/read/write) and device (type, major and minor numbers). -If the program returns 0, the attempt fails with -EPERM, otherwise -it succeeds. - -An example of BPF_CGROUP_DEVICE program may be found in the kernel -source tree in the tools/testing/selftests/bpf/progs/dev_cgroup.c file. +create bpf programs of type BPF_PROG_TYPE_CGROUP_DEVICE and attach +them to cgroups with BPF_CGROUP_DEVICE flag. On an attempt to access a +device file, corresponding BPF programs will be executed, and depending +on the return value the attempt will succeed or fail with -EPERM. + +A BPF_PROG_TYPE_CGROUP_DEVICE program takes a pointer to the +bpf_cgroup_dev_ctx structure, which describes the device access attempt: +access type (mknod/read/write) and device (type, major and minor numbers). +If the program returns 0, the attempt fails with -EPERM, otherwise it +succeeds. + +An example of BPF_PROG_TYPE_CGROUP_DEVICE program may be found in +tools/testing/selftests/bpf/progs/dev_cgroup.c in the kernel source tree. RDMA diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 91ba391f9b32..43dc35fe5bc0 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1266,7 +1266,7 @@ The VGA and EFI output is eventually overwritten by the real console. - The xen output can only be used by Xen PV guests. + The xen option can only be used in Xen domains. The sclp output can only be used on s390. diff --git a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml index 07b20383cbca..b446d0f0f1b4 100644 --- a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml +++ b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml @@ -50,7 +50,6 @@ properties: data-lanes: description: array of physical DSI data lane indexes. minItems: 1 - maxItems: 4 items: - const: 1 - const: 2 @@ -71,7 +70,6 @@ properties: data-lanes: description: array of physical DSI data lane indexes. minItems: 1 - maxItems: 4 items: - const: 1 - const: 2 diff --git a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi86.yaml b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi86.yaml index 1c2daf7c24cc..911564468c5e 100644 --- a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi86.yaml +++ b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi86.yaml @@ -18,7 +18,7 @@ properties: const: ti,sn65dsi86 reg: - const: 0x2d + enum: [ 0x2c, 0x2d ] enable-gpios: maxItems: 1 diff --git a/Documentation/devicetree/bindings/display/panel/ilitek,ili9341.yaml b/Documentation/devicetree/bindings/display/panel/ilitek,ili9341.yaml index 2ed010f91e2d..20ce88ab4b3a 100644 --- a/Documentation/devicetree/bindings/display/panel/ilitek,ili9341.yaml +++ b/Documentation/devicetree/bindings/display/panel/ilitek,ili9341.yaml @@ -22,7 +22,7 @@ properties: items: - enum: # ili9341 240*320 Color on stm32f429-disco board - - st,sf-tc240t-9370-t + - st,sf-tc240t-9370-t - const: ilitek,ili9341 reg: true diff --git a/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml b/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml index 29de7807df54..bcd41e491f1d 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,sdm660.yaml @@ -31,11 +31,11 @@ properties: clocks: minItems: 1 - maxItems: 3 + maxItems: 7 clock-names: minItems: 1 - maxItems: 3 + maxItems: 7 required: - compatible @@ -72,6 +72,32 @@ allOf: contains: enum: - qcom,sdm660-a2noc + then: + properties: + clocks: + items: + - description: Bus Clock. + - description: Bus A Clock. + - description: IPA Clock. + - description: UFS AXI Clock. + - description: Aggregate2 UFS AXI Clock. + - description: Aggregate2 USB3 AXI Clock. + - description: Config NoC USB2 AXI Clock. + clock-names: + items: + - const: bus + - const: bus_a + - const: ipa + - const: ufs_axi + - const: aggre2_ufs_axi + - const: aggre2_usb3_axi + - const: cfg_noc_usb2_axi + + - if: + properties: + compatible: + contains: + enum: - qcom,sdm660-bimc - qcom,sdm660-cnoc - qcom,sdm660-gnoc @@ -91,6 +117,7 @@ examples: - | #include <dt-bindings/clock/qcom,rpmcc.h> #include <dt-bindings/clock/qcom,mmcc-sdm660.h> + #include <dt-bindings/clock/qcom,gcc-sdm660.h> bimc: interconnect@1008000 { compatible = "qcom,sdm660-bimc"; @@ -123,9 +150,20 @@ examples: compatible = "qcom,sdm660-a2noc"; reg = <0x01704000 0xc100>; #interconnect-cells = <1>; - clock-names = "bus", "bus_a"; + clock-names = "bus", + "bus_a", + "ipa", + "ufs_axi", + "aggre2_ufs_axi", + "aggre2_usb3_axi", + "cfg_noc_usb2_axi"; clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>, - <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>; + <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>, + <&rpmcc RPM_SMD_IPA_CLK>, + <&gcc GCC_UFS_AXI_CLK>, + <&gcc GCC_AGGRE2_UFS_AXI_CLK>, + <&gcc GCC_AGGRE2_USB3_AXI_CLK>, + <&gcc GCC_CFG_NOC_USB2_AXI_CLK>; }; mnoc: interconnect@1745000 { diff --git a/Documentation/devicetree/bindings/media/i2c/ovti,ov5647.yaml b/Documentation/devicetree/bindings/media/i2c/ovti,ov5647.yaml index 3e5d82df90a2..a2abed06a099 100644 --- a/Documentation/devicetree/bindings/media/i2c/ovti,ov5647.yaml +++ b/Documentation/devicetree/bindings/media/i2c/ovti,ov5647.yaml @@ -31,7 +31,7 @@ properties: maxItems: 1 port: - $ref: /schemas/graph.yaml#/properties/port + $ref: /schemas/graph.yaml#/$defs/port-base additionalProperties: false properties: diff --git a/Documentation/devicetree/bindings/media/i2c/ovti,ov9282.yaml b/Documentation/devicetree/bindings/media/i2c/ovti,ov9282.yaml index ad42992c6da3..bf115ab9d926 100644 --- a/Documentation/devicetree/bindings/media/i2c/ovti,ov9282.yaml +++ b/Documentation/devicetree/bindings/media/i2c/ovti,ov9282.yaml @@ -38,7 +38,7 @@ properties: port: additionalProperties: false - $ref: /schemas/graph.yaml#/properties/port + $ref: /schemas/graph.yaml#/$defs/port-base properties: endpoint: diff --git a/Documentation/devicetree/bindings/media/i2c/sony,imx335.yaml b/Documentation/devicetree/bindings/media/i2c/sony,imx335.yaml index 881f79532501..cf2ca2702cc9 100644 --- a/Documentation/devicetree/bindings/media/i2c/sony,imx335.yaml +++ b/Documentation/devicetree/bindings/media/i2c/sony,imx335.yaml @@ -38,7 +38,7 @@ properties: port: additionalProperties: false - $ref: /schemas/graph.yaml#/properties/port + $ref: /schemas/graph.yaml#/$defs/port-base properties: endpoint: diff --git a/Documentation/devicetree/bindings/media/i2c/sony,imx412.yaml b/Documentation/devicetree/bindings/media/i2c/sony,imx412.yaml index 1edeabf39e6a..afcf70947f7e 100644 --- a/Documentation/devicetree/bindings/media/i2c/sony,imx412.yaml +++ b/Documentation/devicetree/bindings/media/i2c/sony,imx412.yaml @@ -38,7 +38,7 @@ properties: port: additionalProperties: false - $ref: /schemas/graph.yaml#/properties/port + $ref: /schemas/graph.yaml#/$defs/port-base properties: endpoint: diff --git a/Documentation/devicetree/bindings/mmc/snps,dwcmshc-sdhci.yaml b/Documentation/devicetree/bindings/mmc/snps,dwcmshc-sdhci.yaml index e6c9a2f77cc7..f300ced4cdf3 100644 --- a/Documentation/devicetree/bindings/mmc/snps,dwcmshc-sdhci.yaml +++ b/Documentation/devicetree/bindings/mmc/snps,dwcmshc-sdhci.yaml @@ -20,9 +20,7 @@ properties: - snps,dwcmshc-sdhci reg: - minItems: 1 - items: - - description: Offset and length of the register set for the device + maxItems: 1 interrupts: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.yaml b/Documentation/devicetree/bindings/net/dsa/dsa.yaml index 16aa192c118e..224cfa45de9a 100644 --- a/Documentation/devicetree/bindings/net/dsa/dsa.yaml +++ b/Documentation/devicetree/bindings/net/dsa/dsa.yaml @@ -73,11 +73,14 @@ patternProperties: dsa-tag-protocol: description: Instead of the default, the switch will use this tag protocol if - possible. Useful when a device supports multiple protcols and + possible. Useful when a device supports multiple protocols and the default is incompatible with the Ethernet device. enum: - dsa - edsa + - ocelot + - ocelot-8021q + - seville phy-handle: true diff --git a/Documentation/devicetree/bindings/net/dsa/marvell.txt b/Documentation/devicetree/bindings/net/dsa/marvell.txt index 30c11fea491b..2363b412410c 100644 --- a/Documentation/devicetree/bindings/net/dsa/marvell.txt +++ b/Documentation/devicetree/bindings/net/dsa/marvell.txt @@ -83,7 +83,7 @@ Example: #interrupt-cells = <2>; switch0: switch@0 { - compatible = "marvell,mv88e6390"; + compatible = "marvell,mv88e6190"; reg = <0>; reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>; diff --git a/Documentation/devicetree/bindings/net/dsa/qca8k.txt b/Documentation/devicetree/bindings/net/dsa/qca8k.txt deleted file mode 100644 index 8c73f67c43ca..000000000000 --- a/Documentation/devicetree/bindings/net/dsa/qca8k.txt +++ /dev/null @@ -1,215 +0,0 @@ -* Qualcomm Atheros QCA8xxx switch family - -Required properties: - -- compatible: should be one of: - "qca,qca8327" - "qca,qca8334" - "qca,qca8337" - -- #size-cells: must be 0 -- #address-cells: must be 1 - -Optional properties: - -- reset-gpios: GPIO to be used to reset the whole device - -Subnodes: - -The integrated switch subnode should be specified according to the binding -described in dsa/dsa.txt. If the QCA8K switch is connect to a SoC's external -mdio-bus each subnode describing a port needs to have a valid phandle -referencing the internal PHY it is connected to. This is because there's no -N:N mapping of port and PHY id. -To declare the internal mdio-bus configuration, declare a mdio node in the -switch node and declare the phandle for the port referencing the internal -PHY is connected to. In this config a internal mdio-bus is registered and -the mdio MASTER is used as communication. - -Don't use mixed external and internal mdio-bus configurations, as this is -not supported by the hardware. - -The CPU port of this switch is always port 0. - -A CPU port node has the following optional node: - -- fixed-link : Fixed-link subnode describing a link to a non-MDIO - managed entity. See - Documentation/devicetree/bindings/net/fixed-link.txt - for details. - -For QCA8K the 'fixed-link' sub-node supports only the following properties: - -- 'speed' (integer, mandatory), to indicate the link speed. Accepted - values are 10, 100 and 1000 -- 'full-duplex' (boolean, optional), to indicate that full duplex is - used. When absent, half duplex is assumed. - -Examples: - -for the external mdio-bus configuration: - - &mdio0 { - phy_port1: phy@0 { - reg = <0>; - }; - - phy_port2: phy@1 { - reg = <1>; - }; - - phy_port3: phy@2 { - reg = <2>; - }; - - phy_port4: phy@3 { - reg = <3>; - }; - - phy_port5: phy@4 { - reg = <4>; - }; - - switch@10 { - compatible = "qca,qca8337"; - #address-cells = <1>; - #size-cells = <0>; - - reset-gpios = <&gpio 42 GPIO_ACTIVE_LOW>; - reg = <0x10>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - port@0 { - reg = <0>; - label = "cpu"; - ethernet = <&gmac1>; - phy-mode = "rgmii"; - fixed-link { - speed = 1000; - full-duplex; - }; - }; - - port@1 { - reg = <1>; - label = "lan1"; - phy-handle = <&phy_port1>; - }; - - port@2 { - reg = <2>; - label = "lan2"; - phy-handle = <&phy_port2>; - }; - - port@3 { - reg = <3>; - label = "lan3"; - phy-handle = <&phy_port3>; - }; - - port@4 { - reg = <4>; - label = "lan4"; - phy-handle = <&phy_port4>; - }; - - port@5 { - reg = <5>; - label = "wan"; - phy-handle = <&phy_port5>; - }; - }; - }; - }; - -for the internal master mdio-bus configuration: - - &mdio0 { - switch@10 { - compatible = "qca,qca8337"; - #address-cells = <1>; - #size-cells = <0>; - - reset-gpios = <&gpio 42 GPIO_ACTIVE_LOW>; - reg = <0x10>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - label = "cpu"; - ethernet = <&gmac1>; - phy-mode = "rgmii"; - fixed-link { - speed = 1000; - full-duplex; - }; - }; - - port@1 { - reg = <1>; - label = "lan1"; - phy-mode = "internal"; - phy-handle = <&phy_port1>; - }; - - port@2 { - reg = <2>; - label = "lan2"; - phy-mode = "internal"; - phy-handle = <&phy_port2>; - }; - - port@3 { - reg = <3>; - label = "lan3"; - phy-mode = "internal"; - phy-handle = <&phy_port3>; - }; - - port@4 { - reg = <4>; - label = "lan4"; - phy-mode = "internal"; - phy-handle = <&phy_port4>; - }; - - port@5 { - reg = <5>; - label = "wan"; - phy-mode = "internal"; - phy-handle = <&phy_port5>; - }; - }; - - mdio { - #address-cells = <1>; - #size-cells = <0>; - - phy_port1: phy@0 { - reg = <0>; - }; - - phy_port2: phy@1 { - reg = <1>; - }; - - phy_port3: phy@2 { - reg = <2>; - }; - - phy_port4: phy@3 { - reg = <3>; - }; - - phy_port5: phy@4 { - reg = <4>; - }; - }; - }; - }; diff --git a/Documentation/devicetree/bindings/net/dsa/qca8k.yaml b/Documentation/devicetree/bindings/net/dsa/qca8k.yaml new file mode 100644 index 000000000000..48de0ace265d --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/qca8k.yaml @@ -0,0 +1,362 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/dsa/qca8k.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Atheros QCA83xx switch family + +maintainers: + - John Crispin <john@phrozen.org> + +description: + If the QCA8K switch is connect to an SoC's external mdio-bus, each subnode + describing a port needs to have a valid phandle referencing the internal PHY + it is connected to. This is because there is no N:N mapping of port and PHY + ID. To declare the internal mdio-bus configuration, declare an MDIO node in + the switch node and declare the phandle for the port, referencing the internal + PHY it is connected to. In this config, an internal mdio-bus is registered and + the MDIO master is used for communication. Mixed external and internal + mdio-bus configurations are not supported by the hardware. + +properties: + compatible: + oneOf: + - enum: + - qca,qca8327 + - qca,qca8328 + - qca,qca8334 + - qca,qca8337 + description: | + qca,qca8328: referenced as AR8328(N)-AK1(A/B) QFN 176 pin package + qca,qca8327: referenced as AR8327(N)-AL1A DR-QFN 148 pin package + qca,qca8334: referenced as QCA8334-AL3C QFN 88 pin package + qca,qca8337: referenced as QCA8337N-AL3(B/C) DR-QFN 148 pin package + + reg: + maxItems: 1 + + reset-gpios: + description: + GPIO to be used to reset the whole device + maxItems: 1 + + qca,ignore-power-on-sel: + $ref: /schemas/types.yaml#/definitions/flag + description: + Ignore power-on pin strapping to configure LED open-drain or EEPROM + presence. This is needed for devices with incorrect configuration or when + the OEM has decided not to use pin strapping and falls back to SW regs. + + qca,led-open-drain: + $ref: /schemas/types.yaml#/definitions/flag + description: + Set LEDs to open-drain mode. This requires the qca,ignore-power-on-sel to + be set, otherwise the driver will fail at probe. This is required if the + OEM does not use pin strapping to set this mode and prefers to set it + using SW regs. The pin strappings related to LED open-drain mode are + B68 on the QCA832x and B49 on the QCA833x. + + mdio: + type: object + description: Qca8k switch have an internal mdio to access switch port. + If this is not present, the legacy mapping is used and the + internal mdio access is used. + With the legacy mapping the reg corresponding to the internal + mdio is the switch reg with an offset of -1. + + properties: + '#address-cells': + const: 1 + '#size-cells': + const: 0 + + patternProperties: + "^(ethernet-)?phy@[0-4]$": + type: object + + allOf: + - $ref: "http://devicetree.org/schemas/net/mdio.yaml#" + + properties: + reg: + maxItems: 1 + + required: + - reg + +patternProperties: + "^(ethernet-)?ports$": + type: object + properties: + '#address-cells': + const: 1 + '#size-cells': + const: 0 + + patternProperties: + "^(ethernet-)?port@[0-6]$": + type: object + description: Ethernet switch ports + + properties: + reg: + description: Port number + + label: + description: + Describes the label associated with this port, which will become + the netdev name + $ref: /schemas/types.yaml#/definitions/string + + link: + description: + Should be a list of phandles to other switch's DSA port. This + port is used as the outgoing port towards the phandle ports. The + full routing information must be given, not just the one hop + routes to neighbouring switches + $ref: /schemas/types.yaml#/definitions/phandle-array + + ethernet: + description: + Should be a phandle to a valid Ethernet device node. This host + device is what the switch port is connected to + $ref: /schemas/types.yaml#/definitions/phandle + + phy-handle: true + + phy-mode: true + + fixed-link: true + + mac-address: true + + sfp: true + + qca,sgmii-rxclk-falling-edge: + $ref: /schemas/types.yaml#/definitions/flag + description: + Set the receive clock phase to falling edge. Mostly commonly used on + the QCA8327 with CPU port 0 set to SGMII. + + qca,sgmii-txclk-falling-edge: + $ref: /schemas/types.yaml#/definitions/flag + description: + Set the transmit clock phase to falling edge. + + qca,sgmii-enable-pll: + $ref: /schemas/types.yaml#/definitions/flag + description: + For SGMII CPU port, explicitly enable PLL, TX and RX chain along with + Signal Detection. On the QCA8327 this should not be enabled, otherwise + the SGMII port will not initialize. When used on the QCA8337, revision 3 + or greater, a warning will be displayed. When the CPU port is set to + SGMII on the QCA8337, it is advised to set this unless a communication + issue is observed. + + required: + - reg + + additionalProperties: false + +oneOf: + - required: + - ports + - required: + - ethernet-ports + +required: + - compatible + - reg + +additionalProperties: true + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + external_phy_port1: ethernet-phy@0 { + reg = <0>; + }; + + external_phy_port2: ethernet-phy@1 { + reg = <1>; + }; + + external_phy_port3: ethernet-phy@2 { + reg = <2>; + }; + + external_phy_port4: ethernet-phy@3 { + reg = <3>; + }; + + external_phy_port5: ethernet-phy@4 { + reg = <4>; + }; + + switch@10 { + compatible = "qca,qca8337"; + #address-cells = <1>; + #size-cells = <0>; + reset-gpios = <&gpio 42 GPIO_ACTIVE_LOW>; + reg = <0x10>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "cpu"; + ethernet = <&gmac1>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + + port@1 { + reg = <1>; + label = "lan1"; + phy-handle = <&external_phy_port1>; + }; + + port@2 { + reg = <2>; + label = "lan2"; + phy-handle = <&external_phy_port2>; + }; + + port@3 { + reg = <3>; + label = "lan3"; + phy-handle = <&external_phy_port3>; + }; + + port@4 { + reg = <4>; + label = "lan4"; + phy-handle = <&external_phy_port4>; + }; + + port@5 { + reg = <5>; + label = "wan"; + phy-handle = <&external_phy_port5>; + }; + }; + }; + }; + - | + #include <dt-bindings/gpio/gpio.h> + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + switch@10 { + compatible = "qca,qca8337"; + #address-cells = <1>; + #size-cells = <0>; + reset-gpios = <&gpio 42 GPIO_ACTIVE_LOW>; + reg = <0x10>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "cpu"; + ethernet = <&gmac1>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + + port@1 { + reg = <1>; + label = "lan1"; + phy-mode = "internal"; + phy-handle = <&internal_phy_port1>; + }; + + port@2 { + reg = <2>; + label = "lan2"; + phy-mode = "internal"; + phy-handle = <&internal_phy_port2>; + }; + + port@3 { + reg = <3>; + label = "lan3"; + phy-mode = "internal"; + phy-handle = <&internal_phy_port3>; + }; + + port@4 { + reg = <4>; + label = "lan4"; + phy-mode = "internal"; + phy-handle = <&internal_phy_port4>; + }; + + port@5 { + reg = <5>; + label = "wan"; + phy-mode = "internal"; + phy-handle = <&internal_phy_port5>; + }; + + port@6 { + reg = <0>; + label = "cpu"; + ethernet = <&gmac1>; + phy-mode = "sgmii"; + + qca,sgmii-rxclk-falling-edge; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + internal_phy_port1: ethernet-phy@0 { + reg = <0>; + }; + + internal_phy_port2: ethernet-phy@1 { + reg = <1>; + }; + + internal_phy_port3: ethernet-phy@2 { + reg = <2>; + }; + + internal_phy_port4: ethernet-phy@3 { + reg = <3>; + }; + + internal_phy_port5: ethernet-phy@4 { + reg = <4>; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt b/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt index b6ae8541bd55..7959ec237983 100644 --- a/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt +++ b/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt @@ -9,6 +9,7 @@ SMI-based Realtek devices. Required properties: - compatible: must be exactly one of: + "realtek,rtl8365mb" (4+1 ports) "realtek,rtl8366" "realtek,rtl8366rb" (4+1 ports) "realtek,rtl8366s" (4+1 ports) @@ -62,6 +63,8 @@ and subnodes of DSA switches. Examples: +An example for the RTL8366RB: + switch { compatible = "realtek,rtl8366rb"; /* 22 = MDIO (has input reads), 21 = MDC (clock, output only) */ @@ -151,3 +154,87 @@ switch { }; }; }; + +An example for the RTL8365MB-VC: + +switch { + compatible = "realtek,rtl8365mb"; + mdc-gpios = <&gpio1 16 GPIO_ACTIVE_HIGH>; + mdio-gpios = <&gpio1 17 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>; + + switch_intc: interrupt-controller { + interrupt-parent = <&gpio5>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + + ports { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + port@0 { + reg = <0>; + label = "swp0"; + phy-handle = <ðphy0>; + }; + port@1 { + reg = <1>; + label = "swp1"; + phy-handle = <ðphy1>; + }; + port@2 { + reg = <2>; + label = "swp2"; + phy-handle = <ðphy2>; + }; + port@3 { + reg = <3>; + label = "swp3"; + phy-handle = <ðphy3>; + }; + port@6 { + reg = <6>; + label = "cpu"; + ethernet = <&fec1>; + phy-mode = "rgmii"; + tx-internal-delay-ps = <2000>; + rx-internal-delay-ps = <2000>; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + }; + + mdio { + compatible = "realtek,smi-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + ethphy0: phy@0 { + reg = <0>; + interrupt-parent = <&switch_intc>; + interrupts = <0>; + }; + ethphy1: phy@1 { + reg = <1>; + interrupt-parent = <&switch_intc>; + interrupts = <1>; + }; + ethphy2: phy@2 { + reg = <2>; + interrupt-parent = <&switch_intc>; + interrupts = <2>; + }; + ethphy3: phy@3 { + reg = <3>; + interrupt-parent = <&switch_intc>; + interrupts = <3>; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml b/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml index 5629b2e4ccf8..ee4afe361fac 100644 --- a/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml +++ b/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml @@ -34,7 +34,6 @@ properties: clocks: minItems: 3 - maxItems: 5 items: - description: MAC host clock - description: MAC apb clock diff --git a/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml b/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml index 948677ade6d1..d7748dd33199 100644 --- a/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ipq8064-mdio.yaml @@ -51,6 +51,9 @@ examples: switch@10 { compatible = "qca,qca8337"; reg = <0x10>; - /* ... */ + + ports { + /* ... */ + }; }; }; diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index 42689b7d03a2..c115c95ee584 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -21,6 +21,7 @@ select: contains: enum: - snps,dwmac + - snps,dwmac-3.40a - snps,dwmac-3.50a - snps,dwmac-3.610 - snps,dwmac-3.70a @@ -76,6 +77,7 @@ properties: - rockchip,rk3399-gmac - rockchip,rv1108-gmac - snps,dwmac + - snps,dwmac-3.40a - snps,dwmac-3.50a - snps,dwmac-3.610 - snps,dwmac-3.70a diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml index 8a03a24a2019..6bc61c42418f 100644 --- a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml +++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml @@ -24,6 +24,7 @@ properties: - socionext,uniphier-ld11-ave4 - socionext,uniphier-ld20-ave4 - socionext,uniphier-pxs3-ave4 + - socionext,uniphier-nx1-ave4 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml index 2911e565b260..acea1cd444fd 100644 --- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml @@ -41,7 +41,6 @@ properties: - description: builtin MSI controller. interrupt-names: - minItems: 1 items: - const: msi diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst index 364680cdad2e..8ba72e898099 100644 --- a/Documentation/gpu/amdgpu.rst +++ b/Documentation/gpu/amdgpu.rst @@ -300,8 +300,8 @@ pcie_replay_count .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c :doc: pcie_replay_count -+GPU SmartShift Information -============================ +GPU SmartShift Information +========================== GPU SmartShift information via sysfs diff --git a/Documentation/gpu/drm-internals.rst b/Documentation/gpu/drm-internals.rst index 06af044c882f..607f78f0f189 100644 --- a/Documentation/gpu/drm-internals.rst +++ b/Documentation/gpu/drm-internals.rst @@ -111,15 +111,6 @@ Component Helper Usage .. kernel-doc:: drivers/gpu/drm/drm_drv.c :doc: component helper usage recommendations -IRQ Helper Library -~~~~~~~~~~~~~~~~~~ - -.. kernel-doc:: drivers/gpu/drm/drm_irq.c - :doc: irq helpers - -.. kernel-doc:: drivers/gpu/drm/drm_irq.c - :export: - Memory Manager Initialization ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/hwmon/k10temp.rst b/Documentation/hwmon/k10temp.rst index 8557e26281c3..91b99adc6c48 100644 --- a/Documentation/hwmon/k10temp.rst +++ b/Documentation/hwmon/k10temp.rst @@ -132,20 +132,3 @@ On Family 17h and Family 18h CPUs, additional temperature sensors may report Core Complex Die (CCD) temperatures. Up to 8 such temperatures are reported as temp{3..10}_input, labeled Tccd{1..8}. Actual support depends on the CPU variant. - -Various Family 17h and 18h CPUs report voltage and current telemetry -information. The following attributes may be reported. - -Attribute Label Description -=============== ======= ================ -in0_input Vcore Core voltage -in1_input Vsoc SoC voltage -curr1_input Icore Core current -curr2_input Isoc SoC current -=============== ======= ================ - -Current values are raw (unscaled) as reported by the CPU. Core current is -reported as multiples of 1A / LSB. SoC is reported as multiples of 0.25A -/ LSB. The real current is board specific. Reported currents should be seen -as rough guidance, and should be scaled using sensors3.conf as appropriate -for a given board. diff --git a/MAINTAINERS b/MAINTAINERS index 76e0fdcdd877..703aa3150a15 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -414,7 +414,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm F: drivers/acpi/pmic/ ACPI THERMAL DRIVER -M: Zhang Rui <rui.zhang@intel.com> +M: Rafael J. Wysocki <rafael@kernel.org> +R: Zhang Rui <rui.zhang@intel.com> L: linux-acpi@vger.kernel.org S: Supported W: https://01.org/linux-acpi @@ -1275,6 +1276,7 @@ F: drivers/input/mouse/bcm5974.c APPLE DART IOMMU DRIVER M: Sven Peter <sven@svenpeter.dev> +R: Alyssa Rosenzweig <alyssa@rosenzweig.io> L: iommu@lists.linux-foundation.org S: Maintained F: Documentation/devicetree/bindings/iommu/apple,dart.yaml @@ -1711,6 +1713,8 @@ F: drivers/*/*alpine* ARM/APPLE MACHINE SUPPORT M: Hector Martin <marcan@marcan.st> +M: Sven Peter <sven@svenpeter.dev> +R: Alyssa Rosenzweig <alyssa@rosenzweig.io> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained W: https://asahilinux.org @@ -2236,6 +2240,7 @@ F: arch/arm/mach-pxa/mioa701.c ARM/MStar/Sigmastar Armv7 SoC support M: Daniel Palmer <daniel@thingy.jp> +M: Romain Perier <romain.perier@gmail.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained W: http://linux-chenxing.org/ @@ -2712,6 +2717,7 @@ F: drivers/power/reset/keystone-reset.c ARM/TEXAS INSTRUMENTS K3 ARCHITECTURE M: Nishanth Menon <nm@ti.com> +M: Vignesh Raghavendra <vigneshr@ti.com> M: Tero Kristo <kristo@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported @@ -4656,7 +4662,7 @@ W: http://linux-cifs.samba.org/ T: git git://git.samba.org/sfrench/cifs-2.6.git F: Documentation/admin-guide/cifs/ F: fs/cifs/ -F: fs/cifs_common/ +F: fs/smbfs_common/ COMPACTPCI HOTPLUG CORE M: Scott Murray <scott@spiteful.org> @@ -7434,7 +7440,7 @@ FREESCALE IMX / MXC FEC DRIVER M: Joakim Zhang <qiangqing.zhang@nxp.com> L: netdev@vger.kernel.org S: Maintained -F: Documentation/devicetree/bindings/net/fsl-fec.txt +F: Documentation/devicetree/bindings/net/fsl,fec.yaml F: drivers/net/ethernet/freescale/fec.h F: drivers/net/ethernet/freescale/fec_main.c F: drivers/net/ethernet/freescale/fec_ptp.c @@ -8608,9 +8614,8 @@ F: Documentation/devicetree/bindings/iio/humidity/st,hts221.yaml F: drivers/iio/humidity/hts221* HUAWEI ETHERNET DRIVER -M: Bin Luo <luobin9@huawei.com> L: netdev@vger.kernel.org -S: Supported +S: Orphan F: Documentation/networking/device_drivers/ethernet/huawei/hinic.rst F: drivers/net/ethernet/huawei/hinic/ @@ -9302,7 +9307,7 @@ S: Maintained F: drivers/platform/x86/intel/atomisp2/led.c INTEL BIOS SAR INT1092 DRIVER -M: Shravan S <s.shravan@intel.com> +M: Shravan Sudhakar <s.shravan@intel.com> M: Intel Corporation <linuxwwan@intel.com> L: platform-driver-x86@vger.kernel.org S: Maintained @@ -9624,7 +9629,7 @@ F: include/uapi/linux/isst_if.h F: tools/power/x86/intel-speed-select/ INTEL STRATIX10 FIRMWARE DRIVERS -M: Richard Gong <richard.gong@linux.intel.com> +M: Dinh Nguyen <dinguyen@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/ABI/testing/sysfs-devices-platform-stratix10-rsu @@ -10194,8 +10199,8 @@ M: Hyunchul Lee <hyc.lee@gmail.com> L: linux-cifs@vger.kernel.org S: Maintained T: git git://git.samba.org/ksmbd.git -F: fs/cifs_common/ F: fs/ksmbd/ +F: fs/smbfs_common/ KERNEL UNIT TESTING FRAMEWORK (KUnit) M: Brendan Higgins <brendanhiggins@google.com> @@ -11148,6 +11153,7 @@ S: Maintained F: Documentation/devicetree/bindings/net/dsa/marvell.txt F: Documentation/networking/devlink/mv88e6xxx.rst F: drivers/net/dsa/mv88e6xxx/ +F: include/linux/dsa/mv88e6xxx.h F: include/linux/platform_data/mv88e6xxx.h MARVELL ARMADA 3700 PHY DRIVERS @@ -17793,7 +17799,6 @@ F: drivers/staging/nvec/ STAGING - OLPC SECONDARY DISPLAY CONTROLLER (DCON) M: Jens Frederich <jfrederich@gmail.com> -M: Daniel Drake <dsd@laptop.org> M: Jon Nettleton <jon.nettleton@gmail.com> S: Maintained W: http://wiki.laptop.org/go/DCON @@ -18549,13 +18554,14 @@ T: git git://linuxtv.org/media_tree.git F: drivers/media/radio/radio-raremono.c THERMAL -M: Zhang Rui <rui.zhang@intel.com> +M: Rafael J. Wysocki <rafael@kernel.org> M: Daniel Lezcano <daniel.lezcano@linaro.org> R: Amit Kucheria <amitk@kernel.org> +R: Zhang Rui <rui.zhang@intel.com> L: linux-pm@vger.kernel.org S: Supported Q: https://patchwork.kernel.org/project/linux-pm/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/thermal/linux.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git thermal F: Documentation/devicetree/bindings/thermal/ F: drivers/thermal/ F: include/linux/cpu_cooling.h @@ -20698,7 +20704,6 @@ S: Maintained F: mm/zbud.c ZD1211RW WIRELESS DRIVER -M: Daniel Drake <dsd@gentoo.org> M: Ulrich Kunitz <kune@deine-taler.de> L: linux-wireless@vger.kernel.org L: zd1211-devs@lists.sourceforge.net (subscribers-only) @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc5 NAME = Opossums on Parade # *DOCUMENTATION* diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index fc196421b2ce..59baf6c132a7 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1989,8 +1989,6 @@ config ARCH_HIBERNATION_POSSIBLE endmenu -source "drivers/firmware/Kconfig" - if CRYPTO source "arch/arm/crypto/Kconfig" endif diff --git a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts index 614999dcb990..cd4672501add 100644 --- a/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts +++ b/arch/arm/boot/dts/at91-sama5d27_som1_ek.dts @@ -71,7 +71,6 @@ isc: isc@f0008000 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_isc_base &pinctrl_isc_data_8bit &pinctrl_isc_data_9_10 &pinctrl_isc_data_11_12>; - status = "okay"; }; qspi1: spi@f0024000 { diff --git a/arch/arm/boot/dts/at91-sama7g5ek.dts b/arch/arm/boot/dts/at91-sama7g5ek.dts index 4cbed98cc2f4..f3d6aaa3a78d 100644 --- a/arch/arm/boot/dts/at91-sama7g5ek.dts +++ b/arch/arm/boot/dts/at91-sama7g5ek.dts @@ -196,11 +196,13 @@ regulator-state-standby { regulator-on-in-suspend; + regulator-suspend-microvolt = <1350000>; regulator-mode = <4>; }; regulator-state-mem { regulator-on-in-suspend; + regulator-suspend-microvolt = <1350000>; regulator-mode = <4>; }; }; @@ -353,7 +355,10 @@ #address-cells = <1>; #size-cells = <0>; pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_gmac0_default &pinctrl_gmac0_txck_default &pinctrl_gmac0_phy_irq>; + pinctrl-0 = <&pinctrl_gmac0_default + &pinctrl_gmac0_mdio_default + &pinctrl_gmac0_txck_default + &pinctrl_gmac0_phy_irq>; phy-mode = "rgmii-id"; status = "okay"; @@ -368,7 +373,9 @@ #address-cells = <1>; #size-cells = <0>; pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_gmac1_default &pinctrl_gmac1_phy_irq>; + pinctrl-0 = <&pinctrl_gmac1_default + &pinctrl_gmac1_mdio_default + &pinctrl_gmac1_phy_irq>; phy-mode = "rmii"; status = "okay"; @@ -423,14 +430,20 @@ <PIN_PA15__G0_TXEN>, <PIN_PA30__G0_RXCK>, <PIN_PA18__G0_RXDV>, - <PIN_PA22__G0_MDC>, - <PIN_PA23__G0_MDIO>, <PIN_PA25__G0_125CK>; + slew-rate = <0>; + bias-disable; + }; + + pinctrl_gmac0_mdio_default: gmac0_mdio_default { + pinmux = <PIN_PA22__G0_MDC>, + <PIN_PA23__G0_MDIO>; bias-disable; }; pinctrl_gmac0_txck_default: gmac0_txck_default { pinmux = <PIN_PA24__G0_TXCK>; + slew-rate = <0>; bias-pull-up; }; @@ -447,8 +460,13 @@ <PIN_PD25__G1_RX0>, <PIN_PD26__G1_RX1>, <PIN_PD27__G1_RXER>, - <PIN_PD24__G1_RXDV>, - <PIN_PD28__G1_MDC>, + <PIN_PD24__G1_RXDV>; + slew-rate = <0>; + bias-disable; + }; + + pinctrl_gmac1_mdio_default: gmac1_mdio_default { + pinmux = <PIN_PD28__G1_MDC>, <PIN_PD29__G1_MDIO>; bias-disable; }; @@ -540,6 +558,7 @@ <PIN_PA8__SDMMC0_DAT5>, <PIN_PA9__SDMMC0_DAT6>, <PIN_PA10__SDMMC0_DAT7>; + slew-rate = <0>; bias-pull-up; }; @@ -547,6 +566,7 @@ pinmux = <PIN_PA0__SDMMC0_CK>, <PIN_PA2__SDMMC0_RSTN>, <PIN_PA11__SDMMC0_DS>; + slew-rate = <0>; bias-pull-up; }; }; @@ -558,6 +578,7 @@ <PIN_PC0__SDMMC1_DAT1>, <PIN_PC1__SDMMC1_DAT2>, <PIN_PC2__SDMMC1_DAT3>; + slew-rate = <0>; bias-pull-up; }; @@ -566,6 +587,7 @@ <PIN_PB28__SDMMC1_RSTN>, <PIN_PC5__SDMMC1_1V8SEL>, <PIN_PC4__SDMMC1_CD>; + slew-rate = <0>; bias-pull-up; }; }; @@ -577,11 +599,13 @@ <PIN_PD6__SDMMC2_DAT1>, <PIN_PD7__SDMMC2_DAT2>, <PIN_PD8__SDMMC2_DAT3>; + slew-rate = <0>; bias-pull-up; }; ck { pinmux = <PIN_PD4__SDMMC2_CK>; + slew-rate = <0>; bias-pull-up; }; }; @@ -634,6 +658,15 @@ pinctrl-0 = <&pinctrl_sdmmc2_default>; }; +&shdwc { + atmel,shdwc-debouncer = <976>; + status = "okay"; + + input@0 { + reg = <0>; + }; +}; + &spdifrx { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_spdifrx_default>; diff --git a/arch/arm/boot/dts/imx53-m53menlo.dts b/arch/arm/boot/dts/imx53-m53menlo.dts index d3082b9774e4..4f88e96d81dd 100644 --- a/arch/arm/boot/dts/imx53-m53menlo.dts +++ b/arch/arm/boot/dts/imx53-m53menlo.dts @@ -56,6 +56,7 @@ panel { compatible = "edt,etm0700g0dh6"; pinctrl-0 = <&pinctrl_display_gpio>; + pinctrl-names = "default"; enable-gpios = <&gpio6 0 GPIO_ACTIVE_HIGH>; port { @@ -76,8 +77,7 @@ regulator-name = "vbus"; regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; - gpio = <&gpio1 2 GPIO_ACTIVE_HIGH>; - enable-active-high; + gpio = <&gpio1 2 0>; }; }; diff --git a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi index cb8b539eb29d..e5c4dc65fbab 100644 --- a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi +++ b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi @@ -5,6 +5,7 @@ #include <dt-bindings/gpio/gpio.h> #include <dt-bindings/interrupt-controller/irq.h> #include <dt-bindings/input/input.h> +#include <dt-bindings/leds/common.h> #include <dt-bindings/pwm/pwm.h> / { @@ -277,6 +278,7 @@ led-cur = /bits/ 8 <0x20>; max-cur = /bits/ 8 <0x60>; reg = <0>; + color = <LED_COLOR_ID_RED>; }; chan@1 { @@ -284,6 +286,7 @@ led-cur = /bits/ 8 <0x20>; max-cur = /bits/ 8 <0x60>; reg = <1>; + color = <LED_COLOR_ID_GREEN>; }; chan@2 { @@ -291,6 +294,7 @@ led-cur = /bits/ 8 <0x20>; max-cur = /bits/ 8 <0x60>; reg = <2>; + color = <LED_COLOR_ID_BLUE>; }; chan@3 { @@ -298,6 +302,7 @@ led-cur = /bits/ 8 <0x0>; max-cur = /bits/ 8 <0x0>; reg = <3>; + color = <LED_COLOR_ID_WHITE>; }; }; diff --git a/arch/arm/boot/dts/imx6qdl-pico.dtsi b/arch/arm/boot/dts/imx6qdl-pico.dtsi index 5de4ccb97916..f7a56d6b160c 100644 --- a/arch/arm/boot/dts/imx6qdl-pico.dtsi +++ b/arch/arm/boot/dts/imx6qdl-pico.dtsi @@ -176,7 +176,18 @@ pinctrl-0 = <&pinctrl_enet>; phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 26 GPIO_ACTIVE_LOW>; + phy-handle = <&phy>; status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + phy: ethernet-phy@1 { + reg = <1>; + qca,clk-out-frequency = <125000000>; + }; + }; }; &hdmi { diff --git a/arch/arm/boot/dts/imx6sx-sdb.dts b/arch/arm/boot/dts/imx6sx-sdb.dts index 5a63ca615722..99f4cf777a38 100644 --- a/arch/arm/boot/dts/imx6sx-sdb.dts +++ b/arch/arm/boot/dts/imx6sx-sdb.dts @@ -114,7 +114,7 @@ compatible = "micron,n25q256a", "jedec,spi-nor"; spi-max-frequency = <29000000>; spi-rx-bus-width = <4>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; reg = <0>; }; @@ -124,7 +124,7 @@ compatible = "micron,n25q256a", "jedec,spi-nor"; spi-max-frequency = <29000000>; spi-rx-bus-width = <4>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; reg = <2>; }; }; diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi index 779cc536566d..a3fde3316c73 100644 --- a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi +++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi @@ -292,7 +292,7 @@ compatible = "micron,n25q256a", "jedec,spi-nor"; spi-max-frequency = <29000000>; spi-rx-bus-width = <4>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; reg = <0>; }; }; diff --git a/arch/arm/boot/dts/omap3430-sdp.dts b/arch/arm/boot/dts/omap3430-sdp.dts index c5b903718414..7d530ae3483b 100644 --- a/arch/arm/boot/dts/omap3430-sdp.dts +++ b/arch/arm/boot/dts/omap3430-sdp.dts @@ -101,7 +101,7 @@ nand@1,0 { compatible = "ti,omap2-nand"; - reg = <0 0 4>; /* CS0, offset 0, IO size 4 */ + reg = <1 0 4>; /* CS1, offset 0, IO size 4 */ interrupt-parent = <&gpmc>; interrupts = <0 IRQ_TYPE_NONE>, /* fifoevent */ <1 IRQ_TYPE_NONE>; /* termcount */ diff --git a/arch/arm/boot/dts/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom-apq8064.dtsi index 0b2bed6e7adf..d1c1c6aab2b8 100644 --- a/arch/arm/boot/dts/qcom-apq8064.dtsi +++ b/arch/arm/boot/dts/qcom-apq8064.dtsi @@ -198,7 +198,7 @@ clock-frequency = <19200000>; }; - pxo_board { + pxo_board: pxo_board { compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <27000000>; @@ -1148,22 +1148,21 @@ }; gpu: adreno-3xx@4300000 { - compatible = "qcom,adreno-3xx"; + compatible = "qcom,adreno-320.2", "qcom,adreno"; reg = <0x04300000 0x20000>; reg-names = "kgsl_3d0_reg_memory"; interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "kgsl_3d0_irq"; clock-names = - "core_clk", - "iface_clk", - "mem_clk", - "mem_iface_clk"; + "core", + "iface", + "mem", + "mem_iface"; clocks = <&mmcc GFX3D_CLK>, <&mmcc GFX3D_AHB_CLK>, <&mmcc GFX3D_AXI_CLK>, <&mmcc MMSS_IMEM_AHB_CLK>; - qcom,chipid = <0x03020002>; iommus = <&gfx3d 0 &gfx3d 1 @@ -1306,7 +1305,7 @@ reg-names = "dsi_pll", "dsi_phy", "dsi_phy_regulator"; clock-names = "iface_clk", "ref"; clocks = <&mmcc DSI_M_AHB_CLK>, - <&cxo_board>; + <&pxo_board>; }; diff --git a/arch/arm/boot/dts/sama7g5.dtsi b/arch/arm/boot/dts/sama7g5.dtsi index cc6be6db7b80..6c58c151c6d9 100644 --- a/arch/arm/boot/dts/sama7g5.dtsi +++ b/arch/arm/boot/dts/sama7g5.dtsi @@ -75,6 +75,17 @@ #size-cells = <1>; ranges; + securam: securam@e0000000 { + compatible = "microchip,sama7g5-securam", "atmel,sama5d2-securam", "mmio-sram"; + reg = <0xe0000000 0x4000>; + clocks = <&pmc PMC_TYPE_PERIPHERAL 18>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0xe0000000 0x4000>; + no-memory-wc; + status = "okay"; + }; + secumod: secumod@e0004000 { compatible = "microchip,sama7g5-secumod", "atmel,sama5d2-secumod", "syscon"; reg = <0xe0004000 0x4000>; @@ -111,6 +122,17 @@ clock-names = "td_slck", "md_slck", "main_xtal"; }; + shdwc: shdwc@e001d010 { + compatible = "microchip,sama7g5-shdwc", "syscon"; + reg = <0xe001d010 0x10>; + clocks = <&clk32k 0>; + #address-cells = <1>; + #size-cells = <0>; + atmel,wakeup-rtc-timer; + atmel,wakeup-rtt-timer; + status = "disabled"; + }; + rtt: rtt@e001d020 { compatible = "microchip,sama7g5-rtt", "microchip,sam9x60-rtt", "atmel,at91sam9260-rtt"; reg = <0xe001d020 0x30>; @@ -137,6 +159,11 @@ clocks = <&clk32k 0>; }; + chipid@e0020000 { + compatible = "microchip,sama7g5-chipid"; + reg = <0xe0020000 0x8>; + }; + sdmmc0: mmc@e1204000 { compatible = "microchip,sama7g5-sdhci", "microchip,sam9x60-sdhci"; reg = <0xe1204000 0x4000>; @@ -515,6 +542,18 @@ }; }; + uddrc: uddrc@e3800000 { + compatible = "microchip,sama7g5-uddrc"; + reg = <0xe3800000 0x4000>; + status = "okay"; + }; + + ddr3phy: ddr3phy@e3804000 { + compatible = "microchip,sama7g5-ddr3phy"; + reg = <0xe3804000 0x1000>; + status = "okay"; + }; + gic: interrupt-controller@e8c11000 { compatible = "arm,cortex-a7-gic"; #interrupt-cells = <3>; diff --git a/arch/arm/boot/dts/spear3xx.dtsi b/arch/arm/boot/dts/spear3xx.dtsi index f266b7b03482..cc88ebe7a60c 100644 --- a/arch/arm/boot/dts/spear3xx.dtsi +++ b/arch/arm/boot/dts/spear3xx.dtsi @@ -47,7 +47,7 @@ }; gmac: eth@e0800000 { - compatible = "st,spear600-gmac"; + compatible = "snps,dwmac-3.40a"; reg = <0xe0800000 0x8000>; interrupts = <23 22>; interrupt-names = "macirq", "eth_wake_irq"; diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi index 2ad9fd7c94ec..8af4b77fe655 100644 --- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi +++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi @@ -17,6 +17,7 @@ * TAKE CARE WHEN MAINTAINING THIS FILE TO PROPAGATE ANY RELEVANT * CHANGES TO vexpress-v2m.dtsi! */ +#include <dt-bindings/interrupt-controller/arm-gic.h> / { v2m_fixed_3v3: fixed-regulator-0 { @@ -101,16 +102,68 @@ }; bus@8000000 { - motherboard-bus { - model = "V2M-P1"; + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 63>; + interrupt-map = <0 0 &gic GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>, + <0 1 &gic GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>, + <0 2 &gic GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>, + <0 3 &gic GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>, + <0 4 &gic GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>, + <0 5 &gic GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>, + <0 6 &gic GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>, + <0 7 &gic GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>, + <0 8 &gic GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>, + <0 9 &gic GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>, + <0 10 &gic GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>, + <0 11 &gic GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>, + <0 12 &gic GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>, + <0 13 &gic GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>, + <0 14 &gic GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>, + <0 15 &gic GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>, + <0 16 &gic GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>, + <0 17 &gic GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>, + <0 18 &gic GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>, + <0 19 &gic GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>, + <0 20 &gic GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>, + <0 21 &gic GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>, + <0 22 &gic GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>, + <0 23 &gic GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>, + <0 24 &gic GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>, + <0 25 &gic GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>, + <0 26 &gic GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>, + <0 27 &gic GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>, + <0 28 &gic GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>, + <0 29 &gic GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>, + <0 30 &gic GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>, + <0 31 &gic GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>, + <0 32 &gic GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>, + <0 33 &gic GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>, + <0 34 &gic GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>, + <0 35 &gic GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>, + <0 36 &gic GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>, + <0 37 &gic GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>, + <0 38 &gic GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>, + <0 39 &gic GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>, + <0 40 &gic GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>, + <0 41 &gic GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>, + <0 42 &gic GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>; + + motherboard-bus@8000000 { arm,hbi = <0x190>; arm,vexpress,site = <0>; - arm,v2m-memory-map = "rs1"; compatible = "arm,vexpress,v2m-p1", "simple-bus"; #address-cells = <2>; /* SMB chipselect number and offset */ #size-cells = <1>; - #interrupt-cells = <1>; - ranges; + ranges = <0 0 0x08000000 0x04000000>, + <1 0 0x14000000 0x04000000>, + <2 0 0x18000000 0x04000000>, + <3 0 0x1c000000 0x04000000>, + <4 0 0x0c000000 0x04000000>, + <5 0 0x10000000 0x04000000>; nor_flash: flash@0 { compatible = "arm,vexpress-flash", "cfi-flash"; @@ -215,7 +268,7 @@ clock-names = "apb_pclk"; }; - mmci@50000 { + mmc@50000 { compatible = "arm,pl180", "arm,primecell"; reg = <0x050000 0x1000>; interrupts = <9>, <10>; @@ -275,7 +328,7 @@ clock-names = "uartclk", "apb_pclk"; }; - wdt@f0000 { + watchdog@f0000 { compatible = "arm,sp805", "arm,primecell"; reg = <0x0f0000 0x1000>; interrupts = <0>; diff --git a/arch/arm/boot/dts/vexpress-v2m.dtsi b/arch/arm/boot/dts/vexpress-v2m.dtsi index ec13ceb9ed36..f434fe5cf4a1 100644 --- a/arch/arm/boot/dts/vexpress-v2m.dtsi +++ b/arch/arm/boot/dts/vexpress-v2m.dtsi @@ -17,18 +17,73 @@ * TAKE CARE WHEN MAINTAINING THIS FILE TO PROPAGATE ANY RELEVANT * CHANGES TO vexpress-v2m-rs1.dtsi! */ +#include <dt-bindings/interrupt-controller/arm-gic.h> / { - bus@4000000 { - motherboard { - model = "V2M-P1"; + bus@40000000 { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x40000000 0x40000000 0x10000000>, + <0x10000000 0x10000000 0x00020000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 63>; + interrupt-map = <0 0 &gic GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>, + <0 1 &gic GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>, + <0 2 &gic GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>, + <0 3 &gic GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>, + <0 4 &gic GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>, + <0 5 &gic GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>, + <0 6 &gic GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>, + <0 7 &gic GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>, + <0 8 &gic GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>, + <0 9 &gic GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>, + <0 10 &gic GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>, + <0 11 &gic GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>, + <0 12 &gic GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>, + <0 13 &gic GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>, + <0 14 &gic GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>, + <0 15 &gic GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>, + <0 16 &gic GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>, + <0 17 &gic GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>, + <0 18 &gic GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>, + <0 19 &gic GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>, + <0 20 &gic GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>, + <0 21 &gic GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>, + <0 22 &gic GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>, + <0 23 &gic GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>, + <0 24 &gic GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>, + <0 25 &gic GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>, + <0 26 &gic GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>, + <0 27 &gic GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>, + <0 28 &gic GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>, + <0 29 &gic GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>, + <0 30 &gic GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>, + <0 31 &gic GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>, + <0 32 &gic GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>, + <0 33 &gic GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>, + <0 34 &gic GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>, + <0 35 &gic GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>, + <0 36 &gic GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>, + <0 37 &gic GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>, + <0 38 &gic GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>, + <0 39 &gic GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>, + <0 40 &gic GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>, + <0 41 &gic GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>, + <0 42 &gic GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>; + + motherboard-bus@40000000 { arm,hbi = <0x190>; arm,vexpress,site = <0>; compatible = "arm,vexpress,v2m-p1", "simple-bus"; #address-cells = <2>; /* SMB chipselect number and offset */ #size-cells = <1>; - #interrupt-cells = <1>; - ranges; + ranges = <0 0 0x40000000 0x04000000>, + <1 0 0x44000000 0x04000000>, + <2 0 0x48000000 0x04000000>, + <3 0 0x4c000000 0x04000000>, + <7 0 0x10000000 0x00020000>; flash@0,00000000 { compatible = "arm,vexpress-flash", "cfi-flash"; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts index e63c5c0bfb43..679537e17ff5 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts @@ -237,62 +237,7 @@ }; bus@8000000 { - compatible = "simple-bus"; - - #address-cells = <2>; - #size-cells = <1>; - ranges = <0 0 0 0x08000000 0x04000000>, - <1 0 0 0x14000000 0x04000000>, - <2 0 0 0x18000000 0x04000000>, - <3 0 0 0x1c000000 0x04000000>, - <4 0 0 0x0c000000 0x04000000>, - <5 0 0 0x10000000 0x04000000>; - - #interrupt-cells = <1>; - interrupt-map-mask = <0 0 63>; - interrupt-map = <0 0 0 &gic 0 0 4>, - <0 0 1 &gic 0 1 4>, - <0 0 2 &gic 0 2 4>, - <0 0 3 &gic 0 3 4>, - <0 0 4 &gic 0 4 4>, - <0 0 5 &gic 0 5 4>, - <0 0 6 &gic 0 6 4>, - <0 0 7 &gic 0 7 4>, - <0 0 8 &gic 0 8 4>, - <0 0 9 &gic 0 9 4>, - <0 0 10 &gic 0 10 4>, - <0 0 11 &gic 0 11 4>, - <0 0 12 &gic 0 12 4>, - <0 0 13 &gic 0 13 4>, - <0 0 14 &gic 0 14 4>, - <0 0 15 &gic 0 15 4>, - <0 0 16 &gic 0 16 4>, - <0 0 17 &gic 0 17 4>, - <0 0 18 &gic 0 18 4>, - <0 0 19 &gic 0 19 4>, - <0 0 20 &gic 0 20 4>, - <0 0 21 &gic 0 21 4>, - <0 0 22 &gic 0 22 4>, - <0 0 23 &gic 0 23 4>, - <0 0 24 &gic 0 24 4>, - <0 0 25 &gic 0 25 4>, - <0 0 26 &gic 0 26 4>, - <0 0 27 &gic 0 27 4>, - <0 0 28 &gic 0 28 4>, - <0 0 29 &gic 0 29 4>, - <0 0 30 &gic 0 30 4>, - <0 0 31 &gic 0 31 4>, - <0 0 32 &gic 0 32 4>, - <0 0 33 &gic 0 33 4>, - <0 0 34 &gic 0 34 4>, - <0 0 35 &gic 0 35 4>, - <0 0 36 &gic 0 36 4>, - <0 0 37 &gic 0 37 4>, - <0 0 38 &gic 0 38 4>, - <0 0 39 &gic 0 39 4>, - <0 0 40 &gic 0 40 4>, - <0 0 41 &gic 0 41 4>, - <0 0 42 &gic 0 42 4>; + ranges = <0x8000000 0 0x8000000 0x18000000>; }; site2: hsb@40000000 { diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts index 012d40a7228c..511e87cc2bc5 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts @@ -609,62 +609,7 @@ }; smb: bus@8000000 { - compatible = "simple-bus"; - - #address-cells = <2>; - #size-cells = <1>; - ranges = <0 0 0 0x08000000 0x04000000>, - <1 0 0 0x14000000 0x04000000>, - <2 0 0 0x18000000 0x04000000>, - <3 0 0 0x1c000000 0x04000000>, - <4 0 0 0x0c000000 0x04000000>, - <5 0 0 0x10000000 0x04000000>; - - #interrupt-cells = <1>; - interrupt-map-mask = <0 0 63>; - interrupt-map = <0 0 0 &gic 0 0 4>, - <0 0 1 &gic 0 1 4>, - <0 0 2 &gic 0 2 4>, - <0 0 3 &gic 0 3 4>, - <0 0 4 &gic 0 4 4>, - <0 0 5 &gic 0 5 4>, - <0 0 6 &gic 0 6 4>, - <0 0 7 &gic 0 7 4>, - <0 0 8 &gic 0 8 4>, - <0 0 9 &gic 0 9 4>, - <0 0 10 &gic 0 10 4>, - <0 0 11 &gic 0 11 4>, - <0 0 12 &gic 0 12 4>, - <0 0 13 &gic 0 13 4>, - <0 0 14 &gic 0 14 4>, - <0 0 15 &gic 0 15 4>, - <0 0 16 &gic 0 16 4>, - <0 0 17 &gic 0 17 4>, - <0 0 18 &gic 0 18 4>, - <0 0 19 &gic 0 19 4>, - <0 0 20 &gic 0 20 4>, - <0 0 21 &gic 0 21 4>, - <0 0 22 &gic 0 22 4>, - <0 0 23 &gic 0 23 4>, - <0 0 24 &gic 0 24 4>, - <0 0 25 &gic 0 25 4>, - <0 0 26 &gic 0 26 4>, - <0 0 27 &gic 0 27 4>, - <0 0 28 &gic 0 28 4>, - <0 0 29 &gic 0 29 4>, - <0 0 30 &gic 0 30 4>, - <0 0 31 &gic 0 31 4>, - <0 0 32 &gic 0 32 4>, - <0 0 33 &gic 0 33 4>, - <0 0 34 &gic 0 34 4>, - <0 0 35 &gic 0 35 4>, - <0 0 36 &gic 0 36 4>, - <0 0 37 &gic 0 37 4>, - <0 0 38 &gic 0 38 4>, - <0 0 39 &gic 0 39 4>, - <0 0 40 &gic 0 40 4>, - <0 0 41 &gic 0 41 4>, - <0 0 42 &gic 0 42 4>; + ranges = <0x8000000 0 0x8000000 0x18000000>; }; site2: hsb@40000000 { diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts index 7aa64ae25779..3b88209bacea 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts @@ -207,62 +207,7 @@ }; smb: bus@8000000 { - compatible = "simple-bus"; - - #address-cells = <2>; - #size-cells = <1>; - ranges = <0 0 0x08000000 0x04000000>, - <1 0 0x14000000 0x04000000>, - <2 0 0x18000000 0x04000000>, - <3 0 0x1c000000 0x04000000>, - <4 0 0x0c000000 0x04000000>, - <5 0 0x10000000 0x04000000>; - - #interrupt-cells = <1>; - interrupt-map-mask = <0 0 63>; - interrupt-map = <0 0 0 &gic 0 0 4>, - <0 0 1 &gic 0 1 4>, - <0 0 2 &gic 0 2 4>, - <0 0 3 &gic 0 3 4>, - <0 0 4 &gic 0 4 4>, - <0 0 5 &gic 0 5 4>, - <0 0 6 &gic 0 6 4>, - <0 0 7 &gic 0 7 4>, - <0 0 8 &gic 0 8 4>, - <0 0 9 &gic 0 9 4>, - <0 0 10 &gic 0 10 4>, - <0 0 11 &gic 0 11 4>, - <0 0 12 &gic 0 12 4>, - <0 0 13 &gic 0 13 4>, - <0 0 14 &gic 0 14 4>, - <0 0 15 &gic 0 15 4>, - <0 0 16 &gic 0 16 4>, - <0 0 17 &gic 0 17 4>, - <0 0 18 &gic 0 18 4>, - <0 0 19 &gic 0 19 4>, - <0 0 20 &gic 0 20 4>, - <0 0 21 &gic 0 21 4>, - <0 0 22 &gic 0 22 4>, - <0 0 23 &gic 0 23 4>, - <0 0 24 &gic 0 24 4>, - <0 0 25 &gic 0 25 4>, - <0 0 26 &gic 0 26 4>, - <0 0 27 &gic 0 27 4>, - <0 0 28 &gic 0 28 4>, - <0 0 29 &gic 0 29 4>, - <0 0 30 &gic 0 30 4>, - <0 0 31 &gic 0 31 4>, - <0 0 32 &gic 0 32 4>, - <0 0 33 &gic 0 33 4>, - <0 0 34 &gic 0 34 4>, - <0 0 35 &gic 0 35 4>, - <0 0 36 &gic 0 36 4>, - <0 0 37 &gic 0 37 4>, - <0 0 38 &gic 0 38 4>, - <0 0 39 &gic 0 39 4>, - <0 0 40 &gic 0 40 4>, - <0 0 41 &gic 0 41 4>, - <0 0 42 &gic 0 42 4>; + ranges = <0 0x8000000 0x18000000>; }; site2: hsb@40000000 { diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts index 4c5847955856..5916e4877eac 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts @@ -295,64 +295,6 @@ }; }; - smb: bus@4000000 { - compatible = "simple-bus"; - - #address-cells = <2>; - #size-cells = <1>; - ranges = <0 0 0x40000000 0x04000000>, - <1 0 0x44000000 0x04000000>, - <2 0 0x48000000 0x04000000>, - <3 0 0x4c000000 0x04000000>, - <7 0 0x10000000 0x00020000>; - - #interrupt-cells = <1>; - interrupt-map-mask = <0 0 63>; - interrupt-map = <0 0 0 &gic 0 0 4>, - <0 0 1 &gic 0 1 4>, - <0 0 2 &gic 0 2 4>, - <0 0 3 &gic 0 3 4>, - <0 0 4 &gic 0 4 4>, - <0 0 5 &gic 0 5 4>, - <0 0 6 &gic 0 6 4>, - <0 0 7 &gic 0 7 4>, - <0 0 8 &gic 0 8 4>, - <0 0 9 &gic 0 9 4>, - <0 0 10 &gic 0 10 4>, - <0 0 11 &gic 0 11 4>, - <0 0 12 &gic 0 12 4>, - <0 0 13 &gic 0 13 4>, - <0 0 14 &gic 0 14 4>, - <0 0 15 &gic 0 15 4>, - <0 0 16 &gic 0 16 4>, - <0 0 17 &gic 0 17 4>, - <0 0 18 &gic 0 18 4>, - <0 0 19 &gic 0 19 4>, - <0 0 20 &gic 0 20 4>, - <0 0 21 &gic 0 21 4>, - <0 0 22 &gic 0 22 4>, - <0 0 23 &gic 0 23 4>, - <0 0 24 &gic 0 24 4>, - <0 0 25 &gic 0 25 4>, - <0 0 26 &gic 0 26 4>, - <0 0 27 &gic 0 27 4>, - <0 0 28 &gic 0 28 4>, - <0 0 29 &gic 0 29 4>, - <0 0 30 &gic 0 30 4>, - <0 0 31 &gic 0 31 4>, - <0 0 32 &gic 0 32 4>, - <0 0 33 &gic 0 33 4>, - <0 0 34 &gic 0 34 4>, - <0 0 35 &gic 0 35 4>, - <0 0 36 &gic 0 36 4>, - <0 0 37 &gic 0 37 4>, - <0 0 38 &gic 0 38 4>, - <0 0 39 &gic 0 39 4>, - <0 0 40 &gic 0 40 4>, - <0 0 41 &gic 0 41 4>, - <0 0 42 &gic 0 42 4>; - }; - site2: hsb@e0000000 { compatible = "simple-bus"; #address-cells = <1>; diff --git a/arch/arm/common/sharpsl_param.c b/arch/arm/common/sharpsl_param.c index efeb5724d9e9..6237ede2f0c7 100644 --- a/arch/arm/common/sharpsl_param.c +++ b/arch/arm/common/sharpsl_param.c @@ -40,7 +40,9 @@ EXPORT_SYMBOL(sharpsl_param); void sharpsl_save_param(void) { - memcpy(&sharpsl_param, param_start(PARAM_BASE), sizeof(struct sharpsl_param_info)); + struct sharpsl_param_info *params = param_start(PARAM_BASE); + + memcpy(&sharpsl_param, params, sizeof(*params)); if (sharpsl_param.comadj_keyword != COMADJ_MAGIC) sharpsl_param.comadj=-1; diff --git a/arch/arm/configs/gemini_defconfig b/arch/arm/configs/gemini_defconfig index d2d5f1cf815f..e6ff844821cf 100644 --- a/arch/arm/configs/gemini_defconfig +++ b/arch/arm/configs/gemini_defconfig @@ -76,6 +76,7 @@ CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_DRM=y CONFIG_DRM_PANEL_ILITEK_IL9322=y CONFIG_DRM_TVE200=y +CONFIG_FB=y CONFIG_LOGO=y CONFIG_USB=y CONFIG_USB_MON=y diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index ccee86d0045d..5e4128dadd8d 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -292,6 +292,7 @@ CONFIG_DRM_IMX_LDB=y CONFIG_DRM_IMX_HDMI=y CONFIG_DRM_ETNAVIV=y CONFIG_DRM_MXSFB=y +CONFIG_FB=y CONFIG_FB_MODE_HELPERS=y CONFIG_LCD_CLASS_DEVICE=y CONFIG_LCD_L4F00242T03=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index ba67c4717dcc..b4f74454f20f 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -456,6 +456,7 @@ CONFIG_PINCTRL_STMFX=y CONFIG_PINCTRL_PALMAS=y CONFIG_PINCTRL_OWL=y CONFIG_PINCTRL_S500=y +CONFIG_PINCTRL_MSM=y CONFIG_PINCTRL_APQ8064=y CONFIG_PINCTRL_APQ8084=y CONFIG_PINCTRL_IPQ8064=y @@ -725,6 +726,7 @@ CONFIG_DRM_PL111=m CONFIG_DRM_LIMA=m CONFIG_DRM_PANFROST=m CONFIG_DRM_ASPEED_GFX=m +CONFIG_FB=y CONFIG_FB_EFI=y CONFIG_FB_WM8505=y CONFIG_FB_SH_MOBILE_LCDC=y @@ -1122,6 +1124,7 @@ CONFIG_PHY_DM816X_USB=m CONFIG_OMAP_USB2=y CONFIG_TI_PIPE3=y CONFIG_TWL4030_USB=m +CONFIG_RAS=y CONFIG_NVMEM_IMX_OCOTP=y CONFIG_ROCKCHIP_EFUSE=m CONFIG_NVMEM_SUNXI_SID=y diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index d6cfe7c4bb00..8711d6824c1f 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -47,12 +47,26 @@ struct at91_pm_bu { unsigned long ddr_phy_calibration[BACKUP_DDR_PHY_CALIBRATION]; }; +/* + * struct at91_pm_sfrbu_offsets: registers mapping for SFRBU + * @pswbu: power switch BU control registers + */ +struct at91_pm_sfrbu_regs { + struct { + u32 key; + u32 ctrl; + u32 state; + u32 softsw; + } pswbu; +}; + /** * struct at91_soc_pm - AT91 SoC power management data structure * @config_shdwc_ws: wakeup sources configuration function for SHDWC * @config_pmc_ws: wakeup srouces configuration function for PMC * @ws_ids: wakup sources of_device_id array * @data: PM data to be used on last phase of suspend + * @sfrbu_regs: SFRBU registers mapping * @bu: backup unit mapped data (for backup mode) * @memcs: memory chip select */ @@ -62,6 +76,7 @@ struct at91_soc_pm { const struct of_device_id *ws_ids; struct at91_pm_bu *bu; struct at91_pm_data data; + struct at91_pm_sfrbu_regs sfrbu_regs; void *memcs; }; @@ -356,9 +371,36 @@ static int at91_suspend_finish(unsigned long val) return 0; } +static void at91_pm_switch_ba_to_vbat(void) +{ + unsigned int offset = offsetof(struct at91_pm_sfrbu_regs, pswbu); + unsigned int val; + + /* Just for safety. */ + if (!soc_pm.data.sfrbu) + return; + + val = readl(soc_pm.data.sfrbu + offset); + + /* Already on VBAT. */ + if (!(val & soc_pm.sfrbu_regs.pswbu.state)) + return; + + val &= ~soc_pm.sfrbu_regs.pswbu.softsw; + val |= soc_pm.sfrbu_regs.pswbu.key | soc_pm.sfrbu_regs.pswbu.ctrl; + writel(val, soc_pm.data.sfrbu + offset); + + /* Wait for update. */ + val = readl(soc_pm.data.sfrbu + offset); + while (val & soc_pm.sfrbu_regs.pswbu.state) + val = readl(soc_pm.data.sfrbu + offset); +} + static void at91_pm_suspend(suspend_state_t state) { if (soc_pm.data.mode == AT91_PM_BACKUP) { + at91_pm_switch_ba_to_vbat(); + cpu_suspend(0, at91_suspend_finish); /* The SRAM is lost between suspend cycles */ @@ -589,18 +631,22 @@ static const struct of_device_id ramc_phy_ids[] __initconst = { { /* Sentinel. */ }, }; -static __init void at91_dt_ramc(bool phy_mandatory) +static __init int at91_dt_ramc(bool phy_mandatory) { struct device_node *np; const struct of_device_id *of_id; int idx = 0; void *standby = NULL; const struct ramc_info *ramc; + int ret; for_each_matching_node_and_match(np, ramc_ids, &of_id) { soc_pm.data.ramc[idx] = of_iomap(np, 0); - if (!soc_pm.data.ramc[idx]) - panic(pr_fmt("unable to map ramc[%d] cpu registers\n"), idx); + if (!soc_pm.data.ramc[idx]) { + pr_err("unable to map ramc[%d] cpu registers\n", idx); + ret = -ENOMEM; + goto unmap_ramc; + } ramc = of_id->data; if (ramc) { @@ -612,25 +658,42 @@ static __init void at91_dt_ramc(bool phy_mandatory) idx++; } - if (!idx) - panic(pr_fmt("unable to find compatible ram controller node in dtb\n")); + if (!idx) { + pr_err("unable to find compatible ram controller node in dtb\n"); + ret = -ENODEV; + goto unmap_ramc; + } /* Lookup for DDR PHY node, if any. */ for_each_matching_node_and_match(np, ramc_phy_ids, &of_id) { soc_pm.data.ramc_phy = of_iomap(np, 0); - if (!soc_pm.data.ramc_phy) - panic(pr_fmt("unable to map ramc phy cpu registers\n")); + if (!soc_pm.data.ramc_phy) { + pr_err("unable to map ramc phy cpu registers\n"); + ret = -ENOMEM; + goto unmap_ramc; + } } - if (phy_mandatory && !soc_pm.data.ramc_phy) - panic(pr_fmt("DDR PHY is mandatory!\n")); + if (phy_mandatory && !soc_pm.data.ramc_phy) { + pr_err("DDR PHY is mandatory!\n"); + ret = -ENODEV; + goto unmap_ramc; + } if (!standby) { pr_warn("ramc no standby function available\n"); - return; + return 0; } at91_cpuidle_device.dev.platform_data = standby; + + return 0; + +unmap_ramc: + while (idx) + iounmap(soc_pm.data.ramc[--idx]); + + return ret; } static void at91rm9200_idle(void) @@ -1017,6 +1080,8 @@ static void __init at91_pm_init(void (*pm_idle)(void)) void __init at91rm9200_pm_init(void) { + int ret; + if (!IS_ENABLED(CONFIG_SOC_AT91RM9200)) return; @@ -1028,7 +1093,9 @@ void __init at91rm9200_pm_init(void) soc_pm.data.standby_mode = AT91_PM_STANDBY; soc_pm.data.suspend_mode = AT91_PM_ULP0; - at91_dt_ramc(false); + ret = at91_dt_ramc(false); + if (ret) + return; /* * AT91RM9200 SDRAM low-power mode cannot be used with self-refresh. @@ -1046,13 +1113,17 @@ void __init sam9x60_pm_init(void) static const int iomaps[] __initconst = { [AT91_PM_ULP1] = AT91_PM_IOMAP(SHDWC), }; + int ret; if (!IS_ENABLED(CONFIG_SOC_SAM9X60)) return; at91_pm_modes_validate(modes, ARRAY_SIZE(modes)); at91_pm_modes_init(iomaps, ARRAY_SIZE(iomaps)); - at91_dt_ramc(false); + ret = at91_dt_ramc(false); + if (ret) + return; + at91_pm_init(NULL); soc_pm.ws_ids = sam9x60_ws_ids; @@ -1061,6 +1132,8 @@ void __init sam9x60_pm_init(void) void __init at91sam9_pm_init(void) { + int ret; + if (!IS_ENABLED(CONFIG_SOC_AT91SAM9)) return; @@ -1072,7 +1145,10 @@ void __init at91sam9_pm_init(void) soc_pm.data.standby_mode = AT91_PM_STANDBY; soc_pm.data.suspend_mode = AT91_PM_ULP0; - at91_dt_ramc(false); + ret = at91_dt_ramc(false); + if (ret) + return; + at91_pm_init(at91sam9_idle); } @@ -1081,12 +1157,16 @@ void __init sama5_pm_init(void) static const int modes[] __initconst = { AT91_PM_STANDBY, AT91_PM_ULP0, AT91_PM_ULP0_FAST, }; + int ret; if (!IS_ENABLED(CONFIG_SOC_SAMA5)) return; at91_pm_modes_validate(modes, ARRAY_SIZE(modes)); - at91_dt_ramc(false); + ret = at91_dt_ramc(false); + if (ret) + return; + at91_pm_init(NULL); } @@ -1101,18 +1181,27 @@ void __init sama5d2_pm_init(void) [AT91_PM_BACKUP] = AT91_PM_IOMAP(SHDWC) | AT91_PM_IOMAP(SFRBU), }; + int ret; if (!IS_ENABLED(CONFIG_SOC_SAMA5D2)) return; at91_pm_modes_validate(modes, ARRAY_SIZE(modes)); at91_pm_modes_init(iomaps, ARRAY_SIZE(iomaps)); - at91_dt_ramc(false); + ret = at91_dt_ramc(false); + if (ret) + return; + at91_pm_init(NULL); soc_pm.ws_ids = sama5d2_ws_ids; soc_pm.config_shdwc_ws = at91_sama5d2_config_shdwc_ws; soc_pm.config_pmc_ws = at91_sama5d2_config_pmc_ws; + + soc_pm.sfrbu_regs.pswbu.key = (0x4BD20C << 8); + soc_pm.sfrbu_regs.pswbu.ctrl = BIT(0); + soc_pm.sfrbu_regs.pswbu.softsw = BIT(1); + soc_pm.sfrbu_regs.pswbu.state = BIT(3); } void __init sama7_pm_init(void) @@ -1127,18 +1216,27 @@ void __init sama7_pm_init(void) [AT91_PM_BACKUP] = AT91_PM_IOMAP(SFRBU) | AT91_PM_IOMAP(SHDWC), }; + int ret; if (!IS_ENABLED(CONFIG_SOC_SAMA7)) return; at91_pm_modes_validate(modes, ARRAY_SIZE(modes)); - at91_dt_ramc(true); + ret = at91_dt_ramc(true); + if (ret) + return; + at91_pm_modes_init(iomaps, ARRAY_SIZE(iomaps)); at91_pm_init(NULL); soc_pm.ws_ids = sama7g5_ws_ids; soc_pm.config_pmc_ws = at91_sam9x60_config_pmc_ws; + + soc_pm.sfrbu_regs.pswbu.key = (0x4BD20C << 8); + soc_pm.sfrbu_regs.pswbu.ctrl = BIT(0); + soc_pm.sfrbu_regs.pswbu.softsw = BIT(1); + soc_pm.sfrbu_regs.pswbu.state = BIT(2); } static int __init at91_pm_modes_select(char *str) diff --git a/arch/arm/mach-at91/pm_suspend.S b/arch/arm/mach-at91/pm_suspend.S index cbd61a3bcab1..fdb4f63ecde4 100644 --- a/arch/arm/mach-at91/pm_suspend.S +++ b/arch/arm/mach-at91/pm_suspend.S @@ -1014,31 +1014,55 @@ ENTRY(at91_pm_suspend_in_sram) mov tmp1, #0 mcr p15, 0, tmp1, c7, c10, 4 + /* Flush tlb. */ + mov r4, #0 + mcr p15, 0, r4, c8, c7, 0 + + ldr tmp1, [r0, #PM_DATA_PMC_MCKR_OFFSET] + str tmp1, .mckr_offset + ldr tmp1, [r0, #PM_DATA_PMC_VERSION] + str tmp1, .pmc_version + ldr tmp1, [r0, #PM_DATA_MEMCTRL] + str tmp1, .memtype + ldr tmp1, [r0, #PM_DATA_MODE] + str tmp1, .pm_mode + + /* + * ldrne below are here to preload their address in the TLB as access + * to RAM may be limited while in self-refresh. + */ ldr tmp1, [r0, #PM_DATA_PMC] str tmp1, .pmc_base + cmp tmp1, #0 + ldrne tmp2, [tmp1, #0] + ldr tmp1, [r0, #PM_DATA_RAMC0] str tmp1, .sramc_base + cmp tmp1, #0 + ldrne tmp2, [tmp1, #0] + ldr tmp1, [r0, #PM_DATA_RAMC1] str tmp1, .sramc1_base + cmp tmp1, #0 + ldrne tmp2, [tmp1, #0] + +#ifndef CONFIG_SOC_SAM_V4_V5 + /* ldrne below are here to preload their address in the TLB */ ldr tmp1, [r0, #PM_DATA_RAMC_PHY] str tmp1, .sramc_phy_base - ldr tmp1, [r0, #PM_DATA_MEMCTRL] - str tmp1, .memtype - ldr tmp1, [r0, #PM_DATA_MODE] - str tmp1, .pm_mode - ldr tmp1, [r0, #PM_DATA_PMC_MCKR_OFFSET] - str tmp1, .mckr_offset - ldr tmp1, [r0, #PM_DATA_PMC_VERSION] - str tmp1, .pmc_version - /* Both ldrne below are here to preload their address in the TLB */ + cmp tmp1, #0 + ldrne tmp2, [tmp1, #0] + ldr tmp1, [r0, #PM_DATA_SHDWC] str tmp1, .shdwc cmp tmp1, #0 ldrne tmp2, [tmp1, #0] + ldr tmp1, [r0, #PM_DATA_SFRBU] str tmp1, .sfrbu cmp tmp1, #0 ldrne tmp2, [tmp1, #0x10] +#endif /* Active the self-refresh mode */ at91_sramc_self_refresh_ena diff --git a/arch/arm/mach-dove/include/mach/uncompress.h b/arch/arm/mach-dove/include/mach/uncompress.h index 7a4bd8838036..ddf873f35e2b 100644 --- a/arch/arm/mach-dove/include/mach/uncompress.h +++ b/arch/arm/mach-dove/include/mach/uncompress.h @@ -11,7 +11,7 @@ #define LSR_THRE 0x20 -static void putc(const char c) +static inline void putc(const char c) { int i; @@ -24,7 +24,7 @@ static void putc(const char c) *UART_THR = c; } -static void flush(void) +static inline void flush(void) { } diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c index 11dcc369ec14..c9d7c29d95e1 100644 --- a/arch/arm/mach-imx/mach-imx6q.c +++ b/arch/arm/mach-imx/mach-imx6q.c @@ -172,6 +172,9 @@ static void __init imx6q_init_machine(void) imx_get_soc_revision()); imx6q_enet_phy_init(); + + of_platform_default_populate(NULL, NULL, NULL); + imx_anatop_init(); cpu_is_imx6q() ? imx6q_pm_init() : imx6dl_pm_init(); imx6q_1588_init(); diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c index 9244437cb1b9..f2ecca339910 100644 --- a/arch/arm/mach-imx/pm-imx6.c +++ b/arch/arm/mach-imx/pm-imx6.c @@ -10,6 +10,7 @@ #include <linux/io.h> #include <linux/irq.h> #include <linux/genalloc.h> +#include <linux/irqchip/arm-gic.h> #include <linux/mfd/syscon.h> #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h> #include <linux/of.h> @@ -619,6 +620,7 @@ static void __init imx6_pm_common_init(const struct imx6_pm_socdata static void imx6_pm_stby_poweroff(void) { + gic_cpu_if_down(0); imx6_set_lpm(STOP_POWER_OFF); imx6q_suspend_finish(0); diff --git a/arch/arm/mach-omap1/include/mach/memory.h b/arch/arm/mach-omap1/include/mach/memory.h index 36bc0000cb6a..ba3a350479c8 100644 --- a/arch/arm/mach-omap1/include/mach/memory.h +++ b/arch/arm/mach-omap1/include/mach/memory.h @@ -9,16 +9,4 @@ /* REVISIT: omap1 legacy drivers still rely on this */ #include <mach/soc.h> -/* - * Bus address is physical address, except for OMAP-1510 Local Bus. - * OMAP-1510 bus address is translated into a Local Bus address if the - * OMAP bus type is lbus. We do the address translation based on the - * device overriding the defaults used in the dma-mapping API. - */ - -/* - * OMAP-1510 Local Bus address offset - */ -#define OMAP1510_LB_OFFSET UL(0x30000000) - #endif diff --git a/arch/arm/mach-omap1/usb.c b/arch/arm/mach-omap1/usb.c index 86d3b3c157af..e60831c82b78 100644 --- a/arch/arm/mach-omap1/usb.c +++ b/arch/arm/mach-omap1/usb.c @@ -11,6 +11,7 @@ #include <linux/platform_device.h> #include <linux/dma-map-ops.h> #include <linux/io.h> +#include <linux/delay.h> #include <asm/irq.h> @@ -206,8 +207,6 @@ static inline void udc_device_init(struct omap_usb_config *pdata) #endif -#if IS_ENABLED(CONFIG_USB_OHCI_HCD) - /* The dmamask must be set for OHCI to work */ static u64 ohci_dmamask = ~(u32)0; @@ -236,20 +235,15 @@ static struct platform_device ohci_device = { static inline void ohci_device_init(struct omap_usb_config *pdata) { + if (!IS_ENABLED(CONFIG_USB_OHCI_HCD)) + return; + if (cpu_is_omap7xx()) ohci_resources[1].start = INT_7XX_USB_HHC_1; pdata->ohci_device = &ohci_device; pdata->ocpi_enable = &ocpi_enable; } -#else - -static inline void ohci_device_init(struct omap_usb_config *pdata) -{ -} - -#endif - #if defined(CONFIG_USB_OTG) && defined(CONFIG_ARCH_OMAP_OTG) static struct resource otg_resources[] = { @@ -534,33 +528,87 @@ bad: } #ifdef CONFIG_ARCH_OMAP15XX +/* OMAP-1510 OHCI has its own MMU for DMA */ +#define OMAP1510_LB_MEMSIZE 32 /* Should be same as SDRAM size */ +#define OMAP1510_LB_CLOCK_DIV 0xfffec10c +#define OMAP1510_LB_MMU_CTL 0xfffec208 +#define OMAP1510_LB_MMU_LCK 0xfffec224 +#define OMAP1510_LB_MMU_LD_TLB 0xfffec228 +#define OMAP1510_LB_MMU_CAM_H 0xfffec22c +#define OMAP1510_LB_MMU_CAM_L 0xfffec230 +#define OMAP1510_LB_MMU_RAM_H 0xfffec234 +#define OMAP1510_LB_MMU_RAM_L 0xfffec238 -/* ULPD_DPLL_CTRL */ -#define DPLL_IOB (1 << 13) -#define DPLL_PLL_ENABLE (1 << 4) -#define DPLL_LOCK (1 << 0) +/* + * Bus address is physical address, except for OMAP-1510 Local Bus. + * OMAP-1510 bus address is translated into a Local Bus address if the + * OMAP bus type is lbus. + */ +#define OMAP1510_LB_OFFSET UL(0x30000000) -/* ULPD_APLL_CTRL */ -#define APLL_NDPLL_SWITCH (1 << 0) +/* + * OMAP-1510 specific Local Bus clock on/off + */ +static int omap_1510_local_bus_power(int on) +{ + if (on) { + omap_writel((1 << 1) | (1 << 0), OMAP1510_LB_MMU_CTL); + udelay(200); + } else { + omap_writel(0, OMAP1510_LB_MMU_CTL); + } -static int omap_1510_usb_ohci_notifier(struct notifier_block *nb, - unsigned long event, void *data) + return 0; +} + +/* + * OMAP-1510 specific Local Bus initialization + * NOTE: This assumes 32MB memory size in OMAP1510LB_MEMSIZE. + * See also arch/mach-omap/memory.h for __virt_to_dma() and + * __dma_to_virt() which need to match with the physical + * Local Bus address below. + */ +static int omap_1510_local_bus_init(void) { - struct device *dev = data; + unsigned int tlb; + unsigned long lbaddr, physaddr; + + omap_writel((omap_readl(OMAP1510_LB_CLOCK_DIV) & 0xfffffff8) | 0x4, + OMAP1510_LB_CLOCK_DIV); + + /* Configure the Local Bus MMU table */ + for (tlb = 0; tlb < OMAP1510_LB_MEMSIZE; tlb++) { + lbaddr = tlb * 0x00100000 + OMAP1510_LB_OFFSET; + physaddr = tlb * 0x00100000 + PHYS_OFFSET; + omap_writel((lbaddr & 0x0fffffff) >> 22, OMAP1510_LB_MMU_CAM_H); + omap_writel(((lbaddr & 0x003ffc00) >> 6) | 0xc, + OMAP1510_LB_MMU_CAM_L); + omap_writel(physaddr >> 16, OMAP1510_LB_MMU_RAM_H); + omap_writel((physaddr & 0x0000fc00) | 0x300, OMAP1510_LB_MMU_RAM_L); + omap_writel(tlb << 4, OMAP1510_LB_MMU_LCK); + omap_writel(0x1, OMAP1510_LB_MMU_LD_TLB); + } - if (event != BUS_NOTIFY_ADD_DEVICE) - return NOTIFY_DONE; + /* Enable the walking table */ + omap_writel(omap_readl(OMAP1510_LB_MMU_CTL) | (1 << 3), OMAP1510_LB_MMU_CTL); + udelay(200); - if (strncmp(dev_name(dev), "ohci", 4) == 0 && - dma_direct_set_offset(dev, PHYS_OFFSET, OMAP1510_LB_OFFSET, - (u64)-1)) - WARN_ONCE(1, "failed to set DMA offset\n"); - return NOTIFY_OK; + return 0; } -static struct notifier_block omap_1510_usb_ohci_nb = { - .notifier_call = omap_1510_usb_ohci_notifier, -}; +static void omap_1510_local_bus_reset(void) +{ + omap_1510_local_bus_power(1); + omap_1510_local_bus_init(); +} + +/* ULPD_DPLL_CTRL */ +#define DPLL_IOB (1 << 13) +#define DPLL_PLL_ENABLE (1 << 4) +#define DPLL_LOCK (1 << 0) + +/* ULPD_APLL_CTRL */ +#define APLL_NDPLL_SWITCH (1 << 0) static void __init omap_1510_usb_init(struct omap_usb_config *config) { @@ -616,19 +664,19 @@ static void __init omap_1510_usb_init(struct omap_usb_config *config) } #endif -#if IS_ENABLED(CONFIG_USB_OHCI_HCD) - if (config->register_host) { + if (IS_ENABLED(CONFIG_USB_OHCI_HCD) && config->register_host) { int status; - bus_register_notifier(&platform_bus_type, - &omap_1510_usb_ohci_nb); ohci_device.dev.platform_data = config; + dma_direct_set_offset(&ohci_device.dev, PHYS_OFFSET, + OMAP1510_LB_OFFSET, (u64)-1); status = platform_device_register(&ohci_device); if (status) pr_debug("can't register OHCI device, %d\n", status); /* hcd explicitly gates 48MHz */ + + config->lb_reset = omap_1510_local_bus_reset; } -#endif } #else diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 12b26e04686f..0c2936c7a379 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -3614,6 +3614,8 @@ int omap_hwmod_init_module(struct device *dev, oh->flags |= HWMOD_SWSUP_SIDLE_ACT; if (data->cfg->quirks & SYSC_QUIRK_SWSUP_MSTANDBY) oh->flags |= HWMOD_SWSUP_MSTANDBY; + if (data->cfg->quirks & SYSC_QUIRK_CLKDM_NOAUTO) + oh->flags |= HWMOD_CLKDM_NOAUTO; error = omap_hwmod_check_module(dev, oh, data, sysc_fields, rev_offs, sysc_offs, syss_offs, diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index a951276f0547..a903b26cde40 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -36,6 +36,10 @@ * +-----+ * |RSVD | JIT scratchpad * current ARM_SP => +-----+ <= (BPF_FP - STACK_SIZE + SCRATCH_SIZE) + * | ... | caller-saved registers + * +-----+ + * | ... | arguments passed on stack + * ARM_SP during call => +-----| * | | * | ... | Function call stack * | | @@ -63,6 +67,12 @@ * * When popping registers off the stack at the end of a BPF function, we * reference them via the current ARM_FP register. + * + * Some eBPF operations are implemented via a call to a helper function. + * Such calls are "invisible" in the eBPF code, so it is up to the calling + * program to preserve any caller-saved ARM registers during the call. The + * JIT emits code to push and pop those registers onto the stack, immediately + * above the callee stack frame. */ #define CALLEE_MASK (1 << ARM_R4 | 1 << ARM_R5 | 1 << ARM_R6 | \ 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R9 | \ @@ -70,6 +80,8 @@ #define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR) #define CALLEE_POP_MASK (CALLEE_MASK | 1 << ARM_PC) +#define CALLER_MASK (1 << ARM_R0 | 1 << ARM_R1 | 1 << ARM_R2 | 1 << ARM_R3) + enum { /* Stack layout - these are offsets from (top of stack - 4) */ BPF_R2_HI, @@ -464,6 +476,7 @@ static inline int epilogue_offset(const struct jit_ctx *ctx) static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op) { + const int exclude_mask = BIT(ARM_R0) | BIT(ARM_R1); const s8 *tmp = bpf2a32[TMP_REG_1]; #if __LINUX_ARM_ARCH__ == 7 @@ -495,11 +508,17 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op) emit(ARM_MOV_R(ARM_R0, rm), ctx); } + /* Push caller-saved registers on stack */ + emit(ARM_PUSH(CALLER_MASK & ~exclude_mask), ctx); + /* Call appropriate function */ emit_mov_i(ARM_IP, op == BPF_DIV ? (u32)jit_udiv32 : (u32)jit_mod32, ctx); emit_blx_r(ARM_IP, ctx); + /* Restore caller-saved registers from stack */ + emit(ARM_POP(CALLER_MASK & ~exclude_mask), ctx); + /* Save return value */ if (rd != ARM_R0) emit(ARM_MOV_R(rd, ARM_R0), ctx); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 5c7ae4c3954b..fee914c716aa 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1931,8 +1931,6 @@ source "drivers/cpufreq/Kconfig" endmenu -source "drivers/firmware/Kconfig" - source "drivers/acpi/Kconfig" source "arch/arm64/kvm/Kconfig" diff --git a/arch/arm64/boot/dts/arm/foundation-v8.dtsi b/arch/arm64/boot/dts/arm/foundation-v8.dtsi index 05ae893d1b2e..fbf13f7c2baf 100644 --- a/arch/arm64/boot/dts/arm/foundation-v8.dtsi +++ b/arch/arm64/boot/dts/arm/foundation-v8.dtsi @@ -115,7 +115,6 @@ bus@8000000 { compatible = "arm,vexpress,v2m-p1", "simple-bus"; - arm,v2m-memory-map = "rs1"; #address-cells = <2>; /* SMB chipselect number and offset */ #size-cells = <1>; diff --git a/arch/arm64/boot/dts/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts index b8a21092db4d..269b649934b5 100644 --- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts +++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts @@ -192,32 +192,9 @@ remote-endpoint = <&clcd_pads>; }; }; - - panel-timing { - clock-frequency = <63500127>; - hactive = <1024>; - hback-porch = <152>; - hfront-porch = <48>; - hsync-len = <104>; - vactive = <768>; - vback-porch = <23>; - vfront-porch = <3>; - vsync-len = <4>; - }; }; bus@8000000 { - compatible = "simple-bus"; - - #address-cells = <2>; - #size-cells = <1>; - ranges = <0 0 0 0x08000000 0x04000000>, - <1 0 0 0x14000000 0x04000000>, - <2 0 0 0x18000000 0x04000000>, - <3 0 0 0x1c000000 0x04000000>, - <4 0 0 0x0c000000 0x04000000>, - <5 0 0 0x10000000 0x04000000>; - #interrupt-cells = <1>; interrupt-map-mask = <0 0 63>; interrupt-map = <0 0 0 &gic 0 0 GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 8e7a66943b01..6288e104a089 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -27,8 +27,6 @@ reg = <0x0 0x2b1f0000 0x0 0x1000>; interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "mhu_lpri_rx", - "mhu_hpri_rx"; #mbox-cells = <1>; clocks = <&soc_refclk100mhz>; clock-names = "apb_pclk"; @@ -804,16 +802,6 @@ }; bus@8000000 { - compatible = "simple-bus"; - #address-cells = <2>; - #size-cells = <1>; - ranges = <0 0 0 0x08000000 0x04000000>, - <1 0 0 0x14000000 0x04000000>, - <2 0 0 0x18000000 0x04000000>, - <3 0 0 0x1c000000 0x04000000>, - <4 0 0 0x0c000000 0x04000000>, - <5 0 0 0x10000000 0x04000000>; - #interrupt-cells = <1>; interrupt-map-mask = <0 0 15>; interrupt-map = <0 0 0 &gic 0 GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi index 40d95c58b55e..fefd2b5f0176 100644 --- a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi +++ b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi @@ -92,16 +92,23 @@ }; bus@8000000 { - motherboard-bus { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0x8000000 0 0x8000000 0x18000000>; + + motherboard-bus@8000000 { compatible = "arm,vexpress,v2p-p1", "simple-bus"; #address-cells = <2>; /* SMB chipselect number and offset */ #size-cells = <1>; - #interrupt-cells = <1>; - ranges; - model = "V2M-Juno"; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; arm,hbi = <0x252>; arm,vexpress,site = <0>; - arm,v2m-memory-map = "rs1"; flash@0 { /* 2 * 32MiB NOR Flash memory mounted on CS0 */ @@ -218,7 +225,7 @@ }; }; - mmci@50000 { + mmc@50000 { compatible = "arm,pl180", "arm,primecell"; reg = <0x050000 0x1000>; interrupts = <5>; @@ -246,7 +253,7 @@ clock-names = "KMIREFCLK", "apb_pclk"; }; - wdt@f0000 { + watchdog@f0000 { compatible = "arm,sp805", "arm,primecell"; reg = <0x0f0000 0x10000>; interrupts = <7>; diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts index 3050f45bade4..258991ad7cc0 100644 --- a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts +++ b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts @@ -133,17 +133,6 @@ }; bus@8000000 { - compatible = "simple-bus"; - - #address-cells = <2>; - #size-cells = <1>; - ranges = <0 0 0 0x08000000 0x04000000>, - <1 0 0 0x14000000 0x04000000>, - <2 0 0 0x18000000 0x04000000>, - <3 0 0 0x1c000000 0x04000000>, - <4 0 0 0x0c000000 0x04000000>, - <5 0 0 0x10000000 0x04000000>; - #interrupt-cells = <1>; interrupt-map-mask = <0 0 63>; interrupt-map = <0 0 0 &gic GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-motherboard-rs2.dtsi b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard-rs2.dtsi index b917d9d3f1c4..33182d9e5826 100644 --- a/arch/arm64/boot/dts/arm/rtsm_ve-motherboard-rs2.dtsi +++ b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard-rs2.dtsi @@ -6,7 +6,7 @@ */ / { bus@8000000 { - motherboard-bus { + motherboard-bus@8000000 { arm,v2m-memory-map = "rs2"; iofpga-bus@300000000 { diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi index 4c4a381d2c75..5f6cab668aa0 100644 --- a/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi +++ b/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi @@ -77,13 +77,21 @@ }; bus@8000000 { - motherboard-bus { - arm,v2m-memory-map = "rs1"; + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0x8000000 0 0x8000000 0x18000000>; + + motherboard-bus@8000000 { compatible = "arm,vexpress,v2m-p1", "simple-bus"; #address-cells = <2>; /* SMB chipselect number and offset */ #size-cells = <1>; - #interrupt-cells = <1>; - ranges; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; flash@0 { compatible = "arm,vexpress-flash", "cfi-flash"; @@ -130,7 +138,7 @@ clock-names = "apb_pclk"; }; - mmci@50000 { + mmc@50000 { compatible = "arm,pl180", "arm,primecell"; reg = <0x050000 0x1000>; interrupts = <9>, <10>; @@ -190,7 +198,7 @@ clock-names = "uartclk", "apb_pclk"; }; - wdt@f0000 { + watchdog@f0000 { compatible = "arm,sp805", "arm,primecell"; reg = <0x0f0000 0x1000>; interrupts = <0>; diff --git a/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts index d859914500a7..5b6d9d8e934d 100644 --- a/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts +++ b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts @@ -145,61 +145,6 @@ }; smb: bus@8000000 { - compatible = "simple-bus"; - - #address-cells = <2>; - #size-cells = <1>; - ranges = <0 0 0 0x08000000 0x04000000>, - <1 0 0 0x14000000 0x04000000>, - <2 0 0 0x18000000 0x04000000>, - <3 0 0 0x1c000000 0x04000000>, - <4 0 0 0x0c000000 0x04000000>, - <5 0 0 0x10000000 0x04000000>; - - #interrupt-cells = <1>; - interrupt-map-mask = <0 0 63>; - interrupt-map = <0 0 0 &gic GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>, - <0 0 1 &gic GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>, - <0 0 2 &gic GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>, - <0 0 3 &gic GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>, - <0 0 4 &gic GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>, - <0 0 5 &gic GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>, - <0 0 6 &gic GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>, - <0 0 7 &gic GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>, - <0 0 8 &gic GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>, - <0 0 9 &gic GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>, - <0 0 10 &gic GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>, - <0 0 11 &gic GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>, - <0 0 12 &gic GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>, - <0 0 13 &gic GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>, - <0 0 14 &gic GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>, - <0 0 15 &gic GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>, - <0 0 16 &gic GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>, - <0 0 17 &gic GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>, - <0 0 18 &gic GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>, - <0 0 19 &gic GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>, - <0 0 20 &gic GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>, - <0 0 21 &gic GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>, - <0 0 22 &gic GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>, - <0 0 23 &gic GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>, - <0 0 24 &gic GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>, - <0 0 25 &gic GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>, - <0 0 26 &gic GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>, - <0 0 27 &gic GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>, - <0 0 28 &gic GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>, - <0 0 29 &gic GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>, - <0 0 30 &gic GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>, - <0 0 31 &gic GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>, - <0 0 32 &gic GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>, - <0 0 33 &gic GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>, - <0 0 34 &gic GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>, - <0 0 35 &gic GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>, - <0 0 36 &gic GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>, - <0 0 37 &gic GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>, - <0 0 38 &gic GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>, - <0 0 39 &gic GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>, - <0 0 40 &gic GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>, - <0 0 41 &gic GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>, - <0 0 42 &gic GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>; + ranges = <0x8000000 0 0x8000000 0x18000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 343ecf0e8973..06b36cc65865 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -405,9 +405,9 @@ interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>; clock-frequency = <0>; /* fixed up by bootloader */ clocks = <&clockgen QORIQ_CLK_HWACCEL 1>; - voltage-ranges = <1800 1800 3300 3300>; + voltage-ranges = <1800 1800>; sdhci,auto-cmd12; - broken-cd; + non-removable; little-endian; bus-width = <4>; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi index 988f8ab679ad..40f5e7a3b064 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi @@ -91,7 +91,7 @@ #size-cells = <1>; compatible = "jedec,spi-nor"; spi-max-frequency = <80000000>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts index 4e2820d19244..a2b24d4d4e3e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts @@ -48,7 +48,7 @@ #size-cells = <1>; compatible = "jedec,spi-nor"; spi-max-frequency = <80000000>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi index d0456daefda8..9db9b90bf2bc 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi @@ -102,6 +102,7 @@ regulator-min-microvolt = <850000>; regulator-max-microvolt = <950000>; regulator-boot-on; + regulator-always-on; regulator-ramp-delay = <3125>; nxp,dvs-run-voltage = <950000>; nxp,dvs-standby-voltage = <850000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts index 05cb60991fb9..d52686f4c059 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts @@ -647,7 +647,7 @@ pinctrl_hog: hoggrp { fsl,pins = < MX8MM_IOMUXC_NAND_CE0_B_GPIO3_IO1 0x40000159 /* M2_GDIS# */ - MX8MM_IOMUXC_GPIO1_IO12_GPIO1_IO12 0x40000041 /* M2_RST# */ + MX8MM_IOMUXC_GPIO1_IO13_GPIO1_IO13 0x40000041 /* M2_RST# */ MX8MM_IOMUXC_NAND_DATA01_GPIO3_IO7 0x40000119 /* M2_OFF# */ MX8MM_IOMUXC_GPIO1_IO15_GPIO1_IO15 0x40000159 /* M2_WDIS# */ MX8MM_IOMUXC_SAI1_TXD2_GPIO4_IO14 0x40000041 /* AMP GPIO1 */ diff --git a/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi index 54eaf3d6055b..3b2d627a0342 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi @@ -101,7 +101,7 @@ #size-cells = <1>; compatible = "jedec,spi-nor"; spi-max-frequency = <80000000>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts b/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts index e77db4996e58..236f425e1570 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts @@ -633,7 +633,7 @@ pinctrl_hog: hoggrp { fsl,pins = < MX8MN_IOMUXC_NAND_CE0_B_GPIO3_IO1 0x40000159 /* M2_GDIS# */ - MX8MN_IOMUXC_GPIO1_IO12_GPIO1_IO12 0x40000041 /* M2_RST# */ + MX8MN_IOMUXC_GPIO1_IO13_GPIO1_IO13 0x40000041 /* M2_RST# */ MX8MN_IOMUXC_NAND_DATA01_GPIO3_IO7 0x40000119 /* M2_OFF# */ MX8MN_IOMUXC_GPIO1_IO15_GPIO1_IO15 0x40000159 /* M2_WDIS# */ MX8MN_IOMUXC_SAI2_RXFS_GPIO4_IO21 0x40000041 /* APP GPIO1 */ diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi index aa78e0d8c72b..fc178eebf8aa 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi @@ -74,7 +74,7 @@ compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <80000000>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-evk.dts b/arch/arm64/boot/dts/freescale/imx8mq-evk.dts index 49f9db971f3b..b83df77195ec 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-evk.dts @@ -337,6 +337,8 @@ #size-cells = <1>; compatible = "micron,n25q256a", "jedec,spi-nor"; spi-max-frequency = <29000000>; + spi-tx-bus-width = <1>; + spi-rx-bus-width = <4>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts b/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts index f593e4ff62e1..564746d5000d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-kontron-pitx-imx8m.dts @@ -281,7 +281,7 @@ #address-cells = <1>; #size-cells = <1>; reg = <0>; - spi-tx-bus-width = <4>; + spi-tx-bus-width = <1>; spi-rx-bus-width = <4>; m25p,fast-read; spi-max-frequency = <50000000>; diff --git a/arch/arm64/boot/dts/qcom/pm8150.dtsi b/arch/arm64/boot/dts/qcom/pm8150.dtsi index c566a64b1373..0df76f7b1cc1 100644 --- a/arch/arm64/boot/dts/qcom/pm8150.dtsi +++ b/arch/arm64/boot/dts/qcom/pm8150.dtsi @@ -48,8 +48,10 @@ #size-cells = <0>; pon: power-on@800 { - compatible = "qcom,pm8916-pon"; + compatible = "qcom,pm8998-pon"; reg = <0x0800>; + mode-bootloader = <0x2>; + mode-recovery = <0x1>; pon_pwrkey: pwrkey { compatible = "qcom,pm8941-pwrkey"; diff --git a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts index 8ac96f8e79d4..28d5b5528516 100644 --- a/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts +++ b/arch/arm64/boot/dts/qcom/qrb5165-rb5.dts @@ -804,6 +804,16 @@ }; }; +&pon_pwrkey { + status = "okay"; +}; + +&pon_resin { + status = "okay"; + + linux,code = <KEY_VOLUMEDOWN>; +}; + &qupv3_id_0 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index 0f2b3c00e434..70c88c37de32 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -273,7 +273,6 @@ "Headphone Jack", "HPOL", "Headphone Jack", "HPOR"; - #sound-dai-cells = <0>; #address-cells = <1>; #size-cells = <0>; @@ -301,11 +300,11 @@ }; }; - dai-link@2 { + dai-link@5 { link-name = "MultiMedia2"; - reg = <2>; + reg = <LPASS_DP_RX>; cpu { - sound-dai = <&lpass_cpu 2>; + sound-dai = <&lpass_cpu LPASS_DP_RX>; }; codec { @@ -782,7 +781,7 @@ hp_i2c: &i2c9 { qcom,playback-sd-lines = <0>; }; - hdmi-primary@0 { + hdmi@5 { reg = <LPASS_DP_RX>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi index 53a21d086178..fd78f16181dd 100644 --- a/arch/arm64/boot/dts/qcom/sc7280.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi @@ -1850,9 +1850,9 @@ cpufreq_hw: cpufreq@18591000 { compatible = "qcom,cpufreq-epss"; - reg = <0 0x18591100 0 0x900>, - <0 0x18592100 0 0x900>, - <0 0x18593100 0 0x900>; + reg = <0 0x18591000 0 0x1000>, + <0 0x18592000 0 0x1000>, + <0 0x18593000 0 0x1000>; clocks = <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_GPLL0>; clock-names = "xo", "alternate"; #freq-domain-cells = <1>; diff --git a/arch/arm64/boot/dts/qcom/sdm630.dtsi b/arch/arm64/boot/dts/qcom/sdm630.dtsi index 9153e6616ba4..9c7f87e42fcc 100644 --- a/arch/arm64/boot/dts/qcom/sdm630.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm630.dtsi @@ -654,9 +654,20 @@ compatible = "qcom,sdm660-a2noc"; reg = <0x01704000 0xc100>; #interconnect-cells = <1>; - clock-names = "bus", "bus_a"; + clock-names = "bus", + "bus_a", + "ipa", + "ufs_axi", + "aggre2_ufs_axi", + "aggre2_usb3_axi", + "cfg_noc_usb2_axi"; clocks = <&rpmcc RPM_SMD_AGGR2_NOC_CLK>, - <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>; + <&rpmcc RPM_SMD_AGGR2_NOC_A_CLK>, + <&rpmcc RPM_SMD_IPA_CLK>, + <&gcc GCC_UFS_AXI_CLK>, + <&gcc GCC_AGGRE2_UFS_AXI_CLK>, + <&gcc GCC_AGGRE2_USB3_AXI_CLK>, + <&gcc GCC_CFG_NOC_USB2_AXI_CLK>; }; mnoc: interconnect@1745000 { diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 6d7172e6f4c3..b3b911926184 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -128,23 +128,28 @@ no-map; }; - wlan_msa_mem: memory@8c400000 { - reg = <0 0x8c400000 0 0x100000>; + ipa_fw_mem: memory@8c400000 { + reg = <0 0x8c400000 0 0x10000>; no-map; }; - gpu_mem: memory@8c515000 { - reg = <0 0x8c515000 0 0x2000>; + ipa_gsi_mem: memory@8c410000 { + reg = <0 0x8c410000 0 0x5000>; no-map; }; - ipa_fw_mem: memory@8c517000 { - reg = <0 0x8c517000 0 0x5a000>; + gpu_mem: memory@8c415000 { + reg = <0 0x8c415000 0 0x2000>; no-map; }; - adsp_mem: memory@8c600000 { - reg = <0 0x8c600000 0 0x1a00000>; + adsp_mem: memory@8c500000 { + reg = <0 0x8c500000 0 0x1a00000>; + no-map; + }; + + wlan_msa_mem: memory@8df00000 { + reg = <0 0x8df00000 0 0x100000>; no-map; }; diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts index 385e5029437d..2ba23aa582a1 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts @@ -16,6 +16,17 @@ #include "sdm850.dtsi" #include "pm8998.dtsi" +/* + * Update following upstream (sdm845.dtsi) reserved + * memory mappings for firmware loading to succeed + * and enable the IPA device. + */ +/delete-node/ &ipa_fw_mem; +/delete-node/ &ipa_gsi_mem; +/delete-node/ &gpu_mem; +/delete-node/ &adsp_mem; +/delete-node/ &wlan_msa_mem; + / { model = "Lenovo Yoga C630"; compatible = "lenovo,yoga-c630", "qcom,sdm845"; @@ -58,6 +69,29 @@ }; }; + /* Reserved memory changes for IPA */ + reserved-memory { + wlan_msa_mem: memory@8c400000 { + reg = <0 0x8c400000 0 0x100000>; + no-map; + }; + + gpu_mem: memory@8c515000 { + reg = <0 0x8c515000 0 0x2000>; + no-map; + }; + + ipa_fw_mem: memory@8c517000 { + reg = <0 0x8c517000 0 0x5a000>; + no-map; + }; + + adsp_mem: memory@8c600000 { + reg = <0 0x8c600000 0 0x1a00000>; + no-map; + }; + }; + sn65dsi86_refclk: sn65dsi86-refclk { compatible = "fixed-clock"; #clock-cells = <0>; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 23505fc35324..a8158c948966 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -43,7 +43,7 @@ void __init arm64_hugetlb_cma_reserve(void) #ifdef CONFIG_ARM64_4K_PAGES order = PUD_SHIFT - PAGE_SHIFT; #else - order = CONT_PMD_SHIFT + PMD_SHIFT - PAGE_SHIFT; + order = CONT_PMD_SHIFT - PAGE_SHIFT; #endif /* * HugeTLB CMA reservation is required for gigantic diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 045792cde481..1e33666fa679 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -388,8 +388,6 @@ config CRASH_DUMP help Generate crash dump after being started by kexec. -source "drivers/firmware/Kconfig" - endmenu menu "Power management and ACPI options" diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 771ca53af06d..6b8f591c5054 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -3316,8 +3316,6 @@ source "drivers/cpuidle/Kconfig" endmenu -source "drivers/firmware/Kconfig" - source "arch/mips/kvm/Kconfig" source "arch/mips/vdso/Kconfig" diff --git a/arch/mips/include/asm/mips-cps.h b/arch/mips/include/asm/mips-cps.h index 35fb8ee6dd33..fd43d876892e 100644 --- a/arch/mips/include/asm/mips-cps.h +++ b/arch/mips/include/asm/mips-cps.h @@ -10,8 +10,6 @@ #include <linux/io.h> #include <linux/types.h> -#include <asm/mips-boards/launch.h> - extern unsigned long __cps_access_bad_size(void) __compiletime_error("Bad size for CPS accessor"); @@ -167,30 +165,11 @@ static inline uint64_t mips_cps_cluster_config(unsigned int cluster) */ static inline unsigned int mips_cps_numcores(unsigned int cluster) { - unsigned int ncores; - if (!mips_cm_present()) return 0; /* Add one before masking to handle 0xff indicating no cores */ - ncores = (mips_cps_cluster_config(cluster) + 1) & CM_GCR_CONFIG_PCORES; - - if (IS_ENABLED(CONFIG_SOC_MT7621)) { - struct cpulaunch *launch; - - /* - * Ralink MT7621S SoC is single core, but the GCR_CONFIG method - * always reports 2 cores. Check the second core's LAUNCH_FREADY - * flag to detect if the second core is missing. This method - * only works before the core has been started. - */ - launch = (struct cpulaunch *)CKSEG0ADDR(CPULAUNCH); - launch += 2; /* MT7621 has 2 VPEs per core */ - if (!(launch->flags & LAUNCH_FREADY)) - ncores = 1; - } - - return ncores; + return (mips_cps_cluster_config(cluster) + 1) & CM_GCR_CONFIG_PCORES; } /** diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 4742b6f169b7..27a8b49af11f 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -384,6 +384,4 @@ config KEXEC_FILE endmenu -source "drivers/firmware/Kconfig" - source "drivers/parisc/Kconfig" diff --git a/arch/powerpc/boot/dts/fsl/t1023rdb.dts b/arch/powerpc/boot/dts/fsl/t1023rdb.dts index 5ba6fbfca274..f82f85c65964 100644 --- a/arch/powerpc/boot/dts/fsl/t1023rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1023rdb.dts @@ -154,7 +154,7 @@ fm1mac3: ethernet@e4000 { phy-handle = <&sgmii_aqr_phy3>; - phy-connection-type = "sgmii-2500"; + phy-connection-type = "2500base-x"; sleep = <&rcpm 0x20000000>; }; diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index d4b145b279f6..9f38040f0641 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -136,6 +136,14 @@ static inline void kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap) if (kuap_is_disabled()) return; + if (unlikely(kuap != KUAP_NONE)) { + current->thread.kuap = KUAP_NONE; + kuap_lock(kuap, false); + } + + if (likely(regs->kuap == KUAP_NONE)) + return; + current->thread.kuap = regs->kuap; kuap_unlock(regs->kuap, false); diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index a95f63788c6b..4ba834599c4d 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -23,6 +23,7 @@ #define BRANCH_ABSOLUTE 0x2 bool is_offset_in_branch_range(long offset); +bool is_offset_in_cond_branch_range(long offset); int create_branch(struct ppc_inst *instr, const u32 *addr, unsigned long target, int flags); int create_cond_branch(struct ppc_inst *instr, const u32 *addr, diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index 6b800d3e2681..a1d238255f07 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -265,13 +265,16 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte local_paca->irq_soft_mask = IRQS_ALL_DISABLED; local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - if (is_implicit_soft_masked(regs)) { - // Adjust regs->softe soft implicit soft-mask, so - // arch_irq_disabled_regs(regs) behaves as expected. + if (!(regs->msr & MSR_EE) || is_implicit_soft_masked(regs)) { + /* + * Adjust regs->softe to be soft-masked if it had not been + * reconcied (e.g., interrupt entry with MSR[EE]=0 but softe + * not yet set disabled), or if it was in an implicit soft + * masked state. This makes arch_irq_disabled_regs(regs) + * behave as expected. + */ regs->softe = IRQS_ALL_DISABLED; } - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) - BUG_ON(!arch_irq_disabled_regs(regs) && !(regs->msr & MSR_EE)); /* Don't do any per-CPU operations until interrupt state is fixed */ @@ -525,10 +528,9 @@ static __always_inline long ____##func(struct pt_regs *regs) /* kernel/traps.c */ DECLARE_INTERRUPT_HANDLER_NMI(system_reset_exception); #ifdef CONFIG_PPC_BOOK3S_64 -DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception); -#else -DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception); +DECLARE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async); #endif +DECLARE_INTERRUPT_HANDLER_NMI(machine_check_exception); DECLARE_INTERRUPT_HANDLER(SMIException); DECLARE_INTERRUPT_HANDLER(handle_hmi_exception); DECLARE_INTERRUPT_HANDLER(unknown_exception); diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 792eefaf230b..27574f218b37 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -39,6 +39,11 @@ static inline bool security_ftr_enabled(u64 feature) return !!(powerpc_security_features & feature); } +#ifdef CONFIG_PPC_BOOK3S_64 +enum stf_barrier_type stf_barrier_type_get(void); +#else +static inline enum stf_barrier_type stf_barrier_type_get(void) { return STF_BARRIER_NONE; } +#endif // Features indicating support for Spectre/Meltdown mitigations diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 111249fd619d..038ce8d9061d 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -184,6 +184,15 @@ u64 dma_iommu_get_required_mask(struct device *dev) struct iommu_table *tbl = get_iommu_table_base(dev); u64 mask; + if (dev_is_pci(dev)) { + u64 bypass_mask = dma_direct_get_required_mask(dev); + + if (dma_iommu_dma_supported(dev, bypass_mask)) { + dev_info(dev, "%s: returning bypass mask 0x%llx\n", __func__, bypass_mask); + return bypass_mask; + } + } + if (!tbl) return 0; diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 37859e62a8dc..eaf1f72131a1 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1243,7 +1243,7 @@ EXC_COMMON_BEGIN(machine_check_common) li r10,MSR_RI mtmsrd r10,1 addi r3,r1,STACK_FRAME_OVERHEAD - bl machine_check_exception + bl machine_check_exception_async b interrupt_return_srr @@ -1303,7 +1303,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) subi r12,r12,1 sth r12,PACA_IN_MCE(r13) - /* Invoke machine_check_exception to print MCE event and panic. */ + /* + * Invoke machine_check_exception to print MCE event and panic. + * This is the NMI version of the handler because we are called from + * the early handler which is a true NMI. + */ addi r3,r1,STACK_FRAME_OVERHEAD bl machine_check_exception @@ -1665,27 +1669,30 @@ EXC_COMMON_BEGIN(program_check_common) */ andi. r10,r12,MSR_PR - bne 2f /* If userspace, go normal path */ + bne .Lnormal_stack /* If userspace, go normal path */ andis. r10,r12,(SRR1_PROGTM)@h - bne 1f /* If TM, emergency */ + bne .Lemergency_stack /* If TM, emergency */ cmpdi r1,-INT_FRAME_SIZE /* check if r1 is in userspace */ - blt 2f /* normal path if not */ + blt .Lnormal_stack /* normal path if not */ /* Use the emergency stack */ -1: andi. r10,r12,MSR_PR /* Set CR0 correctly for label */ +.Lemergency_stack: + andi. r10,r12,MSR_PR /* Set CR0 correctly for label */ /* 3 in EXCEPTION_PROLOG_COMMON */ mr r10,r1 /* Save r1 */ ld r1,PACAEMERGSP(r13) /* Use emergency stack */ subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */ __ISTACK(program_check)=0 __GEN_COMMON_BODY program_check - b 3f -2: + b .Ldo_program_check + +.Lnormal_stack: __ISTACK(program_check)=1 __GEN_COMMON_BODY program_check -3: + +.Ldo_program_check: addi r3,r1,STACK_FRAME_OVERHEAD bl program_check_exception REST_NVGPRS(r1) /* instruction emulation may change GPRs */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 551b653228c4..c4f1d6b7d992 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -229,6 +229,9 @@ notrace void arch_local_irq_restore(unsigned long mask) return; } + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(in_nmi() || in_hardirq()); + /* * After the stb, interrupts are unmasked and there are no interrupts * pending replay. The restart sequence makes this atomic with @@ -321,6 +324,9 @@ notrace void arch_local_irq_restore(unsigned long mask) if (mask) return; + if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) + WARN_ON_ONCE(in_nmi() || in_hardirq()); + /* * From this point onward, we can take interrupts, preempt, * etc... unless we got hard-disabled. We check if an event diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 1a998490fe60..15fb5ea1b9ea 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -263,6 +263,11 @@ static int __init handle_no_stf_barrier(char *p) early_param("no_stf_barrier", handle_no_stf_barrier); +enum stf_barrier_type stf_barrier_type_get(void) +{ + return stf_enabled_flush_types; +} + /* This is the generic flag used by other architectures */ static int __init handle_ssbd(char *p) { diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index aac8c0412ff9..11741703d26e 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -340,10 +340,16 @@ static bool exception_common(int signr, struct pt_regs *regs, int code, return false; } - show_signal_msg(signr, regs, code, addr); + /* + * Must not enable interrupts even for user-mode exception, because + * this can be called from machine check, which may be a NMI or IRQ + * which don't like interrupts being enabled. Could check for + * in_hardirq || in_nmi perhaps, but there doesn't seem to be a good + * reason why _exception() should enable irqs for an exception handler, + * the handlers themselves do that directly. + */ - if (arch_irqs_disabled()) - interrupt_cond_local_irq_enable(regs); + show_signal_msg(signr, regs, code, addr); current->thread.trap_nr = code; @@ -790,24 +796,22 @@ void die_mce(const char *str, struct pt_regs *regs, long err) * do_exit() checks for in_interrupt() and panics in that case, so * exit the irq/nmi before calling die. */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) - irq_exit(); - else + if (in_nmi()) nmi_exit(); + else + irq_exit(); die(str, regs, err); } /* - * BOOK3S_64 does not call this handler as a non-maskable interrupt + * BOOK3S_64 does not usually call this handler as a non-maskable interrupt * (it uses its own early real-mode handler to handle the MCE proper * and then raises irq_work to call this handler when interrupts are - * enabled). + * enabled). The only time when this is not true is if the early handler + * is unrecoverable, then it does call this directly to try to get a + * message out. */ -#ifdef CONFIG_PPC_BOOK3S_64 -DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception) -#else -DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception) -#endif +static void __machine_check_exception(struct pt_regs *regs) { int recover = 0; @@ -841,12 +845,19 @@ bail: /* Must die if the interrupt is not recoverable */ if (regs_is_unrecoverable(regs)) die_mce("Unrecoverable Machine check", regs, SIGBUS); +} #ifdef CONFIG_PPC_BOOK3S_64 - return; -#else - return 0; +DEFINE_INTERRUPT_HANDLER_ASYNC(machine_check_exception_async) +{ + __machine_check_exception(regs); +} #endif +DEFINE_INTERRUPT_HANDLER_NMI(machine_check_exception) +{ + __machine_check_exception(regs); + + return 0; } DEFINE_INTERRUPT_HANDLER(SMIException) /* async? */ diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index f9a3019e37b4..c5ed98823835 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -228,6 +228,11 @@ bool is_offset_in_branch_range(long offset) return (offset >= -0x2000000 && offset <= 0x1fffffc && !(offset & 0x3)); } +bool is_offset_in_cond_branch_range(long offset) +{ + return offset >= -0x8000 && offset <= 0x7fff && !(offset & 0x3); +} + /* * Helper to check if a given instruction is a conditional branch * Derived from the conditional checks in analyse_instr() @@ -280,7 +285,7 @@ int create_cond_branch(struct ppc_inst *instr, const u32 *addr, offset = offset - (unsigned long)addr; /* Check we can represent the target in the instruction format */ - if (offset < -0x8000 || offset > 0x7FFF || offset & 0x3) + if (!is_offset_in_cond_branch_range(offset)) return 1; /* Mask out the flags and target, so they don't step on each other. */ diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 99fad093f43e..7e9b978b768e 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -24,16 +24,30 @@ #define EMIT(instr) PLANT_INSTR(image, ctx->idx, instr) /* Long jump; (unconditional 'branch') */ -#define PPC_JMP(dest) EMIT(PPC_INST_BRANCH | \ - (((dest) - (ctx->idx * 4)) & 0x03fffffc)) +#define PPC_JMP(dest) \ + do { \ + long offset = (long)(dest) - (ctx->idx * 4); \ + if (!is_offset_in_branch_range(offset)) { \ + pr_err_ratelimited("Branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx); \ + return -ERANGE; \ + } \ + EMIT(PPC_INST_BRANCH | (offset & 0x03fffffc)); \ + } while (0) + /* blr; (unconditional 'branch' with link) to absolute address */ #define PPC_BL_ABS(dest) EMIT(PPC_INST_BL | \ (((dest) - (unsigned long)(image + ctx->idx)) & 0x03fffffc)) /* "cond" here covers BO:BI fields. */ -#define PPC_BCC_SHORT(cond, dest) EMIT(PPC_INST_BRANCH_COND | \ - (((cond) & 0x3ff) << 16) | \ - (((dest) - (ctx->idx * 4)) & \ - 0xfffc)) +#define PPC_BCC_SHORT(cond, dest) \ + do { \ + long offset = (long)(dest) - (ctx->idx * 4); \ + if (!is_offset_in_cond_branch_range(offset)) { \ + pr_err_ratelimited("Conditional branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx); \ + return -ERANGE; \ + } \ + EMIT(PPC_INST_BRANCH_COND | (((cond) & 0x3ff) << 16) | (offset & 0xfffc)); \ + } while (0) + /* Sign-extended 32-bit immediate load */ #define PPC_LI32(d, i) do { \ if ((int)(uintptr_t)(i) >= -32768 && \ @@ -78,11 +92,6 @@ #define PPC_FUNC_ADDR(d,i) do { PPC_LI32(d, i); } while(0) #endif -static inline bool is_nearbranch(int offset) -{ - return (offset < 32768) && (offset >= -32768); -} - /* * The fly in the ointment of code size changing from pass to pass is * avoided by padding the short branch case with a NOP. If code size differs @@ -91,7 +100,7 @@ static inline bool is_nearbranch(int offset) * state. */ #define PPC_BCC(cond, dest) do { \ - if (is_nearbranch((dest) - (ctx->idx * 4))) { \ + if (is_offset_in_cond_branch_range((long)(dest) - (ctx->idx * 4))) { \ PPC_BCC_SHORT(cond, dest); \ EMIT(PPC_RAW_NOP()); \ } else { \ diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h index 7b713edfa7e2..b63b35e45e55 100644 --- a/arch/powerpc/net/bpf_jit64.h +++ b/arch/powerpc/net/bpf_jit64.h @@ -16,18 +16,18 @@ * with our redzone usage. * * [ prev sp ] <------------- - * [ nv gpr save area ] 6*8 | + * [ nv gpr save area ] 5*8 | * [ tail_call_cnt ] 8 | - * [ local_tmp_var ] 8 | + * [ local_tmp_var ] 16 | * fp (r31) --> [ ebpf stack space ] upto 512 | * [ frame header ] 32/112 | * sp (r1) ---> [ stack pointer ] -------------- */ /* for gpr non volatile registers BPG_REG_6 to 10 */ -#define BPF_PPC_STACK_SAVE (6*8) +#define BPF_PPC_STACK_SAVE (5*8) /* for bpf JIT code internal usage */ -#define BPF_PPC_STACK_LOCALS 16 +#define BPF_PPC_STACK_LOCALS 24 /* stack frame excluding BPF stack, ensure this is quadword aligned */ #define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \ BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 53aefee3fe70..fcbf7a917c56 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -210,7 +210,11 @@ skip_init_ctx: /* Now build the prologue, body code & epilogue for real. */ cgctx.idx = 0; bpf_jit_build_prologue(code_base, &cgctx); - bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass); + if (bpf_jit_build_body(fp, code_base, &cgctx, addrs, extra_pass)) { + bpf_jit_binary_free(bpf_hdr); + fp = org_fp; + goto out_addrs; + } bpf_jit_build_epilogue(code_base, &cgctx); if (bpf_jit_enable > 1) diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index beb12cbc8c29..0da31d41d413 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -200,7 +200,7 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun } } -static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) +static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) { /* * By now, the eBPF program has already setup parameters in r3-r6 @@ -261,7 +261,9 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 bpf_jit_emit_common_epilogue(image, ctx); EMIT(PPC_RAW_BCTR()); + /* out: */ + return 0; } /* Assemble the body code between the prologue & epilogue */ @@ -355,7 +357,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * PPC_LI32(_R0, imm); EMIT(PPC_RAW_ADDC(dst_reg, dst_reg, _R0)); } - if (imm >= 0) + if (imm >= 0 || (BPF_OP(code) == BPF_SUB && imm == 0x80000000)) EMIT(PPC_RAW_ADDZE(dst_reg_h, dst_reg_h)); else EMIT(PPC_RAW_ADDME(dst_reg_h, dst_reg_h)); @@ -623,7 +625,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * EMIT(PPC_RAW_LI(dst_reg_h, 0)); break; case BPF_ALU | BPF_ARSH | BPF_X: /* (s32) dst >>= src */ - EMIT(PPC_RAW_SRAW(dst_reg_h, dst_reg, src_reg)); + EMIT(PPC_RAW_SRAW(dst_reg, dst_reg, src_reg)); break; case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */ bpf_set_seen_register(ctx, tmp_reg); @@ -1073,7 +1075,7 @@ cond_branch: break; case BPF_JMP32 | BPF_JSET | BPF_K: /* andi does not sign-extend the immediate */ - if (imm >= -32768 && imm < 32768) { + if (imm >= 0 && imm < 32768) { /* PPC_ANDI is _only/always_ dot-form */ EMIT(PPC_RAW_ANDI(_R0, dst_reg, imm)); } else { @@ -1090,7 +1092,9 @@ cond_branch: */ case BPF_JMP | BPF_TAIL_CALL: ctx->seen |= SEEN_TAILCALL; - bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + ret = bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + if (ret < 0) + return ret; break; default: @@ -1103,7 +1107,7 @@ cond_branch: return -EOPNOTSUPP; } if (BPF_CLASS(code) == BPF_ALU && !fp->aux->verifier_zext && - !insn_is_zext(&insn[i + 1])) + !insn_is_zext(&insn[i + 1]) && !(BPF_OP(code) == BPF_END && imm == 64)) EMIT(PPC_RAW_LI(dst_reg_h, 0)); } diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index b87a63dba9c8..8b5157ccfeba 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -15,6 +15,7 @@ #include <linux/if_vlan.h> #include <asm/kprobes.h> #include <linux/bpf.h> +#include <asm/security_features.h> #include "bpf_jit64.h" @@ -35,9 +36,9 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx) * [ prev sp ] <------------- * [ ... ] | * sp (r1) ---> [ stack pointer ] -------------- - * [ nv gpr save area ] 6*8 + * [ nv gpr save area ] 5*8 * [ tail_call_cnt ] 8 - * [ local_tmp_var ] 8 + * [ local_tmp_var ] 16 * [ unused red zone ] 208 bytes protected */ static int bpf_jit_stack_local(struct codegen_context *ctx) @@ -45,12 +46,12 @@ static int bpf_jit_stack_local(struct codegen_context *ctx) if (bpf_has_stack_frame(ctx)) return STACK_FRAME_MIN_SIZE + ctx->stack_size; else - return -(BPF_PPC_STACK_SAVE + 16); + return -(BPF_PPC_STACK_SAVE + 24); } static int bpf_jit_stack_tailcallcnt(struct codegen_context *ctx) { - return bpf_jit_stack_local(ctx) + 8; + return bpf_jit_stack_local(ctx) + 16; } static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg) @@ -206,7 +207,7 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun EMIT(PPC_RAW_BCTRL()); } -static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) +static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) { /* * By now, the eBPF program has already setup parameters in r3, r4 and r5 @@ -267,13 +268,38 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 bpf_jit_emit_common_epilogue(image, ctx); EMIT(PPC_RAW_BCTR()); + /* out: */ + return 0; } +/* + * We spill into the redzone always, even if the bpf program has its own stackframe. + * Offsets hardcoded based on BPF_PPC_STACK_SAVE -- see bpf_jit_stack_local() + */ +void bpf_stf_barrier(void); + +asm ( +" .global bpf_stf_barrier ;" +" bpf_stf_barrier: ;" +" std 21,-64(1) ;" +" std 22,-56(1) ;" +" sync ;" +" ld 21,-64(1) ;" +" ld 22,-56(1) ;" +" ori 31,31,0 ;" +" .rept 14 ;" +" b 1f ;" +" 1: ;" +" .endr ;" +" blr ;" +); + /* Assemble the body code between the prologue & epilogue */ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx, u32 *addrs, bool extra_pass) { + enum stf_barrier_type stf_barrier = stf_barrier_type_get(); const struct bpf_insn *insn = fp->insnsi; int flen = fp->len; int i, ret; @@ -328,18 +354,25 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * EMIT(PPC_RAW_SUB(dst_reg, dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU | BPF_ADD | BPF_K: /* (u32) dst += (u32) imm */ - case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */ case BPF_ALU64 | BPF_ADD | BPF_K: /* dst += imm */ + if (!imm) { + goto bpf_alu32_trunc; + } else if (imm >= -32768 && imm < 32768) { + EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm))); + } else { + PPC_LI32(b2p[TMP_REG_1], imm); + EMIT(PPC_RAW_ADD(dst_reg, dst_reg, b2p[TMP_REG_1])); + } + goto bpf_alu32_trunc; + case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */ case BPF_ALU64 | BPF_SUB | BPF_K: /* dst -= imm */ - if (BPF_OP(code) == BPF_SUB) - imm = -imm; - if (imm) { - if (imm >= -32768 && imm < 32768) - EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm))); - else { - PPC_LI32(b2p[TMP_REG_1], imm); - EMIT(PPC_RAW_ADD(dst_reg, dst_reg, b2p[TMP_REG_1])); - } + if (!imm) { + goto bpf_alu32_trunc; + } else if (imm > -32768 && imm <= 32768) { + EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(-imm))); + } else { + PPC_LI32(b2p[TMP_REG_1], imm); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, b2p[TMP_REG_1])); } goto bpf_alu32_trunc; case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */ @@ -389,8 +422,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ if (imm == 0) return -EINVAL; - else if (imm == 1) - goto bpf_alu32_trunc; + if (imm == 1) { + if (BPF_OP(code) == BPF_DIV) { + goto bpf_alu32_trunc; + } else { + EMIT(PPC_RAW_LI(dst_reg, 0)); + break; + } + } PPC_LI32(b2p[TMP_REG_1], imm); switch (BPF_CLASS(code)) { @@ -631,6 +670,29 @@ emit_clear: * BPF_ST NOSPEC (speculation barrier) */ case BPF_ST | BPF_NOSPEC: + if (!security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) || + !security_ftr_enabled(SEC_FTR_STF_BARRIER)) + break; + + switch (stf_barrier) { + case STF_BARRIER_EIEIO: + EMIT(PPC_RAW_EIEIO() | 0x02000000); + break; + case STF_BARRIER_SYNC_ORI: + EMIT(PPC_RAW_SYNC()); + EMIT(PPC_RAW_LD(b2p[TMP_REG_1], _R13, 0)); + EMIT(PPC_RAW_ORI(_R31, _R31, 0)); + break; + case STF_BARRIER_FALLBACK: + EMIT(PPC_RAW_MFLR(b2p[TMP_REG_1])); + PPC_LI64(12, dereference_kernel_function_descriptor(bpf_stf_barrier)); + EMIT(PPC_RAW_MTCTR(12)); + EMIT(PPC_RAW_BCTRL()); + EMIT(PPC_RAW_MTLR(b2p[TMP_REG_1])); + break; + case STF_BARRIER_NONE: + break; + } break; /* @@ -993,7 +1055,9 @@ cond_branch: */ case BPF_JMP | BPF_TAIL_CALL: ctx->seen |= SEEN_TAILCALL; - bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + ret = bpf_jit_emit_tail_call(image, ctx, addrs[i + 1]); + if (ret < 0) + return ret; break; default: diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index bc15200852b7..09fafcf2d3a0 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -867,6 +867,10 @@ static int __init eeh_pseries_init(void) if (is_kdump_kernel() || reset_devices) { pr_info("Issue PHB reset ...\n"); list_for_each_entry(phb, &hose_list, list_node) { + // Skip if the slot is empty + if (list_empty(&PCI_DN(phb->dn)->child_list)) + continue; + pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list); config_addr = pseries_eeh_get_pe_config_addr(pdn); diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 1b305e411862..8627362f613e 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -507,12 +507,27 @@ static void pseries_msi_unmask(struct irq_data *d) irq_chip_unmask_parent(d); } +static void pseries_msi_write_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct msi_desc *entry = irq_data_get_msi_desc(data); + + /* + * Do not update the MSIx vector table. It's not strictly necessary + * because the table is initialized by the underlying hypervisor, PowerVM + * or QEMU/KVM. However, if the MSIx vector entry is cleared, any further + * activation will fail. This can happen in some drivers (eg. IPR) which + * deactivate an IRQ used for testing MSI support. + */ + entry->msg = *msg; +} + static struct irq_chip pseries_pci_msi_irq_chip = { .name = "pSeries-PCI-MSI", .irq_shutdown = pseries_msi_shutdown, .irq_mask = pseries_msi_mask, .irq_unmask = pseries_msi_unmask, .irq_eoi = irq_chip_eoi_parent, + .irq_write_msi_msg = pseries_msi_write_msg, }; static struct msi_domain_info pseries_msi_domain_info = { diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 301a54233c7e..6a6fa9e976d5 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -561,5 +561,3 @@ menu "Power management options" source "kernel/power/Kconfig" endmenu - -source "drivers/firmware/Kconfig" diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index b933b1583c9f..34fbb3ea21d5 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -82,4 +82,5 @@ static inline int syscall_get_arch(struct task_struct *task) #endif } +asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t); #endif /* _ASM_RISCV_SYSCALL_H */ diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 893e47195e30..208e31bc5d1c 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -16,18 +16,24 @@ #ifdef CONFIG_MMU #include <linux/types.h> -#include <generated/vdso-offsets.h> +/* + * All systems with an MMU have a VDSO, but systems without an MMU don't + * support shared libraries and therefor don't have one. + */ +#ifdef CONFIG_MMU + +#define __VVAR_PAGES 1 -#ifndef CONFIG_GENERIC_TIME_VSYSCALL -struct vdso_data { -}; -#endif +#ifndef __ASSEMBLY__ +#include <generated/vdso-offsets.h> #define VDSO_SYMBOL(base, name) \ (void __user *)((unsigned long)(base) + __vdso_##name##_offset) #endif /* CONFIG_MMU */ -asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t); +#endif /* !__ASSEMBLY__ */ + +#endif /* CONFIG_MMU */ #endif /* _ASM_RISCV_VDSO_H */ diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h index 4b989ae15d59..8062996c2dfd 100644 --- a/arch/riscv/include/uapi/asm/unistd.h +++ b/arch/riscv/include/uapi/asm/unistd.h @@ -18,9 +18,10 @@ #ifdef __LP64__ #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT -#define __ARCH_WANT_SYS_CLONE3 #endif /* __LP64__ */ +#define __ARCH_WANT_SYS_CLONE3 + #include <asm-generic/unistd.h> /* diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c index a63c667c27b3..44b1420a2270 100644 --- a/arch/riscv/kernel/syscall_table.c +++ b/arch/riscv/kernel/syscall_table.c @@ -7,7 +7,6 @@ #include <linux/linkage.h> #include <linux/syscalls.h> #include <asm-generic/syscalls.h> -#include <asm/vdso.h> #include <asm/syscall.h> #undef __SYSCALL diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 25a3b8849599..b70956d80408 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -12,14 +12,24 @@ #include <linux/binfmts.h> #include <linux/err.h> #include <asm/page.h> +#include <asm/vdso.h> + #ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> #else -#include <asm/vdso.h> +struct vdso_data { +}; #endif extern char vdso_start[], vdso_end[]; +enum vvar_pages { + VVAR_DATA_PAGE_OFFSET, + VVAR_NR_PAGES, +}; + +#define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) + static unsigned int vdso_pages __ro_after_init; static struct page **vdso_pagelist __ro_after_init; @@ -38,7 +48,7 @@ static int __init vdso_init(void) vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT; vdso_pagelist = - kcalloc(vdso_pages + 1, sizeof(struct page *), GFP_KERNEL); + kcalloc(vdso_pages + VVAR_NR_PAGES, sizeof(struct page *), GFP_KERNEL); if (unlikely(vdso_pagelist == NULL)) { pr_err("vdso: pagelist allocation failed\n"); return -ENOMEM; @@ -63,38 +73,41 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, unsigned long vdso_base, vdso_len; int ret; - vdso_len = (vdso_pages + 1) << PAGE_SHIFT; + BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); + + vdso_len = (vdso_pages + VVAR_NR_PAGES) << PAGE_SHIFT; + + if (mmap_write_lock_killable(mm)) + return -EINTR; - mmap_write_lock(mm); vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0); if (IS_ERR_VALUE(vdso_base)) { ret = vdso_base; goto end; } - /* - * Put vDSO base into mm struct. We need to do this before calling - * install_special_mapping or the perf counter mmap tracking code - * will fail to recognise it as a vDSO (since arch_vma_name fails). - */ - mm->context.vdso = (void *)vdso_base; + mm->context.vdso = NULL; + ret = install_special_mapping(mm, vdso_base, VVAR_SIZE, + (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]); + if (unlikely(ret)) + goto end; ret = - install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT, + install_special_mapping(mm, vdso_base + VVAR_SIZE, + vdso_pages << PAGE_SHIFT, (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), vdso_pagelist); - if (unlikely(ret)) { - mm->context.vdso = NULL; + if (unlikely(ret)) goto end; - } - vdso_base += (vdso_pages << PAGE_SHIFT); - ret = install_special_mapping(mm, vdso_base, PAGE_SIZE, - (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]); + /* + * Put vDSO base into mm struct. We need to do this before calling + * install_special_mapping or the perf counter mmap tracking code + * will fail to recognise it as a vDSO (since arch_vma_name fails). + */ + mm->context.vdso = (void *)vdso_base + VVAR_SIZE; - if (unlikely(ret)) - mm->context.vdso = NULL; end: mmap_write_unlock(mm); return ret; @@ -105,7 +118,7 @@ const char *arch_vma_name(struct vm_area_struct *vma) if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso)) return "[vdso]"; if (vma->vm_mm && (vma->vm_start == - (long)vma->vm_mm->context.vdso + PAGE_SIZE)) + (long)vma->vm_mm->context.vdso - VVAR_SIZE)) return "[vdso_data]"; return NULL; } diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index e6f558bca71b..e9111f700af0 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -3,12 +3,13 @@ * Copyright (C) 2012 Regents of the University of California */ #include <asm/page.h> +#include <asm/vdso.h> OUTPUT_ARCH(riscv) SECTIONS { - PROVIDE(_vdso_data = . + PAGE_SIZE); + PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index 094118663285..89f81067e09e 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -16,6 +16,8 @@ static void ipi_remote_fence_i(void *info) void flush_icache_all(void) { + local_flush_icache_all(); + if (IS_ENABLED(CONFIG_RISCV_SBI)) sbi_remote_fence_i(NULL); else diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index e4803ec51110..6b3c366af78e 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -207,6 +207,8 @@ int zpci_enable_device(struct zpci_dev *); int zpci_disable_device(struct zpci_dev *); int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh); int zpci_deconfigure_device(struct zpci_dev *zdev); +void zpci_device_reserved(struct zpci_dev *zdev); +bool zpci_is_device_configured(struct zpci_dev *zdev); int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64); int zpci_unregister_ioat(struct zpci_dev *, u8); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 840d8594437d..1a374d021e25 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1826,7 +1826,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) jit.addrs = kvcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL); if (jit.addrs == NULL) { fp = orig_fp; - goto out; + goto free_addrs; } /* * Three initial passes: diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index e7e6788d75a8..b833155ce838 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -92,7 +92,7 @@ void zpci_remove_reserved_devices(void) spin_unlock(&zpci_list_lock); list_for_each_entry_safe(zdev, tmp, &remove, entry) - zpci_zdev_put(zdev); + zpci_device_reserved(zdev); } int pci_domain_nr(struct pci_bus *bus) @@ -751,6 +751,14 @@ error: return ERR_PTR(rc); } +bool zpci_is_device_configured(struct zpci_dev *zdev) +{ + enum zpci_state state = zdev->state; + + return state != ZPCI_FN_STATE_RESERVED && + state != ZPCI_FN_STATE_STANDBY; +} + /** * zpci_scan_configured_device() - Scan a freshly configured zpci_dev * @zdev: The zpci_dev to be configured @@ -822,6 +830,31 @@ int zpci_deconfigure_device(struct zpci_dev *zdev) return 0; } +/** + * zpci_device_reserved() - Mark device as resverved + * @zdev: the zpci_dev that was reserved + * + * Handle the case that a given zPCI function was reserved by another system. + * After a call to this function the zpci_dev can not be found via + * get_zdev_by_fid() anymore but may still be accessible via existing + * references though it will not be functional anymore. + */ +void zpci_device_reserved(struct zpci_dev *zdev) +{ + if (zdev->has_hp_slot) + zpci_exit_slot(zdev); + /* + * Remove device from zpci_list as it is going away. This also + * makes sure we ignore subsequent zPCI events for this device. + */ + spin_lock(&zpci_list_lock); + list_del(&zdev->entry); + spin_unlock(&zpci_list_lock); + zdev->state = ZPCI_FN_STATE_RESERVED; + zpci_dbg(3, "rsv fid:%x\n", zdev->fid); + zpci_zdev_put(zdev); +} + void zpci_release_device(struct kref *kref) { struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref); @@ -843,6 +876,12 @@ void zpci_release_device(struct kref *kref) case ZPCI_FN_STATE_STANDBY: if (zdev->has_hp_slot) zpci_exit_slot(zdev); + spin_lock(&zpci_list_lock); + list_del(&zdev->entry); + spin_unlock(&zpci_list_lock); + zpci_dbg(3, "rsv fid:%x\n", zdev->fid); + fallthrough; + case ZPCI_FN_STATE_RESERVED: if (zdev->has_resources) zpci_cleanup_bus_resources(zdev); zpci_bus_device_unregister(zdev); @@ -851,10 +890,6 @@ void zpci_release_device(struct kref *kref) default: break; } - - spin_lock(&zpci_list_lock); - list_del(&zdev->entry); - spin_unlock(&zpci_list_lock); zpci_dbg(3, "rem fid:%x\n", zdev->fid); kfree(zdev); } diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index c856f80cb21b..5b8d647523f9 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -140,7 +140,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) /* The 0x0304 event may immediately reserve the device */ if (!clp_get_state(zdev->fid, &state) && state == ZPCI_FN_STATE_RESERVED) { - zpci_zdev_put(zdev); + zpci_device_reserved(zdev); } } break; @@ -151,7 +151,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) case 0x0308: /* Standby -> Reserved */ if (!zdev) break; - zpci_zdev_put(zdev); + zpci_device_reserved(zdev); break; default: break; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ab83c22d274e..bd70e8a39fbf 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1405,7 +1405,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" - depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6 + depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !MWINCHIP3D && !MK6 select X86_PAE help Select this if you have a 32-bit processor and more than 4 @@ -2832,8 +2832,6 @@ config HAVE_ATOMIC_IOMAP def_bool y depends on X86_32 -source "drivers/firmware/Kconfig" - source "arch/x86/kvm/Kconfig" source "arch/x86/Kconfig.assembler" diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 2a57dbed4894..6dfa8ddaa60f 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2465,6 +2465,7 @@ static int x86_pmu_event_init(struct perf_event *event) if (err) { if (event->destroy) event->destroy(event); + event->destroy = NULL; } if (READ_ONCE(x86_pmu.attr_rdpmc) && diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 1248fc1937f8..69698051a6ab 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -263,6 +263,7 @@ static struct event_constraint intel_icl_event_constraints[] = { INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf), + INTEL_EVENT_CONSTRAINT(0xef, 0xf), INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf), EVENT_CONSTRAINT_END }; diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 32a1ad356c18..db2d92fb44da 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -122,17 +122,27 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, ipi_arg->reserved = 0; ipi_arg->vp_set.valid_bank_mask = 0; - if (!cpumask_equal(mask, cpu_present_mask)) { + /* + * Use HV_GENERIC_SET_ALL and avoid converting cpumask to VP_SET + * when the IPI is sent to all currently present CPUs. + */ + if (!cpumask_equal(mask, cpu_present_mask) || exclude_self) { ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; if (exclude_self) nr_bank = cpumask_to_vpset_noself(&(ipi_arg->vp_set), mask); else nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask); - } - if (nr_bank < 0) - goto ipi_mask_ex_done; - if (!nr_bank) + + /* + * 'nr_bank <= 0' means some CPUs in cpumask can't be + * represented in VP_SET. Return an error and fall back to + * native (architectural) method of sending IPIs. + */ + if (nr_bank <= 0) + goto ipi_mask_ex_done; + } else { ipi_arg->vp_set.format = HV_GENERIC_SET_ALL; + } status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank, ipi_arg, NULL); diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 14ebd2196569..43184640b579 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -25,7 +25,7 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs) * For !SMAP hardware we patch out CLAC on entry. */ if (boot_cpu_has(X86_FEATURE_SMAP) || - (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV))) + (IS_ENABLED(CONFIG_64BIT) && boot_cpu_has(X86_FEATURE_XENPV))) mask |= X86_EFLAGS_AC; WARN_ON_ONCE(flags & mask); diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h index eceea9299097..6c5765192102 100644 --- a/arch/x86/include/asm/kvmclock.h +++ b/arch/x86/include/asm/kvmclock.h @@ -2,6 +2,20 @@ #ifndef _ASM_X86_KVM_CLOCK_H #define _ASM_X86_KVM_CLOCK_H +#include <linux/percpu.h> + extern struct clocksource kvm_clock; +DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); + +static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) +{ + return &this_cpu_read(hv_clock_per_cpu)->pvti; +} + +static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) +{ + return this_cpu_read(hv_clock_per_cpu); +} + #endif /* _ASM_X86_KVM_CLOCK_H */ diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 3506d8c598c1..4557f7cb0fa6 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -14,16 +14,19 @@ static inline int pci_xen_hvm_init(void) return -1; } #endif -#if defined(CONFIG_XEN_DOM0) +#ifdef CONFIG_XEN_PV_DOM0 int __init pci_xen_initial_domain(void); -int xen_find_device_domain_owner(struct pci_dev *dev); -int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); -int xen_unregister_device_domain_owner(struct pci_dev *dev); #else static inline int __init pci_xen_initial_domain(void) { return -1; } +#endif +#ifdef CONFIG_XEN_DOM0 +int xen_find_device_domain_owner(struct pci_dev *dev); +int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); +int xen_unregister_device_domain_owner(struct pci_dev *dev); +#else static inline int xen_find_device_domain_owner(struct pci_dev *dev) { return -1; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0f8885949e8c..b3410f1ac217 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -326,6 +326,7 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_SMAP cr4_set_bits(X86_CR4_SMAP); #else + clear_cpu_cap(c, X86_FEATURE_SMAP); cr4_clear_bits(X86_CR4_SMAP); #endif } diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 4b8813bafffd..bb1c3f5f60c8 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -527,12 +527,14 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) rdt_domain_reconfigure_cdp(r); if (r->alloc_capable && domain_setup_ctrlval(r, d)) { - kfree(d); + kfree(hw_dom); return; } if (r->mon_capable && domain_setup_mon_state(r, d)) { - kfree(d); + kfree(hw_dom->ctrl_val); + kfree(hw_dom->mbps_val); + kfree(hw_dom); return; } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 38837dad46e6..391a4e2b8604 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -714,12 +714,6 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, - { PCI_VENDOR_ID_INTEL, 0x3e20, - PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, - { PCI_VENDOR_ID_INTEL, 0x3ec4, - PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, - { PCI_VENDOR_ID_INTEL, 0x8a12, - PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 445c57c9c539..fa17a27390ab 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -379,9 +379,14 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx, sizeof(fpu->state.fxsave))) return -EFAULT; - /* Reject invalid MXCSR values. */ - if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask) - return -EINVAL; + if (IS_ENABLED(CONFIG_X86_64)) { + /* Reject invalid MXCSR values. */ + if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask) + return -EINVAL; + } else { + /* Mask invalid bits out for historical reasons (broken hardware). */ + fpu->state.fxsave.mxcsr &= ~mxcsr_feature_mask; + } /* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */ if (use_xsave()) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 42fc41dd0e1f..882213df3713 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -10,6 +10,7 @@ #include <asm/irq_remapping.h> #include <asm/hpet.h> #include <asm/time.h> +#include <asm/mwait.h> #undef pr_fmt #define pr_fmt(fmt) "hpet: " fmt @@ -916,6 +917,83 @@ static bool __init hpet_counting(void) return false; } +static bool __init mwait_pc10_supported(void) +{ + unsigned int eax, ebx, ecx, mwait_substates; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return false; + + if (!cpu_feature_enabled(X86_FEATURE_MWAIT)) + return false; + + if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF) + return false; + + cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates); + + return (ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) && + (ecx & CPUID5_ECX_INTERRUPT_BREAK) && + (mwait_substates & (0xF << 28)); +} + +/* + * Check whether the system supports PC10. If so force disable HPET as that + * stops counting in PC10. This check is overbroad as it does not take any + * of the following into account: + * + * - ACPI tables + * - Enablement of intel_idle + * - Command line arguments which limit intel_idle C-state support + * + * That's perfectly fine. HPET is a piece of hardware designed by committee + * and the only reasons why it is still in use on modern systems is the + * fact that it is impossible to reliably query TSC and CPU frequency via + * CPUID or firmware. + * + * If HPET is functional it is useful for calibrating TSC, but this can be + * done via PMTIMER as well which seems to be the last remaining timer on + * X86/INTEL platforms that has not been completely wreckaged by feature + * creep. + * + * In theory HPET support should be removed altogether, but there are older + * systems out there which depend on it because TSC and APIC timer are + * dysfunctional in deeper C-states. + * + * It's only 20 years now that hardware people have been asked to provide + * reliable and discoverable facilities which can be used for timekeeping + * and per CPU timer interrupts. + * + * The probability that this problem is going to be solved in the + * forseeable future is close to zero, so the kernel has to be cluttered + * with heuristics to keep up with the ever growing amount of hardware and + * firmware trainwrecks. Hopefully some day hardware people will understand + * that the approach of "This can be fixed in software" is not sustainable. + * Hope dies last... + */ +static bool __init hpet_is_pc10_damaged(void) +{ + unsigned long long pcfg; + + /* Check whether PC10 substates are supported */ + if (!mwait_pc10_supported()) + return false; + + /* Check whether PC10 is enabled in PKG C-state limit */ + rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, pcfg); + if ((pcfg & 0xF) < 8) + return false; + + if (hpet_force_user) { + pr_warn("HPET force enabled via command line, but dysfunctional in PC10.\n"); + return false; + } + + pr_info("HPET dysfunctional in PC10. Force disabled.\n"); + boot_hpet_disable = true; + return true; +} + /** * hpet_enable - Try to setup the HPET timer. Returns 1 on success. */ @@ -929,6 +1007,9 @@ int __init hpet_enable(void) if (!is_hpet_capable()) return 0; + if (hpet_is_pc10_damaged()) + return 0; + hpet_set_mapping(); if (!hpet_virt_address) return 0; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index ad273e5861c1..73c74b961d0f 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -49,18 +49,9 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); static struct pvclock_vsyscall_time_info hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE); static struct pvclock_wall_clock wall_clock __bss_decrypted; -static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); static struct pvclock_vsyscall_time_info *hvclock_mem; - -static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) -{ - return &this_cpu_read(hv_clock_per_cpu)->pvti; -} - -static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) -{ - return this_cpu_read(hv_clock_per_cpu); -} +DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); +EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu); /* * The wallclock is the time of day when we booted. Since then, some time may diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 9f90f460a28c..bf1033a62e48 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -130,6 +130,8 @@ static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, } else { ret = ES_VMM_ERROR; } + } else if (ghcb->save.sw_exit_info_1 & 0xffffffff) { + ret = ES_VMM_ERROR; } else { ret = ES_OK; } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index fe03bd978761..751aa85a3001 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -65,8 +65,8 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( for (i = 0; i < nent; i++) { e = &entries[i]; - if (e->function == function && (e->index == index || - !(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX))) + if (e->function == function && + (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index)) return e; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index c589ac832265..9a144ca8e146 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -435,7 +435,6 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); __FOP_RET(#op) asm(".pushsection .fixup, \"ax\"\n" - ".global kvm_fastop_exception \n" "kvm_fastop_exception: xor %esi, %esi; ret\n" ".popsection"); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 9ecfcf13a046..116b08904ac3 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6848,7 +6848,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) */ tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (tsx_ctrl) - vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + tsx_ctrl->mask = ~(u64)TSX_CTRL_CPUID_CLEAR; } err = alloc_loaded_vmcs(&vmx->vmcs01); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 3d41a09c2c14..5debe4ac6f81 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -113,7 +113,7 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, false /* no mapping of GSI to PIRQ */); } -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 static int xen_register_gsi(u32 gsi, int triggering, int polarity) { int rc, irq; @@ -261,7 +261,7 @@ error: return irq; } -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 static bool __read_mostly pci_seg_supported = true; static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) @@ -375,10 +375,10 @@ static void xen_initdom_restore_msi_irqs(struct pci_dev *dev) WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret); } } -#else /* CONFIG_XEN_DOM0 */ +#else /* CONFIG_XEN_PV_DOM0 */ #define xen_initdom_setup_msi_irqs NULL #define xen_initdom_restore_msi_irqs NULL -#endif /* !CONFIG_XEN_DOM0 */ +#endif /* !CONFIG_XEN_PV_DOM0 */ static void xen_teardown_msi_irqs(struct pci_dev *dev) { @@ -555,7 +555,7 @@ int __init pci_xen_hvm_init(void) return 0; } -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 int __init pci_xen_initial_domain(void) { int irq; @@ -583,6 +583,9 @@ int __init pci_xen_initial_domain(void) } return 0; } +#endif + +#ifdef CONFIG_XEN_DOM0 struct xen_device_domain_owner { domid_t domain; @@ -656,4 +659,4 @@ int xen_unregister_device_domain_owner(struct pci_dev *dev) return 0; } EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner); -#endif +#endif /* CONFIG_XEN_DOM0 */ diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c index ee2beda590d0..1d4a00e767ec 100644 --- a/arch/x86/platform/olpc/olpc.c +++ b/arch/x86/platform/olpc/olpc.c @@ -274,7 +274,7 @@ static struct olpc_ec_driver ec_xo1_driver = { static struct olpc_ec_driver ec_xo1_5_driver = { .ec_cmd = olpc_xo1_ec_cmd, -#ifdef CONFIG_OLPC_XO1_5_SCI +#ifdef CONFIG_OLPC_XO15_SCI /* * XO-1.5 EC wakeups are available when olpc-xo15-sci driver is * compiled in diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 9ac7457f52a3..ed0442e35434 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -16,15 +16,15 @@ /* * PVH variables. * - * pvh_bootparams and pvh_start_info need to live in the data segment since + * pvh_bootparams and pvh_start_info need to live in a data segment since * they are used after startup_{32|64}, which clear .bss, are invoked. */ -struct boot_params pvh_bootparams __section(".data"); -struct hvm_start_info pvh_start_info __section(".data"); +struct boot_params __initdata pvh_bootparams; +struct hvm_start_info __initdata pvh_start_info; -unsigned int pvh_start_info_sz = sizeof(pvh_start_info); +const unsigned int __initconst pvh_start_info_sz = sizeof(pvh_start_info); -static u64 pvh_get_root_pointer(void) +static u64 __init pvh_get_root_pointer(void) { return pvh_start_info.rsdp_paddr; } @@ -107,7 +107,7 @@ void __init __weak xen_pvh_init(struct boot_params *boot_params) BUG(); } -static void hypervisor_specific_init(bool xen_guest) +static void __init hypervisor_specific_init(bool xen_guest) { if (xen_guest) xen_pvh_init(&pvh_bootparams); diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index afc1da68b06d..6bcd3d8ca6ac 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -43,13 +43,9 @@ config XEN_PV_SMP def_bool y depends on XEN_PV && SMP -config XEN_DOM0 - bool "Xen PV Dom0 support" - default y - depends on XEN_PV && PCI_XEN && SWIOTLB_XEN - depends on X86_IO_APIC && ACPI && PCI - help - Support running as a Xen PV Dom0 guest. +config XEN_PV_DOM0 + def_bool y + depends on XEN_PV && XEN_DOM0 config XEN_PVHVM def_bool y @@ -86,3 +82,12 @@ config XEN_PVH def_bool n help Support for running as a Xen PVH guest. + +config XEN_DOM0 + bool "Xen Dom0 support" + default XEN_PV + depends on (XEN_PV && SWIOTLB_XEN) || (XEN_PVH && X86_64) + depends on X86_IO_APIC && ACPI && PCI + select X86_X2APIC if XEN_PVH && X86_64 + help + Support running as a Xen Dom0 guest. diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 40b5779fce21..4953260e281c 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -45,7 +45,7 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o -obj-$(CONFIG_XEN_DOM0) += vga.o +obj-$(CONFIG_XEN_PV_DOM0) += vga.o obj-$(CONFIG_SWIOTLB_XEN) += pci-swiotlb-xen.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c79bd0af2e8c..95d970359e17 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -3,6 +3,7 @@ #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG #include <linux/memblock.h> #endif +#include <linux/console.h> #include <linux/cpu.h> #include <linux/kexec.h> #include <linux/slab.h> @@ -10,12 +11,15 @@ #include <xen/xen.h> #include <xen/features.h> +#include <xen/interface/sched.h> +#include <xen/interface/version.h> #include <xen/page.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> #include <asm/cpu.h> #include <asm/e820/api.h> +#include <asm/setup.h> #include "xen-ops.h" #include "smp.h" @@ -52,9 +56,6 @@ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); -enum xen_domain_type xen_domain_type = XEN_NATIVE; -EXPORT_SYMBOL_GPL(xen_domain_type); - unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START; EXPORT_SYMBOL(machine_to_phys_mapping); unsigned long machine_to_phys_nr; @@ -69,10 +70,12 @@ __read_mostly int xen_have_vector_callback; EXPORT_SYMBOL_GPL(xen_have_vector_callback); /* - * NB: needs to live in .data because it's used by xen_prepare_pvh which runs - * before clearing the bss. + * NB: These need to live in .data or alike because they're used by + * xen_prepare_pvh() which runs before clearing the bss. */ -uint32_t xen_start_flags __section(".data") = 0; +enum xen_domain_type __ro_after_init xen_domain_type = XEN_NATIVE; +EXPORT_SYMBOL_GPL(xen_domain_type); +uint32_t __ro_after_init xen_start_flags; EXPORT_SYMBOL(xen_start_flags); /* @@ -258,6 +261,45 @@ int xen_vcpu_setup(int cpu) return ((per_cpu(xen_vcpu, cpu) == NULL) ? -ENODEV : 0); } +void __init xen_banner(void) +{ + unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL); + struct xen_extraversion extra; + + HYPERVISOR_xen_version(XENVER_extraversion, &extra); + + pr_info("Booting kernel on %s\n", pv_info.name); + pr_info("Xen version: %u.%u%s%s\n", + version >> 16, version & 0xffff, extra.extraversion, + xen_feature(XENFEAT_mmu_pt_update_preserve_ad) + ? " (preserve-AD)" : ""); +} + +/* Check if running on Xen version (major, minor) or later */ +bool xen_running_on_version_or_later(unsigned int major, unsigned int minor) +{ + unsigned int version; + + if (!xen_domain()) + return false; + + version = HYPERVISOR_xen_version(XENVER_version, NULL); + if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) || + ((version >> 16) > major)) + return true; + return false; +} + +void __init xen_add_preferred_consoles(void) +{ + add_preferred_console("xenboot", 0, NULL); + if (!boot_params.screen_info.orig_video_isVGA) + add_preferred_console("tty", 0, NULL); + add_preferred_console("hvc", 0, NULL); + if (boot_params.screen_info.orig_video_isVGA) + add_preferred_console("tty", 0, NULL); +} + void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 6e0d0754f94f..a7b7d674f500 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -28,7 +28,6 @@ #include <linux/mm.h> #include <linux/page-flags.h> #include <linux/highmem.h> -#include <linux/console.h> #include <linux/pci.h> #include <linux/gfp.h> #include <linux/edd.h> @@ -109,17 +108,6 @@ struct tls_descs { */ static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); -static void __init xen_banner(void) -{ - unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL); - struct xen_extraversion extra; - HYPERVISOR_xen_version(XENVER_extraversion, &extra); - - pr_info("Booting paravirtualized kernel on %s\n", pv_info.name); - pr_info("Xen version: %d.%d%s (preserve-AD)\n", - version >> 16, version & 0xffff, extra.extraversion); -} - static void __init xen_pv_init_platform(void) { populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP)); @@ -142,22 +130,6 @@ static void __init xen_pv_guest_late_init(void) #endif } -/* Check if running on Xen version (major, minor) or later */ -bool -xen_running_on_version_or_later(unsigned int major, unsigned int minor) -{ - unsigned int version; - - if (!xen_domain()) - return false; - - version = HYPERVISOR_xen_version(XENVER_version, NULL); - if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) || - ((version >> 16) > major)) - return true; - return false; -} - static __read_mostly unsigned int cpuid_leaf5_ecx_val; static __read_mostly unsigned int cpuid_leaf5_edx_val; @@ -1364,7 +1336,6 @@ asmlinkage __visible void __init xen_start_kernel(void) boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN; if (!xen_initial_domain()) { - add_preferred_console("xenboot", 0, NULL); if (pci_xen) x86_init.pci.arch_init = pci_xen_init; x86_platform.set_legacy_features = @@ -1409,11 +1380,7 @@ asmlinkage __visible void __init xen_start_kernel(void) #endif } - if (!boot_params.screen_info.orig_video_isVGA) - add_preferred_console("tty", 0, NULL); - add_preferred_console("hvc", 0, NULL); - if (boot_params.screen_info.orig_video_isVGA) - add_preferred_console("tty", 0, NULL); + xen_add_preferred_consoles(); #ifdef CONFIG_PCI /* PCI BIOS service won't work from a PV guest. */ diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 0d5e34b9e6f9..bcae606bbc5c 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/acpi.h> +#include <linux/export.h> #include <xen/hvc-console.h> @@ -18,10 +19,11 @@ /* * PVH variables. * - * The variable xen_pvh needs to live in the data segment since it is used + * The variable xen_pvh needs to live in a data segment since it is used * after startup_{32|64} is invoked, which will clear the .bss segment. */ -bool xen_pvh __section(".data") = 0; +bool __ro_after_init xen_pvh; +EXPORT_SYMBOL_GPL(xen_pvh); void __init xen_pvh_init(struct boot_params *boot_params) { @@ -36,6 +38,10 @@ void __init xen_pvh_init(struct boot_params *boot_params) pfn = __pa(hypercall_page); wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); + if (xen_initial_domain()) + x86_init.oem.arch_setup = xen_add_preferred_consoles; + x86_init.oem.banner = xen_banner; + xen_efi_init(boot_params); } diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 8d751939c6f3..3359c23573c5 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2398,7 +2398,7 @@ static int remap_area_pfn_pte_fn(pte_t *ptep, unsigned long addr, void *data) int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages) + unsigned int domid, bool no_translate) { int err = 0; struct remap_data rmd; diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 8d7ec49a35fb..8bc8b72a205d 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -51,6 +51,7 @@ void __init xen_remap_memory(void); phys_addr_t __init xen_find_free_area(phys_addr_t size); char * __init xen_memory_setup(void); void __init xen_arch_setup(void); +void xen_banner(void); void xen_enable_sysenter(void); void xen_enable_syscall(void); void xen_vcpu_restore(void); @@ -109,7 +110,7 @@ static inline void xen_uninit_lock_cpu(int cpu) struct dom0_vga_console_info; -#ifdef CONFIG_XEN_DOM0 +#ifdef CONFIG_XEN_PV_DOM0 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size); #else static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, @@ -118,6 +119,8 @@ static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, } #endif +void xen_add_preferred_consoles(void); + void __init xen_init_apic(void); #ifdef CONFIG_XEN_EFI diff --git a/arch/xtensa/include/asm/kmem_layout.h b/arch/xtensa/include/asm/kmem_layout.h index 7cbf68ca7106..6fc05cba61a2 100644 --- a/arch/xtensa/include/asm/kmem_layout.h +++ b/arch/xtensa/include/asm/kmem_layout.h @@ -78,7 +78,7 @@ #endif #define XCHAL_KIO_SIZE 0x10000000 -#if (!XCHAL_HAVE_PTP_MMU || XCHAL_HAVE_SPANNING_WAY) && defined(CONFIG_OF) +#if (!XCHAL_HAVE_PTP_MMU || XCHAL_HAVE_SPANNING_WAY) && defined(CONFIG_USE_OF) #define XCHAL_KIO_PADDR xtensa_get_kio_paddr() #ifndef __ASSEMBLY__ extern unsigned long xtensa_kio_paddr; diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c index 764b54bef701..15051a8a1539 100644 --- a/arch/xtensa/kernel/irq.c +++ b/arch/xtensa/kernel/irq.c @@ -143,7 +143,7 @@ unsigned xtensa_get_ext_irq_no(unsigned irq) void __init init_IRQ(void) { -#ifdef CONFIG_OF +#ifdef CONFIG_USE_OF irqchip_init(); #else #ifdef CONFIG_HAVE_SMP diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index ed184106e4cf..ee9082a142fe 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -63,7 +63,7 @@ extern unsigned long initrd_end; extern int initrd_below_start_ok; #endif -#ifdef CONFIG_OF +#ifdef CONFIG_USE_OF void *dtb_start = __dtb_start; #endif @@ -125,7 +125,7 @@ __tagtable(BP_TAG_INITRD, parse_tag_initrd); #endif /* CONFIG_BLK_DEV_INITRD */ -#ifdef CONFIG_OF +#ifdef CONFIG_USE_OF static int __init parse_tag_fdt(const bp_tag_t *tag) { @@ -135,7 +135,7 @@ static int __init parse_tag_fdt(const bp_tag_t *tag) __tagtable(BP_TAG_FDT, parse_tag_fdt); -#endif /* CONFIG_OF */ +#endif /* CONFIG_USE_OF */ static int __init parse_tag_cmdline(const bp_tag_t* tag) { @@ -183,7 +183,7 @@ static int __init parse_bootparam(const bp_tag_t *tag) } #endif -#ifdef CONFIG_OF +#ifdef CONFIG_USE_OF #if !XCHAL_HAVE_PTP_MMU || XCHAL_HAVE_SPANNING_WAY unsigned long xtensa_kio_paddr = XCHAL_KIO_DEFAULT_PADDR; @@ -232,7 +232,7 @@ void __init early_init_devtree(void *params) strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); } -#endif /* CONFIG_OF */ +#endif /* CONFIG_USE_OF */ /* * Initialize architecture. (Early stage) @@ -253,7 +253,7 @@ void __init init_arch(bp_tag_t *bp_start) if (bp_start) parse_bootparam(bp_start); -#ifdef CONFIG_OF +#ifdef CONFIG_USE_OF early_init_devtree(dtb_start); #endif diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c index 7e4d97dc8bd8..38acda4f04e8 100644 --- a/arch/xtensa/mm/mmu.c +++ b/arch/xtensa/mm/mmu.c @@ -101,7 +101,7 @@ void init_mmu(void) void init_kio(void) { -#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF) +#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_USE_OF) /* * Update the IO area mapping in case xtensa_kio_paddr has changed */ diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c index 4f7d6142d41f..538e6748e85a 100644 --- a/arch/xtensa/platforms/xtfpga/setup.c +++ b/arch/xtensa/platforms/xtfpga/setup.c @@ -51,8 +51,12 @@ void platform_power_off(void) void platform_restart(void) { - /* Flush and reset the mmu, simulate a processor reset, and - * jump to the reset vector. */ + /* Try software reset first. */ + WRITE_ONCE(*(u32 *)XTFPGA_SWRST_VADDR, 0xdead); + + /* If software reset did not work, flush and reset the mmu, + * simulate a processor reset, and jump to the reset vector. + */ cpu_reset(); /* control never gets here */ } @@ -66,7 +70,7 @@ void __init platform_calibrate_ccount(void) #endif -#ifdef CONFIG_OF +#ifdef CONFIG_USE_OF static void __init xtfpga_clk_setup(struct device_node *np) { @@ -284,4 +288,4 @@ static int __init xtavnet_init(void) */ arch_initcall(xtavnet_init); -#endif /* CONFIG_OF */ +#endif /* CONFIG_USE_OF */ diff --git a/block/bdev.c b/block/bdev.c index cf2780cb44a7..485a258b0ab3 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -490,7 +490,6 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) bdev = I_BDEV(inode); mutex_init(&bdev->bd_fsfreeze_mutex); spin_lock_init(&bdev->bd_size_lock); - bdev->bd_disk = disk; bdev->bd_partno = partno; bdev->bd_inode = inode; bdev->bd_stats = alloc_percpu(struct disk_stats); @@ -498,6 +497,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) iput(inode); return NULL; } + bdev->bd_disk = disk; return bdev; } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index dd13c2bbc29c..480e1a134859 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2662,15 +2662,6 @@ bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) * are likely to increase the throughput. */ bfqq->new_bfqq = new_bfqq; - /* - * The above assignment schedules the following redirections: - * each time some I/O for bfqq arrives, the process that - * generated that I/O is disassociated from bfqq and - * associated with new_bfqq. Here we increases new_bfqq->ref - * in advance, adding the number of processes that are - * expected to be associated with new_bfqq as they happen to - * issue I/O. - */ new_bfqq->ref += process_refs; return new_bfqq; } @@ -2733,10 +2724,6 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, { struct bfq_queue *in_service_bfqq, *new_bfqq; - /* if a merge has already been setup, then proceed with that first */ - if (bfqq->new_bfqq) - return bfqq->new_bfqq; - /* * Check delayed stable merge for rotational or non-queueing * devs. For this branch to be executed, bfqq must not be @@ -2838,6 +2825,9 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, if (bfq_too_late_for_merging(bfqq)) return NULL; + if (bfqq->new_bfqq) + return bfqq->new_bfqq; + if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq)) return NULL; diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 4b66d2776eda..3b38d15723de 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -129,6 +129,7 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(PCI_P2PDMA), QUEUE_FLAG_NAME(ZONE_RESETALL), QUEUE_FLAG_NAME(RQ_ALLOC_TIME), + QUEUE_FLAG_NAME(HCTX_ACTIVE), QUEUE_FLAG_NAME(NOWAIT), }; #undef QUEUE_FLAG_NAME diff --git a/block/genhd.c b/block/genhd.c index 7b6e5e1cf956..496e8458c357 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1268,6 +1268,7 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, out_destroy_part_tbl: xa_destroy(&disk->part_tbl); + disk->part0->bd_disk = NULL; iput(disk->part0->bd_inode); out_free_bdi: bdi_put(disk->bdi); diff --git a/drivers/Kconfig b/drivers/Kconfig index 30d2db37cc87..0d399ddaa185 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -17,6 +17,8 @@ source "drivers/bus/Kconfig" source "drivers/connector/Kconfig" +source "drivers/firmware/Kconfig" + source "drivers/gnss/Kconfig" source "drivers/mtd/Kconfig" diff --git a/drivers/acpi/arm64/gtdt.c b/drivers/acpi/arm64/gtdt.c index 0a0a982f9c28..c0e77c1c8e09 100644 --- a/drivers/acpi/arm64/gtdt.c +++ b/drivers/acpi/arm64/gtdt.c @@ -36,7 +36,7 @@ struct acpi_gtdt_descriptor { static struct acpi_gtdt_descriptor acpi_gtdt_desc __initdata; -static inline void *next_platform_timer(void *platform_timer) +static inline __init void *next_platform_timer(void *platform_timer) { struct acpi_gtdt_header *gh = platform_timer; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index a3ef6cce644c..7dd80acf92c7 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3007,6 +3007,18 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, ndr_desc->target_node = NUMA_NO_NODE; } + /* Fallback to address based numa information if node lookup failed */ + if (ndr_desc->numa_node == NUMA_NO_NODE) { + ndr_desc->numa_node = memory_add_physaddr_to_nid(spa->address); + dev_info(acpi_desc->dev, "changing numa node from %d to %d for nfit region [%pa-%pa]", + NUMA_NO_NODE, ndr_desc->numa_node, &res.start, &res.end); + } + if (ndr_desc->target_node == NUMA_NO_NODE) { + ndr_desc->target_node = phys_to_target_node(spa->address); + dev_info(acpi_desc->dev, "changing target node from %d to %d for nfit region [%pa-%pa]", + NUMA_NO_NODE, ndr_desc->numa_node, &res.start, &res.end); + } + /* * Persistence domain bits are hierarchical, if * ACPI_NFIT_CAPABILITY_CACHE_FLUSH is set then diff --git a/drivers/base/core.c b/drivers/base/core.c index e65dd803a453..15986cc2fe5e 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -95,6 +95,8 @@ int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup) list_add(&link->s_hook, &sup->consumers); list_add(&link->c_hook, &con->suppliers); + pr_debug("%pfwP Linked as a fwnode consumer to %pfwP\n", + con, sup); out: mutex_unlock(&fwnode_link_lock); @@ -102,6 +104,21 @@ out: } /** + * __fwnode_link_del - Delete a link between two fwnode_handles. + * @link: the fwnode_link to be deleted + * + * The fwnode_link_lock needs to be held when this function is called. + */ +static void __fwnode_link_del(struct fwnode_link *link) +{ + pr_debug("%pfwP Dropping the fwnode link to %pfwP\n", + link->consumer, link->supplier); + list_del(&link->s_hook); + list_del(&link->c_hook); + kfree(link); +} + +/** * fwnode_links_purge_suppliers - Delete all supplier links of fwnode_handle. * @fwnode: fwnode whose supplier links need to be deleted * @@ -112,11 +129,8 @@ static void fwnode_links_purge_suppliers(struct fwnode_handle *fwnode) struct fwnode_link *link, *tmp; mutex_lock(&fwnode_link_lock); - list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) { - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); - } + list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) + __fwnode_link_del(link); mutex_unlock(&fwnode_link_lock); } @@ -131,11 +145,8 @@ static void fwnode_links_purge_consumers(struct fwnode_handle *fwnode) struct fwnode_link *link, *tmp; mutex_lock(&fwnode_link_lock); - list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) { - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); - } + list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) + __fwnode_link_del(link); mutex_unlock(&fwnode_link_lock); } @@ -975,6 +986,7 @@ int device_links_check_suppliers(struct device *dev) { struct device_link *link; int ret = 0; + struct fwnode_handle *sup_fw; /* * Device waiting for supplier to become available is not allowed to @@ -983,10 +995,11 @@ int device_links_check_suppliers(struct device *dev) mutex_lock(&fwnode_link_lock); if (dev->fwnode && !list_empty(&dev->fwnode->suppliers) && !fw_devlink_is_permissive()) { - dev_dbg(dev, "probe deferral - wait for supplier %pfwP\n", - list_first_entry(&dev->fwnode->suppliers, - struct fwnode_link, - c_hook)->supplier); + sup_fw = list_first_entry(&dev->fwnode->suppliers, + struct fwnode_link, + c_hook)->supplier; + dev_err_probe(dev, -EPROBE_DEFER, "wait for supplier %pfwP\n", + sup_fw); mutex_unlock(&fwnode_link_lock); return -EPROBE_DEFER; } @@ -1001,8 +1014,9 @@ int device_links_check_suppliers(struct device *dev) if (link->status != DL_STATE_AVAILABLE && !(link->flags & DL_FLAG_SYNC_STATE_ONLY)) { device_links_missing_supplier(dev); - dev_dbg(dev, "probe deferral - supplier %s not ready\n", - dev_name(link->supplier)); + dev_err_probe(dev, -EPROBE_DEFER, + "supplier %s not ready\n", + dev_name(link->supplier)); ret = -EPROBE_DEFER; break; } @@ -1722,6 +1736,25 @@ static int fw_devlink_create_devlink(struct device *con, struct device *sup_dev; int ret = 0; + /* + * In some cases, a device P might also be a supplier to its child node + * C. However, this would defer the probe of C until the probe of P + * completes successfully. This is perfectly fine in the device driver + * model. device_add() doesn't guarantee probe completion of the device + * by the time it returns. + * + * However, there are a few drivers that assume C will finish probing + * as soon as it's added and before P finishes probing. So, we provide + * a flag to let fw_devlink know not to delay the probe of C until the + * probe of P completes successfully. + * + * When such a flag is set, we can't create device links where P is the + * supplier of C as that would delay the probe of C. + */ + if (sup_handle->flags & FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD && + fwnode_is_ancestor_of(sup_handle, con->fwnode)) + return -EINVAL; + sup_dev = get_dev_from_fwnode(sup_handle); if (sup_dev) { /* @@ -1772,14 +1805,21 @@ static int fw_devlink_create_devlink(struct device *con, * be broken by applying logic. Check for these types of cycles and * break them so that devices in the cycle probe properly. * - * If the supplier's parent is dependent on the consumer, then - * the consumer-supplier dependency is a false dependency. So, - * treat it as an invalid link. + * If the supplier's parent is dependent on the consumer, then the + * consumer and supplier have a cyclic dependency. Since fw_devlink + * can't tell which of the inferred dependencies are incorrect, don't + * enforce probe ordering between any of the devices in this cyclic + * dependency. Do this by relaxing all the fw_devlink device links in + * this cycle and by treating the fwnode link between the consumer and + * the supplier as an invalid dependency. */ sup_dev = fwnode_get_next_parent_dev(sup_handle); if (sup_dev && device_is_dependent(con, sup_dev)) { - dev_dbg(con, "Not linking to %pfwP - False link\n", - sup_handle); + dev_info(con, "Fixing up cyclic dependency with %pfwP (%s)\n", + sup_handle, dev_name(sup_dev)); + device_links_write_lock(); + fw_devlink_relax_cycle(con, sup_dev); + device_links_write_unlock(); ret = -EINVAL; } else { /* @@ -1858,9 +1898,7 @@ static void __fw_devlink_link_to_consumers(struct device *dev) if (!own_link || ret == -EAGAIN) continue; - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); + __fwnode_link_del(link); } } @@ -1912,9 +1950,7 @@ static void __fw_devlink_link_to_suppliers(struct device *dev, if (!own_link || ret == -EAGAIN) continue; - list_del(&link->s_hook); - list_del(&link->c_hook); - kfree(link); + __fwnode_link_del(link); /* If no device link was created, nothing more to do. */ if (ret) diff --git a/drivers/base/test/Makefile b/drivers/base/test/Makefile index 64b2f3d744d5..7f76fee6f989 100644 --- a/drivers/base/test/Makefile +++ b/drivers/base/test/Makefile @@ -2,4 +2,4 @@ obj-$(CONFIG_TEST_ASYNC_DRIVER_PROBE) += test_async_driver_probe.o obj-$(CONFIG_DRIVER_PE_KUNIT_TEST) += property-entry-test.o -CFLAGS_REMOVE_property-entry-test.o += -fplugin-arg-structleak_plugin-byref -fplugin-arg-structleak_plugin-byref-all +CFLAGS_property-entry-test.o += $(DISABLE_STRUCTLEAK_PLUGIN) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 5170a630778d..1183f7872b71 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -97,13 +97,18 @@ struct nbd_config { atomic_t recv_threads; wait_queue_head_t recv_wq; - loff_t blksize; + unsigned int blksize_bits; loff_t bytesize; #if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbg_dir; #endif }; +static inline unsigned int nbd_blksize(struct nbd_config *config) +{ + return 1u << config->blksize_bits; +} + struct nbd_device { struct blk_mq_tag_set tag_set; @@ -146,7 +151,7 @@ static struct dentry *nbd_dbg_dir; #define NBD_MAGIC 0x68797548 -#define NBD_DEF_BLKSIZE 1024 +#define NBD_DEF_BLKSIZE_BITS 10 static unsigned int nbds_max = 16; static int max_part = 16; @@ -317,12 +322,12 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize) { if (!blksize) - blksize = NBD_DEF_BLKSIZE; + blksize = 1u << NBD_DEF_BLKSIZE_BITS; if (blksize < 512 || blksize > PAGE_SIZE || !is_power_of_2(blksize)) return -EINVAL; nbd->config->bytesize = bytesize; - nbd->config->blksize = blksize; + nbd->config->blksize_bits = __ffs(blksize); if (!nbd->task_recv) return 0; @@ -1337,7 +1342,7 @@ static int nbd_start_device(struct nbd_device *nbd) args->index = i; queue_work(nbd->recv_workq, &args->work); } - return nbd_set_size(nbd, config->bytesize, config->blksize); + return nbd_set_size(nbd, config->bytesize, nbd_blksize(config)); } static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev) @@ -1406,11 +1411,11 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, case NBD_SET_BLKSIZE: return nbd_set_size(nbd, config->bytesize, arg); case NBD_SET_SIZE: - return nbd_set_size(nbd, arg, config->blksize); + return nbd_set_size(nbd, arg, nbd_blksize(config)); case NBD_SET_SIZE_BLOCKS: - if (check_mul_overflow((loff_t)arg, config->blksize, &bytesize)) + if (check_shl_overflow(arg, config->blksize_bits, &bytesize)) return -EINVAL; - return nbd_set_size(nbd, bytesize, config->blksize); + return nbd_set_size(nbd, bytesize, nbd_blksize(config)); case NBD_SET_TIMEOUT: nbd_set_cmd_timeout(nbd, arg); return 0; @@ -1476,7 +1481,7 @@ static struct nbd_config *nbd_alloc_config(void) atomic_set(&config->recv_threads, 0); init_waitqueue_head(&config->recv_wq); init_waitqueue_head(&config->conn_wait); - config->blksize = NBD_DEF_BLKSIZE; + config->blksize_bits = NBD_DEF_BLKSIZE_BITS; atomic_set(&config->live_connections, 0); try_module_get(THIS_MODULE); return config; @@ -1604,7 +1609,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd) debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_fops); debugfs_create_u64("size_bytes", 0444, dir, &config->bytesize); debugfs_create_u32("timeout", 0444, dir, &nbd->tag_set.timeout); - debugfs_create_u64("blocksize", 0444, dir, &config->blksize); + debugfs_create_u32("blocksize_bits", 0444, dir, &config->blksize_bits); debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_fops); return 0; @@ -1826,7 +1831,7 @@ nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = { static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd) { struct nbd_config *config = nbd->config; - u64 bsize = config->blksize; + u64 bsize = nbd_blksize(config); u64 bytes = config->bytesize; if (info->attrs[NBD_ATTR_SIZE_BYTES]) @@ -1835,7 +1840,7 @@ static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd) if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) bsize = nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]); - if (bytes != config->bytesize || bsize != config->blksize) + if (bytes != config->bytesize || bsize != nbd_blksize(config)) return nbd_set_size(nbd, bytes, bsize); return 0; } diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index a51c2a8feed9..6a8b7fb5be58 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1464,6 +1464,9 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { /* Quirks that need to be set based on detected module */ SYSC_QUIRK("aess", 0, 0, 0x10, -ENODEV, 0x40000000, 0xffffffff, SYSC_MODULE_QUIRK_AESS), + /* Errata i893 handling for dra7 dcan1 and 2 */ + SYSC_QUIRK("dcan", 0x4ae3c000, 0x20, -ENODEV, -ENODEV, 0xa3170504, 0xffffffff, + SYSC_QUIRK_CLKDM_NOAUTO), SYSC_QUIRK("dcan", 0x48480000, 0x20, -ENODEV, -ENODEV, 0xa3170504, 0xffffffff, SYSC_QUIRK_CLKDM_NOAUTO), SYSC_QUIRK("dss", 0x4832a000, 0, 0x10, 0x14, 0x00000020, 0xffffffff, @@ -2954,6 +2957,7 @@ static int sysc_init_soc(struct sysc *ddata) break; case SOC_AM3: sysc_add_disabled(0x48310000); /* rng */ + break; default: break; } diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 220a58cf0a44..cda7d7162cbb 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -203,10 +203,7 @@ config INTEL_STRATIX10_RSU Say Y here if you want Intel RSU support. config QCOM_SCM - tristate "Qcom SCM driver" - depends on ARM || ARM64 - depends on HAVE_ARM_SMCCC - select RESET_CONTROLLER + tristate config QCOM_SCM_DOWNLOAD_MODE_DEFAULT bool "Qualcomm download mode enabled by default" diff --git a/drivers/firmware/arm_scmi/Kconfig b/drivers/firmware/arm_scmi/Kconfig index 7f4d2435503b..3d7081e84853 100644 --- a/drivers/firmware/arm_scmi/Kconfig +++ b/drivers/firmware/arm_scmi/Kconfig @@ -68,7 +68,7 @@ config ARM_SCMI_TRANSPORT_SMC config ARM_SCMI_TRANSPORT_VIRTIO bool "SCMI transport based on VirtIO" - depends on VIRTIO + depends on VIRTIO=y || VIRTIO=ARM_SCMI_PROTOCOL select ARM_SCMI_HAVE_TRANSPORT select ARM_SCMI_HAVE_MSG help diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c index 224577f86928..11e8efb71375 100644 --- a/drivers/firmware/arm_scmi/virtio.c +++ b/drivers/firmware/arm_scmi/virtio.c @@ -110,18 +110,16 @@ static void scmi_finalize_message(struct scmi_vio_channel *vioch, if (vioch->is_rx) { scmi_vio_feed_vq_rx(vioch, msg); } else { - unsigned long flags; - - spin_lock_irqsave(&vioch->lock, flags); + /* Here IRQs are assumed to be already disabled by the caller */ + spin_lock(&vioch->lock); list_add(&msg->list, &vioch->free_list); - spin_unlock_irqrestore(&vioch->lock, flags); + spin_unlock(&vioch->lock); } } static void scmi_vio_complete_cb(struct virtqueue *vqueue) { unsigned long ready_flags; - unsigned long flags; unsigned int length; struct scmi_vio_channel *vioch; struct scmi_vio_msg *msg; @@ -140,7 +138,8 @@ static void scmi_vio_complete_cb(struct virtqueue *vqueue) goto unlock_ready_out; } - spin_lock_irqsave(&vioch->lock, flags); + /* IRQs already disabled here no need to irqsave */ + spin_lock(&vioch->lock); if (cb_enabled) { virtqueue_disable_cb(vqueue); cb_enabled = false; @@ -151,7 +150,7 @@ static void scmi_vio_complete_cb(struct virtqueue *vqueue) goto unlock_out; cb_enabled = true; } - spin_unlock_irqrestore(&vioch->lock, flags); + spin_unlock(&vioch->lock); if (msg) { msg->rx_len = length; @@ -161,11 +160,18 @@ static void scmi_vio_complete_cb(struct virtqueue *vqueue) scmi_finalize_message(vioch, msg); } + /* + * Release ready_lock and re-enable IRQs between loop iterations + * to allow virtio_chan_free() to possibly kick in and set the + * flag vioch->ready to false even in between processing of + * messages, so as to force outstanding messages to be ignored + * when system is shutting down. + */ spin_unlock_irqrestore(&vioch->ready_lock, ready_flags); } unlock_out: - spin_unlock_irqrestore(&vioch->lock, flags); + spin_unlock(&vioch->lock); unlock_ready_out: spin_unlock_irqrestore(&vioch->ready_lock, ready_flags); } @@ -384,8 +390,11 @@ static int scmi_vio_probe(struct virtio_device *vdev) struct virtqueue *vqs[VIRTIO_SCMI_VQ_MAX_CNT]; /* Only one SCMI VirtiO device allowed */ - if (scmi_vdev) - return -EINVAL; + if (scmi_vdev) { + dev_err(dev, + "One SCMI Virtio device was already initialized: only one allowed.\n"); + return -EBUSY; + } have_vq_rx = scmi_vio_have_vq_rx(vdev); vq_cnt = have_vq_rx ? VIRTIO_SCMI_VQ_MAX_CNT : 1; @@ -428,16 +437,25 @@ static int scmi_vio_probe(struct virtio_device *vdev) } vdev->priv = channels; - scmi_vdev = vdev; + /* Ensure initialized scmi_vdev is visible */ + smp_store_mb(scmi_vdev, vdev); return 0; } static void scmi_vio_remove(struct virtio_device *vdev) { + /* + * Once we get here, virtio_chan_free() will have already been called by + * the SCMI core for any existing channel and, as a consequence, all the + * virtio channels will have been already marked NOT ready, causing any + * outstanding message on any vqueue to be ignored by complete_cb: now + * we can just stop processing buffers and destroy the vqueues. + */ vdev->config->reset(vdev); vdev->config->del_vqs(vdev); - scmi_vdev = NULL; + /* Ensure scmi_vdev is visible as NULL */ + smp_store_mb(scmi_vdev, NULL); } static int scmi_vio_validate(struct virtio_device *vdev) @@ -476,7 +494,7 @@ static int __init virtio_scmi_init(void) return register_virtio_driver(&virtio_scmi_driver); } -static void __exit virtio_scmi_exit(void) +static void virtio_scmi_exit(void) { unregister_virtio_driver(&virtio_scmi_driver); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d356e329e6f8..269437b01328 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1087,6 +1087,7 @@ struct amdgpu_device { bool no_hw_access; struct pci_saved_state *pci_state; + pci_channel_state_t pci_channel_state; struct amdgpu_reset_control *reset_cntl; }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 2d6b2d77b738..054c1a224def 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -563,6 +563,7 @@ kfd_mem_dmaunmap_userptr(struct kgd_mem *mem, dma_unmap_sgtable(adev->dev, ttm->sg, direction, 0); sg_free_table(ttm->sg); + kfree(ttm->sg); ttm->sg = NULL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index ab3794c42d36..af9bdf16eefd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2394,10 +2394,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (r) goto init_failed; - r = amdgpu_amdkfd_resume_iommu(adev); - if (r) - goto init_failed; - r = amdgpu_device_ip_hw_init_phase1(adev); if (r) goto init_failed; @@ -2436,6 +2432,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) if (!adev->gmc.xgmi.pending_reset) amdgpu_amdkfd_device_init(adev); + r = amdgpu_amdkfd_resume_iommu(adev); + if (r) + goto init_failed; + amdgpu_fru_get_product_info(adev); init_failed: @@ -5399,6 +5399,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta return PCI_ERS_RESULT_DISCONNECT; } + adev->pci_channel_state = state; + switch (state) { case pci_channel_io_normal: return PCI_ERS_RESULT_CAN_RECOVER; @@ -5541,6 +5543,10 @@ void amdgpu_pci_resume(struct pci_dev *pdev) DRM_INFO("PCI error: resume callback!!\n"); + /* Only continue execution for the case of pci_channel_io_frozen */ + if (adev->pci_channel_state != pci_channel_io_frozen) + return; + for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = adev->rings[i]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 7a7316731911..dc50c05f23fc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -837,6 +837,28 @@ static int convert_tiling_flags_to_modifier(struct amdgpu_framebuffer *afb) return 0; } +/* Mirrors the is_displayable check in radeonsi's gfx6_compute_surface */ +static int check_tiling_flags_gfx6(struct amdgpu_framebuffer *afb) +{ + u64 micro_tile_mode; + + /* Zero swizzle mode means linear */ + if (AMDGPU_TILING_GET(afb->tiling_flags, SWIZZLE_MODE) == 0) + return 0; + + micro_tile_mode = AMDGPU_TILING_GET(afb->tiling_flags, MICRO_TILE_MODE); + switch (micro_tile_mode) { + case 0: /* DISPLAY */ + case 3: /* RENDER */ + return 0; + default: + drm_dbg_kms(afb->base.dev, + "Micro tile mode %llu not supported for scanout\n", + micro_tile_mode); + return -EINVAL; + } +} + static void get_block_dimensions(unsigned int block_log2, unsigned int cpp, unsigned int *width, unsigned int *height) { @@ -1103,6 +1125,7 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object *obj) { + struct amdgpu_device *adev = drm_to_adev(dev); int ret, i; /* @@ -1122,6 +1145,14 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev, if (ret) return ret; + if (!dev->mode_config.allow_fb_modifiers) { + drm_WARN_ONCE(dev, adev->family >= AMDGPU_FAMILY_AI, + "GFX9+ requires FB check based on format modifier\n"); + ret = check_tiling_flags_gfx6(rfb); + if (ret) + return ret; + } + if (dev->mode_config.allow_fb_modifiers && !(rfb->base.flags & DRM_MODE_FB_MODIFIERS)) { ret = convert_tiling_flags_to_modifier(rfb); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index e7f06bd0f0cd..1916ec84dd71 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -31,6 +31,8 @@ /* delay 0.1 second to enable gfx off feature */ #define GFX_OFF_DELAY_ENABLE msecs_to_jiffies(100) +#define GFX_OFF_NO_DELAY 0 + /* * GPU GFX IP block helpers function. */ @@ -558,6 +560,8 @@ int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev) void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable) { + unsigned long delay = GFX_OFF_DELAY_ENABLE; + if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) return; @@ -573,8 +577,14 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable) adev->gfx.gfx_off_req_count--; - if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state) - schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE); + if (adev->gfx.gfx_off_req_count == 0 && + !adev->gfx.gfx_off_state) { + /* If going to s2idle, no need to wait */ + if (adev->in_s0ix) + delay = GFX_OFF_NO_DELAY; + schedule_delayed_work(&adev->gfx.gfx_off_delay_work, + delay); + } } else { if (adev->gfx.gfx_off_req_count == 0) { cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 603c259b073b..025184a556ee 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3599,7 +3599,7 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring) /* set static priority for a queue/ring */ gfx_v9_0_mqd_set_priority(ring, mqd); - mqd->cp_hqd_quantum = RREG32(mmCP_HQD_QUANTUM); + mqd->cp_hqd_quantum = RREG32_SOC15(GC, 0, mmCP_HQD_QUANTUM); /* map_queues packet doesn't need activate the queue, * so only kiq need set this field. diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 41c3a0d70b7c..e47104a1f559 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -1098,6 +1098,8 @@ static int gmc_v10_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v10_0_gart_disable(adev); + if (amdgpu_sriov_vf(adev)) { /* full access mode, so don't touch any GMC register */ DRM_DEBUG("For SRIOV client, shouldn't do anything.\n"); @@ -1106,7 +1108,6 @@ static int gmc_v10_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); - gmc_v10_0_gart_disable(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index d90c16a6b2b8..5551359d5dfd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1794,6 +1794,8 @@ static int gmc_v9_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v9_0_gart_disable(adev); + if (amdgpu_sriov_vf(adev)) { /* full access mode, so don't touch any GMC register */ DRM_DEBUG("For SRIOV client, shouldn't do anything.\n"); @@ -1802,7 +1804,6 @@ static int gmc_v9_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); - gmc_v9_0_gart_disable(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 779f5c911e11..e32efcfb0c8b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -868,6 +868,12 @@ static int sdma_v5_2_start(struct amdgpu_device *adev) msleep(1000); } + /* TODO: check whether can submit a doorbell request to raise + * a doorbell fence to exit gfxoff. + */ + if (adev->in_s0ix) + amdgpu_gfx_off_ctrl(adev, false); + sdma_v5_2_soft_reset(adev); /* unhalt the MEs */ sdma_v5_2_enable(adev, true); @@ -876,6 +882,8 @@ static int sdma_v5_2_start(struct amdgpu_device *adev) /* start the gfx rings and rlc compute queues */ r = sdma_v5_2_gfx_resume(adev); + if (adev->in_s0ix) + amdgpu_gfx_off_ctrl(adev, true); if (r) return r; r = sdma_v5_2_rlc_resume(adev); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index c2a4d920da40..4a416231b24c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -1085,18 +1085,12 @@ static int kfd_resume(struct kfd_dev *kfd) int err = 0; err = kfd->dqm->ops.start(kfd->dqm); - if (err) { + if (err) dev_err(kfd_device, "Error starting queue manager for device %x:%x\n", kfd->pdev->vendor, kfd->pdev->device); - goto dqm_start_error; - } return err; - -dqm_start_error: - kfd_iommu_suspend(kfd); - return err; } static inline void kfd_queue_work(struct workqueue_struct *wq, diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 7dffc04a557e..127667e549c1 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -25,6 +25,8 @@ config DRM_AMD_DC_HDCP config DRM_AMD_DC_SI bool "AMD DC support for Southern Islands ASICs" + depends on DRM_AMDGPU_SI + depends on DRM_AMD_DC default n help Choose this option to enable new AMD DC support for SI asics 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 66c799f5c7cf..1ea31dcc7a8b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1115,6 +1115,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) init_data.asic_id.pci_revision_id = adev->pdev->revision; init_data.asic_id.hw_internal_rev = adev->external_rev_id; + init_data.asic_id.chip_id = adev->pdev->device; init_data.asic_id.vram_width = adev->gmc.vram_width; /* TODO: initialize init_data.asic_id.vram_type here!!!! */ @@ -1719,6 +1720,7 @@ static int dm_late_init(void *handle) linear_lut[i] = 0xFFFF * i / 15; params.set = 0; + params.backlight_ramping_override = false; params.backlight_ramping_start = 0xCCCC; params.backlight_ramping_reduction = 0xCCCCCCCC; params.backlight_lut_array_size = 16; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index f6dbc5a74757..6d655e158267 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -1306,12 +1306,6 @@ static void override_training_settings( { uint32_t lane; - /* Override link settings */ - if (link->preferred_link_setting.link_rate != LINK_RATE_UNKNOWN) - lt_settings->link_settings.link_rate = link->preferred_link_setting.link_rate; - if (link->preferred_link_setting.lane_count != LANE_COUNT_UNKNOWN) - lt_settings->link_settings.lane_count = link->preferred_link_setting.lane_count; - /* Override link spread */ if (!link->dp_ss_off && overrides->downspread != NULL) lt_settings->link_settings.link_spread = *overrides->downspread ? @@ -1826,14 +1820,13 @@ bool perform_link_training_with_retries( if (panel_mode == DP_PANEL_MODE_EDP) { struct cp_psp *cp_psp = &stream->ctx->cp_psp; - if (cp_psp && cp_psp->funcs.enable_assr) { - if (!cp_psp->funcs.enable_assr(cp_psp->handle, link)) { - /* since eDP implies ASSR on, change panel - * mode to disable ASSR - */ - panel_mode = DP_PANEL_MODE_DEFAULT; - } - } + if (cp_psp && cp_psp->funcs.enable_assr) + /* ASSR is bound to fail with unsigned PSP + * verstage used during devlopment phase. + * Report and continue with eDP panel mode to + * perform eDP link training with right settings + */ + cp_psp->funcs.enable_assr(cp_psp->handle, link); } #endif diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h index d8b22618b79e..c337588231ff 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h @@ -118,6 +118,7 @@ struct dcn10_link_enc_registers { uint32_t RDPCSTX_PHY_CNTL4; uint32_t RDPCSTX_PHY_CNTL5; uint32_t RDPCSTX_PHY_CNTL6; + uint32_t RDPCSPIPE_PHY_CNTL6; uint32_t RDPCSTX_PHY_CNTL7; uint32_t RDPCSTX_PHY_CNTL8; uint32_t RDPCSTX_PHY_CNTL9; diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c index 90127c1f9e35..b0892443fbd5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c @@ -37,6 +37,7 @@ #include "link_enc_cfg.h" #include "dc_dmub_srv.h" +#include "dal_asic_id.h" #define CTX \ enc10->base.ctx @@ -62,6 +63,10 @@ #define AUX_REG_WRITE(reg_name, val) \ dm_write_reg(CTX, AUX_REG(reg_name), val) +#ifndef MIN +#define MIN(X, Y) ((X) < (Y) ? (X) : (Y)) +#endif + void dcn31_link_encoder_set_dio_phy_mux( struct link_encoder *enc, enum encoder_type_select sel, @@ -215,8 +220,8 @@ static const struct link_encoder_funcs dcn31_link_enc_funcs = { .fec_is_active = enc2_fec_is_active, .get_dig_frontend = dcn10_get_dig_frontend, .get_dig_mode = dcn10_get_dig_mode, - .is_in_alt_mode = dcn20_link_encoder_is_in_alt_mode, - .get_max_link_cap = dcn20_link_encoder_get_max_link_cap, + .is_in_alt_mode = dcn31_link_encoder_is_in_alt_mode, + .get_max_link_cap = dcn31_link_encoder_get_max_link_cap, .set_dio_phy_mux = dcn31_link_encoder_set_dio_phy_mux, }; @@ -404,3 +409,60 @@ void dcn31_link_encoder_disable_output( } } +bool dcn31_link_encoder_is_in_alt_mode(struct link_encoder *enc) +{ + struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); + uint32_t dp_alt_mode_disable; + bool is_usb_c_alt_mode = false; + + if (enc->features.flags.bits.DP_IS_USB_C) { + if (enc->ctx->asic_id.hw_internal_rev != YELLOW_CARP_B0) { + // [Note] no need to check hw_internal_rev once phy mux selection is ready + REG_GET(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, &dp_alt_mode_disable); + } else { + /* + * B0 phys use a new set of registers to check whether alt mode is disabled. + * if value == 1 alt mode is disabled, otherwise it is enabled. + */ + if ((enc10->base.transmitter == TRANSMITTER_UNIPHY_A) + || (enc10->base.transmitter == TRANSMITTER_UNIPHY_B) + || (enc10->base.transmitter == TRANSMITTER_UNIPHY_E)) { + REG_GET(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, &dp_alt_mode_disable); + } else { + // [Note] need to change TRANSMITTER_UNIPHY_C/D to F/G once phy mux selection is ready + REG_GET(RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, &dp_alt_mode_disable); + } + } + + is_usb_c_alt_mode = (dp_alt_mode_disable == 0); + } + + return is_usb_c_alt_mode; +} + +void dcn31_link_encoder_get_max_link_cap(struct link_encoder *enc, + struct dc_link_settings *link_settings) +{ + struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc); + uint32_t is_in_usb_c_dp4_mode = 0; + + dcn10_link_encoder_get_max_link_cap(enc, link_settings); + + /* in usb c dp2 mode, max lane count is 2 */ + if (enc->funcs->is_in_alt_mode && enc->funcs->is_in_alt_mode(enc)) { + if (enc->ctx->asic_id.hw_internal_rev != YELLOW_CARP_B0) { + // [Note] no need to check hw_internal_rev once phy mux selection is ready + REG_GET(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, &is_in_usb_c_dp4_mode); + } else { + if ((enc10->base.transmitter == TRANSMITTER_UNIPHY_A) + || (enc10->base.transmitter == TRANSMITTER_UNIPHY_B) + || (enc10->base.transmitter == TRANSMITTER_UNIPHY_E)) { + REG_GET(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, &is_in_usb_c_dp4_mode); + } else { + REG_GET(RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, &is_in_usb_c_dp4_mode); + } + } + if (!is_in_usb_c_dp4_mode) + link_settings->lane_count = MIN(LANE_COUNT_TWO, link_settings->lane_count); + } +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.h index 32d146312838..3454f1e7c1f1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.h @@ -69,6 +69,7 @@ SRI(RDPCSTX_PHY_CNTL4, RDPCSTX, id), \ SRI(RDPCSTX_PHY_CNTL5, RDPCSTX, id), \ SRI(RDPCSTX_PHY_CNTL6, RDPCSTX, id), \ + SRI(RDPCSPIPE_PHY_CNTL6, RDPCSPIPE, id), \ SRI(RDPCSTX_PHY_CNTL7, RDPCSTX, id), \ SRI(RDPCSTX_PHY_CNTL8, RDPCSTX, id), \ SRI(RDPCSTX_PHY_CNTL9, RDPCSTX, id), \ @@ -115,7 +116,9 @@ LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX2_MPLL_EN, mask_sh),\ LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX3_MPLL_EN, mask_sh),\ LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\ - LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh),\ + LE_SF(RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\ + LE_SF(RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh),\ + LE_SF(RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE_ACK, mask_sh),\ LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL7, RDPCS_PHY_DP_MPLLB_FRACN_QUOT, mask_sh),\ LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL7, RDPCS_PHY_DP_MPLLB_FRACN_DEN, mask_sh),\ LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL8, RDPCS_PHY_DP_MPLLB_SSC_PEAK, mask_sh),\ @@ -243,4 +246,13 @@ void dcn31_link_encoder_disable_output( struct link_encoder *enc, enum signal_type signal); +/* + * Check whether USB-C DP Alt mode is disabled + */ +bool dcn31_link_encoder_is_in_alt_mode( + struct link_encoder *enc); + +void dcn31_link_encoder_get_max_link_cap(struct link_encoder *enc, + struct dc_link_settings *link_settings); + #endif /* __DC_LINK_ENCODER__DCN31_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index a7702d3c75cd..0006bbac466c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -928,7 +928,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_dcc = DCC_ENABLE, .vsr_support = true, .performance_trace = false, - .max_downscale_src_width = 7680,/*upto 8K*/ + .max_downscale_src_width = 3840,/*upto 4K*/ .disable_pplib_wm_range = false, .scl_reset_length10 = true, .sanity_checks = false, @@ -1284,6 +1284,12 @@ static struct stream_encoder *dcn31_stream_encoder_create( if (!enc1 || !vpg || !afmt) return NULL; + if (ctx->asic_id.chip_family == FAMILY_YELLOW_CARP && + ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0) { + if ((eng_id == ENGINE_ID_DIGC) || (eng_id == ENGINE_ID_DIGD)) + eng_id = eng_id + 3; // For B0 only. C->F, D->G. + } + dcn30_dio_stream_encoder_construct(enc1, ctx, ctx->dc_bios, eng_id, vpg, afmt, &stream_enc_regs[eng_id], diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index 381c17caace1..5adc471bef57 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -227,7 +227,7 @@ enum { #define FAMILY_YELLOW_CARP 146 #define YELLOW_CARP_A0 0x01 -#define YELLOW_CARP_B0 0x02 // TODO: DCN31 - update with correct B0 ID +#define YELLOW_CARP_B0 0x1A #define YELLOW_CARP_UNKNOWN 0xFF #ifndef ASICREV_IS_YELLOW_CARP diff --git a/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_4_2_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_4_2_0_offset.h index 92caf8441d1e..01a56556cde1 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_4_2_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_4_2_0_offset.h @@ -11932,5 +11932,32 @@ #define ixDPCSSYS_CR4_RAWLANEX_DIG_PCS_XF_RX_OVRD_OUT_2 0xe0c7 #define ixDPCSSYS_CR4_RAWLANEX_DIG_PCS_XF_TX_OVRD_IN_2 0xe0c8 +//RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6 +#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT 0x10 +#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT 0x11 +#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT 0x12 +#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK 0x00010000L +#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK 0x00020000L +#define RDPCSPIPE0_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK 0x00040000L + +//RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6 +#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT 0x10 +#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT 0x11 +#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT 0x12 +#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK 0x00010000L +#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK 0x00020000L +#define RDPCSPIPE1_RDPCSPIPE_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK 0x00040000L + +//[Note] Hack. RDPCSPIPE only has 2 instances. +#define regRDPCSPIPE0_RDPCSPIPE_PHY_CNTL6 0x2d73 +#define regRDPCSPIPE0_RDPCSPIPE_PHY_CNTL6_BASE_IDX 2 +#define regRDPCSPIPE1_RDPCSPIPE_PHY_CNTL6 0x2e4b +#define regRDPCSPIPE1_RDPCSPIPE_PHY_CNTL6_BASE_IDX 2 +#define regRDPCSPIPE2_RDPCSPIPE_PHY_CNTL6 0x2d73 +#define regRDPCSPIPE2_RDPCSPIPE_PHY_CNTL6_BASE_IDX 2 +#define regRDPCSPIPE3_RDPCSPIPE_PHY_CNTL6 0x2e4b +#define regRDPCSPIPE3_RDPCSPIPE_PHY_CNTL6_BASE_IDX 2 +#define regRDPCSPIPE4_RDPCSPIPE_PHY_CNTL6 0x2d73 +#define regRDPCSPIPE4_RDPCSPIPE_PHY_CNTL6_BASE_IDX 2 #endif diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 9870c4e6af36..b5001db7a95c 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -793,7 +793,6 @@ static int exynos5433_decon_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct decon_context *ctx; - struct resource *res; int ret; int i; @@ -818,8 +817,7 @@ static int exynos5433_decon_probe(struct platform_device *pdev) ctx->clks[i] = clk; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctx->addr = devm_ioremap_resource(dev, res); + ctx->addr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->addr)) return PTR_ERR(ctx->addr); diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index e39fac889edc..8d137857818c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1738,7 +1738,6 @@ static const struct component_ops exynos_dsi_component_ops = { static int exynos_dsi_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct exynos_dsi *dsi; int ret, i; @@ -1789,8 +1788,7 @@ static int exynos_dsi_probe(struct platform_device *pdev) } } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - dsi->reg_base = devm_ioremap_resource(dev, res); + dsi->reg_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(dsi->reg_base)) return PTR_ERR(dsi->reg_base); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index a3c718148c45..ecfd82d0afb7 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -85,7 +85,6 @@ struct fimc_scaler { /* * A structure of fimc context. * - * @regs_res: register resources. * @regs: memory mapped io registers. * @lock: locking of operations. * @clocks: fimc clocks. @@ -103,7 +102,6 @@ struct fimc_context { struct exynos_drm_ipp_formats *formats; unsigned int num_formats; - struct resource *regs_res; void __iomem *regs; spinlock_t lock; struct clk *clocks[FIMC_CLKS_MAX]; @@ -1327,8 +1325,7 @@ static int fimc_probe(struct platform_device *pdev) ctx->num_formats = num_formats; /* resource memory */ - ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctx->regs = devm_ioremap_resource(dev, ctx->regs_res); + ctx->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->regs)) return PTR_ERR(ctx->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 700ca4fa6665..c735e53939d8 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -1202,9 +1202,7 @@ static int fimd_probe(struct platform_device *pdev) return PTR_ERR(ctx->lcd_clk); } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - - ctx->regs = devm_ioremap_resource(dev, res); + ctx->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->regs)) return PTR_ERR(ctx->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index b00230626c6a..471fd6c8135f 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -1449,7 +1449,6 @@ static const struct component_ops g2d_component_ops = { static int g2d_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct g2d_data *g2d; int ret; @@ -1491,9 +1490,7 @@ static int g2d_probe(struct platform_device *pdev) clear_bit(G2D_BIT_SUSPEND_RUNQUEUE, &g2d->flags); clear_bit(G2D_BIT_ENGINE_BUSY, &g2d->flags); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - - g2d->regs = devm_ioremap_resource(dev, res); + g2d->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(g2d->regs)) { ret = PTR_ERR(g2d->regs); goto err_put_clk; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 90d7bf906885..166a80262896 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -86,7 +86,6 @@ struct gsc_scaler { /* * A structure of gsc context. * - * @regs_res: register resources. * @regs: memory mapped io registers. * @gsc_clk: gsc gate clock. * @sc: scaler infomations. @@ -103,7 +102,6 @@ struct gsc_context { struct exynos_drm_ipp_formats *formats; unsigned int num_formats; - struct resource *regs_res; void __iomem *regs; const char **clk_names; struct clk *clocks[GSC_MAX_CLOCKS]; @@ -1272,9 +1270,7 @@ static int gsc_probe(struct platform_device *pdev) } } - /* resource memory */ - ctx->regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ctx->regs = devm_ioremap_resource(dev, ctx->regs_res); + ctx->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ctx->regs)) return PTR_ERR(ctx->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c index ee61be4cf152..dec7df35baa9 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c +++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c @@ -278,7 +278,6 @@ static const struct component_ops rotator_component_ops = { static int rotator_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *regs_res; struct rot_context *rot; const struct rot_variant *variant; int irq; @@ -292,8 +291,7 @@ static int rotator_probe(struct platform_device *pdev) rot->formats = variant->formats; rot->num_formats = variant->num_formats; rot->dev = dev; - regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - rot->regs = devm_ioremap_resource(dev, regs_res); + rot->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(rot->regs)) return PTR_ERR(rot->regs); diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c index f9ae5b038d59..3a7851b7dc66 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c +++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c @@ -485,7 +485,6 @@ static const struct component_ops scaler_component_ops = { static int scaler_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *regs_res; struct scaler_context *scaler; int irq; int ret, i; @@ -498,8 +497,7 @@ static int scaler_probe(struct platform_device *pdev) (struct scaler_data *)of_device_get_match_data(dev); scaler->dev = dev; - regs_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - scaler->regs = devm_ioremap_resource(dev, regs_res); + scaler->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(scaler->regs)) return PTR_ERR(scaler->regs); diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index c769dec576de..7655142a4651 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1957,7 +1957,6 @@ static int hdmi_probe(struct platform_device *pdev) struct hdmi_audio_infoframe *audio_infoframe; struct device *dev = &pdev->dev; struct hdmi_context *hdata; - struct resource *res; int ret; hdata = devm_kzalloc(dev, sizeof(struct hdmi_context), GFP_KERNEL); @@ -1979,8 +1978,7 @@ static int hdmi_probe(struct platform_device *pdev) return ret; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - hdata->regs = devm_ioremap_resource(dev, res); + hdata->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(hdata->regs)) { ret = PTR_ERR(hdata->regs); return ret; diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 43ec7fcd3f5d..a3eae3f3eadc 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1577,8 +1577,14 @@ static void gen11_dsi_sync_state(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc); - enum pipe pipe = intel_crtc->pipe; + struct intel_crtc *intel_crtc; + enum pipe pipe; + + if (!crtc_state) + return; + + intel_crtc = to_intel_crtc(crtc_state->uapi.crtc); + pipe = intel_crtc->pipe; /* wa verify 1409054076:icl,jsl,ehl */ if (DISPLAY_VER(dev_priv) == 11 && pipe == PIPE_B && diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c index 532237588511..4e0f96bf6158 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.c +++ b/drivers/gpu/drm/i915/display/intel_audio.c @@ -1308,8 +1308,9 @@ static void i915_audio_component_init(struct drm_i915_private *dev_priv) else aud_freq = aud_freq_init; - /* use BIOS provided value for TGL unless it is a known bad value */ - if (IS_TIGERLAKE(dev_priv) && aud_freq_init != AUD_FREQ_TGL_BROKEN) + /* use BIOS provided value for TGL and RKL unless it is a known bad value */ + if ((IS_TIGERLAKE(dev_priv) || IS_ROCKETLAKE(dev_priv)) && + aud_freq_init != AUD_FREQ_TGL_BROKEN) aud_freq = aud_freq_init; drm_dbg_kms(&dev_priv->drm, "use AUD_FREQ_CNTRL of 0x%x (init value 0x%x)\n", diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index e86e6ed2d3bf..fd71346aac7b 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -451,13 +451,23 @@ parse_lfp_backlight(struct drm_i915_private *i915, } i915->vbt.backlight.type = INTEL_BACKLIGHT_DISPLAY_DDI; - if (bdb->version >= 191 && - get_blocksize(backlight_data) >= sizeof(*backlight_data)) { - const struct lfp_backlight_control_method *method; + if (bdb->version >= 191) { + size_t exp_size; - method = &backlight_data->backlight_control[panel_type]; - i915->vbt.backlight.type = method->type; - i915->vbt.backlight.controller = method->controller; + if (bdb->version >= 236) + exp_size = sizeof(struct bdb_lfp_backlight_data); + else if (bdb->version >= 234) + exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_234; + else + exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_191; + + if (get_blocksize(backlight_data) >= exp_size) { + const struct lfp_backlight_control_method *method; + + method = &backlight_data->backlight_control[panel_type]; + i915->vbt.backlight.type = method->type; + i915->vbt.backlight.controller = method->controller; + } } i915->vbt.backlight.pwm_freq_hz = entry->pwm_freq_hz; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 9903a78df896..bd184325d0c7 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -3807,7 +3807,13 @@ void hsw_ddi_get_config(struct intel_encoder *encoder, static void intel_ddi_sync_state(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { - if (intel_crtc_has_dp_encoder(crtc_state)) + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + enum phy phy = intel_port_to_phy(i915, encoder->port); + + if (intel_phy_is_tc(i915, phy)) + intel_tc_port_sanitize(enc_to_dig_port(encoder)); + + if (crtc_state && intel_crtc_has_dp_encoder(crtc_state)) intel_dp_sync_state(encoder, crtc_state); } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 134a6acbd8fb..17f44ffea586 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -13082,18 +13082,16 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) readout_plane_state(dev_priv); for_each_intel_encoder(dev, encoder) { + struct intel_crtc_state *crtc_state = NULL; + pipe = 0; if (encoder->get_hw_state(encoder, &pipe)) { - struct intel_crtc_state *crtc_state; - crtc = intel_get_crtc_for_pipe(dev_priv, pipe); crtc_state = to_intel_crtc_state(crtc->base.state); encoder->base.crtc = &crtc->base; intel_encoder_get_config(encoder, crtc_state); - if (encoder->sync_state) - encoder->sync_state(encoder, crtc_state); /* read out to slave crtc as well for bigjoiner */ if (crtc_state->bigjoiner) { @@ -13108,6 +13106,9 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) encoder->base.crtc = NULL; } + if (encoder->sync_state) + encoder->sync_state(encoder, crtc_state); + drm_dbg_kms(&dev_priv->drm, "[ENCODER:%d:%s] hw state readout: %s, pipe %c\n", encoder->base.base.id, encoder->base.name, @@ -13390,17 +13391,6 @@ intel_modeset_setup_hw_state(struct drm_device *dev, intel_modeset_readout_hw_state(dev); /* HW state is read out, now we need to sanitize this mess. */ - - /* Sanitize the TypeC port mode upfront, encoders depend on this */ - for_each_intel_encoder(dev, encoder) { - enum phy phy = intel_port_to_phy(dev_priv, encoder->port); - - /* We need to sanitize only the MST primary port. */ - if (encoder->type != INTEL_OUTPUT_DP_MST && - intel_phy_is_tc(dev_priv, phy)) - intel_tc_port_sanitize(enc_to_dig_port(encoder)); - } - get_encoder_power_domains(dev_priv); if (HAS_PCH_IBX(dev_priv)) diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h index 330077c2e588..a2108a8f544d 100644 --- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h @@ -814,6 +814,11 @@ struct lfp_brightness_level { u16 reserved; } __packed; +#define EXP_BDB_LFP_BL_DATA_SIZE_REV_191 \ + offsetof(struct bdb_lfp_backlight_data, brightness_level) +#define EXP_BDB_LFP_BL_DATA_SIZE_REV_234 \ + offsetof(struct bdb_lfp_backlight_data, brightness_precision_bits) + struct bdb_lfp_backlight_data { u8 entry_size; struct lfp_backlight_data_entry data[16]; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c index e382b7f2353b..5ab136ffdeb2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c @@ -118,7 +118,7 @@ i915_gem_shrink(struct i915_gem_ww_ctx *ww, intel_wakeref_t wakeref = 0; unsigned long count = 0; unsigned long scanned = 0; - int err; + int err = 0; /* CHV + VTD workaround use stop_machine(); need to trylock vm->mutex */ bool trylock_vm = !ww && intel_vm_no_concurrent_access_wa(i915); @@ -242,12 +242,15 @@ skip: list_splice_tail(&still_in_list, phase->list); spin_unlock_irqrestore(&i915->mm.obj_lock, flags); if (err) - return err; + break; } if (shrink & I915_SHRINK_BOUND) intel_runtime_pm_put(&i915->runtime_pm, wakeref); + if (err) + return err; + if (nr_scanned) *nr_scanned += scanned; return count; diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 745e84c72c90..e866105dd174 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -362,8 +362,9 @@ static int __intel_context_active(struct i915_active *active) return 0; } -static int sw_fence_dummy_notify(struct i915_sw_fence *sf, - enum i915_sw_fence_notify state) +static int __i915_sw_fence_call +sw_fence_dummy_notify(struct i915_sw_fence *sf, + enum i915_sw_fence_notify state) { return NOTIFY_DONE; } diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 591a5224287e..0a03fbed9f9b 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -882,8 +882,6 @@ void intel_rps_park(struct intel_rps *rps) if (!intel_rps_is_enabled(rps)) return; - GEM_BUG_ON(atomic_read(&rps->num_waiters)); - if (!intel_rps_clear_active(rps)) return; diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h index 99e1fad5ca20..c9086a600bce 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_ctb_abi.h @@ -102,11 +102,11 @@ static_assert(sizeof(struct guc_ct_buffer_desc) == 64); * | +-------+--------------------------------------------------------------+ * | | 7:0 | NUM_DWORDS = length (in dwords) of the embedded HXG message | * +---+-------+--------------------------------------------------------------+ - * | 1 | 31:0 | +--------------------------------------------------------+ | - * +---+-------+ | | | - * |...| | | Embedded `HXG Message`_ | | - * +---+-------+ | | | - * | n | 31:0 | +--------------------------------------------------------+ | + * | 1 | 31:0 | | + * +---+-------+ | + * |...| | [Embedded `HXG Message`_] | + * +---+-------+ | + * | n | 31:0 | | * +---+-------+--------------------------------------------------------------+ */ diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h index bbf1ddb77434..9baa3cb07d13 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_communication_mmio_abi.h @@ -38,11 +38,11 @@ * +---+-------+--------------------------------------------------------------+ * | | Bits | Description | * +===+=======+==============================================================+ - * | 0 | 31:0 | +--------------------------------------------------------+ | - * +---+-------+ | | | - * |...| | | Embedded `HXG Message`_ | | - * +---+-------+ | | | - * | n | 31:0 | +--------------------------------------------------------+ | + * | 0 | 31:0 | | + * +---+-------+ | + * |...| | [Embedded `HXG Message`_] | + * +---+-------+ | + * | n | 31:0 | | * +---+-------+--------------------------------------------------------------+ */ diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index b56a8e37a3cd..1bb1be5c48c8 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -576,7 +576,7 @@ retry: /* No one is going to touch shadow bb from now on. */ i915_gem_object_flush_map(bb->obj); - i915_gem_object_unlock(bb->obj); + i915_gem_ww_ctx_fini(&ww); } } return 0; @@ -630,7 +630,7 @@ retry: return ret; } - i915_gem_object_unlock(wa_ctx->indirect_ctx.obj); + i915_gem_ww_ctx_fini(&ww); /* FIXME: we are not tracking our pinned VMA leaving it * up to the core to fix up the stray pin_count upon diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 664970f2bc62..4037030f0984 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -8193,6 +8193,11 @@ enum { #define HSW_SPR_STRETCH_MAX_X1 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 3) #define HSW_FBCQ_DIS (1 << 22) #define BDW_DPRS_MASK_VBLANK_SRD (1 << 0) +#define SKL_PLANE1_STRETCH_MAX_MASK REG_GENMASK(1, 0) +#define SKL_PLANE1_STRETCH_MAX_X8 REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 0) +#define SKL_PLANE1_STRETCH_MAX_X4 REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 1) +#define SKL_PLANE1_STRETCH_MAX_X2 REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 2) +#define SKL_PLANE1_STRETCH_MAX_X1 REG_FIELD_PREP(SKL_PLANE1_STRETCH_MAX_MASK, 3) #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B) #define _CHICKEN_TRANS_A 0x420c0 diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index ce446716d092..79da5eca60af 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -829,8 +829,6 @@ static void __i915_request_ctor(void *arg) i915_sw_fence_init(&rq->submit, submit_notify); i915_sw_fence_init(&rq->semaphore, semaphore_notify); - dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, 0, 0); - rq->capture_list = NULL; init_llist_head(&rq->execute_cb); @@ -905,17 +903,12 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) rq->ring = ce->ring; rq->execution_mask = ce->engine->mask; - kref_init(&rq->fence.refcount); - rq->fence.flags = 0; - rq->fence.error = 0; - INIT_LIST_HEAD(&rq->fence.cb_list); - ret = intel_timeline_get_seqno(tl, rq, &seqno); if (ret) goto err_free; - rq->fence.context = tl->fence_context; - rq->fence.seqno = seqno; + dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock, + tl->fence_context, seqno); RCU_INIT_POINTER(rq->timeline, tl); rq->hwsp_seqno = tl->hwsp_seqno; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 65bc3709f54c..a725792d5248 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -76,6 +76,8 @@ struct intel_wm_config { static void gen9_init_clock_gating(struct drm_i915_private *dev_priv) { + enum pipe pipe; + if (HAS_LLC(dev_priv)) { /* * WaCompressedResourceDisplayNewHashMode:skl,kbl @@ -89,6 +91,16 @@ static void gen9_init_clock_gating(struct drm_i915_private *dev_priv) SKL_DE_COMPRESSED_HASH_MODE); } + for_each_pipe(dev_priv, pipe) { + /* + * "Plane N strech max must be programmed to 11b (x1) + * when Async flips are enabled on that plane." + */ + if (!IS_GEMINILAKE(dev_priv) && intel_vtd_active()) + intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe), + SKL_PLANE1_STRETCH_MAX_MASK, SKL_PLANE1_STRETCH_MAX_X1); + } + /* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl,cfl */ intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1, intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | SKL_EDP_PSR_FIX_RDWRAP); diff --git a/drivers/gpu/drm/kmb/kmb_drv.c b/drivers/gpu/drm/kmb/kmb_drv.c index 1c2f4799f421..12ce669650cc 100644 --- a/drivers/gpu/drm/kmb/kmb_drv.c +++ b/drivers/gpu/drm/kmb/kmb_drv.c @@ -172,10 +172,10 @@ static int kmb_setup_mode_config(struct drm_device *drm) ret = drmm_mode_config_init(drm); if (ret) return ret; - drm->mode_config.min_width = KMB_MIN_WIDTH; - drm->mode_config.min_height = KMB_MIN_HEIGHT; - drm->mode_config.max_width = KMB_MAX_WIDTH; - drm->mode_config.max_height = KMB_MAX_HEIGHT; + drm->mode_config.min_width = KMB_FB_MIN_WIDTH; + drm->mode_config.min_height = KMB_FB_MIN_HEIGHT; + drm->mode_config.max_width = KMB_FB_MAX_WIDTH; + drm->mode_config.max_height = KMB_FB_MAX_HEIGHT; drm->mode_config.funcs = &kmb_mode_config_funcs; ret = kmb_setup_crtc(drm); diff --git a/drivers/gpu/drm/kmb/kmb_drv.h b/drivers/gpu/drm/kmb/kmb_drv.h index ebbaa5f422d5..69a62e2d03ff 100644 --- a/drivers/gpu/drm/kmb/kmb_drv.h +++ b/drivers/gpu/drm/kmb/kmb_drv.h @@ -20,6 +20,11 @@ #define DRIVER_MAJOR 1 #define DRIVER_MINOR 1 +#define KMB_FB_MAX_WIDTH 1920 +#define KMB_FB_MAX_HEIGHT 1080 +#define KMB_FB_MIN_WIDTH 1 +#define KMB_FB_MIN_HEIGHT 1 + #define KMB_LCD_DEFAULT_CLK 200000000 #define KMB_SYS_CLK_MHZ 500 diff --git a/drivers/gpu/drm/kmb/kmb_plane.c b/drivers/gpu/drm/kmb/kmb_plane.c index ecee6782612d..06b0c42c9e91 100644 --- a/drivers/gpu/drm/kmb/kmb_plane.c +++ b/drivers/gpu/drm/kmb/kmb_plane.c @@ -94,9 +94,10 @@ static int kmb_plane_atomic_check(struct drm_plane *plane, if (ret) return ret; - if (new_plane_state->crtc_w > KMB_MAX_WIDTH || new_plane_state->crtc_h > KMB_MAX_HEIGHT) - return -EINVAL; - if (new_plane_state->crtc_w < KMB_MIN_WIDTH || new_plane_state->crtc_h < KMB_MIN_HEIGHT) + if (new_plane_state->crtc_w > KMB_FB_MAX_WIDTH || + new_plane_state->crtc_h > KMB_FB_MAX_HEIGHT || + new_plane_state->crtc_w < KMB_FB_MIN_WIDTH || + new_plane_state->crtc_h < KMB_FB_MIN_HEIGHT) return -EINVAL; can_position = (plane->type == DRM_PLANE_TYPE_OVERLAY); crtc_state = @@ -277,6 +278,44 @@ static void config_csc(struct kmb_drm_private *kmb, int plane_id) kmb_write_lcd(kmb, LCD_LAYERn_CSC_OFF3(plane_id), csc_coef_lcd[11]); } +static void kmb_plane_set_alpha(struct kmb_drm_private *kmb, + const struct drm_plane_state *state, + unsigned char plane_id, + unsigned int *val) +{ + u16 plane_alpha = state->alpha; + u16 pixel_blend_mode = state->pixel_blend_mode; + int has_alpha = state->fb->format->has_alpha; + + if (plane_alpha != DRM_BLEND_ALPHA_OPAQUE) + *val |= LCD_LAYER_ALPHA_STATIC; + + if (has_alpha) { + switch (pixel_blend_mode) { + case DRM_MODE_BLEND_PIXEL_NONE: + break; + case DRM_MODE_BLEND_PREMULTI: + *val |= LCD_LAYER_ALPHA_EMBED | LCD_LAYER_ALPHA_PREMULT; + break; + case DRM_MODE_BLEND_COVERAGE: + *val |= LCD_LAYER_ALPHA_EMBED; + break; + default: + DRM_DEBUG("Missing pixel blend mode case (%s == %ld)\n", + __stringify(pixel_blend_mode), + (long)pixel_blend_mode); + break; + } + } + + if (plane_alpha == DRM_BLEND_ALPHA_OPAQUE && !has_alpha) { + *val &= LCD_LAYER_ALPHA_DISABLED; + return; + } + + kmb_write_lcd(kmb, LCD_LAYERn_ALPHA(plane_id), plane_alpha); +} + static void kmb_plane_atomic_update(struct drm_plane *plane, struct drm_atomic_state *state) { @@ -303,11 +342,12 @@ static void kmb_plane_atomic_update(struct drm_plane *plane, fb = new_plane_state->fb; if (!fb) return; + num_planes = fb->format->num_planes; kmb_plane = to_kmb_plane(plane); - plane_id = kmb_plane->id; kmb = to_kmb(plane->dev); + plane_id = kmb_plane->id; spin_lock_irq(&kmb->irq_lock); if (kmb->kmb_under_flow || kmb->kmb_flush_done) { @@ -400,20 +440,32 @@ static void kmb_plane_atomic_update(struct drm_plane *plane, config_csc(kmb, plane_id); } + kmb_plane_set_alpha(kmb, plane->state, plane_id, &val); + kmb_write_lcd(kmb, LCD_LAYERn_CFG(plane_id), val); + /* Configure LCD_CONTROL */ + ctrl = kmb_read_lcd(kmb, LCD_CONTROL); + + /* Set layer blending config */ + ctrl &= ~LCD_CTRL_ALPHA_ALL; + ctrl |= LCD_CTRL_ALPHA_BOTTOM_VL1 | + LCD_CTRL_ALPHA_BLEND_VL2; + + ctrl &= ~LCD_CTRL_ALPHA_BLEND_BKGND_DISABLE; + switch (plane_id) { case LAYER_0: - ctrl = LCD_CTRL_VL1_ENABLE; + ctrl |= LCD_CTRL_VL1_ENABLE; break; case LAYER_1: - ctrl = LCD_CTRL_VL2_ENABLE; + ctrl |= LCD_CTRL_VL2_ENABLE; break; case LAYER_2: - ctrl = LCD_CTRL_GL1_ENABLE; + ctrl |= LCD_CTRL_GL1_ENABLE; break; case LAYER_3: - ctrl = LCD_CTRL_GL2_ENABLE; + ctrl |= LCD_CTRL_GL2_ENABLE; break; } @@ -425,7 +477,7 @@ static void kmb_plane_atomic_update(struct drm_plane *plane, */ ctrl |= LCD_CTRL_VHSYNC_IDLE_LVL; - kmb_set_bitmask_lcd(kmb, LCD_CONTROL, ctrl); + kmb_write_lcd(kmb, LCD_CONTROL, ctrl); /* Enable pipeline AXI read transactions for the DMA * after setting graphics layers. This must be done @@ -490,6 +542,9 @@ struct kmb_plane *kmb_plane_init(struct drm_device *drm) enum drm_plane_type plane_type; const u32 *plane_formats; int num_plane_formats; + unsigned int blend_caps = BIT(DRM_MODE_BLEND_PIXEL_NONE) | + BIT(DRM_MODE_BLEND_PREMULTI) | + BIT(DRM_MODE_BLEND_COVERAGE); for (i = 0; i < KMB_MAX_PLANES; i++) { plane = drmm_kzalloc(drm, sizeof(*plane), GFP_KERNEL); @@ -521,8 +576,16 @@ struct kmb_plane *kmb_plane_init(struct drm_device *drm) drm_dbg(drm, "%s : %d i=%d type=%d", __func__, __LINE__, i, plane_type); + drm_plane_create_alpha_property(&plane->base_plane); + + drm_plane_create_blend_mode_property(&plane->base_plane, + blend_caps); + + drm_plane_create_zpos_immutable_property(&plane->base_plane, i); + drm_plane_helper_add(&plane->base_plane, &kmb_plane_helper_funcs); + if (plane_type == DRM_PLANE_TYPE_PRIMARY) { primary = plane; kmb->plane = plane; diff --git a/drivers/gpu/drm/kmb/kmb_plane.h b/drivers/gpu/drm/kmb/kmb_plane.h index 486490f7a3ec..6e8d22cf8819 100644 --- a/drivers/gpu/drm/kmb/kmb_plane.h +++ b/drivers/gpu/drm/kmb/kmb_plane.h @@ -35,6 +35,9 @@ #define POSSIBLE_CRTCS 1 #define to_kmb_plane(x) container_of(x, struct kmb_plane, base_plane) +#define POSSIBLE_CRTCS 1 +#define KMB_MAX_PLANES 2 + enum layer_id { LAYER_0, LAYER_1, @@ -43,8 +46,6 @@ enum layer_id { /* KMB_MAX_PLANES */ }; -#define KMB_MAX_PLANES 1 - enum sub_plane_id { Y_PLANE, U_PLANE, diff --git a/drivers/gpu/drm/kmb/kmb_regs.h b/drivers/gpu/drm/kmb/kmb_regs.h index 48150569f702..9756101b0d32 100644 --- a/drivers/gpu/drm/kmb/kmb_regs.h +++ b/drivers/gpu/drm/kmb/kmb_regs.h @@ -43,8 +43,10 @@ #define LCD_CTRL_OUTPUT_ENABLED BIT(19) #define LCD_CTRL_BPORCH_ENABLE BIT(21) #define LCD_CTRL_FPORCH_ENABLE BIT(22) +#define LCD_CTRL_ALPHA_BLEND_BKGND_DISABLE BIT(23) #define LCD_CTRL_PIPELINE_DMA BIT(28) #define LCD_CTRL_VHSYNC_IDLE_LVL BIT(31) +#define LCD_CTRL_ALPHA_ALL (0xff << 6) /* interrupts */ #define LCD_INT_STATUS (0x4 * 0x001) @@ -115,6 +117,7 @@ #define LCD_LAYER_ALPHA_EMBED BIT(5) #define LCD_LAYER_ALPHA_COMBI (LCD_LAYER_ALPHA_STATIC | \ LCD_LAYER_ALPHA_EMBED) +#define LCD_LAYER_ALPHA_DISABLED ~(LCD_LAYER_ALPHA_COMBI) /* RGB multiplied with alpha */ #define LCD_LAYER_ALPHA_PREMULT BIT(6) #define LCD_LAYER_INVERT_COL BIT(7) diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index e9c6af78b1d7..3ddf739a6f9b 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -17,7 +17,7 @@ config DRM_MSM select DRM_SCHED select SHMEM select TMPFS - select QCOM_SCM if ARCH_QCOM + select QCOM_SCM select WANT_DEV_COREDUMP select SND_SOC_HDMI_CODEC if SND_SOC select SYNC_FILE @@ -55,7 +55,7 @@ config DRM_MSM_GPU_SUDO config DRM_MSM_HDMI_HDCP bool "Enable HDMI HDCP support in MSM DRM driver" - depends on DRM_MSM && QCOM_SCM + depends on DRM_MSM default y help Choose this option to enable HDCP state machine diff --git a/drivers/gpu/drm/nouveau/dispnv50/crc.c b/drivers/gpu/drm/nouveau/dispnv50/crc.c index b8c31b697797..66f32d965c72 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/crc.c +++ b/drivers/gpu/drm/nouveau/dispnv50/crc.c @@ -704,6 +704,7 @@ static const struct file_operations nv50_crc_flip_threshold_fops = { .open = nv50_crc_debugfs_flip_threshold_open, .read = seq_read, .write = nv50_crc_debugfs_flip_threshold_set, + .release = single_release, }; int nv50_head_crc_late_register(struct nv50_head *head) diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c index d66f97280282..72099d1e4816 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/head.c +++ b/drivers/gpu/drm/nouveau/dispnv50/head.c @@ -52,6 +52,7 @@ nv50_head_flush_clr(struct nv50_head *head, void nv50_head_flush_set_wndw(struct nv50_head *head, struct nv50_head_atom *asyh) { + if (asyh->set.curs ) head->func->curs_set(head, asyh); if (asyh->set.olut ) { asyh->olut.offset = nv50_lut_load(&head->olut, asyh->olut.buffer, @@ -67,7 +68,6 @@ nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh) if (asyh->set.view ) head->func->view (head, asyh); if (asyh->set.mode ) head->func->mode (head, asyh); if (asyh->set.core ) head->func->core_set(head, asyh); - if (asyh->set.curs ) head->func->curs_set(head, asyh); if (asyh->set.base ) head->func->base (head, asyh); if (asyh->set.ovly ) head->func->ovly (head, asyh); if (asyh->set.dither ) head->func->dither (head, asyh); diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h index c68cc957248e..a582c0cb0cb0 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/class.h +++ b/drivers/gpu/drm/nouveau/include/nvif/class.h @@ -71,6 +71,7 @@ #define PASCAL_CHANNEL_GPFIFO_A /* cla06f.h */ 0x0000c06f #define VOLTA_CHANNEL_GPFIFO_A /* clc36f.h */ 0x0000c36f #define TURING_CHANNEL_GPFIFO_A /* clc36f.h */ 0x0000c46f +#define AMPERE_CHANNEL_GPFIFO_B /* clc36f.h */ 0x0000c76f #define NV50_DISP /* cl5070.h */ 0x00005070 #define G82_DISP /* cl5070.h */ 0x00008270 @@ -200,6 +201,7 @@ #define PASCAL_DMA_COPY_B 0x0000c1b5 #define VOLTA_DMA_COPY_A 0x0000c3b5 #define TURING_DMA_COPY_A 0x0000c5b5 +#define AMPERE_DMA_COPY_B 0x0000c7b5 #define FERMI_DECOMPRESS 0x000090b8 diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h index 54fab7cc36c1..64ee82c7c1be 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/fifo.h @@ -77,4 +77,5 @@ int gp100_fifo_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct int gp10b_fifo_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fifo **); int gv100_fifo_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fifo **); int tu102_fifo_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fifo **); +int ga102_fifo_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fifo **); #endif diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 6d07e653f82d..c58bcdba2c7a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -844,6 +844,7 @@ nouveau_bo_move_init(struct nouveau_drm *drm) struct ttm_resource *, struct ttm_resource *); int (*init)(struct nouveau_channel *, u32 handle); } _methods[] = { + { "COPY", 4, 0xc7b5, nve0_bo_move_copy, nve0_bo_move_init }, { "COPY", 4, 0xc5b5, nve0_bo_move_copy, nve0_bo_move_init }, { "GRCE", 0, 0xc5b5, nve0_bo_move_copy, nvc0_bo_move_init }, { "COPY", 4, 0xc3b5, nve0_bo_move_copy, nve0_bo_move_init }, diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index 80099ef75702..ea7769135b0d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -250,7 +250,8 @@ static int nouveau_channel_ind(struct nouveau_drm *drm, struct nvif_device *device, u64 runlist, bool priv, struct nouveau_channel **pchan) { - static const u16 oclasses[] = { TURING_CHANNEL_GPFIFO_A, + static const u16 oclasses[] = { AMPERE_CHANNEL_GPFIFO_B, + TURING_CHANNEL_GPFIFO_A, VOLTA_CHANNEL_GPFIFO_A, PASCAL_CHANNEL_GPFIFO_A, MAXWELL_CHANNEL_GPFIFO_A, @@ -386,7 +387,8 @@ nouveau_channel_init(struct nouveau_channel *chan, u32 vram, u32 gart) nvif_object_map(&chan->user, NULL, 0); - if (chan->user.oclass >= FERMI_CHANNEL_GPFIFO) { + if (chan->user.oclass >= FERMI_CHANNEL_GPFIFO && + chan->user.oclass < AMPERE_CHANNEL_GPFIFO_B) { ret = nvif_notify_ctor(&chan->user, "abi16ChanKilled", nouveau_channel_killed, true, NV906F_V0_NTFY_KILLED, diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c index c2bc05eb2e54..1cbe01048b93 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c @@ -207,6 +207,7 @@ static const struct file_operations nouveau_pstate_fops = { .open = nouveau_debugfs_pstate_open, .read = seq_read, .write = nouveau_debugfs_pstate_set, + .release = single_release, }; static struct drm_info_list nouveau_debugfs_list[] = { diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 1f828c9f691c..6109cd9e3399 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -345,6 +345,9 @@ nouveau_accel_gr_init(struct nouveau_drm *drm) u32 arg0, arg1; int ret; + if (device->info.family >= NV_DEVICE_INFO_V0_AMPERE) + return; + /* Allocate channel that has access to the graphics engine. */ if (device->info.family >= NV_DEVICE_INFO_V0_KEPLER) { arg0 = nvif_fifo_runlist(device, NV_DEVICE_HOST_RUNLIST_ENGINES_GR); @@ -469,6 +472,7 @@ nouveau_accel_init(struct nouveau_drm *drm) case PASCAL_CHANNEL_GPFIFO_A: case VOLTA_CHANNEL_GPFIFO_A: case TURING_CHANNEL_GPFIFO_A: + case AMPERE_CHANNEL_GPFIFO_B: ret = nvc0_fence_create(drm); break; default: diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 5b27845075a1..8c2ecc282723 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -247,10 +247,8 @@ nouveau_gem_new(struct nouveau_cli *cli, u64 size, int align, uint32_t domain, } ret = nouveau_bo_init(nvbo, size, align, domain, NULL, NULL); - if (ret) { - nouveau_bo_ref(NULL, &nvbo); + if (ret) return ret; - } /* we restrict allowed domains on nv50+ to only the types * that were requested at creation time. not possibly on diff --git a/drivers/gpu/drm/nouveau/nv84_fence.c b/drivers/gpu/drm/nouveau/nv84_fence.c index 7c9c928c3196..c3526a8622e3 100644 --- a/drivers/gpu/drm/nouveau/nv84_fence.c +++ b/drivers/gpu/drm/nouveau/nv84_fence.c @@ -204,7 +204,7 @@ nv84_fence_create(struct nouveau_drm *drm) priv->base.context_new = nv84_fence_context_new; priv->base.context_del = nv84_fence_context_del; - priv->base.uevent = true; + priv->base.uevent = drm->client.device.info.family < NV_DEVICE_INFO_V0_AMPERE; mutex_init(&priv->mutex); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 93ddf63d1114..ca75c5f6ecaf 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2602,6 +2602,7 @@ nv172_chipset = { .top = { 0x00000001, ga100_top_new }, .disp = { 0x00000001, ga102_disp_new }, .dma = { 0x00000001, gv100_dma_new }, + .fifo = { 0x00000001, ga102_fifo_new }, }; static const struct nvkm_device_chip @@ -2622,6 +2623,7 @@ nv174_chipset = { .top = { 0x00000001, ga100_top_new }, .disp = { 0x00000001, ga102_disp_new }, .dma = { 0x00000001, gv100_dma_new }, + .fifo = { 0x00000001, ga102_fifo_new }, }; static const struct nvkm_device_chip @@ -2642,6 +2644,7 @@ nv177_chipset = { .top = { 0x00000001, ga100_top_new }, .disp = { 0x00000001, ga102_disp_new }, .dma = { 0x00000001, gv100_dma_new }, + .fifo = { 0x00000001, ga102_fifo_new }, }; static int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild index 3209eb7af65f..5e831d347a95 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/Kbuild @@ -18,6 +18,7 @@ nvkm-y += nvkm/engine/fifo/gp100.o nvkm-y += nvkm/engine/fifo/gp10b.o nvkm-y += nvkm/engine/fifo/gv100.o nvkm-y += nvkm/engine/fifo/tu102.o +nvkm-y += nvkm/engine/fifo/ga102.o nvkm-y += nvkm/engine/fifo/chan.o nvkm-y += nvkm/engine/fifo/channv50.o diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c new file mode 100644 index 000000000000..c630dbd2911a --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c @@ -0,0 +1,311 @@ +/* + * Copyright 2021 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ +#define ga102_fifo(p) container_of((p), struct ga102_fifo, base.engine) +#define ga102_chan(p) container_of((p), struct ga102_chan, object) +#include <engine/fifo.h> +#include "user.h" + +#include <core/memory.h> +#include <subdev/mmu.h> +#include <subdev/timer.h> +#include <subdev/top.h> + +#include <nvif/cl0080.h> +#include <nvif/clc36f.h> +#include <nvif/class.h> + +struct ga102_fifo { + struct nvkm_fifo base; +}; + +struct ga102_chan { + struct nvkm_object object; + + struct { + u32 runl; + u32 chan; + } ctrl; + + struct nvkm_memory *mthd; + struct nvkm_memory *inst; + struct nvkm_memory *user; + struct nvkm_memory *runl; + + struct nvkm_vmm *vmm; +}; + +static int +ga102_chan_sclass(struct nvkm_object *object, int index, struct nvkm_oclass *oclass) +{ + if (index == 0) { + oclass->ctor = nvkm_object_new; + oclass->base = (struct nvkm_sclass) { -1, -1, AMPERE_DMA_COPY_B }; + return 0; + } + + return -EINVAL; +} + +static int +ga102_chan_map(struct nvkm_object *object, void *argv, u32 argc, + enum nvkm_object_map *type, u64 *addr, u64 *size) +{ + struct ga102_chan *chan = ga102_chan(object); + struct nvkm_device *device = chan->object.engine->subdev.device; + u64 bar2 = nvkm_memory_bar2(chan->user); + + if (bar2 == ~0ULL) + return -EFAULT; + + *type = NVKM_OBJECT_MAP_IO; + *addr = device->func->resource_addr(device, 3) + bar2; + *size = 0x1000; + return 0; +} + +static int +ga102_chan_fini(struct nvkm_object *object, bool suspend) +{ + struct ga102_chan *chan = ga102_chan(object); + struct nvkm_device *device = chan->object.engine->subdev.device; + + nvkm_wr32(device, chan->ctrl.chan, 0x00000003); + + nvkm_wr32(device, chan->ctrl.runl + 0x098, 0x01000000); + nvkm_msec(device, 2000, + if (!(nvkm_rd32(device, chan->ctrl.runl + 0x098) & 0x00100000)) + break; + ); + + nvkm_wr32(device, chan->ctrl.runl + 0x088, 0); + + nvkm_wr32(device, chan->ctrl.chan, 0xffffffff); + return 0; +} + +static int +ga102_chan_init(struct nvkm_object *object) +{ + struct ga102_chan *chan = ga102_chan(object); + struct nvkm_device *device = chan->object.engine->subdev.device; + + nvkm_mask(device, chan->ctrl.runl + 0x300, 0x80000000, 0x80000000); + + nvkm_wr32(device, chan->ctrl.runl + 0x080, lower_32_bits(nvkm_memory_addr(chan->runl))); + nvkm_wr32(device, chan->ctrl.runl + 0x084, upper_32_bits(nvkm_memory_addr(chan->runl))); + nvkm_wr32(device, chan->ctrl.runl + 0x088, 2); + + nvkm_wr32(device, chan->ctrl.chan, 0x00000002); + nvkm_wr32(device, chan->ctrl.runl + 0x0090, 0); + return 0; +} + +static void * +ga102_chan_dtor(struct nvkm_object *object) +{ + struct ga102_chan *chan = ga102_chan(object); + + if (chan->vmm) { + nvkm_vmm_part(chan->vmm, chan->inst); + nvkm_vmm_unref(&chan->vmm); + } + + nvkm_memory_unref(&chan->runl); + nvkm_memory_unref(&chan->user); + nvkm_memory_unref(&chan->inst); + nvkm_memory_unref(&chan->mthd); + return chan; +} + +static const struct nvkm_object_func +ga102_chan = { + .dtor = ga102_chan_dtor, + .init = ga102_chan_init, + .fini = ga102_chan_fini, + .map = ga102_chan_map, + .sclass = ga102_chan_sclass, +}; + +static int +ga102_chan_new(struct nvkm_device *device, + const struct nvkm_oclass *oclass, void *argv, u32 argc, struct nvkm_object **pobject) +{ + struct volta_channel_gpfifo_a_v0 *args = argv; + struct nvkm_top_device *tdev; + struct nvkm_vmm *vmm; + struct ga102_chan *chan; + int ret; + + if (argc != sizeof(*args)) + return -ENOSYS; + + vmm = nvkm_uvmm_search(oclass->client, args->vmm); + if (IS_ERR(vmm)) + return PTR_ERR(vmm); + + if (!(chan = kzalloc(sizeof(*chan), GFP_KERNEL))) + return -ENOMEM; + + nvkm_object_ctor(&ga102_chan, oclass, &chan->object); + *pobject = &chan->object; + + list_for_each_entry(tdev, &device->top->device, head) { + if (tdev->type == NVKM_ENGINE_CE) { + chan->ctrl.runl = tdev->runlist; + break; + } + } + + if (!chan->ctrl.runl) + return -ENODEV; + + chan->ctrl.chan = nvkm_rd32(device, chan->ctrl.runl + 0x004) & 0xfffffff0; + + args->chid = 0; + args->inst = 0; + args->token = nvkm_rd32(device, chan->ctrl.runl + 0x008) & 0xffff0000; + + ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x1000, 0x1000, true, &chan->mthd); + if (ret) + return ret; + + ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x1000, 0x1000, true, &chan->inst); + if (ret) + return ret; + + nvkm_kmap(chan->inst); + nvkm_wo32(chan->inst, 0x010, 0x0000face); + nvkm_wo32(chan->inst, 0x030, 0x7ffff902); + nvkm_wo32(chan->inst, 0x048, lower_32_bits(args->ioffset)); + nvkm_wo32(chan->inst, 0x04c, upper_32_bits(args->ioffset) | + (order_base_2(args->ilength / 8) << 16)); + nvkm_wo32(chan->inst, 0x084, 0x20400000); + nvkm_wo32(chan->inst, 0x094, 0x30000001); + nvkm_wo32(chan->inst, 0x0ac, 0x00020000); + nvkm_wo32(chan->inst, 0x0e4, 0x00000000); + nvkm_wo32(chan->inst, 0x0e8, 0); + nvkm_wo32(chan->inst, 0x0f4, 0x00001000); + nvkm_wo32(chan->inst, 0x0f8, 0x10003080); + nvkm_mo32(chan->inst, 0x218, 0x00000000, 0x00000000); + nvkm_wo32(chan->inst, 0x220, lower_32_bits(nvkm_memory_bar2(chan->mthd))); + nvkm_wo32(chan->inst, 0x224, upper_32_bits(nvkm_memory_bar2(chan->mthd))); + nvkm_done(chan->inst); + + ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x1000, 0x1000, true, &chan->user); + if (ret) + return ret; + + ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x1000, 0x1000, true, &chan->runl); + if (ret) + return ret; + + nvkm_kmap(chan->runl); + nvkm_wo32(chan->runl, 0x00, 0x80030001); + nvkm_wo32(chan->runl, 0x04, 1); + nvkm_wo32(chan->runl, 0x08, 0); + nvkm_wo32(chan->runl, 0x0c, 0x00000000); + nvkm_wo32(chan->runl, 0x10, lower_32_bits(nvkm_memory_addr(chan->user))); + nvkm_wo32(chan->runl, 0x14, upper_32_bits(nvkm_memory_addr(chan->user))); + nvkm_wo32(chan->runl, 0x18, lower_32_bits(nvkm_memory_addr(chan->inst))); + nvkm_wo32(chan->runl, 0x1c, upper_32_bits(nvkm_memory_addr(chan->inst))); + nvkm_done(chan->runl); + + ret = nvkm_vmm_join(vmm, chan->inst); + if (ret) + return ret; + + chan->vmm = nvkm_vmm_ref(vmm); + return 0; +} + +static const struct nvkm_device_oclass +ga102_chan_oclass = { + .ctor = ga102_chan_new, +}; + +static int +ga102_user_new(struct nvkm_device *device, + const struct nvkm_oclass *oclass, void *argv, u32 argc, struct nvkm_object **pobject) +{ + return tu102_fifo_user_new(oclass, argv, argc, pobject); +} + +static const struct nvkm_device_oclass +ga102_user_oclass = { + .ctor = ga102_user_new, +}; + +static int +ga102_fifo_sclass(struct nvkm_oclass *oclass, int index, const struct nvkm_device_oclass **class) +{ + if (index == 0) { + oclass->base = (struct nvkm_sclass) { -1, -1, VOLTA_USERMODE_A }; + *class = &ga102_user_oclass; + return 0; + } else + if (index == 1) { + oclass->base = (struct nvkm_sclass) { 0, 0, AMPERE_CHANNEL_GPFIFO_B }; + *class = &ga102_chan_oclass; + return 0; + } + + return 2; +} + +static int +ga102_fifo_info(struct nvkm_engine *engine, u64 mthd, u64 *data) +{ + switch (mthd) { + case NV_DEVICE_HOST_CHANNELS: *data = 1; return 0; + default: + break; + } + + return -ENOSYS; +} + +static void * +ga102_fifo_dtor(struct nvkm_engine *engine) +{ + return ga102_fifo(engine); +} + +static const struct nvkm_engine_func +ga102_fifo = { + .dtor = ga102_fifo_dtor, + .info = ga102_fifo_info, + .base.sclass = ga102_fifo_sclass, +}; + +int +ga102_fifo_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, + struct nvkm_fifo **pfifo) +{ + struct ga102_fifo *fifo; + + if (!(fifo = kzalloc(sizeof(*fifo), GFP_KERNEL))) + return -ENOMEM; + + nvkm_engine_ctor(&ga102_fifo, device, type, inst, true, &fifo->base.engine); + *pfifo = &fifo->base; + return 0; +} diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/top/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/top/ga100.c index 31933f3e5a07..c982d834c8d9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/top/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/top/ga100.c @@ -54,7 +54,7 @@ ga100_top_oneinit(struct nvkm_top *top) info->reset = (data & 0x0000001f); break; case 2: - info->runlist = (data & 0x0000fc00) >> 10; + info->runlist = (data & 0x00fffc00); info->engine = (data & 0x00000003); break; default: @@ -85,9 +85,10 @@ ga100_top_oneinit(struct nvkm_top *top) } nvkm_debug(subdev, "%02x.%d (%8s): addr %06x fault %2d " - "runlist %2d engine %2d reset %2d\n", type, inst, + "runlist %6x engine %2d reset %2d\n", type, inst, info->type == NVKM_SUBDEV_NR ? "????????" : nvkm_subdev_type[info->type], - info->addr, info->fault, info->runlist, info->engine, info->reset); + info->addr, info->fault, info->runlist < 0 ? 0 : info->runlist, + info->engine, info->reset); info = NULL; } diff --git a/drivers/gpu/drm/panel/panel-abt-y030xx067a.c b/drivers/gpu/drm/panel/panel-abt-y030xx067a.c index 2d8794d495d0..3d8a9ab47cae 100644 --- a/drivers/gpu/drm/panel/panel-abt-y030xx067a.c +++ b/drivers/gpu/drm/panel/panel-abt-y030xx067a.c @@ -146,8 +146,8 @@ static const struct reg_sequence y030xx067a_init_sequence[] = { { 0x09, REG09_SUB_BRIGHT_R(0x20) }, { 0x0a, REG0A_SUB_BRIGHT_B(0x20) }, { 0x0b, REG0B_HD_FREERUN | REG0B_VD_FREERUN }, - { 0x0c, REG0C_CONTRAST_R(0x10) }, - { 0x0d, REG0D_CONTRAST_G(0x10) }, + { 0x0c, REG0C_CONTRAST_R(0x00) }, + { 0x0d, REG0D_CONTRAST_G(0x00) }, { 0x0e, REG0E_CONTRAST_B(0x10) }, { 0x0f, 0 }, { 0x10, REG10_BRIGHT(0x7f) }, diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index ba9e14da41b4..a25b98b7f5bd 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -1174,26 +1174,24 @@ static bool vop_crtc_mode_fixup(struct drm_crtc *crtc, * * Action plan: * - * 1. When DRM gives us a mode, we should add 999 Hz to it. That way - * if the clock we need is 60000001 Hz (~60 MHz) and DRM tells us to - * make 60000 kHz then the clock framework will actually give us - * the right clock. + * 1. Try to set the exact rate first, and confirm the clock framework + * can provide it. * - * NOTE: if the PLL (maybe through a divider) could actually make - * a clock rate 999 Hz higher instead of the one we want then this - * could be a problem. Unfortunately there's not much we can do - * since it's baked into DRM to use kHz. It shouldn't matter in - * practice since Rockchip PLLs are controlled by tables and - * even if there is a divider in the middle I wouldn't expect PLL - * rates in the table that are just a few kHz different. + * 2. If the clock framework cannot provide the exact rate, we should + * add 999 Hz to the requested rate. That way if the clock we need + * is 60000001 Hz (~60 MHz) and DRM tells us to make 60000 kHz then + * the clock framework will actually give us the right clock. * - * 2. Get the clock framework to round the rate for us to tell us + * 3. Get the clock framework to round the rate for us to tell us * what it will actually make. * - * 3. Store the rounded up rate so that we don't need to worry about + * 4. Store the rounded up rate so that we don't need to worry about * this in the actual clk_set_rate(). */ - rate = clk_round_rate(vop->dclk, adjusted_mode->clock * 1000 + 999); + rate = clk_round_rate(vop->dclk, adjusted_mode->clock * 1000); + if (rate / 1000 != adjusted_mode->clock) + rate = clk_round_rate(vop->dclk, + adjusted_mode->clock * 1000 + 999); adjusted_mode->clock = DIV_ROUND_UP(rate, 1000); return true; diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c index f75fb157f2ff..016b877051da 100644 --- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c +++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c @@ -216,11 +216,13 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master, goto err_disable_clk_tmds; } + ret = sun8i_hdmi_phy_init(hdmi->phy); + if (ret) + goto err_disable_clk_tmds; + drm_encoder_helper_add(encoder, &sun8i_dw_hdmi_encoder_helper_funcs); drm_simple_encoder_init(drm, encoder, DRM_MODE_ENCODER_TMDS); - sun8i_hdmi_phy_init(hdmi->phy); - plat_data->mode_valid = hdmi->quirks->mode_valid; plat_data->use_drm_infoframe = hdmi->quirks->use_drm_infoframe; sun8i_hdmi_phy_set_ops(hdmi->phy, plat_data); @@ -262,6 +264,7 @@ static void sun8i_dw_hdmi_unbind(struct device *dev, struct device *master, struct sun8i_dw_hdmi *hdmi = dev_get_drvdata(dev); dw_hdmi_unbind(hdmi->hdmi); + sun8i_hdmi_phy_deinit(hdmi->phy); clk_disable_unprepare(hdmi->clk_tmds); reset_control_assert(hdmi->rst_ctrl); gpiod_set_value(hdmi->ddc_en, 0); diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h index 74f6ed0e2570..bffe1b9cd3dc 100644 --- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h +++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h @@ -169,6 +169,7 @@ struct sun8i_hdmi_phy { struct clk *clk_phy; struct clk *clk_pll0; struct clk *clk_pll1; + struct device *dev; unsigned int rcal; struct regmap *regs; struct reset_control *rst_phy; @@ -205,7 +206,8 @@ encoder_to_sun8i_dw_hdmi(struct drm_encoder *encoder) int sun8i_hdmi_phy_get(struct sun8i_dw_hdmi *hdmi, struct device_node *node); -void sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy); +int sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy); +void sun8i_hdmi_phy_deinit(struct sun8i_hdmi_phy *phy); void sun8i_hdmi_phy_set_ops(struct sun8i_hdmi_phy *phy, struct dw_hdmi_plat_data *plat_data); diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c index c9239708d398..b64d93da651d 100644 --- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c +++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c @@ -506,9 +506,60 @@ static void sun8i_hdmi_phy_init_h3(struct sun8i_hdmi_phy *phy) phy->rcal = (val & SUN8I_HDMI_PHY_ANA_STS_RCAL_MASK) >> 2; } -void sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy) +int sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy) { + int ret; + + ret = reset_control_deassert(phy->rst_phy); + if (ret) { + dev_err(phy->dev, "Cannot deassert phy reset control: %d\n", ret); + return ret; + } + + ret = clk_prepare_enable(phy->clk_bus); + if (ret) { + dev_err(phy->dev, "Cannot enable bus clock: %d\n", ret); + goto err_assert_rst_phy; + } + + ret = clk_prepare_enable(phy->clk_mod); + if (ret) { + dev_err(phy->dev, "Cannot enable mod clock: %d\n", ret); + goto err_disable_clk_bus; + } + + if (phy->variant->has_phy_clk) { + ret = sun8i_phy_clk_create(phy, phy->dev, + phy->variant->has_second_pll); + if (ret) { + dev_err(phy->dev, "Couldn't create the PHY clock\n"); + goto err_disable_clk_mod; + } + + clk_prepare_enable(phy->clk_phy); + } + phy->variant->phy_init(phy); + + return 0; + +err_disable_clk_mod: + clk_disable_unprepare(phy->clk_mod); +err_disable_clk_bus: + clk_disable_unprepare(phy->clk_bus); +err_assert_rst_phy: + reset_control_assert(phy->rst_phy); + + return ret; +} + +void sun8i_hdmi_phy_deinit(struct sun8i_hdmi_phy *phy) +{ + clk_disable_unprepare(phy->clk_mod); + clk_disable_unprepare(phy->clk_bus); + clk_disable_unprepare(phy->clk_phy); + + reset_control_assert(phy->rst_phy); } void sun8i_hdmi_phy_set_ops(struct sun8i_hdmi_phy *phy, @@ -638,6 +689,7 @@ static int sun8i_hdmi_phy_probe(struct platform_device *pdev) return -ENOMEM; phy->variant = (struct sun8i_hdmi_phy_variant *)match->data; + phy->dev = dev; ret = of_address_to_resource(node, 0, &res); if (ret) { @@ -696,47 +748,10 @@ static int sun8i_hdmi_phy_probe(struct platform_device *pdev) goto err_put_clk_pll1; } - ret = reset_control_deassert(phy->rst_phy); - if (ret) { - dev_err(dev, "Cannot deassert phy reset control: %d\n", ret); - goto err_put_rst_phy; - } - - ret = clk_prepare_enable(phy->clk_bus); - if (ret) { - dev_err(dev, "Cannot enable bus clock: %d\n", ret); - goto err_deassert_rst_phy; - } - - ret = clk_prepare_enable(phy->clk_mod); - if (ret) { - dev_err(dev, "Cannot enable mod clock: %d\n", ret); - goto err_disable_clk_bus; - } - - if (phy->variant->has_phy_clk) { - ret = sun8i_phy_clk_create(phy, dev, - phy->variant->has_second_pll); - if (ret) { - dev_err(dev, "Couldn't create the PHY clock\n"); - goto err_disable_clk_mod; - } - - clk_prepare_enable(phy->clk_phy); - } - platform_set_drvdata(pdev, phy); return 0; -err_disable_clk_mod: - clk_disable_unprepare(phy->clk_mod); -err_disable_clk_bus: - clk_disable_unprepare(phy->clk_bus); -err_deassert_rst_phy: - reset_control_assert(phy->rst_phy); -err_put_rst_phy: - reset_control_put(phy->rst_phy); err_put_clk_pll1: clk_put(phy->clk_pll1); err_put_clk_pll0: @@ -753,12 +768,6 @@ static int sun8i_hdmi_phy_remove(struct platform_device *pdev) { struct sun8i_hdmi_phy *phy = platform_get_drvdata(pdev); - clk_disable_unprepare(phy->clk_mod); - clk_disable_unprepare(phy->clk_bus); - clk_disable_unprepare(phy->clk_phy); - - reset_control_assert(phy->rst_phy); - reset_control_put(phy->rst_phy); clk_put(phy->clk_pll0); diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 16c7aabb94d3..a29d64f87563 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -1845,7 +1845,6 @@ tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc, bool prepare_bandwidth_transition) { const struct tegra_plane_state *old_tegra_state, *new_tegra_state; - const struct tegra_dc_state *old_dc_state, *new_dc_state; u32 i, new_avg_bw, old_avg_bw, new_peak_bw, old_peak_bw; const struct drm_plane_state *old_plane_state; const struct drm_crtc_state *old_crtc_state; @@ -1858,8 +1857,6 @@ tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc, return; old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc); - old_dc_state = to_const_dc_state(old_crtc_state); - new_dc_state = to_const_dc_state(crtc->state); if (!crtc->state->active) { if (!old_crtc_state->active) diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h index f0cb691852a1..40378308d527 100644 --- a/drivers/gpu/drm/tegra/dc.h +++ b/drivers/gpu/drm/tegra/dc.h @@ -35,12 +35,6 @@ static inline struct tegra_dc_state *to_dc_state(struct drm_crtc_state *state) return NULL; } -static inline const struct tegra_dc_state * -to_const_dc_state(const struct drm_crtc_state *state) -{ - return to_dc_state((struct drm_crtc_state *)state); -} - struct tegra_dc_stats { unsigned long frames; unsigned long vblank; diff --git a/drivers/gpu/drm/tegra/uapi.c b/drivers/gpu/drm/tegra/uapi.c index dc16a24f4dbe..690a339c52ec 100644 --- a/drivers/gpu/drm/tegra/uapi.c +++ b/drivers/gpu/drm/tegra/uapi.c @@ -222,7 +222,7 @@ int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_f mapping->iova = sg_dma_address(mapping->sgt->sgl); } - mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->size; + mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->gem.size; err = xa_alloc(&context->mappings, &args->mapping, mapping, XA_LIMIT(1, U32_MAX), GFP_KERNEL); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index b4b4653fe301..ed8a4b7f8b6e 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -1395,14 +1395,6 @@ static int vc4_hdmi_audio_prepare(struct device *dev, void *data, return 0; } -static const struct snd_soc_dapm_widget vc4_hdmi_audio_widgets[] = { - SND_SOC_DAPM_OUTPUT("TX"), -}; - -static const struct snd_soc_dapm_route vc4_hdmi_audio_routes[] = { - { "TX", NULL, "Playback" }, -}; - static const struct snd_soc_component_driver vc4_hdmi_audio_cpu_dai_comp = { .name = "vc4-hdmi-cpu-dai-component", }; diff --git a/drivers/gpu/host1x/fence.c b/drivers/gpu/host1x/fence.c index 6941add95d0f..ecab72882192 100644 --- a/drivers/gpu/host1x/fence.c +++ b/drivers/gpu/host1x/fence.c @@ -15,7 +15,7 @@ #include "intr.h" #include "syncpt.h" -DEFINE_SPINLOCK(lock); +static DEFINE_SPINLOCK(lock); struct host1x_syncpt_fence { struct dma_fence base; @@ -152,8 +152,10 @@ struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold) return ERR_PTR(-ENOMEM); fence->waiter = kzalloc(sizeof(*fence->waiter), GFP_KERNEL); - if (!fence->waiter) + if (!fence->waiter) { + kfree(fence); return ERR_PTR(-ENOMEM); + } fence->sp = sp; fence->threshold = threshold; diff --git a/drivers/hsi/clients/ssi_protocol.c b/drivers/hsi/clients/ssi_protocol.c index 96d0eccca3aa..21f11a5b965b 100644 --- a/drivers/hsi/clients/ssi_protocol.c +++ b/drivers/hsi/clients/ssi_protocol.c @@ -1055,14 +1055,16 @@ static const struct net_device_ops ssip_pn_ops = { static void ssip_pn_setup(struct net_device *dev) { + static const u8 addr = PN_MEDIA_SOS; + dev->features = 0; dev->netdev_ops = &ssip_pn_ops; dev->type = ARPHRD_PHONET; dev->flags = IFF_POINTOPOINT | IFF_NOARP; dev->mtu = SSIP_DEFAULT_MTU; dev->hard_header_len = 1; - dev->dev_addr[0] = PN_MEDIA_SOS; dev->addr_len = 1; + dev_addr_set(dev, &addr); dev->tx_queue_len = SSIP_TXQUEUE_LEN; dev->needs_free_netdev = true; diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index 38bc35ac8135..3618a924e78e 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -362,12 +362,6 @@ static const struct hwmon_channel_info *k10temp_info[] = { HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL), - HWMON_CHANNEL_INFO(in, - HWMON_I_INPUT | HWMON_I_LABEL, - HWMON_I_INPUT | HWMON_I_LABEL), - HWMON_CHANNEL_INFO(curr, - HWMON_C_INPUT | HWMON_C_LABEL, - HWMON_C_INPUT | HWMON_C_LABEL), NULL }; diff --git a/drivers/hwmon/ltc2947-core.c b/drivers/hwmon/ltc2947-core.c index bb3f7749a0b0..5423466de697 100644 --- a/drivers/hwmon/ltc2947-core.c +++ b/drivers/hwmon/ltc2947-core.c @@ -989,8 +989,12 @@ static int ltc2947_setup(struct ltc2947_data *st) return ret; /* check external clock presence */ - extclk = devm_clk_get(st->dev, NULL); - if (!IS_ERR(extclk)) { + extclk = devm_clk_get_optional(st->dev, NULL); + if (IS_ERR(extclk)) + return dev_err_probe(st->dev, PTR_ERR(extclk), + "Failed to get external clock\n"); + + if (extclk) { unsigned long rate_hz; u8 pre = 0, div, tbctl; u64 aux; diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c index 116681fde33d..89fe7b9fe26b 100644 --- a/drivers/hwmon/mlxreg-fan.c +++ b/drivers/hwmon/mlxreg-fan.c @@ -315,8 +315,8 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, { struct mlxreg_fan *fan = cdev->devdata; unsigned long cur_state; + int i, config = 0; u32 regval; - int i; int err; /* @@ -329,6 +329,12 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, * overwritten. */ if (state >= MLXREG_FAN_SPEED_MIN && state <= MLXREG_FAN_SPEED_MAX) { + /* + * This is configuration change, which is only supported through sysfs. + * For configuration non-zero value is to be returned to avoid thermal + * statistics update. + */ + config = 1; state -= MLXREG_FAN_MAX_STATE; for (i = 0; i < state; i++) fan->cooling_levels[i] = state; @@ -343,7 +349,7 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, cur_state = MLXREG_FAN_PWM_DUTY2STATE(regval); if (state < cur_state) - return 0; + return config; state = cur_state; } @@ -359,7 +365,7 @@ static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev, dev_err(fan->dev, "Failed to write PWM duty\n"); return err; } - return 0; + return config; } static const struct thermal_cooling_device_ops mlxreg_fan_cooling_ops = { diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index 0d68a78be980..ae664613289c 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -340,18 +340,11 @@ static ssize_t occ_show_temp_10(struct device *dev, if (val == OCC_TEMP_SENSOR_FAULT) return -EREMOTEIO; - /* - * VRM doesn't return temperature, only alarm bit. This - * attribute maps to tempX_alarm instead of tempX_input for - * VRM - */ - if (temp->fru_type != OCC_FRU_TYPE_VRM) { - /* sensor not ready */ - if (val == 0) - return -EAGAIN; + /* sensor not ready */ + if (val == 0) + return -EAGAIN; - val *= 1000; - } + val *= 1000; break; case 2: val = temp->fru_type; @@ -886,7 +879,7 @@ static int occ_setup_sensor_attrs(struct occ *occ) 0, i); attr++; - if (sensors->temp.version > 1 && + if (sensors->temp.version == 2 && temp->fru_type == OCC_FRU_TYPE_VRM) { snprintf(attr->name, sizeof(attr->name), "temp%d_alarm", s); diff --git a/drivers/hwmon/pmbus/ibm-cffps.c b/drivers/hwmon/pmbus/ibm-cffps.c index df712ce4b164..53f7d1418bc9 100644 --- a/drivers/hwmon/pmbus/ibm-cffps.c +++ b/drivers/hwmon/pmbus/ibm-cffps.c @@ -171,8 +171,14 @@ static ssize_t ibm_cffps_debugfs_read(struct file *file, char __user *buf, cmd = CFFPS_SN_CMD; break; case CFFPS_DEBUGFS_MAX_POWER_OUT: - rc = i2c_smbus_read_word_swapped(psu->client, - CFFPS_MAX_POWER_OUT_CMD); + if (psu->version == cffps1) { + rc = i2c_smbus_read_word_swapped(psu->client, + CFFPS_MAX_POWER_OUT_CMD); + } else { + rc = i2c_smbus_read_word_data(psu->client, + CFFPS_MAX_POWER_OUT_CMD); + } + if (rc < 0) return rc; diff --git a/drivers/hwmon/pmbus/mp2975.c b/drivers/hwmon/pmbus/mp2975.c index eb94bd5f4e2a..51986adfbf47 100644 --- a/drivers/hwmon/pmbus/mp2975.c +++ b/drivers/hwmon/pmbus/mp2975.c @@ -54,7 +54,7 @@ #define MP2975_RAIL2_FUNC (PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT | \ PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT | \ - PMBUS_PHASE_VIRTUAL) + PMBUS_HAVE_POUT | PMBUS_PHASE_VIRTUAL) struct mp2975_data { struct pmbus_driver_info info; diff --git a/drivers/hwmon/tmp421.c b/drivers/hwmon/tmp421.c index ede66ea6a730..b963a369c5ab 100644 --- a/drivers/hwmon/tmp421.c +++ b/drivers/hwmon/tmp421.c @@ -100,71 +100,81 @@ struct tmp421_data { s16 temp[4]; }; -static int temp_from_s16(s16 reg) +static int temp_from_raw(u16 reg, bool extended) { /* Mask out status bits */ int temp = reg & ~0xf; - return (temp * 1000 + 128) / 256; -} - -static int temp_from_u16(u16 reg) -{ - /* Mask out status bits */ - int temp = reg & ~0xf; - - /* Add offset for extended temperature range. */ - temp -= 64 * 256; + if (extended) + temp = temp - 64 * 256; + else + temp = (s16)temp; - return (temp * 1000 + 128) / 256; + return DIV_ROUND_CLOSEST(temp * 1000, 256); } -static struct tmp421_data *tmp421_update_device(struct device *dev) +static int tmp421_update_device(struct tmp421_data *data) { - struct tmp421_data *data = dev_get_drvdata(dev); struct i2c_client *client = data->client; + int ret = 0; int i; mutex_lock(&data->update_lock); if (time_after(jiffies, data->last_updated + (HZ / 2)) || !data->valid) { - data->config = i2c_smbus_read_byte_data(client, - TMP421_CONFIG_REG_1); + ret = i2c_smbus_read_byte_data(client, TMP421_CONFIG_REG_1); + if (ret < 0) + goto exit; + data->config = ret; for (i = 0; i < data->channels; i++) { - data->temp[i] = i2c_smbus_read_byte_data(client, - TMP421_TEMP_MSB[i]) << 8; - data->temp[i] |= i2c_smbus_read_byte_data(client, - TMP421_TEMP_LSB[i]); + ret = i2c_smbus_read_byte_data(client, TMP421_TEMP_MSB[i]); + if (ret < 0) + goto exit; + data->temp[i] = ret << 8; + + ret = i2c_smbus_read_byte_data(client, TMP421_TEMP_LSB[i]); + if (ret < 0) + goto exit; + data->temp[i] |= ret; } data->last_updated = jiffies; data->valid = 1; } +exit: mutex_unlock(&data->update_lock); - return data; + if (ret < 0) { + data->valid = 0; + return ret; + } + + return 0; } static int tmp421_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { - struct tmp421_data *tmp421 = tmp421_update_device(dev); + struct tmp421_data *tmp421 = dev_get_drvdata(dev); + int ret = 0; + + ret = tmp421_update_device(tmp421); + if (ret) + return ret; switch (attr) { case hwmon_temp_input: - if (tmp421->config & TMP421_CONFIG_RANGE) - *val = temp_from_u16(tmp421->temp[channel]); - else - *val = temp_from_s16(tmp421->temp[channel]); + *val = temp_from_raw(tmp421->temp[channel], + tmp421->config & TMP421_CONFIG_RANGE); return 0; case hwmon_temp_fault: /* - * The OPEN bit signals a fault. This is bit 0 of the temperature - * register (low byte). + * Any of OPEN or /PVLD bits indicate a hardware mulfunction + * and the conversion result may be incorrect */ - *val = tmp421->temp[channel] & 0x01; + *val = !!(tmp421->temp[channel] & 0x03); return 0; default: return -EOPNOTSUPP; @@ -177,9 +187,6 @@ static umode_t tmp421_is_visible(const void *data, enum hwmon_sensor_types type, { switch (attr) { case hwmon_temp_fault: - if (channel == 0) - return 0; - return 0444; case hwmon_temp_input: return 0444; default: diff --git a/drivers/hwmon/w83791d.c b/drivers/hwmon/w83791d.c index 37b25a1474c4..3c1be2c11fdf 100644 --- a/drivers/hwmon/w83791d.c +++ b/drivers/hwmon/w83791d.c @@ -273,9 +273,6 @@ struct w83791d_data { char valid; /* !=0 if following fields are valid */ unsigned long last_updated; /* In jiffies */ - /* array of 2 pointers to subclients */ - struct i2c_client *lm75[2]; - /* volts */ u8 in[NUMBER_OF_VIN]; /* Register value */ u8 in_max[NUMBER_OF_VIN]; /* Register value */ @@ -1257,7 +1254,6 @@ static const struct attribute_group w83791d_group_fanpwm45 = { static int w83791d_detect_subclients(struct i2c_client *client) { struct i2c_adapter *adapter = client->adapter; - struct w83791d_data *data = i2c_get_clientdata(client); int address = client->addr; int i, id; u8 val; @@ -1280,22 +1276,19 @@ static int w83791d_detect_subclients(struct i2c_client *client) } val = w83791d_read(client, W83791D_REG_I2C_SUBADDR); - if (!(val & 0x08)) - data->lm75[0] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + (val & 0x7)); - if (!(val & 0x80)) { - if (!IS_ERR(data->lm75[0]) && - ((val & 0x7) == ((val >> 4) & 0x7))) { - dev_err(&client->dev, - "duplicate addresses 0x%x, " - "use force_subclient\n", - data->lm75[0]->addr); - return -ENODEV; - } - data->lm75[1] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + ((val >> 4) & 0x7)); + + if (!(val & 0x88) && (val & 0x7) == ((val >> 4) & 0x7)) { + dev_err(&client->dev, + "duplicate addresses 0x%x, use force_subclient\n", 0x48 + (val & 0x7)); + return -ENODEV; } + if (!(val & 0x08)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + (val & 0x7)); + + if (!(val & 0x80)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + ((val >> 4) & 0x7)); + return 0; } diff --git a/drivers/hwmon/w83792d.c b/drivers/hwmon/w83792d.c index abd5c3a722b9..1f175f381350 100644 --- a/drivers/hwmon/w83792d.c +++ b/drivers/hwmon/w83792d.c @@ -264,9 +264,6 @@ struct w83792d_data { char valid; /* !=0 if following fields are valid */ unsigned long last_updated; /* In jiffies */ - /* array of 2 pointers to subclients */ - struct i2c_client *lm75[2]; - u8 in[9]; /* Register value */ u8 in_max[9]; /* Register value */ u8 in_min[9]; /* Register value */ @@ -927,7 +924,6 @@ w83792d_detect_subclients(struct i2c_client *new_client) int address = new_client->addr; u8 val; struct i2c_adapter *adapter = new_client->adapter; - struct w83792d_data *data = i2c_get_clientdata(new_client); id = i2c_adapter_id(adapter); if (force_subclients[0] == id && force_subclients[1] == address) { @@ -946,21 +942,19 @@ w83792d_detect_subclients(struct i2c_client *new_client) } val = w83792d_read_value(new_client, W83792D_REG_I2C_SUBADDR); - if (!(val & 0x08)) - data->lm75[0] = devm_i2c_new_dummy_device(&new_client->dev, adapter, - 0x48 + (val & 0x7)); - if (!(val & 0x80)) { - if (!IS_ERR(data->lm75[0]) && - ((val & 0x7) == ((val >> 4) & 0x7))) { - dev_err(&new_client->dev, - "duplicate addresses 0x%x, use force_subclient\n", - data->lm75[0]->addr); - return -ENODEV; - } - data->lm75[1] = devm_i2c_new_dummy_device(&new_client->dev, adapter, - 0x48 + ((val >> 4) & 0x7)); + + if (!(val & 0x88) && (val & 0x7) == ((val >> 4) & 0x7)) { + dev_err(&new_client->dev, + "duplicate addresses 0x%x, use force_subclient\n", 0x48 + (val & 0x7)); + return -ENODEV; } + if (!(val & 0x08)) + devm_i2c_new_dummy_device(&new_client->dev, adapter, 0x48 + (val & 0x7)); + + if (!(val & 0x80)) + devm_i2c_new_dummy_device(&new_client->dev, adapter, 0x48 + ((val >> 4) & 0x7)); + return 0; } diff --git a/drivers/hwmon/w83793.c b/drivers/hwmon/w83793.c index e7d0484eabe4..1d2854de1cfc 100644 --- a/drivers/hwmon/w83793.c +++ b/drivers/hwmon/w83793.c @@ -202,7 +202,6 @@ static inline s8 TEMP_TO_REG(long val, s8 min, s8 max) } struct w83793_data { - struct i2c_client *lm75[2]; struct device *hwmon_dev; struct mutex update_lock; char valid; /* !=0 if following fields are valid */ @@ -1566,7 +1565,6 @@ w83793_detect_subclients(struct i2c_client *client) int address = client->addr; u8 tmp; struct i2c_adapter *adapter = client->adapter; - struct w83793_data *data = i2c_get_clientdata(client); id = i2c_adapter_id(adapter); if (force_subclients[0] == id && force_subclients[1] == address) { @@ -1586,21 +1584,19 @@ w83793_detect_subclients(struct i2c_client *client) } tmp = w83793_read_value(client, W83793_REG_I2C_SUBADDR); - if (!(tmp & 0x08)) - data->lm75[0] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + (tmp & 0x7)); - if (!(tmp & 0x80)) { - if (!IS_ERR(data->lm75[0]) - && ((tmp & 0x7) == ((tmp >> 4) & 0x7))) { - dev_err(&client->dev, - "duplicate addresses 0x%x, " - "use force_subclients\n", data->lm75[0]->addr); - return -ENODEV; - } - data->lm75[1] = devm_i2c_new_dummy_device(&client->dev, adapter, - 0x48 + ((tmp >> 4) & 0x7)); + + if (!(tmp & 0x88) && (tmp & 0x7) == ((tmp >> 4) & 0x7)) { + dev_err(&client->dev, + "duplicate addresses 0x%x, use force_subclient\n", 0x48 + (tmp & 0x7)); + return -ENODEV; } + if (!(tmp & 0x08)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + (tmp & 0x7)); + + if (!(tmp & 0x80)) + devm_i2c_new_dummy_device(&client->dev, adapter, 0x48 + ((tmp >> 4) & 0x7)); + return 0; } diff --git a/drivers/i2c/busses/i2c-mlxcpld.c b/drivers/i2c/busses/i2c-mlxcpld.c index 4e0b7c2882ce..015e11c4663f 100644 --- a/drivers/i2c/busses/i2c-mlxcpld.c +++ b/drivers/i2c/busses/i2c-mlxcpld.c @@ -49,7 +49,7 @@ #define MLXCPLD_LPCI2C_NACK_IND 2 #define MLXCPLD_I2C_FREQ_1000KHZ_SET 0x04 -#define MLXCPLD_I2C_FREQ_400KHZ_SET 0x0f +#define MLXCPLD_I2C_FREQ_400KHZ_SET 0x0c #define MLXCPLD_I2C_FREQ_100KHZ_SET 0x42 enum mlxcpld_i2c_frequency { @@ -495,7 +495,7 @@ mlxcpld_i2c_set_frequency(struct mlxcpld_i2c_priv *priv, return err; /* Set frequency only if it is not 100KHz, which is default. */ - switch ((data->reg & data->mask) >> data->bit) { + switch ((regval & data->mask) >> data->bit) { case MLXCPLD_I2C_FREQ_1000KHZ: freq = MLXCPLD_I2C_FREQ_1000KHZ_SET; break; diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c index 477480d1de6b..7d4b3eb7077a 100644 --- a/drivers/i2c/busses/i2c-mt65xx.c +++ b/drivers/i2c/busses/i2c-mt65xx.c @@ -41,6 +41,8 @@ #define I2C_HANDSHAKE_RST 0x0020 #define I2C_FIFO_ADDR_CLR 0x0001 #define I2C_DELAY_LEN 0x0002 +#define I2C_ST_START_CON 0x8001 +#define I2C_FS_START_CON 0x1800 #define I2C_TIME_CLR_VALUE 0x0000 #define I2C_TIME_DEFAULT_VALUE 0x0003 #define I2C_WRRD_TRANAC_VALUE 0x0002 @@ -480,6 +482,7 @@ static void mtk_i2c_init_hw(struct mtk_i2c *i2c) { u16 control_reg; u16 intr_stat_reg; + u16 ext_conf_val; mtk_i2c_writew(i2c, I2C_CHN_CLR_FLAG, OFFSET_START); intr_stat_reg = mtk_i2c_readw(i2c, OFFSET_INTR_STAT); @@ -518,8 +521,13 @@ static void mtk_i2c_init_hw(struct mtk_i2c *i2c) if (i2c->dev_comp->ltiming_adjust) mtk_i2c_writew(i2c, i2c->ltiming_reg, OFFSET_LTIMING); + if (i2c->speed_hz <= I2C_MAX_STANDARD_MODE_FREQ) + ext_conf_val = I2C_ST_START_CON; + else + ext_conf_val = I2C_FS_START_CON; + if (i2c->dev_comp->timing_adjust) { - mtk_i2c_writew(i2c, i2c->ac_timing.ext, OFFSET_EXT_CONF); + ext_conf_val = i2c->ac_timing.ext; mtk_i2c_writew(i2c, i2c->ac_timing.inter_clk_div, OFFSET_CLOCK_DIV); mtk_i2c_writew(i2c, I2C_SCL_MIS_COMP_VALUE, @@ -544,6 +552,7 @@ static void mtk_i2c_init_hw(struct mtk_i2c *i2c) OFFSET_HS_STA_STO_AC_TIMING); } } + mtk_i2c_writew(i2c, ext_conf_val, OFFSET_EXT_CONF); /* If use i2c pin from PMIC mt6397 side, need set PATH_DIR first */ if (i2c->have_pmic) diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index aaeeacc12121..546cc935e035 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -454,6 +454,7 @@ static int i2c_acpi_notify(struct notifier_block *nb, unsigned long value, break; i2c_acpi_register_device(adapter, adev, &info); + put_device(&adapter->dev); break; case ACPI_RECONFIG_DEVICE_REMOVE: if (!acpi_device_enumerated(adev)) diff --git a/drivers/iio/test/Makefile b/drivers/iio/test/Makefile index f1099b495301..467519a2027e 100644 --- a/drivers/iio/test/Makefile +++ b/drivers/iio/test/Makefile @@ -5,3 +5,4 @@ # Keep in alphabetical order obj-$(CONFIG_IIO_TEST_FORMAT) += iio-test-format.o +CFLAGS_iio-test-format.o += $(DISABLE_STRUCTLEAK_PLUGIN) diff --git a/drivers/interconnect/qcom/sdm660.c b/drivers/interconnect/qcom/sdm660.c index 632dbdd21915..fb23a5b780a4 100644 --- a/drivers/interconnect/qcom/sdm660.c +++ b/drivers/interconnect/qcom/sdm660.c @@ -44,9 +44,9 @@ #define NOC_PERM_MODE_BYPASS (1 << NOC_QOS_MODE_BYPASS) #define NOC_QOS_PRIORITYn_ADDR(n) (0x8 + (n * 0x1000)) -#define NOC_QOS_PRIORITY_MASK 0xf +#define NOC_QOS_PRIORITY_P1_MASK 0xc +#define NOC_QOS_PRIORITY_P0_MASK 0x3 #define NOC_QOS_PRIORITY_P1_SHIFT 0x2 -#define NOC_QOS_PRIORITY_P0_SHIFT 0x3 #define NOC_QOS_MODEn_ADDR(n) (0xc + (n * 0x1000)) #define NOC_QOS_MODEn_MASK 0x3 @@ -173,6 +173,16 @@ static const struct clk_bulk_data bus_mm_clocks[] = { { .id = "iface" }, }; +static const struct clk_bulk_data bus_a2noc_clocks[] = { + { .id = "bus" }, + { .id = "bus_a" }, + { .id = "ipa" }, + { .id = "ufs_axi" }, + { .id = "aggre2_ufs_axi" }, + { .id = "aggre2_usb3_axi" }, + { .id = "cfg_noc_usb2_axi" }, +}; + /** * struct qcom_icc_provider - Qualcomm specific interconnect provider * @provider: generic interconnect provider @@ -307,7 +317,7 @@ DEFINE_QNODE(slv_bimc_cfg, SDM660_SLAVE_BIMC_CFG, 4, -1, 56, true, -1, 0, -1, 0) DEFINE_QNODE(slv_prng, SDM660_SLAVE_PRNG, 4, -1, 44, true, -1, 0, -1, 0); DEFINE_QNODE(slv_spdm, SDM660_SLAVE_SPDM, 4, -1, 60, true, -1, 0, -1, 0); DEFINE_QNODE(slv_qdss_cfg, SDM660_SLAVE_QDSS_CFG, 4, -1, 63, true, -1, 0, -1, 0); -DEFINE_QNODE(slv_cnoc_mnoc_cfg, SDM660_SLAVE_BLSP_1, 4, -1, 66, true, -1, 0, -1, SDM660_MASTER_CNOC_MNOC_CFG); +DEFINE_QNODE(slv_cnoc_mnoc_cfg, SDM660_SLAVE_CNOC_MNOC_CFG, 4, -1, 66, true, -1, 0, -1, SDM660_MASTER_CNOC_MNOC_CFG); DEFINE_QNODE(slv_snoc_cfg, SDM660_SLAVE_SNOC_CFG, 4, -1, 70, true, -1, 0, -1, 0); DEFINE_QNODE(slv_qm_cfg, SDM660_SLAVE_QM_CFG, 4, -1, 212, true, -1, 0, -1, 0); DEFINE_QNODE(slv_clk_ctl, SDM660_SLAVE_CLK_CTL, 4, -1, 47, true, -1, 0, -1, 0); @@ -624,13 +634,12 @@ static int qcom_icc_noc_set_qos_priority(struct regmap *rmap, /* Must be updated one at a time, P1 first, P0 last */ val = qos->areq_prio << NOC_QOS_PRIORITY_P1_SHIFT; rc = regmap_update_bits(rmap, NOC_QOS_PRIORITYn_ADDR(qos->qos_port), - NOC_QOS_PRIORITY_MASK, val); + NOC_QOS_PRIORITY_P1_MASK, val); if (rc) return rc; - val = qos->prio_level << NOC_QOS_PRIORITY_P0_SHIFT; return regmap_update_bits(rmap, NOC_QOS_PRIORITYn_ADDR(qos->qos_port), - NOC_QOS_PRIORITY_MASK, val); + NOC_QOS_PRIORITY_P0_MASK, qos->prio_level); } static int qcom_icc_set_noc_qos(struct icc_node *src, u64 max_bw) @@ -810,6 +819,10 @@ static int qnoc_probe(struct platform_device *pdev) qp->bus_clks = devm_kmemdup(dev, bus_mm_clocks, sizeof(bus_mm_clocks), GFP_KERNEL); qp->num_clks = ARRAY_SIZE(bus_mm_clocks); + } else if (of_device_is_compatible(dev->of_node, "qcom,sdm660-a2noc")) { + qp->bus_clks = devm_kmemdup(dev, bus_a2noc_clocks, + sizeof(bus_a2noc_clocks), GFP_KERNEL); + qp->num_clks = ARRAY_SIZE(bus_a2noc_clocks); } else { if (of_device_is_compatible(dev->of_node, "qcom,sdm660-bimc")) qp->is_bimc_node = true; diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 124c41adeca1..c5c71b7ab7e8 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -308,7 +308,6 @@ config APPLE_DART config ARM_SMMU tristate "ARM Ltd. System MMU (SMMU) Support" depends on ARM64 || ARM || (COMPILE_TEST && !GENERIC_ATOMIC64) - depends on QCOM_SCM || !QCOM_SCM #if QCOM_SCM=m this can't be =y select IOMMU_API select IOMMU_IO_PGTABLE_LPAE select ARM_DMA_USE_IOMMU if ARM @@ -438,7 +437,7 @@ config QCOM_IOMMU # Note: iommu drivers cannot (yet?) be built as modules bool "Qualcomm IOMMU Support" depends on ARCH_QCOM || (COMPILE_TEST && !GENERIC_ATOMIC64) - depends on QCOM_SCM=y + select QCOM_SCM select IOMMU_API select IOMMU_IO_PGTABLE_LPAE select ARM_DMA_USE_IOMMU diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index 559db9259e65..fdfa39ec2a4d 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -183,7 +183,6 @@ struct apple_dart_master_cfg { static struct platform_driver apple_dart_driver; static const struct iommu_ops apple_dart_iommu_ops; -static const struct iommu_flush_ops apple_dart_tlb_ops; static struct apple_dart_domain *to_dart_domain(struct iommu_domain *dom) { @@ -338,22 +337,6 @@ static void apple_dart_iotlb_sync_map(struct iommu_domain *domain, apple_dart_domain_flush_tlb(to_dart_domain(domain)); } -static void apple_dart_tlb_flush_all(void *cookie) -{ - apple_dart_domain_flush_tlb(cookie); -} - -static void apple_dart_tlb_flush_walk(unsigned long iova, size_t size, - size_t granule, void *cookie) -{ - apple_dart_domain_flush_tlb(cookie); -} - -static const struct iommu_flush_ops apple_dart_tlb_ops = { - .tlb_flush_all = apple_dart_tlb_flush_all, - .tlb_flush_walk = apple_dart_tlb_flush_walk, -}; - static phys_addr_t apple_dart_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { @@ -435,7 +418,6 @@ static int apple_dart_finalize_domain(struct iommu_domain *domain, .ias = 32, .oas = 36, .coherent_walk = 1, - .tlb = &apple_dart_tlb_ops, .iommu_dev = dart->dev, }; @@ -661,16 +643,34 @@ static int apple_dart_of_xlate(struct device *dev, struct of_phandle_args *args) return -EINVAL; } +static DEFINE_MUTEX(apple_dart_groups_lock); + +static void apple_dart_release_group(void *iommu_data) +{ + int i, sid; + struct apple_dart_stream_map *stream_map; + struct apple_dart_master_cfg *group_master_cfg = iommu_data; + + mutex_lock(&apple_dart_groups_lock); + + for_each_stream_map(i, group_master_cfg, stream_map) + for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) + stream_map->dart->sid2group[sid] = NULL; + + kfree(iommu_data); + mutex_unlock(&apple_dart_groups_lock); +} + static struct iommu_group *apple_dart_device_group(struct device *dev) { - static DEFINE_MUTEX(lock); int i, sid; struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev); struct apple_dart_stream_map *stream_map; + struct apple_dart_master_cfg *group_master_cfg; struct iommu_group *group = NULL; struct iommu_group *res = ERR_PTR(-EINVAL); - mutex_lock(&lock); + mutex_lock(&apple_dart_groups_lock); for_each_stream_map(i, cfg, stream_map) { for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) { @@ -698,6 +698,20 @@ static struct iommu_group *apple_dart_device_group(struct device *dev) #endif group = generic_device_group(dev); + res = ERR_PTR(-ENOMEM); + if (!group) + goto out; + + group_master_cfg = kzalloc(sizeof(*group_master_cfg), GFP_KERNEL); + if (!group_master_cfg) { + iommu_group_put(group); + goto out; + } + + memcpy(group_master_cfg, cfg, sizeof(*group_master_cfg)); + iommu_group_set_iommudata(group, group_master_cfg, + apple_dart_release_group); + for_each_stream_map(i, cfg, stream_map) for_each_set_bit(sid, &stream_map->sidmap, DART_MAX_STREAMS) stream_map->dart->sid2group[sid] = group; @@ -705,7 +719,7 @@ static struct iommu_group *apple_dart_device_group(struct device *dev) res = group; out: - mutex_unlock(&lock); + mutex_unlock(&apple_dart_groups_lock); return res; } diff --git a/drivers/iommu/arm/arm-smmu/Makefile b/drivers/iommu/arm/arm-smmu/Makefile index e240a7bcf310..b0cc01aa20c9 100644 --- a/drivers/iommu/arm/arm-smmu/Makefile +++ b/drivers/iommu/arm/arm-smmu/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_QCOM_IOMMU) += qcom_iommu.o obj-$(CONFIG_ARM_SMMU) += arm_smmu.o -arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o arm-smmu-qcom.o +arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o +arm_smmu-$(CONFIG_ARM_SMMU_QCOM) += arm-smmu-qcom.o diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c index 9f465e146799..2c25cce38060 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c @@ -215,7 +215,8 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu) of_device_is_compatible(np, "nvidia,tegra186-smmu")) return nvidia_smmu_impl_init(smmu); - smmu = qcom_smmu_impl_init(smmu); + if (IS_ENABLED(CONFIG_ARM_SMMU_QCOM)) + smmu = qcom_smmu_impl_init(smmu); if (of_device_is_compatible(np, "marvell,ap806-smmu-500")) smmu->impl = &mrvl_mmu500_impl; diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 0ec5514c9980..b7708b93f3fa 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1942,18 +1942,18 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, reason = dmar_get_fault_reason(fault_reason, &fault_type); if (fault_type == INTR_REMAP) - pr_err("[INTR-REMAP] Request device [0x%02x:0x%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n", + pr_err("[INTR-REMAP] Request device [%02x:%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n", source_id >> 8, PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr >> 48, fault_reason, reason); else if (pasid == INVALID_IOASID) - pr_err("[%s NO_PASID] Request device [0x%02x:0x%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", + pr_err("[%s NO_PASID] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", type ? "DMA Read" : "DMA Write", source_id >> 8, PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason); else - pr_err("[%s PASID 0x%x] Request device [0x%02x:0x%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", + pr_err("[%s PASID 0x%x] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", type ? "DMA Read" : "DMA Write", pasid, source_id >> 8, PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr, diff --git a/drivers/ipack/devices/ipoctal.c b/drivers/ipack/devices/ipoctal.c index c14e65a5d38f..c709861198e5 100644 --- a/drivers/ipack/devices/ipoctal.c +++ b/drivers/ipack/devices/ipoctal.c @@ -33,6 +33,7 @@ struct ipoctal_channel { unsigned int pointer_read; unsigned int pointer_write; struct tty_port tty_port; + bool tty_registered; union scc2698_channel __iomem *regs; union scc2698_block __iomem *block_regs; unsigned int board_id; @@ -81,22 +82,34 @@ static int ipoctal_port_activate(struct tty_port *port, struct tty_struct *tty) return 0; } -static int ipoctal_open(struct tty_struct *tty, struct file *file) +static int ipoctal_install(struct tty_driver *driver, struct tty_struct *tty) { struct ipoctal_channel *channel = dev_get_drvdata(tty->dev); struct ipoctal *ipoctal = chan_to_ipoctal(channel, tty->index); - int err; - - tty->driver_data = channel; + int res; if (!ipack_get_carrier(ipoctal->dev)) return -EBUSY; - err = tty_port_open(&channel->tty_port, tty, file); - if (err) - ipack_put_carrier(ipoctal->dev); + res = tty_standard_install(driver, tty); + if (res) + goto err_put_carrier; + + tty->driver_data = channel; + + return 0; + +err_put_carrier: + ipack_put_carrier(ipoctal->dev); + + return res; +} + +static int ipoctal_open(struct tty_struct *tty, struct file *file) +{ + struct ipoctal_channel *channel = tty->driver_data; - return err; + return tty_port_open(&channel->tty_port, tty, file); } static void ipoctal_reset_stats(struct ipoctal_stats *stats) @@ -264,7 +277,6 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, int res; int i; struct tty_driver *tty; - char name[20]; struct ipoctal_channel *channel; struct ipack_region *region; void __iomem *addr; @@ -355,8 +367,11 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, /* Fill struct tty_driver with ipoctal data */ tty->owner = THIS_MODULE; tty->driver_name = KBUILD_MODNAME; - sprintf(name, KBUILD_MODNAME ".%d.%d.", bus_nr, slot); - tty->name = name; + tty->name = kasprintf(GFP_KERNEL, KBUILD_MODNAME ".%d.%d.", bus_nr, slot); + if (!tty->name) { + res = -ENOMEM; + goto err_put_driver; + } tty->major = 0; tty->minor_start = 0; @@ -371,8 +386,7 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, res = tty_register_driver(tty); if (res) { dev_err(&ipoctal->dev->dev, "Can't register tty driver.\n"); - tty_driver_kref_put(tty); - return res; + goto err_free_name; } /* Save struct tty_driver for use it when uninstalling the device */ @@ -383,7 +397,9 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, channel = &ipoctal->channel[i]; tty_port_init(&channel->tty_port); - tty_port_alloc_xmit_buf(&channel->tty_port); + res = tty_port_alloc_xmit_buf(&channel->tty_port); + if (res) + continue; channel->tty_port.ops = &ipoctal_tty_port_ops; ipoctal_reset_stats(&channel->stats); @@ -391,13 +407,15 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, spin_lock_init(&channel->lock); channel->pointer_read = 0; channel->pointer_write = 0; - tty_dev = tty_port_register_device(&channel->tty_port, tty, i, NULL); + tty_dev = tty_port_register_device_attr(&channel->tty_port, tty, + i, NULL, channel, NULL); if (IS_ERR(tty_dev)) { dev_err(&ipoctal->dev->dev, "Failed to register tty device.\n"); + tty_port_free_xmit_buf(&channel->tty_port); tty_port_destroy(&channel->tty_port); continue; } - dev_set_drvdata(tty_dev, channel); + channel->tty_registered = true; } /* @@ -409,6 +427,13 @@ static int ipoctal_inst_slot(struct ipoctal *ipoctal, unsigned int bus_nr, ipoctal_irq_handler, ipoctal); return 0; + +err_free_name: + kfree(tty->name); +err_put_driver: + tty_driver_kref_put(tty); + + return res; } static inline int ipoctal_copy_write_buffer(struct ipoctal_channel *channel, @@ -648,6 +673,7 @@ static void ipoctal_cleanup(struct tty_struct *tty) static const struct tty_operations ipoctal_fops = { .ioctl = NULL, + .install = ipoctal_install, .open = ipoctal_open, .close = ipoctal_close, .write = ipoctal_write_tty, @@ -690,12 +716,17 @@ static void __ipoctal_remove(struct ipoctal *ipoctal) for (i = 0; i < NR_CHANNELS; i++) { struct ipoctal_channel *channel = &ipoctal->channel[i]; + + if (!channel->tty_registered) + continue; + tty_unregister_device(ipoctal->tty_drv, i); tty_port_free_xmit_buf(&channel->tty_port); tty_port_destroy(&channel->tty_port); } tty_unregister_driver(ipoctal->tty_drv); + kfree(ipoctal->tty_drv->name); tty_driver_kref_put(ipoctal->tty_drv); kfree(ipoctal); } diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c index cb0afe897162..7313454e403a 100644 --- a/drivers/isdn/capi/kcapi.c +++ b/drivers/isdn/capi/kcapi.c @@ -480,6 +480,11 @@ int detach_capi_ctr(struct capi_ctr *ctr) ctr_down(ctr, CAPI_CTR_DETACHED); + if (ctr->cnr < 1 || ctr->cnr - 1 >= CAPI_MAXCONTR) { + err = -EINVAL; + goto unlock_out; + } + if (capi_controller[ctr->cnr - 1] != ctr) { err = -EINVAL; goto unlock_out; diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index 2a1ddd47a096..a52f275f8263 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -949,8 +949,8 @@ nj_release(struct tiger_hw *card) nj_disable_hwirq(card); mode_tiger(&card->bc[0], ISDN_P_NONE); mode_tiger(&card->bc[1], ISDN_P_NONE); - card->isac.release(&card->isac); spin_unlock_irqrestore(&card->lock, flags); + card->isac.release(&card->isac); release_region(card->base, card->base_s); card->base_s = 0; } diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig index 157c924686e4..80321e03809a 100644 --- a/drivers/media/platform/Kconfig +++ b/drivers/media/platform/Kconfig @@ -565,7 +565,7 @@ config VIDEO_QCOM_VENUS depends on VIDEO_DEV && VIDEO_V4L2 && QCOM_SMEM depends on (ARCH_QCOM && IOMMU_DMA) || COMPILE_TEST select QCOM_MDT_LOADER if ARCH_QCOM - select QCOM_SCM if ARCH_QCOM + select QCOM_SCM select VIDEOBUF2_DMA_CONTIG select V4L2_MEM2MEM_DEV help diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 71313961cc54..95b3511b0560 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -547,7 +547,7 @@ config MMC_SDHCI_MSM depends on MMC_SDHCI_PLTFM select MMC_SDHCI_IO_ACCESSORS select MMC_CQHCI - select QCOM_SCM if MMC_CRYPTO && ARCH_QCOM + select QCOM_SCM if MMC_CRYPTO help This selects the Secure Digital Host Controller Interface (SDHCI) support present in Qualcomm SOCs. The controller supports diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 3f28eb4d17fe..8f36536cb1b6 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -746,7 +746,7 @@ static void meson_mmc_desc_chain_transfer(struct mmc_host *mmc, u32 cmd_cfg) writel(start, host->regs + SD_EMMC_START); } -/* local sg copy to buffer version with _to/fromio usage for dram_access_quirk */ +/* local sg copy for dram_access_quirk */ static void meson_mmc_copy_buffer(struct meson_host *host, struct mmc_data *data, size_t buflen, bool to_buffer) { @@ -764,21 +764,27 @@ static void meson_mmc_copy_buffer(struct meson_host *host, struct mmc_data *data sg_miter_start(&miter, sgl, nents, sg_flags); while ((offset < buflen) && sg_miter_next(&miter)) { - unsigned int len; + unsigned int buf_offset = 0; + unsigned int len, left; + u32 *buf = miter.addr; len = min(miter.length, buflen - offset); + left = len; - /* When dram_access_quirk, the bounce buffer is a iomem mapping */ - if (host->dram_access_quirk) { - if (to_buffer) - memcpy_toio(host->bounce_iomem_buf + offset, miter.addr, len); - else - memcpy_fromio(miter.addr, host->bounce_iomem_buf + offset, len); + if (to_buffer) { + do { + writel(*buf++, host->bounce_iomem_buf + offset + buf_offset); + + buf_offset += 4; + left -= 4; + } while (left); } else { - if (to_buffer) - memcpy(host->bounce_buf + offset, miter.addr, len); - else - memcpy(miter.addr, host->bounce_buf + offset, len); + do { + *buf++ = readl(host->bounce_iomem_buf + offset + buf_offset); + + buf_offset += 4; + left -= 4; + } while (left); } offset += len; @@ -830,7 +836,11 @@ static void meson_mmc_start_cmd(struct mmc_host *mmc, struct mmc_command *cmd) if (data->flags & MMC_DATA_WRITE) { cmd_cfg |= CMD_CFG_DATA_WR; WARN_ON(xfer_bytes > host->bounce_buf_size); - meson_mmc_copy_buffer(host, data, xfer_bytes, true); + if (host->dram_access_quirk) + meson_mmc_copy_buffer(host, data, xfer_bytes, true); + else + sg_copy_to_buffer(data->sg, data->sg_len, + host->bounce_buf, xfer_bytes); dma_wmb(); } @@ -849,12 +859,43 @@ static void meson_mmc_start_cmd(struct mmc_host *mmc, struct mmc_command *cmd) writel(cmd->arg, host->regs + SD_EMMC_CMD_ARG); } +static int meson_mmc_validate_dram_access(struct mmc_host *mmc, struct mmc_data *data) +{ + struct scatterlist *sg; + int i; + + /* Reject request if any element offset or size is not 32bit aligned */ + for_each_sg(data->sg, sg, data->sg_len, i) { + if (!IS_ALIGNED(sg->offset, sizeof(u32)) || + !IS_ALIGNED(sg->length, sizeof(u32))) { + dev_err(mmc_dev(mmc), "unaligned sg offset %u len %u\n", + data->sg->offset, data->sg->length); + return -EINVAL; + } + } + + return 0; +} + static void meson_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq) { struct meson_host *host = mmc_priv(mmc); bool needs_pre_post_req = mrq->data && !(mrq->data->host_cookie & SD_EMMC_PRE_REQ_DONE); + /* + * The memory at the end of the controller used as bounce buffer for + * the dram_access_quirk only accepts 32bit read/write access, + * check the aligment and length of the data before starting the request. + */ + if (host->dram_access_quirk && mrq->data) { + mrq->cmd->error = meson_mmc_validate_dram_access(mmc, mrq->data); + if (mrq->cmd->error) { + mmc_request_done(mmc, mrq); + return; + } + } + if (needs_pre_post_req) { meson_mmc_get_transfer_mode(mmc, mrq); if (!meson_mmc_desc_chain_mode(mrq->data)) @@ -999,7 +1040,11 @@ static irqreturn_t meson_mmc_irq_thread(int irq, void *dev_id) if (meson_mmc_bounce_buf_read(data)) { xfer_bytes = data->blksz * data->blocks; WARN_ON(xfer_bytes > host->bounce_buf_size); - meson_mmc_copy_buffer(host, data, xfer_bytes, false); + if (host->dram_access_quirk) + meson_mmc_copy_buffer(host, data, xfer_bytes, false); + else + sg_copy_from_buffer(data->sg, data->sg_len, + host->bounce_buf, xfer_bytes); } next_cmd = meson_mmc_get_next_command(cmd); diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c index 5564d7b23e7c..d1a1c548c515 100644 --- a/drivers/mmc/host/sdhci-of-at91.c +++ b/drivers/mmc/host/sdhci-of-at91.c @@ -11,6 +11,7 @@ #include <linux/delay.h> #include <linux/err.h> #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/kernel.h> #include <linux/mmc/host.h> #include <linux/mmc/slot-gpio.h> @@ -61,7 +62,6 @@ static void sdhci_at91_set_force_card_detect(struct sdhci_host *host) static void sdhci_at91_set_clock(struct sdhci_host *host, unsigned int clock) { u16 clk; - unsigned long timeout; host->mmc->actual_clock = 0; @@ -86,16 +86,11 @@ static void sdhci_at91_set_clock(struct sdhci_host *host, unsigned int clock) sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL); /* Wait max 20 ms */ - timeout = 20; - while (!((clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL)) - & SDHCI_CLOCK_INT_STABLE)) { - if (timeout == 0) { - pr_err("%s: Internal clock never stabilised.\n", - mmc_hostname(host->mmc)); - return; - } - timeout--; - mdelay(1); + if (read_poll_timeout(sdhci_readw, clk, (clk & SDHCI_CLOCK_INT_STABLE), + 1000, 20000, false, host, SDHCI_CLOCK_CONTROL)) { + pr_err("%s: Internal clock never stabilised.\n", + mmc_hostname(host->mmc)); + return; } clk |= SDHCI_CLOCK_CARD_EN; @@ -114,6 +109,7 @@ static void sdhci_at91_reset(struct sdhci_host *host, u8 mask) { struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct sdhci_at91_priv *priv = sdhci_pltfm_priv(pltfm_host); + unsigned int tmp; sdhci_reset(host, mask); @@ -126,6 +122,10 @@ static void sdhci_at91_reset(struct sdhci_host *host, u8 mask) sdhci_writel(host, calcr | SDMMC_CALCR_ALWYSON | SDMMC_CALCR_EN, SDMMC_CALCR); + + if (read_poll_timeout(sdhci_readl, tmp, !(tmp & SDMMC_CALCR_EN), + 10, 20000, false, host, SDMMC_CALCR)) + dev_err(mmc_dev(host->mmc), "Failed to calibrate\n"); } } diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c index f0695d68c47e..97f254bdbb16 100644 --- a/drivers/net/appletalk/cops.c +++ b/drivers/net/appletalk/cops.c @@ -945,8 +945,8 @@ static int cops_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) dev->broadcast[0] = 0xFF; /* Set hardware address. */ - dev->dev_addr[0] = aa->s_node; dev->addr_len = 1; + dev_addr_set(dev, &aa->s_node); return 0; case SIOCGIFADDR: diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c index 1f8925e75b3f..388d7b3bd4c2 100644 --- a/drivers/net/appletalk/ltpc.c +++ b/drivers/net/appletalk/ltpc.c @@ -846,9 +846,8 @@ static int ltpc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) set_30 (dev,ltflags); dev->broadcast[0] = 0xFF; - dev->dev_addr[0] = aa->s_node; - dev->addr_len=1; + dev_addr_set(dev, &aa->s_node); return 0; diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index 12d085405bd0..8c3ccc7c83cd 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -207,7 +207,8 @@ static int __init arcrimi_found(struct net_device *dev) } /* get and check the station ID from offset 1 in shmem */ - dev->dev_addr[0] = arcnet_readb(lp->mem_start, COM9026_REG_R_STATION); + arcnet_set_addr(dev, arcnet_readb(lp->mem_start, + COM9026_REG_R_STATION)); arc_printk(D_NORMAL, dev, "ARCnet RIM I: station %02Xh found at IRQ %d, ShMem %lXh (%ld*%d bytes)\n", dev->dev_addr[0], @@ -324,7 +325,7 @@ static int __init arc_rimi_init(void) return -ENOMEM; if (node && node != 0xff) - dev->dev_addr[0] = node; + arcnet_set_addr(dev, node); dev->mem_start = io; dev->irq = irq; diff --git a/drivers/net/arcnet/arcdevice.h b/drivers/net/arcnet/arcdevice.h index 5d4a4c7efbbf..19e996a829c9 100644 --- a/drivers/net/arcnet/arcdevice.h +++ b/drivers/net/arcnet/arcdevice.h @@ -364,6 +364,11 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, struct net_device *dev); void arcnet_timeout(struct net_device *dev, unsigned int txqueue); +static inline void arcnet_set_addr(struct net_device *dev, u8 addr) +{ + dev_addr_set(dev, &addr); +} + /* I/O equivalents */ #ifdef CONFIG_SA1100_CT6001 diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index be618e4b9ed5..293a621e654c 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -151,7 +151,7 @@ static int __init com20020_init(void) return -ENOMEM; if (node && node != 0xff) - dev->dev_addr[0] = node; + arcnet_set_addr(dev, node); dev->netdev_ops = &com20020_netdev_ops; diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 3c8f665c1558..6382e1937cca 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -194,7 +194,7 @@ static int com20020pci_probe(struct pci_dev *pdev, SET_NETDEV_DEV(dev, &pdev->dev); dev->base_addr = ioaddr; - dev->dev_addr[0] = node; + arcnet_set_addr(dev, node); dev->sysfs_groups[0] = &com20020_state_group; dev->irq = pdev->irq; lp->card_name = "PCI COM20020"; diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c index 78043a9c5981..06e1651b594b 100644 --- a/drivers/net/arcnet/com20020.c +++ b/drivers/net/arcnet/com20020.c @@ -157,7 +157,7 @@ static int com20020_set_hwaddr(struct net_device *dev, void *addr) struct arcnet_local *lp = netdev_priv(dev); struct sockaddr *hwaddr = addr; - memcpy(dev->dev_addr, hwaddr->sa_data, 1); + dev_addr_set(dev, hwaddr->sa_data); com20020_set_subaddress(lp, ioaddr, SUB_NODE); arcnet_outb(dev->dev_addr[0], ioaddr, COM20020_REG_W_XREG); @@ -220,7 +220,7 @@ int com20020_found(struct net_device *dev, int shared) /* FIXME: do this some other way! */ if (!dev->dev_addr[0]) - dev->dev_addr[0] = arcnet_inb(ioaddr, 8); + arcnet_set_addr(dev, arcnet_inb(ioaddr, 8)); com20020_set_subaddress(lp, ioaddr, SUB_SETUP1); arcnet_outb(lp->setup, ioaddr, COM20020_REG_W_XREG); diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index b88a109b3b15..24150c933fcb 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -133,7 +133,7 @@ static int com20020_probe(struct pcmcia_device *p_dev) lp->hw.owner = THIS_MODULE; /* fill in our module parameters as defaults */ - dev->dev_addr[0] = node; + arcnet_set_addr(dev, node); p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8; p_dev->resource[0]->end = 16; diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 3856b447d38e..37b47749fc8b 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -252,7 +252,7 @@ static int __init com90io_found(struct net_device *dev) /* get and check the station ID from offset 1 in shmem */ - dev->dev_addr[0] = get_buffer_byte(dev, 1); + arcnet_set_addr(dev, get_buffer_byte(dev, 1)); err = register_netdev(dev); if (err) { diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index d8dfb9ea0de8..f49dae194284 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -531,7 +531,8 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, } /* get and check the station ID from offset 1 in shmem */ - dev->dev_addr[0] = arcnet_readb(lp->mem_start, COM9026_REG_R_STATION); + arcnet_set_addr(dev, arcnet_readb(lp->mem_start, + COM9026_REG_R_STATION)); dev->base_addr = ioaddr; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 77dc79a7f574..0c52612cb8e9 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4414,7 +4414,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) } /* success */ - memcpy(bond_dev->dev_addr, ss->__data, bond_dev->addr_len); + dev_addr_set(bond_dev, ss->__data); return 0; unwind: diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index b9e9842fed94..c48b77167fab 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -811,8 +811,8 @@ int bond_create_sysfs(struct bond_net *bn) */ if (ret == -EEXIST) { /* Is someone being kinky and naming a device bonding_master? */ - if (__dev_get_by_name(bn->net, - class_attr_bonding_masters.attr.name)) + if (netdev_name_in_use(bn->net, + class_attr_bonding_masters.attr.name)) pr_err("network device named %s already exists in sysfs\n", class_attr_bonding_masters.attr.name); ret = 0; diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index a5f1aa911fe2..7b1457a6e327 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -70,6 +70,7 @@ config NET_DSA_QCA8K config NET_DSA_REALTEK_SMI tristate "Realtek SMI Ethernet switch family support" select NET_DSA_TAG_RTL4_A + select NET_DSA_TAG_RTL8_4 select FIXED_PHY select IRQ_DOMAIN select REALTEK_PHY diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile index f3598c040994..8da1569a34e6 100644 --- a/drivers/net/dsa/Makefile +++ b/drivers/net/dsa/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_NET_DSA_MT7530) += mt7530.o obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o obj-$(CONFIG_NET_DSA_QCA8K) += qca8k.o obj-$(CONFIG_NET_DSA_REALTEK_SMI) += realtek-smi.o -realtek-smi-objs := realtek-smi-core.o rtl8366.o rtl8366rb.o +realtek-smi-objs := realtek-smi-core.o rtl8366.o rtl8366rb.o rtl8365mb.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 1542bfb8b5e5..7c2968a639eb 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -449,8 +449,10 @@ EXPORT_SYMBOL(ksz_switch_register); void ksz_switch_remove(struct ksz_device *dev) { /* timer started */ - if (dev->mib_read_interval) + if (dev->mib_read_interval) { + dev->mib_read_interval = 0; cancel_delayed_work_sync(&dev->mib_read); + } dev->dev_ops->exit(dev); dsa_unregister_switch(dev->ds); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 03744d1c43fc..8dadcae93c9b 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -12,6 +12,7 @@ #include <linux/bitfield.h> #include <linux/delay.h> +#include <linux/dsa/mv88e6xxx.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/if_bridge.h> @@ -749,7 +750,11 @@ static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, ops = chip->info->ops; mv88e6xxx_reg_lock(chip); - if ((!mv88e6xxx_port_ppu_updates(chip, port) || + /* Internal PHYs propagate their configuration directly to the MAC. + * External PHYs depend on whether the PPU is enabled for this port. + */ + if (((!mv88e6xxx_phy_is_internal(ds, port) && + !mv88e6xxx_port_ppu_updates(chip, port)) || mode == MLO_AN_FIXED) && ops->port_sync_link) err = ops->port_sync_link(chip, port, mode, false); mv88e6xxx_reg_unlock(chip); @@ -772,7 +777,12 @@ static void mv88e6xxx_mac_link_up(struct dsa_switch *ds, int port, ops = chip->info->ops; mv88e6xxx_reg_lock(chip); - if (!mv88e6xxx_port_ppu_updates(chip, port) || mode == MLO_AN_FIXED) { + /* Internal PHYs propagate their configuration directly to the MAC. + * External PHYs depend on whether the PPU is enabled for this port. + */ + if ((!mv88e6xxx_phy_is_internal(ds, port) && + !mv88e6xxx_port_ppu_updates(chip, port)) || + mode == MLO_AN_FIXED) { /* FIXME: for an automedia port, should we force the link * down here - what if the link comes up due to "other" media * while we're bringing the port up, how is the exclusivity @@ -1677,6 +1687,30 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, return 0; } +static int mv88e6xxx_port_commit_pvid(struct mv88e6xxx_chip *chip, int port) +{ + struct dsa_port *dp = dsa_to_port(chip->ds, port); + struct mv88e6xxx_port *p = &chip->ports[port]; + u16 pvid = MV88E6XXX_VID_STANDALONE; + bool drop_untagged = false; + int err; + + if (dp->bridge_dev) { + if (br_vlan_enabled(dp->bridge_dev)) { + pvid = p->bridge_pvid.vid; + drop_untagged = !p->bridge_pvid.valid; + } else { + pvid = MV88E6XXX_VID_BRIDGED; + } + } + + err = mv88e6xxx_port_set_pvid(chip, port, pvid); + if (err) + return err; + + return mv88e6xxx_port_drop_untagged(chip, port, drop_untagged); +} + static int mv88e6xxx_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack) @@ -1690,7 +1724,16 @@ static int mv88e6xxx_port_vlan_filtering(struct dsa_switch *ds, int port, return -EOPNOTSUPP; mv88e6xxx_reg_lock(chip); + err = mv88e6xxx_port_set_8021q_mode(chip, port, mode); + if (err) + goto unlock; + + err = mv88e6xxx_port_commit_pvid(chip, port); + if (err) + goto unlock; + +unlock: mv88e6xxx_reg_unlock(chip); return err; @@ -1725,11 +1768,15 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port, u16 fid; int err; - /* Null VLAN ID corresponds to the port private database */ + /* Ports have two private address databases: one for when the port is + * standalone and one for when the port is under a bridge and the + * 802.1Q mode is disabled. When the port is standalone, DSA wants its + * address database to remain 100% empty, so we never load an ATU entry + * into a standalone port's database. Therefore, translate the null + * VLAN ID into the port's database used for VLAN-unaware bridging. + */ if (vid == 0) { - err = mv88e6xxx_port_get_fid(chip, port, &fid); - if (err) - return err; + fid = MV88E6XXX_FID_BRIDGED; } else { err = mv88e6xxx_vtu_get(chip, vid, &vlan); if (err) @@ -2123,6 +2170,7 @@ static int mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, struct mv88e6xxx_chip *chip = ds->priv; bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; + struct mv88e6xxx_port *p = &chip->ports[port]; bool warn; u8 member; int err; @@ -2156,13 +2204,21 @@ static int mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, } if (pvid) { - err = mv88e6xxx_port_set_pvid(chip, port, vlan->vid); - if (err) { - dev_err(ds->dev, "p%d: failed to set PVID %d\n", - port, vlan->vid); + p->bridge_pvid.vid = vlan->vid; + p->bridge_pvid.valid = true; + + err = mv88e6xxx_port_commit_pvid(chip, port); + if (err) + goto out; + } else if (vlan->vid && p->bridge_pvid.vid == vlan->vid) { + /* The old pvid was reinstalled as a non-pvid VLAN */ + p->bridge_pvid.valid = false; + + err = mv88e6xxx_port_commit_pvid(chip, port); + if (err) goto out; - } } + out: mv88e6xxx_reg_unlock(chip); @@ -2212,6 +2268,7 @@ static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { struct mv88e6xxx_chip *chip = ds->priv; + struct mv88e6xxx_port *p = &chip->ports[port]; int err = 0; u16 pvid; @@ -2229,7 +2286,9 @@ static int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, goto unlock; if (vlan->vid == pvid) { - err = mv88e6xxx_port_set_pvid(chip, port, 0); + p->bridge_pvid.valid = false; + + err = mv88e6xxx_port_commit_pvid(chip, port); if (err) goto unlock; } @@ -2393,7 +2452,16 @@ static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, int err; mv88e6xxx_reg_lock(chip); + err = mv88e6xxx_bridge_map(chip, br); + if (err) + goto unlock; + + err = mv88e6xxx_port_commit_pvid(chip, port); + if (err) + goto unlock; + +unlock: mv88e6xxx_reg_unlock(chip); return err; @@ -2403,11 +2471,20 @@ static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) { struct mv88e6xxx_chip *chip = ds->priv; + int err; mv88e6xxx_reg_lock(chip); + if (mv88e6xxx_bridge_map(chip, br) || mv88e6xxx_port_vlan_map(chip, port)) dev_err(ds->dev, "failed to remap in-chip Port VLAN\n"); + + err = mv88e6xxx_port_commit_pvid(chip, port); + if (err) + dev_err(ds->dev, + "port %d failed to restore standalone pvid: %pe\n", + port, ERR_PTR(err)); + mv88e6xxx_reg_unlock(chip); } @@ -2853,6 +2930,20 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) if (err) return err; + /* Associate MV88E6XXX_VID_BRIDGED with MV88E6XXX_FID_BRIDGED in the + * ATU by virtue of the fact that mv88e6xxx_atu_new() will pick it as + * the first free FID after MV88E6XXX_FID_STANDALONE. This will be used + * as the private PVID on ports under a VLAN-unaware bridge. + * Shared (DSA and CPU) ports must also be members of it, to translate + * the VID from the DSA tag into MV88E6XXX_FID_BRIDGED, instead of + * relying on their port default FID. + */ + err = mv88e6xxx_port_vlan_join(chip, port, MV88E6XXX_VID_BRIDGED, + MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_UNTAGGED, + false); + if (err) + return err; + if (chip->info->ops->port_set_jumbo_size) { err = chip->info->ops->port_set_jumbo_size(chip, port, 10218); if (err) @@ -2925,7 +3016,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) * database, and allow bidirectional communication between the * CPU and DSA port(s), and the other ports. */ - err = mv88e6xxx_port_set_fid(chip, port, 0); + err = mv88e6xxx_port_set_fid(chip, port, MV88E6XXX_FID_STANDALONE); if (err) return err; @@ -3115,6 +3206,10 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) } } + err = mv88e6xxx_vtu_setup(chip); + if (err) + goto unlock; + /* Setup Switch Port Registers */ for (i = 0; i < mv88e6xxx_num_ports(chip); i++) { if (dsa_is_unused_port(ds, i)) @@ -3144,10 +3239,6 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) if (err) goto unlock; - err = mv88e6xxx_vtu_setup(chip); - if (err) - goto unlock; - err = mv88e6xxx_pvt_setup(chip); if (err) goto unlock; diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 59f316cc8583..8271b8aa7b71 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -21,6 +21,9 @@ #define EDSA_HLEN 8 #define MV88E6XXX_N_FID 4096 +#define MV88E6XXX_FID_STANDALONE 0 +#define MV88E6XXX_FID_BRIDGED 1 + /* PVT limits for 4-bit port and 5-bit switch */ #define MV88E6XXX_MAX_PVT_SWITCHES 32 #define MV88E6XXX_MAX_PVT_PORTS 16 @@ -246,9 +249,15 @@ struct mv88e6xxx_policy { u16 vid; }; +struct mv88e6xxx_vlan { + u16 vid; + bool valid; +}; + struct mv88e6xxx_port { struct mv88e6xxx_chip *chip; int port; + struct mv88e6xxx_vlan bridge_pvid; u64 serdes_stats[2]; u64 atu_member_violation; u64 atu_miss_violation; diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index 451028c57af8..d9817b20ea64 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -1257,6 +1257,27 @@ int mv88e6xxx_port_set_8021q_mode(struct mv88e6xxx_chip *chip, int port, return 0; } +int mv88e6xxx_port_drop_untagged(struct mv88e6xxx_chip *chip, int port, + bool drop_untagged) +{ + u16 old, new; + int err; + + err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_CTL2, &old); + if (err) + return err; + + if (drop_untagged) + new = old | MV88E6XXX_PORT_CTL2_DISCARD_UNTAGGED; + else + new = old & ~MV88E6XXX_PORT_CTL2_DISCARD_UNTAGGED; + + if (new == old) + return 0; + + return mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_CTL2, new); +} + int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port) { u16 reg; diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index b10e5aebacf6..03382b66f800 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -423,6 +423,8 @@ int mv88e6393x_port_set_cmode(struct mv88e6xxx_chip *chip, int port, phy_interface_t mode); int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode); int mv88e6352_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode); +int mv88e6xxx_port_drop_untagged(struct mv88e6xxx_chip *chip, int port, + bool drop_untagged); int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port); int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port, int upstream_port); diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 01c01bd0c854..83808e7dbdda 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -266,12 +266,12 @@ static void felix_8021q_cpu_port_deinit(struct ocelot *ocelot, int port) */ static int felix_setup_mmio_filtering(struct felix *felix) { - unsigned long user_ports = 0, cpu_ports = 0; + unsigned long user_ports = dsa_user_ports(felix->ds); struct ocelot_vcap_filter *redirect_rule; struct ocelot_vcap_filter *tagging_rule; struct ocelot *ocelot = &felix->ocelot; struct dsa_switch *ds = felix->ds; - int port, ret; + int cpu = -1, port, ret; tagging_rule = kzalloc(sizeof(struct ocelot_vcap_filter), GFP_KERNEL); if (!tagging_rule) @@ -284,12 +284,15 @@ static int felix_setup_mmio_filtering(struct felix *felix) } for (port = 0; port < ocelot->num_phys_ports; port++) { - if (dsa_is_user_port(ds, port)) - user_ports |= BIT(port); - if (dsa_is_cpu_port(ds, port)) - cpu_ports |= BIT(port); + if (dsa_is_cpu_port(ds, port)) { + cpu = port; + break; + } } + if (cpu < 0) + return -EINVAL; + tagging_rule->key_type = OCELOT_VCAP_KEY_ETYPE; *(__be16 *)tagging_rule->key.etype.etype.value = htons(ETH_P_1588); *(__be16 *)tagging_rule->key.etype.etype.mask = htons(0xffff); @@ -325,7 +328,7 @@ static int felix_setup_mmio_filtering(struct felix *felix) * the CPU port module */ redirect_rule->action.mask_mode = OCELOT_MASK_MODE_REDIRECT; - redirect_rule->action.port_mask = cpu_ports; + redirect_rule->action.port_mask = BIT(cpu); } else { /* Trap PTP packets only to the CPU port module (which is * redirected to the NPI port) @@ -1076,6 +1079,101 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) return 0; } +static void ocelot_port_purge_txtstamp_skb(struct ocelot *ocelot, int port, + struct sk_buff *skb) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct sk_buff *clone = OCELOT_SKB_CB(skb)->clone; + struct sk_buff *skb_match = NULL, *skb_tmp; + unsigned long flags; + + if (!clone) + return; + + spin_lock_irqsave(&ocelot_port->tx_skbs.lock, flags); + + skb_queue_walk_safe(&ocelot_port->tx_skbs, skb, skb_tmp) { + if (skb != clone) + continue; + __skb_unlink(skb, &ocelot_port->tx_skbs); + skb_match = skb; + break; + } + + spin_unlock_irqrestore(&ocelot_port->tx_skbs.lock, flags); + + WARN_ONCE(!skb_match, + "Could not find skb clone in TX timestamping list\n"); +} + +#define work_to_xmit_work(w) \ + container_of((w), struct felix_deferred_xmit_work, work) + +static void felix_port_deferred_xmit(struct kthread_work *work) +{ + struct felix_deferred_xmit_work *xmit_work = work_to_xmit_work(work); + struct dsa_switch *ds = xmit_work->dp->ds; + struct sk_buff *skb = xmit_work->skb; + u32 rew_op = ocelot_ptp_rew_op(skb); + struct ocelot *ocelot = ds->priv; + int port = xmit_work->dp->index; + int retries = 10; + + do { + if (ocelot_can_inject(ocelot, 0)) + break; + + cpu_relax(); + } while (--retries); + + if (!retries) { + dev_err(ocelot->dev, "port %d failed to inject skb\n", + port); + ocelot_port_purge_txtstamp_skb(ocelot, port, skb); + kfree_skb(skb); + return; + } + + ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + + consume_skb(skb); + kfree(xmit_work); +} + +static int felix_port_setup_tagger_data(struct dsa_switch *ds, int port) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct ocelot *ocelot = ds->priv; + struct felix *felix = ocelot_to_felix(ocelot); + struct felix_port *felix_port; + + if (!dsa_port_is_user(dp)) + return 0; + + felix_port = kzalloc(sizeof(*felix_port), GFP_KERNEL); + if (!felix_port) + return -ENOMEM; + + felix_port->xmit_worker = felix->xmit_worker; + felix_port->xmit_work_fn = felix_port_deferred_xmit; + + dp->priv = felix_port; + + return 0; +} + +static void felix_port_teardown_tagger_data(struct dsa_switch *ds, int port) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct felix_port *felix_port = dp->priv; + + if (!felix_port) + return; + + dp->priv = NULL; + kfree(felix_port); +} + /* Hardware initialization done here so that we can allocate structures with * devm without fear of dsa_register_switch returning -EPROBE_DEFER and causing * us to allocate structures twice (leak memory) and map PCI memory twice @@ -1104,6 +1202,12 @@ static int felix_setup(struct dsa_switch *ds) } } + felix->xmit_worker = kthread_create_worker(0, "felix_xmit"); + if (IS_ERR(felix->xmit_worker)) { + err = PTR_ERR(felix->xmit_worker); + goto out_deinit_timestamp; + } + for (port = 0; port < ds->num_ports; port++) { if (dsa_is_unused_port(ds, port)) continue; @@ -1114,6 +1218,14 @@ static int felix_setup(struct dsa_switch *ds) * bits of vlan tag. */ felix_port_qos_map_init(ocelot, port); + + err = felix_port_setup_tagger_data(ds, port); + if (err) { + dev_err(ds->dev, + "port %d failed to set up tagger data: %pe\n", + port, ERR_PTR(err)); + goto out_deinit_ports; + } } err = ocelot_devlink_sb_register(ocelot); @@ -1128,6 +1240,7 @@ static int felix_setup(struct dsa_switch *ds) * there's no real point in checking for errors. */ felix_set_tag_protocol(ds, port, felix->tag_proto); + break; } ds->mtu_enforcement_ingress = true; @@ -1140,9 +1253,13 @@ out_deinit_ports: if (dsa_is_unused_port(ds, port)) continue; + felix_port_teardown_tagger_data(ds, port); ocelot_deinit_port(ocelot, port); } + kthread_destroy_worker(felix->xmit_worker); + +out_deinit_timestamp: ocelot_deinit_timestamp(ocelot); ocelot_deinit(ocelot); @@ -1164,19 +1281,23 @@ static void felix_teardown(struct dsa_switch *ds) continue; felix_del_tag_protocol(ds, port, felix->tag_proto); + break; } - ocelot_devlink_sb_unregister(ocelot); - ocelot_deinit_timestamp(ocelot); - ocelot_deinit(ocelot); - for (port = 0; port < ocelot->num_phys_ports; port++) { if (dsa_is_unused_port(ds, port)) continue; + felix_port_teardown_tagger_data(ds, port); ocelot_deinit_port(ocelot, port); } + kthread_destroy_worker(felix->xmit_worker); + + ocelot_devlink_sb_unregister(ocelot); + ocelot_deinit_timestamp(ocelot); + ocelot_deinit(ocelot); + if (felix->info->mdio_bus_free) felix->info->mdio_bus_free(ocelot); } @@ -1293,8 +1414,12 @@ static void felix_txtstamp(struct dsa_switch *ds, int port, if (!ocelot->ptp) return; - if (ocelot_port_txtstamp_request(ocelot, port, skb, &clone)) + if (ocelot_port_txtstamp_request(ocelot, port, skb, &clone)) { + dev_err_ratelimited(ds->dev, + "port %d delivering skb without TX timestamp\n", + port); return; + } if (clone) OCELOT_SKB_CB(skb)->clone = clone; diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 54024b6f9498..be3e42e135c0 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -62,6 +62,7 @@ struct felix { resource_size_t switch_base; resource_size_t imdio_base; enum dsa_tag_protocol tag_proto; + struct kthread_worker *xmit_worker; }; struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port); diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index a984f06f6f04..bf58d4d1ae9b 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -889,62 +889,183 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv) } static int -qca8k_setup_of_rgmii_delay(struct qca8k_priv *priv) +qca8k_setup_mac_pwr_sel(struct qca8k_priv *priv) { - struct device_node *port_dn; - phy_interface_t mode; - struct dsa_port *dp; - u32 val; + u32 mask = 0; + int ret = 0; - /* CPU port is already checked */ - dp = dsa_to_port(priv->ds, 0); + /* SoC specific settings for ipq8064. + * If more device require this consider adding + * a dedicated binding. + */ + if (of_machine_is_compatible("qcom,ipq8064")) + mask |= QCA8K_MAC_PWR_RGMII0_1_8V; + + /* SoC specific settings for ipq8065 */ + if (of_machine_is_compatible("qcom,ipq8065")) + mask |= QCA8K_MAC_PWR_RGMII1_1_8V; + + if (mask) { + ret = qca8k_rmw(priv, QCA8K_REG_MAC_PWR_SEL, + QCA8K_MAC_PWR_RGMII0_1_8V | + QCA8K_MAC_PWR_RGMII1_1_8V, + mask); + } - port_dn = dp->dn; + return ret; +} + +static int qca8k_find_cpu_port(struct dsa_switch *ds) +{ + struct qca8k_priv *priv = ds->priv; - /* Check if port 0 is set to the correct type */ - of_get_phy_mode(port_dn, &mode); - if (mode != PHY_INTERFACE_MODE_RGMII_ID && - mode != PHY_INTERFACE_MODE_RGMII_RXID && - mode != PHY_INTERFACE_MODE_RGMII_TXID) { + /* Find the connected cpu port. Valid port are 0 or 6 */ + if (dsa_is_cpu_port(ds, 0)) return 0; + + dev_dbg(priv->dev, "port 0 is not the CPU port. Checking port 6"); + + if (dsa_is_cpu_port(ds, 6)) + return 6; + + return -EINVAL; +} + +static int +qca8k_setup_of_pws_reg(struct qca8k_priv *priv) +{ + struct device_node *node = priv->dev->of_node; + const struct qca8k_match_data *data; + u32 val = 0; + int ret; + + /* QCA8327 require to set to the correct mode. + * His bigger brother QCA8328 have the 172 pin layout. + * Should be applied by default but we set this just to make sure. + */ + if (priv->switch_id == QCA8K_ID_QCA8327) { + data = of_device_get_match_data(priv->dev); + + /* Set the correct package of 148 pin for QCA8327 */ + if (data->reduced_package) + val |= QCA8327_PWS_PACKAGE148_EN; + + ret = qca8k_rmw(priv, QCA8K_REG_PWS, QCA8327_PWS_PACKAGE148_EN, + val); + if (ret) + return ret; } - switch (mode) { - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_RXID: - if (of_property_read_u32(port_dn, "rx-internal-delay-ps", &val)) - val = 2; - else - /* Switch regs accept value in ns, convert ps to ns */ - val = val / 1000; + if (of_property_read_bool(node, "qca,ignore-power-on-sel")) + val |= QCA8K_PWS_POWER_ON_SEL; - if (val > QCA8K_MAX_DELAY) { - dev_err(priv->dev, "rgmii rx delay is limited to a max value of 3ns, setting to the max value"); - val = 3; + if (of_property_read_bool(node, "qca,led-open-drain")) { + if (!(val & QCA8K_PWS_POWER_ON_SEL)) { + dev_err(priv->dev, "qca,led-open-drain require qca,ignore-power-on-sel to be set."); + return -EINVAL; } - priv->rgmii_rx_delay = val; - /* Stop here if we need to check only for rx delay */ - if (mode != PHY_INTERFACE_MODE_RGMII_ID) - break; + val |= QCA8K_PWS_LED_OPEN_EN_CSR; + } - fallthrough; - case PHY_INTERFACE_MODE_RGMII_TXID: - if (of_property_read_u32(port_dn, "tx-internal-delay-ps", &val)) - val = 1; - else - /* Switch regs accept value in ns, convert ps to ns */ - val = val / 1000; + return qca8k_rmw(priv, QCA8K_REG_PWS, + QCA8K_PWS_LED_OPEN_EN_CSR | QCA8K_PWS_POWER_ON_SEL, + val); +} - if (val > QCA8K_MAX_DELAY) { - dev_err(priv->dev, "rgmii tx delay is limited to a max value of 3ns, setting to the max value"); - val = 3; - } +static int +qca8k_parse_port_config(struct qca8k_priv *priv) +{ + int port, cpu_port_index = 0, ret; + struct device_node *port_dn; + phy_interface_t mode; + struct dsa_port *dp; + u32 delay; - priv->rgmii_tx_delay = val; - break; - default: - return 0; + /* We have 2 CPU port. Check them */ + for (port = 0; port < QCA8K_NUM_PORTS && cpu_port_index < QCA8K_NUM_CPU_PORTS; port++) { + /* Skip every other port */ + if (port != 0 && port != 6) + continue; + + dp = dsa_to_port(priv->ds, port); + port_dn = dp->dn; + cpu_port_index++; + + if (!of_device_is_available(port_dn)) + continue; + + ret = of_get_phy_mode(port_dn, &mode); + if (ret) + continue; + + switch (mode) { + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_TXID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_SGMII: + delay = 0; + + if (!of_property_read_u32(port_dn, "tx-internal-delay-ps", &delay)) + /* Switch regs accept value in ns, convert ps to ns */ + delay = delay / 1000; + else if (mode == PHY_INTERFACE_MODE_RGMII_ID || + mode == PHY_INTERFACE_MODE_RGMII_TXID) + delay = 1; + + if (delay > QCA8K_MAX_DELAY) { + dev_err(priv->dev, "rgmii tx delay is limited to a max value of 3ns, setting to the max value"); + delay = 3; + } + + priv->ports_config.rgmii_tx_delay[cpu_port_index] = delay; + + delay = 0; + + if (!of_property_read_u32(port_dn, "rx-internal-delay-ps", &delay)) + /* Switch regs accept value in ns, convert ps to ns */ + delay = delay / 1000; + else if (mode == PHY_INTERFACE_MODE_RGMII_ID || + mode == PHY_INTERFACE_MODE_RGMII_RXID) + delay = 2; + + if (delay > QCA8K_MAX_DELAY) { + dev_err(priv->dev, "rgmii rx delay is limited to a max value of 3ns, setting to the max value"); + delay = 3; + } + + priv->ports_config.rgmii_rx_delay[cpu_port_index] = delay; + + /* Skip sgmii parsing for rgmii* mode */ + if (mode == PHY_INTERFACE_MODE_RGMII || + mode == PHY_INTERFACE_MODE_RGMII_ID || + mode == PHY_INTERFACE_MODE_RGMII_TXID || + mode == PHY_INTERFACE_MODE_RGMII_RXID) + break; + + if (of_property_read_bool(port_dn, "qca,sgmii-txclk-falling-edge")) + priv->ports_config.sgmii_tx_clk_falling_edge = true; + + if (of_property_read_bool(port_dn, "qca,sgmii-rxclk-falling-edge")) + priv->ports_config.sgmii_rx_clk_falling_edge = true; + + if (of_property_read_bool(port_dn, "qca,sgmii-enable-pll")) { + priv->ports_config.sgmii_enable_pll = true; + + if (priv->switch_id == QCA8K_ID_QCA8327) { + dev_err(priv->dev, "SGMII PLL should NOT be enabled for qca8327. Aborting enabling"); + priv->ports_config.sgmii_enable_pll = false; + } + + if (priv->switch_revision < 2) + dev_warn(priv->dev, "SGMII PLL should NOT be enabled for qca8337 with revision 2 or more."); + } + + break; + default: + continue; + } } return 0; @@ -954,15 +1075,20 @@ static int qca8k_setup(struct dsa_switch *ds) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; - int ret, i; + int cpu_port, ret, i; u32 mask; - /* Make sure that port 0 is the cpu port */ - if (!dsa_is_cpu_port(ds, 0)) { - dev_err(priv->dev, "port 0 is not the CPU port"); - return -EINVAL; + cpu_port = qca8k_find_cpu_port(ds); + if (cpu_port < 0) { + dev_err(priv->dev, "No cpu port configured in both cpu port0 and port6"); + return cpu_port; } + /* Parse CPU port config to be later used in phy_link mac_config */ + ret = qca8k_parse_port_config(priv); + if (ret) + return ret; + mutex_init(&priv->reg_mutex); /* Start by setting up the register mapping */ @@ -975,7 +1101,11 @@ qca8k_setup(struct dsa_switch *ds) if (ret) return ret; - ret = qca8k_setup_of_rgmii_delay(priv); + ret = qca8k_setup_of_pws_reg(priv); + if (ret) + return ret; + + ret = qca8k_setup_mac_pwr_sel(priv); if (ret) return ret; @@ -993,7 +1123,7 @@ qca8k_setup(struct dsa_switch *ds) dev_warn(priv->dev, "mib init failed"); /* Enable QCA header mode on the cpu port */ - ret = qca8k_write(priv, QCA8K_REG_PORT_HDR_CTRL(QCA8K_CPU_PORT), + ret = qca8k_write(priv, QCA8K_REG_PORT_HDR_CTRL(cpu_port), QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_TX_S | QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_RX_S); if (ret) { @@ -1015,10 +1145,10 @@ qca8k_setup(struct dsa_switch *ds) /* Forward all unknown frames to CPU port for Linux processing */ ret = qca8k_write(priv, QCA8K_REG_GLOBAL_FW_CTRL1, - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_IGMP_DP_S | - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_BC_DP_S | - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_MC_DP_S | - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_UC_DP_S); + BIT(cpu_port) << QCA8K_GLOBAL_FW_CTRL1_IGMP_DP_S | + BIT(cpu_port) << QCA8K_GLOBAL_FW_CTRL1_BC_DP_S | + BIT(cpu_port) << QCA8K_GLOBAL_FW_CTRL1_MC_DP_S | + BIT(cpu_port) << QCA8K_GLOBAL_FW_CTRL1_UC_DP_S); if (ret) return ret; @@ -1026,7 +1156,7 @@ qca8k_setup(struct dsa_switch *ds) for (i = 0; i < QCA8K_NUM_PORTS; i++) { /* CPU port gets connected to all user ports of the switch */ if (dsa_is_cpu_port(ds, i)) { - ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(QCA8K_CPU_PORT), + ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(cpu_port), QCA8K_PORT_LOOKUP_MEMBER, dsa_user_ports(ds)); if (ret) return ret; @@ -1038,7 +1168,7 @@ qca8k_setup(struct dsa_switch *ds) ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i), QCA8K_PORT_LOOKUP_MEMBER, - BIT(QCA8K_CPU_PORT)); + BIT(cpu_port)); if (ret) return ret; @@ -1137,12 +1267,53 @@ qca8k_setup(struct dsa_switch *ds) } static void +qca8k_mac_config_setup_internal_delay(struct qca8k_priv *priv, int cpu_port_index, + u32 reg) +{ + u32 delay, val = 0; + int ret; + + /* Delay can be declared in 3 different way. + * Mode to rgmii and internal-delay standard binding defined + * rgmii-id or rgmii-tx/rx phy mode set. + * The parse logic set a delay different than 0 only when one + * of the 3 different way is used. In all other case delay is + * not enabled. With ID or TX/RXID delay is enabled and set + * to the default and recommended value. + */ + if (priv->ports_config.rgmii_tx_delay[cpu_port_index]) { + delay = priv->ports_config.rgmii_tx_delay[cpu_port_index]; + + val |= QCA8K_PORT_PAD_RGMII_TX_DELAY(delay) | + QCA8K_PORT_PAD_RGMII_TX_DELAY_EN; + } + + if (priv->ports_config.rgmii_rx_delay[cpu_port_index]) { + delay = priv->ports_config.rgmii_rx_delay[cpu_port_index]; + + val |= QCA8K_PORT_PAD_RGMII_RX_DELAY(delay) | + QCA8K_PORT_PAD_RGMII_RX_DELAY_EN; + } + + /* Set RGMII delay based on the selected values */ + ret = qca8k_rmw(priv, reg, + QCA8K_PORT_PAD_RGMII_TX_DELAY_MASK | + QCA8K_PORT_PAD_RGMII_RX_DELAY_MASK | + QCA8K_PORT_PAD_RGMII_TX_DELAY_EN | + QCA8K_PORT_PAD_RGMII_RX_DELAY_EN, + val); + if (ret) + dev_err(priv->dev, "Failed to set internal delay for CPU port%d", + cpu_port_index == QCA8K_CPU_PORT0 ? 0 : 6); +} + +static void qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) { struct qca8k_priv *priv = ds->priv; + int cpu_port_index, ret; u32 reg, val; - int ret; switch (port) { case 0: /* 1st CPU port */ @@ -1154,6 +1325,7 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, return; reg = QCA8K_REG_PORT0_PAD_CTRL; + cpu_port_index = QCA8K_CPU_PORT0; break; case 1: case 2: @@ -1172,6 +1344,7 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, return; reg = QCA8K_REG_PORT6_PAD_CTRL; + cpu_port_index = QCA8K_CPU_PORT6; break; default: dev_err(ds->dev, "%s: unsupported port: %i\n", __func__, port); @@ -1186,23 +1359,18 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, switch (state->interface) { case PHY_INTERFACE_MODE_RGMII: - /* RGMII mode means no delay so don't enable the delay */ - qca8k_write(priv, reg, QCA8K_PORT_PAD_RGMII_EN); - break; case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_TXID: case PHY_INTERFACE_MODE_RGMII_RXID: - /* RGMII_ID needs internal delay. This is enabled through - * PORT5_PAD_CTRL for all ports, rather than individual port - * registers + qca8k_write(priv, reg, QCA8K_PORT_PAD_RGMII_EN); + + /* Configure rgmii delay */ + qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg); + + /* QCA8337 requires to set rgmii rx delay for all ports. + * This is enabled through PORT5_PAD_CTRL for all ports, + * rather than individual port registers. */ - qca8k_write(priv, reg, - QCA8K_PORT_PAD_RGMII_EN | - QCA8K_PORT_PAD_RGMII_TX_DELAY(priv->rgmii_tx_delay) | - QCA8K_PORT_PAD_RGMII_RX_DELAY(priv->rgmii_rx_delay) | - QCA8K_PORT_PAD_RGMII_TX_DELAY_EN | - QCA8K_PORT_PAD_RGMII_RX_DELAY_EN); - /* QCA8337 requires to set rgmii rx delay */ if (priv->switch_id == QCA8K_ID_QCA8337) qca8k_write(priv, QCA8K_REG_PORT5_PAD_CTRL, QCA8K_PORT_PAD_RGMII_RX_DELAY_EN); @@ -1227,8 +1395,11 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, if (ret) return; - val |= QCA8K_SGMII_EN_PLL | QCA8K_SGMII_EN_RX | - QCA8K_SGMII_EN_TX | QCA8K_SGMII_EN_SD; + val |= QCA8K_SGMII_EN_SD; + + if (priv->ports_config.sgmii_enable_pll) + val |= QCA8K_SGMII_EN_PLL | QCA8K_SGMII_EN_RX | + QCA8K_SGMII_EN_TX; if (dsa_is_cpu_port(ds, port)) { /* CPU port, we're talking to the CPU MAC, be a PHY */ @@ -1243,6 +1414,35 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, } qca8k_write(priv, QCA8K_REG_SGMII_CTRL, val); + + /* For qca8327/qca8328/qca8334/qca8338 sgmii is unique and + * falling edge is set writing in the PORT0 PAD reg + */ + if (priv->switch_id == QCA8K_ID_QCA8327 || + priv->switch_id == QCA8K_ID_QCA8337) + reg = QCA8K_REG_PORT0_PAD_CTRL; + + val = 0; + + /* SGMII Clock phase configuration */ + if (priv->ports_config.sgmii_rx_clk_falling_edge) + val |= QCA8K_PORT0_PAD_SGMII_RXCLK_FALLING_EDGE; + + if (priv->ports_config.sgmii_tx_clk_falling_edge) + val |= QCA8K_PORT0_PAD_SGMII_TXCLK_FALLING_EDGE; + + if (val) + ret = qca8k_rmw(priv, reg, + QCA8K_PORT0_PAD_SGMII_RXCLK_FALLING_EDGE | + QCA8K_PORT0_PAD_SGMII_TXCLK_FALLING_EDGE, + val); + + /* From original code is reported port instability as SGMII also + * require delay set. Apply advised values here or take them from DT. + */ + if (state->interface == PHY_INTERFACE_MODE_SGMII) + qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg); + break; default: dev_err(ds->dev, "xMII mode %s not supported for port %d\n", @@ -1522,9 +1722,12 @@ static int qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; - int port_mask = BIT(QCA8K_CPU_PORT); + int port_mask, cpu_port; int i, ret; + cpu_port = dsa_to_port(ds, port)->cpu_dp->index; + port_mask = BIT(cpu_port); + for (i = 1; i < QCA8K_NUM_PORTS; i++) { if (dsa_to_port(ds, i)->bridge_dev != br) continue; @@ -1551,7 +1754,9 @@ static void qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; - int i; + int cpu_port, i; + + cpu_port = dsa_to_port(ds, port)->cpu_dp->index; for (i = 1; i < QCA8K_NUM_PORTS; i++) { if (dsa_to_port(ds, i)->bridge_dev != br) @@ -1568,7 +1773,7 @@ qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) * this port */ qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), - QCA8K_PORT_LOOKUP_MEMBER, BIT(QCA8K_CPU_PORT)); + QCA8K_PORT_LOOKUP_MEMBER, BIT(cpu_port)); } static int @@ -1939,7 +2144,12 @@ static int qca8k_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(qca8k_pm_ops, qca8k_suspend, qca8k_resume); -static const struct qca8k_match_data qca832x = { +static const struct qca8k_match_data qca8327 = { + .id = QCA8K_ID_QCA8327, + .reduced_package = true, +}; + +static const struct qca8k_match_data qca8328 = { .id = QCA8K_ID_QCA8327, }; @@ -1948,7 +2158,8 @@ static const struct qca8k_match_data qca833x = { }; static const struct of_device_id qca8k_of_match[] = { - { .compatible = "qca,qca8327", .data = &qca832x }, + { .compatible = "qca,qca8327", .data = &qca8327 }, + { .compatible = "qca,qca8328", .data = &qca8328 }, { .compatible = "qca,qca8334", .data = &qca833x }, { .compatible = "qca,qca8337", .data = &qca833x }, { /* sentinel */ }, diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h index ed3b05ad6745..e10571a398c9 100644 --- a/drivers/net/dsa/qca8k.h +++ b/drivers/net/dsa/qca8k.h @@ -13,6 +13,7 @@ #include <linux/gpio.h> #define QCA8K_NUM_PORTS 7 +#define QCA8K_NUM_CPU_PORTS 2 #define QCA8K_MAX_MTU 9000 #define PHY_ID_QCA8327 0x004dd034 @@ -24,8 +25,6 @@ #define QCA8K_NUM_FDB_RECORDS 2048 -#define QCA8K_CPU_PORT 0 - #define QCA8K_PORT_VID_DEF 1 /* Global control registers */ @@ -35,16 +34,26 @@ #define QCA8K_MASK_CTRL_DEVICE_ID_MASK GENMASK(15, 8) #define QCA8K_MASK_CTRL_DEVICE_ID(x) ((x) >> 8) #define QCA8K_REG_PORT0_PAD_CTRL 0x004 +#define QCA8K_PORT0_PAD_SGMII_RXCLK_FALLING_EDGE BIT(19) +#define QCA8K_PORT0_PAD_SGMII_TXCLK_FALLING_EDGE BIT(18) #define QCA8K_REG_PORT5_PAD_CTRL 0x008 #define QCA8K_REG_PORT6_PAD_CTRL 0x00c #define QCA8K_PORT_PAD_RGMII_EN BIT(26) +#define QCA8K_PORT_PAD_RGMII_TX_DELAY_MASK GENMASK(23, 22) #define QCA8K_PORT_PAD_RGMII_TX_DELAY(x) ((x) << 22) +#define QCA8K_PORT_PAD_RGMII_RX_DELAY_MASK GENMASK(21, 20) #define QCA8K_PORT_PAD_RGMII_RX_DELAY(x) ((x) << 20) #define QCA8K_PORT_PAD_RGMII_TX_DELAY_EN BIT(25) #define QCA8K_PORT_PAD_RGMII_RX_DELAY_EN BIT(24) #define QCA8K_MAX_DELAY 3 #define QCA8K_PORT_PAD_SGMII_EN BIT(7) #define QCA8K_REG_PWS 0x010 +#define QCA8K_PWS_POWER_ON_SEL BIT(31) +/* This reg is only valid for QCA832x and toggle the package + * type from 176 pin (by default) to 148 pin used on QCA8327 + */ +#define QCA8327_PWS_PACKAGE148_EN BIT(30) +#define QCA8K_PWS_LED_OPEN_EN_CSR BIT(24) #define QCA8K_PWS_SERDES_AEN_DIS BIT(7) #define QCA8K_REG_MODULE_EN 0x030 #define QCA8K_MODULE_EN_MIB BIT(0) @@ -100,6 +109,11 @@ #define QCA8K_SGMII_MODE_CTRL_PHY (1 << 22) #define QCA8K_SGMII_MODE_CTRL_MAC (2 << 22) +/* MAC_PWR_SEL registers */ +#define QCA8K_REG_MAC_PWR_SEL 0x0e4 +#define QCA8K_MAC_PWR_RGMII1_1_8V BIT(18) +#define QCA8K_MAC_PWR_RGMII0_1_8V BIT(19) + /* EEE control registers */ #define QCA8K_REG_EEE_CTRL 0x100 #define QCA8K_REG_EEE_CTRL_LPI_EN(_i) ((_i + 1) * 2) @@ -248,14 +262,27 @@ struct ar8xxx_port_status { struct qca8k_match_data { u8 id; + bool reduced_package; +}; + +enum { + QCA8K_CPU_PORT0, + QCA8K_CPU_PORT6, +}; + +struct qca8k_ports_config { + bool sgmii_rx_clk_falling_edge; + bool sgmii_tx_clk_falling_edge; + bool sgmii_enable_pll; + u8 rgmii_rx_delay[QCA8K_NUM_CPU_PORTS]; /* 0: CPU port0, 1: CPU port6 */ + u8 rgmii_tx_delay[QCA8K_NUM_CPU_PORTS]; /* 0: CPU port0, 1: CPU port6 */ }; struct qca8k_priv { u8 switch_id; u8 switch_revision; - u8 rgmii_tx_delay; - u8 rgmii_rx_delay; bool legacy_phy_port_mapping; + struct qca8k_ports_config ports_config; struct regmap *regmap; struct mii_bus *bus; struct ar8xxx_port_status port_sts[QCA8K_NUM_PORTS]; diff --git a/drivers/net/dsa/realtek-smi-core.c b/drivers/net/dsa/realtek-smi-core.c index 2fcfd917b876..c66ebd0ee217 100644 --- a/drivers/net/dsa/realtek-smi-core.c +++ b/drivers/net/dsa/realtek-smi-core.c @@ -501,6 +501,10 @@ static const struct of_device_id realtek_smi_of_match[] = { .compatible = "realtek,rtl8366s", .data = NULL, }, + { + .compatible = "realtek,rtl8365mb", + .data = &rtl8365mb_variant, + }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, realtek_smi_of_match); diff --git a/drivers/net/dsa/realtek-smi-core.h b/drivers/net/dsa/realtek-smi-core.h index 214f710d7dd5..5bfa53e2480a 100644 --- a/drivers/net/dsa/realtek-smi-core.h +++ b/drivers/net/dsa/realtek-smi-core.h @@ -140,5 +140,6 @@ int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset); void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data); extern const struct realtek_smi_variant rtl8366rb_variant; +extern const struct realtek_smi_variant rtl8365mb_variant; #endif /* _REALTEK_SMI_H */ diff --git a/drivers/net/dsa/rtl8365mb.c b/drivers/net/dsa/rtl8365mb.c new file mode 100644 index 000000000000..baaae97283c5 --- /dev/null +++ b/drivers/net/dsa/rtl8365mb.c @@ -0,0 +1,1982 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Realtek SMI subdriver for the Realtek RTL8365MB-VC ethernet switch. + * + * Copyright (C) 2021 Alvin Šipraga <alsi@bang-olufsen.dk> + * Copyright (C) 2021 Michael Rasmussen <mir@bang-olufsen.dk> + * + * The RTL8365MB-VC is a 4+1 port 10/100/1000M switch controller. It includes 4 + * integrated PHYs for the user facing ports, and an extension interface which + * can be connected to the CPU - or another PHY - via either MII, RMII, or + * RGMII. The switch is configured via the Realtek Simple Management Interface + * (SMI), which uses the MDIO/MDC lines. + * + * Below is a simplified block diagram of the chip and its relevant interfaces. + * + * .-----------------------------------. + * | | + * UTP <---------------> Giga PHY <-> PCS <-> P0 GMAC | + * UTP <---------------> Giga PHY <-> PCS <-> P1 GMAC | + * UTP <---------------> Giga PHY <-> PCS <-> P2 GMAC | + * UTP <---------------> Giga PHY <-> PCS <-> P3 GMAC | + * | | + * CPU/PHY <-MII/RMII/RGMII---> Extension <---> Extension | + * | interface 1 GMAC 1 | + * | | + * SMI driver/ <-MDC/SCL---> Management ~~~~~~~~~~~~~~ | + * EEPROM <-MDIO/SDA--> interface ~REALTEK ~~~~~ | + * | ~RTL8365MB ~~~ | + * | ~GXXXC TAIWAN~ | + * GPIO <--------------> Reset ~~~~~~~~~~~~~~ | + * | | + * Interrupt <----------> Link UP/DOWN events | + * controller | | + * '-----------------------------------' + * + * The driver uses DSA to integrate the 4 user and 1 extension ports into the + * kernel. Netdevices are created for the user ports, as are PHY devices for + * their integrated PHYs. The device tree firmware should also specify the link + * partner of the extension port - either via a fixed-link or other phy-handle. + * See the device tree bindings for more detailed information. Note that the + * driver has only been tested with a fixed-link, but in principle it should not + * matter. + * + * NOTE: Currently, only the RGMII interface is implemented in this driver. + * + * The interrupt line is asserted on link UP/DOWN events. The driver creates a + * custom irqchip to handle this interrupt and demultiplex the events by reading + * the status registers via SMI. Interrupts are then propagated to the relevant + * PHY device. + * + * The EEPROM contains initial register values which the chip will read over I2C + * upon hardware reset. It is also possible to omit the EEPROM. In both cases, + * the driver will manually reprogram some registers using jam tables to reach + * an initial state defined by the vendor driver. + * + * This Linux driver is written based on an OS-agnostic vendor driver from + * Realtek. The reference GPL-licensed sources can be found in the OpenWrt + * source tree under the name rtl8367c. The vendor driver claims to support a + * number of similar switch controllers from Realtek, but the only hardware we + * have is the RTL8365MB-VC. Moreover, there does not seem to be any chip under + * the name RTL8367C. Although one wishes that the 'C' stood for some kind of + * common hardware revision, there exist examples of chips with the suffix -VC + * which are explicitly not supported by the rtl8367c driver and which instead + * require the rtl8367d vendor driver. With all this uncertainty, the driver has + * been modestly named rtl8365mb. Future implementors may wish to rename things + * accordingly. + * + * In the same family of chips, some carry up to 8 user ports and up to 2 + * extension ports. Where possible this driver tries to make things generic, but + * more work must be done to support these configurations. According to + * documentation from Realtek, the family should include the following chips: + * + * - RTL8363NB + * - RTL8363NB-VB + * - RTL8363SC + * - RTL8363SC-VB + * - RTL8364NB + * - RTL8364NB-VB + * - RTL8365MB-VC + * - RTL8366SC + * - RTL8367RB-VB + * - RTL8367SB + * - RTL8367S + * - RTL8370MB + * - RTL8310SR + * + * Some of the register logic for these additional chips has been skipped over + * while implementing this driver. It is therefore not possible to assume that + * things will work out-of-the-box for other chips, and a careful review of the + * vendor driver may be needed to expand support. The RTL8365MB-VC seems to be + * one of the simpler chips. + */ + +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/interrupt.h> +#include <linux/irqdomain.h> +#include <linux/mutex.h> +#include <linux/of_irq.h> +#include <linux/regmap.h> +#include <linux/if_bridge.h> + +#include "realtek-smi-core.h" + +/* Chip-specific data and limits */ +#define RTL8365MB_CHIP_ID_8365MB_VC 0x6367 +#define RTL8365MB_CPU_PORT_NUM_8365MB_VC 6 +#define RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC 2112 + +/* Family-specific data and limits */ +#define RTL8365MB_NUM_PHYREGS 32 +#define RTL8365MB_PHYREGMAX (RTL8365MB_NUM_PHYREGS - 1) +#define RTL8365MB_MAX_NUM_PORTS (RTL8365MB_CPU_PORT_NUM_8365MB_VC + 1) + +/* Chip identification registers */ +#define RTL8365MB_CHIP_ID_REG 0x1300 + +#define RTL8365MB_CHIP_VER_REG 0x1301 + +#define RTL8365MB_MAGIC_REG 0x13C2 +#define RTL8365MB_MAGIC_VALUE 0x0249 + +/* Chip reset register */ +#define RTL8365MB_CHIP_RESET_REG 0x1322 +#define RTL8365MB_CHIP_RESET_SW_MASK 0x0002 +#define RTL8365MB_CHIP_RESET_HW_MASK 0x0001 + +/* Interrupt polarity register */ +#define RTL8365MB_INTR_POLARITY_REG 0x1100 +#define RTL8365MB_INTR_POLARITY_MASK 0x0001 +#define RTL8365MB_INTR_POLARITY_HIGH 0 +#define RTL8365MB_INTR_POLARITY_LOW 1 + +/* Interrupt control/status register - enable/check specific interrupt types */ +#define RTL8365MB_INTR_CTRL_REG 0x1101 +#define RTL8365MB_INTR_STATUS_REG 0x1102 +#define RTL8365MB_INTR_SLIENT_START_2_MASK 0x1000 +#define RTL8365MB_INTR_SLIENT_START_MASK 0x0800 +#define RTL8365MB_INTR_ACL_ACTION_MASK 0x0200 +#define RTL8365MB_INTR_CABLE_DIAG_FIN_MASK 0x0100 +#define RTL8365MB_INTR_INTERRUPT_8051_MASK 0x0080 +#define RTL8365MB_INTR_LOOP_DETECTION_MASK 0x0040 +#define RTL8365MB_INTR_GREEN_TIMER_MASK 0x0020 +#define RTL8365MB_INTR_SPECIAL_CONGEST_MASK 0x0010 +#define RTL8365MB_INTR_SPEED_CHANGE_MASK 0x0008 +#define RTL8365MB_INTR_LEARN_OVER_MASK 0x0004 +#define RTL8365MB_INTR_METER_EXCEEDED_MASK 0x0002 +#define RTL8365MB_INTR_LINK_CHANGE_MASK 0x0001 +#define RTL8365MB_INTR_ALL_MASK \ + (RTL8365MB_INTR_SLIENT_START_2_MASK | \ + RTL8365MB_INTR_SLIENT_START_MASK | \ + RTL8365MB_INTR_ACL_ACTION_MASK | \ + RTL8365MB_INTR_CABLE_DIAG_FIN_MASK | \ + RTL8365MB_INTR_INTERRUPT_8051_MASK | \ + RTL8365MB_INTR_LOOP_DETECTION_MASK | \ + RTL8365MB_INTR_GREEN_TIMER_MASK | \ + RTL8365MB_INTR_SPECIAL_CONGEST_MASK | \ + RTL8365MB_INTR_SPEED_CHANGE_MASK | \ + RTL8365MB_INTR_LEARN_OVER_MASK | \ + RTL8365MB_INTR_METER_EXCEEDED_MASK | \ + RTL8365MB_INTR_LINK_CHANGE_MASK) + +/* Per-port interrupt type status registers */ +#define RTL8365MB_PORT_LINKDOWN_IND_REG 0x1106 +#define RTL8365MB_PORT_LINKDOWN_IND_MASK 0x07FF + +#define RTL8365MB_PORT_LINKUP_IND_REG 0x1107 +#define RTL8365MB_PORT_LINKUP_IND_MASK 0x07FF + +/* PHY indirect access registers */ +#define RTL8365MB_INDIRECT_ACCESS_CTRL_REG 0x1F00 +#define RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK 0x0002 +#define RTL8365MB_INDIRECT_ACCESS_CTRL_RW_READ 0 +#define RTL8365MB_INDIRECT_ACCESS_CTRL_RW_WRITE 1 +#define RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_MASK 0x0001 +#define RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE 1 +#define RTL8365MB_INDIRECT_ACCESS_STATUS_REG 0x1F01 +#define RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG 0x1F02 +#define RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_5_1_MASK GENMASK(4, 0) +#define RTL8365MB_INDIRECT_ACCESS_ADDRESS_PHYNUM_MASK GENMASK(6, 5) +#define RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_9_6_MASK GENMASK(11, 8) +#define RTL8365MB_PHY_BASE 0x2000 +#define RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG 0x1F03 +#define RTL8365MB_INDIRECT_ACCESS_READ_DATA_REG 0x1F04 + +/* PHY OCP address prefix register */ +#define RTL8365MB_GPHY_OCP_MSB_0_REG 0x1D15 +#define RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK 0x0FC0 +#define RTL8365MB_PHY_OCP_ADDR_PREFIX_MASK 0xFC00 + +/* The PHY OCP addresses of PHY registers 0~31 start here */ +#define RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE 0xA400 + +/* EXT port interface mode values - used in DIGITAL_INTERFACE_SELECT */ +#define RTL8365MB_EXT_PORT_MODE_DISABLE 0 +#define RTL8365MB_EXT_PORT_MODE_RGMII 1 +#define RTL8365MB_EXT_PORT_MODE_MII_MAC 2 +#define RTL8365MB_EXT_PORT_MODE_MII_PHY 3 +#define RTL8365MB_EXT_PORT_MODE_TMII_MAC 4 +#define RTL8365MB_EXT_PORT_MODE_TMII_PHY 5 +#define RTL8365MB_EXT_PORT_MODE_GMII 6 +#define RTL8365MB_EXT_PORT_MODE_RMII_MAC 7 +#define RTL8365MB_EXT_PORT_MODE_RMII_PHY 8 +#define RTL8365MB_EXT_PORT_MODE_SGMII 9 +#define RTL8365MB_EXT_PORT_MODE_HSGMII 10 +#define RTL8365MB_EXT_PORT_MODE_1000X_100FX 11 +#define RTL8365MB_EXT_PORT_MODE_1000X 12 +#define RTL8365MB_EXT_PORT_MODE_100FX 13 + +/* EXT port interface mode configuration registers 0~1 */ +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 0x1305 +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 0x13C3 +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(_extport) \ + (RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 + \ + ((_extport) >> 1) * (0x13C3 - 0x1305)) +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(_extport) \ + (0xF << (((_extport) % 2))) +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET(_extport) \ + (((_extport) % 2) * 4) + +/* EXT port RGMII TX/RX delay configuration registers 1~2 */ +#define RTL8365MB_EXT_RGMXF_REG1 0x1307 +#define RTL8365MB_EXT_RGMXF_REG2 0x13C5 +#define RTL8365MB_EXT_RGMXF_REG(_extport) \ + (RTL8365MB_EXT_RGMXF_REG1 + \ + (((_extport) >> 1) * (0x13C5 - 0x1307))) +#define RTL8365MB_EXT_RGMXF_RXDELAY_MASK 0x0007 +#define RTL8365MB_EXT_RGMXF_TXDELAY_MASK 0x0008 + +/* External port speed values - used in DIGITAL_INTERFACE_FORCE */ +#define RTL8365MB_PORT_SPEED_10M 0 +#define RTL8365MB_PORT_SPEED_100M 1 +#define RTL8365MB_PORT_SPEED_1000M 2 + +/* EXT port force configuration registers 0~2 */ +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 0x1310 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG1 0x1311 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG2 0x13C4 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(_extport) \ + (RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 + \ + ((_extport) & 0x1) + \ + ((((_extport) >> 1) & 0x1) * (0x13C4 - 0x1310))) +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_EN_MASK 0x1000 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_NWAY_MASK 0x0080 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_TXPAUSE_MASK 0x0040 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_RXPAUSE_MASK 0x0020 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_LINK_MASK 0x0010 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_DUPLEX_MASK 0x0004 +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_SPEED_MASK 0x0003 + +/* CPU port mask register - controls which ports are treated as CPU ports */ +#define RTL8365MB_CPU_PORT_MASK_REG 0x1219 +#define RTL8365MB_CPU_PORT_MASK_MASK 0x07FF + +/* CPU control register */ +#define RTL8365MB_CPU_CTRL_REG 0x121A +#define RTL8365MB_CPU_CTRL_TRAP_PORT_EXT_MASK 0x0400 +#define RTL8365MB_CPU_CTRL_TAG_FORMAT_MASK 0x0200 +#define RTL8365MB_CPU_CTRL_RXBYTECOUNT_MASK 0x0080 +#define RTL8365MB_CPU_CTRL_TAG_POSITION_MASK 0x0040 +#define RTL8365MB_CPU_CTRL_TRAP_PORT_MASK 0x0038 +#define RTL8365MB_CPU_CTRL_INSERTMODE_MASK 0x0006 +#define RTL8365MB_CPU_CTRL_EN_MASK 0x0001 + +/* Maximum packet length register */ +#define RTL8365MB_CFG0_MAX_LEN_REG 0x088C +#define RTL8365MB_CFG0_MAX_LEN_MASK 0x3FFF + +/* Port learning limit registers */ +#define RTL8365MB_LUT_PORT_LEARN_LIMIT_BASE 0x0A20 +#define RTL8365MB_LUT_PORT_LEARN_LIMIT_REG(_physport) \ + (RTL8365MB_LUT_PORT_LEARN_LIMIT_BASE + (_physport)) + +/* Port isolation (forwarding mask) registers */ +#define RTL8365MB_PORT_ISOLATION_REG_BASE 0x08A2 +#define RTL8365MB_PORT_ISOLATION_REG(_physport) \ + (RTL8365MB_PORT_ISOLATION_REG_BASE + (_physport)) +#define RTL8365MB_PORT_ISOLATION_MASK 0x07FF + +/* MSTP port state registers - indexed by tree instancrSTI (tree ine */ +#define RTL8365MB_MSTI_CTRL_BASE 0x0A00 +#define RTL8365MB_MSTI_CTRL_REG(_msti, _physport) \ + (RTL8365MB_MSTI_CTRL_BASE + ((_msti) << 1) + ((_physport) >> 3)) +#define RTL8365MB_MSTI_CTRL_PORT_STATE_OFFSET(_physport) ((_physport) << 1) +#define RTL8365MB_MSTI_CTRL_PORT_STATE_MASK(_physport) \ + (0x3 << RTL8365MB_MSTI_CTRL_PORT_STATE_OFFSET((_physport))) + +/* MIB counter value registers */ +#define RTL8365MB_MIB_COUNTER_BASE 0x1000 +#define RTL8365MB_MIB_COUNTER_REG(_x) (RTL8365MB_MIB_COUNTER_BASE + (_x)) + +/* MIB counter address register */ +#define RTL8365MB_MIB_ADDRESS_REG 0x1004 +#define RTL8365MB_MIB_ADDRESS_PORT_OFFSET 0x007C +#define RTL8365MB_MIB_ADDRESS(_p, _x) \ + (((RTL8365MB_MIB_ADDRESS_PORT_OFFSET) * (_p) + (_x)) >> 2) + +#define RTL8365MB_MIB_CTRL0_REG 0x1005 +#define RTL8365MB_MIB_CTRL0_RESET_MASK 0x0002 +#define RTL8365MB_MIB_CTRL0_BUSY_MASK 0x0001 + +/* The DSA callback .get_stats64 runs in atomic context, so we are not allowed + * to block. On the other hand, accessing MIB counters absolutely requires us to + * block. The solution is thus to schedule work which polls the MIB counters + * asynchronously and updates some private data, which the callback can then + * fetch atomically. Three seconds should be a good enough polling interval. + */ +#define RTL8365MB_STATS_INTERVAL_JIFFIES (3 * HZ) + +enum rtl8365mb_mib_counter_index { + RTL8365MB_MIB_ifInOctets, + RTL8365MB_MIB_dot3StatsFCSErrors, + RTL8365MB_MIB_dot3StatsSymbolErrors, + RTL8365MB_MIB_dot3InPauseFrames, + RTL8365MB_MIB_dot3ControlInUnknownOpcodes, + RTL8365MB_MIB_etherStatsFragments, + RTL8365MB_MIB_etherStatsJabbers, + RTL8365MB_MIB_ifInUcastPkts, + RTL8365MB_MIB_etherStatsDropEvents, + RTL8365MB_MIB_ifInMulticastPkts, + RTL8365MB_MIB_ifInBroadcastPkts, + RTL8365MB_MIB_inMldChecksumError, + RTL8365MB_MIB_inIgmpChecksumError, + RTL8365MB_MIB_inMldSpecificQuery, + RTL8365MB_MIB_inMldGeneralQuery, + RTL8365MB_MIB_inIgmpSpecificQuery, + RTL8365MB_MIB_inIgmpGeneralQuery, + RTL8365MB_MIB_inMldLeaves, + RTL8365MB_MIB_inIgmpLeaves, + RTL8365MB_MIB_etherStatsOctets, + RTL8365MB_MIB_etherStatsUnderSizePkts, + RTL8365MB_MIB_etherOversizeStats, + RTL8365MB_MIB_etherStatsPkts64Octets, + RTL8365MB_MIB_etherStatsPkts65to127Octets, + RTL8365MB_MIB_etherStatsPkts128to255Octets, + RTL8365MB_MIB_etherStatsPkts256to511Octets, + RTL8365MB_MIB_etherStatsPkts512to1023Octets, + RTL8365MB_MIB_etherStatsPkts1024to1518Octets, + RTL8365MB_MIB_ifOutOctets, + RTL8365MB_MIB_dot3StatsSingleCollisionFrames, + RTL8365MB_MIB_dot3StatsMultipleCollisionFrames, + RTL8365MB_MIB_dot3StatsDeferredTransmissions, + RTL8365MB_MIB_dot3StatsLateCollisions, + RTL8365MB_MIB_etherStatsCollisions, + RTL8365MB_MIB_dot3StatsExcessiveCollisions, + RTL8365MB_MIB_dot3OutPauseFrames, + RTL8365MB_MIB_ifOutDiscards, + RTL8365MB_MIB_dot1dTpPortInDiscards, + RTL8365MB_MIB_ifOutUcastPkts, + RTL8365MB_MIB_ifOutMulticastPkts, + RTL8365MB_MIB_ifOutBroadcastPkts, + RTL8365MB_MIB_outOampduPkts, + RTL8365MB_MIB_inOampduPkts, + RTL8365MB_MIB_inIgmpJoinsSuccess, + RTL8365MB_MIB_inIgmpJoinsFail, + RTL8365MB_MIB_inMldJoinsSuccess, + RTL8365MB_MIB_inMldJoinsFail, + RTL8365MB_MIB_inReportSuppressionDrop, + RTL8365MB_MIB_inLeaveSuppressionDrop, + RTL8365MB_MIB_outIgmpReports, + RTL8365MB_MIB_outIgmpLeaves, + RTL8365MB_MIB_outIgmpGeneralQuery, + RTL8365MB_MIB_outIgmpSpecificQuery, + RTL8365MB_MIB_outMldReports, + RTL8365MB_MIB_outMldLeaves, + RTL8365MB_MIB_outMldGeneralQuery, + RTL8365MB_MIB_outMldSpecificQuery, + RTL8365MB_MIB_inKnownMulticastPkts, + RTL8365MB_MIB_END, +}; + +struct rtl8365mb_mib_counter { + u32 offset; + u32 length; + const char *name; +}; + +#define RTL8365MB_MAKE_MIB_COUNTER(_offset, _length, _name) \ + [RTL8365MB_MIB_ ## _name] = { _offset, _length, #_name } + +static struct rtl8365mb_mib_counter rtl8365mb_mib_counters[] = { + RTL8365MB_MAKE_MIB_COUNTER(0, 4, ifInOctets), + RTL8365MB_MAKE_MIB_COUNTER(4, 2, dot3StatsFCSErrors), + RTL8365MB_MAKE_MIB_COUNTER(6, 2, dot3StatsSymbolErrors), + RTL8365MB_MAKE_MIB_COUNTER(8, 2, dot3InPauseFrames), + RTL8365MB_MAKE_MIB_COUNTER(10, 2, dot3ControlInUnknownOpcodes), + RTL8365MB_MAKE_MIB_COUNTER(12, 2, etherStatsFragments), + RTL8365MB_MAKE_MIB_COUNTER(14, 2, etherStatsJabbers), + RTL8365MB_MAKE_MIB_COUNTER(16, 2, ifInUcastPkts), + RTL8365MB_MAKE_MIB_COUNTER(18, 2, etherStatsDropEvents), + RTL8365MB_MAKE_MIB_COUNTER(20, 2, ifInMulticastPkts), + RTL8365MB_MAKE_MIB_COUNTER(22, 2, ifInBroadcastPkts), + RTL8365MB_MAKE_MIB_COUNTER(24, 2, inMldChecksumError), + RTL8365MB_MAKE_MIB_COUNTER(26, 2, inIgmpChecksumError), + RTL8365MB_MAKE_MIB_COUNTER(28, 2, inMldSpecificQuery), + RTL8365MB_MAKE_MIB_COUNTER(30, 2, inMldGeneralQuery), + RTL8365MB_MAKE_MIB_COUNTER(32, 2, inIgmpSpecificQuery), + RTL8365MB_MAKE_MIB_COUNTER(34, 2, inIgmpGeneralQuery), + RTL8365MB_MAKE_MIB_COUNTER(36, 2, inMldLeaves), + RTL8365MB_MAKE_MIB_COUNTER(38, 2, inIgmpLeaves), + RTL8365MB_MAKE_MIB_COUNTER(40, 4, etherStatsOctets), + RTL8365MB_MAKE_MIB_COUNTER(44, 2, etherStatsUnderSizePkts), + RTL8365MB_MAKE_MIB_COUNTER(46, 2, etherOversizeStats), + RTL8365MB_MAKE_MIB_COUNTER(48, 2, etherStatsPkts64Octets), + RTL8365MB_MAKE_MIB_COUNTER(50, 2, etherStatsPkts65to127Octets), + RTL8365MB_MAKE_MIB_COUNTER(52, 2, etherStatsPkts128to255Octets), + RTL8365MB_MAKE_MIB_COUNTER(54, 2, etherStatsPkts256to511Octets), + RTL8365MB_MAKE_MIB_COUNTER(56, 2, etherStatsPkts512to1023Octets), + RTL8365MB_MAKE_MIB_COUNTER(58, 2, etherStatsPkts1024to1518Octets), + RTL8365MB_MAKE_MIB_COUNTER(60, 4, ifOutOctets), + RTL8365MB_MAKE_MIB_COUNTER(64, 2, dot3StatsSingleCollisionFrames), + RTL8365MB_MAKE_MIB_COUNTER(66, 2, dot3StatsMultipleCollisionFrames), + RTL8365MB_MAKE_MIB_COUNTER(68, 2, dot3StatsDeferredTransmissions), + RTL8365MB_MAKE_MIB_COUNTER(70, 2, dot3StatsLateCollisions), + RTL8365MB_MAKE_MIB_COUNTER(72, 2, etherStatsCollisions), + RTL8365MB_MAKE_MIB_COUNTER(74, 2, dot3StatsExcessiveCollisions), + RTL8365MB_MAKE_MIB_COUNTER(76, 2, dot3OutPauseFrames), + RTL8365MB_MAKE_MIB_COUNTER(78, 2, ifOutDiscards), + RTL8365MB_MAKE_MIB_COUNTER(80, 2, dot1dTpPortInDiscards), + RTL8365MB_MAKE_MIB_COUNTER(82, 2, ifOutUcastPkts), + RTL8365MB_MAKE_MIB_COUNTER(84, 2, ifOutMulticastPkts), + RTL8365MB_MAKE_MIB_COUNTER(86, 2, ifOutBroadcastPkts), + RTL8365MB_MAKE_MIB_COUNTER(88, 2, outOampduPkts), + RTL8365MB_MAKE_MIB_COUNTER(90, 2, inOampduPkts), + RTL8365MB_MAKE_MIB_COUNTER(92, 4, inIgmpJoinsSuccess), + RTL8365MB_MAKE_MIB_COUNTER(96, 2, inIgmpJoinsFail), + RTL8365MB_MAKE_MIB_COUNTER(98, 2, inMldJoinsSuccess), + RTL8365MB_MAKE_MIB_COUNTER(100, 2, inMldJoinsFail), + RTL8365MB_MAKE_MIB_COUNTER(102, 2, inReportSuppressionDrop), + RTL8365MB_MAKE_MIB_COUNTER(104, 2, inLeaveSuppressionDrop), + RTL8365MB_MAKE_MIB_COUNTER(106, 2, outIgmpReports), + RTL8365MB_MAKE_MIB_COUNTER(108, 2, outIgmpLeaves), + RTL8365MB_MAKE_MIB_COUNTER(110, 2, outIgmpGeneralQuery), + RTL8365MB_MAKE_MIB_COUNTER(112, 2, outIgmpSpecificQuery), + RTL8365MB_MAKE_MIB_COUNTER(114, 2, outMldReports), + RTL8365MB_MAKE_MIB_COUNTER(116, 2, outMldLeaves), + RTL8365MB_MAKE_MIB_COUNTER(118, 2, outMldGeneralQuery), + RTL8365MB_MAKE_MIB_COUNTER(120, 2, outMldSpecificQuery), + RTL8365MB_MAKE_MIB_COUNTER(122, 2, inKnownMulticastPkts), +}; + +static_assert(ARRAY_SIZE(rtl8365mb_mib_counters) == RTL8365MB_MIB_END); + +struct rtl8365mb_jam_tbl_entry { + u16 reg; + u16 val; +}; + +/* Lifted from the vendor driver sources */ +static const struct rtl8365mb_jam_tbl_entry rtl8365mb_init_jam_8365mb_vc[] = { + { 0x13EB, 0x15BB }, { 0x1303, 0x06D6 }, { 0x1304, 0x0700 }, + { 0x13E2, 0x003F }, { 0x13F9, 0x0090 }, { 0x121E, 0x03CA }, + { 0x1233, 0x0352 }, { 0x1237, 0x00A0 }, { 0x123A, 0x0030 }, + { 0x1239, 0x0084 }, { 0x0301, 0x1000 }, { 0x1349, 0x001F }, + { 0x18E0, 0x4004 }, { 0x122B, 0x241C }, { 0x1305, 0xC000 }, + { 0x13F0, 0x0000 }, +}; + +static const struct rtl8365mb_jam_tbl_entry rtl8365mb_init_jam_common[] = { + { 0x1200, 0x7FCB }, { 0x0884, 0x0003 }, { 0x06EB, 0x0001 }, + { 0x03Fa, 0x0007 }, { 0x08C8, 0x00C0 }, { 0x0A30, 0x020E }, + { 0x0800, 0x0000 }, { 0x0802, 0x0000 }, { 0x09DA, 0x0013 }, + { 0x1D32, 0x0002 }, +}; + +enum rtl8365mb_stp_state { + RTL8365MB_STP_STATE_DISABLED = 0, + RTL8365MB_STP_STATE_BLOCKING = 1, + RTL8365MB_STP_STATE_LEARNING = 2, + RTL8365MB_STP_STATE_FORWARDING = 3, +}; + +enum rtl8365mb_cpu_insert { + RTL8365MB_CPU_INSERT_TO_ALL = 0, + RTL8365MB_CPU_INSERT_TO_TRAPPING = 1, + RTL8365MB_CPU_INSERT_TO_NONE = 2, +}; + +enum rtl8365mb_cpu_position { + RTL8365MB_CPU_POS_AFTER_SA = 0, + RTL8365MB_CPU_POS_BEFORE_CRC = 1, +}; + +enum rtl8365mb_cpu_format { + RTL8365MB_CPU_FORMAT_8BYTES = 0, + RTL8365MB_CPU_FORMAT_4BYTES = 1, +}; + +enum rtl8365mb_cpu_rxlen { + RTL8365MB_CPU_RXLEN_72BYTES = 0, + RTL8365MB_CPU_RXLEN_64BYTES = 1, +}; + +/** + * struct rtl8365mb_cpu - CPU port configuration + * @enable: enable/disable hardware insertion of CPU tag in switch->CPU frames + * @mask: port mask of ports that parse should parse CPU tags + * @trap_port: forward trapped frames to this port + * @insert: CPU tag insertion mode in switch->CPU frames + * @position: position of CPU tag in frame + * @rx_length: minimum CPU RX length + * @format: CPU tag format + * + * Represents the CPU tagging and CPU port configuration of the switch. These + * settings are configurable at runtime. + */ +struct rtl8365mb_cpu { + bool enable; + u32 mask; + u32 trap_port; + enum rtl8365mb_cpu_insert insert; + enum rtl8365mb_cpu_position position; + enum rtl8365mb_cpu_rxlen rx_length; + enum rtl8365mb_cpu_format format; +}; + +/** + * struct rtl8365mb_port - private per-port data + * @smi: pointer to parent realtek_smi data + * @index: DSA port index, same as dsa_port::index + * @stats: link statistics populated by rtl8365mb_stats_poll, ready for atomic + * access via rtl8365mb_get_stats64 + * @stats_lock: protect the stats structure during read/update + * @mib_work: delayed work for polling MIB counters + */ +struct rtl8365mb_port { + struct realtek_smi *smi; + unsigned int index; + struct rtnl_link_stats64 stats; + spinlock_t stats_lock; + struct delayed_work mib_work; +}; + +/** + * struct rtl8365mb - private chip-specific driver data + * @smi: pointer to parent realtek_smi data + * @irq: registered IRQ or zero + * @chip_id: chip identifier + * @chip_ver: chip silicon revision + * @port_mask: mask of all ports + * @learn_limit_max: maximum number of L2 addresses the chip can learn + * @cpu: CPU tagging and CPU port configuration for this chip + * @mib_lock: prevent concurrent reads of MIB counters + * @ports: per-port data + * @jam_table: chip-specific initialization jam table + * @jam_size: size of the chip's jam table + * + * Private data for this driver. + */ +struct rtl8365mb { + struct realtek_smi *smi; + int irq; + u32 chip_id; + u32 chip_ver; + u32 port_mask; + u32 learn_limit_max; + struct rtl8365mb_cpu cpu; + struct mutex mib_lock; + struct rtl8365mb_port ports[RTL8365MB_MAX_NUM_PORTS]; + const struct rtl8365mb_jam_tbl_entry *jam_table; + size_t jam_size; +}; + +static int rtl8365mb_phy_poll_busy(struct realtek_smi *smi) +{ + u32 val; + + return regmap_read_poll_timeout(smi->map, + RTL8365MB_INDIRECT_ACCESS_STATUS_REG, + val, !val, 10, 100); +} + +static int rtl8365mb_phy_ocp_prepare(struct realtek_smi *smi, int phy, + u32 ocp_addr) +{ + u32 val; + int ret; + + /* Set OCP prefix */ + val = FIELD_GET(RTL8365MB_PHY_OCP_ADDR_PREFIX_MASK, ocp_addr); + ret = regmap_update_bits( + smi->map, RTL8365MB_GPHY_OCP_MSB_0_REG, + RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK, + FIELD_PREP(RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK, val)); + if (ret) + return ret; + + /* Set PHY register address */ + val = RTL8365MB_PHY_BASE; + val |= FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_ADDRESS_PHYNUM_MASK, phy); + val |= FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_5_1_MASK, + ocp_addr >> 1); + val |= FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_9_6_MASK, + ocp_addr >> 6); + ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG, + val); + if (ret) + return ret; + + return 0; +} + +static int rtl8365mb_phy_ocp_read(struct realtek_smi *smi, int phy, + u32 ocp_addr, u16 *data) +{ + u32 val; + int ret; + + ret = rtl8365mb_phy_poll_busy(smi); + if (ret) + return ret; + + ret = rtl8365mb_phy_ocp_prepare(smi, phy, ocp_addr); + if (ret) + return ret; + + /* Execute read operation */ + val = FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_MASK, + RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE) | + FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK, + RTL8365MB_INDIRECT_ACCESS_CTRL_RW_READ); + ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); + if (ret) + return ret; + + ret = rtl8365mb_phy_poll_busy(smi); + if (ret) + return ret; + + /* Get PHY register data */ + ret = regmap_read(smi->map, RTL8365MB_INDIRECT_ACCESS_READ_DATA_REG, + &val); + if (ret) + return ret; + + *data = val & 0xFFFF; + + return 0; +} + +static int rtl8365mb_phy_ocp_write(struct realtek_smi *smi, int phy, + u32 ocp_addr, u16 data) +{ + u32 val; + int ret; + + ret = rtl8365mb_phy_poll_busy(smi); + if (ret) + return ret; + + ret = rtl8365mb_phy_ocp_prepare(smi, phy, ocp_addr); + if (ret) + return ret; + + /* Set PHY register data */ + ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG, + data); + if (ret) + return ret; + + /* Execute write operation */ + val = FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_MASK, + RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE) | + FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK, + RTL8365MB_INDIRECT_ACCESS_CTRL_RW_WRITE); + ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); + if (ret) + return ret; + + ret = rtl8365mb_phy_poll_busy(smi); + if (ret) + return ret; + + return 0; +} + +static int rtl8365mb_phy_read(struct realtek_smi *smi, int phy, int regnum) +{ + u32 ocp_addr; + u16 val; + int ret; + + if (regnum > RTL8365MB_PHYREGMAX) + return -EINVAL; + + ocp_addr = RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE + regnum * 2; + + ret = rtl8365mb_phy_ocp_read(smi, phy, ocp_addr, &val); + if (ret) { + dev_err(smi->dev, + "failed to read PHY%d reg %02x @ %04x, ret %d\n", phy, + regnum, ocp_addr, ret); + return ret; + } + + dev_dbg(smi->dev, "read PHY%d register 0x%02x @ %04x, val <- %04x\n", + phy, regnum, ocp_addr, val); + + return val; +} + +static int rtl8365mb_phy_write(struct realtek_smi *smi, int phy, int regnum, + u16 val) +{ + u32 ocp_addr; + int ret; + + if (regnum > RTL8365MB_PHYREGMAX) + return -EINVAL; + + ocp_addr = RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE + regnum * 2; + + ret = rtl8365mb_phy_ocp_write(smi, phy, ocp_addr, val); + if (ret) { + dev_err(smi->dev, + "failed to write PHY%d reg %02x @ %04x, ret %d\n", phy, + regnum, ocp_addr, ret); + return ret; + } + + dev_dbg(smi->dev, "write PHY%d register 0x%02x @ %04x, val -> %04x\n", + phy, regnum, ocp_addr, val); + + return 0; +} + +static enum dsa_tag_protocol +rtl8365mb_get_tag_protocol(struct dsa_switch *ds, int port, + enum dsa_tag_protocol mp) +{ + return DSA_TAG_PROTO_RTL8_4; +} + +static int rtl8365mb_ext_config_rgmii(struct realtek_smi *smi, int port, + phy_interface_t interface) +{ + struct device_node *dn; + struct dsa_port *dp; + int tx_delay = 0; + int rx_delay = 0; + int ext_port; + u32 val; + int ret; + + if (port == smi->cpu_port) { + ext_port = 1; + } else { + dev_err(smi->dev, "only one EXT port is currently supported\n"); + return -EINVAL; + } + + dp = dsa_to_port(smi->ds, port); + dn = dp->dn; + + /* Set the RGMII TX/RX delay + * + * The Realtek vendor driver indicates the following possible + * configuration settings: + * + * TX delay: + * 0 = no delay, 1 = 2 ns delay + * RX delay: + * 0 = no delay, 7 = maximum delay + * No units are specified, but there are a total of 8 steps. + * + * The vendor driver also states that this must be configured *before* + * forcing the external interface into a particular mode, which is done + * in the rtl8365mb_phylink_mac_link_{up,down} functions. + * + * Only configure an RGMII TX (resp. RX) delay if the + * tx-internal-delay-ps (resp. rx-internal-delay-ps) OF property is + * specified. We ignore the detail of the RGMII interface mode + * (RGMII_{RXID, TXID, etc.}), as this is considered to be a PHY-only + * property. + * + * For the RX delay, we assume that a register value of 4 corresponds to + * 2 ns. But this is just an educated guess, so ignore all other values + * to avoid too much confusion. + */ + if (!of_property_read_u32(dn, "tx-internal-delay-ps", &val)) { + val = val / 1000; /* convert to ns */ + + if (val == 0 || val == 2) + tx_delay = val / 2; + else + dev_warn(smi->dev, + "EXT port TX delay must be 0 or 2 ns\n"); + } + + if (!of_property_read_u32(dn, "rx-internal-delay-ps", &val)) { + val = val / 1000; /* convert to ns */ + + if (val == 0 || val == 2) + rx_delay = val * 2; + else + dev_warn(smi->dev, + "EXT port RX delay must be 0 to 2 ns\n"); + } + + ret = regmap_update_bits( + smi->map, RTL8365MB_EXT_RGMXF_REG(ext_port), + RTL8365MB_EXT_RGMXF_TXDELAY_MASK | + RTL8365MB_EXT_RGMXF_RXDELAY_MASK, + FIELD_PREP(RTL8365MB_EXT_RGMXF_TXDELAY_MASK, tx_delay) | + FIELD_PREP(RTL8365MB_EXT_RGMXF_RXDELAY_MASK, rx_delay)); + if (ret) + return ret; + + ret = regmap_update_bits( + smi->map, RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(ext_port), + RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(ext_port), + RTL8365MB_EXT_PORT_MODE_RGMII + << RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET( + ext_port)); + if (ret) + return ret; + + return 0; +} + +static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, + bool link, int speed, int duplex, + bool tx_pause, bool rx_pause) +{ + u32 r_tx_pause; + u32 r_rx_pause; + u32 r_duplex; + u32 r_speed; + u32 r_link; + int ext_port; + int val; + int ret; + + if (port == smi->cpu_port) { + ext_port = 1; + } else { + dev_err(smi->dev, "only one EXT port is currently supported\n"); + return -EINVAL; + } + + if (link) { + /* Force the link up with the desired configuration */ + r_link = 1; + r_rx_pause = rx_pause ? 1 : 0; + r_tx_pause = tx_pause ? 1 : 0; + + if (speed == SPEED_1000) { + r_speed = RTL8365MB_PORT_SPEED_1000M; + } else if (speed == SPEED_100) { + r_speed = RTL8365MB_PORT_SPEED_100M; + } else if (speed == SPEED_10) { + r_speed = RTL8365MB_PORT_SPEED_10M; + } else { + dev_err(smi->dev, "unsupported port speed %s\n", + phy_speed_to_str(speed)); + return -EINVAL; + } + + if (duplex == DUPLEX_FULL) { + r_duplex = 1; + } else if (duplex == DUPLEX_HALF) { + r_duplex = 0; + } else { + dev_err(smi->dev, "unsupported duplex %s\n", + phy_duplex_to_str(duplex)); + return -EINVAL; + } + } else { + /* Force the link down and reset any programmed configuration */ + r_link = 0; + r_tx_pause = 0; + r_rx_pause = 0; + r_speed = 0; + r_duplex = 0; + } + + val = FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_EN_MASK, 1) | + FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_TXPAUSE_MASK, + r_tx_pause) | + FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_RXPAUSE_MASK, + r_rx_pause) | + FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_LINK_MASK, r_link) | + FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_DUPLEX_MASK, + r_duplex) | + FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_SPEED_MASK, r_speed); + ret = regmap_write(smi->map, + RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(ext_port), + val); + if (ret) + return ret; + + return 0; +} + +static bool rtl8365mb_phy_mode_supported(struct dsa_switch *ds, int port, + phy_interface_t interface) +{ + if (dsa_is_user_port(ds, port) && + (interface == PHY_INTERFACE_MODE_NA || + interface == PHY_INTERFACE_MODE_INTERNAL)) + /* Internal PHY */ + return true; + else if (dsa_is_cpu_port(ds, port) && + phy_interface_mode_is_rgmii(interface)) + /* Extension MAC */ + return true; + + return false; +} + +static void rtl8365mb_phylink_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct realtek_smi *smi = ds->priv; + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0 }; + + /* include/linux/phylink.h says: + * When @state->interface is %PHY_INTERFACE_MODE_NA, phylink + * expects the MAC driver to return all supported link modes. + */ + if (state->interface != PHY_INTERFACE_MODE_NA && + !rtl8365mb_phy_mode_supported(ds, port, state->interface)) { + dev_err(smi->dev, "phy mode %s is unsupported on port %d\n", + phy_modes(state->interface), port); + linkmode_zero(supported); + return; + } + + phylink_set_port_modes(mask); + + phylink_set(mask, Autoneg); + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); + + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + phylink_set(mask, 1000baseT_Full); + + linkmode_and(supported, supported, mask); + linkmode_and(state->advertising, state->advertising, mask); +} + +static void rtl8365mb_phylink_mac_config(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct realtek_smi *smi = ds->priv; + int ret; + + if (!rtl8365mb_phy_mode_supported(ds, port, state->interface)) { + dev_err(smi->dev, "phy mode %s is unsupported on port %d\n", + phy_modes(state->interface), port); + return; + } + + if (mode != MLO_AN_PHY && mode != MLO_AN_FIXED) { + dev_err(smi->dev, + "port %d supports only conventional PHY or fixed-link\n", + port); + return; + } + + if (phy_interface_mode_is_rgmii(state->interface)) { + ret = rtl8365mb_ext_config_rgmii(smi, port, state->interface); + if (ret) + dev_err(smi->dev, + "failed to configure RGMII mode on port %d: %d\n", + port, ret); + return; + } + + /* TODO: Implement MII and RMII modes, which the RTL8365MB-VC also + * supports + */ +} + +static void rtl8365mb_phylink_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb_port *p; + struct rtl8365mb *mb; + int ret; + + mb = smi->chip_data; + p = &mb->ports[port]; + cancel_delayed_work_sync(&p->mib_work); + + if (phy_interface_mode_is_rgmii(interface)) { + ret = rtl8365mb_ext_config_forcemode(smi, port, false, 0, 0, + false, false); + if (ret) + dev_err(smi->dev, + "failed to reset forced mode on port %d: %d\n", + port, ret); + + return; + } +} + +static void rtl8365mb_phylink_mac_link_up(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev, int speed, + int duplex, bool tx_pause, + bool rx_pause) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb_port *p; + struct rtl8365mb *mb; + int ret; + + mb = smi->chip_data; + p = &mb->ports[port]; + schedule_delayed_work(&p->mib_work, 0); + + if (phy_interface_mode_is_rgmii(interface)) { + ret = rtl8365mb_ext_config_forcemode(smi, port, true, speed, + duplex, tx_pause, + rx_pause); + if (ret) + dev_err(smi->dev, + "failed to force mode on port %d: %d\n", port, + ret); + + return; + } +} + +static void rtl8365mb_port_stp_state_set(struct dsa_switch *ds, int port, + u8 state) +{ + struct realtek_smi *smi = ds->priv; + enum rtl8365mb_stp_state val; + int msti = 0; + + switch (state) { + case BR_STATE_DISABLED: + val = RTL8365MB_STP_STATE_DISABLED; + break; + case BR_STATE_BLOCKING: + case BR_STATE_LISTENING: + val = RTL8365MB_STP_STATE_BLOCKING; + break; + case BR_STATE_LEARNING: + val = RTL8365MB_STP_STATE_LEARNING; + break; + case BR_STATE_FORWARDING: + val = RTL8365MB_STP_STATE_FORWARDING; + break; + default: + dev_err(smi->dev, "invalid STP state: %u\n", state); + return; + } + + regmap_update_bits(smi->map, RTL8365MB_MSTI_CTRL_REG(msti, port), + RTL8365MB_MSTI_CTRL_PORT_STATE_MASK(port), + val << RTL8365MB_MSTI_CTRL_PORT_STATE_OFFSET(port)); +} + +static int rtl8365mb_port_set_learning(struct realtek_smi *smi, int port, + bool enable) +{ + struct rtl8365mb *mb = smi->chip_data; + + /* Enable/disable learning by limiting the number of L2 addresses the + * port can learn. Realtek documentation states that a limit of zero + * disables learning. When enabling learning, set it to the chip's + * maximum. + */ + return regmap_write(smi->map, RTL8365MB_LUT_PORT_LEARN_LIMIT_REG(port), + enable ? mb->learn_limit_max : 0); +} + +static int rtl8365mb_port_set_isolation(struct realtek_smi *smi, int port, + u32 mask) +{ + return regmap_write(smi->map, RTL8365MB_PORT_ISOLATION_REG(port), mask); +} + +static int rtl8365mb_mib_counter_read(struct realtek_smi *smi, int port, + u32 offset, u32 length, u64 *mibvalue) +{ + u64 tmpvalue = 0; + u32 val; + int ret; + int i; + + /* The MIB address is an SRAM address. We request a particular address + * and then poll the control register before reading the value from some + * counter registers. + */ + ret = regmap_write(smi->map, RTL8365MB_MIB_ADDRESS_REG, + RTL8365MB_MIB_ADDRESS(port, offset)); + if (ret) + return ret; + + /* Poll for completion */ + ret = regmap_read_poll_timeout(smi->map, RTL8365MB_MIB_CTRL0_REG, val, + !(val & RTL8365MB_MIB_CTRL0_BUSY_MASK), + 10, 100); + if (ret) + return ret; + + /* Presumably this indicates a MIB counter read failure */ + if (val & RTL8365MB_MIB_CTRL0_RESET_MASK) + return -EIO; + + /* There are four MIB counter registers each holding a 16 bit word of a + * MIB counter. Depending on the offset, we should read from the upper + * two or lower two registers. In case the MIB counter is 4 words, we + * read from all four registers. + */ + if (length == 4) + offset = 3; + else + offset = (offset + 1) % 4; + + /* Read the MIB counter 16 bits at a time */ + for (i = 0; i < length; i++) { + ret = regmap_read(smi->map, + RTL8365MB_MIB_COUNTER_REG(offset - i), &val); + if (ret) + return ret; + + tmpvalue = ((tmpvalue) << 16) | (val & 0xFFFF); + } + + /* Only commit the result if no error occurred */ + *mibvalue = tmpvalue; + + return 0; +} + +static void rtl8365mb_get_ethtool_stats(struct dsa_switch *ds, int port, u64 *data) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb *mb; + int ret; + int i; + + mb = smi->chip_data; + + mutex_lock(&mb->mib_lock); + for (i = 0; i < RTL8365MB_MIB_END; i++) { + struct rtl8365mb_mib_counter *mib = &rtl8365mb_mib_counters[i]; + + ret = rtl8365mb_mib_counter_read(smi, port, mib->offset, + mib->length, &data[i]); + if (ret) { + dev_err(smi->dev, + "failed to read port %d counters: %d\n", port, + ret); + break; + } + } + mutex_unlock(&mb->mib_lock); +} + +static void rtl8365mb_get_strings(struct dsa_switch *ds, int port, u32 stringset, u8 *data) +{ + int i; + + if (stringset != ETH_SS_STATS) + return; + + for (i = 0; i < RTL8365MB_MIB_END; i++) { + struct rtl8365mb_mib_counter *mib = &rtl8365mb_mib_counters[i]; + + strncpy(data + i * ETH_GSTRING_LEN, mib->name, ETH_GSTRING_LEN); + } +} + +static int rtl8365mb_get_sset_count(struct dsa_switch *ds, int port, int sset) +{ + if (sset != ETH_SS_STATS) + return -EOPNOTSUPP; + + return RTL8365MB_MIB_END; +} + +static void rtl8365mb_get_phy_stats(struct dsa_switch *ds, int port, + struct ethtool_eth_phy_stats *phy_stats) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb_mib_counter *mib; + struct rtl8365mb *mb; + + mb = smi->chip_data; + mib = &rtl8365mb_mib_counters[RTL8365MB_MIB_dot3StatsSymbolErrors]; + + mutex_lock(&mb->mib_lock); + rtl8365mb_mib_counter_read(smi, port, mib->offset, mib->length, + &phy_stats->SymbolErrorDuringCarrier); + mutex_unlock(&mb->mib_lock); +} + +static void rtl8365mb_get_mac_stats(struct dsa_switch *ds, int port, + struct ethtool_eth_mac_stats *mac_stats) +{ + u64 cnt[RTL8365MB_MIB_END] = { + [RTL8365MB_MIB_ifOutOctets] = 1, + [RTL8365MB_MIB_ifOutUcastPkts] = 1, + [RTL8365MB_MIB_ifOutMulticastPkts] = 1, + [RTL8365MB_MIB_ifOutBroadcastPkts] = 1, + [RTL8365MB_MIB_dot3OutPauseFrames] = 1, + [RTL8365MB_MIB_ifOutDiscards] = 1, + [RTL8365MB_MIB_ifInOctets] = 1, + [RTL8365MB_MIB_ifInUcastPkts] = 1, + [RTL8365MB_MIB_ifInMulticastPkts] = 1, + [RTL8365MB_MIB_ifInBroadcastPkts] = 1, + [RTL8365MB_MIB_dot3InPauseFrames] = 1, + [RTL8365MB_MIB_dot3StatsSingleCollisionFrames] = 1, + [RTL8365MB_MIB_dot3StatsMultipleCollisionFrames] = 1, + [RTL8365MB_MIB_dot3StatsFCSErrors] = 1, + [RTL8365MB_MIB_dot3StatsDeferredTransmissions] = 1, + [RTL8365MB_MIB_dot3StatsLateCollisions] = 1, + [RTL8365MB_MIB_dot3StatsExcessiveCollisions] = 1, + + }; + struct realtek_smi *smi = ds->priv; + struct rtl8365mb *mb; + int ret; + int i; + + mb = smi->chip_data; + + mutex_lock(&mb->mib_lock); + for (i = 0; i < RTL8365MB_MIB_END; i++) { + struct rtl8365mb_mib_counter *mib = &rtl8365mb_mib_counters[i]; + + /* Only fetch required MIB counters (marked = 1 above) */ + if (!cnt[i]) + continue; + + ret = rtl8365mb_mib_counter_read(smi, port, mib->offset, + mib->length, &cnt[i]); + if (ret) + break; + } + mutex_unlock(&mb->mib_lock); + + /* The RTL8365MB-VC exposes MIB objects, which we have to translate into + * IEEE 802.3 Managed Objects. This is not always completely faithful, + * but we try out best. See RFC 3635 for a detailed treatment of the + * subject. + */ + + mac_stats->FramesTransmittedOK = cnt[RTL8365MB_MIB_ifOutUcastPkts] + + cnt[RTL8365MB_MIB_ifOutMulticastPkts] + + cnt[RTL8365MB_MIB_ifOutBroadcastPkts] + + cnt[RTL8365MB_MIB_dot3OutPauseFrames] - + cnt[RTL8365MB_MIB_ifOutDiscards]; + mac_stats->SingleCollisionFrames = + cnt[RTL8365MB_MIB_dot3StatsSingleCollisionFrames]; + mac_stats->MultipleCollisionFrames = + cnt[RTL8365MB_MIB_dot3StatsMultipleCollisionFrames]; + mac_stats->FramesReceivedOK = cnt[RTL8365MB_MIB_ifInUcastPkts] + + cnt[RTL8365MB_MIB_ifInMulticastPkts] + + cnt[RTL8365MB_MIB_ifInBroadcastPkts] + + cnt[RTL8365MB_MIB_dot3InPauseFrames]; + mac_stats->FrameCheckSequenceErrors = + cnt[RTL8365MB_MIB_dot3StatsFCSErrors]; + mac_stats->OctetsTransmittedOK = cnt[RTL8365MB_MIB_ifOutOctets] - + 18 * mac_stats->FramesTransmittedOK; + mac_stats->FramesWithDeferredXmissions = + cnt[RTL8365MB_MIB_dot3StatsDeferredTransmissions]; + mac_stats->LateCollisions = cnt[RTL8365MB_MIB_dot3StatsLateCollisions]; + mac_stats->FramesAbortedDueToXSColls = + cnt[RTL8365MB_MIB_dot3StatsExcessiveCollisions]; + mac_stats->OctetsReceivedOK = cnt[RTL8365MB_MIB_ifInOctets] - + 18 * mac_stats->FramesReceivedOK; + mac_stats->MulticastFramesXmittedOK = + cnt[RTL8365MB_MIB_ifOutMulticastPkts]; + mac_stats->BroadcastFramesXmittedOK = + cnt[RTL8365MB_MIB_ifOutBroadcastPkts]; + mac_stats->MulticastFramesReceivedOK = + cnt[RTL8365MB_MIB_ifInMulticastPkts]; + mac_stats->BroadcastFramesReceivedOK = + cnt[RTL8365MB_MIB_ifInBroadcastPkts]; +} + +static void rtl8365mb_get_ctrl_stats(struct dsa_switch *ds, int port, + struct ethtool_eth_ctrl_stats *ctrl_stats) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb_mib_counter *mib; + struct rtl8365mb *mb; + + mb = smi->chip_data; + mib = &rtl8365mb_mib_counters[RTL8365MB_MIB_dot3ControlInUnknownOpcodes]; + + mutex_lock(&mb->mib_lock); + rtl8365mb_mib_counter_read(smi, port, mib->offset, mib->length, + &ctrl_stats->UnsupportedOpcodesReceived); + mutex_unlock(&mb->mib_lock); +} + +static void rtl8365mb_stats_update(struct realtek_smi *smi, int port) +{ + u64 cnt[RTL8365MB_MIB_END] = { + [RTL8365MB_MIB_ifOutOctets] = 1, + [RTL8365MB_MIB_ifOutUcastPkts] = 1, + [RTL8365MB_MIB_ifOutMulticastPkts] = 1, + [RTL8365MB_MIB_ifOutBroadcastPkts] = 1, + [RTL8365MB_MIB_ifOutDiscards] = 1, + [RTL8365MB_MIB_ifInOctets] = 1, + [RTL8365MB_MIB_ifInUcastPkts] = 1, + [RTL8365MB_MIB_ifInMulticastPkts] = 1, + [RTL8365MB_MIB_ifInBroadcastPkts] = 1, + [RTL8365MB_MIB_etherStatsDropEvents] = 1, + [RTL8365MB_MIB_etherStatsCollisions] = 1, + [RTL8365MB_MIB_etherStatsFragments] = 1, + [RTL8365MB_MIB_etherStatsJabbers] = 1, + [RTL8365MB_MIB_dot3StatsFCSErrors] = 1, + [RTL8365MB_MIB_dot3StatsLateCollisions] = 1, + }; + struct rtl8365mb *mb = smi->chip_data; + struct rtnl_link_stats64 *stats; + int ret; + int i; + + stats = &mb->ports[port].stats; + + mutex_lock(&mb->mib_lock); + for (i = 0; i < RTL8365MB_MIB_END; i++) { + struct rtl8365mb_mib_counter *c = &rtl8365mb_mib_counters[i]; + + /* Only fetch required MIB counters (marked = 1 above) */ + if (!cnt[i]) + continue; + + ret = rtl8365mb_mib_counter_read(smi, port, c->offset, + c->length, &cnt[i]); + if (ret) + break; + } + mutex_unlock(&mb->mib_lock); + + /* Don't update statistics if there was an error reading the counters */ + if (ret) + return; + + spin_lock(&mb->ports[port].stats_lock); + + stats->rx_packets = cnt[RTL8365MB_MIB_ifInUcastPkts] + + cnt[RTL8365MB_MIB_ifInMulticastPkts] + + cnt[RTL8365MB_MIB_ifInBroadcastPkts] - + cnt[RTL8365MB_MIB_ifOutDiscards]; + + stats->tx_packets = cnt[RTL8365MB_MIB_ifOutUcastPkts] + + cnt[RTL8365MB_MIB_ifOutMulticastPkts] + + cnt[RTL8365MB_MIB_ifOutBroadcastPkts]; + + /* if{In,Out}Octets includes FCS - remove it */ + stats->rx_bytes = cnt[RTL8365MB_MIB_ifInOctets] - 4 * stats->rx_packets; + stats->tx_bytes = + cnt[RTL8365MB_MIB_ifOutOctets] - 4 * stats->tx_packets; + + stats->rx_dropped = cnt[RTL8365MB_MIB_etherStatsDropEvents]; + stats->tx_dropped = cnt[RTL8365MB_MIB_ifOutDiscards]; + + stats->multicast = cnt[RTL8365MB_MIB_ifInMulticastPkts]; + stats->collisions = cnt[RTL8365MB_MIB_etherStatsCollisions]; + + stats->rx_length_errors = cnt[RTL8365MB_MIB_etherStatsFragments] + + cnt[RTL8365MB_MIB_etherStatsJabbers]; + stats->rx_crc_errors = cnt[RTL8365MB_MIB_dot3StatsFCSErrors]; + stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors; + + stats->tx_aborted_errors = cnt[RTL8365MB_MIB_ifOutDiscards]; + stats->tx_window_errors = cnt[RTL8365MB_MIB_dot3StatsLateCollisions]; + stats->tx_errors = stats->tx_aborted_errors + stats->tx_window_errors; + + spin_unlock(&mb->ports[port].stats_lock); +} + +static void rtl8365mb_stats_poll(struct work_struct *work) +{ + struct rtl8365mb_port *p = container_of(to_delayed_work(work), + struct rtl8365mb_port, + mib_work); + struct realtek_smi *smi = p->smi; + + rtl8365mb_stats_update(smi, p->index); + + schedule_delayed_work(&p->mib_work, RTL8365MB_STATS_INTERVAL_JIFFIES); +} + +static void rtl8365mb_get_stats64(struct dsa_switch *ds, int port, + struct rtnl_link_stats64 *s) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb_port *p; + struct rtl8365mb *mb; + + mb = smi->chip_data; + p = &mb->ports[port]; + + spin_lock(&p->stats_lock); + memcpy(s, &p->stats, sizeof(*s)); + spin_unlock(&p->stats_lock); +} + +static void rtl8365mb_stats_setup(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + int i; + + /* Per-chip global mutex to protect MIB counter access, since doing + * so requires accessing a series of registers in a particular order. + */ + mutex_init(&mb->mib_lock); + + for (i = 0; i < smi->num_ports; i++) { + struct rtl8365mb_port *p = &mb->ports[i]; + + if (dsa_is_unused_port(smi->ds, i)) + continue; + + /* Per-port spinlock to protect the stats64 data */ + spin_lock_init(&p->stats_lock); + + /* This work polls the MIB counters and keeps the stats64 data + * up-to-date. + */ + INIT_DELAYED_WORK(&p->mib_work, rtl8365mb_stats_poll); + } +} + +static void rtl8365mb_stats_teardown(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + int i; + + for (i = 0; i < smi->num_ports; i++) { + struct rtl8365mb_port *p = &mb->ports[i]; + + if (dsa_is_unused_port(smi->ds, i)) + continue; + + cancel_delayed_work_sync(&p->mib_work); + } +} + +static int rtl8365mb_get_and_clear_status_reg(struct realtek_smi *smi, u32 reg, + u32 *val) +{ + int ret; + + ret = regmap_read(smi->map, reg, val); + if (ret) + return ret; + + return regmap_write(smi->map, reg, *val); +} + +static irqreturn_t rtl8365mb_irq(int irq, void *data) +{ + struct realtek_smi *smi = data; + unsigned long line_changes = 0; + struct rtl8365mb *mb; + u32 stat; + int line; + int ret; + + mb = smi->chip_data; + + ret = rtl8365mb_get_and_clear_status_reg(smi, RTL8365MB_INTR_STATUS_REG, + &stat); + if (ret) + goto out_error; + + if (stat & RTL8365MB_INTR_LINK_CHANGE_MASK) { + u32 linkdown_ind; + u32 linkup_ind; + u32 val; + + ret = rtl8365mb_get_and_clear_status_reg( + smi, RTL8365MB_PORT_LINKUP_IND_REG, &val); + if (ret) + goto out_error; + + linkup_ind = FIELD_GET(RTL8365MB_PORT_LINKUP_IND_MASK, val); + + ret = rtl8365mb_get_and_clear_status_reg( + smi, RTL8365MB_PORT_LINKDOWN_IND_REG, &val); + if (ret) + goto out_error; + + linkdown_ind = FIELD_GET(RTL8365MB_PORT_LINKDOWN_IND_MASK, val); + + line_changes = (linkup_ind | linkdown_ind) & mb->port_mask; + } + + if (!line_changes) + goto out_none; + + for_each_set_bit(line, &line_changes, smi->num_ports) { + int child_irq = irq_find_mapping(smi->irqdomain, line); + + handle_nested_irq(child_irq); + } + + return IRQ_HANDLED; + +out_error: + dev_err(smi->dev, "failed to read interrupt status: %d\n", ret); + +out_none: + return IRQ_NONE; +} + +static struct irq_chip rtl8365mb_irq_chip = { + .name = "rtl8365mb", + /* The hardware doesn't support masking IRQs on a per-port basis */ +}; + +static int rtl8365mb_irq_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_data(irq, domain->host_data); + irq_set_chip_and_handler(irq, &rtl8365mb_irq_chip, handle_simple_irq); + irq_set_nested_thread(irq, 1); + irq_set_noprobe(irq); + + return 0; +} + +static void rtl8365mb_irq_unmap(struct irq_domain *d, unsigned int irq) +{ + irq_set_nested_thread(irq, 0); + irq_set_chip_and_handler(irq, NULL, NULL); + irq_set_chip_data(irq, NULL); +} + +static const struct irq_domain_ops rtl8365mb_irqdomain_ops = { + .map = rtl8365mb_irq_map, + .unmap = rtl8365mb_irq_unmap, + .xlate = irq_domain_xlate_onecell, +}; + +static int rtl8365mb_set_irq_enable(struct realtek_smi *smi, bool enable) +{ + return regmap_update_bits(smi->map, RTL8365MB_INTR_CTRL_REG, + RTL8365MB_INTR_LINK_CHANGE_MASK, + FIELD_PREP(RTL8365MB_INTR_LINK_CHANGE_MASK, + enable ? 1 : 0)); +} + +static int rtl8365mb_irq_enable(struct realtek_smi *smi) +{ + return rtl8365mb_set_irq_enable(smi, true); +} + +static int rtl8365mb_irq_disable(struct realtek_smi *smi) +{ + return rtl8365mb_set_irq_enable(smi, false); +} + +static int rtl8365mb_irq_setup(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + struct device_node *intc; + u32 irq_trig; + int virq; + int irq; + u32 val; + int ret; + int i; + + intc = of_get_child_by_name(smi->dev->of_node, "interrupt-controller"); + if (!intc) { + dev_err(smi->dev, "missing child interrupt-controller node\n"); + return -EINVAL; + } + + /* rtl8365mb IRQs cascade off this one */ + irq = of_irq_get(intc, 0); + if (irq <= 0) { + if (irq != -EPROBE_DEFER) + dev_err(smi->dev, "failed to get parent irq: %d\n", + irq); + ret = irq ? irq : -EINVAL; + goto out_put_node; + } + + smi->irqdomain = irq_domain_add_linear(intc, smi->num_ports, + &rtl8365mb_irqdomain_ops, smi); + if (!smi->irqdomain) { + dev_err(smi->dev, "failed to add irq domain\n"); + ret = -ENOMEM; + goto out_put_node; + } + + for (i = 0; i < smi->num_ports; i++) { + virq = irq_create_mapping(smi->irqdomain, i); + if (!virq) { + dev_err(smi->dev, + "failed to create irq domain mapping\n"); + ret = -EINVAL; + goto out_remove_irqdomain; + } + + irq_set_parent(virq, irq); + } + + /* Configure chip interrupt signal polarity */ + irq_trig = irqd_get_trigger_type(irq_get_irq_data(irq)); + switch (irq_trig) { + case IRQF_TRIGGER_RISING: + case IRQF_TRIGGER_HIGH: + val = RTL8365MB_INTR_POLARITY_HIGH; + break; + case IRQF_TRIGGER_FALLING: + case IRQF_TRIGGER_LOW: + val = RTL8365MB_INTR_POLARITY_LOW; + break; + default: + dev_err(smi->dev, "unsupported irq trigger type %u\n", + irq_trig); + ret = -EINVAL; + goto out_remove_irqdomain; + } + + ret = regmap_update_bits(smi->map, RTL8365MB_INTR_POLARITY_REG, + RTL8365MB_INTR_POLARITY_MASK, + FIELD_PREP(RTL8365MB_INTR_POLARITY_MASK, val)); + if (ret) + goto out_remove_irqdomain; + + /* Disable the interrupt in case the chip has it enabled on reset */ + ret = rtl8365mb_irq_disable(smi); + if (ret) + goto out_remove_irqdomain; + + /* Clear the interrupt status register */ + ret = regmap_write(smi->map, RTL8365MB_INTR_STATUS_REG, + RTL8365MB_INTR_ALL_MASK); + if (ret) + goto out_remove_irqdomain; + + ret = request_threaded_irq(irq, NULL, rtl8365mb_irq, IRQF_ONESHOT, + "rtl8365mb", smi); + if (ret) { + dev_err(smi->dev, "failed to request irq: %d\n", ret); + goto out_remove_irqdomain; + } + + /* Store the irq so that we know to free it during teardown */ + mb->irq = irq; + + ret = rtl8365mb_irq_enable(smi); + if (ret) + goto out_free_irq; + + of_node_put(intc); + + return 0; + +out_free_irq: + free_irq(mb->irq, smi); + mb->irq = 0; + +out_remove_irqdomain: + for (i = 0; i < smi->num_ports; i++) { + virq = irq_find_mapping(smi->irqdomain, i); + irq_dispose_mapping(virq); + } + + irq_domain_remove(smi->irqdomain); + smi->irqdomain = NULL; + +out_put_node: + of_node_put(intc); + + return ret; +} + +static void rtl8365mb_irq_teardown(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + int virq; + int i; + + if (mb->irq) { + free_irq(mb->irq, smi); + mb->irq = 0; + } + + if (smi->irqdomain) { + for (i = 0; i < smi->num_ports; i++) { + virq = irq_find_mapping(smi->irqdomain, i); + irq_dispose_mapping(virq); + } + + irq_domain_remove(smi->irqdomain); + smi->irqdomain = NULL; + } +} + +static int rtl8365mb_cpu_config(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb_cpu *cpu = &mb->cpu; + u32 val; + int ret; + + ret = regmap_update_bits(smi->map, RTL8365MB_CPU_PORT_MASK_REG, + RTL8365MB_CPU_PORT_MASK_MASK, + FIELD_PREP(RTL8365MB_CPU_PORT_MASK_MASK, + cpu->mask)); + if (ret) + return ret; + + val = FIELD_PREP(RTL8365MB_CPU_CTRL_EN_MASK, cpu->enable ? 1 : 0) | + FIELD_PREP(RTL8365MB_CPU_CTRL_INSERTMODE_MASK, cpu->insert) | + FIELD_PREP(RTL8365MB_CPU_CTRL_TAG_POSITION_MASK, cpu->position) | + FIELD_PREP(RTL8365MB_CPU_CTRL_RXBYTECOUNT_MASK, cpu->rx_length) | + FIELD_PREP(RTL8365MB_CPU_CTRL_TAG_FORMAT_MASK, cpu->format) | + FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_MASK, cpu->trap_port) | + FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_EXT_MASK, + cpu->trap_port >> 3); + ret = regmap_write(smi->map, RTL8365MB_CPU_CTRL_REG, val); + if (ret) + return ret; + + return 0; +} + +static int rtl8365mb_switch_init(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + int ret; + int i; + + /* Do any chip-specific init jam before getting to the common stuff */ + if (mb->jam_table) { + for (i = 0; i < mb->jam_size; i++) { + ret = regmap_write(smi->map, mb->jam_table[i].reg, + mb->jam_table[i].val); + if (ret) + return ret; + } + } + + /* Common init jam */ + for (i = 0; i < ARRAY_SIZE(rtl8365mb_init_jam_common); i++) { + ret = regmap_write(smi->map, rtl8365mb_init_jam_common[i].reg, + rtl8365mb_init_jam_common[i].val); + if (ret) + return ret; + } + + return 0; +} + +static int rtl8365mb_reset_chip(struct realtek_smi *smi) +{ + u32 val; + + realtek_smi_write_reg_noack(smi, RTL8365MB_CHIP_RESET_REG, + FIELD_PREP(RTL8365MB_CHIP_RESET_HW_MASK, + 1)); + + /* Realtek documentation says the chip needs 1 second to reset. Sleep + * for 100 ms before accessing any registers to prevent ACK timeouts. + */ + msleep(100); + return regmap_read_poll_timeout(smi->map, RTL8365MB_CHIP_RESET_REG, val, + !(val & RTL8365MB_CHIP_RESET_HW_MASK), + 20000, 1e6); +} + +static int rtl8365mb_setup(struct dsa_switch *ds) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8365mb *mb; + int ret; + int i; + + mb = smi->chip_data; + + ret = rtl8365mb_reset_chip(smi); + if (ret) { + dev_err(smi->dev, "failed to reset chip: %d\n", ret); + goto out_error; + } + + /* Configure switch to vendor-defined initial state */ + ret = rtl8365mb_switch_init(smi); + if (ret) { + dev_err(smi->dev, "failed to initialize switch: %d\n", ret); + goto out_error; + } + + /* Set up cascading IRQs */ + ret = rtl8365mb_irq_setup(smi); + if (ret == -EPROBE_DEFER) + return ret; + else if (ret) + dev_info(smi->dev, "no interrupt support\n"); + + /* Configure CPU tagging */ + ret = rtl8365mb_cpu_config(smi); + if (ret) + goto out_teardown_irq; + + /* Configure ports */ + for (i = 0; i < smi->num_ports; i++) { + struct rtl8365mb_port *p = &mb->ports[i]; + + if (dsa_is_unused_port(smi->ds, i)) + continue; + + /* Set up per-port private data */ + p->smi = smi; + p->index = i; + + /* Forward only to the CPU */ + ret = rtl8365mb_port_set_isolation(smi, i, BIT(smi->cpu_port)); + if (ret) + goto out_teardown_irq; + + /* Disable learning */ + ret = rtl8365mb_port_set_learning(smi, i, false); + if (ret) + goto out_teardown_irq; + + /* Set the initial STP state of all ports to DISABLED, otherwise + * ports will still forward frames to the CPU despite being + * administratively down by default. + */ + rtl8365mb_port_stp_state_set(smi->ds, i, BR_STATE_DISABLED); + } + + /* Set maximum packet length to 1536 bytes */ + ret = regmap_update_bits(smi->map, RTL8365MB_CFG0_MAX_LEN_REG, + RTL8365MB_CFG0_MAX_LEN_MASK, + FIELD_PREP(RTL8365MB_CFG0_MAX_LEN_MASK, 1536)); + if (ret) + goto out_teardown_irq; + + ret = realtek_smi_setup_mdio(smi); + if (ret) { + dev_err(smi->dev, "could not set up MDIO bus\n"); + goto out_teardown_irq; + } + + /* Start statistics counter polling */ + rtl8365mb_stats_setup(smi); + + return 0; + +out_teardown_irq: + rtl8365mb_irq_teardown(smi); + +out_error: + return ret; +} + +static void rtl8365mb_teardown(struct dsa_switch *ds) +{ + struct realtek_smi *smi = ds->priv; + + rtl8365mb_stats_teardown(smi); + rtl8365mb_irq_teardown(smi); +} + +static int rtl8365mb_get_chip_id_and_ver(struct regmap *map, u32 *id, u32 *ver) +{ + int ret; + + /* For some reason we have to write a magic value to an arbitrary + * register whenever accessing the chip ID/version registers. + */ + ret = regmap_write(map, RTL8365MB_MAGIC_REG, RTL8365MB_MAGIC_VALUE); + if (ret) + return ret; + + ret = regmap_read(map, RTL8365MB_CHIP_ID_REG, id); + if (ret) + return ret; + + ret = regmap_read(map, RTL8365MB_CHIP_VER_REG, ver); + if (ret) + return ret; + + /* Reset magic register */ + ret = regmap_write(map, RTL8365MB_MAGIC_REG, 0); + if (ret) + return ret; + + return 0; +} + +static int rtl8365mb_detect(struct realtek_smi *smi) +{ + struct rtl8365mb *mb = smi->chip_data; + u32 chip_id; + u32 chip_ver; + int ret; + + ret = rtl8365mb_get_chip_id_and_ver(smi->map, &chip_id, &chip_ver); + if (ret) { + dev_err(smi->dev, "failed to read chip id and version: %d\n", + ret); + return ret; + } + + switch (chip_id) { + case RTL8365MB_CHIP_ID_8365MB_VC: + dev_info(smi->dev, + "found an RTL8365MB-VC switch (ver=0x%04x)\n", + chip_ver); + + smi->cpu_port = RTL8365MB_CPU_PORT_NUM_8365MB_VC; + smi->num_ports = smi->cpu_port + 1; + + mb->smi = smi; + mb->chip_id = chip_id; + mb->chip_ver = chip_ver; + mb->port_mask = BIT(smi->num_ports) - 1; + mb->learn_limit_max = RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC; + mb->jam_table = rtl8365mb_init_jam_8365mb_vc; + mb->jam_size = ARRAY_SIZE(rtl8365mb_init_jam_8365mb_vc); + + mb->cpu.enable = 1; + mb->cpu.mask = BIT(smi->cpu_port); + mb->cpu.trap_port = smi->cpu_port; + mb->cpu.insert = RTL8365MB_CPU_INSERT_TO_ALL; + mb->cpu.position = RTL8365MB_CPU_POS_AFTER_SA; + mb->cpu.rx_length = RTL8365MB_CPU_RXLEN_64BYTES; + mb->cpu.format = RTL8365MB_CPU_FORMAT_8BYTES; + + break; + default: + dev_err(smi->dev, + "found an unknown Realtek switch (id=0x%04x, ver=0x%04x)\n", + chip_id, chip_ver); + return -ENODEV; + } + + return 0; +} + +static const struct dsa_switch_ops rtl8365mb_switch_ops = { + .get_tag_protocol = rtl8365mb_get_tag_protocol, + .setup = rtl8365mb_setup, + .teardown = rtl8365mb_teardown, + .phylink_validate = rtl8365mb_phylink_validate, + .phylink_mac_config = rtl8365mb_phylink_mac_config, + .phylink_mac_link_down = rtl8365mb_phylink_mac_link_down, + .phylink_mac_link_up = rtl8365mb_phylink_mac_link_up, + .port_stp_state_set = rtl8365mb_port_stp_state_set, + .get_strings = rtl8365mb_get_strings, + .get_ethtool_stats = rtl8365mb_get_ethtool_stats, + .get_sset_count = rtl8365mb_get_sset_count, + .get_eth_phy_stats = rtl8365mb_get_phy_stats, + .get_eth_mac_stats = rtl8365mb_get_mac_stats, + .get_eth_ctrl_stats = rtl8365mb_get_ctrl_stats, + .get_stats64 = rtl8365mb_get_stats64, +}; + +static const struct realtek_smi_ops rtl8365mb_smi_ops = { + .detect = rtl8365mb_detect, + .phy_read = rtl8365mb_phy_read, + .phy_write = rtl8365mb_phy_write, +}; + +const struct realtek_smi_variant rtl8365mb_variant = { + .ds_ops = &rtl8365mb_switch_ops, + .ops = &rtl8365mb_smi_ops, + .clk_delay = 10, + .cmd_read = 0xb9, + .cmd_write = 0xb8, + .chip_data_sz = sizeof(struct rtl8365mb), +}; +EXPORT_SYMBOL_GPL(rtl8365mb_variant); diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c index d2370cda4be0..03deacd83e61 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/rtl8366rb.c @@ -1345,7 +1345,7 @@ rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) default: dev_err(smi->dev, "unknown bridge state requested\n"); return; - }; + } /* Set the same status for the port on all the FIDs */ for (i = 0; i < RTL8366RB_NUM_FIDS; i++) { diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index 6f0ea2facea9..1d124b0f65e7 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -567,6 +567,7 @@ static int corkscrew_setup(struct net_device *dev, int ioaddr, { struct corkscrew_private *vp = netdev_priv(dev); unsigned int eeprom[0x40], checksum = 0; /* EEPROM contents */ + __be16 addr[ETH_ALEN / 2]; int i; int irq; @@ -619,7 +620,6 @@ static int corkscrew_setup(struct net_device *dev, int ioaddr, /* Read the station address from the EEPROM. */ EL3WINDOW(0); for (i = 0; i < 0x18; i++) { - __be16 *phys_addr = (__be16 *) dev->dev_addr; int timer; outw(EEPROM_Read + i, ioaddr + Wn0EepromCmd); /* Pause for at least 162 us. for the read to take place. */ @@ -631,8 +631,9 @@ static int corkscrew_setup(struct net_device *dev, int ioaddr, eeprom[i] = inw(ioaddr + Wn0EepromData); checksum ^= eeprom[i]; if (i < 3) - phys_addr[i] = htons(eeprom[i]); + addr[i] = htons(eeprom[i]); } + eth_hw_addr_set(dev, (u8 *)addr); checksum = (checksum ^ (checksum >> 8)) & 0xff; if (checksum != 0x00) pr_cont(" ***INVALID CHECKSUM %4.4x*** ", checksum); diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c index dd4d3c48b98d..dc3b7c960611 100644 --- a/drivers/net/ethernet/3com/3c574_cs.c +++ b/drivers/net/ethernet/3com/3c574_cs.c @@ -305,15 +305,13 @@ static int tc574_config(struct pcmcia_device *link) struct net_device *dev = link->priv; struct el3_private *lp = netdev_priv(dev); int ret, i, j; + __be16 addr[ETH_ALEN / 2]; unsigned int ioaddr; - __be16 *phys_addr; char *cardname; __u32 config; u8 *buf; size_t len; - phys_addr = (__be16 *)dev->dev_addr; - dev_dbg(&link->dev, "3c574_config()\n"); link->io_lines = 16; @@ -347,19 +345,20 @@ static int tc574_config(struct pcmcia_device *link) len = pcmcia_get_tuple(link, 0x88, &buf); if (buf && len >= 6) { for (i = 0; i < 3; i++) - phys_addr[i] = htons(le16_to_cpu(buf[i * 2])); + addr[i] = htons(le16_to_cpu(buf[i * 2])); kfree(buf); } else { kfree(buf); /* 0 < len < 6 */ EL3WINDOW(0); for (i = 0; i < 3; i++) - phys_addr[i] = htons(read_eeprom(ioaddr, i + 10)); - if (phys_addr[0] == htons(0x6060)) { + addr[i] = htons(read_eeprom(ioaddr, i + 10)); + if (addr[0] == htons(0x6060)) { pr_notice("IO port conflict at 0x%03lx-0x%03lx\n", dev->base_addr, dev->base_addr+15); goto failed; } } + eth_hw_addr_set(dev, (u8 *)addr); if (link->prod_id[1]) cardname = link->prod_id[1]; else diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c index 09816e84314d..4673bc1604e7 100644 --- a/drivers/net/ethernet/3com/3c589_cs.c +++ b/drivers/net/ethernet/3com/3c589_cs.c @@ -237,8 +237,8 @@ static void tc589_detach(struct pcmcia_device *link) static int tc589_config(struct pcmcia_device *link) { struct net_device *dev = link->priv; - __be16 *phys_addr; int ret, i, j, multi = 0, fifo; + __be16 addr[ETH_ALEN / 2]; unsigned int ioaddr; static const char * const ram_split[] = {"5:3", "3:1", "1:1", "3:5"}; u8 *buf; @@ -246,7 +246,6 @@ static int tc589_config(struct pcmcia_device *link) dev_dbg(&link->dev, "3c589_config\n"); - phys_addr = (__be16 *)dev->dev_addr; /* Is this a 3c562? */ if (link->manf_id != MANFID_3COM) dev_info(&link->dev, "hmmm, is this really a 3Com card??\n"); @@ -285,18 +284,19 @@ static int tc589_config(struct pcmcia_device *link) len = pcmcia_get_tuple(link, 0x88, &buf); if (buf && len >= 6) { for (i = 0; i < 3; i++) - phys_addr[i] = htons(le16_to_cpu(buf[i*2])); + addr[i] = htons(le16_to_cpu(buf[i*2])); kfree(buf); } else { kfree(buf); /* 0 < len < 6 */ for (i = 0; i < 3; i++) - phys_addr[i] = htons(read_eeprom(ioaddr, i)); - if (phys_addr[0] == htons(0x6060)) { + addr[i] = htons(read_eeprom(ioaddr, i)); + if (addr[0] == htons(0x6060)) { dev_err(&link->dev, "IO port conflict at 0x%03lx-0x%03lx\n", dev->base_addr, dev->base_addr+15); goto failed; } } + eth_hw_addr_set(dev, (u8 *)addr); /* The address and resource configuration register aren't loaded from * the EEPROM and *must* be set to 0 and IRQ3 for the PCMCIA version. diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 7b0ae9efc004..ccf07667aa5e 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -1091,6 +1091,7 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq, struct vortex_private *vp; int option; unsigned int eeprom[0x40], checksum = 0; /* EEPROM contents */ + __be16 addr[ETH_ALEN / 2]; int i, step; struct net_device *dev; static int printed_version; @@ -1284,7 +1285,8 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq, if ((checksum != 0x00) && !(vci->drv_flags & IS_TORNADO)) pr_cont(" ***INVALID CHECKSUM %4.4x*** ", checksum); for (i = 0; i < 3; i++) - ((__be16 *)dev->dev_addr)[i] = htons(eeprom[i + 10]); + addr[i] = htons(eeprom[i + 10]); + eth_hw_addr_set(dev, (u8 *)addr); if (print_info) pr_cont(" %pM", dev->dev_addr); /* Unfortunately an all zero eeprom passes the checksum and this diff --git a/drivers/net/ethernet/8390/apne.c b/drivers/net/ethernet/8390/apne.c index da1ae37a9d73..991ad953aa79 100644 --- a/drivers/net/ethernet/8390/apne.c +++ b/drivers/net/ethernet/8390/apne.c @@ -320,8 +320,7 @@ static int __init apne_probe1(struct net_device *dev, int ioaddr) i = request_irq(dev->irq, apne_interrupt, IRQF_SHARED, DRV_NAME, dev); if (i) return i; - for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = SA_prom[i]; + eth_hw_addr_set(dev, SA_prom); pr_cont(" %pM\n", dev->dev_addr); diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index b3e612b18abd..1f8acbba5b6b 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -748,11 +748,13 @@ static int ax_init_dev(struct net_device *dev) /* load the mac-address from the device */ if (ax->plat->flags & AXFLG_MAC_FROMDEV) { + u8 addr[ETH_ALEN]; + ei_outb(E8390_NODMA + E8390_PAGE1 + E8390_STOP, ei_local->mem + E8390_CMD); /* 0x61 */ for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = - ei_inb(ioaddr + EN1_PHYS_SHIFT(i)); + addr[i] = ei_inb(ioaddr + EN1_PHYS_SHIFT(i)); + eth_hw_addr_set(dev, addr); } if ((ax->plat->flags & AXFLG_MAC_FROMPLATFORM) && diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index 3c370e686ec3..3aef959fc25b 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -187,6 +187,7 @@ static int get_prom(struct pcmcia_device *link) { struct net_device *dev = link->priv; unsigned int ioaddr = dev->base_addr; + u8 addr[ETH_ALEN]; int i, j; /* This is based on drivers/net/ethernet/8390/ne.c */ @@ -220,9 +221,11 @@ static int get_prom(struct pcmcia_device *link) for (i = 0; i < 6; i += 2) { j = inw(ioaddr + AXNET_DATAPORT); - dev->dev_addr[i] = j & 0xff; - dev->dev_addr[i+1] = j >> 8; + addr[i] = j & 0xff; + addr[i+1] = j >> 8; } + eth_hw_addr_set(dev, addr); + return 1; } /* get_prom */ diff --git a/drivers/net/ethernet/8390/mcf8390.c b/drivers/net/ethernet/8390/mcf8390.c index 4ad8031ab669..e320cccba61a 100644 --- a/drivers/net/ethernet/8390/mcf8390.c +++ b/drivers/net/ethernet/8390/mcf8390.c @@ -374,8 +374,7 @@ static int mcf8390_init(struct net_device *dev) if (ret) return ret; - for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = SA_prom[i]; + eth_hw_addr_set(dev, SA_prom); netdev_dbg(dev, "Found ethernet address: %pM\n", dev->dev_addr); diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c index 9afc712f5948..0a9118b8be0c 100644 --- a/drivers/net/ethernet/8390/ne.c +++ b/drivers/net/ethernet/8390/ne.c @@ -500,9 +500,7 @@ static int __init ne_probe1(struct net_device *dev, unsigned long ioaddr) dev->base_addr = ioaddr; - for (i = 0; i < ETH_ALEN; i++) { - dev->dev_addr[i] = SA_prom[i]; - } + eth_hw_addr_set(dev, SA_prom); pr_cont("%pM\n", dev->dev_addr); diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c index 96ad72abd373..0f07fe03da98 100644 --- a/drivers/net/ethernet/8390/pcnet_cs.c +++ b/drivers/net/ethernet/8390/pcnet_cs.c @@ -278,6 +278,7 @@ static struct hw_info *get_hwinfo(struct pcmcia_device *link) { struct net_device *dev = link->priv; u_char __iomem *base, *virt; + u8 addr[ETH_ALEN]; int i, j; /* Allocate a small memory window */ @@ -302,7 +303,8 @@ static struct hw_info *get_hwinfo(struct pcmcia_device *link) (readb(base+2) == hw_info[i].a1) && (readb(base+4) == hw_info[i].a2)) { for (j = 0; j < 6; j++) - dev->dev_addr[j] = readb(base + (j<<1)); + addr[j] = readb(base + (j<<1)); + eth_hw_addr_set(dev, addr); break; } } @@ -324,6 +326,7 @@ static struct hw_info *get_prom(struct pcmcia_device *link) { struct net_device *dev = link->priv; unsigned int ioaddr = dev->base_addr; + u8 addr[ETH_ALEN]; u_char prom[32]; int i, j; @@ -362,7 +365,8 @@ static struct hw_info *get_prom(struct pcmcia_device *link) } if ((i < NR_INFO) || ((prom[28] == 0x57) && (prom[30] == 0x57))) { for (j = 0; j < 6; j++) - dev->dev_addr[j] = prom[j<<1]; + addr[j] = prom[j<<1]; + eth_hw_addr_set(dev, addr); return (i < NR_INFO) ? hw_info+i : &default_info; } return NULL; @@ -377,6 +381,7 @@ static struct hw_info *get_prom(struct pcmcia_device *link) static struct hw_info *get_dl10019(struct pcmcia_device *link) { struct net_device *dev = link->priv; + u8 addr[ETH_ALEN]; int i; u_char sum; @@ -385,7 +390,8 @@ static struct hw_info *get_dl10019(struct pcmcia_device *link) if (sum != 0xff) return NULL; for (i = 0; i < 6; i++) - dev->dev_addr[i] = inb_p(dev->base_addr + 0x14 + i); + addr[i] = inb_p(dev->base_addr + 0x14 + i); + eth_hw_addr_set(dev, addr); i = inb(dev->base_addr + 0x1f); return ((i == 0x91)||(i == 0x99)) ? &dl10022_info : &dl10019_info; } @@ -400,6 +406,7 @@ static struct hw_info *get_ax88190(struct pcmcia_device *link) { struct net_device *dev = link->priv; unsigned int ioaddr = dev->base_addr; + u8 addr[ETH_ALEN]; int i, j; /* Not much of a test, but the alternatives are messy */ @@ -413,9 +420,10 @@ static struct hw_info *get_ax88190(struct pcmcia_device *link) for (i = 0; i < 6; i += 2) { j = inw(ioaddr + PCNET_DATAPORT); - dev->dev_addr[i] = j & 0xff; - dev->dev_addr[i+1] = j >> 8; + addr[i] = j & 0xff; + addr[i+1] = j >> 8; } + eth_hw_addr_set(dev, addr); return NULL; } @@ -430,6 +438,7 @@ static struct hw_info *get_ax88190(struct pcmcia_device *link) static struct hw_info *get_hwired(struct pcmcia_device *link) { struct net_device *dev = link->priv; + u8 addr[ETH_ALEN]; int i; for (i = 0; i < 6; i++) @@ -438,7 +447,8 @@ static struct hw_info *get_hwired(struct pcmcia_device *link) return NULL; for (i = 0; i < 6; i++) - dev->dev_addr[i] = hw_addr[i]; + addr[i] = hw_addr[i]; + eth_hw_addr_set(dev, addr); return &default_info; } /* get_hwired */ diff --git a/drivers/net/ethernet/8390/stnic.c b/drivers/net/ethernet/8390/stnic.c index fbbd7f22c142..bd89ca8a92df 100644 --- a/drivers/net/ethernet/8390/stnic.c +++ b/drivers/net/ethernet/8390/stnic.c @@ -104,8 +104,8 @@ STNIC_WRITE (int reg, byte val) static int __init stnic_probe(void) { struct net_device *dev; - int i, err; struct ei_device *ei_local; + int err; /* If we are not running on a SolutionEngine, give up now */ if (! MACH_SE) @@ -119,8 +119,7 @@ static int __init stnic_probe(void) #ifdef CONFIG_SH_STANDARD_BIOS sh_bios_get_node_addr (stnic_eadr); #endif - for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = stnic_eadr[i]; + eth_hw_addr_set(dev, stnic_eadr); /* Set the base address to point to the NIC, not the "real" base! */ dev->base_addr = 0x1000; diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c index 35a500a21521..e8b4fe813a08 100644 --- a/drivers/net/ethernet/8390/zorro8390.c +++ b/drivers/net/ethernet/8390/zorro8390.c @@ -364,8 +364,7 @@ static int zorro8390_init(struct net_device *dev, unsigned long board, if (i) return i; - for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = SA_prom[i]; + eth_hw_addr_set(dev, SA_prom); pr_debug("Found ethernet address: %pM\n", dev->dev_addr); diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index d796684ec9ca..412ae3e43ffb 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -100,6 +100,7 @@ config JME config KORINA tristate "Korina (IDT RC32434) Ethernet support" depends on MIKROTIK_RB532 || COMPILE_TEST + select CRC32 select MII help If you have a Mikrotik RouterBoard 500 or IDT RC32434 diff --git a/drivers/net/ethernet/actions/owl-emac.c b/drivers/net/ethernet/actions/owl-emac.c index 2c25ff3623cd..1cfdd01b4c2e 100644 --- a/drivers/net/ethernet/actions/owl-emac.c +++ b/drivers/net/ethernet/actions/owl-emac.c @@ -342,7 +342,7 @@ static u32 owl_emac_dma_cmd_stop(struct owl_emac_priv *priv) static void owl_emac_set_hw_mac_addr(struct net_device *netdev) { struct owl_emac_priv *priv = netdev_priv(netdev); - u8 *mac_addr = netdev->dev_addr; + const u8 *mac_addr = netdev->dev_addr; u32 addr_high, addr_low; addr_high = mac_addr[0] << 8 | mac_addr[1]; @@ -1385,7 +1385,7 @@ static void owl_emac_get_mac_addr(struct net_device *netdev) struct device *dev = netdev->dev.parent; int ret; - ret = eth_platform_get_mac_address(dev, netdev->dev_addr); + ret = platform_get_ethdev_address(dev, netdev); if (!ret && is_valid_ether_addr(netdev->dev_addr)) return; diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index e0f6cc910bd2..c6982f7caf9b 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -641,6 +641,7 @@ static int starfire_init_one(struct pci_dev *pdev, struct netdev_private *np; int i, irq, chip_idx = ent->driver_data; struct net_device *dev; + u8 addr[ETH_ALEN]; long ioaddr; void __iomem *base; int drv_flags, io_size; @@ -696,7 +697,8 @@ static int starfire_init_one(struct pci_dev *pdev, /* Serial EEPROM reads are hidden by the hardware. */ for (i = 0; i < 6; i++) - dev->dev_addr[i] = readb(base + EEPROMCtrl + 20 - i); + addr[i] = readb(base + EEPROMCtrl + 20 - i); + eth_hw_addr_set(dev, addr); #if ! defined(final_version) /* Dump the EEPROM contents during development. */ if (debug > 4) @@ -955,7 +957,7 @@ static int netdev_open(struct net_device *dev) writew(0, ioaddr + PerfFilterTable + 4); writew(0, ioaddr + PerfFilterTable + 8); for (i = 1; i < 16; i++) { - __be16 *eaddrs = (__be16 *)dev->dev_addr; + const __be16 *eaddrs = (const __be16 *)dev->dev_addr; void __iomem *setup_frm = ioaddr + PerfFilterTable + i * 16; writew(be16_to_cpu(eaddrs[2]), setup_frm); setup_frm += 4; writew(be16_to_cpu(eaddrs[1]), setup_frm); setup_frm += 4; @@ -1787,14 +1789,14 @@ static void set_rx_mode(struct net_device *dev) } else if (netdev_mc_count(dev) <= 14) { /* Use the 16 element perfect filter, skip first two entries. */ void __iomem *filter_addr = ioaddr + PerfFilterTable + 2 * 16; - __be16 *eaddrs; + const __be16 *eaddrs; netdev_for_each_mc_addr(ha, dev) { eaddrs = (__be16 *) ha->addr; writew(be16_to_cpu(eaddrs[2]), filter_addr); filter_addr += 4; writew(be16_to_cpu(eaddrs[1]), filter_addr); filter_addr += 4; writew(be16_to_cpu(eaddrs[0]), filter_addr); filter_addr += 8; } - eaddrs = (__be16 *)dev->dev_addr; + eaddrs = (const __be16 *)dev->dev_addr; i = netdev_mc_count(dev) + 2; while (i++ < 16) { writew(be16_to_cpu(eaddrs[0]), filter_addr); filter_addr += 4; @@ -1805,7 +1807,7 @@ static void set_rx_mode(struct net_device *dev) } else { /* Must use a multicast hash table. */ void __iomem *filter_addr; - __be16 *eaddrs; + const __be16 *eaddrs; __le16 mc_filter[32] __attribute__ ((aligned(sizeof(long)))); /* Multicast hash filter */ memset(mc_filter, 0, sizeof(mc_filter)); @@ -1819,7 +1821,7 @@ static void set_rx_mode(struct net_device *dev) } /* Clear the perfect filter list, skip first two entries. */ filter_addr = ioaddr + PerfFilterTable + 2 * 16; - eaddrs = (__be16 *)dev->dev_addr; + eaddrs = (const __be16 *)dev->dev_addr; for (i = 2; i < 16; i++) { writew(be16_to_cpu(eaddrs[0]), filter_addr); filter_addr += 4; writew(be16_to_cpu(eaddrs[1]), filter_addr); filter_addr += 4; diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index cc34eaf0491f..447dc64a17e5 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -1346,6 +1346,7 @@ static int greth_of_probe(struct platform_device *ofdev) int i; int err; int tmp; + u8 addr[ETH_ALEN]; unsigned long timeout; dev = alloc_etherdev(sizeof(struct greth_private)); @@ -1449,8 +1450,6 @@ static int greth_of_probe(struct platform_device *ofdev) break; } if (i == 6) { - u8 addr[ETH_ALEN]; - err = of_get_mac_address(ofdev->dev.of_node, addr); if (!err) { for (i = 0; i < 6; i++) @@ -1464,7 +1463,8 @@ static int greth_of_probe(struct platform_device *ofdev) } for (i = 0; i < 6; i++) - dev->dev_addr[i] = macaddr[i]; + addr[i] = macaddr[i]; + eth_hw_addr_set(dev, addr); macaddr[5]++; diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c index 82f4f2608102..1fc9a1cd3ef8 100644 --- a/drivers/net/ethernet/alacritech/slicoss.c +++ b/drivers/net/ethernet/alacritech/slicoss.c @@ -1008,7 +1008,7 @@ static void slic_set_link_autoneg(struct slic_device *sdev) static void slic_set_mac_address(struct slic_device *sdev) { - u8 *addr = sdev->netdev->dev_addr; + const u8 *addr = sdev->netdev->dev_addr; u32 val; val = addr[5] | addr[4] << 8 | addr[3] << 16 | addr[2] << 24; diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index 7aaef593b031..732da15a3827 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -869,6 +869,7 @@ static int ace_init(struct net_device *dev) int board_idx, ecode = 0; short i; unsigned char cache_size; + u8 addr[ETH_ALEN]; ap = netdev_priv(dev); regs = ap->regs; @@ -988,12 +989,13 @@ static int ace_init(struct net_device *dev) writel(mac1, ®s->MacAddrHi); writel(mac2, ®s->MacAddrLo); - dev->dev_addr[0] = (mac1 >> 8) & 0xff; - dev->dev_addr[1] = mac1 & 0xff; - dev->dev_addr[2] = (mac2 >> 24) & 0xff; - dev->dev_addr[3] = (mac2 >> 16) & 0xff; - dev->dev_addr[4] = (mac2 >> 8) & 0xff; - dev->dev_addr[5] = mac2 & 0xff; + addr[0] = (mac1 >> 8) & 0xff; + addr[1] = mac1 & 0xff; + addr[2] = (mac2 >> 24) & 0xff; + addr[3] = (mac2 >> 16) & 0xff; + addr[4] = (mac2 >> 8) & 0xff; + addr[5] = mac2 & 0xff; + eth_hw_addr_set(dev, addr); printk("MAC: %pM\n", dev->dev_addr); @@ -2712,7 +2714,7 @@ static int ace_set_mac_addr(struct net_device *dev, void *p) struct ace_private *ap = netdev_priv(dev); struct ace_regs __iomem *regs = ap->regs; struct sockaddr *addr=p; - u8 *da; + const u8 *da; struct cmd cmd; if(netif_running(dev)) @@ -2720,7 +2722,7 @@ static int ace_set_mac_addr(struct net_device *dev, void *p) eth_hw_addr_set(dev, addr->sa_data); - da = (u8 *)dev->dev_addr; + da = (const u8 *)dev->dev_addr; writel(da[0] << 8 | da[1], ®s->MacAddrHi); writel((da[2] << 24) | (da[3] << 16) | (da[4] << 8) | da[5], diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 7b75b0cd7ac9..d75d95a97dd9 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -849,7 +849,7 @@ static int init_phy(struct net_device *dev) return 0; } -static void tse_update_mac_addr(struct altera_tse_private *priv, u8 *addr) +static void tse_update_mac_addr(struct altera_tse_private *priv, const u8 *addr) { u32 msb; u32 lsb; diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index 0b493467b042..9421afb950f7 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -1743,6 +1743,7 @@ static int amd8111e_probe_one(struct pci_dev *pdev, unsigned long reg_addr, reg_len; struct amd8111e_priv *lp; struct net_device *dev; + u8 addr[ETH_ALEN]; err = pci_enable_device(pdev); if (err) { @@ -1809,7 +1810,8 @@ static int amd8111e_probe_one(struct pci_dev *pdev, /* Initializing MAC address */ for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = readb(lp->mmio + PADR + i); + addr[i] = readb(lp->mmio + PADR + i); + eth_hw_addr_set(dev, addr); /* Setting user defined parametrs */ lp->ext_phy_option = speed_duplex[card_idx]; diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c index 2c07d15c8dfe..30ee5329bd7c 100644 --- a/drivers/net/ethernet/amd/nmclan_cs.c +++ b/drivers/net/ethernet/amd/nmclan_cs.c @@ -529,7 +529,8 @@ static void mace_write(mace_private *lp, unsigned int ioaddr, int reg, mace_init Resets the MACE chip. ---------------------------------------------------------------------------- */ -static int mace_init(mace_private *lp, unsigned int ioaddr, char *enet_addr) +static int mace_init(mace_private *lp, unsigned int ioaddr, + const char *enet_addr) { int i; int ct = 0; diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 820baa2604ac..f5c50ff377ff 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1595,6 +1595,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) struct net_device *dev; const struct pcnet32_access *a = NULL; u8 promaddr[ETH_ALEN]; + u8 addr[ETH_ALEN]; int ret = -ENODEV; /* reset the chip */ @@ -1760,9 +1761,10 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) unsigned int val; val = a->read_csr(ioaddr, i + 12) & 0x0ffff; /* There may be endianness issues here. */ - dev->dev_addr[2 * i] = val & 0x0ff; - dev->dev_addr[2 * i + 1] = (val >> 8) & 0x0ff; + addr[2 * i] = val & 0x0ff; + addr[2 * i + 1] = (val >> 8) & 0x0ff; } + eth_hw_addr_set(dev, addr); /* read PROM address and compare with CSR address */ for (i = 0; i < ETH_ALEN; i++) @@ -1780,8 +1782,11 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) } /* if the ethernet address is not valid, force to 00:00:00:00:00:00 */ - if (!is_valid_ether_addr(dev->dev_addr)) - eth_zero_addr(dev->dev_addr); + if (!is_valid_ether_addr(dev->dev_addr)) { + static const u8 zero_addr[ETH_ALEN] = {}; + + eth_hw_addr_set(dev, zero_addr); + } if (pcnet32_debug & NETIF_MSG_PROBE) { pr_cont(" %pM", dev->dev_addr); diff --git a/drivers/net/ethernet/amd/sun3lance.c b/drivers/net/ethernet/amd/sun3lance.c index 4a845bc071b2..007bd7787291 100644 --- a/drivers/net/ethernet/amd/sun3lance.c +++ b/drivers/net/ethernet/amd/sun3lance.c @@ -305,7 +305,6 @@ static int __init lance_probe( struct net_device *dev) unsigned long ioaddr; struct lance_private *lp; - int i; static int did_version; volatile unsigned short *ioaddr_probe; unsigned short tmp1, tmp2; @@ -373,8 +372,7 @@ static int __init lance_probe( struct net_device *dev) dev->irq); /* copy in the ethernet address from the prom */ - for(i = 0; i < 6 ; i++) - dev->dev_addr[i] = idprom->id_ethaddr[i]; + eth_hw_addr_set(dev, idprom->id_ethaddr); /* tell the card it's ether address, bytes swapped */ MEM->init.hwaddr[0] = dev->dev_addr[1]; diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c index ddece276ae23..22d609563af8 100644 --- a/drivers/net/ethernet/amd/sunlance.c +++ b/drivers/net/ethernet/amd/sunlance.c @@ -1301,7 +1301,6 @@ static int sparc_lance_probe_one(struct platform_device *op, struct device_node *dp = op->dev.of_node; struct lance_private *lp; struct net_device *dev; - int i; dev = alloc_etherdev(sizeof(struct lance_private) + 8); if (!dev) @@ -1315,8 +1314,7 @@ static int sparc_lance_probe_one(struct platform_device *op, * will copy the address in the device structure to the lance * initialization block. */ - for (i = 0; i < 6; i++) - dev->dev_addr[i] = idprom->id_ethaddr[i]; + eth_hw_addr_set(dev, idprom->id_ethaddr); /* Get the IO region */ lp->lregs = of_ioremap(&op->resource[0], 0, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index d5fd49dd25f3..3936543a74d8 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1080,7 +1080,7 @@ static int xgbe_add_mac_addresses(struct xgbe_prv_data *pdata) return 0; } -static int xgbe_set_mac_address(struct xgbe_prv_data *pdata, u8 *addr) +static int xgbe_set_mac_address(struct xgbe_prv_data *pdata, const u8 *addr) { unsigned int mac_addr_hi, mac_addr_lo; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index b5bf5af8db5f..30d24d19f40d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1912,10 +1912,8 @@ static int xgbe_close(struct net_device *netdev) clk_disable_unprepare(pdata->ptpclk); clk_disable_unprepare(pdata->sysclk); - flush_workqueue(pdata->an_workqueue); destroy_workqueue(pdata->an_workqueue); - flush_workqueue(pdata->dev_workqueue); destroy_workqueue(pdata->dev_workqueue); set_bit(XGBE_DOWN, &pdata->dev_state); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 3305979a9f7c..607a2c90513b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -729,7 +729,7 @@ struct xgbe_ext_stats { struct xgbe_hw_if { int (*tx_complete)(struct xgbe_ring_desc *); - int (*set_mac_address)(struct xgbe_prv_data *, u8 *addr); + int (*set_mac_address)(struct xgbe_prv_data *, const u8 *addr); int (*config_rx_mode)(struct xgbe_prv_data *); int (*enable_rx_csum)(struct xgbe_prv_data *); diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.c b/drivers/net/ethernet/apm/xgene-v2/mac.c index 2da979e4fad1..6423e22e05b2 100644 --- a/drivers/net/ethernet/apm/xgene-v2/mac.c +++ b/drivers/net/ethernet/apm/xgene-v2/mac.c @@ -65,7 +65,7 @@ void xge_mac_set_speed(struct xge_pdata *pdata) void xge_mac_set_station_addr(struct xge_pdata *pdata) { - u8 *dev_addr = pdata->ndev->dev_addr; + const u8 *dev_addr = pdata->ndev->dev_addr; u32 addr0, addr1; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 5f657879134e..e641dbbea1e2 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -378,8 +378,8 @@ u32 xgene_enet_rd_stat(struct xgene_enet_pdata *pdata, u32 rd_addr) static void xgene_gmac_set_mac_addr(struct xgene_enet_pdata *pdata) { + const u8 *dev_addr = pdata->ndev->dev_addr; u32 addr0, addr1; - u8 *dev_addr = pdata->ndev->dev_addr; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c index f482ced2cadd..72b5e8eb0ec7 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c @@ -165,8 +165,8 @@ static void xgene_sgmac_reset(struct xgene_enet_pdata *p) static void xgene_sgmac_set_mac_addr(struct xgene_enet_pdata *p) { + const u8 *dev_addr = p->ndev->dev_addr; u32 addr0, addr1; - u8 *dev_addr = p->ndev->dev_addr; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c index 304b5d43f236..86607b79c09f 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c @@ -207,8 +207,8 @@ static void xgene_pcs_reset(struct xgene_enet_pdata *pdata) static void xgene_xgmac_set_mac_addr(struct xgene_enet_pdata *pdata) { + const u8 *dev_addr = pdata->ndev->dev_addr; u32 addr0, addr1; - u8 *dev_addr = pdata->ndev->dev_addr; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index a989d2df59ad..9a650d1c1bdd 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -308,7 +308,7 @@ bmac_init_registers(struct net_device *dev) { struct bmac_data *bp = netdev_priv(dev); volatile unsigned short regValue; - unsigned short *pWord16; + const unsigned short *pWord16; int i; /* XXDEBUG(("bmac: enter init_registers\n")); */ @@ -371,7 +371,7 @@ bmac_init_registers(struct net_device *dev) bmwrite(dev, BHASH1, bp->hash_table_mask[2]); /* bits 47 - 32 */ bmwrite(dev, BHASH0, bp->hash_table_mask[3]); /* bits 63 - 48 */ - pWord16 = (unsigned short *)dev->dev_addr; + pWord16 = (const unsigned short *)dev->dev_addr; bmwrite(dev, MADD0, *pWord16++); bmwrite(dev, MADD1, *pWord16++); bmwrite(dev, MADD2, *pWord16); @@ -521,19 +521,16 @@ static int bmac_resume(struct macio_dev *mdev) static int bmac_set_address(struct net_device *dev, void *addr) { struct bmac_data *bp = netdev_priv(dev); - unsigned char *p = addr; - unsigned short *pWord16; + const unsigned short *pWord16; unsigned long flags; - int i; XXDEBUG(("bmac: enter set_address\n")); spin_lock_irqsave(&bp->lock, flags); - for (i = 0; i < 6; ++i) { - dev->dev_addr[i] = p[i]; - } + eth_hw_addr_set(dev, addr); + /* load up the hardware address */ - pWord16 = (unsigned short *)dev->dev_addr; + pWord16 = (const unsigned short *)dev->dev_addr; bmwrite(dev, MADD0, *pWord16++); bmwrite(dev, MADD1, *pWord16++); bmwrite(dev, MADD2, *pWord16); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index bed481816ea3..062a300a566a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -217,7 +217,7 @@ struct aq_hw_ops { int (*hw_ring_tx_head_update)(struct aq_hw_s *self, struct aq_ring_s *aq_ring); - int (*hw_set_mac_address)(struct aq_hw_s *self, u8 *mac_addr); + int (*hw_set_mac_address)(struct aq_hw_s *self, const u8 *mac_addr); int (*hw_soft_reset)(struct aq_hw_s *self); @@ -226,7 +226,7 @@ struct aq_hw_ops { int (*hw_reset)(struct aq_hw_s *self); - int (*hw_init)(struct aq_hw_s *self, u8 *mac_addr); + int (*hw_init)(struct aq_hw_s *self, const u8 *mac_addr); int (*hw_start)(struct aq_hw_s *self); @@ -373,7 +373,7 @@ struct aq_fw_ops { int (*set_phyloopback)(struct aq_hw_s *self, u32 mode, bool enable); int (*set_power)(struct aq_hw_s *self, unsigned int power_state, - u8 *mac); + const u8 *mac); int (*send_fw_request)(struct aq_hw_s *self, const struct hw_fw_request_iface *fw_req, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c index 4a6dfac857ca..02058fe79f52 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c @@ -35,7 +35,7 @@ static int aq_apply_macsec_cfg(struct aq_nic_s *nic); static int aq_apply_secy_cfg(struct aq_nic_s *nic, const struct macsec_secy *secy); -static void aq_ether_addr_to_mac(u32 mac[2], unsigned char *emac) +static void aq_ether_addr_to_mac(u32 mac[2], const unsigned char *emac) { u32 tmp[2] = { 0 }; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 694aa70bcafe..1acf544afeb4 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -300,6 +300,7 @@ static bool aq_nic_is_valid_ether_addr(const u8 *addr) int aq_nic_ndev_register(struct aq_nic_s *self) { + u8 addr[ETH_ALEN]; int err = 0; if (!self->ndev) { @@ -316,12 +317,13 @@ int aq_nic_ndev_register(struct aq_nic_s *self) #endif mutex_lock(&self->fwreq_mutex); - err = self->aq_fw_ops->get_mac_permanent(self->aq_hw, - self->ndev->dev_addr); + err = self->aq_fw_ops->get_mac_permanent(self->aq_hw, addr); mutex_unlock(&self->fwreq_mutex); if (err) goto err_exit; + eth_hw_addr_set(self->ndev, addr); + if (!is_valid_ether_addr(self->ndev->dev_addr) || !aq_nic_is_valid_ether_addr(self->ndev->dev_addr)) { netdev_warn(self->ndev, "MAC is invalid, will use random."); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index 611875ef2cd1..4625ccb79499 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -322,7 +322,7 @@ static int hw_atl_a0_hw_init_rx_path(struct aq_hw_s *self) return aq_hw_err_from_flags(self); } -static int hw_atl_a0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl_a0_hw_mac_addr_set(struct aq_hw_s *self, const u8 *mac_addr) { unsigned int h = 0U; unsigned int l = 0U; @@ -348,7 +348,7 @@ err_exit: return err; } -static int hw_atl_a0_hw_init(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl_a0_hw_init(struct aq_hw_s *self, const u8 *mac_addr) { static u32 aq_hw_atl_igcr_table_[4][2] = { [AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U }, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 9f1b15077e7d..d875ce3ec759 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -533,7 +533,7 @@ static int hw_atl_b0_hw_init_rx_path(struct aq_hw_s *self) return aq_hw_err_from_flags(self); } -int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr) +int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, const u8 *mac_addr) { unsigned int h = 0U; unsigned int l = 0U; @@ -558,7 +558,7 @@ err_exit: return err; } -static int hw_atl_b0_hw_init(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl_b0_hw_init(struct aq_hw_s *self, const u8 *mac_addr) { static u32 aq_hw_atl_igcr_table_[4][2] = { [AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U }, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h index d8db972113ec..5298846dd9f7 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h @@ -58,7 +58,7 @@ int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self, struct aq_ring_s *ring); void hw_atl_b0_hw_init_rx_rss_ctrl1(struct aq_hw_s *self); -int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr); +int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, const u8 *mac_addr); int hw_atl_b0_set_fc(struct aq_hw_s *self, u32 fc, u32 tc); int hw_atl_b0_set_loopback(struct aq_hw_s *self, u32 mode, bool enable); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index 404cbf60d3f2..fc0e66006644 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -944,7 +944,7 @@ u32 hw_atl_utils_get_fw_version(struct aq_hw_s *self) } static int aq_fw1x_set_wake_magic(struct aq_hw_s *self, bool wol_enabled, - u8 *mac) + const u8 *mac) { struct hw_atl_utils_fw_rpc *prpc = NULL; unsigned int rpc_size = 0U; @@ -987,7 +987,7 @@ err_exit: } static int aq_fw1x_set_power(struct aq_hw_s *self, unsigned int power_state, - u8 *mac) + const u8 *mac) { struct hw_atl_utils_fw_rpc *prpc = NULL; unsigned int rpc_size = 0U; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index ee0c22d04935..eac631c45c56 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -358,7 +358,7 @@ static int aq_fw2x_get_phy_temp(struct aq_hw_s *self, int *temp) return 0; } -static int aq_fw2x_set_wol(struct aq_hw_s *self, u8 *mac) +static int aq_fw2x_set_wol(struct aq_hw_s *self, const u8 *mac) { struct hw_atl_utils_fw_rpc *rpc = NULL; struct offload_info *info = NULL; @@ -404,7 +404,7 @@ err_exit: } static int aq_fw2x_set_power(struct aq_hw_s *self, unsigned int power_state, - u8 *mac) + const u8 *mac) { int err = 0; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c index 92f64048bf69..c98708bb044c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c @@ -516,7 +516,7 @@ static int hw_atl2_hw_init_rx_path(struct aq_hw_s *self) return aq_hw_err_from_flags(self); } -static int hw_atl2_hw_init(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl2_hw_init(struct aq_hw_s *self, const u8 *mac_addr) { static u32 aq_hw_atl2_igcr_table_[4][2] = { [AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U }, diff --git a/drivers/net/ethernet/arc/Kconfig b/drivers/net/ethernet/arc/Kconfig index 840a9ce7ba1c..0a67612af228 100644 --- a/drivers/net/ethernet/arc/Kconfig +++ b/drivers/net/ethernet/arc/Kconfig @@ -21,6 +21,7 @@ config ARC_EMAC_CORE depends on ARC || ARCH_ROCKCHIP || COMPILE_TEST select MII select PHYLIB + select CRC32 config ARC_EMAC tristate "ARC EMAC support" diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 1aaaf8a4e7c5..ada3a9f0c8c8 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1971,7 +1971,7 @@ static int ag71xx_probe(struct platform_device *pdev) err = of_get_ethdev_address(np, ndev); if (err) { netif_err(ag, probe, ndev, "invalid MAC address, using random address\n"); - eth_random_addr(ndev->dev_addr); + eth_hw_addr_random(ndev); } err = of_get_phy_mode(np, &ag->phy_if_mode); diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 55c9e6fcb471..969591bbc066 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -218,7 +218,8 @@ static inline void __b44_cam_read(struct b44 *bp, unsigned char *data, int index data[1] = (val >> 0) & 0xFF; } -static inline void __b44_cam_write(struct b44 *bp, unsigned char *data, int index) +static inline void __b44_cam_write(struct b44 *bp, + const unsigned char *data, int index) { u32 val; @@ -1507,7 +1508,8 @@ static void bwfilter_table(struct b44 *bp, u8 *pp, u32 bytes, u32 table_offset) } } -static int b44_magic_pattern(u8 *macaddr, u8 *ppattern, u8 *pmask, int offset) +static int b44_magic_pattern(const u8 *macaddr, u8 *ppattern, u8 *pmask, + int offset) { int magicsync = 6; int k, j, len = offset; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index b813745e8de3..40933bf5a710 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1818,7 +1818,7 @@ static inline void umac_reset(struct bcm_sysport_priv *priv) } static void umac_set_hw_addr(struct bcm_sysport_priv *priv, - unsigned char *addr) + const unsigned char *addr) { u32 mac0 = (addr[0] << 24) | (addr[1] << 16) | (addr[2] << 8) | addr[3]; diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index d2c7834850cc..7b525c65bacb 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -768,7 +768,7 @@ static void bgmac_umac_cmd_maskset(struct bgmac *bgmac, u32 mask, u32 set, udelay(2); } -static void bgmac_write_mac_address(struct bgmac *bgmac, u8 *addr) +static void bgmac_write_mac_address(struct bgmac *bgmac, const u8 *addr) { u32 tmp; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 248b81249cb0..babc955ba64e 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -2704,7 +2704,7 @@ bnx2_alloc_bad_rbuf(struct bnx2 *bp) } static void -bnx2_set_mac_addr(struct bnx2 *bp, u8 *mac_addr, u32 pos) +bnx2_set_mac_addr(struct bnx2 *bp, const u8 *mac_addr, u32 pos) { u32 val; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index e789430f407c..2b06d78baa08 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1994,7 +1994,7 @@ int bnx2x_idle_chk(struct bnx2x *bp); * operation has been successfully scheduled and a negative - if a requested * operations has failed. */ -int bnx2x_set_mac_one(struct bnx2x *bp, u8 *mac, +int bnx2x_set_mac_one(struct bnx2x *bp, const u8 *mac, struct bnx2x_vlan_mac_obj *obj, bool set, int mac_type, unsigned long *ramrod_flags); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index ef49e38ae027..aec666e97683 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -8417,7 +8417,7 @@ alloc_mem_err: * Init service functions */ -int bnx2x_set_mac_one(struct bnx2x *bp, u8 *mac, +int bnx2x_set_mac_one(struct bnx2x *bp, const u8 *mac, struct bnx2x_vlan_mac_obj *obj, bool set, int mac_type, unsigned long *ramrod_flags) { @@ -9146,7 +9146,7 @@ u32 bnx2x_send_unload_req(struct bnx2x *bp, int unload_mode) else if (bp->wol) { u32 emac_base = port ? GRCBASE_EMAC1 : GRCBASE_EMAC0; - u8 *mac_addr = bp->dev->dev_addr; + const u8 *mac_addr = bp->dev->dev_addr; struct pci_dev *pdev = bp->pdev; u32 val; u16 pmc; @@ -11823,9 +11823,10 @@ static void bnx2x_get_mac_hwinfo(struct bnx2x *bp) u32 val, val2; int func = BP_ABS_FUNC(bp); int port = BP_PORT(bp); + u8 addr[ETH_ALEN] = {}; /* Zero primary MAC configuration */ - eth_zero_addr(bp->dev->dev_addr); + eth_hw_addr_set(bp->dev, addr); if (BP_NOMCP(bp)) { BNX2X_ERROR("warning: random MAC workaround active\n"); @@ -11834,8 +11835,10 @@ static void bnx2x_get_mac_hwinfo(struct bnx2x *bp) val2 = MF_CFG_RD(bp, func_mf_config[func].mac_upper); val = MF_CFG_RD(bp, func_mf_config[func].mac_lower); if ((val2 != FUNC_MF_CFG_UPPERMAC_DEFAULT) && - (val != FUNC_MF_CFG_LOWERMAC_DEFAULT)) - bnx2x_set_mac_buf(bp->dev->dev_addr, val, val2); + (val != FUNC_MF_CFG_LOWERMAC_DEFAULT)) { + bnx2x_set_mac_buf(addr, val, val2); + eth_hw_addr_set(bp->dev, addr); + } if (CNIC_SUPPORT(bp)) bnx2x_get_cnic_mac_hwinfo(bp); @@ -11843,7 +11846,8 @@ static void bnx2x_get_mac_hwinfo(struct bnx2x *bp) /* in SF read MACs from port configuration */ val2 = SHMEM_RD(bp, dev_info.port_hw_config[port].mac_upper); val = SHMEM_RD(bp, dev_info.port_hw_config[port].mac_lower); - bnx2x_set_mac_buf(bp->dev->dev_addr, val, val2); + bnx2x_set_mac_buf(addr, val, val2); + eth_hw_addr_set(bp->dev, addr); if (CNIC_SUPPORT(bp)) bnx2x_get_cnic_mac_hwinfo(bp); @@ -12291,7 +12295,9 @@ static int bnx2x_init_bp(struct bnx2x *bp) if (rc) return rc; } else { - eth_zero_addr(bp->dev->dev_addr); + static const u8 zero_addr[ETH_ALEN] = {}; + + eth_hw_addr_set(bp->dev, zero_addr); } bnx2x_set_modes_bitmap(bp); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index 966d5722c5e2..8c2cf5519787 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -508,7 +508,8 @@ int bnx2x_vfpf_init(struct bnx2x *bp); void bnx2x_vfpf_close_vf(struct bnx2x *bp); int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp, bool is_leading); -int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr, u8 vf_qid, bool set); +int bnx2x_vfpf_config_mac(struct bnx2x *bp, const u8 *addr, u8 vf_qid, + bool set); int bnx2x_vfpf_config_rss(struct bnx2x *bp, struct bnx2x_config_rss_params *params); int bnx2x_vfpf_set_mcast(struct net_device *dev); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 7c96f943c6f3..c9129b9ba446 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -721,7 +721,7 @@ out: } /* request pf to add a mac for the vf */ -int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr, u8 vf_qid, bool set) +int bnx2x_vfpf_config_mac(struct bnx2x *bp, const u8 *addr, u8 vf_qid, bool set) { struct vfpf_set_q_filters_tlv *req = &bp->vf2pf_mbox->req.set_q_filters; struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f05f4271d4c1..66263aa0d96b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4869,7 +4869,7 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp, #endif static int bnxt_hwrm_set_vnic_filter(struct bnxt *bp, u16 vnic_id, u16 idx, - u8 *mac_addr) + const u8 *mac_addr) { struct hwrm_cfa_l2_filter_alloc_output *resp; struct hwrm_cfa_l2_filter_alloc_input *req; @@ -6366,7 +6366,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp) if (rx_rings != bp->rx_nr_rings) { netdev_warn(bp->dev, "Able to reserve only %d out of %d requested RX rings\n", rx_rings, bp->rx_nr_rings); - if ((bp->dev->priv_flags & IFF_RXFH_CONFIGURED) && + if (netif_is_rxfh_configured(bp->dev) && (bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) != bnxt_get_nr_rss_ctxs(bp, rx_rings) || bnxt_get_max_rss_ring(bp) >= rx_rings)) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 7260910e75fb..fbb56b1f70fd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -909,7 +909,7 @@ static int bnxt_set_channels(struct net_device *dev, if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) != bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) && - (dev->priv_flags & IFF_RXFH_CONFIGURED)) { + netif_is_rxfh_configured(dev)) { netdev_warn(dev, "RSS table size change required, RSS table entries must be default to proceed\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index d4ebc5d710ba..1d177fed44a6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -1151,7 +1151,7 @@ void bnxt_hwrm_exec_fwd_req(struct bnxt *bp) } } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) +int bnxt_approve_mac(struct bnxt *bp, const u8 *mac, bool strict) { struct hwrm_func_vf_cfg_input *req; int rc = 0; @@ -1246,7 +1246,7 @@ void bnxt_update_vf_mac(struct bnxt *bp) { } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) +int bnxt_approve_mac(struct bnxt *bp, const u8 *mac, bool strict) { return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h index 995535e4c11b..9a4bacba477b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -41,5 +41,5 @@ int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset); void bnxt_sriov_disable(struct bnxt *); void bnxt_hwrm_exec_fwd_req(struct bnxt *); void bnxt_update_vf_mac(struct bnxt *); -int bnxt_approve_mac(struct bnxt *, u8 *, bool); +int bnxt_approve_mac(struct bnxt *, const u8 *, bool); #endif diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 83c55e7b099f..5da9c00b43b1 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3266,7 +3266,7 @@ static void bcmgenet_umac_reset(struct bcmgenet_priv *priv) } static void bcmgenet_set_hw_addr(struct bcmgenet_priv *priv, - unsigned char *addr) + const unsigned char *addr) { bcmgenet_umac_writel(priv, get_unaligned_be32(&addr[0]), UMAC_MAC0); bcmgenet_umac_writel(priv, get_unaligned_be16(&addr[4]), UMAC_MAC1); @@ -3560,7 +3560,7 @@ static void bcmgenet_timeout(struct net_device *dev, unsigned int txqueue) #define MAX_MDF_FILTER 17 static inline void bcmgenet_set_mdf_addr(struct bcmgenet_priv *priv, - unsigned char *addr, + const unsigned char *addr, int *i) { bcmgenet_umac_writel(priv, addr[0] << 8 | addr[1], @@ -4085,8 +4085,12 @@ static int bcmgenet_probe(struct platform_device *pdev) eth_hw_addr_set(dev, pd->mac_address); else if (device_get_ethdev_address(&pdev->dev, dev)) - if (has_acpi_companion(&pdev->dev)) - bcmgenet_get_hw_addr(priv, dev->dev_addr); + if (has_acpi_companion(&pdev->dev)) { + u8 addr[ETH_ALEN]; + + bcmgenet_get_hw_addr(priv, addr); + eth_hw_addr_set(dev, addr); + } if (!is_valid_ether_addr(dev->dev_addr)) { dev_warn(&pdev->dev, "using random Ethernet MAC\n"); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 5a50ea75094f..e9518b98914b 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -3942,7 +3942,8 @@ static int tg3_load_tso_firmware(struct tg3 *tp) } /* tp->lock is held. */ -static void __tg3_set_one_mac_addr(struct tg3 *tp, u8 *mac_addr, int index) +static void __tg3_set_one_mac_addr(struct tg3 *tp, const u8 *mac_addr, + int index) { u32 addr_high, addr_low; @@ -10273,8 +10274,7 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy) if (tg3_asic_rev(tp) == ASIC_REV_5705 && tg3_chip_rev_id(tp) != CHIPREV_ID_5705_A0) { - if (tg3_flag(tp, TSO_CAPABLE) && - tg3_asic_rev(tp) == ASIC_REV_5705) { + if (tg3_flag(tp, TSO_CAPABLE)) { rdmac_mode |= RDMAC_MODE_FIFO_SIZE_128; } else if (!(tr32(TG3PCI_PCISTATE) & PCISTATE_BUS_SPEED_HIGH) && !tg3_flag(tp, IS_5788)) { @@ -16911,19 +16911,18 @@ static int tg3_get_invariants(struct tg3 *tp, const struct pci_device_id *ent) return err; } -static int tg3_get_device_address(struct tg3 *tp) +static int tg3_get_device_address(struct tg3 *tp, u8 *addr) { - struct net_device *dev = tp->dev; u32 hi, lo, mac_offset; int addr_ok = 0; int err; - if (!eth_platform_get_mac_address(&tp->pdev->dev, dev->dev_addr)) + if (!eth_platform_get_mac_address(&tp->pdev->dev, addr)) return 0; if (tg3_flag(tp, IS_SSB_CORE)) { - err = ssb_gige_get_macaddr(tp->pdev, &dev->dev_addr[0]); - if (!err && is_valid_ether_addr(&dev->dev_addr[0])) + err = ssb_gige_get_macaddr(tp->pdev, addr); + if (!err && is_valid_ether_addr(addr)) return 0; } @@ -16947,41 +16946,41 @@ static int tg3_get_device_address(struct tg3 *tp) /* First try to get it from MAC address mailbox. */ tg3_read_mem(tp, NIC_SRAM_MAC_ADDR_HIGH_MBOX, &hi); if ((hi >> 16) == 0x484b) { - dev->dev_addr[0] = (hi >> 8) & 0xff; - dev->dev_addr[1] = (hi >> 0) & 0xff; + addr[0] = (hi >> 8) & 0xff; + addr[1] = (hi >> 0) & 0xff; tg3_read_mem(tp, NIC_SRAM_MAC_ADDR_LOW_MBOX, &lo); - dev->dev_addr[2] = (lo >> 24) & 0xff; - dev->dev_addr[3] = (lo >> 16) & 0xff; - dev->dev_addr[4] = (lo >> 8) & 0xff; - dev->dev_addr[5] = (lo >> 0) & 0xff; + addr[2] = (lo >> 24) & 0xff; + addr[3] = (lo >> 16) & 0xff; + addr[4] = (lo >> 8) & 0xff; + addr[5] = (lo >> 0) & 0xff; /* Some old bootcode may report a 0 MAC address in SRAM */ - addr_ok = is_valid_ether_addr(&dev->dev_addr[0]); + addr_ok = is_valid_ether_addr(addr); } if (!addr_ok) { /* Next, try NVRAM. */ if (!tg3_flag(tp, NO_NVRAM) && !tg3_nvram_read_be32(tp, mac_offset + 0, &hi) && !tg3_nvram_read_be32(tp, mac_offset + 4, &lo)) { - memcpy(&dev->dev_addr[0], ((char *)&hi) + 2, 2); - memcpy(&dev->dev_addr[2], (char *)&lo, sizeof(lo)); + memcpy(&addr[0], ((char *)&hi) + 2, 2); + memcpy(&addr[2], (char *)&lo, sizeof(lo)); } /* Finally just fetch it out of the MAC control regs. */ else { hi = tr32(MAC_ADDR_0_HIGH); lo = tr32(MAC_ADDR_0_LOW); - dev->dev_addr[5] = lo & 0xff; - dev->dev_addr[4] = (lo >> 8) & 0xff; - dev->dev_addr[3] = (lo >> 16) & 0xff; - dev->dev_addr[2] = (lo >> 24) & 0xff; - dev->dev_addr[1] = hi & 0xff; - dev->dev_addr[0] = (hi >> 8) & 0xff; + addr[5] = lo & 0xff; + addr[4] = (lo >> 8) & 0xff; + addr[3] = (lo >> 16) & 0xff; + addr[2] = (lo >> 24) & 0xff; + addr[1] = hi & 0xff; + addr[0] = (hi >> 8) & 0xff; } } - if (!is_valid_ether_addr(&dev->dev_addr[0])) + if (!is_valid_ether_addr(addr)) return -EINVAL; return 0; } @@ -17557,6 +17556,7 @@ static int tg3_init_one(struct pci_dev *pdev, char str[40]; u64 dma_mask, persist_dma_mask; netdev_features_t features = 0; + u8 addr[ETH_ALEN] __aligned(2); err = pci_enable_device(pdev); if (err) { @@ -17779,12 +17779,13 @@ static int tg3_init_one(struct pci_dev *pdev, tp->rx_pending = 63; } - err = tg3_get_device_address(tp); + err = tg3_get_device_address(tp, addr); if (err) { dev_err(&pdev->dev, "Could not obtain valid ethernet address, aborting\n"); goto err_out_apeunmap; } + eth_hw_addr_set(dev, addr); intmbx = MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW; rcvmbx = MAILBOX_RCVRET_CON_IDX_0 + TG3_64BIT_REG_LOW; diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index b1947fd9a07c..bbdc829c3524 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -3515,7 +3515,6 @@ static void bnad_uninit(struct bnad *bnad) { if (bnad->work_q) { - flush_workqueue(bnad->work_q); destroy_workqueue(bnad->work_q); bnad->work_q = NULL; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 683f14665c2c..029dea2873e3 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -313,7 +313,7 @@ static void macb_get_hwaddr(struct macb *bp) addr[5] = (top >> 8) & 0xff; if (is_valid_ether_addr(addr)) { - memcpy(bp->dev->dev_addr, addr, sizeof(addr)); + eth_hw_addr_set(bp->dev, addr); return; } } diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c index dc51f36fdf2a..457cb7121000 100644 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@ -607,7 +607,7 @@ static inline void xgmac_mac_disable(void __iomem *ioaddr) writel(value, ioaddr + XGMAC_CONTROL); } -static void xgmac_set_mac_addr(void __iomem *ioaddr, unsigned char *addr, +static void xgmac_set_mac_addr(void __iomem *ioaddr, const unsigned char *addr, int num) { u32 data; @@ -1693,6 +1693,7 @@ static int xgmac_probe(struct platform_device *pdev) struct resource *res; struct net_device *ndev = NULL; struct xgmac_priv *priv = NULL; + u8 addr[ETH_ALEN]; u32 uid; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1785,7 +1786,8 @@ static int xgmac_probe(struct platform_device *pdev) ndev->max_mtu = XGMAC_MAX_MTU; /* Get the MAC address */ - xgmac_get_mac_addr(priv->base, ndev->dev_addr, 0); + xgmac_get_mac_addr(priv->base, addr, 0); + eth_hw_addr_set(ndev, addr); if (!is_valid_ether_addr(ndev->dev_addr)) netdev_warn(ndev, "MAC address %pM not valid", ndev->dev_addr); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index ec7928b54e4a..73cb03266549 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -490,7 +490,6 @@ void cleanup_rx_oom_poll_fn(struct net_device *netdev) wq = &lio->rxq_status_wq[q_no]; if (wq->wq) { cancel_delayed_work_sync(&wq->wk.work); - flush_workqueue(wq->wq); destroy_workqueue(wq->wq); wq->wq = NULL; } diff --git a/drivers/net/ethernet/chelsio/cxgb/gmac.h b/drivers/net/ethernet/chelsio/cxgb/gmac.h index dfa77491a910..5913eaf442b5 100644 --- a/drivers/net/ethernet/chelsio/cxgb/gmac.h +++ b/drivers/net/ethernet/chelsio/cxgb/gmac.h @@ -117,7 +117,7 @@ struct cmac_ops { const struct cmac_statistics *(*statistics_update)(struct cmac *, int); int (*macaddress_get)(struct cmac *, u8 mac_addr[6]); - int (*macaddress_set)(struct cmac *, u8 mac_addr[6]); + int (*macaddress_set)(struct cmac *, const u8 mac_addr[6]); }; typedef struct _cmac_instance cmac_instance; diff --git a/drivers/net/ethernet/chelsio/cxgb/pm3393.c b/drivers/net/ethernet/chelsio/cxgb/pm3393.c index c27908e66f5e..0bb37e4680c7 100644 --- a/drivers/net/ethernet/chelsio/cxgb/pm3393.c +++ b/drivers/net/ethernet/chelsio/cxgb/pm3393.c @@ -496,7 +496,7 @@ static int pm3393_macaddress_get(struct cmac *cmac, u8 mac_addr[6]) return 0; } -static int pm3393_macaddress_set(struct cmac *cmac, u8 ma[6]) +static int pm3393_macaddress_set(struct cmac *cmac, const u8 ma[6]) { u32 val, lo, mid, hi, enabled = cmac->instance->enabled; diff --git a/drivers/net/ethernet/chelsio/cxgb/vsc7326.c b/drivers/net/ethernet/chelsio/cxgb/vsc7326.c index a19284bdb80e..2ad3efb550c2 100644 --- a/drivers/net/ethernet/chelsio/cxgb/vsc7326.c +++ b/drivers/net/ethernet/chelsio/cxgb/vsc7326.c @@ -379,7 +379,7 @@ static int mac_intr_clear(struct cmac *mac) } /* Expect MAC address to be in network byte order. */ -static int mac_set_address(struct cmac* mac, u8 addr[6]) +static int mac_set_address(struct cmac* mac, const u8 addr[6]) { u32 val; int port = mac->instance->index; diff --git a/drivers/net/ethernet/chelsio/cxgb3/common.h b/drivers/net/ethernet/chelsio/cxgb3/common.h index b706f2fbe4f4..a309016f7f8c 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/common.h +++ b/drivers/net/ethernet/chelsio/cxgb3/common.h @@ -710,7 +710,7 @@ int t3_mac_enable(struct cmac *mac, int which); int t3_mac_disable(struct cmac *mac, int which); int t3_mac_set_mtu(struct cmac *mac, unsigned int mtu); int t3_mac_set_rx_mode(struct cmac *mac, struct net_device *dev); -int t3_mac_set_address(struct cmac *mac, unsigned int idx, u8 addr[6]); +int t3_mac_set_address(struct cmac *mac, unsigned int idx, const u8 addr[6]); int t3_mac_set_num_ucast(struct cmac *mac, int n); const struct mac_stats *t3_mac_update_stats(struct cmac *mac); int t3_mac_set_speed_duplex_fc(struct cmac *mac, int speed, int duplex, int fc); diff --git a/drivers/net/ethernet/chelsio/cxgb3/xgmac.c b/drivers/net/ethernet/chelsio/cxgb3/xgmac.c index 3af19a550372..1bdc6cad1e49 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/xgmac.c +++ b/drivers/net/ethernet/chelsio/cxgb3/xgmac.c @@ -240,7 +240,7 @@ static void set_addr_filter(struct cmac *mac, int idx, const u8 * addr) } /* Set one of the station's unicast MAC addresses. */ -int t3_mac_set_address(struct cmac *mac, unsigned int idx, u8 addr[6]) +int t3_mac_set_address(struct cmac *mac, unsigned int idx, const u8 addr[6]) { if (idx >= mac->nucast) return -EINVAL; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index bcad69c48074..4af5561cbfc5 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -870,7 +870,7 @@ static void do_abort_syn_rcv(struct sock *child, struct sock *parent) * created only after 3 way handshake is done. */ sock_orphan(child); - percpu_counter_inc((child)->sk_prot->orphan_count); + INC_ORPHAN_COUNT(child); chtls_release_resources(child); chtls_conn_done(child); } else { diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h index b1161bdeda4d..f61ca657601c 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.h @@ -95,7 +95,7 @@ struct deferred_skb_cb { #define WSCALE_OK(tp) ((tp)->rx_opt.wscale_ok) #define TSTAMP_OK(tp) ((tp)->rx_opt.tstamp_ok) #define SACK_OK(tp) ((tp)->rx_opt.sack_ok) -#define INC_ORPHAN_COUNT(sk) percpu_counter_inc((sk)->sk_prot->orphan_count) +#define INC_ORPHAN_COUNT(sk) this_cpu_inc(*(sk)->sk_prot->orphan_count) /* TLS SKB */ #define skb_ulp_tls_inline(skb) (ULP_SKB_CB(skb)->ulp.tls.ofld) diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index bd7920ab166f..4a97aa8e1387 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -1314,6 +1314,7 @@ cs89x0_probe1(struct net_device *dev, void __iomem *ioaddr, int modular) int tmp; unsigned rev_type = 0; int eeprom_buff[CHKSUM_LEN]; + u8 addr[ETH_ALEN]; int retval; /* Initialize the device structure. */ @@ -1387,9 +1388,10 @@ cs89x0_probe1(struct net_device *dev, void __iomem *ioaddr, int modular) for (i = 0; i < ETH_ALEN / 2; i++) { unsigned int Addr; Addr = readreg(dev, PP_IA + i * 2); - dev->dev_addr[i * 2] = Addr & 0xFF; - dev->dev_addr[i * 2 + 1] = Addr >> 8; + addr[i * 2] = Addr & 0xFF; + addr[i * 2 + 1] = Addr >> 8; } + eth_hw_addr_set(dev, addr); /* Load the Adapter Configuration. * Note: Barring any more specific information from some @@ -1464,9 +1466,10 @@ cs89x0_probe1(struct net_device *dev, void __iomem *ioaddr, int modular) /* eeprom_buff has 32-bit ints, so we can't just memcpy it */ /* store the initial memory base address */ for (i = 0; i < ETH_ALEN / 2; i++) { - dev->dev_addr[i * 2] = eeprom_buff[i]; - dev->dev_addr[i * 2 + 1] = eeprom_buff[i] >> 8; + addr[i * 2] = eeprom_buff[i]; + addr[i * 2 + 1] = eeprom_buff[i] >> 8; } + eth_hw_addr_set(dev, addr); cs89_dbg(1, debug, "%s: new adapter_cnf: 0x%x\n", dev->name, lp->adapter_cnf); } diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 66348cc3aaaf..aacf141986d5 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1098,6 +1098,7 @@ static int enic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) static int enic_set_vf_port(struct net_device *netdev, int vf, struct nlattr *port[]) { + static const u8 zero_addr[ETH_ALEN] = {}; struct enic *enic = netdev_priv(netdev); struct enic_port_profile prev_pp; struct enic_port_profile *pp; @@ -1162,7 +1163,7 @@ static int enic_set_vf_port(struct net_device *netdev, int vf, } else { memset(pp, 0, sizeof(*pp)); if (vf == PORT_SELF_VF) - eth_zero_addr(netdev->dev_addr); + eth_hw_addr_set(netdev, zero_addr); } } else { /* Set flag to indicate that the port assoc/disassoc @@ -1174,7 +1175,7 @@ static int enic_set_vf_port(struct net_device *netdev, int vf, if (pp->request == PORT_REQUEST_DISASSOCIATE) { eth_zero_addr(pp->mac_addr); if (vf == PORT_SELF_VF) - eth_zero_addr(netdev->dev_addr); + eth_hw_addr_set(netdev, zero_addr); } } diff --git a/drivers/net/ethernet/cisco/enic/enic_pp.c b/drivers/net/ethernet/cisco/enic/enic_pp.c index e6a83198c3dd..80f46dbd5117 100644 --- a/drivers/net/ethernet/cisco/enic/enic_pp.c +++ b/drivers/net/ethernet/cisco/enic/enic_pp.c @@ -73,9 +73,9 @@ static int enic_set_port_profile(struct enic *enic, int vf) struct vic_provinfo *vp; const u8 oui[3] = VIC_PROVINFO_CISCO_OUI; const __be16 os_type = htons(VIC_GENERIC_PROV_OS_TYPE_LINUX); + const u8 *client_mac; char uuid_str[38]; char client_mac_str[18]; - u8 *client_mac; int err; ENIC_PP_BY_INDEX(enic, vf, pp, &err); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 82d32caf1374..941f175fb911 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2473,7 +2473,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) port->mac_addr[0], port->mac_addr[1], port->mac_addr[2]); dev_info(dev, "using a random ethernet address\n"); - eth_random_addr(netdev->dev_addr); + eth_hw_addr_random(netdev); } gmac_write_mac_address(netdev); diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index e13dd53a8b3b..0985ab216566 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1425,6 +1425,7 @@ dm9000_probe(struct platform_device *pdev) enum of_gpio_flags flags; struct regulator *power; bool inv_mac_addr = false; + u8 addr[ETH_ALEN]; power = devm_regulator_get(dev, "vcc"); if (IS_ERR(power)) { @@ -1666,7 +1667,8 @@ dm9000_probe(struct platform_device *pdev) /* try reading the node address from the attached EEPROM */ for (i = 0; i < 6; i += 2) - dm9000_read_eeprom(db, i / 2, ndev->dev_addr+i); + dm9000_read_eeprom(db, i / 2, addr + i); + eth_hw_addr_set(ndev, addr); if (!is_valid_ether_addr(ndev->dev_addr) && pdata != NULL) { mac_src = "platform data"; @@ -1678,7 +1680,8 @@ dm9000_probe(struct platform_device *pdev) mac_src = "chip"; for (i = 0; i < 6; i++) - ndev->dev_addr[i] = ior(db, i+DM9000_PAR); + addr[i] = ior(db, i + DM9000_PAR); + eth_hw_addr_set(ndev, pdata->dev_addr); } if (!is_valid_ether_addr(ndev->dev_addr)) { diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index 117c26fa5909..d51b3d24a0c8 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -666,8 +666,8 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) struct de_private *de = netdev_priv(dev); u16 hash_table[32]; struct netdev_hw_addr *ha; + const u16 *eaddrs; int i; - u16 *eaddrs; memset(hash_table, 0, sizeof(hash_table)); __set_bit_le(255, hash_table); /* Broadcast entry */ @@ -685,7 +685,7 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) setup_frm = &de->setup_frame[13*6]; /* Fill the final entry with our physical address. */ - eaddrs = (u16 *)dev->dev_addr; + eaddrs = (const u16 *)dev->dev_addr; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[2]; *setup_frm++ = eaddrs[2]; @@ -695,7 +695,7 @@ static void build_setup_frame_perfect(u16 *setup_frm, struct net_device *dev) { struct de_private *de = netdev_priv(dev); struct netdev_hw_addr *ha; - u16 *eaddrs; + const u16 *eaddrs; /* We have <= 14 addresses so we can use the wonderful 16 address perfect filtering of the Tulip. */ @@ -710,7 +710,7 @@ static void build_setup_frame_perfect(u16 *setup_frm, struct net_device *dev) setup_frm = &de->setup_frame[15*6]; /* Fill the final entry with our physical address. */ - eaddrs = (u16 *)dev->dev_addr; + eaddrs = (const u16 *)dev->dev_addr; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[2]; *setup_frm++ = eaddrs[2]; @@ -1713,6 +1713,7 @@ static const struct ethtool_ops de_ethtool_ops = { static void de21040_get_mac_address(struct de_private *de) { + u8 addr[ETH_ALEN]; unsigned i; dw32 (ROMCmd, 0); /* Reset the pointer with a dummy write. */ @@ -1724,12 +1725,13 @@ static void de21040_get_mac_address(struct de_private *de) value = dr32(ROMCmd); rmb(); } while (value < 0 && --boguscnt > 0); - de->dev->dev_addr[i] = value; + addr[i] = value; udelay(1); if (boguscnt <= 0) pr_warn("timeout reading 21040 MAC address byte %u\n", i); } + eth_hw_addr_set(de->dev, addr); } static void de21040_get_media_info(struct de_private *de) @@ -1821,8 +1823,7 @@ static void de21041_get_srom_info(struct de_private *de) #endif /* store MAC address */ - for (i = 0; i < 6; i ++) - de->dev->dev_addr[i] = ee_data[i + sa_offset]; + eth_hw_addr_set(de->dev, &ee_data[sa_offset]); /* get offset of controller 0 info leaf. ignore 2nd byte. */ ofs = ee_data[SROMC0InfoLeaf]; diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 36ab4cbf2ad0..13121c4dcfe6 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -4031,6 +4031,7 @@ get_hw_addr(struct net_device *dev) int broken, i, k, tmp, status = 0; u_short j,chksum; struct de4x5_private *lp = netdev_priv(dev); + u8 addr[ETH_ALEN]; broken = de4x5_bad_srom(lp); @@ -4042,28 +4043,30 @@ get_hw_addr(struct net_device *dev) if (lp->chipset == DC21040) { while ((tmp = inl(DE4X5_APROM)) < 0); k += (u_char) tmp; - dev->dev_addr[i++] = (u_char) tmp; + addr[i++] = (u_char) tmp; while ((tmp = inl(DE4X5_APROM)) < 0); k += (u_short) (tmp << 8); - dev->dev_addr[i++] = (u_char) tmp; + addr[i++] = (u_char) tmp; } else if (!broken) { - dev->dev_addr[i] = (u_char) lp->srom.ieee_addr[i]; i++; - dev->dev_addr[i] = (u_char) lp->srom.ieee_addr[i]; i++; + addr[i] = (u_char) lp->srom.ieee_addr[i]; i++; + addr[i] = (u_char) lp->srom.ieee_addr[i]; i++; } else if ((broken == SMC) || (broken == ACCTON)) { - dev->dev_addr[i] = *((u_char *)&lp->srom + i); i++; - dev->dev_addr[i] = *((u_char *)&lp->srom + i); i++; + addr[i] = *((u_char *)&lp->srom + i); i++; + addr[i] = *((u_char *)&lp->srom + i); i++; } } else { k += (u_char) (tmp = inb(EISA_APROM)); - dev->dev_addr[i++] = (u_char) tmp; + addr[i++] = (u_char) tmp; k += (u_short) ((tmp = inb(EISA_APROM)) << 8); - dev->dev_addr[i++] = (u_char) tmp; + addr[i++] = (u_char) tmp; } if (k > 0xffff) k-=0xffff; } if (k == 0xffff) k=0; + eth_hw_addr_set(dev, addr); + if (lp->bus == PCI) { if (lp->chipset == DC21040) { while ((tmp = inl(DE4X5_APROM)) < 0); @@ -4095,8 +4098,9 @@ get_hw_addr(struct net_device *dev) int x = dev->dev_addr[i]; x = ((x & 0xf) << 4) + ((x & 0xf0) >> 4); x = ((x & 0x33) << 2) + ((x & 0xcc) >> 2); - dev->dev_addr[i] = ((x & 0x55) << 1) + ((x & 0xaa) >> 1); + addr[i] = ((x & 0x55) << 1) + ((x & 0xaa) >> 1); } + eth_hw_addr_set(dev, addr); } #endif /* CONFIG_PPC_PMAC */ @@ -4158,12 +4162,9 @@ test_bad_enet(struct net_device *dev, int status) if ((tmp == 0) || (tmp == 0x5fa)) { if ((lp->chipset == last.chipset) && (lp->bus_num == last.bus) && (lp->bus_num > 0)) { - for (i=0; i<ETH_ALEN; i++) dev->dev_addr[i] = last.addr[i]; - for (i=ETH_ALEN-1; i>2; --i) { - dev->dev_addr[i] += 1; - if (dev->dev_addr[i] != 0) break; - } - for (i=0; i<ETH_ALEN; i++) last.addr[i] = dev->dev_addr[i]; + eth_addr_inc(last.addr); + eth_hw_addr_set(dev, last.addr); + if (!an_exception(lp)) { dev->irq = last.irq; } @@ -5391,9 +5392,7 @@ de4x5_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user *data if (netif_queue_stopped(dev)) return -EBUSY; netif_stop_queue(dev); - for (i=0; i<ETH_ALEN; i++) { - dev->dev_addr[i] = tmp.addr[i]; - } + eth_hw_addr_set(dev, tmp.addr); build_setup_frame(dev, PHYS_ADDR_ONLY); /* Set up the descriptor and give ownership to the card */ load_packet(dev, lp->setup_frame, TD_IC | PERFECT_F | TD_SET | diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c index c763b692e164..83f1727d1423 100644 --- a/drivers/net/ethernet/dec/tulip/dmfe.c +++ b/drivers/net/ethernet/dec/tulip/dmfe.c @@ -476,8 +476,7 @@ static int dmfe_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } /* Set Node address */ - for (i = 0; i < 6; i++) - dev->dev_addr[i] = db->srom[20 + i]; + eth_hw_addr_set(dev, &db->srom[20]); err = register_netdev (dev); if (err) @@ -1436,9 +1435,9 @@ static void update_cr6(u32 cr6_data, void __iomem *ioaddr) static void dm9132_id_table(struct net_device *dev) { + const u16 *addrptr = (const u16 *)dev->dev_addr; struct dmfe_board_info *db = netdev_priv(dev); void __iomem *ioaddr = db->ioaddr + 0xc0; - u16 *addrptr = (u16 *)dev->dev_addr; struct netdev_hw_addr *ha; u16 i, hash_table[4]; @@ -1477,7 +1476,7 @@ static void send_filter_frame(struct net_device *dev) struct dmfe_board_info *db = netdev_priv(dev); struct netdev_hw_addr *ha; struct tx_desc *txptr; - u16 * addrptr; + const u16 * addrptr; u32 * suptr; int i; @@ -1487,7 +1486,7 @@ static void send_filter_frame(struct net_device *dev) suptr = (u32 *) txptr->tx_buf_ptr; /* Node address */ - addrptr = (u16 *) dev->dev_addr; + addrptr = (const u16 *) dev->dev_addr; *suptr++ = addrptr[0]; *suptr++ = addrptr[1]; *suptr++ = addrptr[2]; diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index 1ba6452c0683..79df5a72877b 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -339,7 +339,7 @@ static void tulip_up(struct net_device *dev) } } else { /* This is set_rx_mode(), but without starting the transmitter. */ - u16 *eaddrs = (u16 *)dev->dev_addr; + const u16 *eaddrs = (const u16 *)dev->dev_addr; u16 *setup_frm = &tp->setup_frame[15*6]; dma_addr_t mapping; @@ -1001,8 +1001,8 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) struct tulip_private *tp = netdev_priv(dev); u16 hash_table[32]; struct netdev_hw_addr *ha; + const u16 *eaddrs; int i; - u16 *eaddrs; memset(hash_table, 0, sizeof(hash_table)); __set_bit_le(255, hash_table); /* Broadcast entry */ @@ -1019,7 +1019,7 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) setup_frm = &tp->setup_frame[13*6]; /* Fill the final entry with our physical address. */ - eaddrs = (u16 *)dev->dev_addr; + eaddrs = (const u16 *)dev->dev_addr; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[2]; *setup_frm++ = eaddrs[2]; @@ -1029,7 +1029,7 @@ static void build_setup_frame_perfect(u16 *setup_frm, struct net_device *dev) { struct tulip_private *tp = netdev_priv(dev); struct netdev_hw_addr *ha; - u16 *eaddrs; + const u16 *eaddrs; /* We have <= 14 addresses so we can use the wonderful 16 address perfect filtering of the Tulip. */ @@ -1044,7 +1044,7 @@ static void build_setup_frame_perfect(u16 *setup_frm, struct net_device *dev) setup_frm = &tp->setup_frame[15*6]; /* Fill the final entry with our physical address. */ - eaddrs = (u16 *)dev->dev_addr; + eaddrs = (const u16 *)dev->dev_addr; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[0]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[1]; *setup_frm++ = eaddrs[2]; *setup_frm++ = eaddrs[2]; @@ -1305,6 +1305,7 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) int chip_idx = ent->driver_data; const char *chip_name = tulip_tbl[chip_idx].chip_name; unsigned int eeprom_missing = 0; + u8 addr[ETH_ALEN] __aligned(2); unsigned int force_csr0 = 0; board_idx++; @@ -1506,13 +1507,15 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) do { value = ioread32(ioaddr + CSR9); } while (value < 0 && --boguscnt > 0); - put_unaligned_le16(value, ((__le16 *)dev->dev_addr) + i); + put_unaligned_le16(value, ((__le16 *)addr) + i); sum += value & 0xffff; } + eth_hw_addr_set(dev, addr); } else if (chip_idx == COMET) { /* No need to read the EEPROM. */ - put_unaligned_le32(ioread32(ioaddr + 0xA4), dev->dev_addr); - put_unaligned_le16(ioread32(ioaddr + 0xA8), dev->dev_addr + 4); + put_unaligned_le32(ioread32(ioaddr + 0xA4), addr); + put_unaligned_le16(ioread32(ioaddr + 0xA8), addr + 4); + eth_hw_addr_set(dev, addr); for (i = 0; i < 6; i ++) sum += dev->dev_addr[i]; } else { @@ -1575,20 +1578,23 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) #endif for (i = 0; i < 6; i ++) { - dev->dev_addr[i] = ee_data[i + sa_offset]; + addr[i] = ee_data[i + sa_offset]; sum += ee_data[i + sa_offset]; } + eth_hw_addr_set(dev, addr); } /* Lite-On boards have the address byte-swapped. */ if ((dev->dev_addr[0] == 0xA0 || dev->dev_addr[0] == 0xC0 || dev->dev_addr[0] == 0x02) && - dev->dev_addr[1] == 0x00) + dev->dev_addr[1] == 0x00) { for (i = 0; i < 6; i+=2) { - char tmp = dev->dev_addr[i]; - dev->dev_addr[i] = dev->dev_addr[i+1]; - dev->dev_addr[i+1] = tmp; + addr[i] = dev->dev_addr[i+1]; + addr[i+1] = dev->dev_addr[i]; } + eth_hw_addr_set(dev, addr); + } + /* On the Zynx 315 Etherarray and other multiport boards only the first Tulip has an EEPROM. On Sparc systems the mac address is held in the OBP property @@ -1599,17 +1605,18 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (sum == 0 || sum == 6*0xff) { #if defined(CONFIG_SPARC) struct device_node *dp = pci_device_to_OF_node(pdev); - const unsigned char *addr; + const unsigned char *addr2; int len; #endif eeprom_missing = 1; for (i = 0; i < 5; i++) - dev->dev_addr[i] = last_phys_addr[i]; - dev->dev_addr[i] = last_phys_addr[i] + 1; + addr[i] = last_phys_addr[i]; + addr[i] = last_phys_addr[i] + 1; + eth_hw_addr_set(dev, addr); #if defined(CONFIG_SPARC) - addr = of_get_property(dp, "local-mac-address", &len); - if (addr && len == ETH_ALEN) - eth_hw_addr_set(dev, addr); + addr2 = of_get_property(dp, "local-mac-address", &len); + if (addr2 && len == ETH_ALEN) + eth_hw_addr_set(dev, addr2); #endif #if defined(__i386__) || defined(__x86_64__) /* Patch up x86 BIOS bug. */ if (last_irq) diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c index d67ef7d02d6b..77d9058431e3 100644 --- a/drivers/net/ethernet/dec/tulip/uli526x.c +++ b/drivers/net/ethernet/dec/tulip/uli526x.c @@ -272,6 +272,7 @@ static int uli526x_init_one(struct pci_dev *pdev, struct uli526x_board_info *db; /* board information structure */ struct net_device *dev; void __iomem *ioaddr; + u8 addr[ETH_ALEN]; int i, err; ULI526X_DBUG(0, "uli526x_init_one()", 0); @@ -379,7 +380,7 @@ static int uli526x_init_one(struct pci_dev *pdev, uw32(DCR13, 0x1b0); //Select ID Table access port //Read MAC address from CR14 for (i = 0; i < 6; i++) - dev->dev_addr[i] = ur32(DCR14); + addr[i] = ur32(DCR14); //Read end uw32(DCR13, 0); //Clear CR13 uw32(DCR0, 0); //Clear CR0 @@ -388,8 +389,10 @@ static int uli526x_init_one(struct pci_dev *pdev, else /*Exist SROM*/ { for (i = 0; i < 6; i++) - dev->dev_addr[i] = db->srom[20 + i]; + addr[i] = db->srom[20 + i]; } + eth_hw_addr_set(dev, addr); + err = register_netdev (dev); if (err) goto err_out_unmap; @@ -1343,7 +1346,7 @@ static void send_filter_frame(struct net_device *dev, int mc_cnt) void __iomem *ioaddr = db->ioaddr; struct netdev_hw_addr *ha; struct tx_desc *txptr; - u16 * addrptr; + const u16 * addrptr; u32 * suptr; int i; @@ -1353,7 +1356,7 @@ static void send_filter_frame(struct net_device *dev, int mc_cnt) suptr = (u32 *) txptr->tx_buf_ptr; /* Node address */ - addrptr = (u16 *) dev->dev_addr; + addrptr = (const u16 *) dev->dev_addr; *suptr++ = addrptr[0] << FLT_SHIFT; *suptr++ = addrptr[1] << FLT_SHIFT; *suptr++ = addrptr[2] << FLT_SHIFT; diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index 85b99099c6b9..86b1d23eba83 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -355,6 +355,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) int chip_idx = ent->driver_data; int irq; int i, option = find_cnt < MAX_UNITS ? options[find_cnt] : 0; + __le16 addr[ETH_ALEN / 2]; void __iomem *ioaddr; i = pcim_enable_device(pdev); @@ -382,7 +383,8 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out_netdev; for (i = 0; i < 3; i++) - ((__le16 *)dev->dev_addr)[i] = cpu_to_le16(eeprom_read(ioaddr, i)); + addr[i] = cpu_to_le16(eeprom_read(ioaddr, i)); + eth_hw_addr_set(dev, (u8 *)addr); /* Reset the chip to erase previous misconfiguration. No hold time required! */ @@ -877,7 +879,7 @@ static void init_registers(struct net_device *dev) 8000 16 longwords 0200 2 longwords 2000 32 longwords C000 32 longwords 0400 4 longwords */ -#if defined (__i386__) && !defined(MODULE) +#if defined (__i386__) && !defined(MODULE) && !defined(CONFIG_UML) /* When not a module we can work around broken '486 PCI boards. */ if (boot_cpu_data.x86 <= 4) { i |= 0x4800; diff --git a/drivers/net/ethernet/dec/tulip/xircom_cb.c b/drivers/net/ethernet/dec/tulip/xircom_cb.c index a8de79355578..8759f9f76b62 100644 --- a/drivers/net/ethernet/dec/tulip/xircom_cb.c +++ b/drivers/net/ethernet/dec/tulip/xircom_cb.c @@ -1015,12 +1015,14 @@ static void read_mac_address(struct xircom_private *card) xw32(CSR10, i + 3); data_count = xr32(CSR9); if ((tuple == 0x22) && (data_id == 0x04) && (data_count == 0x06)) { + u8 addr[ETH_ALEN]; int j; for (j = 0; j < 6; j++) { xw32(CSR10, i + j + 4); - card->dev->dev_addr[j] = xr32(CSR9) & 0xff; + addr[j] = xr32(CSR9) & 0xff; } + eth_hw_addr_set(card->dev, addr); break; } else if (link == 0) { break; diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 202ecb132053..a301f7e6a440 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -349,8 +349,7 @@ parse_eeprom (struct net_device *dev) } /* Set MAC address */ - for (i = 0; i < 6; i++) - dev->dev_addr[i] = psrom->mac_addr[i]; + eth_hw_addr_set(dev, psrom->mac_addr); if (np->chip_id == CHIP_IP1000A) { np->led_mode = psrom->led_mode; @@ -567,7 +566,7 @@ static void rio_hw_init(struct net_device *dev) */ for (i = 0; i < 3; i++) dw16(StationAddr0 + 2 * i, - cpu_to_le16(((u16 *)dev->dev_addr)[i])); + cpu_to_le16(((const u16 *)dev->dev_addr)[i])); set_multicast (dev); if (np->coalesce) { diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c index 194b0812f7f6..c710dc17be90 100644 --- a/drivers/net/ethernet/dlink/sundance.c +++ b/drivers/net/ethernet/dlink/sundance.c @@ -508,6 +508,7 @@ static int sundance_probe1(struct pci_dev *pdev, int bar = 1; #endif int phy, phy_end, phy_idx = 0; + __le16 addr[ETH_ALEN / 2]; if (pci_enable_device(pdev)) return -EIO; @@ -528,8 +529,9 @@ static int sundance_probe1(struct pci_dev *pdev, goto err_out_res; for (i = 0; i < 3; i++) - ((__le16 *)dev->dev_addr)[i] = + addr[i] = cpu_to_le16(eeprom_read(ioaddr, i + EEPROM_SA_OFFSET)); + eth_hw_addr_set(dev, (u8 *)addr); np = netdev_priv(dev); np->ndev = dev; diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c index 6c51cf991dad..92462ed87bc4 100644 --- a/drivers/net/ethernet/dnet.c +++ b/drivers/net/ethernet/dnet.c @@ -60,11 +60,11 @@ static void __dnet_set_hwaddr(struct dnet *bp) { u16 tmp; - tmp = be16_to_cpup((__be16 *)bp->dev->dev_addr); + tmp = be16_to_cpup((const __be16 *)bp->dev->dev_addr); dnet_writew_mac(bp, DNET_INTERNAL_MAC_ADDR_0_REG, tmp); - tmp = be16_to_cpup((__be16 *)(bp->dev->dev_addr + 2)); + tmp = be16_to_cpup((const __be16 *)(bp->dev->dev_addr + 2)); dnet_writew_mac(bp, DNET_INTERNAL_MAC_ADDR_1_REG, tmp); - tmp = be16_to_cpup((__be16 *)(bp->dev->dev_addr + 4)); + tmp = be16_to_cpup((const __be16 *)(bp->dev->dev_addr + 4)); dnet_writew_mac(bp, DNET_INTERNAL_MAC_ADDR_2_REG, tmp); } @@ -93,7 +93,7 @@ static void dnet_get_hwaddr(struct dnet *bp) *((__be16 *)(addr + 4)) = cpu_to_be16(tmp); if (is_valid_ether_addr(addr)) - memcpy(bp->dev->dev_addr, addr, sizeof(addr)); + eth_hw_addr_set(bp->dev, addr); } static int dnet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c index b2d4fb3feb74..46e3a05e9582 100644 --- a/drivers/net/ethernet/ec_bhf.c +++ b/drivers/net/ethernet/ec_bhf.c @@ -479,6 +479,7 @@ static int ec_bhf_probe(struct pci_dev *dev, const struct pci_device_id *id) struct net_device *net_dev; struct ec_bhf_priv *priv; void __iomem *dma_io; + u8 addr[ETH_ALEN]; void __iomem *io; int err = 0; @@ -539,7 +540,8 @@ static int ec_bhf_probe(struct pci_dev *dev, const struct pci_device_id *id) if (err < 0) goto err_free_net_dev; - memcpy_fromio(net_dev->dev_addr, priv->mii_io + MII_MAC_ADDR, 6); + memcpy_fromio(addr, priv->mii_io + MII_MAC_ADDR, ETH_ALEN); + eth_hw_addr_set(net_dev, addr); err = register_netdev(net_dev); if (err < 0) diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 649c5c429bd7..528eb0f223b1 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -1080,7 +1080,7 @@ err: } /* Uses synchronous MCCQ */ -int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, +int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr, u32 if_id, u32 *pmac_id, u32 domain) { struct be_mcc_wrb *wrb; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index c30d6d6f0f3a..db1f3b908582 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -2385,7 +2385,7 @@ int be_pci_fnum_get(struct be_adapter *adapter); int be_fw_wait_ready(struct be_adapter *adapter); int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr, bool permanent, u32 if_handle, u32 pmac_id); -int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, u32 if_id, +int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr, u32 if_id, u32 *pmac_id, u32 domain); int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 domain); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index ef60e2da05a4..d51f24c9e1b8 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -272,7 +272,7 @@ void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm, u16 num_popped) iowrite32(val, adapter->db + DB_CQ_OFFSET); } -static int be_dev_mac_add(struct be_adapter *adapter, u8 *mac) +static int be_dev_mac_add(struct be_adapter *adapter, const u8 *mac) { int i; @@ -4621,7 +4621,6 @@ static void be_destroy_err_recovery_workq(void) if (!be_err_recovery_workq) return; - flush_workqueue(be_err_recovery_workq); destroy_workqueue(be_err_recovery_workq); be_err_recovery_workq = NULL; } diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index cd3a3b8f23b6..b1c8ffea6ad2 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -802,8 +802,8 @@ static int ethoc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static void ethoc_do_set_mac_address(struct net_device *dev) { + const unsigned char *mac = dev->dev_addr; struct ethoc *priv = netdev_priv(dev); - unsigned char *mac = dev->dev_addr; ethoc_write(priv, MAC_ADDR0, (mac[2] << 24) | (mac[3] << 16) | (mac[4] << 8) | (mac[5] << 0)); @@ -1154,8 +1154,12 @@ static int ethoc_probe(struct platform_device *pdev) /* Check that the given MAC address is valid. If it isn't, read the * current MAC from the controller. */ - if (!is_valid_ether_addr(netdev->dev_addr)) - ethoc_get_mac_address(netdev, netdev->dev_addr); + if (!is_valid_ether_addr(netdev->dev_addr)) { + u8 addr[ETH_ALEN]; + + ethoc_get_mac_address(netdev, addr); + eth_hw_addr_set(netdev, addr); + } /* Check the MAC again for validity, if it still isn't choose and * program a random one. diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c index 25c91b3c5fd3..b3939a5f7b03 100644 --- a/drivers/net/ethernet/fealnx.c +++ b/drivers/net/ethernet/fealnx.c @@ -482,6 +482,7 @@ static int fealnx_init_one(struct pci_dev *pdev, struct net_device *dev; void *ring_space; dma_addr_t ring_dma; + u8 addr[ETH_ALEN]; #ifdef USE_IO_OPS int bar = 0; #else @@ -525,7 +526,8 @@ static int fealnx_init_one(struct pci_dev *pdev, /* read ethernet id */ for (i = 0; i < 6; ++i) - dev->dev_addr[i] = ioread8(ioaddr + PAR0 + i); + addr[i] = ioread8(ioaddr + PAR0 + i); + eth_hw_addr_set(dev, addr); /* Reset the chip to erase previous misconfiguration. */ iowrite32(0x00000001, ioaddr + BCR); @@ -827,7 +829,7 @@ static int netdev_open(struct net_device *dev) return -EAGAIN; for (i = 0; i < 3; i++) - iowrite16(((unsigned short*)dev->dev_addr)[i], + iowrite16(((const unsigned short *)dev->dev_addr)[i], ioaddr + PAR0 + i*2); init_ring(dev); @@ -857,7 +859,7 @@ static int netdev_open(struct net_device *dev) np->bcrvalue |= 0x04; /* big-endian */ #endif -#if defined(__i386__) && !defined(MODULE) +#if defined(__i386__) && !defined(MODULE) && !defined(CONFIG_UML) if (boot_cpu_data.x86 <= 4) np->crvalue = 0xa00; else diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index cd8a7d94f60c..6b2927d863e2 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -272,7 +272,7 @@ static int dpaa_netdev_init(struct net_device *net_dev, } else { eth_hw_addr_random(net_dev); err = priv->mac_dev->change_addr(priv->mac_dev->fman_mac, - (enet_addr_t *)net_dev->dev_addr); + (const enet_addr_t *)net_dev->dev_addr); if (err) { dev_err(dev, "Failed to set random MAC address\n"); return -EINVAL; @@ -452,7 +452,7 @@ static int dpaa_set_mac_address(struct net_device *net_dev, void *addr) mac_dev = priv->mac_dev; err = mac_dev->change_addr(mac_dev->fman_mac, - (enet_addr_t *)net_dev->dev_addr); + (const enet_addr_t *)net_dev->dev_addr); if (err < 0) { netif_err(priv, drv, net_dev, "mac_dev->change_addr() = %d\n", err); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 34f189271ef2..714e961e7a77 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -533,6 +533,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, percpu_stats->rx_packets++; percpu_stats->rx_bytes += dpaa2_fd_get_len(fd); + ch->stats.bytes_per_cdan += dpaa2_fd_get_len(fd); list_add_tail(&skb->list, ch->rx_list); @@ -641,6 +642,7 @@ static int dpaa2_eth_consume_frames(struct dpaa2_eth_channel *ch, fq->stats.frames += cleaned; ch->stats.frames += cleaned; + ch->stats.frames_per_cdan += cleaned; /* A dequeue operation only pulls frames from a single queue * into the store. Return the frame queue as an out param. @@ -1264,7 +1266,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev) /* Tx confirmation frame processing routine */ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv, - struct dpaa2_eth_channel *ch __always_unused, + struct dpaa2_eth_channel *ch, const struct dpaa2_fd *fd, struct dpaa2_eth_fq *fq) { @@ -1279,6 +1281,7 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv, percpu_extras = this_cpu_ptr(priv->percpu_extras); percpu_extras->tx_conf_frames++; percpu_extras->tx_conf_bytes += fd_len; + ch->stats.bytes_per_cdan += fd_len; /* Check frame errors in the FD field */ fd_errors = dpaa2_fd_get_ctrl(fd) & DPAA2_FD_TX_ERR_MASK; @@ -1601,6 +1604,12 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget) } } while (store_cleaned); + /* Update NET DIM with the values for this CDAN */ + dpaa2_io_update_net_dim(ch->dpio, ch->stats.frames_per_cdan, + ch->stats.bytes_per_cdan); + ch->stats.frames_per_cdan = 0; + ch->stats.bytes_per_cdan = 0; + /* We didn't consume the entire budget, so finish napi and * re-enable data availability notifications */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index 628d2d45f045..2085844227fe 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -384,6 +384,8 @@ struct dpaa2_eth_ch_stats { __u64 xdp_redirect; /* Must be last, does not show up in ethtool stats */ __u64 frames; + __u64 frames_per_cdan; + __u64 bytes_per_cdan; }; /* Maximum number of queues associated with a DPNI */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 2da5f881f630..adb8ce5306ee 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -820,7 +820,63 @@ static int dpaa2_eth_set_tunable(struct net_device *net_dev, return err; } +static int dpaa2_eth_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *ic, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct dpaa2_eth_priv *priv = netdev_priv(dev); + struct dpaa2_io *dpio = priv->channel[0]->dpio; + + dpaa2_io_get_irq_coalescing(dpio, &ic->rx_coalesce_usecs); + ic->use_adaptive_rx_coalesce = dpaa2_io_get_adaptive_coalescing(dpio); + + return 0; +} + +static int dpaa2_eth_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *ic, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct dpaa2_eth_priv *priv = netdev_priv(dev); + struct dpaa2_io *dpio; + int prev_adaptive; + u32 prev_rx_usecs; + int i, j, err; + + /* Keep track of the previous value, just in case we fail */ + dpio = priv->channel[0]->dpio; + dpaa2_io_get_irq_coalescing(dpio, &prev_rx_usecs); + prev_adaptive = dpaa2_io_get_adaptive_coalescing(dpio); + + /* Setup new value for rx coalescing */ + for (i = 0; i < priv->num_channels; i++) { + dpio = priv->channel[i]->dpio; + + dpaa2_io_set_adaptive_coalescing(dpio, + ic->use_adaptive_rx_coalesce); + err = dpaa2_io_set_irq_coalescing(dpio, ic->rx_coalesce_usecs); + if (err) + goto restore_rx_usecs; + } + + return 0; + +restore_rx_usecs: + for (j = 0; j < i; j++) { + dpio = priv->channel[j]->dpio; + + dpaa2_io_set_irq_coalescing(dpio, prev_rx_usecs); + dpaa2_io_set_adaptive_coalescing(dpio, prev_adaptive); + } + + return err; +} + const struct ethtool_ops dpaa2_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS | + ETHTOOL_COALESCE_USE_ADAPTIVE_RX, .get_drvinfo = dpaa2_eth_get_drvinfo, .nway_reset = dpaa2_eth_nway_reset, .get_link = ethtool_op_get_link, @@ -836,4 +892,6 @@ const struct ethtool_ops dpaa2_ethtool_ops = { .get_ts_info = dpaa2_eth_get_ts_info, .get_tunable = dpaa2_eth_get_tunable, .set_tunable = dpaa2_eth_set_tunable, + .get_coalesce = dpaa2_eth_get_coalesce, + .set_coalesce = dpaa2_eth_set_coalesce, }; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 3cbfa8b4e265..8e31fe15bf3c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -7,7 +7,9 @@ #include <linux/udp.h> #include <linux/vmalloc.h> #include <linux/ptp_classify.h> +#include <net/ip6_checksum.h> #include <net/pkt_sched.h> +#include <net/tso.h> static int enetc_num_stack_tx_queues(struct enetc_ndev_priv *priv) { @@ -314,12 +316,261 @@ dma_err: return 0; } +static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb, + struct enetc_tx_swbd *tx_swbd, + union enetc_tx_bd *txbd, int *i, int hdr_len, + int data_len) +{ + union enetc_tx_bd txbd_tmp; + u8 flags = 0, e_flags = 0; + dma_addr_t addr; + + enetc_clear_tx_bd(&txbd_tmp); + addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE; + + if (skb_vlan_tag_present(skb)) + flags |= ENETC_TXBD_FLAGS_EX; + + txbd_tmp.addr = cpu_to_le64(addr); + txbd_tmp.buf_len = cpu_to_le16(hdr_len); + + /* first BD needs frm_len and offload flags set */ + txbd_tmp.frm_len = cpu_to_le16(hdr_len + data_len); + txbd_tmp.flags = flags; + + /* For the TSO header we do not set the dma address since we do not + * want it unmapped when we do cleanup. We still set len so that we + * count the bytes sent. + */ + tx_swbd->len = hdr_len; + tx_swbd->do_twostep_tstamp = false; + tx_swbd->check_wb = false; + + /* Actually write the header in the BD */ + *txbd = txbd_tmp; + + /* Add extension BD for VLAN */ + if (flags & ENETC_TXBD_FLAGS_EX) { + /* Get the next BD */ + enetc_bdr_idx_inc(tx_ring, i); + txbd = ENETC_TXBD(*tx_ring, *i); + tx_swbd = &tx_ring->tx_swbd[*i]; + prefetchw(txbd); + + /* Setup the VLAN fields */ + enetc_clear_tx_bd(&txbd_tmp); + txbd_tmp.ext.vid = cpu_to_le16(skb_vlan_tag_get(skb)); + txbd_tmp.ext.tpid = 0; /* < C-TAG */ + e_flags |= ENETC_TXBD_E_FLAGS_VLAN_INS; + + /* Write the BD */ + txbd_tmp.ext.e_flags = e_flags; + *txbd = txbd_tmp; + } +} + +static int enetc_map_tx_tso_data(struct enetc_bdr *tx_ring, struct sk_buff *skb, + struct enetc_tx_swbd *tx_swbd, + union enetc_tx_bd *txbd, char *data, + int size, bool last_bd) +{ + union enetc_tx_bd txbd_tmp; + dma_addr_t addr; + u8 flags = 0; + + enetc_clear_tx_bd(&txbd_tmp); + + addr = dma_map_single(tx_ring->dev, data, size, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(tx_ring->dev, addr))) { + netdev_err(tx_ring->ndev, "DMA map error\n"); + return -ENOMEM; + } + + if (last_bd) { + flags |= ENETC_TXBD_FLAGS_F; + tx_swbd->is_eof = 1; + } + + txbd_tmp.addr = cpu_to_le64(addr); + txbd_tmp.buf_len = cpu_to_le16(size); + txbd_tmp.flags = flags; + + tx_swbd->dma = addr; + tx_swbd->len = size; + tx_swbd->dir = DMA_TO_DEVICE; + + *txbd = txbd_tmp; + + return 0; +} + +static __wsum enetc_tso_hdr_csum(struct tso_t *tso, struct sk_buff *skb, + char *hdr, int hdr_len, int *l4_hdr_len) +{ + char *l4_hdr = hdr + skb_transport_offset(skb); + int mac_hdr_len = skb_network_offset(skb); + + if (tso->tlen != sizeof(struct udphdr)) { + struct tcphdr *tcph = (struct tcphdr *)(l4_hdr); + + tcph->check = 0; + } else { + struct udphdr *udph = (struct udphdr *)(l4_hdr); + + udph->check = 0; + } + + /* Compute the IP checksum. This is necessary since tso_build_hdr() + * already incremented the IP ID field. + */ + if (!tso->ipv6) { + struct iphdr *iph = (void *)(hdr + mac_hdr_len); + + iph->check = 0; + iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + } + + /* Compute the checksum over the L4 header. */ + *l4_hdr_len = hdr_len - skb_transport_offset(skb); + return csum_partial(l4_hdr, *l4_hdr_len, 0); +} + +static void enetc_tso_complete_csum(struct enetc_bdr *tx_ring, struct tso_t *tso, + struct sk_buff *skb, char *hdr, int len, + __wsum sum) +{ + char *l4_hdr = hdr + skb_transport_offset(skb); + __sum16 csum_final; + + /* Complete the L4 checksum by appending the pseudo-header to the + * already computed checksum. + */ + if (!tso->ipv6) + csum_final = csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + len, ip_hdr(skb)->protocol, sum); + else + csum_final = csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + len, ipv6_hdr(skb)->nexthdr, sum); + + if (tso->tlen != sizeof(struct udphdr)) { + struct tcphdr *tcph = (struct tcphdr *)(l4_hdr); + + tcph->check = csum_final; + } else { + struct udphdr *udph = (struct udphdr *)(l4_hdr); + + udph->check = csum_final; + } +} + +static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) +{ + int hdr_len, total_len, data_len; + struct enetc_tx_swbd *tx_swbd; + union enetc_tx_bd *txbd; + struct tso_t tso; + __wsum csum, csum2; + int count = 0, pos; + int err, i, bd_data_num; + + /* Initialize the TSO handler, and prepare the first payload */ + hdr_len = tso_start(skb, &tso); + total_len = skb->len - hdr_len; + i = tx_ring->next_to_use; + + while (total_len > 0) { + char *hdr; + + /* Get the BD */ + txbd = ENETC_TXBD(*tx_ring, i); + tx_swbd = &tx_ring->tx_swbd[i]; + prefetchw(txbd); + + /* Determine the length of this packet */ + data_len = min_t(int, skb_shinfo(skb)->gso_size, total_len); + total_len -= data_len; + + /* prepare packet headers: MAC + IP + TCP */ + hdr = tx_ring->tso_headers + i * TSO_HEADER_SIZE; + tso_build_hdr(skb, hdr, &tso, data_len, total_len == 0); + + /* compute the csum over the L4 header */ + csum = enetc_tso_hdr_csum(&tso, skb, hdr, hdr_len, &pos); + enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, &i, hdr_len, data_len); + bd_data_num = 0; + count++; + + while (data_len > 0) { + int size; + + size = min_t(int, tso.size, data_len); + + /* Advance the index in the BDR */ + enetc_bdr_idx_inc(tx_ring, &i); + txbd = ENETC_TXBD(*tx_ring, i); + tx_swbd = &tx_ring->tx_swbd[i]; + prefetchw(txbd); + + /* Compute the checksum over this segment of data and + * add it to the csum already computed (over the L4 + * header and possible other data segments). + */ + csum2 = csum_partial(tso.data, size, 0); + csum = csum_block_add(csum, csum2, pos); + pos += size; + + err = enetc_map_tx_tso_data(tx_ring, skb, tx_swbd, txbd, + tso.data, size, + size == data_len); + if (err) + goto err_map_data; + + data_len -= size; + count++; + bd_data_num++; + tso_build_data(skb, &tso, size); + + if (unlikely(bd_data_num >= ENETC_MAX_SKB_FRAGS && data_len)) + goto err_chained_bd; + } + + enetc_tso_complete_csum(tx_ring, &tso, skb, hdr, pos, csum); + + if (total_len == 0) + tx_swbd->skb = skb; + + /* Go to the next BD */ + enetc_bdr_idx_inc(tx_ring, &i); + } + + tx_ring->next_to_use = i; + enetc_update_tx_ring_tail(tx_ring); + + return count; + +err_map_data: + dev_err(tx_ring->dev, "DMA map error"); + +err_chained_bd: + do { + tx_swbd = &tx_ring->tx_swbd[i]; + enetc_free_tx_frame(tx_ring, tx_swbd); + if (i == 0) + i = tx_ring->bd_count; + i--; + } while (count--); + + return 0; +} + static netdev_tx_t enetc_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_bdr *tx_ring; - int count; + int count, err; /* Queue one-step Sync packet if already locked */ if (skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) { @@ -332,19 +583,35 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb, tx_ring = priv->tx_ring[skb->queue_mapping]; - if (unlikely(skb_shinfo(skb)->nr_frags > ENETC_MAX_SKB_FRAGS)) - if (unlikely(skb_linearize(skb))) - goto drop_packet_err; + if (skb_is_gso(skb)) { + if (enetc_bd_unused(tx_ring) < tso_count_descs(skb)) { + netif_stop_subqueue(ndev, tx_ring->index); + return NETDEV_TX_BUSY; + } - count = skb_shinfo(skb)->nr_frags + 1; /* fragments + head */ - if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_NEEDED(count)) { - netif_stop_subqueue(ndev, tx_ring->index); - return NETDEV_TX_BUSY; - } + enetc_lock_mdio(); + count = enetc_map_tx_tso_buffs(tx_ring, skb); + enetc_unlock_mdio(); + } else { + if (unlikely(skb_shinfo(skb)->nr_frags > ENETC_MAX_SKB_FRAGS)) + if (unlikely(skb_linearize(skb))) + goto drop_packet_err; + + count = skb_shinfo(skb)->nr_frags + 1; /* fragments + head */ + if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_NEEDED(count)) { + netif_stop_subqueue(ndev, tx_ring->index); + return NETDEV_TX_BUSY; + } - enetc_lock_mdio(); - count = enetc_map_tx_buffs(tx_ring, skb); - enetc_unlock_mdio(); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + err = skb_checksum_help(skb); + if (err) + goto drop_packet_err; + } + enetc_lock_mdio(); + count = enetc_map_tx_buffs(tx_ring, skb); + enetc_unlock_mdio(); + } if (unlikely(!count)) goto drop_packet_err; @@ -1493,15 +1760,32 @@ static int enetc_alloc_txbdr(struct enetc_bdr *txr) return -ENOMEM; err = enetc_dma_alloc_bdr(txr, sizeof(union enetc_tx_bd)); - if (err) { - vfree(txr->tx_swbd); - return err; + if (err) + goto err_alloc_bdr; + + txr->tso_headers = dma_alloc_coherent(txr->dev, + txr->bd_count * TSO_HEADER_SIZE, + &txr->tso_headers_dma, + GFP_KERNEL); + if (!txr->tso_headers) { + err = -ENOMEM; + goto err_alloc_tso; } txr->next_to_clean = 0; txr->next_to_use = 0; return 0; + +err_alloc_tso: + dma_free_coherent(txr->dev, txr->bd_count * sizeof(union enetc_tx_bd), + txr->bd_base, txr->bd_dma_base); + txr->bd_base = NULL; +err_alloc_bdr: + vfree(txr->tx_swbd); + txr->tx_swbd = NULL; + + return err; } static void enetc_free_txbdr(struct enetc_bdr *txr) @@ -1513,6 +1797,10 @@ static void enetc_free_txbdr(struct enetc_bdr *txr) size = txr->bd_count * sizeof(union enetc_tx_bd); + dma_free_coherent(txr->dev, txr->bd_count * TSO_HEADER_SIZE, + txr->tso_headers, txr->tso_headers_dma); + txr->tso_headers = NULL; + dma_free_coherent(txr->dev, size, txr->bd_base, txr->bd_dma_base); txr->bd_base = NULL; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 08b283347d9c..fb39e406b7fc 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -112,6 +112,10 @@ struct enetc_bdr { dma_addr_t bd_dma_base; u8 tsd_enable; /* Time specific departure */ bool ext_en; /* enable h/w descriptor extensions */ + + /* DMA buffer for TSO headers */ + char *tso_headers; + dma_addr_t tso_headers_dma; } ____cacheline_aligned_in_smp; static inline void enetc_bdr_idx_inc(struct enetc_bdr *bdr, int *i) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 0f5f081a5baf..1514e6a4a3ff 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -635,10 +635,14 @@ struct enetc_cmd_rfse { #define ENETC_RFSE_EN BIT(15) #define ENETC_RFSE_MODE_BD 2 -static inline void enetc_get_primary_mac_addr(struct enetc_hw *hw, u8 *addr) +static inline void enetc_load_primary_mac_addr(struct enetc_hw *hw, + struct net_device *ndev) { + u8 addr[ETH_ALEN] __aligned(4); + *(u32 *)addr = __raw_readl(hw->reg + ENETC_SIPMAR0); *(u16 *)(addr + 4) = __raw_readw(hw->reg + ENETC_SIPMAR1); + eth_hw_addr_set(ndev, addr); } #define ENETC_SI_INT_IDX 0 diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 628a74ba630c..ead2b93bf614 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -759,10 +759,14 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK; + 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_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; @@ -779,7 +783,7 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, } /* pick up primary MAC address from SI */ - enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr); + enetc_load_primary_mac_addr(&si->hw, ndev); } static int enetc_mdio_probe(struct enetc_pf *pf, struct device_node *np) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c index 0704f6bf12fd..17924305afa2 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c @@ -122,16 +122,20 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev, 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_RX | + 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_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; /* pick up primary MAC address from SI */ - enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr); + enetc_load_primary_mac_addr(&si->hw, ndev); } static int enetc_vf_probe(struct pci_dev *pdev, diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index bce3c9398887..1950a8936bc0 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -366,7 +366,7 @@ static void set_dflts(struct dtsec_cfg *cfg) cfg->maximum_frame = DEFAULT_MAXIMUM_FRAME; } -static void set_mac_address(struct dtsec_regs __iomem *regs, u8 *adr) +static void set_mac_address(struct dtsec_regs __iomem *regs, const u8 *adr) { u32 tmp; @@ -516,7 +516,7 @@ static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg, if (addr) { MAKE_ENET_ADDR_FROM_UINT64(addr, eth_addr); - set_mac_address(regs, (u8 *)eth_addr); + set_mac_address(regs, (const u8 *)eth_addr); } /* HASH */ @@ -1022,7 +1022,7 @@ int dtsec_accept_rx_pause_frames(struct fman_mac *dtsec, bool en) return 0; } -int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr) +int dtsec_modify_mac_address(struct fman_mac *dtsec, const enet_addr_t *enet_addr) { struct dtsec_regs __iomem *regs = dtsec->regs; enum comm_mode mode = COMM_MODE_NONE; @@ -1041,7 +1041,7 @@ int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr) * Station address have to be swapped (big endian to little endian */ dtsec->addr = ENET_ADDR_TO_UINT64(*enet_addr); - set_mac_address(dtsec->regs, (u8 *)(*enet_addr)); + set_mac_address(dtsec->regs, (const u8 *)(*enet_addr)); graceful_start(dtsec, mode); diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.h b/drivers/net/ethernet/freescale/fman/fman_dtsec.h index 5149d96ec2c1..68512c3bd6e5 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.h +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.h @@ -37,7 +37,7 @@ struct fman_mac *dtsec_config(struct fman_mac_params *params); int dtsec_set_promiscuous(struct fman_mac *dtsec, bool new_val); -int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr); +int dtsec_modify_mac_address(struct fman_mac *dtsec, const enet_addr_t *enet_addr); int dtsec_adjust_link(struct fman_mac *dtsec, u16 speed); int dtsec_restart_autoneg(struct fman_mac *dtsec); diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 62f42921933d..2216b7f51d26 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -354,7 +354,7 @@ struct fman_mac { bool allmulti_enabled; }; -static void add_addr_in_paddr(struct memac_regs __iomem *regs, u8 *adr, +static void add_addr_in_paddr(struct memac_regs __iomem *regs, const u8 *adr, u8 paddr_num) { u32 tmp0, tmp1; @@ -897,12 +897,12 @@ int memac_accept_rx_pause_frames(struct fman_mac *memac, bool en) return 0; } -int memac_modify_mac_address(struct fman_mac *memac, enet_addr_t *enet_addr) +int memac_modify_mac_address(struct fman_mac *memac, const enet_addr_t *enet_addr) { if (!is_init_done(memac->memac_drv_param)) return -EINVAL; - add_addr_in_paddr(memac->regs, (u8 *)(*enet_addr), 0); + add_addr_in_paddr(memac->regs, (const u8 *)(*enet_addr), 0); return 0; } @@ -1058,7 +1058,7 @@ int memac_init(struct fman_mac *memac) /* MAC Address */ if (memac->addr != 0) { MAKE_ENET_ADDR_FROM_UINT64(memac->addr, eth_addr); - add_addr_in_paddr(memac->regs, (u8 *)eth_addr, 0); + add_addr_in_paddr(memac->regs, (const u8 *)eth_addr, 0); } fixed_link = memac_drv_param->fixed_link; diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h index b2c671ec0ce7..3820f7a22983 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.h +++ b/drivers/net/ethernet/freescale/fman/fman_memac.h @@ -40,7 +40,7 @@ struct fman_mac *memac_config(struct fman_mac_params *params); int memac_set_promiscuous(struct fman_mac *memac, bool new_val); -int memac_modify_mac_address(struct fman_mac *memac, enet_addr_t *enet_addr); +int memac_modify_mac_address(struct fman_mac *memac, const enet_addr_t *enet_addr); int memac_adjust_link(struct fman_mac *memac, u16 speed); int memac_cfg_max_frame_len(struct fman_mac *memac, u16 new_val); int memac_cfg_reset_on_init(struct fman_mac *memac, bool enable); diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index 41946b16f6c7..311c1906e044 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -221,7 +221,7 @@ struct fman_mac { bool allmulti_enabled; }; -static void set_mac_address(struct tgec_regs __iomem *regs, u8 *adr) +static void set_mac_address(struct tgec_regs __iomem *regs, const u8 *adr) { u32 tmp0, tmp1; @@ -514,13 +514,13 @@ int tgec_accept_rx_pause_frames(struct fman_mac *tgec, bool en) return 0; } -int tgec_modify_mac_address(struct fman_mac *tgec, enet_addr_t *p_enet_addr) +int tgec_modify_mac_address(struct fman_mac *tgec, const enet_addr_t *p_enet_addr) { if (!is_init_done(tgec->cfg)) return -EINVAL; tgec->addr = ENET_ADDR_TO_UINT64(*p_enet_addr); - set_mac_address(tgec->regs, (u8 *)(*p_enet_addr)); + set_mac_address(tgec->regs, (const u8 *)(*p_enet_addr)); return 0; } @@ -704,7 +704,7 @@ int tgec_init(struct fman_mac *tgec) if (tgec->addr) { MAKE_ENET_ADDR_FROM_UINT64(tgec->addr, eth_addr); - set_mac_address(tgec->regs, (u8 *)eth_addr); + set_mac_address(tgec->regs, (const u8 *)eth_addr); } /* interrupts */ diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.h b/drivers/net/ethernet/freescale/fman/fman_tgec.h index 3bfd1062b386..b28b20b26148 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.h +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.h @@ -37,7 +37,7 @@ struct fman_mac *tgec_config(struct fman_mac_params *params); int tgec_set_promiscuous(struct fman_mac *tgec, bool new_val); -int tgec_modify_mac_address(struct fman_mac *tgec, enet_addr_t *enet_addr); +int tgec_modify_mac_address(struct fman_mac *tgec, const enet_addr_t *enet_addr); int tgec_cfg_max_frame_len(struct fman_mac *tgec, u16 new_val); int tgec_enable(struct fman_mac *tgec, enum comm_mode mode); int tgec_disable(struct fman_mac *tgec, enum comm_mode mode); diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index 824a81a9f350..daa285a9b8b2 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -66,7 +66,7 @@ struct mac_device { int (*stop)(struct mac_device *mac_dev); void (*adjust_link)(struct mac_device *mac_dev); int (*set_promisc)(struct fman_mac *mac_dev, bool enable); - int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr); + int (*change_addr)(struct fman_mac *mac_dev, const enet_addr_t *enet_addr); int (*set_allmulti)(struct fman_mac *mac_dev, bool enable); int (*set_tstamp)(struct fman_mac *mac_dev, bool enable); int (*set_multi)(struct net_device *net_dev, diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c index 62c0bed82ced..b0d733e9a7c6 100644 --- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c +++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c @@ -334,6 +334,7 @@ static int fmvj18x_config(struct pcmcia_device *link) u8 *buf; size_t len; u_char buggybuf[32]; + u8 addr[ETH_ALEN]; dev_dbg(&link->dev, "fmvj18x_config\n"); @@ -468,8 +469,7 @@ static int fmvj18x_config(struct pcmcia_device *link) goto failed; } /* Read MACID from CIS */ - for (i = 0; i < 6; i++) - dev->dev_addr[i] = buf[i + 5]; + eth_hw_addr_set(dev, &buf[5]); kfree(buf); } else { if (pcmcia_get_mac_from_cis(link, dev)) @@ -490,7 +490,8 @@ static int fmvj18x_config(struct pcmcia_device *link) case UNGERMANN: /* Read MACID from register */ for (i = 0; i < 6; i++) - dev->dev_addr[i] = inb(ioaddr + UNGERMANN_MAC_ID + i); + addr[i] = inb(ioaddr + UNGERMANN_MAC_ID + i); + eth_hw_addr_set(dev, addr); card_name = "Access/CARD"; break; case XXX10304: @@ -499,16 +500,15 @@ static int fmvj18x_config(struct pcmcia_device *link) pr_notice("unable to read hardware net address\n"); goto failed; } - for (i = 0 ; i < 6; i++) { - dev->dev_addr[i] = buggybuf[i]; - } + eth_hw_addr_set(dev, buggybuf); card_name = "FMV-J182"; break; case MBH10302: default: /* Read MACID from register */ for (i = 0; i < 6; i++) - dev->dev_addr[i] = inb(ioaddr + MAC_ID + i); + addr[i] = inb(ioaddr + MAC_ID + i); + eth_hw_addr_set(dev, addr); card_name = "FMV-J181"; break; } diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 85bf825606e8..51ed8fe71d2d 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -30,7 +30,7 @@ #define GVE_MIN_MSIX 3 /* Numbers of gve tx/rx stats in stats report. */ -#define GVE_TX_STATS_REPORT_NUM 5 +#define GVE_TX_STATS_REPORT_NUM 6 #define GVE_RX_STATS_REPORT_NUM 2 /* Interval to schedule a stats report update, 20000ms. */ @@ -341,8 +341,8 @@ struct gve_tx_ring { union { /* GQI fields */ struct { - /* NIC tail pointer */ - __be32 last_nic_done; + /* Spinlock for when cleanup in progress */ + spinlock_t clean_lock; }; /* DQO fields. */ @@ -413,7 +413,9 @@ struct gve_tx_ring { u32 q_num ____cacheline_aligned; /* queue idx */ u32 stop_queue; /* count of queue stops */ u32 wake_queue; /* count of queue wakes */ + u32 queue_timeout; /* count of queue timeouts */ u32 ntfy_id; /* notification block index */ + u32 last_kick_msec; /* Last time the queue was kicked */ dma_addr_t bus; /* dma address of the descr ring */ dma_addr_t q_resources_bus; /* dma address of the queue resources */ dma_addr_t complq_bus_dqo; /* dma address of the dqo.compl_ring */ @@ -779,7 +781,7 @@ struct gve_queue_page_list *gve_assign_rx_qpl(struct gve_priv *priv) gve_num_tx_qpls(priv)); /* we are out of rx qpls */ - if (id == priv->qpl_cfg.qpl_map_size) + if (id == gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv)) return NULL; set_bit(id, priv->qpl_cfg.qpl_id_map); @@ -821,15 +823,15 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev); bool gve_tx_poll(struct gve_notify_block *block, int budget); int gve_tx_alloc_rings(struct gve_priv *priv); void gve_tx_free_rings_gqi(struct gve_priv *priv); -__be32 gve_tx_load_event_counter(struct gve_priv *priv, - struct gve_tx_ring *tx); +u32 gve_tx_load_event_counter(struct gve_priv *priv, + struct gve_tx_ring *tx); +bool gve_tx_clean_pending(struct gve_priv *priv, struct gve_tx_ring *tx); /* rx handling */ void gve_rx_write_doorbell(struct gve_priv *priv, struct gve_rx_ring *rx); -bool gve_rx_poll(struct gve_notify_block *block, int budget); +int gve_rx_poll(struct gve_notify_block *block, int budget); +bool gve_rx_work_pending(struct gve_rx_ring *rx); int gve_rx_alloc_rings(struct gve_priv *priv); void gve_rx_free_rings_gqi(struct gve_priv *priv); -bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, - netdev_features_t feat); /* Reset */ void gve_schedule_reset(struct gve_priv *priv); int gve_reset(struct gve_priv *priv, bool attempt_teardown); diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index 47c3d8f313fc..3953f6f7a427 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -270,6 +270,7 @@ enum gve_stat_names { TX_LAST_COMPLETION_PROCESSED = 5, RX_NEXT_EXPECTED_SEQUENCE = 6, RX_BUFFERS_POSTED = 7, + TX_TIMEOUT_CNT = 8, // stats from NIC RX_QUEUE_DROP_CNT = 65, RX_NO_BUFFERS_POSTED = 66, diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 716e6240305d..618a3e1d858e 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -330,8 +330,7 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = tmp_tx_bytes; data[i++] = tx->wake_queue; data[i++] = tx->stop_queue; - data[i++] = be32_to_cpu(gve_tx_load_event_counter(priv, - tx)); + data[i++] = gve_tx_load_event_counter(priv, tx); data[i++] = tx->dma_mapping_error; /* stats from NIC */ if (skip_nic_stats) { diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index cd9df68cc01e..7647cd05b1d2 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -24,6 +24,9 @@ #define GVE_VERSION "1.0.0" #define GVE_VERSION_PREFIX "GVE-" +// Minimum amount of time between queue kicks in msec (10 seconds) +#define MIN_TX_TIMEOUT_GAP (1000 * 10) + const char gve_version_str[] = GVE_VERSION; static const char gve_version_prefix[] = GVE_VERSION_PREFIX; @@ -41,6 +44,7 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) { struct gve_priv *priv = netdev_priv(dev); unsigned int start; + u64 packets, bytes; int ring; if (priv->rx) { @@ -48,10 +52,12 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) do { start = u64_stats_fetch_begin(&priv->rx[ring].statss); - s->rx_packets += priv->rx[ring].rpackets; - s->rx_bytes += priv->rx[ring].rbytes; + packets = priv->rx[ring].rpackets; + bytes = priv->rx[ring].rbytes; } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); + s->rx_packets += packets; + s->rx_bytes += bytes; } } if (priv->tx) { @@ -59,10 +65,12 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) do { start = u64_stats_fetch_begin(&priv->tx[ring].statss); - s->tx_packets += priv->tx[ring].pkt_done; - s->tx_bytes += priv->tx[ring].bytes_done; + packets = priv->tx[ring].pkt_done; + bytes = priv->tx[ring].bytes_done; } while (u64_stats_fetch_retry(&priv->tx[ring].statss, start)); + s->tx_packets += packets; + s->tx_bytes += bytes; } } } @@ -82,6 +90,9 @@ static int gve_alloc_counter_array(struct gve_priv *priv) static void gve_free_counter_array(struct gve_priv *priv) { + if (!priv->counter_array) + return; + dma_free_coherent(&priv->pdev->dev, priv->num_event_counters * sizeof(*priv->counter_array), @@ -142,6 +153,9 @@ static int gve_alloc_stats_report(struct gve_priv *priv) static void gve_free_stats_report(struct gve_priv *priv) { + if (!priv->stats_report) + return; + del_timer_sync(&priv->stats_report_timer); dma_free_coherent(&priv->pdev->dev, priv->stats_report_len, priv->stats_report, priv->stats_report_bus); @@ -181,34 +195,40 @@ static int gve_napi_poll(struct napi_struct *napi, int budget) __be32 __iomem *irq_doorbell; bool reschedule = false; struct gve_priv *priv; + int work_done = 0; block = container_of(napi, struct gve_notify_block, napi); priv = block->priv; if (block->tx) reschedule |= gve_tx_poll(block, budget); - if (block->rx) - reschedule |= gve_rx_poll(block, budget); + if (block->rx) { + work_done = gve_rx_poll(block, budget); + reschedule |= work_done == budget; + } if (reschedule) return budget; - napi_complete(napi); - irq_doorbell = gve_irq_doorbell(priv, block); - iowrite32be(GVE_IRQ_ACK | GVE_IRQ_EVENT, irq_doorbell); + /* Complete processing - don't unmask irq if busy polling is enabled */ + if (likely(napi_complete_done(napi, work_done))) { + irq_doorbell = gve_irq_doorbell(priv, block); + iowrite32be(GVE_IRQ_ACK | GVE_IRQ_EVENT, irq_doorbell); - /* Double check we have no extra work. - * Ensure unmask synchronizes with checking for work. - */ - mb(); - if (block->tx) - reschedule |= gve_tx_poll(block, -1); - if (block->rx) - reschedule |= gve_rx_poll(block, -1); - if (reschedule && napi_reschedule(napi)) - iowrite32be(GVE_IRQ_MASK, irq_doorbell); + /* Ensure IRQ ACK is visible before we check pending work. + * If queue had issued updates, it would be truly visible. + */ + mb(); - return 0; + if (block->tx) + reschedule |= gve_tx_clean_pending(priv, block->tx); + if (block->rx) + reschedule |= gve_rx_work_pending(block->rx); + + if (reschedule && napi_reschedule(napi)) + iowrite32be(GVE_IRQ_MASK, irq_doorbell); + } + return work_done; } static int gve_napi_poll_dqo(struct napi_struct *napi, int budget) @@ -370,18 +390,19 @@ static void gve_free_notify_blocks(struct gve_priv *priv) { int i; - if (priv->msix_vectors) { - /* Free the irqs */ - for (i = 0; i < priv->num_ntfy_blks; i++) { - struct gve_notify_block *block = &priv->ntfy_blocks[i]; - int msix_idx = i; + if (!priv->msix_vectors) + return; - irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector, - NULL); - free_irq(priv->msix_vectors[msix_idx].vector, block); - } - free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv); + /* Free the irqs */ + for (i = 0; i < priv->num_ntfy_blks; i++) { + struct gve_notify_block *block = &priv->ntfy_blocks[i]; + int msix_idx = i; + + irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector, + NULL); + free_irq(priv->msix_vectors[msix_idx].vector, block); } + free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv); dma_free_coherent(&priv->pdev->dev, priv->num_ntfy_blks * sizeof(*priv->ntfy_blocks), priv->ntfy_blocks, priv->ntfy_block_bus); @@ -1103,9 +1124,47 @@ static void gve_turnup(struct gve_priv *priv) static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) { - struct gve_priv *priv = netdev_priv(dev); + struct gve_notify_block *block; + struct gve_tx_ring *tx = NULL; + struct gve_priv *priv; + u32 last_nic_done; + u32 current_time; + u32 ntfy_idx; + + netdev_info(dev, "Timeout on tx queue, %d", txqueue); + priv = netdev_priv(dev); + if (txqueue > priv->tx_cfg.num_queues) + goto reset; + + ntfy_idx = gve_tx_idx_to_ntfy(priv, txqueue); + if (ntfy_idx > priv->num_ntfy_blks) + goto reset; + block = &priv->ntfy_blocks[ntfy_idx]; + tx = block->tx; + + current_time = jiffies_to_msecs(jiffies); + if (tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time) + goto reset; + + /* Check to see if there are missed completions, which will allow us to + * kick the queue. + */ + last_nic_done = gve_tx_load_event_counter(priv, tx); + if (last_nic_done - tx->done) { + netdev_info(dev, "Kicking queue %d", txqueue); + iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block)); + napi_schedule(&block->napi); + tx->last_kick_msec = current_time; + goto out; + } // Else reset. + +reset: gve_schedule_reset(priv); + +out: + if (tx) + tx->queue_timeout++; priv->tx_timeo_cnt++; } @@ -1184,9 +1243,10 @@ static void gve_handle_reset(struct gve_priv *priv) void gve_handle_report_stats(struct gve_priv *priv) { - int idx, stats_idx = 0, tx_bytes; - unsigned int start = 0; struct stats *stats = priv->stats_report->stats; + int idx, stats_idx = 0; + unsigned int start = 0; + u64 tx_bytes; if (!gve_get_report_stats(priv)) return; @@ -1233,6 +1293,11 @@ void gve_handle_report_stats(struct gve_priv *priv) .value = cpu_to_be64(last_completion), .queue_id = cpu_to_be32(idx), }; + stats[stats_idx++] = (struct stats) { + .stat_name = cpu_to_be32(TX_TIMEOUT_CNT), + .value = cpu_to_be64(priv->tx[idx].queue_timeout), + .queue_id = cpu_to_be32(idx), + }; } } /* rx stats */ diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index bb8261368250..95bc4d8a1811 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -16,19 +16,23 @@ static void gve_rx_free_buffer(struct device *dev, dma_addr_t dma = (dma_addr_t)(be64_to_cpu(data_slot->addr) & GVE_DATA_SLOT_ADDR_PAGE_MASK); + page_ref_sub(page_info->page, page_info->pagecnt_bias - 1); gve_free_page(dev, page_info->page, dma, DMA_FROM_DEVICE); } static void gve_rx_unfill_pages(struct gve_priv *priv, struct gve_rx_ring *rx) { - if (rx->data.raw_addressing) { - u32 slots = rx->mask + 1; - int i; + u32 slots = rx->mask + 1; + int i; + if (rx->data.raw_addressing) { for (i = 0; i < slots; i++) gve_rx_free_buffer(&priv->pdev->dev, &rx->data.page_info[i], &rx->data.data_ring[i]); } else { + for (i = 0; i < slots; i++) + page_ref_sub(rx->data.page_info[i].page, + rx->data.page_info[i].pagecnt_bias - 1); gve_unassign_qpl(priv, rx->data.qpl->id); rx->data.qpl = NULL; } @@ -69,6 +73,9 @@ static void gve_setup_rx_buffer(struct gve_rx_slot_page_info *page_info, page_info->page_offset = 0; page_info->page_address = page_address(page); *slot_addr = cpu_to_be64(addr); + /* The page already has 1 ref */ + page_ref_add(page, INT_MAX - 1); + page_info->pagecnt_bias = INT_MAX; } static int gve_rx_alloc_buffer(struct gve_priv *priv, struct device *dev, @@ -104,8 +111,14 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx) if (!rx->data.page_info) return -ENOMEM; - if (!rx->data.raw_addressing) + if (!rx->data.raw_addressing) { rx->data.qpl = gve_assign_rx_qpl(priv); + if (!rx->data.qpl) { + kvfree(rx->data.page_info); + rx->data.page_info = NULL; + return -ENOMEM; + } + } for (i = 0; i < slots; i++) { if (!rx->data.raw_addressing) { struct page *page = rx->data.qpl->pages[i]; @@ -289,21 +302,22 @@ static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info, __be64 *sl static bool gve_rx_can_flip_buffers(struct net_device *netdev) { - return PAGE_SIZE == 4096 + return PAGE_SIZE >= 4096 ? netdev->mtu + GVE_RX_PAD + ETH_HLEN <= PAGE_SIZE / 2 : false; } -static int gve_rx_can_recycle_buffer(struct page *page) +static int gve_rx_can_recycle_buffer(struct gve_rx_slot_page_info *page_info) { - int pagecount = page_count(page); + int pagecount = page_count(page_info->page); /* This page is not being used by any SKBs - reuse */ - if (pagecount == 1) + if (pagecount == page_info->pagecnt_bias) return 1; /* This page is still being used by an SKB - we can't reuse */ - else if (pagecount >= 2) + else if (pagecount > page_info->pagecnt_bias) return 0; - WARN(pagecount < 1, "Pagecount should never be < 1"); + WARN(pagecount < page_info->pagecnt_bias, + "Pagecount should never be less than the bias."); return -1; } @@ -319,11 +333,11 @@ gve_rx_raw_addressing(struct device *dev, struct net_device *netdev, if (!skb) return NULL; - /* Optimistically stop the kernel from freeing the page by increasing - * the page bias. We will check the refcount in refill to determine if - * we need to alloc a new page. + /* Optimistically stop the kernel from freeing the page. + * We will check again in refill to determine if we need to alloc a + * new page. */ - get_page(page_info->page); + gve_dec_pagecnt_bias(page_info); return skb; } @@ -346,7 +360,7 @@ gve_rx_qpl(struct device *dev, struct net_device *netdev, /* No point in recycling if we didn't get the skb */ if (skb) { /* Make sure that the page isn't freed. */ - get_page(page_info->page); + gve_dec_pagecnt_bias(page_info); gve_rx_flip_buff(page_info, &data_slot->qpl_offset); } } else { @@ -370,8 +384,18 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, union gve_rx_data_slot *data_slot; struct sk_buff *skb = NULL; dma_addr_t page_bus; + void *va; u16 len; + /* Prefetch two packet pages ahead, we will need it soon. */ + page_info = &rx->data.page_info[(idx + 2) & rx->mask]; + va = page_info->page_address + GVE_RX_PAD + + page_info->page_offset; + + prefetch(page_info->page); /* Kernel page struct. */ + prefetch(va); /* Packet header. */ + prefetch(va + 64); /* Next cacheline too. */ + /* drop this packet */ if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR)) { u64_stats_update_begin(&rx->statss); @@ -402,7 +426,7 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, int recycle = 0; if (can_flip) { - recycle = gve_rx_can_recycle_buffer(page_info->page); + recycle = gve_rx_can_recycle_buffer(page_info); if (recycle < 0) { if (!rx->data.raw_addressing) gve_schedule_reset(priv); @@ -450,7 +474,7 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, return true; } -static bool gve_rx_work_pending(struct gve_rx_ring *rx) +bool gve_rx_work_pending(struct gve_rx_ring *rx) { struct gve_rx_desc *desc; __be16 flags_seq; @@ -493,7 +517,7 @@ static bool gve_rx_refill_buffers(struct gve_priv *priv, struct gve_rx_ring *rx) * owns half the page it is impossible to tell which half. Either * the whole page is free or it needs to be replaced. */ - int recycle = gve_rx_can_recycle_buffer(page_info->page); + int recycle = gve_rx_can_recycle_buffer(page_info); if (recycle < 0) { if (!rx->data.raw_addressing) @@ -508,8 +532,13 @@ static bool gve_rx_refill_buffers(struct gve_priv *priv, struct gve_rx_ring *rx) gve_rx_free_buffer(dev, page_info, data_slot); page_info->page = NULL; - if (gve_rx_alloc_buffer(priv, dev, page_info, data_slot)) + if (gve_rx_alloc_buffer(priv, dev, page_info, + data_slot)) { + u64_stats_update_begin(&rx->statss); + rx->rx_buf_alloc_fail++; + u64_stats_update_end(&rx->statss); break; + } } } fill_cnt++; @@ -518,8 +547,8 @@ static bool gve_rx_refill_buffers(struct gve_priv *priv, struct gve_rx_ring *rx) return true; } -bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, - netdev_features_t feat) +static int gve_clean_rx_done(struct gve_rx_ring *rx, int budget, + netdev_features_t feat) { struct gve_priv *priv = rx->gve; u32 work_done = 0, packets = 0; @@ -540,6 +569,10 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, "[%d] seqno=%d rx->desc.seqno=%d\n", rx->q_num, GVE_SEQNO(desc->flags_seq), rx->desc.seqno); + + /* prefetch two descriptors ahead */ + prefetch(rx->desc.desc_ring + ((cnt + 2) & rx->mask)); + dropped = !gve_rx(rx, desc, feat, idx); if (!dropped) { bytes += be16_to_cpu(desc->len) - GVE_RX_PAD; @@ -553,13 +586,15 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, } if (!work_done && rx->fill_cnt - cnt > rx->db_threshold) - return false; + return 0; - u64_stats_update_begin(&rx->statss); - rx->rpackets += packets; - rx->rbytes += bytes; - u64_stats_update_end(&rx->statss); - rx->cnt = cnt; + if (work_done) { + u64_stats_update_begin(&rx->statss); + rx->rpackets += packets; + rx->rbytes += bytes; + u64_stats_update_end(&rx->statss); + rx->cnt = cnt; + } /* restock ring slots */ if (!rx->data.raw_addressing) { @@ -570,26 +605,26 @@ bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, * falls below a threshold. */ if (!gve_rx_refill_buffers(priv, rx)) - return false; + return 0; /* If we were not able to completely refill buffers, we'll want * to schedule this queue for work again to refill buffers. */ if (rx->fill_cnt - cnt <= rx->db_threshold) { gve_rx_write_doorbell(priv, rx); - return true; + return budget; } } gve_rx_write_doorbell(priv, rx); - return gve_rx_work_pending(rx); + return work_done; } -bool gve_rx_poll(struct gve_notify_block *block, int budget) +int gve_rx_poll(struct gve_notify_block *block, int budget) { struct gve_rx_ring *rx = block->rx; netdev_features_t feat; - bool repoll = false; + int work_done = 0; feat = block->napi.dev->features; @@ -598,8 +633,7 @@ bool gve_rx_poll(struct gve_notify_block *block, int budget) budget = INT_MAX; if (budget > 0) - repoll |= gve_clean_rx_done(rx, budget, feat); - else - repoll |= gve_rx_work_pending(rx); - return repoll; + work_done = gve_clean_rx_done(rx, budget, feat); + + return work_done; } diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 9922ce46a635..a9cb241fedf4 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -144,7 +144,7 @@ static void gve_tx_free_ring(struct gve_priv *priv, int idx) gve_tx_remove_from_block(priv, idx); slots = tx->mask + 1; - gve_clean_tx_done(priv, tx, tx->req, false); + gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); netdev_tx_reset_queue(tx->netdev_txq); dma_free_coherent(hdev, sizeof(*tx->q_resources), @@ -176,6 +176,7 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) /* Make sure everything is zeroed to start */ memset(tx, 0, sizeof(*tx)); + spin_lock_init(&tx->clean_lock); tx->q_num = idx; tx->mask = slots - 1; @@ -328,10 +329,16 @@ static inline bool gve_can_tx(struct gve_tx_ring *tx, int bytes_required) return (gve_tx_avail(tx) >= MAX_TX_DESC_NEEDED && can_alloc); } +static_assert(NAPI_POLL_WEIGHT >= MAX_TX_DESC_NEEDED); + /* Stops the queue if the skb cannot be transmitted. */ -static int gve_maybe_stop_tx(struct gve_tx_ring *tx, struct sk_buff *skb) +static int gve_maybe_stop_tx(struct gve_priv *priv, struct gve_tx_ring *tx, + struct sk_buff *skb) { int bytes_required = 0; + u32 nic_done; + u32 to_do; + int ret; if (!tx->raw_addressing) bytes_required = gve_skb_fifo_bytes_required(tx, skb); @@ -339,29 +346,28 @@ static int gve_maybe_stop_tx(struct gve_tx_ring *tx, struct sk_buff *skb) if (likely(gve_can_tx(tx, bytes_required))) return 0; - /* No space, so stop the queue */ - tx->stop_queue++; - netif_tx_stop_queue(tx->netdev_txq); - smp_mb(); /* sync with restarting queue in gve_clean_tx_done() */ - - /* Now check for resources again, in case gve_clean_tx_done() freed - * resources after we checked and we stopped the queue after - * gve_clean_tx_done() checked. - * - * gve_maybe_stop_tx() gve_clean_tx_done() - * nsegs/can_alloc test failed - * gve_tx_free_fifo() - * if (tx queue stopped) - * netif_tx_queue_wake() - * netif_tx_stop_queue() - * Need to check again for space here! - */ - if (likely(!gve_can_tx(tx, bytes_required))) - return -EBUSY; + ret = -EBUSY; + spin_lock(&tx->clean_lock); + nic_done = gve_tx_load_event_counter(priv, tx); + to_do = nic_done - tx->done; - netif_tx_start_queue(tx->netdev_txq); - tx->wake_queue++; - return 0; + /* Only try to clean if there is hope for TX */ + if (to_do + gve_tx_avail(tx) >= MAX_TX_DESC_NEEDED) { + if (to_do > 0) { + to_do = min_t(u32, to_do, NAPI_POLL_WEIGHT); + gve_clean_tx_done(priv, tx, to_do, false); + } + if (likely(gve_can_tx(tx, bytes_required))) + ret = 0; + } + if (ret) { + /* No space, so stop the queue */ + tx->stop_queue++; + netif_tx_stop_queue(tx->netdev_txq); + } + spin_unlock(&tx->clean_lock); + + return ret; } static void gve_tx_fill_pkt_desc(union gve_tx_desc *pkt_desc, @@ -576,7 +582,7 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev) WARN(skb_get_queue_mapping(skb) >= priv->tx_cfg.num_queues, "skb queue index out of range"); tx = &priv->tx[skb_get_queue_mapping(skb)]; - if (unlikely(gve_maybe_stop_tx(tx, skb))) { + if (unlikely(gve_maybe_stop_tx(priv, tx, skb))) { /* We need to ring the txq doorbell -- we have stopped the Tx * queue for want of resources, but prior calls to gve_tx() * may have added descriptors without ringing the doorbell. @@ -672,19 +678,19 @@ static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx, return pkts; } -__be32 gve_tx_load_event_counter(struct gve_priv *priv, - struct gve_tx_ring *tx) +u32 gve_tx_load_event_counter(struct gve_priv *priv, + struct gve_tx_ring *tx) { - u32 counter_index = be32_to_cpu((tx->q_resources->counter_index)); + u32 counter_index = be32_to_cpu(tx->q_resources->counter_index); + __be32 counter = READ_ONCE(priv->counter_array[counter_index]); - return READ_ONCE(priv->counter_array[counter_index]); + return be32_to_cpu(counter); } bool gve_tx_poll(struct gve_notify_block *block, int budget) { struct gve_priv *priv = block->priv; struct gve_tx_ring *tx = block->tx; - bool repoll = false; u32 nic_done; u32 to_do; @@ -692,17 +698,23 @@ bool gve_tx_poll(struct gve_notify_block *block, int budget) if (budget == 0) budget = INT_MAX; + /* In TX path, it may try to clean completed pkts in order to xmit, + * to avoid cleaning conflict, use spin_lock(), it yields better + * concurrency between xmit/clean than netif's lock. + */ + spin_lock(&tx->clean_lock); /* Find out how much work there is to be done */ - tx->last_nic_done = gve_tx_load_event_counter(priv, tx); - nic_done = be32_to_cpu(tx->last_nic_done); - if (budget > 0) { - /* Do as much work as we have that the budget will - * allow - */ - to_do = min_t(u32, (nic_done - tx->done), budget); - gve_clean_tx_done(priv, tx, to_do, true); - } + nic_done = gve_tx_load_event_counter(priv, tx); + to_do = min_t(u32, (nic_done - tx->done), budget); + gve_clean_tx_done(priv, tx, to_do, true); + spin_unlock(&tx->clean_lock); /* If we still have work we want to repoll */ - repoll |= (nic_done != tx->done); - return repoll; + return nic_done != tx->done; +} + +bool gve_tx_clean_pending(struct gve_priv *priv, struct gve_tx_ring *tx) +{ + u32 nic_done = gve_tx_load_event_counter(priv, tx); + + return nic_done != tx->done; } diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c index 93f3dcbeeea9..45ff7a9ab5f9 100644 --- a/drivers/net/ethernet/google/gve/gve_utils.c +++ b/drivers/net/ethernet/google/gve/gve_utils.c @@ -18,12 +18,16 @@ void gve_tx_remove_from_block(struct gve_priv *priv, int queue_idx) void gve_tx_add_to_block(struct gve_priv *priv, int queue_idx) { + unsigned int active_cpus = min_t(int, priv->num_ntfy_blks / 2, + num_online_cpus()); int ntfy_idx = gve_tx_idx_to_ntfy(priv, queue_idx); struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; struct gve_tx_ring *tx = &priv->tx[queue_idx]; block->tx = tx; tx->ntfy_id = ntfy_idx; + netif_set_xps_queue(priv->dev, get_cpu_mask(ntfy_idx % active_cpus), + queue_idx); } void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx) diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 37b605fed32c..c84ef494bd60 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -998,7 +998,7 @@ static int hip04_mac_probe(struct platform_device *pdev) hip04_config_port(ndev, SPEED_100, DUPLEX_FULL); hip04_config_fifo(priv); - eth_random_addr(ndev->dev_addr); + eth_hw_addr_random(ndev); hip04_update_mac_address(ndev); ret = hip04_alloc_ring(ndev, d); diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c index 29190eb890c8..a6c18b6527f9 100644 --- a/drivers/net/ethernet/hisilicon/hisi_femac.c +++ b/drivers/net/ethernet/hisilicon/hisi_femac.c @@ -427,7 +427,7 @@ static void hisi_femac_free_skb_rings(struct hisi_femac_priv *priv) } static int hisi_femac_set_hw_mac_addr(struct hisi_femac_priv *priv, - unsigned char *mac) + const unsigned char *mac) { u32 reg; diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index 5f7ccdc834b7..d7e62eca050f 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -429,7 +429,7 @@ static void hix5hd2_port_disable(struct hix5hd2_priv *priv) static void hix5hd2_hw_set_mac_addr(struct net_device *dev) { struct hix5hd2_priv *priv = netdev_priv(dev); - unsigned char *mac = dev->dev_addr; + const unsigned char *mac = dev->dev_addr; u32 val; val = mac[1] | (mac[0] << 8); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index 2b7db1c22321..d72657444ef3 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -499,7 +499,7 @@ struct hnae_ae_ops { u32 *tx_usecs_high, u32 *rx_usecs_high); void (*set_promisc_mode)(struct hnae_handle *handle, u32 en); int (*get_mac_addr)(struct hnae_handle *handle, void **p); - int (*set_mac_addr)(struct hnae_handle *handle, void *p); + int (*set_mac_addr)(struct hnae_handle *handle, const void *p); int (*add_uc_addr)(struct hnae_handle *handle, const unsigned char *addr); int (*rm_uc_addr)(struct hnae_handle *handle, @@ -558,7 +558,7 @@ struct hnae_handle { enum hnae_media_type media_type; struct list_head node; /* list to hnae_ae_dev->handle_list */ struct hnae_buf_ops *bops; /* operation for the buffer */ - struct hnae_queue **qs; /* array base of all queues */ + struct hnae_queue *qs[]; /* flexible array of all queues */ }; #define ring_to_dev(ring) ((ring)->q->dev->dev) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index 75e4ec569da8..bc3e406f0139 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -81,8 +81,8 @@ static struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev, vfnum_per_port = hns_ae_get_vf_num_per_port(dsaf_dev, port_id); qnum_per_vf = hns_ae_get_q_num_per_vf(dsaf_dev, port_id); - vf_cb = kzalloc(sizeof(*vf_cb) + - qnum_per_vf * sizeof(struct hnae_queue *), GFP_KERNEL); + vf_cb = kzalloc(struct_size(vf_cb, ae_handle.qs, qnum_per_vf), + GFP_KERNEL); if (unlikely(!vf_cb)) { dev_err(dsaf_dev->dev, "malloc vf_cb fail!\n"); ae_handle = ERR_PTR(-ENOMEM); @@ -108,7 +108,6 @@ static struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev, goto vf_id_err; } - ae_handle->qs = (struct hnae_queue **)(&ae_handle->qs + 1); for (i = 0; i < qnum_per_vf; i++) { ae_handle->qs[i] = &ring_pair_cb->q; ae_handle->qs[i]->rx_ring.q = ae_handle->qs[i]; @@ -207,7 +206,7 @@ static void hns_ae_fini_queue(struct hnae_queue *q) hns_rcb_reset_ring_hw(q); } -static int hns_ae_set_mac_address(struct hnae_handle *handle, void *p) +static int hns_ae_set_mac_address(struct hnae_handle *handle, const void *p) { int ret; struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index f387a859a201..8f391e2adcc0 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -450,7 +450,7 @@ static void hns_gmac_update_stats(void *mac_drv) += dsaf_read_dev(drv, GMAC_TX_PAUSE_FRAMES_REG); } -static void hns_gmac_set_mac_addr(void *mac_drv, char *mac_addr) +static void hns_gmac_set_mac_addr(void *mac_drv, const char *mac_addr) { struct mac_driver *drv = (struct mac_driver *)mac_drv; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index f41379de2186..7edf8569514c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -240,7 +240,7 @@ int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb, u8 vmid, u8 *port_num) *@addr:mac address */ int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, - u32 vmid, char *addr) + u32 vmid, const char *addr) { int ret; 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 8943ffab4418..e3bb05959ba9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h @@ -348,7 +348,7 @@ struct mac_driver { /*disable mac when disable nic or dsaf*/ void (*mac_disable)(void *mac_drv, enum mac_commom_mode mode); /* config mac address*/ - void (*set_mac_addr)(void *mac_drv, char *mac_addr); + void (*set_mac_addr)(void *mac_drv, const char *mac_addr); /*adjust mac mode of port,include speed and duplex*/ int (*adjust_link)(void *mac_drv, enum mac_speed speed, u32 full_duplex); @@ -425,7 +425,8 @@ int hns_mac_init(struct dsaf_device *dsaf_dev); void mac_adjust_link(struct net_device *net_dev); bool hns_mac_need_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex); void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status); -int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, u32 vmid, char *addr); +int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, u32 vmid, + const char *addr); int hns_mac_set_multi(struct hns_mac_cb *mac_cb, u32 port_num, char *addr, bool enable); int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vm, bool enable); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index cba04bfa0b3f..5526a10caac5 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -210,7 +210,7 @@ struct hnae_vf_cb { u8 port_index; struct hns_mac_cb *mac_cb; struct dsaf_device *dsaf_dev; - struct hnae_handle ae_handle; /* must be the last number */ + struct hnae_handle ae_handle; /* must be the last member */ }; struct dsaf_int_xge_src { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c index 401fef5f1d07..fc26ffaae620 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c @@ -255,7 +255,7 @@ static void hns_xgmac_pausefrm_cfg(void *mac_drv, u32 rx_en, u32 tx_en) dsaf_write_dev(drv, XGMAC_MAC_PAUSE_CTRL_REG, origin); } -static void hns_xgmac_set_pausefrm_mac_addr(void *mac_drv, char *mac_addr) +static void hns_xgmac_set_pausefrm_mac_addr(void *mac_drv, const char *mac_addr) { struct mac_driver *drv = (struct mac_driver *)mac_drv; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 17872c50b63c..98d63e804903 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -298,6 +298,7 @@ enum hnae3_dbg_cmd { HNAE3_DBG_CMD_MAC_TNL_STATUS, HNAE3_DBG_CMD_SERV_INFO, HNAE3_DBG_CMD_UMV_INFO, + HNAE3_DBG_CMD_PAGE_POOL_INFO, HNAE3_DBG_CMD_UNKNOWN, }; @@ -594,7 +595,7 @@ struct hnae3_ae_ops { u32 *tx_usecs_high, u32 *rx_usecs_high); void (*get_mac_addr)(struct hnae3_handle *handle, u8 *p); - int (*set_mac_addr)(struct hnae3_handle *handle, void *p, + int (*set_mac_addr)(struct hnae3_handle *handle, const void *p, bool is_first); int (*do_ioctl)(struct hnae3_handle *handle, struct ifreq *ifr, int cmd); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index a1555f074e06..b26d43c9c088 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -336,6 +336,13 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .buf_len = HNS3_DBG_READ_LEN, .init = hns3_dbg_common_file_init, }, + { + .name = "page_pool_info", + .cmd = HNAE3_DBG_CMD_PAGE_POOL_INFO, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, }; static struct hns3_dbg_cap_info hns3_dbg_cap[] = { @@ -941,6 +948,69 @@ static int hns3_dbg_dev_info(struct hnae3_handle *h, char *buf, int len) return 0; } +static const struct hns3_dbg_item page_pool_info_items[] = { + { "QUEUE_ID", 2 }, + { "ALLOCATE_CNT", 2 }, + { "FREE_CNT", 6 }, + { "POOL_SIZE(PAGE_NUM)", 2 }, + { "ORDER", 2 }, + { "NUMA_ID", 2 }, + { "MAX_LEN", 2 }, +}; + +static void hns3_dump_page_pool_info(struct hns3_enet_ring *ring, + char **result, u32 index) +{ + u32 j = 0; + + sprintf(result[j++], "%u", index); + sprintf(result[j++], "%u", ring->page_pool->pages_state_hold_cnt); + sprintf(result[j++], "%u", + atomic_read(&ring->page_pool->pages_state_release_cnt)); + sprintf(result[j++], "%u", ring->page_pool->p.pool_size); + sprintf(result[j++], "%u", ring->page_pool->p.order); + sprintf(result[j++], "%d", ring->page_pool->p.nid); + sprintf(result[j++], "%uK", ring->page_pool->p.max_len / 1024); +} + +static int +hns3_dbg_page_pool_info(struct hnae3_handle *h, char *buf, int len) +{ + char data_str[ARRAY_SIZE(page_pool_info_items)][HNS3_DBG_DATA_STR_LEN]; + char *result[ARRAY_SIZE(page_pool_info_items)]; + struct hns3_nic_priv *priv = h->priv; + char content[HNS3_DBG_INFO_LEN]; + struct hns3_enet_ring *ring; + int pos = 0; + u32 i; + + if (!priv->ring) { + dev_err(&h->pdev->dev, "priv->ring is NULL\n"); + return -EFAULT; + } + + for (i = 0; i < ARRAY_SIZE(page_pool_info_items); i++) + result[i] = &data_str[i][0]; + + hns3_dbg_fill_content(content, sizeof(content), page_pool_info_items, + NULL, ARRAY_SIZE(page_pool_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + for (i = 0; i < h->kinfo.num_tqps; i++) { + if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || + test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) + return -EPERM; + ring = &priv->ring[(u32)(i + h->kinfo.num_tqps)]; + hns3_dump_page_pool_info(ring, result, i); + hns3_dbg_fill_content(content, sizeof(content), + page_pool_info_items, + (const char **)result, + ARRAY_SIZE(page_pool_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + } + + return 0; +} + static int hns3_dbg_get_cmd_index(struct hns3_dbg_data *dbg_data, u32 *index) { u32 i; @@ -982,6 +1052,10 @@ static const struct hns3_dbg_func hns3_dbg_cmd_func[] = { .cmd = HNAE3_DBG_CMD_TX_QUEUE_INFO, .dbg_dump = hns3_dbg_tx_queue_info, }, + { + .cmd = HNAE3_DBG_CMD_PAGE_POOL_INFO, + .dbg_dump = hns3_dbg_page_pool_info, + }, }; static int hns3_dbg_read_cmd(struct hns3_dbg_data *dbg_data, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c index 59b0ae7d59e0..4c441e6a5082 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c @@ -119,8 +119,8 @@ int hclge_devlink_init(struct hclge_dev *hdev) priv->hdev = hdev; hdev->devlink = devlink; + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); - devlink_reload_enable(devlink); return 0; } @@ -128,8 +128,6 @@ void hclge_devlink_uninit(struct hclge_dev *hdev) { struct devlink *devlink = hdev->devlink; - devlink_reload_disable(devlink); - devlink_unregister(devlink); devlink_free(devlink); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index cd981b33d4ff..7bb34af3981e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9442,7 +9442,7 @@ int hclge_update_mac_node_for_dev_addr(struct hclge_vport *vport, return 0; } -static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p, +static int hclge_set_mac_addr(struct hnae3_handle *handle, const void *p, bool is_first) { const unsigned char *new_addr = (const unsigned char *)p; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c index d60cc9426f70..fdc19868b818 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c @@ -121,8 +121,8 @@ int hclgevf_devlink_init(struct hclgevf_dev *hdev) priv->hdev = hdev; hdev->devlink = devlink; + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); - devlink_reload_enable(devlink); return 0; } @@ -130,8 +130,6 @@ void hclgevf_devlink_uninit(struct hclgevf_dev *hdev) { struct devlink *devlink = hdev->devlink; - devlink_reload_disable(devlink); - devlink_unregister(devlink); devlink_free(devlink); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 5fdac8685f95..2e6dcf75fba6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1349,7 +1349,7 @@ static void hclgevf_get_mac_addr(struct hnae3_handle *handle, u8 *p) ether_addr_copy(p, hdev->hw.mac.mac_addr); } -static int hclgevf_set_mac_addr(struct hnae3_handle *handle, void *p, +static int hclgevf_set_mac_addr(struct hnae3_handle *handle, const void *p, bool is_first) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 6414e922cf8c..f9a766b8ac43 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -1181,6 +1181,7 @@ static int nic_dev_init(struct pci_dev *pdev) struct net_device *netdev; struct hinic_hwdev *hwdev; struct devlink *devlink; + u8 addr[ETH_ALEN]; int err, num_qps; devlink = hinic_devlink_alloc(&pdev->dev); @@ -1259,11 +1260,12 @@ static int nic_dev_init(struct pci_dev *pdev) pci_set_drvdata(pdev, netdev); - err = hinic_port_get_mac(nic_dev, netdev->dev_addr); + err = hinic_port_get_mac(nic_dev, addr); if (err) { dev_err(&pdev->dev, "Failed to get mac address\n"); goto err_get_mac; } + eth_hw_addr_set(netdev, addr); if (!is_valid_ether_addr(netdev->dev_addr)) { if (!HINIC_IS_VF(nic_dev->hwdev->hwif)) { diff --git a/drivers/net/ethernet/i825xx/sun3_82586.c b/drivers/net/ethernet/i825xx/sun3_82586.c index 0696f723228a..3909c6a0af89 100644 --- a/drivers/net/ethernet/i825xx/sun3_82586.c +++ b/drivers/net/ethernet/i825xx/sun3_82586.c @@ -339,14 +339,13 @@ static const struct net_device_ops sun3_82586_netdev_ops = { static int __init sun3_82586_probe1(struct net_device *dev,int ioaddr) { - int i, size, retval; + int size, retval; if (!request_region(ioaddr, SUN3_82586_TOTAL_SIZE, DRV_NAME)) return -EBUSY; /* copy in the ethernet address from the prom */ - for(i = 0; i < 6 ; i++) - dev->dev_addr[i] = idprom->id_ethaddr[i]; + eth_hw_addr_set(dev, idprom->id_ethaddr); printk("%s: SUN3 Intel 82586 found at %lx, ",dev->name,dev->base_addr); @@ -461,7 +460,7 @@ static int init586(struct net_device *dev) ias_cmd->cmd_cmd = swab16(CMD_IASETUP | CMD_LAST); ias_cmd->cmd_link = 0xffff; - memcpy((char *)&ias_cmd->iaddr,(char *) dev->dev_addr,ETH_ALEN); + memcpy((char *)&ias_cmd->iaddr,(const char *) dev->dev_addr,ETH_ALEN); p->scb->cbl_offset = make16(ias_cmd); diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 8db0ec38bbee..6b3fc8823c54 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2975,7 +2975,7 @@ static int emac_init_config(struct emac_instance *dev) } /* Read MAC-address */ - err = of_get_mac_address(np, dev->ndev->dev_addr); + err = of_get_ethdev_address(np, dev->ndev); if (err) { if (err != -EPROBE_DEFER) dev_err(&dev->ofdev->dev, "Can't get valid [local-]mac-address from OF !\n"); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 836617fb3f40..45ba40cf4d07 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -483,17 +483,6 @@ retry: return rc; } -static u64 ibmveth_encode_mac_addr(u8 *mac) -{ - int i; - u64 encoded = 0; - - for (i = 0; i < ETH_ALEN; i++) - encoded = (encoded << 8) | mac[i]; - - return encoded; -} - static int ibmveth_open(struct net_device *netdev) { struct ibmveth_adapter *adapter = netdev_priv(netdev); @@ -553,7 +542,7 @@ static int ibmveth_open(struct net_device *netdev) adapter->rx_queue.num_slots = rxq_entries; adapter->rx_queue.toggle = 1; - mac_address = ibmveth_encode_mac_addr(netdev->dev_addr); + mac_address = ether_addr_to_u64(netdev->dev_addr); rxq_desc.fields.flags_len = IBMVETH_BUF_VALID | adapter->rx_queue.queue_len; @@ -1476,7 +1465,7 @@ static void ibmveth_set_multicast_list(struct net_device *netdev) netdev_for_each_mc_addr(ha, netdev) { /* add the multicast address to the filter table */ u64 mcast_addr; - mcast_addr = ibmveth_encode_mac_addr(ha->addr); + mcast_addr = ether_addr_to_u64(ha->addr); lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address, IbmVethMcastAddFilter, mcast_addr); @@ -1606,7 +1595,7 @@ static int ibmveth_set_mac_addr(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - mac_address = ibmveth_encode_mac_addr(addr->sa_data); + mac_address = ether_addr_to_u64(addr->sa_data); rc = h_change_logical_lan_mac(adapter->vdev->unit_address, mac_address); if (rc) { netdev_err(adapter->netdev, "h_change_logical_lan_mac failed with rc=%d\n", rc); diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index ed8ea63bb172..0b274d8fa45b 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -313,6 +313,20 @@ config ICE To compile this driver as a module, choose M here. The module will be called ice. +config ICE_SWITCHDEV + bool "Switchdev Support" + default y + depends on ICE && NET_SWITCHDEV + help + Switchdev support provides internal SRIOV packet steering and switching. + + To enable it on running kernel use devlink tool: + #devlink dev eswitch set pci/0000:XX:XX.X mode switchdev + + Say Y here if you want to use Switchdev in the driver. + + If unsure, say N. + config FM10K tristate "Intel(R) FM10000 Ethernet Switch Host Interface Support" default n diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 39fb3d57c057..3d528fba754b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -435,7 +435,7 @@ static inline bool i40e_is_channel_macvlan(struct i40e_channel *ch) return !!ch->fwd; } -static inline u8 *i40e_channel_mac(struct i40e_channel *ch) +static inline const u8 *i40e_channel_mac(struct i40e_channel *ch) { if (i40e_is_channel_macvlan(ch)) return ch->fwd->netdev->dev_addr; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f3a1d72538fb..ba862131b9bd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4871,7 +4871,8 @@ static void i40e_clear_interrupt_scheme(struct i40e_pf *pf) { int i; - i40e_free_misc_vector(pf); + if (test_bit(__I40E_MISC_IRQ_REQUESTED, pf->state)) + i40e_free_misc_vector(pf); i40e_put_lump(pf->irq_pile, pf->iwarp_base_vector, I40E_IWARP_IRQ_PILE_ID); @@ -10113,7 +10114,7 @@ static int i40e_get_capabilities(struct i40e_pf *pf, if (pf->hw.aq.asq_last_status == I40E_AQ_RC_ENOMEM) { /* retry with a larger buffer */ buf_len = data_size; - } else if (pf->hw.aq.asq_last_status != I40E_AQ_RC_OK) { + } else if (pf->hw.aq.asq_last_status != I40E_AQ_RC_OK || err) { dev_info(&pf->pdev->dev, "capability discovery failed, err %s aq_err %s\n", i40e_stat_str(&pf->hw, err), diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 7f812abe5abe..ca4712a73574 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1965,7 +1965,6 @@ static void iavf_watchdog_task(struct work_struct *work) } adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; - mutex_unlock(&adapter->crit_lock); queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(10)); diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 4f538cdf42c1..c36faa7d1471 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -26,10 +26,13 @@ ice-y := ice_main.o \ ice_devlink.o \ ice_fw_update.o \ ice_lag.o \ - ice_ethtool.o + ice_ethtool.o \ + ice_repr.o \ + ice_tc_lib.o ice-$(CONFIG_PCI_IOV) += ice_virtchnl_allowlist.o ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o ice_virtchnl_fdir.o ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o +ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 83413772b00c..80f14886b5b1 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -63,6 +63,8 @@ #include "ice_fdir.h" #include "ice_xsk.h" #include "ice_arfs.h" +#include "ice_repr.h" +#include "ice_eswitch.h" #include "ice_lag.h" #define ICE_BAR0 0 @@ -84,6 +86,7 @@ #define ICE_FDIR_MSIX 2 #define ICE_RDMA_NUM_AEQ_MSIX 4 #define ICE_MIN_RDMA_MSIX 2 +#define ICE_ESWITCH_MSIX 1 #define ICE_NO_VSI 0xffff #define ICE_VSI_MAP_CONTIG 0 #define ICE_VSI_MAP_SCATTER 1 @@ -122,10 +125,13 @@ #define ice_for_each_vsi(pf, i) \ for ((i) = 0; (i) < (pf)->num_alloc_vsi; (i)++) -/* Macros for each Tx/Rx ring in a VSI */ +/* Macros for each Tx/Xdp/Rx ring in a VSI */ #define ice_for_each_txq(vsi, i) \ for ((i) = 0; (i) < (vsi)->num_txq; (i)++) +#define ice_for_each_xdp_txq(vsi, i) \ + for ((i) = 0; (i) < (vsi)->num_xdp_txq; (i)++) + #define ice_for_each_rxq(vsi, i) \ for ((i) = 0; (i) < (vsi)->num_rxq; (i)++) @@ -160,9 +166,12 @@ enum ice_feature { ICE_F_DSCP, + ICE_F_SMA_CTRL, ICE_F_MAX }; +DECLARE_STATIC_KEY_FALSE(ice_xdp_locking_key); + struct ice_txq_meta { u32 q_teid; /* Tx-scheduler element identifier */ u16 q_id; /* Entry in VSI's txq_map bitmap */ @@ -271,8 +280,8 @@ struct ice_vsi { struct ice_sw *vsw; /* switch this VSI is on */ struct ice_pf *back; /* back pointer to PF */ struct ice_port_info *port_info; /* back pointer to port_info */ - struct ice_ring **rx_rings; /* Rx ring array */ - struct ice_ring **tx_rings; /* Tx ring array */ + struct ice_rx_ring **rx_rings; /* Rx ring array */ + struct ice_tx_ring **tx_rings; /* Tx ring array */ struct ice_q_vector **q_vectors; /* q_vector array */ irqreturn_t (*irq_handler)(int irq, void *data); @@ -311,10 +320,6 @@ struct ice_vsi { spinlock_t arfs_lock; /* protects aRFS hash table and filter state */ atomic_t *arfs_last_fltr_id; - /* devlink port data */ - struct devlink_port devlink_port; - bool devlink_port_registered; - u16 max_frame; u16 rx_buf_len; @@ -349,11 +354,13 @@ struct ice_vsi { u16 qset_handle[ICE_MAX_TRAFFIC_CLASS]; struct ice_tc_cfg tc_cfg; struct bpf_prog *xdp_prog; - struct ice_ring **xdp_rings; /* XDP ring array */ + struct ice_tx_ring **xdp_rings; /* XDP ring array */ unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */ u16 num_xdp_txq; /* Used XDP queues */ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ + struct net_device **target_netdevs; + /* setup back reference, to which aggregator node this VSI * corresponds to */ @@ -400,6 +407,7 @@ enum ice_pf_flags { ICE_FLAG_PTP, /* PTP is enabled by software */ ICE_FLAG_AUX_ENA, ICE_FLAG_ADV_FEATURES, + ICE_FLAG_CLS_FLOWER, ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, ICE_FLAG_TOTAL_PORT_SHUTDOWN_ENA, ICE_FLAG_NO_MEDIA, @@ -413,6 +421,12 @@ enum ice_pf_flags { ICE_PF_FLAGS_NBITS /* must be last */ }; +struct ice_switchdev_info { + struct ice_vsi *control_vsi; + struct ice_vsi *uplink_vsi; + bool is_running; +}; + struct ice_agg_node { u32 agg_id; #define ICE_MAX_VSIS_IN_AGG_NODE 64 @@ -426,6 +440,9 @@ struct ice_pf { struct devlink_region *nvm_region; struct devlink_region *devcaps_region; + /* devlink port data */ + struct devlink_port devlink_port; + /* OS reserved IRQ details */ struct msix_entry *msix_entries; struct ice_res_tracker *irq_tracker; @@ -439,6 +456,7 @@ struct ice_pf { struct ice_vsi **vsi; /* VSIs created by the driver */ struct ice_sw *first_sw; /* first switch created by firmware */ + u16 eswitch_mode; /* current mode of eswitch */ /* Virtchnl/SR-IOV config info */ struct ice_vf *vf; u16 num_alloc_vfs; /* actual number of VFs allocated */ @@ -502,11 +520,15 @@ struct ice_pf { int aux_idx; u32 sw_int_count; + struct hlist_head tc_flower_fltr_list; + __le64 nvm_phy_type_lo; /* NVM PHY type low */ __le64 nvm_phy_type_hi; /* NVM PHY type high */ struct ice_link_default_override_tlv link_dflt_override; struct ice_lag *lag; /* Link Aggregation information */ + struct ice_switchdev_info switchdev; + #define ICE_INVALID_AGG_NODE_ID 0 #define ICE_PF_AGG_NODE_ID_START 1 #define ICE_MAX_PF_AGG_NODES 32 @@ -518,6 +540,7 @@ struct ice_pf { struct ice_netdev_priv { struct ice_vsi *vsi; + struct ice_repr *repr; }; /** @@ -562,25 +585,42 @@ static inline bool ice_is_xdp_ena_vsi(struct ice_vsi *vsi) return !!vsi->xdp_prog; } -static inline void ice_set_ring_xdp(struct ice_ring *ring) +static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) { ring->flags |= ICE_TX_FLAGS_RING_XDP; } /** * ice_xsk_pool - get XSK buffer pool bound to a ring - * @ring: ring to use + * @ring: Rx ring to use * * Returns a pointer to xdp_umem structure if there is a buffer pool present, * NULL otherwise. */ -static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_ring *ring) +static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring) { struct ice_vsi *vsi = ring->vsi; u16 qid = ring->q_index; - if (ice_ring_is_xdp(ring)) - qid -= vsi->num_xdp_txq; + if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) + return NULL; + + return xsk_get_pool_from_qid(vsi->netdev, qid); +} + +/** + * ice_tx_xsk_pool - get XSK buffer pool bound to a ring + * @ring: Tx ring to use + * + * Returns a pointer to xdp_umem structure if there is a buffer pool present, + * NULL otherwise. Tx equivalent of ice_xsk_pool. + */ +static inline struct xsk_buff_pool *ice_tx_xsk_pool(struct ice_tx_ring *ring) +{ + struct ice_vsi *vsi = ring->vsi; + u16 qid; + + qid = ring->q_index - vsi->num_xdp_txq; if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) return NULL; @@ -603,6 +643,19 @@ static inline struct ice_vsi *ice_get_main_vsi(struct ice_pf *pf) } /** + * ice_get_netdev_priv_vsi - return VSI associated with netdev priv. + * @np: private netdev structure + */ +static inline struct ice_vsi *ice_get_netdev_priv_vsi(struct ice_netdev_priv *np) +{ + /* In case of port representor return source port VSI. */ + if (np->repr) + return np->repr->src_vsi; + else + return np->vsi; +} + +/** * ice_get_ctrl_vsi - Get the control VSI * @pf: PF instance */ @@ -616,6 +669,18 @@ static inline struct ice_vsi *ice_get_ctrl_vsi(struct ice_pf *pf) } /** + * ice_is_switchdev_running - check if switchdev is configured + * @pf: pointer to PF structure + * + * Returns true if eswitch mode is set to DEVLINK_ESWITCH_MODE_SWITCHDEV + * and switchdev is configured, false otherwise. + */ +static inline bool ice_is_switchdev_running(struct ice_pf *pf) +{ + return pf->switchdev.is_running; +} + +/** * ice_set_sriov_cap - enable SRIOV in PF flags * @pf: PF struct */ @@ -643,7 +708,9 @@ bool netif_is_ice(struct net_device *dev); int ice_vsi_setup_tx_rings(struct ice_vsi *vsi); int ice_vsi_setup_rx_rings(struct ice_vsi *vsi); int ice_vsi_open_ctrl(struct ice_vsi *vsi); +int ice_vsi_open(struct ice_vsi *vsi); void ice_set_ethtool_ops(struct net_device *netdev); +void ice_set_ethtool_repr_ops(struct net_device *netdev); void ice_set_ethtool_safe_mode_ops(struct net_device *netdev); u16 ice_get_avail_txq_count(struct ice_pf *pf); u16 ice_get_avail_rxq_count(struct ice_pf *pf); @@ -654,6 +721,7 @@ int ice_up(struct ice_vsi *vsi); int ice_down(struct ice_vsi *vsi); int ice_vsi_cfg(struct ice_vsi *vsi); struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi); +int ice_vsi_determine_xdp_res(struct ice_vsi *vsi); int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog); int ice_destroy_xdp_rings(struct ice_vsi *vsi); int diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index d407cf8c829d..a5425f0dce3f 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -233,6 +233,7 @@ struct ice_aqc_get_sw_cfg_resp_elem { */ #define ICE_AQC_RES_TYPE_VSI_LIST_REP 0x03 #define ICE_AQC_RES_TYPE_VSI_LIST_PRUNE 0x04 +#define ICE_AQC_RES_TYPE_RECIPE 0x05 #define ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK 0x21 #define ICE_AQC_RES_TYPE_FDIR_GUARANTEED_ENTRIES 0x22 #define ICE_AQC_RES_TYPE_FDIR_SHARED_ENTRIES 0x23 @@ -241,6 +242,7 @@ struct ice_aqc_get_sw_cfg_resp_elem { #define ICE_AQC_RES_TYPE_HASH_PROF_BLDR_PROFID 0x60 #define ICE_AQC_RES_TYPE_HASH_PROF_BLDR_TCAM 0x61 +#define ICE_AQC_RES_TYPE_FLAG_SHARED BIT(7) #define ICE_AQC_RES_TYPE_FLAG_SCAN_BOTTOM BIT(12) #define ICE_AQC_RES_TYPE_FLAG_IGNORE_INDEX BIT(13) @@ -474,6 +476,53 @@ struct ice_aqc_vsi_props { #define ICE_MAX_NUM_RECIPES 64 +/* Add/Get Recipe (indirect 0x0290/0x0292) */ +struct ice_aqc_add_get_recipe { + __le16 num_sub_recipes; /* Input in Add cmd, Output in Get cmd */ + __le16 return_index; /* Input, used for Get cmd only */ + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +struct ice_aqc_recipe_content { + u8 rid; +#define ICE_AQ_RECIPE_ID_IS_ROOT BIT(7) +#define ICE_AQ_SW_ID_LKUP_IDX 0 + u8 lkup_indx[5]; +#define ICE_AQ_RECIPE_LKUP_IGNORE BIT(7) +#define ICE_AQ_SW_ID_LKUP_MASK 0x00FF + __le16 mask[5]; + u8 result_indx; +#define ICE_AQ_RECIPE_RESULT_DATA_S 0 +#define ICE_AQ_RECIPE_RESULT_DATA_M (0x3F << ICE_AQ_RECIPE_RESULT_DATA_S) +#define ICE_AQ_RECIPE_RESULT_EN BIT(7) + u8 rsvd0[3]; + u8 act_ctrl_join_priority; + u8 act_ctrl_fwd_priority; + u8 act_ctrl; +#define ICE_AQ_RECIPE_ACT_INV_ACT BIT(2) + u8 rsvd1; + __le32 dflt_act; +}; + +struct ice_aqc_recipe_data_elem { + u8 recipe_indx; + u8 resp_bits; + u8 rsvd0[2]; + u8 recipe_bitmap[8]; + u8 rsvd1[4]; + struct ice_aqc_recipe_content content; + u8 rsvd2[20]; +}; + +/* Set/Get Recipes to Profile Association (direct 0x0291/0x0293) */ +struct ice_aqc_recipe_to_profile { + __le16 profile_id; + u8 rsvd[6]; + DECLARE_BITMAP(recipe_assoc, ICE_MAX_NUM_RECIPES); +}; + /* Add/Update/Remove/Get switch rules (indirect 0x02A0, 0x02A1, 0x02A2, 0x02A3) */ struct ice_aqc_sw_rules { @@ -1230,7 +1279,7 @@ struct ice_aqc_set_mac_lb { u8 reserved[15]; }; -struct ice_aqc_link_topo_addr { +struct ice_aqc_link_topo_params { u8 lport_num; u8 lport_num_valid; #define ICE_AQC_LINK_TOPO_PORT_NUM_VALID BIT(0) @@ -1256,6 +1305,10 @@ struct ice_aqc_link_topo_addr { #define ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED 4 #define ICE_AQC_LINK_TOPO_NODE_CTX_OVERRIDE 5 u8 index; +}; + +struct ice_aqc_link_topo_addr { + struct ice_aqc_link_topo_params topo_params; __le16 handle; #define ICE_AQC_LINK_TOPO_HANDLE_S 0 #define ICE_AQC_LINK_TOPO_HANDLE_M (0x3FF << ICE_AQC_LINK_TOPO_HANDLE_S) @@ -1278,6 +1331,7 @@ struct ice_aqc_link_topo_addr { struct ice_aqc_get_link_topo { struct ice_aqc_link_topo_addr addr; u8 node_part_num; +#define ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575 0x21 u8 rsvd[9]; }; @@ -1291,6 +1345,16 @@ struct ice_aqc_set_port_id_led { u8 rsvd[13]; }; +/* Set/Get GPIO (direct, 0x06EC/0x06ED) */ +struct ice_aqc_gpio { + __le16 gpio_ctrl_handle; +#define ICE_AQC_GPIO_HANDLE_S 0 +#define ICE_AQC_GPIO_HANDLE_M (0x3FF << ICE_AQC_GPIO_HANDLE_S) + u8 gpio_num; + u8 gpio_val; + u8 rsvd[12]; +}; + /* Read/Write SFF EEPROM command (indirect 0x06EE) */ struct ice_aqc_sff_eeprom { u8 lport_num; @@ -1932,10 +1996,13 @@ struct ice_aq_desc { struct ice_aqc_get_phy_caps get_phy; struct ice_aqc_set_phy_cfg set_phy; struct ice_aqc_restart_an restart_an; + struct ice_aqc_gpio read_write_gpio; struct ice_aqc_sff_eeprom read_write_sff_param; struct ice_aqc_set_port_id_led set_port_id_led; struct ice_aqc_get_sw_cfg get_sw_conf; struct ice_aqc_sw_rules sw_rules; + struct ice_aqc_add_get_recipe add_get_recipe; + struct ice_aqc_recipe_to_profile recipe_to_profile; struct ice_aqc_get_topo get_topo; struct ice_aqc_sched_elem_cmd sched_elem_cmd; struct ice_aqc_query_txsched_res query_sched_res; @@ -2044,6 +2111,12 @@ enum ice_adminq_opc { ice_aqc_opc_update_vsi = 0x0211, ice_aqc_opc_free_vsi = 0x0213, + /* recipe commands */ + ice_aqc_opc_add_recipe = 0x0290, + ice_aqc_opc_recipe_to_profile = 0x0291, + ice_aqc_opc_get_recipe = 0x0292, + ice_aqc_opc_get_recipe_to_profile = 0x0293, + /* switch rules population commands */ ice_aqc_opc_add_sw_rules = 0x02A0, ice_aqc_opc_update_sw_rules = 0x02A1, @@ -2079,6 +2152,8 @@ enum ice_adminq_opc { ice_aqc_opc_set_mac_lb = 0x0620, ice_aqc_opc_get_link_topo = 0x06E0, ice_aqc_opc_set_port_id_led = 0x06E9, + ice_aqc_opc_set_gpio = 0x06EC, + ice_aqc_opc_get_gpio = 0x06ED, ice_aqc_opc_sff_eeprom = 0x06EE, /* NVM commands */ diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 3071b8e79499..5daade32ea62 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -614,7 +614,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) return -EINVAL; base_idx = vsi->base_vector; - for (i = 0; i < vsi->num_q_vectors; i++) + ice_for_each_q_vector(vsi, i) if (irq_cpu_rmap_add(netdev->rx_cpu_rmap, pf->msix_entries[base_idx + i].vector)) { ice_free_cpu_rx_rmap(vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index c36057efc7ae..be625977addf 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -115,6 +115,8 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) q_vector->rx.itr_setting = ICE_DFLT_RX_ITR; q_vector->tx.itr_mode = ITR_DYNAMIC; q_vector->rx.itr_mode = ITR_DYNAMIC; + q_vector->tx.type = ICE_TX_CONTAINER; + q_vector->rx.type = ICE_RX_CONTAINER; if (vsi->type == ICE_VSI_VF) goto out; @@ -146,7 +148,8 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) { struct ice_q_vector *q_vector; struct ice_pf *pf = vsi->back; - struct ice_ring *ring; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; struct device *dev; dev = ice_pf_to_dev(pf); @@ -156,10 +159,10 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) } q_vector = vsi->q_vectors[v_idx]; - ice_for_each_ring(ring, q_vector->tx) - ring->q_vector = NULL; - ice_for_each_ring(ring, q_vector->rx) - ring->q_vector = NULL; + ice_for_each_tx_ring(tx_ring, q_vector->tx) + tx_ring->q_vector = NULL; + ice_for_each_rx_ring(rx_ring, q_vector->rx) + rx_ring->q_vector = NULL; /* only VSI with an associated netdev is set up with NAPI */ if (vsi->netdev) @@ -201,12 +204,12 @@ static void ice_cfg_itr_gran(struct ice_hw *hw) } /** - * ice_calc_q_handle - calculate the queue handle + * ice_calc_txq_handle - calculate the queue handle * @vsi: VSI that ring belongs to * @ring: ring to get the absolute queue index * @tc: traffic class number */ -static u16 ice_calc_q_handle(struct ice_vsi *vsi, struct ice_ring *ring, u8 tc) +static u16 ice_calc_txq_handle(struct ice_vsi *vsi, struct ice_tx_ring *ring, u8 tc) { WARN_ONCE(ice_ring_is_xdp(ring) && tc, "XDP ring can't belong to TC other than 0\n"); @@ -218,13 +221,37 @@ static u16 ice_calc_q_handle(struct ice_vsi *vsi, struct ice_ring *ring, u8 tc) } /** + * ice_eswitch_calc_txq_handle + * @ring: pointer to ring which unique index is needed + * + * To correctly work with many netdevs ring->q_index of Tx rings on switchdev + * VSI can repeat. Hardware ring setup requires unique q_index. Calculate it + * here by finding index in vsi->tx_rings of this ring. + * + * Return ICE_INVAL_Q_INDEX when index wasn't found. Should never happen, + * because VSI is get from ring->vsi, so it has to be present in this VSI. + */ +static u16 ice_eswitch_calc_txq_handle(struct ice_tx_ring *ring) +{ + struct ice_vsi *vsi = ring->vsi; + int i; + + ice_for_each_txq(vsi, i) { + if (vsi->tx_rings[i] == ring) + return i; + } + + return ICE_INVAL_Q_INDEX; +} + +/** * ice_cfg_xps_tx_ring - Configure XPS for a Tx ring * @ring: The Tx ring to configure * * This enables/disables XPS for a given Tx descriptor ring * based on the TCs enabled for the VSI that ring belongs to. */ -static void ice_cfg_xps_tx_ring(struct ice_ring *ring) +static void ice_cfg_xps_tx_ring(struct ice_tx_ring *ring) { if (!ring->q_vector || !ring->netdev) return; @@ -246,7 +273,7 @@ static void ice_cfg_xps_tx_ring(struct ice_ring *ring) * Configure the Tx descriptor ring in TLAN context. */ static void -ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) +ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) { struct ice_vsi *vsi = ring->vsi; struct ice_hw *hw = &vsi->back->hw; @@ -258,7 +285,7 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) /* Transmit Queue Length */ tlan_ctx->qlen = ring->count; - ice_set_cgd_num(tlan_ctx, ring); + ice_set_cgd_num(tlan_ctx, ring->dcb_tc); /* PF number */ tlan_ctx->pf_num = hw->pf_id; @@ -280,6 +307,9 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf_id; tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF; break; + case ICE_VSI_SWITCHDEV_CTRL: + tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VMQ; + break; default: return; } @@ -312,7 +342,7 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) * * Returns the offset value for ring into the data buffer. */ -static unsigned int ice_rx_offset(struct ice_ring *rx_ring) +static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring) { if (ice_ring_uses_build_skb(rx_ring)) return ICE_SKB_PAD; @@ -328,7 +358,7 @@ static unsigned int ice_rx_offset(struct ice_ring *rx_ring) * * Configure the Rx descriptor ring in RLAN context. */ -static int ice_setup_rx_ctx(struct ice_ring *ring) +static int ice_setup_rx_ctx(struct ice_rx_ring *ring) { int chain_len = ICE_MAX_CHAINED_RX_BUFS; struct ice_vsi *vsi = ring->vsi; @@ -439,7 +469,7 @@ static int ice_setup_rx_ctx(struct ice_ring *ring) * * Return 0 on success and a negative value on error. */ -int ice_vsi_cfg_rxq(struct ice_ring *ring) +int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) { struct device *dev = ice_pf_to_dev(ring->vsi->back); u16 num_bufs = ICE_DESC_UNUSED(ring); @@ -660,16 +690,16 @@ void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) tx_rings_per_v = (u8)DIV_ROUND_UP(tx_rings_rem, q_vectors - v_id); q_vector->num_ring_tx = tx_rings_per_v; - q_vector->tx.ring = NULL; + q_vector->tx.tx_ring = NULL; q_vector->tx.itr_idx = ICE_TX_ITR; q_base = vsi->num_txq - tx_rings_rem; for (q_id = q_base; q_id < (q_base + tx_rings_per_v); q_id++) { - struct ice_ring *tx_ring = vsi->tx_rings[q_id]; + struct ice_tx_ring *tx_ring = vsi->tx_rings[q_id]; tx_ring->q_vector = q_vector; - tx_ring->next = q_vector->tx.ring; - q_vector->tx.ring = tx_ring; + tx_ring->next = q_vector->tx.tx_ring; + q_vector->tx.tx_ring = tx_ring; } tx_rings_rem -= tx_rings_per_v; @@ -677,16 +707,16 @@ void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi) rx_rings_per_v = (u8)DIV_ROUND_UP(rx_rings_rem, q_vectors - v_id); q_vector->num_ring_rx = rx_rings_per_v; - q_vector->rx.ring = NULL; + q_vector->rx.rx_ring = NULL; q_vector->rx.itr_idx = ICE_RX_ITR; q_base = vsi->num_rxq - rx_rings_rem; for (q_id = q_base; q_id < (q_base + rx_rings_per_v); q_id++) { - struct ice_ring *rx_ring = vsi->rx_rings[q_id]; + struct ice_rx_ring *rx_ring = vsi->rx_rings[q_id]; rx_ring->q_vector = q_vector; - rx_ring->next = q_vector->rx.ring; - q_vector->rx.ring = rx_ring; + rx_ring->next = q_vector->rx.rx_ring; + q_vector->rx.rx_ring = rx_ring; } rx_rings_rem -= rx_rings_per_v; } @@ -711,7 +741,7 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi) * @qg_buf: queue group buffer */ int -ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring, +ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_aqc_add_tx_qgrp *qg_buf) { u8 buf_len = struct_size(qg_buf, txqs, 1); @@ -746,7 +776,14 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring, /* Add unique software queue handle of the Tx queue per * TC into the VSI Tx ring */ - ring->q_handle = ice_calc_q_handle(vsi, ring, tc); + if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) { + ring->q_handle = ice_eswitch_calc_txq_handle(ring); + + if (ring->q_handle == ICE_INVAL_Q_INDEX) + return -ENODEV; + } else { + ring->q_handle = ice_calc_txq_handle(vsi, ring, tc); + } status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, ring->q_handle, 1, qg_buf, buf_len, NULL); @@ -870,7 +907,7 @@ void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector) */ int ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring *ring, + u16 rel_vmvf_num, struct ice_tx_ring *ring, struct ice_txq_meta *txq_meta) { struct ice_pf *pf = vsi->back; @@ -927,7 +964,7 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, * are needed for stopping Tx queue */ void -ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_ring *ring, +ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_txq_meta *txq_meta) { u8 tc; diff --git a/drivers/net/ethernet/intel/ice/ice_base.h b/drivers/net/ethernet/intel/ice/ice_base.h index 20e1c29aa68a..b67dca417acb 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.h +++ b/drivers/net/ethernet/intel/ice/ice_base.h @@ -6,7 +6,7 @@ #include "ice.h" -int ice_vsi_cfg_rxq(struct ice_ring *ring); +int ice_vsi_cfg_rxq(struct ice_rx_ring *ring); int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg); int ice_vsi_ctrl_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx, bool wait); @@ -15,7 +15,7 @@ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi); void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi); void ice_vsi_free_q_vectors(struct ice_vsi *vsi); int -ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring, +ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_aqc_add_tx_qgrp *qg_buf); void ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector); void @@ -25,9 +25,9 @@ ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx); void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector); int ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring *ring, + u16 rel_vmvf_num, struct ice_tx_ring *ring, struct ice_txq_meta *txq_meta); void -ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_ring *ring, +ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_txq_meta *txq_meta); #endif /* _ICE_BASE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 2fb81e359cdf..16a25616cdc3 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -70,6 +70,27 @@ bool ice_is_e810(struct ice_hw *hw) } /** + * ice_is_e810t + * @hw: pointer to the hardware structure + * + * returns true if the device is E810T based, false if not. + */ +bool ice_is_e810t(struct ice_hw *hw) +{ + switch (hw->device_id) { + case ICE_DEV_ID_E810C_SFP: + if (hw->subsystem_device_id == ICE_SUBDEV_ID_E810T || + hw->subsystem_device_id == ICE_SUBDEV_ID_E810T2) + return true; + break; + default: + break; + } + + return false; +} + +/** * ice_clear_pf_cfg - Clear PF configuration * @hw: pointer to the hardware structure * @@ -240,11 +261,13 @@ ice_aq_get_link_topo_handle(struct ice_port_info *pi, u8 node_type, ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); - cmd->addr.node_type_ctx = (ICE_AQC_LINK_TOPO_NODE_CTX_PORT << - ICE_AQC_LINK_TOPO_NODE_CTX_S); + cmd->addr.topo_params.node_type_ctx = + (ICE_AQC_LINK_TOPO_NODE_CTX_PORT << + ICE_AQC_LINK_TOPO_NODE_CTX_S); /* set node type */ - cmd->addr.node_type_ctx |= (ICE_AQC_LINK_TOPO_NODE_TYPE_M & node_type); + cmd->addr.topo_params.node_type_ctx |= + (ICE_AQC_LINK_TOPO_NODE_TYPE_M & node_type); return ice_aq_send_cmd(pi->hw, &desc, NULL, 0, cd); } @@ -568,6 +591,7 @@ static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw) return ICE_ERR_NO_MEMORY; INIT_LIST_HEAD(&sw->vsi_list_map_head); + sw->prof_res_bm_init = 0; status = ice_init_def_sw_recp(hw); if (status) { @@ -594,17 +618,42 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) list_del(&v_pos_map->list_entry); devm_kfree(ice_hw_to_dev(hw), v_pos_map); } - recps = hw->switch_info->recp_list; - for (i = 0; i < ICE_SW_LKUP_LAST; i++) { - struct ice_fltr_mgmt_list_entry *lst_itr, *tmp_entry; + recps = sw->recp_list; + for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) { + struct ice_recp_grp_entry *rg_entry, *tmprg_entry; recps[i].root_rid = i; - mutex_destroy(&recps[i].filt_rule_lock); - list_for_each_entry_safe(lst_itr, tmp_entry, - &recps[i].filt_rules, list_entry) { - list_del(&lst_itr->list_entry); - devm_kfree(ice_hw_to_dev(hw), lst_itr); + list_for_each_entry_safe(rg_entry, tmprg_entry, + &recps[i].rg_list, l_entry) { + list_del(&rg_entry->l_entry); + devm_kfree(ice_hw_to_dev(hw), rg_entry); + } + + if (recps[i].adv_rule) { + struct ice_adv_fltr_mgmt_list_entry *tmp_entry; + struct ice_adv_fltr_mgmt_list_entry *lst_itr; + + mutex_destroy(&recps[i].filt_rule_lock); + list_for_each_entry_safe(lst_itr, tmp_entry, + &recps[i].filt_rules, + list_entry) { + list_del(&lst_itr->list_entry); + devm_kfree(ice_hw_to_dev(hw), lst_itr->lkups); + devm_kfree(ice_hw_to_dev(hw), lst_itr); + } + } else { + struct ice_fltr_mgmt_list_entry *lst_itr, *tmp_entry; + + mutex_destroy(&recps[i].filt_rule_lock); + list_for_each_entry_safe(lst_itr, tmp_entry, + &recps[i].filt_rules, + list_entry) { + list_del(&lst_itr->list_entry); + devm_kfree(ice_hw_to_dev(hw), lst_itr); + } } + if (recps[i].root_buf) + devm_kfree(ice_hw_to_dev(hw), recps[i].root_buf); } ice_rm_all_sw_replay_rule_info(hw); devm_kfree(ice_hw_to_dev(hw), sw->recp_list); @@ -4767,6 +4816,64 @@ ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, } /** + * ice_aq_set_gpio + * @hw: pointer to the hw struct + * @gpio_ctrl_handle: GPIO controller node handle + * @pin_idx: IO Number of the GPIO that needs to be set + * @value: SW provide IO value to set in the LSB + * @cd: pointer to command details structure or NULL + * + * Sends 0x06EC AQ command to set the GPIO pin state that's part of the topology + */ +int +ice_aq_set_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool value, + struct ice_sq_cd *cd) +{ + struct ice_aqc_gpio *cmd; + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_gpio); + cmd = &desc.params.read_write_gpio; + cmd->gpio_ctrl_handle = cpu_to_le16(gpio_ctrl_handle); + cmd->gpio_num = pin_idx; + cmd->gpio_val = value ? 1 : 0; + + return ice_status_to_errno(ice_aq_send_cmd(hw, &desc, NULL, 0, cd)); +} + +/** + * ice_aq_get_gpio + * @hw: pointer to the hw struct + * @gpio_ctrl_handle: GPIO controller node handle + * @pin_idx: IO Number of the GPIO that needs to be set + * @value: IO value read + * @cd: pointer to command details structure or NULL + * + * Sends 0x06ED AQ command to get the value of a GPIO signal which is part of + * the topology + */ +int +ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, + bool *value, struct ice_sq_cd *cd) +{ + struct ice_aqc_gpio *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_gpio); + cmd = &desc.params.read_write_gpio; + cmd->gpio_ctrl_handle = cpu_to_le16(gpio_ctrl_handle); + cmd->gpio_num = pin_idx; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + if (status) + return ice_status_to_errno(status); + + *value = !!cmd->gpio_val; + return 0; +} + +/** * ice_fw_supports_link_override * @hw: pointer to the hardware structure * diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index fb16070f02e2..65c1b3244264 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -183,6 +183,7 @@ ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); +bool ice_is_e810t(struct ice_hw *hw); enum ice_status ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf); @@ -192,6 +193,12 @@ ice_aq_set_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, int ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, u32 *value, struct ice_sq_cd *cd); +int +ice_aq_set_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool value, + struct ice_sq_cd *cd); +int +ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, + bool *value, struct ice_sq_cd *cd); enum ice_status ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, struct ice_sq_cd *cd); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 26b4d5f579e6..4284526e9e24 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -194,17 +194,18 @@ u8 ice_dcb_get_tc(struct ice_vsi *vsi, int queue_index) */ void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) { - struct ice_ring *tx_ring, *rx_ring; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; u16 qoffset, qcount; int i, n; if (!test_bit(ICE_FLAG_DCB_ENA, vsi->back->flags)) { /* Reset the TC information */ - for (i = 0; i < vsi->num_txq; i++) { + ice_for_each_txq(vsi, i) { tx_ring = vsi->tx_rings[i]; tx_ring->dcb_tc = 0; } - for (i = 0; i < vsi->num_rxq; i++) { + ice_for_each_rxq(vsi, i) { rx_ring = vsi->rx_rings[i]; rx_ring->dcb_tc = 0; } @@ -683,6 +684,11 @@ void ice_pf_dcb_recfg(struct ice_pf *pf) vsi->idx); continue; } + /* no need to proceed with remaining cfg if it is switchdev + * VSI + */ + if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) + continue; ice_vsi_map_rings_to_vectors(vsi); if (vsi->type == ICE_VSI_PF) @@ -819,7 +825,7 @@ void ice_update_dcb_stats(struct ice_pf *pf) * tag will already be configured with the correct ID and priority bits */ void -ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring, +ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first) { struct sk_buff *skb = first->skb; diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index 3dcde1750a5e..6700e97b3b51 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -29,7 +29,7 @@ void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi); int ice_init_pf_dcb(struct ice_pf *pf, bool locked); void ice_update_dcb_stats(struct ice_pf *pf); void -ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring, +ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first); void ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, @@ -50,9 +50,9 @@ static inline bool ice_find_q_in_range(u16 low, u16 high, unsigned int tx_q) } static inline void -ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring) +ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, u8 dcb_tc) { - tlan_ctx->cgd_num = ring->dcb_tc; + tlan_ctx->cgd_num = dcb_tc; } static inline bool ice_is_dcb_active(struct ice_pf *pf) @@ -102,7 +102,7 @@ ice_pf_dcb_cfg(struct ice_pf __always_unused *pf, } static inline int -ice_tx_prepare_vlan_flags_dcb(struct ice_ring __always_unused *tx_ring, +ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring __always_unused *tx_ring, struct ice_tx_buf __always_unused *first) { return 0; @@ -131,6 +131,6 @@ static inline void ice_update_dcb_stats(struct ice_pf *pf) { } static inline void ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event) { } static inline void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc) { } -static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring) { } +static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, u8 dcb_tc) { } #endif /* CONFIG_DCB */ #endif /* _ICE_DCB_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index 9d8194671f6a..8d2c39ee775b 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -21,6 +21,8 @@ #define ICE_DEV_ID_E810C_QSFP 0x1592 /* Intel(R) Ethernet Controller E810-C for SFP */ #define ICE_DEV_ID_E810C_SFP 0x1593 +#define ICE_SUBDEV_ID_E810T 0x000E +#define ICE_SUBDEV_ID_E810T2 0x000F /* Intel(R) Ethernet Controller E810-XXV for SFP */ #define ICE_DEV_ID_E810_XXV_SFP 0x159B /* Intel(R) Ethernet Connection E823-C for backplane */ diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index cae1cd97a1ef..55353bf4cbef 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -4,6 +4,7 @@ #include "ice.h" #include "ice_lib.h" #include "ice_devlink.h" +#include "ice_eswitch.h" #include "ice_fw_update.h" /* context for devlink info version reporting */ @@ -423,6 +424,8 @@ ice_devlink_flash_update(struct devlink *devlink, static const struct devlink_ops ice_devlink_ops = { .supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK, + .eswitch_mode_get = ice_eswitch_mode_get, + .eswitch_mode_set = ice_eswitch_mode_set, .info_get = ice_devlink_info_get, .flash_update = ice_devlink_flash_update, }; @@ -484,60 +487,115 @@ void ice_devlink_unregister(struct ice_pf *pf) } /** - * ice_devlink_create_port - Create a devlink port for this VSI - * @vsi: the VSI to create a port for + * ice_devlink_create_pf_port - Create a devlink port for this PF + * @pf: the PF to create a devlink port for * - * Create and register a devlink_port for this VSI. + * Create and register a devlink_port for this PF. * * Return: zero on success or an error code on failure. */ -int ice_devlink_create_port(struct ice_vsi *vsi) +int ice_devlink_create_pf_port(struct ice_pf *pf) { struct devlink_port_attrs attrs = {}; - struct ice_port_info *pi; + struct devlink_port *devlink_port; struct devlink *devlink; + struct ice_vsi *vsi; struct device *dev; - struct ice_pf *pf; int err; - /* Currently we only create devlink_port instances for PF VSIs */ - if (vsi->type != ICE_VSI_PF) - return -EINVAL; - - pf = vsi->back; - devlink = priv_to_devlink(pf); dev = ice_pf_to_dev(pf); - pi = pf->hw.port_info; + + devlink_port = &pf->devlink_port; + + vsi = ice_get_main_vsi(pf); + if (!vsi) + return -EIO; attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = pi->lport; - devlink_port_attrs_set(&vsi->devlink_port, &attrs); - err = devlink_port_register(devlink, &vsi->devlink_port, vsi->idx); + attrs.phys.port_number = pf->hw.bus.func; + devlink_port_attrs_set(devlink_port, &attrs); + devlink = priv_to_devlink(pf); + + err = devlink_port_register(devlink, devlink_port, vsi->idx); if (err) { - dev_err(dev, "devlink_port_register failed: %d\n", err); + dev_err(dev, "Failed to create devlink port for PF %d, error %d\n", + pf->hw.pf_id, err); return err; } - vsi->devlink_port_registered = true; + return 0; +} + +/** + * ice_devlink_destroy_pf_port - Destroy the devlink_port for this PF + * @pf: the PF to cleanup + * + * Unregisters the devlink_port structure associated with this PF. + */ +void ice_devlink_destroy_pf_port(struct ice_pf *pf) +{ + struct devlink_port *devlink_port; + + devlink_port = &pf->devlink_port; + + devlink_port_type_clear(devlink_port); + devlink_port_unregister(devlink_port); +} + +/** + * ice_devlink_create_vf_port - Create a devlink port for this VF + * @vf: the VF to create a port for + * + * Create and register a devlink_port for this VF. + * + * Return: zero on success or an error code on failure. + */ +int ice_devlink_create_vf_port(struct ice_vf *vf) +{ + struct devlink_port_attrs attrs = {}; + struct devlink_port *devlink_port; + struct devlink *devlink; + struct ice_vsi *vsi; + struct device *dev; + struct ice_pf *pf; + int err; + + pf = vf->pf; + dev = ice_pf_to_dev(pf); + vsi = ice_get_vf_vsi(vf); + devlink_port = &vf->devlink_port; + + attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; + attrs.pci_vf.pf = pf->hw.bus.func; + attrs.pci_vf.vf = vf->vf_id; + + devlink_port_attrs_set(devlink_port, &attrs); + devlink = priv_to_devlink(pf); + + err = devlink_port_register(devlink, devlink_port, vsi->idx); + if (err) { + dev_err(dev, "Failed to create devlink port for VF %d, error %d\n", + vf->vf_id, err); + return err; + } return 0; } /** - * ice_devlink_destroy_port - Destroy the devlink_port for this VSI - * @vsi: the VSI to cleanup + * ice_devlink_destroy_vf_port - Destroy the devlink_port for this VF + * @vf: the VF to cleanup * - * Unregisters the devlink_port structure associated with this VSI. + * Unregisters the devlink_port structure associated with this VF. */ -void ice_devlink_destroy_port(struct ice_vsi *vsi) +void ice_devlink_destroy_vf_port(struct ice_vf *vf) { - if (!vsi->devlink_port_registered) - return; + struct devlink_port *devlink_port; - devlink_port_type_clear(&vsi->devlink_port); - devlink_port_unregister(&vsi->devlink_port); + devlink_port = &vf->devlink_port; - vsi->devlink_port_registered = false; + devlink_port_type_clear(devlink_port); + devlink_port_unregister(devlink_port); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.h b/drivers/net/ethernet/intel/ice/ice_devlink.h index e721d7b0d627..b7f9551e4fc4 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.h +++ b/drivers/net/ethernet/intel/ice/ice_devlink.h @@ -8,8 +8,10 @@ struct ice_pf *ice_allocate_pf(struct device *dev); void ice_devlink_register(struct ice_pf *pf); void ice_devlink_unregister(struct ice_pf *pf); -int ice_devlink_create_port(struct ice_vsi *vsi); -void ice_devlink_destroy_port(struct ice_vsi *vsi); +int ice_devlink_create_pf_port(struct ice_pf *pf); +void ice_devlink_destroy_pf_port(struct ice_pf *pf); +int ice_devlink_create_vf_port(struct ice_vf *vf); +void ice_devlink_destroy_vf_port(struct ice_vf *vf); void ice_devlink_init_regions(struct ice_pf *pf); void ice_devlink_destroy_regions(struct ice_pf *pf); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c new file mode 100644 index 000000000000..a20c38446e76 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -0,0 +1,649 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice.h" +#include "ice_lib.h" +#include "ice_eswitch.h" +#include "ice_fltr.h" +#include "ice_repr.h" +#include "ice_devlink.h" +#include "ice_tc_lib.h" + +/** + * ice_eswitch_setup_env - configure switchdev HW filters + * @pf: pointer to PF struct + * + * This function adds HW filters configuration specific for switchdev + * mode. + */ +static int ice_eswitch_setup_env(struct ice_pf *pf) +{ + struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi; + struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + struct ice_port_info *pi = pf->hw.port_info; + bool rule_added = false; + + ice_vsi_manage_vlan_stripping(ctrl_vsi, false); + + ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx); + + if (ice_vsi_add_vlan(uplink_vsi, 0, ICE_FWD_TO_VSI)) + goto err_def_rx; + + if (!ice_is_dflt_vsi_in_use(uplink_vsi->vsw)) { + if (ice_set_dflt_vsi(uplink_vsi->vsw, uplink_vsi)) + goto err_def_rx; + rule_added = true; + } + + if (ice_cfg_dflt_vsi(pi->hw, ctrl_vsi->idx, true, ICE_FLTR_TX)) + goto err_def_tx; + + if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override)) + goto err_override_uplink; + + if (ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_set_allow_override)) + goto err_override_control; + + if (ice_fltr_update_flags_dflt_rule(ctrl_vsi, pi->dflt_tx_vsi_rule_id, + ICE_FLTR_TX, + ICE_SINGLE_ACT_LB_ENABLE)) + goto err_update_action; + + return 0; + +err_update_action: + ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); +err_override_control: + ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); +err_override_uplink: + ice_cfg_dflt_vsi(pi->hw, ctrl_vsi->idx, false, ICE_FLTR_TX); +err_def_tx: + if (rule_added) + ice_clear_dflt_vsi(uplink_vsi->vsw); +err_def_rx: + ice_fltr_add_mac_and_broadcast(uplink_vsi, + uplink_vsi->port_info->mac.perm_addr, + ICE_FWD_TO_VSI); + return -ENODEV; +} + +/** + * ice_eswitch_remap_rings_to_vectors - reconfigure rings of switchdev ctrl VSI + * @pf: pointer to PF struct + * + * In switchdev number of allocated Tx/Rx rings is equal. + * + * This function fills q_vectors structures associated with representor and + * move each ring pairs to port representor netdevs. Each port representor + * will have dedicated 1 Tx/Rx ring pair, so number of rings pair is equal to + * number of VFs. + */ +static void ice_eswitch_remap_rings_to_vectors(struct ice_pf *pf) +{ + struct ice_vsi *vsi = pf->switchdev.control_vsi; + int q_id; + + ice_for_each_txq(vsi, q_id) { + struct ice_repr *repr = pf->vf[q_id].repr; + struct ice_q_vector *q_vector = repr->q_vector; + struct ice_tx_ring *tx_ring = vsi->tx_rings[q_id]; + struct ice_rx_ring *rx_ring = vsi->rx_rings[q_id]; + + q_vector->vsi = vsi; + q_vector->reg_idx = vsi->q_vectors[0]->reg_idx; + + q_vector->num_ring_tx = 1; + q_vector->tx.tx_ring = tx_ring; + tx_ring->q_vector = q_vector; + tx_ring->next = NULL; + tx_ring->netdev = repr->netdev; + /* In switchdev mode, from OS stack perspective, there is only + * one queue for given netdev, so it needs to be indexed as 0. + */ + tx_ring->q_index = 0; + + q_vector->num_ring_rx = 1; + q_vector->rx.rx_ring = rx_ring; + rx_ring->q_vector = q_vector; + rx_ring->next = NULL; + rx_ring->netdev = repr->netdev; + } +} + +/** + * ice_eswitch_setup_reprs - configure port reprs to run in switchdev mode + * @pf: pointer to PF struct + */ +static int ice_eswitch_setup_reprs(struct ice_pf *pf) +{ + struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + int max_vsi_num = 0; + int i; + + ice_for_each_vf(pf, i) { + struct ice_vsi *vsi = pf->vf[i].repr->src_vsi; + struct ice_vf *vf = &pf->vf[i]; + + ice_remove_vsi_fltr(&pf->hw, vsi->idx); + vf->repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, + GFP_KERNEL); + if (!vf->repr->dst) { + ice_fltr_add_mac_and_broadcast(vsi, + vf->hw_lan_addr.addr, + ICE_FWD_TO_VSI); + goto err; + } + + if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof)) { + ice_fltr_add_mac_and_broadcast(vsi, + vf->hw_lan_addr.addr, + ICE_FWD_TO_VSI); + metadata_dst_free(vf->repr->dst); + goto err; + } + + if (ice_vsi_add_vlan(vsi, 0, ICE_FWD_TO_VSI)) { + ice_fltr_add_mac_and_broadcast(vsi, + vf->hw_lan_addr.addr, + ICE_FWD_TO_VSI); + metadata_dst_free(vf->repr->dst); + ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); + goto err; + } + + if (max_vsi_num < vsi->vsi_num) + max_vsi_num = vsi->vsi_num; + + netif_napi_add(vf->repr->netdev, &vf->repr->q_vector->napi, ice_napi_poll, + NAPI_POLL_WEIGHT); + + netif_keep_dst(vf->repr->netdev); + } + + kfree(ctrl_vsi->target_netdevs); + + ctrl_vsi->target_netdevs = kcalloc(max_vsi_num + 1, + sizeof(*ctrl_vsi->target_netdevs), + GFP_KERNEL); + if (!ctrl_vsi->target_netdevs) + goto err; + + ice_for_each_vf(pf, i) { + struct ice_repr *repr = pf->vf[i].repr; + struct ice_vsi *vsi = repr->src_vsi; + struct metadata_dst *dst; + + ctrl_vsi->target_netdevs[vsi->vsi_num] = repr->netdev; + + dst = repr->dst; + dst->u.port_info.port_id = vsi->vsi_num; + dst->u.port_info.lower_dev = repr->netdev; + ice_repr_set_traffic_vsi(repr, ctrl_vsi); + } + + return 0; + +err: + for (i = i - 1; i >= 0; i--) { + struct ice_vsi *vsi = pf->vf[i].repr->src_vsi; + struct ice_vf *vf = &pf->vf[i]; + + ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); + metadata_dst_free(vf->repr->dst); + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, + ICE_FWD_TO_VSI); + } + + return -ENODEV; +} + +/** + * ice_eswitch_release_reprs - clear PR VSIs configuration + * @pf: poiner to PF struct + * @ctrl_vsi: pointer to switchdev control VSI + */ +static void +ice_eswitch_release_reprs(struct ice_pf *pf, struct ice_vsi *ctrl_vsi) +{ + int i; + + kfree(ctrl_vsi->target_netdevs); + ice_for_each_vf(pf, i) { + struct ice_vsi *vsi = pf->vf[i].repr->src_vsi; + struct ice_vf *vf = &pf->vf[i]; + + ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); + metadata_dst_free(vf->repr->dst); + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, + ICE_FWD_TO_VSI); + + netif_napi_del(&vf->repr->q_vector->napi); + } +} + +/** + * ice_eswitch_update_repr - reconfigure VF port representor + * @vsi: VF VSI for which port representor is configured + */ +void ice_eswitch_update_repr(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct ice_repr *repr; + struct ice_vf *vf; + int ret; + + if (!ice_is_switchdev_running(pf)) + return; + + vf = &pf->vf[vsi->vf_id]; + repr = vf->repr; + repr->src_vsi = vsi; + repr->dst->u.port_info.port_id = vsi->vsi_num; + + ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof); + if (ret) { + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, ICE_FWD_TO_VSI); + dev_err(ice_pf_to_dev(pf), "Failed to update VF %d port representor", vsi->vf_id); + } +} + +/** + * ice_eswitch_port_start_xmit - callback for packets transmit + * @skb: send buffer + * @netdev: network interface device structure + * + * Returns NETDEV_TX_OK if sent, else an error code + */ +netdev_tx_t +ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + struct ice_netdev_priv *np; + struct ice_repr *repr; + struct ice_vsi *vsi; + + np = netdev_priv(netdev); + vsi = np->vsi; + + if (ice_is_reset_in_progress(vsi->back->state)) + return NETDEV_TX_BUSY; + + repr = ice_netdev_to_repr(netdev); + skb_dst_drop(skb); + dst_hold((struct dst_entry *)repr->dst); + skb_dst_set(skb, (struct dst_entry *)repr->dst); + skb->queue_mapping = repr->vf->vf_id; + + return ice_start_xmit(skb, netdev); +} + +/** + * ice_eswitch_set_target_vsi - set switchdev context in Tx context descriptor + * @skb: pointer to send buffer + * @off: pointer to offload struct + */ +void +ice_eswitch_set_target_vsi(struct sk_buff *skb, + struct ice_tx_offload_params *off) +{ + struct metadata_dst *dst = skb_metadata_dst(skb); + u64 cd_cmd, dst_vsi; + + if (!dst) { + cd_cmd = ICE_TX_CTX_DESC_SWTCH_UPLINK << ICE_TXD_CTX_QW1_CMD_S; + off->cd_qw1 |= (cd_cmd | ICE_TX_DESC_DTYPE_CTX); + } else { + cd_cmd = ICE_TX_CTX_DESC_SWTCH_VSI << ICE_TXD_CTX_QW1_CMD_S; + dst_vsi = ((u64)dst->u.port_info.port_id << + ICE_TXD_CTX_QW1_VSI_S) & ICE_TXD_CTX_QW1_VSI_M; + off->cd_qw1 = cd_cmd | dst_vsi | ICE_TX_DESC_DTYPE_CTX; + } +} + +/** + * ice_eswitch_release_env - clear switchdev HW filters + * @pf: pointer to PF struct + * + * This function removes HW filters configuration specific for switchdev + * mode and restores default legacy mode settings. + */ +static void ice_eswitch_release_env(struct ice_pf *pf) +{ + struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi; + struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + + ice_vsi_update_security(ctrl_vsi, ice_vsi_ctx_clear_allow_override); + ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override); + ice_cfg_dflt_vsi(&pf->hw, ctrl_vsi->idx, false, ICE_FLTR_TX); + ice_clear_dflt_vsi(uplink_vsi->vsw); + ice_fltr_add_mac_and_broadcast(uplink_vsi, + uplink_vsi->port_info->mac.perm_addr, + ICE_FWD_TO_VSI); +} + +/** + * ice_eswitch_vsi_setup - configure switchdev control VSI + * @pf: pointer to PF structure + * @pi: pointer to port_info structure + */ +static struct ice_vsi * +ice_eswitch_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) +{ + return ice_vsi_setup(pf, pi, ICE_VSI_SWITCHDEV_CTRL, ICE_INVAL_VFID); +} + +/** + * ice_eswitch_napi_del - remove NAPI handle for all port representors + * @pf: pointer to PF structure + */ +static void ice_eswitch_napi_del(struct ice_pf *pf) +{ + int i; + + ice_for_each_vf(pf, i) + netif_napi_del(&pf->vf[i].repr->q_vector->napi); +} + +/** + * ice_eswitch_napi_enable - enable NAPI for all port representors + * @pf: pointer to PF structure + */ +static void ice_eswitch_napi_enable(struct ice_pf *pf) +{ + int i; + + ice_for_each_vf(pf, i) + napi_enable(&pf->vf[i].repr->q_vector->napi); +} + +/** + * ice_eswitch_napi_disable - disable NAPI for all port representors + * @pf: pointer to PF structure + */ +static void ice_eswitch_napi_disable(struct ice_pf *pf) +{ + int i; + + ice_for_each_vf(pf, i) + napi_disable(&pf->vf[i].repr->q_vector->napi); +} + +/** + * ice_eswitch_set_rxdid - configure rxdid on all Rx queues from VSI + * @vsi: VSI to setup rxdid on + * @rxdid: flex descriptor id + */ +static void ice_eswitch_set_rxdid(struct ice_vsi *vsi, u32 rxdid) +{ + struct ice_hw *hw = &vsi->back->hw; + int i; + + ice_for_each_rxq(vsi, i) { + struct ice_rx_ring *ring = vsi->rx_rings[i]; + u16 pf_q = vsi->rxq_map[ring->q_index]; + + ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true); + } +} + +/** + * ice_eswitch_enable_switchdev - configure eswitch in switchdev mode + * @pf: pointer to PF structure + */ +static int ice_eswitch_enable_switchdev(struct ice_pf *pf) +{ + struct ice_vsi *ctrl_vsi; + + pf->switchdev.control_vsi = ice_eswitch_vsi_setup(pf, pf->hw.port_info); + if (!pf->switchdev.control_vsi) + return -ENODEV; + + ctrl_vsi = pf->switchdev.control_vsi; + pf->switchdev.uplink_vsi = ice_get_main_vsi(pf); + if (!pf->switchdev.uplink_vsi) + goto err_vsi; + + if (ice_eswitch_setup_env(pf)) + goto err_vsi; + + if (ice_repr_add_for_all_vfs(pf)) + goto err_repr_add; + + if (ice_eswitch_setup_reprs(pf)) + goto err_setup_reprs; + + ice_eswitch_remap_rings_to_vectors(pf); + + if (ice_vsi_open(ctrl_vsi)) + goto err_setup_reprs; + + ice_eswitch_napi_enable(pf); + + ice_eswitch_set_rxdid(ctrl_vsi, ICE_RXDID_FLEX_NIC_2); + + return 0; + +err_setup_reprs: + ice_repr_rem_from_all_vfs(pf); +err_repr_add: + ice_eswitch_release_env(pf); +err_vsi: + ice_vsi_release(ctrl_vsi); + return -ENODEV; +} + +/** + * ice_eswitch_disable_switchdev - disable switchdev resources + * @pf: pointer to PF structure + */ +static void ice_eswitch_disable_switchdev(struct ice_pf *pf) +{ + struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + + ice_eswitch_napi_disable(pf); + ice_eswitch_release_env(pf); + ice_eswitch_release_reprs(pf, ctrl_vsi); + ice_vsi_release(ctrl_vsi); + ice_repr_rem_from_all_vfs(pf); +} + +/** + * ice_eswitch_mode_set - set new eswitch mode + * @devlink: pointer to devlink structure + * @mode: eswitch mode to switch to + * @extack: pointer to extack structure + */ +int +ice_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + + if (pf->eswitch_mode == mode) + return 0; + + if (pf->num_alloc_vfs) { + dev_info(ice_pf_to_dev(pf), "Changing eswitch mode is allowed only if there is no VFs created"); + NL_SET_ERR_MSG_MOD(extack, "Changing eswitch mode is allowed only if there is no VFs created"); + return -EOPNOTSUPP; + } + + switch (mode) { + case DEVLINK_ESWITCH_MODE_LEGACY: + dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to legacy", + pf->hw.pf_id); + NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to legacy"); + break; + case DEVLINK_ESWITCH_MODE_SWITCHDEV: + { + dev_info(ice_pf_to_dev(pf), "PF %d changed eswitch mode to switchdev", + pf->hw.pf_id); + NL_SET_ERR_MSG_MOD(extack, "Changed eswitch mode to switchdev"); + break; + } + default: + NL_SET_ERR_MSG_MOD(extack, "Unknown eswitch mode"); + return -EINVAL; + } + + pf->eswitch_mode = mode; + return 0; +} + +/** + * ice_eswitch_get_target_netdev - return port representor netdev + * @rx_ring: pointer to Rx ring + * @rx_desc: pointer to Rx descriptor + * + * When working in switchdev mode context (when control VSI is used), this + * function returns netdev of appropriate port representor. For non-switchdev + * context, regular netdev associated with Rx ring is returned. + */ +struct net_device * +ice_eswitch_get_target_netdev(struct ice_rx_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc) +{ + struct ice_32b_rx_flex_desc_nic_2 *desc; + struct ice_vsi *vsi = rx_ring->vsi; + struct ice_vsi *control_vsi; + u16 target_vsi_id; + + control_vsi = vsi->back->switchdev.control_vsi; + if (vsi != control_vsi) + return rx_ring->netdev; + + desc = (struct ice_32b_rx_flex_desc_nic_2 *)rx_desc; + target_vsi_id = le16_to_cpu(desc->src_vsi); + + return vsi->target_netdevs[target_vsi_id]; +} + +/** + * ice_eswitch_mode_get - get current eswitch mode + * @devlink: pointer to devlink structure + * @mode: output parameter for current eswitch mode + */ +int ice_eswitch_mode_get(struct devlink *devlink, u16 *mode) +{ + struct ice_pf *pf = devlink_priv(devlink); + + *mode = pf->eswitch_mode; + return 0; +} + +/** + * ice_is_eswitch_mode_switchdev - check if eswitch mode is set to switchdev + * @pf: pointer to PF structure + * + * Returns true if eswitch mode is set to DEVLINK_ESWITCH_MODE_SWITCHDEV, + * false otherwise. + */ +bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf) +{ + return pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV; +} + +/** + * ice_eswitch_release - cleanup eswitch + * @pf: pointer to PF structure + */ +void ice_eswitch_release(struct ice_pf *pf) +{ + if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY) + return; + + ice_eswitch_disable_switchdev(pf); + pf->switchdev.is_running = false; +} + +/** + * ice_eswitch_configure - configure eswitch + * @pf: pointer to PF structure + */ +int ice_eswitch_configure(struct ice_pf *pf) +{ + int status; + + if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY || pf->switchdev.is_running) + return 0; + + status = ice_eswitch_enable_switchdev(pf); + if (status) + return status; + + pf->switchdev.is_running = true; + return 0; +} + +/** + * ice_eswitch_start_all_tx_queues - start Tx queues of all port representors + * @pf: pointer to PF structure + */ +static void ice_eswitch_start_all_tx_queues(struct ice_pf *pf) +{ + struct ice_repr *repr; + int i; + + if (test_bit(ICE_DOWN, pf->state)) + return; + + ice_for_each_vf(pf, i) { + repr = pf->vf[i].repr; + if (repr) + ice_repr_start_tx_queues(repr); + } +} + +/** + * ice_eswitch_stop_all_tx_queues - stop Tx queues of all port representors + * @pf: pointer to PF structure + */ +void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf) +{ + struct ice_repr *repr; + int i; + + if (test_bit(ICE_DOWN, pf->state)) + return; + + ice_for_each_vf(pf, i) { + repr = pf->vf[i].repr; + if (repr) + ice_repr_stop_tx_queues(repr); + } +} + +/** + * ice_eswitch_rebuild - rebuild eswitch + * @pf: pointer to PF structure + */ +int ice_eswitch_rebuild(struct ice_pf *pf) +{ + struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; + int status; + + ice_eswitch_napi_disable(pf); + ice_eswitch_napi_del(pf); + + status = ice_eswitch_setup_env(pf); + if (status) + return status; + + status = ice_eswitch_setup_reprs(pf); + if (status) + return status; + + ice_eswitch_remap_rings_to_vectors(pf); + + ice_replay_tc_fltrs(pf); + + status = ice_vsi_open(ctrl_vsi); + if (status) + return status; + + ice_eswitch_napi_enable(pf); + ice_eswitch_set_rxdid(ctrl_vsi, ICE_RXDID_FLEX_NIC_2); + ice_eswitch_start_all_tx_queues(pf); + + return 0; +} diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h new file mode 100644 index 000000000000..364cd2a79c37 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_ESWITCH_H_ +#define _ICE_ESWITCH_H_ + +#include <net/devlink.h> + +#ifdef CONFIG_ICE_SWITCHDEV +void ice_eswitch_release(struct ice_pf *pf); +int ice_eswitch_configure(struct ice_pf *pf); +int ice_eswitch_rebuild(struct ice_pf *pf); + +int ice_eswitch_mode_get(struct devlink *devlink, u16 *mode); +int +ice_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack); +bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf); + +void ice_eswitch_update_repr(struct ice_vsi *vsi); + +void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf); + +struct net_device * +ice_eswitch_get_target_netdev(struct ice_rx_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc); + +void ice_eswitch_set_target_vsi(struct sk_buff *skb, + struct ice_tx_offload_params *off); +netdev_tx_t +ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev); +#else /* CONFIG_ICE_SWITCHDEV */ +static inline void ice_eswitch_release(struct ice_pf *pf) { } + +static inline void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf) { } + +static inline void +ice_eswitch_set_target_vsi(struct sk_buff *skb, + struct ice_tx_offload_params *off) { } + +static inline void ice_eswitch_update_repr(struct ice_vsi *vsi) { } + +static inline int ice_eswitch_configure(struct ice_pf *pf) +{ + return -EOPNOTSUPP; +} + +static inline int ice_eswitch_rebuild(struct ice_pf *pf) +{ + return -EOPNOTSUPP; +} + +static inline int ice_eswitch_mode_get(struct devlink *devlink, u16 *mode) +{ + return DEVLINK_ESWITCH_MODE_LEGACY; +} + +static inline int +ice_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf) +{ + return false; +} + +static inline struct net_device * +ice_eswitch_get_target_netdev(struct ice_rx_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc) +{ + return rx_ring->netdev; +} + +static inline netdev_tx_t +ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + return NETDEV_TX_BUSY; +} +#endif /* CONFIG_ICE_SWITCHDEV */ +#endif /* _ICE_ESWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 6f0a29be3ee5..6e0af72c2020 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -170,10 +170,9 @@ static const struct ice_priv_flag ice_gstrings_priv_flags[] = { #define ICE_PRIV_FLAG_ARRAY_SIZE ARRAY_SIZE(ice_gstrings_priv_flags) static void -ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) +__ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo, + struct ice_vsi *vsi) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; struct ice_orom_info *orom; @@ -196,6 +195,26 @@ ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) drvinfo->n_priv_flags = ICE_PRIV_FLAG_ARRAY_SIZE; } +static void +ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + + __ice_get_drvinfo(netdev, drvinfo, np->vsi); +} + +static void +ice_repr_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct ice_repr *repr = ice_netdev_to_repr(netdev); + + if (ice_check_vf_ready_for_cfg(repr->vf)) + return; + + __ice_get_drvinfo(netdev, drvinfo, repr->src_vsi); +} + static int ice_get_regs_len(struct net_device __always_unused *netdev) { return sizeof(ice_regs_dump_list); @@ -584,7 +603,7 @@ static bool ice_lbtest_check_frame(u8 *frame) * * Function sends loopback packets on a test Tx ring. */ -static int ice_diag_send(struct ice_ring *tx_ring, u8 *data, u16 size) +static int ice_diag_send(struct ice_tx_ring *tx_ring, u8 *data, u16 size) { struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; @@ -637,7 +656,7 @@ static int ice_diag_send(struct ice_ring *tx_ring, u8 *data, u16 size) * Function receives loopback packets and verify their correctness. * Returns number of received valid frames. */ -static int ice_lbtest_receive_frames(struct ice_ring *rx_ring) +static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring) { struct ice_rx_buf *rx_buf; int valid_frames, i; @@ -676,9 +695,10 @@ static u64 ice_loopback_test(struct net_device *netdev) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *orig_vsi = np->vsi, *test_vsi; struct ice_pf *pf = orig_vsi->back; - struct ice_ring *tx_ring, *rx_ring; u8 broadcast[ETH_ALEN], ret = 0; int num_frames, valid_frames; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; struct device *dev; u8 *tx_frame; int i; @@ -869,7 +889,7 @@ skip_ol_tests: static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; + struct ice_vsi *vsi = ice_get_netdev_priv_vsi(np); unsigned int i; u8 *p = data; @@ -879,6 +899,9 @@ static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data) ethtool_sprintf(&p, ice_gstrings_vsi_stats[i].stat_string); + if (ice_is_port_repr_netdev(netdev)) + return; + ice_for_each_alloc_txq(vsi, i) { ethtool_sprintf(&p, "tx_queue_%u_packets", i); ethtool_sprintf(&p, "tx_queue_%u_bytes", i); @@ -1308,6 +1331,9 @@ static int ice_get_sset_count(struct net_device *netdev, int sset) * order of strings will suffer from race conditions and are * not safe. */ + if (ice_is_port_repr_netdev(netdev)) + return ICE_VSI_STATS_LEN; + return ICE_ALL_STATS_LEN(netdev); case ETH_SS_TEST: return ICE_TEST_LEN; @@ -1323,9 +1349,10 @@ ice_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats __always_unused *stats, u64 *data) { struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; + struct ice_vsi *vsi = ice_get_netdev_priv_vsi(np); struct ice_pf *pf = vsi->back; - struct ice_ring *ring; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; unsigned int j; int i = 0; char *p; @@ -1339,14 +1366,17 @@ ice_get_ethtool_stats(struct net_device *netdev, sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } + if (ice_is_port_repr_netdev(netdev)) + return; + /* populate per queue stats */ rcu_read_lock(); ice_for_each_alloc_txq(vsi, j) { - ring = READ_ONCE(vsi->tx_rings[j]); - if (ring) { - data[i++] = ring->stats.pkts; - data[i++] = ring->stats.bytes; + tx_ring = READ_ONCE(vsi->tx_rings[j]); + if (tx_ring) { + data[i++] = tx_ring->stats.pkts; + data[i++] = tx_ring->stats.bytes; } else { data[i++] = 0; data[i++] = 0; @@ -1354,10 +1384,10 @@ ice_get_ethtool_stats(struct net_device *netdev, } ice_for_each_alloc_rxq(vsi, j) { - ring = READ_ONCE(vsi->rx_rings[j]); - if (ring) { - data[i++] = ring->stats.pkts; - data[i++] = ring->stats.bytes; + rx_ring = READ_ONCE(vsi->rx_rings[j]); + if (rx_ring) { + data[i++] = rx_ring->stats.pkts; + data[i++] = rx_ring->stats.bytes; } else { data[i++] = 0; data[i++] = 0; @@ -2674,9 +2704,10 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) static int ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) { - struct ice_ring *tx_rings = NULL, *rx_rings = NULL; struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_ring *xdp_rings = NULL; + struct ice_tx_ring *xdp_rings = NULL; + struct ice_tx_ring *tx_rings = NULL; + struct ice_rx_ring *rx_rings = NULL; struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; int i, timeout = 50, err = 0; @@ -2725,12 +2756,12 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) /* set for the next time the netdev is started */ if (!netif_running(vsi->netdev)) { - for (i = 0; i < vsi->alloc_txq; i++) + ice_for_each_alloc_txq(vsi, i) vsi->tx_rings[i]->count = new_tx_cnt; - for (i = 0; i < vsi->alloc_rxq; i++) + ice_for_each_alloc_rxq(vsi, i) vsi->rx_rings[i]->count = new_rx_cnt; if (ice_is_xdp_ena_vsi(vsi)) - for (i = 0; i < vsi->num_xdp_txq; i++) + ice_for_each_xdp_txq(vsi, i) vsi->xdp_rings[i]->count = new_tx_cnt; vsi->num_tx_desc = (u16)new_tx_cnt; vsi->num_rx_desc = (u16)new_rx_cnt; @@ -2779,7 +2810,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) goto free_tx; } - for (i = 0; i < vsi->num_xdp_txq; i++) { + ice_for_each_xdp_txq(vsi, i) { /* clone ring and setup updated count */ xdp_rings[i] = *vsi->xdp_rings[i]; xdp_rings[i].count = new_tx_cnt; @@ -2873,7 +2904,7 @@ process_link: } if (xdp_rings) { - for (i = 0; i < vsi->num_xdp_txq; i++) { + ice_for_each_xdp_txq(vsi, i) { ice_free_tx_ring(vsi->xdp_rings[i]); *vsi->xdp_rings[i] = xdp_rings[i]; } @@ -3262,7 +3293,7 @@ static u32 ice_get_combined_cnt(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, q_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; - if (q_vector->rx.ring && q_vector->tx.ring) + if (q_vector->rx.rx_ring && q_vector->tx.tx_ring) combined++; } @@ -3473,15 +3504,9 @@ static int ice_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) return 0; } -enum ice_container_type { - ICE_RX_CONTAINER, - ICE_TX_CONTAINER, -}; - /** * ice_get_rc_coalesce - get ITR values for specific ring container * @ec: ethtool structure to fill with driver's coalesce settings - * @c_type: container type, Rx or Tx * @rc: ring container that the ITR values will come from * * Query the device for ice_ring_container specific ITR values. This is @@ -3491,24 +3516,23 @@ enum ice_container_type { * Returns 0 on success, negative otherwise. */ static int -ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type, - struct ice_ring_container *rc) +ice_get_rc_coalesce(struct ethtool_coalesce *ec, struct ice_ring_container *rc) { - if (!rc->ring) + if (!rc->rx_ring) return -EINVAL; - switch (c_type) { + switch (rc->type) { case ICE_RX_CONTAINER: ec->use_adaptive_rx_coalesce = ITR_IS_DYNAMIC(rc); ec->rx_coalesce_usecs = rc->itr_setting; - ec->rx_coalesce_usecs_high = rc->ring->q_vector->intrl; + ec->rx_coalesce_usecs_high = rc->rx_ring->q_vector->intrl; break; case ICE_TX_CONTAINER: ec->use_adaptive_tx_coalesce = ITR_IS_DYNAMIC(rc); ec->tx_coalesce_usecs = rc->itr_setting; break; default: - dev_dbg(ice_pf_to_dev(rc->ring->vsi->back), "Invalid c_type %d\n", c_type); + dev_dbg(ice_pf_to_dev(rc->rx_ring->vsi->back), "Invalid c_type %d\n", rc->type); return -EINVAL; } @@ -3529,18 +3553,18 @@ static int ice_get_q_coalesce(struct ice_vsi *vsi, struct ethtool_coalesce *ec, int q_num) { if (q_num < vsi->num_rxq && q_num < vsi->num_txq) { - if (ice_get_rc_coalesce(ec, ICE_RX_CONTAINER, + if (ice_get_rc_coalesce(ec, &vsi->rx_rings[q_num]->q_vector->rx)) return -EINVAL; - if (ice_get_rc_coalesce(ec, ICE_TX_CONTAINER, + if (ice_get_rc_coalesce(ec, &vsi->tx_rings[q_num]->q_vector->tx)) return -EINVAL; } else if (q_num < vsi->num_rxq) { - if (ice_get_rc_coalesce(ec, ICE_RX_CONTAINER, + if (ice_get_rc_coalesce(ec, &vsi->rx_rings[q_num]->q_vector->rx)) return -EINVAL; } else if (q_num < vsi->num_txq) { - if (ice_get_rc_coalesce(ec, ICE_TX_CONTAINER, + if (ice_get_rc_coalesce(ec, &vsi->tx_rings[q_num]->q_vector->tx)) return -EINVAL; } else { @@ -3592,7 +3616,6 @@ ice_get_per_q_coalesce(struct net_device *netdev, u32 q_num, /** * ice_set_rc_coalesce - set ITR values for specific ring container - * @c_type: container type, Rx or Tx * @ec: ethtool structure from user to update ITR settings * @rc: ring container that the ITR values will come from * @vsi: VSI associated to the ring container @@ -3604,18 +3627,18 @@ ice_get_per_q_coalesce(struct net_device *netdev, u32 q_num, * Returns 0 on success, negative otherwise. */ static int -ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, +ice_set_rc_coalesce(struct ethtool_coalesce *ec, struct ice_ring_container *rc, struct ice_vsi *vsi) { - const char *c_type_str = (c_type == ICE_RX_CONTAINER) ? "rx" : "tx"; + const char *c_type_str = (rc->type == ICE_RX_CONTAINER) ? "rx" : "tx"; u32 use_adaptive_coalesce, coalesce_usecs; struct ice_pf *pf = vsi->back; u16 itr_setting; - if (!rc->ring) + if (!rc->rx_ring) return -EINVAL; - switch (c_type) { + switch (rc->type) { case ICE_RX_CONTAINER: if (ec->rx_coalesce_usecs_high > ICE_MAX_INTRL || (ec->rx_coalesce_usecs_high && @@ -3625,15 +3648,15 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, ICE_MAX_INTRL); return -EINVAL; } - if (ec->rx_coalesce_usecs_high != rc->ring->q_vector->intrl && + if (ec->rx_coalesce_usecs_high != rc->rx_ring->q_vector->intrl && (ec->use_adaptive_rx_coalesce || ec->use_adaptive_tx_coalesce)) { netdev_info(vsi->netdev, "Invalid value, %s-usecs-high cannot be changed if adaptive-tx or adaptive-rx is enabled\n", c_type_str); return -EINVAL; } - if (ec->rx_coalesce_usecs_high != rc->ring->q_vector->intrl) { - rc->ring->q_vector->intrl = ec->rx_coalesce_usecs_high; - ice_write_intrl(rc->ring->q_vector, + if (ec->rx_coalesce_usecs_high != rc->rx_ring->q_vector->intrl) { + rc->rx_ring->q_vector->intrl = ec->rx_coalesce_usecs_high; + ice_write_intrl(rc->rx_ring->q_vector, ec->rx_coalesce_usecs_high); } @@ -3648,7 +3671,7 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, break; default: dev_dbg(ice_pf_to_dev(pf), "Invalid container type %d\n", - c_type); + rc->type); return -EINVAL; } @@ -3697,22 +3720,22 @@ static int ice_set_q_coalesce(struct ice_vsi *vsi, struct ethtool_coalesce *ec, int q_num) { if (q_num < vsi->num_rxq && q_num < vsi->num_txq) { - if (ice_set_rc_coalesce(ICE_RX_CONTAINER, ec, + if (ice_set_rc_coalesce(ec, &vsi->rx_rings[q_num]->q_vector->rx, vsi)) return -EINVAL; - if (ice_set_rc_coalesce(ICE_TX_CONTAINER, ec, + if (ice_set_rc_coalesce(ec, &vsi->tx_rings[q_num]->q_vector->tx, vsi)) return -EINVAL; } else if (q_num < vsi->num_rxq) { - if (ice_set_rc_coalesce(ICE_RX_CONTAINER, ec, + if (ice_set_rc_coalesce(ec, &vsi->rx_rings[q_num]->q_vector->rx, vsi)) return -EINVAL; } else if (q_num < vsi->num_txq) { - if (ice_set_rc_coalesce(ICE_TX_CONTAINER, ec, + if (ice_set_rc_coalesce(ec, &vsi->tx_rings[q_num]->q_vector->tx, vsi)) return -EINVAL; @@ -4062,6 +4085,23 @@ void ice_set_ethtool_safe_mode_ops(struct net_device *netdev) netdev->ethtool_ops = &ice_ethtool_safe_mode_ops; } +static const struct ethtool_ops ice_ethtool_repr_ops = { + .get_drvinfo = ice_repr_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_strings = ice_get_strings, + .get_ethtool_stats = ice_get_ethtool_stats, + .get_sset_count = ice_get_sset_count, +}; + +/** + * ice_set_ethtool_repr_ops - setup VF's port representor ethtool ops + * @netdev: network interface device structure + */ +void ice_set_ethtool_repr_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &ice_ethtool_repr_ops; +} + /** * ice_set_ethtool_ops - setup netdev ethtool ops * @netdev: network interface device structure diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 06ac9badee77..5e8f3256f8ea 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -735,7 +735,7 @@ static void ice_release_global_cfg_lock(struct ice_hw *hw) * * This function will request ownership of the change lock. */ -static enum ice_status +enum ice_status ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access) { return ice_acquire_res(hw, ICE_CHANGE_LOCK_RES_ID, access, @@ -748,7 +748,7 @@ ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access) * * This function will release the change lock using the proper Admin Command. */ -static void ice_release_change_lock(struct ice_hw *hw) +void ice_release_change_lock(struct ice_hw *hw) { ice_release_res(hw, ICE_CHANGE_LOCK_RES_ID); } @@ -1330,6 +1330,86 @@ fw_ddp_compat_free_alloc: } /** + * ice_sw_fv_handler + * @sect_type: section type + * @section: pointer to section + * @index: index of the field vector entry to be returned + * @offset: ptr to variable that receives the offset in the field vector table + * + * This is a callback function that can be passed to ice_pkg_enum_entry. + * This function treats the given section as of type ice_sw_fv_section and + * enumerates offset field. "offset" is an index into the field vector table. + */ +static void * +ice_sw_fv_handler(u32 sect_type, void *section, u32 index, u32 *offset) +{ + struct ice_sw_fv_section *fv_section = section; + + if (!section || sect_type != ICE_SID_FLD_VEC_SW) + return NULL; + if (index >= le16_to_cpu(fv_section->count)) + return NULL; + if (offset) + /* "index" passed in to this function is relative to a given + * 4k block. To get to the true index into the field vector + * table need to add the relative index to the base_offset + * field of this section + */ + *offset = le16_to_cpu(fv_section->base_offset) + index; + return fv_section->fv + index; +} + +/** + * ice_get_prof_index_max - get the max profile index for used profile + * @hw: pointer to the HW struct + * + * Calling this function will get the max profile index for used profile + * and store the index number in struct ice_switch_info *switch_info + * in HW for following use. + */ +static enum ice_status ice_get_prof_index_max(struct ice_hw *hw) +{ + u16 prof_index = 0, j, max_prof_index = 0; + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + bool flag = false; + struct ice_fv *fv; + u32 offset; + + memset(&state, 0, sizeof(state)); + + if (!hw->seg) + return ICE_ERR_PARAM; + + ice_seg = hw->seg; + + do { + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &offset, ice_sw_fv_handler); + if (!fv) + break; + ice_seg = NULL; + + /* in the profile that not be used, the prot_id is set to 0xff + * and the off is set to 0x1ff for all the field vectors. + */ + for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) + if (fv->ew[j].prot_id != ICE_PROT_INVALID || + fv->ew[j].off != ICE_FV_OFFSET_INVAL) + flag = true; + if (flag && prof_index > max_prof_index) + max_prof_index = prof_index; + + prof_index++; + flag = false; + } while (fv); + + hw->switch_info->max_used_prof_index = max_prof_index; + + return 0; +} + +/** * ice_init_pkg - initialize/download package * @hw: pointer to the hardware structure * @buf: pointer to the package buffer @@ -1408,6 +1488,7 @@ enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) */ ice_init_pkg_regs(hw); ice_fill_blk_tbls(hw); + ice_get_prof_index_max(hw); } else { ice_debug(hw, ICE_DBG_INIT, "package load failed, %d\n", status); @@ -1485,6 +1566,167 @@ static struct ice_buf_build *ice_pkg_buf_alloc(struct ice_hw *hw) } /** + * ice_get_sw_fv_bitmap - Get switch field vector bitmap based on profile type + * @hw: pointer to hardware structure + * @req_profs: type of profiles requested + * @bm: pointer to memory for returning the bitmap of field vectors + */ +void +ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type req_profs, + unsigned long *bm) +{ + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + struct ice_fv *fv; + + if (req_profs == ICE_PROF_ALL) { + bitmap_set(bm, 0, ICE_MAX_NUM_PROFILES); + return; + } + + memset(&state, 0, sizeof(state)); + bitmap_zero(bm, ICE_MAX_NUM_PROFILES); + ice_seg = hw->seg; + do { + u32 offset; + + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &offset, ice_sw_fv_handler); + ice_seg = NULL; + + if (fv) { + if (req_profs & ICE_PROF_NON_TUN) + set_bit((u16)offset, bm); + } + } while (fv); +} + +/** + * ice_get_sw_fv_list + * @hw: pointer to the HW structure + * @prot_ids: field vector to search for with a given protocol ID + * @ids_cnt: lookup/protocol count + * @bm: bitmap of field vectors to consider + * @fv_list: Head of a list + * + * Finds all the field vector entries from switch block that contain + * a given protocol ID and returns a list of structures of type + * "ice_sw_fv_list_entry". Every structure in the list has a field vector + * definition and profile ID information + * NOTE: The caller of the function is responsible for freeing the memory + * allocated for every list entry. + */ +enum ice_status +ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, + unsigned long *bm, struct list_head *fv_list) +{ + struct ice_sw_fv_list_entry *fvl; + struct ice_sw_fv_list_entry *tmp; + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + struct ice_fv *fv; + u32 offset; + + memset(&state, 0, sizeof(state)); + + if (!ids_cnt || !hw->seg) + return ICE_ERR_PARAM; + + ice_seg = hw->seg; + do { + u16 i; + + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &offset, ice_sw_fv_handler); + if (!fv) + break; + ice_seg = NULL; + + /* If field vector is not in the bitmap list, then skip this + * profile. + */ + if (!test_bit((u16)offset, bm)) + continue; + + for (i = 0; i < ids_cnt; i++) { + int j; + + /* This code assumes that if a switch field vector line + * has a matching protocol, then this line will contain + * the entries necessary to represent every field in + * that protocol header. + */ + for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) + if (fv->ew[j].prot_id == prot_ids[i]) + break; + if (j >= hw->blk[ICE_BLK_SW].es.fvw) + break; + if (i + 1 == ids_cnt) { + fvl = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*fvl), GFP_KERNEL); + if (!fvl) + goto err; + fvl->fv_ptr = fv; + fvl->profile_id = offset; + list_add(&fvl->list_entry, fv_list); + break; + } + } + } while (fv); + if (list_empty(fv_list)) + return ICE_ERR_CFG; + return 0; + +err: + list_for_each_entry_safe(fvl, tmp, fv_list, list_entry) { + list_del(&fvl->list_entry); + devm_kfree(ice_hw_to_dev(hw), fvl); + } + + return ICE_ERR_NO_MEMORY; +} + +/** + * ice_init_prof_result_bm - Initialize the profile result index bitmap + * @hw: pointer to hardware structure + */ +void ice_init_prof_result_bm(struct ice_hw *hw) +{ + struct ice_pkg_enum state; + struct ice_seg *ice_seg; + struct ice_fv *fv; + + memset(&state, 0, sizeof(state)); + + if (!hw->seg) + return; + + ice_seg = hw->seg; + do { + u32 off; + u16 i; + + fv = ice_pkg_enum_entry(ice_seg, &state, ICE_SID_FLD_VEC_SW, + &off, ice_sw_fv_handler); + ice_seg = NULL; + if (!fv) + break; + + bitmap_zero(hw->switch_info->prof_res_bm[off], + ICE_MAX_FV_WORDS); + + /* Determine empty field vector indices, these can be + * used for recipe results. Skip index 0, since it is + * always used for Switch ID. + */ + for (i = 1; i < ICE_MAX_FV_WORDS; i++) + if (fv->ew[i].prot_id == ICE_PROT_INVALID && + fv->ew[i].off == ICE_FV_OFFSET_INVAL) + set_bit(i, hw->switch_info->prof_res_bm[off]); + } while (fv); +} + +/** * ice_pkg_buf_free * @hw: pointer to the HW structure * @bld: pointer to pkg build (allocated by ice_pkg_buf_alloc()) @@ -1863,6 +2105,35 @@ int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, return 0; } +/** + * ice_find_prot_off - find prot ID and offset pair, based on prof and FV index + * @hw: pointer to the hardware structure + * @blk: hardware block + * @prof: profile ID + * @fv_idx: field vector word index + * @prot: variable to receive the protocol ID + * @off: variable to receive the protocol offset + */ +enum ice_status +ice_find_prot_off(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 fv_idx, + u8 *prot, u16 *off) +{ + struct ice_fv_word *fv_ext; + + if (prof >= hw->blk[blk].es.count) + return ICE_ERR_PARAM; + + if (fv_idx >= hw->blk[blk].es.fvw) + return ICE_ERR_PARAM; + + fv_ext = hw->blk[blk].es.t + (prof * hw->blk[blk].es.fvw); + + *prot = fv_ext[fv_idx].prot_id; + *off = fv_ext[fv_idx].off; + + return 0; +} + /* PTG Management */ /** diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index 8a58e79729b9..344c2637facd 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -18,6 +18,20 @@ #define ICE_PKG_CNT 4 +enum ice_status +ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access); +void ice_release_change_lock(struct ice_hw *hw); +enum ice_status +ice_find_prot_off(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 fv_idx, + u8 *prot, u16 *off); +void +ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type type, + unsigned long *bm); +void +ice_init_prof_result_bm(struct ice_hw *hw); +enum ice_status +ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, + unsigned long *bm, struct list_head *fv_list); bool ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port); int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h index 7d8b517a63c9..120bcebaa080 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_type.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -13,6 +13,8 @@ struct ice_fv_word { u8 resvrd; } __packed; +#define ICE_MAX_NUM_PROFILES 256 + #define ICE_MAX_FV_WORDS 48 struct ice_fv { struct ice_fv_word ew[ICE_MAX_FV_WORDS]; @@ -279,6 +281,12 @@ struct ice_sw_fv_section { struct ice_fv fv[]; }; +struct ice_sw_fv_list_entry { + struct list_head list_entry; + u32 profile_id; + struct ice_fv *fv_ptr; +}; + /* The BOOST TCAM stores the match packet header in reverse order, meaning * the fields are reversed; in addition, this means that the normally big endian * fields of the packet are now little endian. @@ -603,4 +611,9 @@ struct ice_chs_chg { }; #define ICE_FLOW_PTYPE_MAX ICE_XLT1_CNT + +enum ice_prof_type { + ICE_PROF_NON_TUN = 0x1, + ICE_PROF_ALL = 0xFF, +}; #endif /* _ICE_FLEX_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index 2418d4fff037..f8c59df4ff9c 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -395,3 +395,210 @@ enum ice_status ice_fltr_remove_eth(struct ice_vsi *vsi, u16 ethertype, return ice_fltr_prepare_eth(vsi, ethertype, flag, action, ice_fltr_remove_eth_list); } + +/** + * ice_fltr_update_rule_flags - update lan_en/lb_en flags + * @hw: pointer to hw + * @rule_id: id of rule being updated + * @recipe_id: recipe id of rule + * @act: current action field + * @type: Rx or Tx + * @src: source VSI + * @new_flags: combinations of lb_en and lan_en + */ +static enum ice_status +ice_fltr_update_rule_flags(struct ice_hw *hw, u16 rule_id, u16 recipe_id, + u32 act, u16 type, u16 src, u32 new_flags) +{ + struct ice_aqc_sw_rules_elem *s_rule; + enum ice_status err; + u32 flags_mask; + + s_rule = kzalloc(ICE_SW_RULE_RX_TX_NO_HDR_SIZE, GFP_KERNEL); + if (!s_rule) + return ICE_ERR_NO_MEMORY; + + flags_mask = ICE_SINGLE_ACT_LB_ENABLE | ICE_SINGLE_ACT_LAN_ENABLE; + act &= ~flags_mask; + act |= (flags_mask & new_flags); + + s_rule->pdata.lkup_tx_rx.recipe_id = cpu_to_le16(recipe_id); + s_rule->pdata.lkup_tx_rx.index = cpu_to_le16(rule_id); + s_rule->pdata.lkup_tx_rx.act = cpu_to_le32(act); + + if (type & ICE_FLTR_RX) { + s_rule->pdata.lkup_tx_rx.src = + cpu_to_le16(hw->port_info->lport); + s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + + } else { + s_rule->pdata.lkup_tx_rx.src = cpu_to_le16(src); + s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_TX); + } + + err = ice_aq_sw_rules(hw, s_rule, ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1, + ice_aqc_opc_update_sw_rules, NULL); + + kfree(s_rule); + return err; +} + +/** + * ice_fltr_build_action - build action for rule + * @vsi_id: id of VSI which is use to build action + */ +static u32 ice_fltr_build_action(u16 vsi_id) +{ + return ((vsi_id << ICE_SINGLE_ACT_VSI_ID_S) & ICE_SINGLE_ACT_VSI_ID_M) | + ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT; +} + +/** + * ice_fltr_find_adv_entry - find advanced rule + * @rules: list of rules + * @rule_id: id of wanted rule + */ +static struct ice_adv_fltr_mgmt_list_entry * +ice_fltr_find_adv_entry(struct list_head *rules, u16 rule_id) +{ + struct ice_adv_fltr_mgmt_list_entry *entry; + + list_for_each_entry(entry, rules, list_entry) { + if (entry->rule_info.fltr_rule_id == rule_id) + return entry; + } + + return NULL; +} + +/** + * ice_fltr_update_adv_rule_flags - update flags on advanced rule + * @vsi: pointer to VSI + * @recipe_id: id of recipe + * @entry: advanced rule entry + * @new_flags: flags to update + */ +static enum ice_status +ice_fltr_update_adv_rule_flags(struct ice_vsi *vsi, u16 recipe_id, + struct ice_adv_fltr_mgmt_list_entry *entry, + u32 new_flags) +{ + struct ice_adv_rule_info *info = &entry->rule_info; + struct ice_sw_act_ctrl *act = &info->sw_act; + u32 action; + + if (act->fltr_act != ICE_FWD_TO_VSI) + return ICE_ERR_NOT_SUPPORTED; + + action = ice_fltr_build_action(act->fwd_id.hw_vsi_id); + + return ice_fltr_update_rule_flags(&vsi->back->hw, info->fltr_rule_id, + recipe_id, action, info->sw_act.flag, + act->src, new_flags); +} + +/** + * ice_fltr_find_regular_entry - find regular rule + * @rules: list of rules + * @rule_id: id of wanted rule + */ +static struct ice_fltr_mgmt_list_entry * +ice_fltr_find_regular_entry(struct list_head *rules, u16 rule_id) +{ + struct ice_fltr_mgmt_list_entry *entry; + + list_for_each_entry(entry, rules, list_entry) { + if (entry->fltr_info.fltr_rule_id == rule_id) + return entry; + } + + return NULL; +} + +/** + * ice_fltr_update_regular_rule - update flags on regular rule + * @vsi: pointer to VSI + * @recipe_id: id of recipe + * @entry: regular rule entry + * @new_flags: flags to update + */ +static enum ice_status +ice_fltr_update_regular_rule(struct ice_vsi *vsi, u16 recipe_id, + struct ice_fltr_mgmt_list_entry *entry, + u32 new_flags) +{ + struct ice_fltr_info *info = &entry->fltr_info; + u32 action; + + if (info->fltr_act != ICE_FWD_TO_VSI) + return ICE_ERR_NOT_SUPPORTED; + + action = ice_fltr_build_action(info->fwd_id.hw_vsi_id); + + return ice_fltr_update_rule_flags(&vsi->back->hw, info->fltr_rule_id, + recipe_id, action, info->flag, + info->src, new_flags); +} + +/** + * ice_fltr_update_flags - update flags on rule + * @vsi: pointer to VSI + * @rule_id: id of rule + * @recipe_id: id of recipe + * @new_flags: flags to update + * + * Function updates flags on regular and advance rule. + * + * Flags should be a combination of ICE_SINGLE_ACT_LB_ENABLE and + * ICE_SINGLE_ACT_LAN_ENABLE. + */ +enum ice_status +ice_fltr_update_flags(struct ice_vsi *vsi, u16 rule_id, u16 recipe_id, + u32 new_flags) +{ + struct ice_adv_fltr_mgmt_list_entry *adv_entry; + struct ice_fltr_mgmt_list_entry *regular_entry; + struct ice_hw *hw = &vsi->back->hw; + struct ice_sw_recipe *recp_list; + struct list_head *fltr_rules; + + recp_list = &hw->switch_info->recp_list[recipe_id]; + if (!recp_list) + return ICE_ERR_DOES_NOT_EXIST; + + fltr_rules = &recp_list->filt_rules; + regular_entry = ice_fltr_find_regular_entry(fltr_rules, rule_id); + if (regular_entry) + return ice_fltr_update_regular_rule(vsi, recipe_id, + regular_entry, new_flags); + + adv_entry = ice_fltr_find_adv_entry(fltr_rules, rule_id); + if (adv_entry) + return ice_fltr_update_adv_rule_flags(vsi, recipe_id, + adv_entry, new_flags); + + return ICE_ERR_DOES_NOT_EXIST; +} + +/** + * ice_fltr_update_flags_dflt_rule - update flags on default rule + * @vsi: pointer to VSI + * @rule_id: id of rule + * @direction: Tx or Rx + * @new_flags: flags to update + * + * Function updates flags on default rule with ICE_SW_LKUP_DFLT. + * + * Flags should be a combination of ICE_SINGLE_ACT_LB_ENABLE and + * ICE_SINGLE_ACT_LAN_ENABLE. + */ +enum ice_status +ice_fltr_update_flags_dflt_rule(struct ice_vsi *vsi, u16 rule_id, u8 direction, + u32 new_flags) +{ + u32 action = ice_fltr_build_action(vsi->vsi_num); + struct ice_hw *hw = &vsi->back->hw; + + return ice_fltr_update_rule_flags(hw, rule_id, ICE_SW_LKUP_DFLT, action, + direction, vsi->vsi_num, new_flags); +} diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.h b/drivers/net/ethernet/intel/ice/ice_fltr.h index 361cb4da9b43..949e38ce016c 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.h +++ b/drivers/net/ethernet/intel/ice/ice_fltr.h @@ -36,4 +36,11 @@ enum ice_status ice_fltr_remove_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, enum ice_sw_fwd_act_type action); void ice_fltr_remove_all(struct ice_vsi *vsi); + +enum ice_status +ice_fltr_update_flags(struct ice_vsi *vsi, u16 rule_id, u16 recipe_id, + u32 new_flags); +enum ice_status +ice_fltr_update_flags_dflt_rule(struct ice_vsi *vsi, u16 rule_id, u8 direction, + u32 new_flags); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 80736e0ec0dc..d981dc6f2323 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -301,6 +301,46 @@ struct ice_32b_rx_flex_desc_nic { } flex_ts; }; +/* Rx Flex Descriptor NIC Profile + * RxDID Profile ID 6 + * Flex-field 0: RSS hash lower 16-bits + * Flex-field 1: RSS hash upper 16-bits + * Flex-field 2: Flow ID lower 16-bits + * Flex-field 3: Source VSI + * Flex-field 4: reserved, VLAN ID taken from L2Tag + */ +struct ice_32b_rx_flex_desc_nic_2 { + /* Qword 0 */ + u8 rxdid; + u8 mir_id_umb_cast; + __le16 ptype_flexi_flags0; + __le16 pkt_len; + __le16 hdr_len_sph_flex_flags1; + + /* Qword 1 */ + __le16 status_error0; + __le16 l2tag1; + __le32 rss_hash; + + /* Qword 2 */ + __le16 status_error1; + u8 flexi_flags2; + u8 ts_low; + __le16 l2tag2_1st; + __le16 l2tag2_2nd; + + /* Qword 3 */ + __le16 flow_id; + __le16 src_vsi; + union { + struct { + __le16 rsvd; + __le16 flow_id_ipv6; + } flex; + __le32 ts_high; + } flex_ts; +}; + /* Receive Flex Descriptor profile IDs: There are a total * of 64 profiles where profile IDs 0/1 are for legacy; and * profiles 2-63 are flex profiles that can be programmed @@ -529,6 +569,9 @@ struct ice_tx_ctx_desc { #define ICE_TXD_CTX_QW1_MSS_S 50 +#define ICE_TXD_CTX_QW1_VSI_S 50 +#define ICE_TXD_CTX_QW1_VSI_M (0x3FFULL << ICE_TXD_CTX_QW1_VSI_S) + enum ice_tx_ctx_desc_cmd_bits { ICE_TX_CTX_DESC_TSO = 0x01, ICE_TX_CTX_DESC_TSYN = 0x02, diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 3adbd9a179a7..f981e77f72ad 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -24,6 +24,8 @@ const char *ice_vsi_type_str(enum ice_vsi_type vsi_type) return "ICE_VSI_CTRL"; case ICE_VSI_LB: return "ICE_VSI_LB"; + case ICE_VSI_SWITCHDEV_CTRL: + return "ICE_VSI_SWITCHDEV_CTRL"; default: return "unknown"; } @@ -44,12 +46,12 @@ static int ice_vsi_ctrl_all_rx_rings(struct ice_vsi *vsi, bool ena) int ret = 0; u16 i; - for (i = 0; i < vsi->num_rxq; i++) + ice_for_each_rxq(vsi, i) ice_vsi_ctrl_one_rx_ring(vsi, ena, i, false); ice_flush(&vsi->back->hw); - for (i = 0; i < vsi->num_rxq; i++) { + ice_for_each_rxq(vsi, i) { ret = ice_vsi_wait_one_rx_ring(vsi, ena, i); if (ret) break; @@ -132,6 +134,7 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) { switch (vsi->type) { case ICE_VSI_PF: + case ICE_VSI_SWITCHDEV_CTRL: case ICE_VSI_CTRL: case ICE_VSI_LB: /* a user could change the values of num_[tr]x_desc using @@ -200,6 +203,14 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) max_t(int, vsi->alloc_rxq, vsi->alloc_txq)); break; + case ICE_VSI_SWITCHDEV_CTRL: + /* The number of queues for ctrl VSI is equal to number of VFs. + * Each ring is associated to the corresponding VF_PR netdev. + */ + vsi->alloc_txq = pf->num_alloc_vfs; + vsi->alloc_rxq = pf->num_alloc_vfs; + vsi->num_q_vectors = 1; + break; case ICE_VSI_VF: vf = &pf->vf[vsi->vf_id]; if (vf->num_req_qs) @@ -379,12 +390,12 @@ static irqreturn_t ice_msix_clean_ctrl_vsi(int __always_unused irq, void *data) { struct ice_q_vector *q_vector = (struct ice_q_vector *)data; - if (!q_vector->tx.ring) + if (!q_vector->tx.tx_ring) return IRQ_HANDLED; #define FDIR_RX_DESC_CLEAN_BUDGET 64 - ice_clean_rx_irq(q_vector->rx.ring, FDIR_RX_DESC_CLEAN_BUDGET); - ice_clean_ctrl_tx_irq(q_vector->tx.ring); + ice_clean_rx_irq(q_vector->rx.rx_ring, FDIR_RX_DESC_CLEAN_BUDGET); + ice_clean_ctrl_tx_irq(q_vector->tx.tx_ring); return IRQ_HANDLED; } @@ -398,7 +409,7 @@ static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) { struct ice_q_vector *q_vector = (struct ice_q_vector *)data; - if (!q_vector->tx.ring && !q_vector->rx.ring) + if (!q_vector->tx.tx_ring && !q_vector->rx.rx_ring) return IRQ_HANDLED; q_vector->total_events++; @@ -408,6 +419,21 @@ static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) return IRQ_HANDLED; } +static irqreturn_t ice_eswitch_msix_clean_rings(int __always_unused irq, void *data) +{ + struct ice_q_vector *q_vector = (struct ice_q_vector *)data; + struct ice_pf *pf = q_vector->vsi->back; + int i; + + if (!q_vector->tx.tx_ring && !q_vector->rx.rx_ring) + return IRQ_HANDLED; + + ice_for_each_vf(pf, i) + napi_schedule(&pf->vf[i].repr->q_vector->napi); + + return IRQ_HANDLED; +} + /** * ice_vsi_alloc - Allocates the next available struct VSI in the PF * @pf: board private structure @@ -448,6 +474,13 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, u16 vf_id) ice_vsi_set_num_qs(vsi, ICE_INVAL_VFID); switch (vsi->type) { + case ICE_VSI_SWITCHDEV_CTRL: + if (ice_vsi_alloc_arrays(vsi)) + goto err_rings; + + /* Setup eswitch MSIX irq handler for VSI */ + vsi->irq_handler = ice_eswitch_msix_clean_rings; + break; case ICE_VSI_PF: if (ice_vsi_alloc_arrays(vsi)) goto err_rings; @@ -606,12 +639,12 @@ static void ice_vsi_put_qs(struct ice_vsi *vsi) mutex_lock(&pf->avail_q_mutex); - for (i = 0; i < vsi->alloc_txq; i++) { + ice_for_each_alloc_txq(vsi, i) { clear_bit(vsi->txq_map[i], pf->avail_txqs); vsi->txq_map[i] = ICE_INVAL_Q_INDEX; } - for (i = 0; i < vsi->alloc_rxq; i++) { + ice_for_each_alloc_rxq(vsi, i) { clear_bit(vsi->rxq_map[i], pf->avail_rxqs); vsi->rxq_map[i] = ICE_INVAL_Q_INDEX; } @@ -707,6 +740,12 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) BIT(cap->rss_table_entry_width)); vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF; break; + case ICE_VSI_SWITCHDEV_CTRL: + vsi->rss_table_size = ICE_VSIQF_HLUT_ARRAY_SIZE; + vsi->rss_size = min_t(u16, num_online_cpus(), + BIT(cap->rss_table_entry_width)); + vsi->rss_lut_type = ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_VSI; + break; case ICE_VSI_VF: /* VF VSI will get a small RSS table. * For VSI_LUT, LUT size should be set to 64 bytes. @@ -980,6 +1019,9 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) case ICE_VSI_PF: ctxt->flags = ICE_AQ_VSI_TYPE_PF; break; + case ICE_VSI_SWITCHDEV_CTRL: + ctxt->flags = ICE_AQ_VSI_TYPE_VMDQ2; + break; case ICE_VSI_VF: ctxt->flags = ICE_AQ_VSI_TYPE_VF; /* VF number here is the absolute VF number (0-255) */ @@ -1249,14 +1291,14 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi) struct ice_q_vector *q_vector = vsi->q_vectors[i]; if (q_vector) { - q_vector->tx.ring = NULL; - q_vector->rx.ring = NULL; + q_vector->tx.tx_ring = NULL; + q_vector->rx.rx_ring = NULL; } } } if (vsi->tx_rings) { - for (i = 0; i < vsi->alloc_txq; i++) { + ice_for_each_alloc_txq(vsi, i) { if (vsi->tx_rings[i]) { kfree_rcu(vsi->tx_rings[i], rcu); WRITE_ONCE(vsi->tx_rings[i], NULL); @@ -1264,7 +1306,7 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi) } } if (vsi->rx_rings) { - for (i = 0; i < vsi->alloc_rxq; i++) { + ice_for_each_alloc_rxq(vsi, i) { if (vsi->rx_rings[i]) { kfree_rcu(vsi->rx_rings[i], rcu); WRITE_ONCE(vsi->rx_rings[i], NULL); @@ -1285,8 +1327,8 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) dev = ice_pf_to_dev(pf); /* Allocate Tx rings */ - for (i = 0; i < vsi->alloc_txq; i++) { - struct ice_ring *ring; + ice_for_each_alloc_txq(vsi, i) { + struct ice_tx_ring *ring; /* allocate with kzalloc(), free with kfree_rcu() */ ring = kzalloc(sizeof(*ring), GFP_KERNEL); @@ -1296,7 +1338,6 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->q_index = i; ring->reg_idx = vsi->txq_map[i]; - ring->ring_active = false; ring->vsi = vsi; ring->tx_tstamps = &pf->ptp.port.tx; ring->dev = dev; @@ -1305,8 +1346,8 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) } /* Allocate Rx rings */ - for (i = 0; i < vsi->alloc_rxq; i++) { - struct ice_ring *ring; + ice_for_each_alloc_rxq(vsi, i) { + struct ice_rx_ring *ring; /* allocate with kzalloc(), free with kfree_rcu() */ ring = kzalloc(sizeof(*ring), GFP_KERNEL); @@ -1315,7 +1356,6 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->q_index = i; ring->reg_idx = vsi->rxq_map[i]; - ring->ring_active = false; ring->vsi = vsi; ring->netdev = vsi->netdev; ring->dev = dev; @@ -1710,7 +1750,7 @@ int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) return ice_vsi_cfg_rxq(vsi->rx_rings[q_idx]); } -int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_ring **tx_rings, u16 q_idx) +int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, u16 q_idx) { struct ice_aqc_add_tx_qgrp *qg_buf; int err; @@ -1766,7 +1806,7 @@ setup_rings: * Configure the Tx VSI for operation. */ static int -ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, u16 count) +ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_tx_ring **rings, u16 count) { struct ice_aqc_add_tx_qgrp *qg_buf; u16 q_idx = 0; @@ -1817,8 +1857,8 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi) if (ret) return ret; - for (i = 0; i < vsi->num_xdp_txq; i++) - vsi->xdp_rings[i]->xsk_pool = ice_xsk_pool(vsi->xdp_rings[i]); + ice_for_each_xdp_txq(vsi, i) + vsi->xdp_rings[i]->xsk_pool = ice_tx_xsk_pool(vsi->xdp_rings[i]); return ret; } @@ -1853,6 +1893,23 @@ void ice_write_intrl(struct ice_q_vector *q_vector, u8 intrl) ice_intrl_usec_to_reg(intrl, ICE_INTRL_GRAN_ABOVE_25)); } +static struct ice_q_vector *ice_pull_qvec_from_rc(struct ice_ring_container *rc) +{ + switch (rc->type) { + case ICE_RX_CONTAINER: + if (rc->rx_ring) + return rc->rx_ring->q_vector; + break; + case ICE_TX_CONTAINER: + if (rc->tx_ring) + return rc->tx_ring->q_vector; + default: + break; + } + + return NULL; +} + /** * __ice_write_itr - write throttle rate to register * @q_vector: pointer to interrupt data structure @@ -1877,11 +1934,10 @@ void ice_write_itr(struct ice_ring_container *rc, u16 itr) { struct ice_q_vector *q_vector; - if (!rc->ring) + q_vector = ice_pull_qvec_from_rc(rc); + if (!q_vector) return; - q_vector = rc->ring->q_vector; - __ice_write_itr(q_vector, rc, itr); } @@ -1899,7 +1955,7 @@ void ice_vsi_cfg_msix(struct ice_vsi *vsi) u16 txq = 0, rxq = 0; int i, q; - for (i = 0; i < vsi->num_q_vectors; i++) { + ice_for_each_q_vector(vsi, i) { struct ice_q_vector *q_vector = vsi->q_vectors[i]; u16 reg_idx = q_vector->reg_idx; @@ -2057,7 +2113,7 @@ int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi) */ static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring **rings, u16 count) + u16 rel_vmvf_num, struct ice_tx_ring **rings, u16 count) { u16 q_idx; @@ -2297,6 +2353,7 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) case ICE_VSI_CTRL: case ICE_VSI_LB: case ICE_VSI_PF: + case ICE_VSI_SWITCHDEV_CTRL: max_agg_nodes = ICE_MAX_PF_AGG_NODES; agg_node_id_start = ICE_PF_AGG_NODE_ID_START; agg_node_iter = &pf->pf_agg_node[0]; @@ -2448,6 +2505,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, switch (vsi->type) { case ICE_VSI_CTRL: + case ICE_VSI_SWITCHDEV_CTRL: case ICE_VSI_PF: ret = ice_vsi_alloc_q_vectors(vsi); if (ret) @@ -2591,7 +2649,7 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi) u32 rxq = 0; int i, q; - for (i = 0; i < vsi->num_q_vectors; i++) { + ice_for_each_q_vector(vsi, i) { struct ice_q_vector *q_vector = vsi->q_vectors[i]; ice_write_intrl(q_vector, 0); @@ -2757,7 +2815,8 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) } else { ice_vsi_close(vsi); } - } else if (vsi->type == ICE_VSI_CTRL) { + } else if (vsi->type == ICE_VSI_CTRL || + vsi->type == ICE_VSI_SWITCHDEV_CTRL) { ice_vsi_close(vsi); } } @@ -2859,7 +2918,8 @@ int ice_vsi_release(struct ice_vsi *vsi) clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); } - ice_devlink_destroy_port(vsi); + if (vsi->type == ICE_VSI_PF) + ice_devlink_destroy_pf_port(pf); if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) ice_rss_clean(vsi); @@ -3135,6 +3195,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) switch (vtype) { case ICE_VSI_CTRL: + case ICE_VSI_SWITCHDEV_CTRL: case ICE_VSI_PF: ret = ice_vsi_alloc_q_vectors(vsi); if (ret) @@ -3154,7 +3215,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) ice_vsi_map_rings_to_vectors(vsi); if (ice_is_xdp_ena_vsi(vsi)) { - vsi->num_xdp_txq = vsi->alloc_rxq; + ret = ice_vsi_determine_xdp_res(vsi); + if (ret) + goto err_vectors; ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog); if (ret) goto err_vectors; @@ -3351,16 +3414,16 @@ out: /** * ice_update_ring_stats - Update ring statistics - * @ring: ring to update + * @stats: stats to be updated * @pkts: number of processed packets * @bytes: number of processed bytes * * This function assumes that caller has acquired a u64_stats_sync lock. */ -static void ice_update_ring_stats(struct ice_ring *ring, u64 pkts, u64 bytes) +static void ice_update_ring_stats(struct ice_q_stats *stats, u64 pkts, u64 bytes) { - ring->stats.bytes += bytes; - ring->stats.pkts += pkts; + stats->bytes += bytes; + stats->pkts += pkts; } /** @@ -3369,10 +3432,10 @@ static void ice_update_ring_stats(struct ice_ring *ring, u64 pkts, u64 bytes) * @pkts: number of processed packets * @bytes: number of processed bytes */ -void ice_update_tx_ring_stats(struct ice_ring *tx_ring, u64 pkts, u64 bytes) +void ice_update_tx_ring_stats(struct ice_tx_ring *tx_ring, u64 pkts, u64 bytes) { u64_stats_update_begin(&tx_ring->syncp); - ice_update_ring_stats(tx_ring, pkts, bytes); + ice_update_ring_stats(&tx_ring->stats, pkts, bytes); u64_stats_update_end(&tx_ring->syncp); } @@ -3382,10 +3445,10 @@ void ice_update_tx_ring_stats(struct ice_ring *tx_ring, u64 pkts, u64 bytes) * @pkts: number of processed packets * @bytes: number of processed bytes */ -void ice_update_rx_ring_stats(struct ice_ring *rx_ring, u64 pkts, u64 bytes) +void ice_update_rx_ring_stats(struct ice_rx_ring *rx_ring, u64 pkts, u64 bytes) { u64_stats_update_begin(&rx_ring->syncp); - ice_update_ring_stats(rx_ring, pkts, bytes); + ice_update_ring_stats(&rx_ring->stats, pkts, bytes); u64_stats_update_end(&rx_ring->syncp); } @@ -3603,6 +3666,19 @@ static void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) } /** + * ice_clear_feature_support + * @pf: pointer to the struct ice_pf instance + * @f: feature enum to clear + */ +void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f) +{ + if (f < 0 || f >= ICE_F_MAX) + return; + + clear_bit(f, pf->features); +} + +/** * ice_init_feature_support * @pf: pointer to the struct ice_pf instance * @@ -3615,8 +3691,71 @@ void ice_init_feature_support(struct ice_pf *pf) case ICE_DEV_ID_E810C_QSFP: case ICE_DEV_ID_E810C_SFP: ice_set_feature_support(pf, ICE_F_DSCP); + if (ice_is_e810t(&pf->hw)) + ice_set_feature_support(pf, ICE_F_SMA_CTRL); break; default: break; } } + +/** + * ice_vsi_update_security - update security block in VSI + * @vsi: pointer to VSI structure + * @fill: function pointer to fill ctx + */ +int +ice_vsi_update_security(struct ice_vsi *vsi, void (*fill)(struct ice_vsi_ctx *)) +{ + struct ice_vsi_ctx ctx = { 0 }; + + ctx.info = vsi->info; + ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); + fill(&ctx); + + if (ice_update_vsi(&vsi->back->hw, vsi->idx, &ctx, NULL)) + return -ENODEV; + + vsi->info = ctx.info; + return 0; +} + +/** + * ice_vsi_ctx_set_antispoof - set antispoof function in VSI ctx + * @ctx: pointer to VSI ctx structure + */ +void ice_vsi_ctx_set_antispoof(struct ice_vsi_ctx *ctx) +{ + ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF | + (ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); +} + +/** + * ice_vsi_ctx_clear_antispoof - clear antispoof function in VSI ctx + * @ctx: pointer to VSI ctx structure + */ +void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx) +{ + ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF & + ~(ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); +} + +/** + * ice_vsi_ctx_set_allow_override - allow destination override on VSI + * @ctx: pointer to VSI ctx structure + */ +void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx) +{ + ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; +} + +/** + * ice_vsi_ctx_clear_allow_override - turn off destination override on VSI + * @ctx: pointer to VSI ctx structure + */ +void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx) +{ + ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; +} diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 4512c8513178..b6c429c5875d 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -14,7 +14,7 @@ void ice_update_eth_stats(struct ice_vsi *vsi); int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx); -int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_ring **tx_rings, u16 q_idx); +int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_tx_ring **tx_rings, u16 q_idx); int ice_vsi_cfg_rxqs(struct ice_vsi *vsi); @@ -93,9 +93,9 @@ void ice_vsi_free_tx_rings(struct ice_vsi *vsi); void ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena); -void ice_update_tx_ring_stats(struct ice_ring *ring, u64 pkts, u64 bytes); +void ice_update_tx_ring_stats(struct ice_tx_ring *ring, u64 pkts, u64 bytes); -void ice_update_rx_ring_stats(struct ice_ring *ring, u64 pkts, u64 bytes); +void ice_update_rx_ring_stats(struct ice_rx_ring *ring, u64 pkts, u64 bytes); void ice_vsi_cfg_frame_size(struct ice_vsi *vsi); @@ -116,6 +116,19 @@ bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi); int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi); int ice_clear_dflt_vsi(struct ice_sw *sw); + +int +ice_vsi_update_security(struct ice_vsi *vsi, void (*fill)(struct ice_vsi_ctx *)); + +void ice_vsi_ctx_set_antispoof(struct ice_vsi_ctx *ctx); + +void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx); + +void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx); + +void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx); + bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f); +void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_init_feature_support(struct ice_pf *pf); #endif /* !_ICE_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index cabe84bb29fe..f531691a3e12 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -19,6 +19,8 @@ */ #define CREATE_TRACE_POINTS #include "ice_trace.h" +#include "ice_eswitch.h" +#include "ice_tc_lib.h" #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" static const char ice_driver_string[] = DRV_SUMMARY; @@ -42,11 +44,12 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)"); #endif /* !CONFIG_DYNAMIC_DEBUG */ static DEFINE_IDA(ice_aux_ida); +DEFINE_STATIC_KEY_FALSE(ice_xdp_locking_key); +EXPORT_SYMBOL(ice_xdp_locking_key); static struct workqueue_struct *ice_wq; static const struct net_device_ops ice_netdev_safe_mode_ops; static const struct net_device_ops ice_netdev_ops; -static int ice_vsi_open(struct ice_vsi *vsi); static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type); @@ -61,7 +64,7 @@ bool netif_is_ice(struct net_device *dev) * ice_get_tx_pending - returns number of Tx descriptors not processed * @ring: the ring of descriptors */ -static u16 ice_get_tx_pending(struct ice_ring *ring) +static u16 ice_get_tx_pending(struct ice_tx_ring *ring) { u16 head, tail; @@ -100,8 +103,8 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf) hw = &vsi->back->hw; - for (i = 0; i < vsi->num_txq; i++) { - struct ice_ring *tx_ring = vsi->tx_rings[i]; + ice_for_each_txq(vsi, i) { + struct ice_tx_ring *tx_ring = vsi->tx_rings[i]; if (tx_ring && tx_ring->desc) { /* If packet counter has not changed the queue is @@ -2306,14 +2309,14 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) irq_num = pf->msix_entries[base + vector].vector; - if (q_vector->tx.ring && q_vector->rx.ring) { + if (q_vector->tx.tx_ring && q_vector->rx.rx_ring) { snprintf(q_vector->name, sizeof(q_vector->name) - 1, "%s-%s-%d", basename, "TxRx", rx_int_idx++); tx_int_idx++; - } else if (q_vector->rx.ring) { + } else if (q_vector->rx.rx_ring) { snprintf(q_vector->name, sizeof(q_vector->name) - 1, "%s-%s-%d", basename, "rx", rx_int_idx++); - } else if (q_vector->tx.ring) { + } else if (q_vector->tx.tx_ring) { snprintf(q_vector->name, sizeof(q_vector->name) - 1, "%s-%s-%d", basename, "tx", tx_int_idx++); } else { @@ -2371,11 +2374,12 @@ free_q_irqs: static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) { struct device *dev = ice_pf_to_dev(vsi->back); - int i; + struct ice_tx_desc *tx_desc; + int i, j; - for (i = 0; i < vsi->num_xdp_txq; i++) { + ice_for_each_xdp_txq(vsi, i) { u16 xdp_q_idx = vsi->alloc_txq + i; - struct ice_ring *xdp_ring; + struct ice_tx_ring *xdp_ring; xdp_ring = kzalloc(sizeof(*xdp_ring), GFP_KERNEL); @@ -2384,16 +2388,29 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) xdp_ring->q_index = xdp_q_idx; xdp_ring->reg_idx = vsi->txq_map[xdp_q_idx]; - xdp_ring->ring_active = false; xdp_ring->vsi = vsi; xdp_ring->netdev = NULL; + xdp_ring->next_dd = ICE_TX_THRESH - 1; + xdp_ring->next_rs = ICE_TX_THRESH - 1; xdp_ring->dev = dev; xdp_ring->count = vsi->num_tx_desc; WRITE_ONCE(vsi->xdp_rings[i], xdp_ring); if (ice_setup_tx_ring(xdp_ring)) goto free_xdp_rings; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring); + xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring); + spin_lock_init(&xdp_ring->tx_lock); + for (j = 0; j < xdp_ring->count; j++) { + tx_desc = ICE_TX_DESC(xdp_ring, j); + tx_desc->cmd_type_offset_bsz = cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE); + } + } + + ice_for_each_rxq(vsi, i) { + if (static_key_enabled(&ice_xdp_locking_key)) + vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq]; + else + vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i]; } return 0; @@ -2459,6 +2476,10 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) if (__ice_vsi_get_qs(&xdp_qs_cfg)) goto err_map_xdp; + if (static_key_enabled(&ice_xdp_locking_key)) + netdev_warn(vsi->netdev, + "Could not allocate one XDP Tx ring per CPU, XDP_TX/XDP_REDIRECT actions will be slower\n"); + if (ice_xdp_alloc_setup_rings(vsi)) goto clear_xdp_rings; @@ -2472,11 +2493,11 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) q_base = vsi->num_xdp_txq - xdp_rings_rem; for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) { - struct ice_ring *xdp_ring = vsi->xdp_rings[q_id]; + struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id]; xdp_ring->q_vector = q_vector; - xdp_ring->next = q_vector->tx.ring; - q_vector->tx.ring = xdp_ring; + xdp_ring->next = q_vector->tx.tx_ring; + q_vector->tx.tx_ring = xdp_ring; } xdp_rings_rem -= xdp_rings_per_v; } @@ -2505,7 +2526,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) return 0; clear_xdp_rings: - for (i = 0; i < vsi->num_xdp_txq; i++) + ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { kfree_rcu(vsi->xdp_rings[i], rcu); vsi->xdp_rings[i] = NULL; @@ -2513,7 +2534,7 @@ clear_xdp_rings: err_map_xdp: mutex_lock(&pf->avail_q_mutex); - for (i = 0; i < vsi->num_xdp_txq; i++) { + ice_for_each_xdp_txq(vsi, i) { clear_bit(vsi->txq_map[i + vsi->alloc_txq], pf->avail_txqs); vsi->txq_map[i + vsi->alloc_txq] = ICE_INVAL_Q_INDEX; } @@ -2546,25 +2567,25 @@ int ice_destroy_xdp_rings(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, v_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; - struct ice_ring *ring; + struct ice_tx_ring *ring; - ice_for_each_ring(ring, q_vector->tx) + ice_for_each_tx_ring(ring, q_vector->tx) if (!ring->tx_buf || !ice_ring_is_xdp(ring)) break; /* restore the value of last node prior to XDP setup */ - q_vector->tx.ring = ring; + q_vector->tx.tx_ring = ring; } free_qmap: mutex_lock(&pf->avail_q_mutex); - for (i = 0; i < vsi->num_xdp_txq; i++) { + ice_for_each_xdp_txq(vsi, i) { clear_bit(vsi->txq_map[i + vsi->alloc_txq], pf->avail_txqs); vsi->txq_map[i + vsi->alloc_txq] = ICE_INVAL_Q_INDEX; } mutex_unlock(&pf->avail_q_mutex); - for (i = 0; i < vsi->num_xdp_txq; i++) + ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { if (vsi->xdp_rings[i]->desc) ice_free_tx_ring(vsi->xdp_rings[i]); @@ -2575,6 +2596,9 @@ free_qmap: devm_kfree(ice_pf_to_dev(pf), vsi->xdp_rings); vsi->xdp_rings = NULL; + if (static_key_enabled(&ice_xdp_locking_key)) + static_branch_dec(&ice_xdp_locking_key); + if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0]) return 0; @@ -2602,7 +2626,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi) int i; ice_for_each_rxq(vsi, i) { - struct ice_ring *rx_ring = vsi->rx_rings[i]; + struct ice_rx_ring *rx_ring = vsi->rx_rings[i]; if (rx_ring->xsk_pool) napi_schedule(&rx_ring->q_vector->napi); @@ -2610,6 +2634,29 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi) } /** + * ice_vsi_determine_xdp_res - figure out how many Tx qs can XDP have + * @vsi: VSI to determine the count of XDP Tx qs + * + * returns 0 if Tx qs count is higher than at least half of CPU count, + * -ENOMEM otherwise + */ +int ice_vsi_determine_xdp_res(struct ice_vsi *vsi) +{ + u16 avail = ice_get_avail_txq_count(vsi->back); + u16 cpus = num_possible_cpus(); + + if (avail < cpus / 2) + return -ENOMEM; + + vsi->num_xdp_txq = min_t(u16, avail, cpus); + + if (vsi->num_xdp_txq < cpus) + static_branch_inc(&ice_xdp_locking_key); + + return 0; +} + +/** * ice_xdp_setup_prog - Add or remove XDP eBPF program * @vsi: VSI to setup XDP for * @prog: XDP program @@ -2638,10 +2685,14 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, } if (!ice_is_xdp_ena_vsi(vsi) && prog) { - vsi->num_xdp_txq = vsi->alloc_rxq; - xdp_ring_err = ice_prepare_xdp_rings(vsi, prog); - if (xdp_ring_err) - NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); + xdp_ring_err = ice_vsi_determine_xdp_res(vsi); + if (xdp_ring_err) { + NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP"); + } else { + xdp_ring_err = ice_prepare_xdp_rings(vsi, prog); + if (xdp_ring_err) + NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); + } } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { xdp_ring_err = ice_destroy_xdp_rings(vsi); if (xdp_ring_err) @@ -3107,6 +3158,9 @@ static void ice_set_netdev_features(struct net_device *netdev) /* enable features */ netdev->features |= netdev->hw_features; + + netdev->hw_features |= NETIF_F_HW_TC; + /* encap and VLAN devices inherit default, csumo and tso features */ netdev->hw_enc_features |= dflt_features | csumo_features | tso_features; @@ -3542,6 +3596,13 @@ static int ice_ena_msix_range(struct ice_pf *pf) v_left -= needed; } + /* reserve for switchdev */ + needed = ICE_ESWITCH_MSIX; + if (v_left < needed) + goto no_hw_vecs_left_err; + v_budget += needed; + v_left -= needed; + /* total used for non-traffic vectors */ v_other = v_budget; @@ -4174,11 +4235,11 @@ static int ice_register_netdev(struct ice_pf *pf) set_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); netif_carrier_off(vsi->netdev); netif_tx_stop_all_queues(vsi->netdev); - err = ice_devlink_create_port(vsi); + err = ice_devlink_create_pf_port(pf); if (err) goto err_devlink_create; - devlink_port_type_eth_set(&vsi->devlink_port, vsi->netdev); + devlink_port_type_eth_set(&pf->devlink_port, vsi->netdev); return 0; err_devlink_create: @@ -5561,7 +5622,7 @@ static void ice_napi_enable_all(struct ice_vsi *vsi) INIT_WORK(&q_vector->rx.dim.work, ice_rx_dim_work); q_vector->rx.dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; - if (q_vector->rx.ring || q_vector->tx.ring) + if (q_vector->rx.rx_ring || q_vector->tx.tx_ring) napi_enable(&q_vector->napi); } } @@ -5621,7 +5682,8 @@ int ice_up(struct ice_vsi *vsi) /** * ice_fetch_u64_stats_per_ring - get packets and bytes stats per ring - * @ring: Tx or Rx ring to read stats from + * @syncp: pointer to u64_stats_sync + * @stats: stats that pkts and bytes count will be taken from * @pkts: packets stats counter * @bytes: bytes stats counter * @@ -5629,19 +5691,16 @@ int ice_up(struct ice_vsi *vsi) * that needs to be performed to read u64 values in 32 bit machine. */ static void -ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts, u64 *bytes) +ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, struct ice_q_stats stats, + u64 *pkts, u64 *bytes) { unsigned int start; - *pkts = 0; - *bytes = 0; - if (!ring) - return; do { - start = u64_stats_fetch_begin_irq(&ring->syncp); - *pkts = ring->stats.pkts; - *bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + start = u64_stats_fetch_begin_irq(syncp); + *pkts = stats.pkts; + *bytes = stats.bytes; + } while (u64_stats_fetch_retry_irq(syncp, start)); } /** @@ -5651,18 +5710,19 @@ ice_fetch_u64_stats_per_ring(struct ice_ring *ring, u64 *pkts, u64 *bytes) * @count: number of rings */ static void -ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_ring **rings, +ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_tx_ring **rings, u16 count) { struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats; u16 i; for (i = 0; i < count; i++) { - struct ice_ring *ring; - u64 pkts, bytes; + struct ice_tx_ring *ring; + u64 pkts = 0, bytes = 0; ring = READ_ONCE(rings[i]); - ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes); + if (ring) + ice_fetch_u64_stats_per_ring(&ring->syncp, ring->stats, &pkts, &bytes); vsi_stats->tx_packets += pkts; vsi_stats->tx_bytes += bytes; vsi->tx_restart += ring->tx_stats.restart_q; @@ -5701,9 +5761,9 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) /* update Rx rings counters */ ice_for_each_rxq(vsi, i) { - struct ice_ring *ring = READ_ONCE(vsi->rx_rings[i]); + struct ice_rx_ring *ring = READ_ONCE(vsi->rx_rings[i]); - ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes); + ice_fetch_u64_stats_per_ring(&ring->syncp, ring->stats, &pkts, &bytes); vsi_stats->rx_packets += pkts; vsi_stats->rx_bytes += bytes; vsi->rx_buf_failed += ring->rx_stats.alloc_buf_failed; @@ -5967,7 +6027,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, q_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; - if (q_vector->rx.ring || q_vector->tx.ring) + if (q_vector->rx.rx_ring || q_vector->tx.tx_ring) napi_disable(&q_vector->napi); cancel_work_sync(&q_vector->tx.dim.work); @@ -5986,9 +6046,11 @@ int ice_down(struct ice_vsi *vsi) /* Caller of this function is expected to set the * vsi->state ICE_DOWN bit */ - if (vsi->netdev) { + if (vsi->netdev && vsi->type == ICE_VSI_PF) { netif_carrier_off(vsi->netdev); netif_tx_disable(vsi->netdev); + } else if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) { + ice_eswitch_stop_all_tx_queues(vsi->back); } ice_vsi_dis_irq(vsi); @@ -6050,12 +6112,13 @@ int ice_vsi_setup_tx_rings(struct ice_vsi *vsi) } ice_for_each_txq(vsi, i) { - struct ice_ring *ring = vsi->tx_rings[i]; + struct ice_tx_ring *ring = vsi->tx_rings[i]; if (!ring) return -EINVAL; - ring->netdev = vsi->netdev; + if (vsi->netdev) + ring->netdev = vsi->netdev; err = ice_setup_tx_ring(ring); if (err) break; @@ -6081,12 +6144,13 @@ int ice_vsi_setup_rx_rings(struct ice_vsi *vsi) } ice_for_each_rxq(vsi, i) { - struct ice_ring *ring = vsi->rx_rings[i]; + struct ice_rx_ring *ring = vsi->rx_rings[i]; if (!ring) return -EINVAL; - ring->netdev = vsi->netdev; + if (vsi->netdev) + ring->netdev = vsi->netdev; err = ice_setup_rx_ring(ring); if (err) break; @@ -6159,7 +6223,7 @@ err_setup_tx: * * Returns 0 on success, negative value on error */ -static int ice_vsi_open(struct ice_vsi *vsi) +int ice_vsi_open(struct ice_vsi *vsi) { char int_name[ICE_INT_NAME_STR_LEN]; struct ice_pf *pf = vsi->back; @@ -6184,14 +6248,16 @@ static int ice_vsi_open(struct ice_vsi *vsi) if (err) goto err_setup_rx; - /* Notify the stack of the actual queue counts. */ - err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_txq); - if (err) - goto err_set_qs; + if (vsi->type == ICE_VSI_PF) { + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_txq); + if (err) + goto err_set_qs; - err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq); - if (err) - goto err_set_qs; + err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq); + if (err) + goto err_set_qs; + } err = ice_up_complete(vsi); if (err) @@ -6430,6 +6496,12 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) goto err_vsi_rebuild; } + err = ice_vsi_rebuild_by_type(pf, ICE_VSI_SWITCHDEV_CTRL); + if (err) { + dev_err(dev, "Switchdev CTRL VSI rebuild failed: %d\n", err); + goto err_vsi_rebuild; + } + /* If Flow Director is active */ if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) { err = ice_vsi_rebuild_by_type(pf, ICE_VSI_CTRL); @@ -6976,7 +7048,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) { struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_ring *tx_ring = NULL; + struct ice_tx_ring *tx_ring = NULL; struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; u32 i; @@ -6994,7 +7066,7 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) } /* now that we have an index, find the tx_ring struct */ - for (i = 0; i < vsi->num_txq; i++) + ice_for_each_txq(vsi, i) if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) if (txqueue == vsi->tx_rings[i]->q_index) { tx_ring = vsi->tx_rings[i]; @@ -7051,6 +7123,72 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) } /** + * ice_setup_tc_cls_flower - flower classifier offloads + * @np: net device to configure + * @filter_dev: device on which filter is added + * @cls_flower: offload data + */ +static int +ice_setup_tc_cls_flower(struct ice_netdev_priv *np, + struct net_device *filter_dev, + struct flow_cls_offload *cls_flower) +{ + struct ice_vsi *vsi = np->vsi; + + if (cls_flower->common.chain_index) + return -EOPNOTSUPP; + + switch (cls_flower->command) { + case FLOW_CLS_REPLACE: + return ice_add_cls_flower(filter_dev, vsi, cls_flower); + case FLOW_CLS_DESTROY: + return ice_del_cls_flower(vsi, cls_flower); + default: + return -EINVAL; + } +} + +/** + * ice_setup_tc_block_cb - callback handler registered for TC block + * @type: TC SETUP type + * @type_data: TC flower offload data that contains user input + * @cb_priv: netdev private data + */ +static int +ice_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) +{ + struct ice_netdev_priv *np = cb_priv; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return ice_setup_tc_cls_flower(np, np->vsi->netdev, + type_data); + default: + return -EOPNOTSUPP; + } +} + +static LIST_HEAD(ice_block_cb_list); + +static int +ice_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + + switch (type) { + case TC_SETUP_BLOCK: + return flow_block_cb_setup_simple(type_data, + &ice_block_cb_list, + ice_setup_tc_block_cb, + np, np, true); + default: + return -EOPNOTSUPP; + } + return -EOPNOTSUPP; +} + +/** * ice_open - Called when a network interface becomes active * @netdev: network interface device structure * @@ -7254,6 +7392,7 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_get_vf_stats = ice_get_vf_stats, .ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid, + .ndo_setup_tc = ice_setup_tc, .ndo_set_features = ice_set_features, .ndo_bridge_getlink = ice_bridge_getlink, .ndo_bridge_setlink = ice_bridge_setlink, diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index 199aa5b71540..0b220dfa7457 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -3,6 +3,44 @@ #ifndef _ICE_PROTOCOL_TYPE_H_ #define _ICE_PROTOCOL_TYPE_H_ +#define ICE_IPV6_ADDR_LENGTH 16 + +/* Each recipe can match up to 5 different fields. Fields to match can be meta- + * data, values extracted from packet headers, or results from other recipes. + * One of the 5 fields is reserved for matching the switch ID. So, up to 4 + * recipes can provide intermediate results to another one through chaining, + * e.g. recipes 0, 1, 2, and 3 can provide intermediate results to recipe 4. + */ +#define ICE_NUM_WORDS_RECIPE 4 + +/* Max recipes that can be chained */ +#define ICE_MAX_CHAIN_RECIPE 5 + +/* 1 word reserved for switch ID from allowed 5 words. + * So a recipe can have max 4 words. And you can chain 5 such recipes + * together. So maximum words that can be programmed for look up is 5 * 4. + */ +#define ICE_MAX_CHAIN_WORDS (ICE_NUM_WORDS_RECIPE * ICE_MAX_CHAIN_RECIPE) + +/* Field vector index corresponding to chaining */ +#define ICE_CHAIN_FV_INDEX_START 47 + +enum ice_protocol_type { + ICE_MAC_OFOS = 0, + ICE_MAC_IL, + ICE_ETYPE_OL, + ICE_VLAN_OFOS, + ICE_IPV4_OFOS, + ICE_IPV4_IL, + ICE_IPV6_OFOS, + ICE_IPV6_IL, + ICE_TCP_IL, + ICE_UDP_OF, + ICE_UDP_ILOS, + ICE_SCTP_IL, + ICE_PROTOCOL_LAST +}; + /* Decoders for ice_prot_id: * - F: First * - I: Inner @@ -35,4 +73,135 @@ enum ice_prot_id { ICE_PROT_META_ID = 255, /* when offset == metadata */ ICE_PROT_INVALID = 255 /* when offset == ICE_FV_OFFSET_INVAL */ }; + +#define ICE_MAC_OFOS_HW 1 +#define ICE_MAC_IL_HW 4 +#define ICE_ETYPE_OL_HW 9 +#define ICE_VLAN_OF_HW 16 +#define ICE_VLAN_OL_HW 17 +#define ICE_IPV4_OFOS_HW 32 +#define ICE_IPV4_IL_HW 33 +#define ICE_IPV6_OFOS_HW 40 +#define ICE_IPV6_IL_HW 41 +#define ICE_TCP_IL_HW 49 +#define ICE_UDP_ILOS_HW 53 + +#define ICE_UDP_OF_HW 52 /* UDP Tunnels */ + +#define ICE_TUN_FLAG_FV_IND 2 + +/* Mapping of software defined protocol ID to hardware defined protocol ID */ +struct ice_protocol_entry { + enum ice_protocol_type type; + u8 protocol_id; +}; + +struct ice_ether_hdr { + u8 dst_addr[ETH_ALEN]; + u8 src_addr[ETH_ALEN]; +}; + +struct ice_ethtype_hdr { + __be16 ethtype_id; +}; + +struct ice_ether_vlan_hdr { + u8 dst_addr[ETH_ALEN]; + u8 src_addr[ETH_ALEN]; + __be32 vlan_id; +}; + +struct ice_vlan_hdr { + __be16 type; + __be16 vlan; +}; + +struct ice_ipv4_hdr { + u8 version; + u8 tos; + __be16 total_length; + __be16 id; + __be16 frag_off; + u8 time_to_live; + u8 protocol; + __be16 check; + __be32 src_addr; + __be32 dst_addr; +}; + +struct ice_ipv6_hdr { + __be32 be_ver_tc_flow; + __be16 payload_len; + u8 next_hdr; + u8 hop_limit; + u8 src_addr[ICE_IPV6_ADDR_LENGTH]; + u8 dst_addr[ICE_IPV6_ADDR_LENGTH]; +}; + +struct ice_sctp_hdr { + __be16 src_port; + __be16 dst_port; + __be32 verification_tag; + __be32 check; +}; + +struct ice_l4_hdr { + __be16 src_port; + __be16 dst_port; + __be16 len; + __be16 check; +}; + +union ice_prot_hdr { + struct ice_ether_hdr eth_hdr; + struct ice_ethtype_hdr ethertype; + struct ice_vlan_hdr vlan_hdr; + struct ice_ipv4_hdr ipv4_hdr; + struct ice_ipv6_hdr ipv6_hdr; + struct ice_l4_hdr l4_hdr; + struct ice_sctp_hdr sctp_hdr; +}; + +/* This is mapping table entry that maps every word within a given protocol + * structure to the real byte offset as per the specification of that + * protocol header. + * for e.g. dst address is 3 words in ethertype header and corresponding bytes + * are 0, 2, 3 in the actual packet header and src address is at 4, 6, 8 + */ +struct ice_prot_ext_tbl_entry { + enum ice_protocol_type prot_type; + /* Byte offset into header of given protocol type */ + u8 offs[sizeof(union ice_prot_hdr)]; +}; + +/* Extractions to be looked up for a given recipe */ +struct ice_prot_lkup_ext { + u16 prot_type; + u8 n_val_words; + /* create a buffer to hold max words per recipe */ + u16 field_off[ICE_MAX_CHAIN_WORDS]; + u16 field_mask[ICE_MAX_CHAIN_WORDS]; + + struct ice_fv_word fv_words[ICE_MAX_CHAIN_WORDS]; + + /* Indicate field offsets that have field vector indices assigned */ + DECLARE_BITMAP(done, ICE_MAX_CHAIN_WORDS); +}; + +struct ice_pref_recipe_group { + u8 n_val_pairs; /* Number of valid pairs */ + struct ice_fv_word pairs[ICE_NUM_WORDS_RECIPE]; + u16 mask[ICE_NUM_WORDS_RECIPE]; +}; + +struct ice_recp_grp_entry { + struct list_head l_entry; + +#define ICE_INVAL_CHAIN_IND 0xFF + u16 rid; + u8 chain_idx; + u16 fv_idx[ICE_NUM_WORDS_RECIPE]; + u16 fv_mask[ICE_NUM_WORDS_RECIPE]; + struct ice_pref_recipe_group r_group; +}; #endif /* _ICE_PROTOCOL_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 05cc5870e4ef..a1be0d04a2d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -6,6 +6,252 @@ #define E810_OUT_PROP_DELAY_NS 1 +static const struct ptp_pin_desc ice_pin_desc_e810t[] = { + /* name idx func chan */ + { "GNSS", GNSS, PTP_PF_EXTTS, 0, { 0, } }, + { "SMA1", SMA1, PTP_PF_NONE, 1, { 0, } }, + { "U.FL1", UFL1, PTP_PF_NONE, 1, { 0, } }, + { "SMA2", SMA2, PTP_PF_NONE, 2, { 0, } }, + { "U.FL2", UFL2, PTP_PF_NONE, 2, { 0, } }, +}; + +/** + * ice_get_sma_config_e810t + * @hw: pointer to the hw struct + * @ptp_pins: pointer to the ptp_pin_desc struture + * + * Read the configuration of the SMA control logic and put it into the + * ptp_pin_desc structure + */ +static int +ice_get_sma_config_e810t(struct ice_hw *hw, struct ptp_pin_desc *ptp_pins) +{ + u8 data, i; + int status; + + /* Read initial pin state */ + status = ice_read_sma_ctrl_e810t(hw, &data); + if (status) + return status; + + /* initialize with defaults */ + for (i = 0; i < NUM_PTP_PINS_E810T; i++) { + snprintf(ptp_pins[i].name, sizeof(ptp_pins[i].name), + "%s", ice_pin_desc_e810t[i].name); + ptp_pins[i].index = ice_pin_desc_e810t[i].index; + ptp_pins[i].func = ice_pin_desc_e810t[i].func; + ptp_pins[i].chan = ice_pin_desc_e810t[i].chan; + } + + /* Parse SMA1/UFL1 */ + switch (data & ICE_SMA1_MASK_E810T) { + case ICE_SMA1_MASK_E810T: + default: + ptp_pins[SMA1].func = PTP_PF_NONE; + ptp_pins[UFL1].func = PTP_PF_NONE; + break; + case ICE_SMA1_DIR_EN_E810T: + ptp_pins[SMA1].func = PTP_PF_PEROUT; + ptp_pins[UFL1].func = PTP_PF_NONE; + break; + case ICE_SMA1_TX_EN_E810T: + ptp_pins[SMA1].func = PTP_PF_EXTTS; + ptp_pins[UFL1].func = PTP_PF_NONE; + break; + case 0: + ptp_pins[SMA1].func = PTP_PF_EXTTS; + ptp_pins[UFL1].func = PTP_PF_PEROUT; + break; + } + + /* Parse SMA2/UFL2 */ + switch (data & ICE_SMA2_MASK_E810T) { + case ICE_SMA2_MASK_E810T: + default: + ptp_pins[SMA2].func = PTP_PF_NONE; + ptp_pins[UFL2].func = PTP_PF_NONE; + break; + case (ICE_SMA2_TX_EN_E810T | ICE_SMA2_UFL2_RX_DIS_E810T): + ptp_pins[SMA2].func = PTP_PF_EXTTS; + ptp_pins[UFL2].func = PTP_PF_NONE; + break; + case (ICE_SMA2_DIR_EN_E810T | ICE_SMA2_UFL2_RX_DIS_E810T): + ptp_pins[SMA2].func = PTP_PF_PEROUT; + ptp_pins[UFL2].func = PTP_PF_NONE; + break; + case (ICE_SMA2_DIR_EN_E810T | ICE_SMA2_TX_EN_E810T): + ptp_pins[SMA2].func = PTP_PF_NONE; + ptp_pins[UFL2].func = PTP_PF_EXTTS; + break; + case ICE_SMA2_DIR_EN_E810T: + ptp_pins[SMA2].func = PTP_PF_PEROUT; + ptp_pins[UFL2].func = PTP_PF_EXTTS; + break; + } + + return 0; +} + +/** + * ice_ptp_set_sma_config_e810t + * @hw: pointer to the hw struct + * @ptp_pins: pointer to the ptp_pin_desc struture + * + * Set the configuration of the SMA control logic based on the configuration in + * num_pins parameter + */ +static int +ice_ptp_set_sma_config_e810t(struct ice_hw *hw, + const struct ptp_pin_desc *ptp_pins) +{ + int status; + u8 data; + + /* SMA1 and UFL1 cannot be set to TX at the same time */ + if (ptp_pins[SMA1].func == PTP_PF_PEROUT && + ptp_pins[UFL1].func == PTP_PF_PEROUT) + return -EINVAL; + + /* SMA2 and UFL2 cannot be set to RX at the same time */ + if (ptp_pins[SMA2].func == PTP_PF_EXTTS && + ptp_pins[UFL2].func == PTP_PF_EXTTS) + return -EINVAL; + + /* Read initial pin state value */ + status = ice_read_sma_ctrl_e810t(hw, &data); + if (status) + return status; + + /* Set the right sate based on the desired configuration */ + data &= ~ICE_SMA1_MASK_E810T; + if (ptp_pins[SMA1].func == PTP_PF_NONE && + ptp_pins[UFL1].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA1 + U.FL1 disabled"); + data |= ICE_SMA1_MASK_E810T; + } else if (ptp_pins[SMA1].func == PTP_PF_EXTTS && + ptp_pins[UFL1].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA1 RX"); + data |= ICE_SMA1_TX_EN_E810T; + } else if (ptp_pins[SMA1].func == PTP_PF_NONE && + ptp_pins[UFL1].func == PTP_PF_PEROUT) { + /* U.FL 1 TX will always enable SMA 1 RX */ + dev_info(ice_hw_to_dev(hw), "SMA1 RX + U.FL1 TX"); + } else if (ptp_pins[SMA1].func == PTP_PF_EXTTS && + ptp_pins[UFL1].func == PTP_PF_PEROUT) { + dev_info(ice_hw_to_dev(hw), "SMA1 RX + U.FL1 TX"); + } else if (ptp_pins[SMA1].func == PTP_PF_PEROUT && + ptp_pins[UFL1].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA1 TX"); + data |= ICE_SMA1_DIR_EN_E810T; + } + + data &= ~ICE_SMA2_MASK_E810T; + if (ptp_pins[SMA2].func == PTP_PF_NONE && + ptp_pins[UFL2].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA2 + U.FL2 disabled"); + data |= ICE_SMA2_MASK_E810T; + } else if (ptp_pins[SMA2].func == PTP_PF_EXTTS && + ptp_pins[UFL2].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA2 RX"); + data |= (ICE_SMA2_TX_EN_E810T | + ICE_SMA2_UFL2_RX_DIS_E810T); + } else if (ptp_pins[SMA2].func == PTP_PF_NONE && + ptp_pins[UFL2].func == PTP_PF_EXTTS) { + dev_info(ice_hw_to_dev(hw), "UFL2 RX"); + data |= (ICE_SMA2_DIR_EN_E810T | ICE_SMA2_TX_EN_E810T); + } else if (ptp_pins[SMA2].func == PTP_PF_PEROUT && + ptp_pins[UFL2].func == PTP_PF_NONE) { + dev_info(ice_hw_to_dev(hw), "SMA2 TX"); + data |= (ICE_SMA2_DIR_EN_E810T | + ICE_SMA2_UFL2_RX_DIS_E810T); + } else if (ptp_pins[SMA2].func == PTP_PF_PEROUT && + ptp_pins[UFL2].func == PTP_PF_EXTTS) { + dev_info(ice_hw_to_dev(hw), "SMA2 TX + U.FL2 RX"); + data |= ICE_SMA2_DIR_EN_E810T; + } + + return ice_write_sma_ctrl_e810t(hw, data); +} + +/** + * ice_ptp_set_sma_e810t + * @info: the driver's PTP info structure + * @pin: pin index in kernel structure + * @func: Pin function to be set (PTP_PF_NONE, PTP_PF_EXTTS or PTP_PF_PEROUT) + * + * Set the configuration of a single SMA pin + */ +static int +ice_ptp_set_sma_e810t(struct ptp_clock_info *info, unsigned int pin, + enum ptp_pin_function func) +{ + struct ptp_pin_desc ptp_pins[NUM_PTP_PINS_E810T]; + struct ice_pf *pf = ptp_info_to_pf(info); + struct ice_hw *hw = &pf->hw; + int err; + + if (pin < SMA1 || func > PTP_PF_PEROUT) + return -EOPNOTSUPP; + + err = ice_get_sma_config_e810t(hw, ptp_pins); + if (err) + return err; + + /* Disable the same function on the other pin sharing the channel */ + if (pin == SMA1 && ptp_pins[UFL1].func == func) + ptp_pins[UFL1].func = PTP_PF_NONE; + if (pin == UFL1 && ptp_pins[SMA1].func == func) + ptp_pins[SMA1].func = PTP_PF_NONE; + + if (pin == SMA2 && ptp_pins[UFL2].func == func) + ptp_pins[UFL2].func = PTP_PF_NONE; + if (pin == UFL2 && ptp_pins[SMA2].func == func) + ptp_pins[SMA2].func = PTP_PF_NONE; + + /* Set up new pin function in the temp table */ + ptp_pins[pin].func = func; + + return ice_ptp_set_sma_config_e810t(hw, ptp_pins); +} + +/** + * ice_verify_pin_e810t + * @info: the driver's PTP info structure + * @pin: Pin index + * @func: Assigned function + * @chan: Assigned channel + * + * Verify if pin supports requested pin function. If the Check pins consistency. + * Reconfigure the SMA logic attached to the given pin to enable its + * desired functionality + */ +static int +ice_verify_pin_e810t(struct ptp_clock_info *info, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + /* Don't allow channel reassignment */ + if (chan != ice_pin_desc_e810t[pin].chan) + return -EOPNOTSUPP; + + /* Check if functions are properly assigned */ + switch (func) { + case PTP_PF_NONE: + break; + case PTP_PF_EXTTS: + if (pin == UFL1) + return -EOPNOTSUPP; + break; + case PTP_PF_PEROUT: + if (pin == UFL2 || pin == GNSS) + return -EOPNOTSUPP; + break; + case PTP_PF_PHYSYNC: + return -EOPNOTSUPP; + } + + return ice_ptp_set_sma_e810t(info, pin, func); +} + /** * ice_set_tx_tstamp - Enable or disable Tx timestamping * @pf: The PF pointer to search in @@ -735,17 +981,34 @@ ice_ptp_gpio_enable_e810(struct ptp_clock_info *info, { struct ice_pf *pf = ptp_info_to_pf(info); struct ice_perout_channel clk_cfg = {0}; + bool sma_pres = false; unsigned int chan; u32 gpio_pin; int err; + if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) + sma_pres = true; + switch (rq->type) { case PTP_CLK_REQ_PEROUT: chan = rq->perout.index; - if (chan == PPS_CLK_GEN_CHAN) + if (sma_pres) { + if (chan == ice_pin_desc_e810t[SMA1].chan) + clk_cfg.gpio_pin = GPIO_20; + else if (chan == ice_pin_desc_e810t[SMA2].chan) + clk_cfg.gpio_pin = GPIO_22; + else + return -1; + } else if (ice_is_e810t(&pf->hw)) { + if (chan == 0) + clk_cfg.gpio_pin = GPIO_20; + else + clk_cfg.gpio_pin = GPIO_22; + } else if (chan == PPS_CLK_GEN_CHAN) { clk_cfg.gpio_pin = PPS_PIN_INDEX; - else + } else { clk_cfg.gpio_pin = chan; + } clk_cfg.period = ((rq->perout.period.sec * NSEC_PER_SEC) + rq->perout.period.nsec); @@ -757,7 +1020,19 @@ ice_ptp_gpio_enable_e810(struct ptp_clock_info *info, break; case PTP_CLK_REQ_EXTTS: chan = rq->extts.index; - gpio_pin = chan; + if (sma_pres) { + if (chan < ice_pin_desc_e810t[SMA2].chan) + gpio_pin = GPIO_21; + else + gpio_pin = GPIO_23; + } else if (ice_is_e810t(&pf->hw)) { + if (chan == 0) + gpio_pin = GPIO_21; + else + gpio_pin = GPIO_23; + } else { + gpio_pin = chan; + } err = ice_ptp_cfg_extts(pf, !!on, chan, gpio_pin, rq->extts.flags); @@ -1012,7 +1287,7 @@ int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr) * The timestamp is in ns, so we must convert the result first. */ void -ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring, +ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { u32 ts_high; @@ -1038,13 +1313,93 @@ ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring, } /** + * ice_ptp_disable_sma_pins_e810t - Disable E810-T SMA pins + * @pf: pointer to the PF structure + * @info: PTP clock info structure + * + * Disable the OS access to the SMA pins. Called to clear out the OS + * indications of pin support when we fail to setup the E810-T SMA control + * register. + */ +static void +ice_ptp_disable_sma_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) +{ + struct device *dev = ice_pf_to_dev(pf); + + dev_warn(dev, "Failed to configure E810-T SMA pin control\n"); + + info->enable = NULL; + info->verify = NULL; + info->n_pins = 0; + info->n_ext_ts = 0; + info->n_per_out = 0; +} + +/** + * ice_ptp_setup_sma_pins_e810t - Setup the SMA pins + * @pf: pointer to the PF structure + * @info: PTP clock info structure + * + * Finish setting up the SMA pins by allocating pin_config, and setting it up + * according to the current status of the SMA. On failure, disable all of the + * extended SMA pin support. + */ +static void +ice_ptp_setup_sma_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + /* Allocate memory for kernel pins interface */ + info->pin_config = devm_kcalloc(dev, info->n_pins, + sizeof(*info->pin_config), GFP_KERNEL); + if (!info->pin_config) { + ice_ptp_disable_sma_pins_e810t(pf, info); + return; + } + + /* Read current SMA status */ + err = ice_get_sma_config_e810t(&pf->hw, info->pin_config); + if (err) + ice_ptp_disable_sma_pins_e810t(pf, info); +} + +/** + * ice_ptp_setup_pins_e810t - Setup PTP pins in sysfs + * @pf: pointer to the PF instance + * @info: PTP clock capabilities + */ +static void +ice_ptp_setup_pins_e810t(struct ice_pf *pf, struct ptp_clock_info *info) +{ + /* Check if SMA controller is in the netlist */ + if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL) && + !ice_is_pca9575_present(&pf->hw)) + ice_clear_feature_support(pf, ICE_F_SMA_CTRL); + + if (!ice_is_feature_supported(pf, ICE_F_SMA_CTRL)) { + info->n_ext_ts = N_EXT_TS_E810_NO_SMA; + info->n_per_out = N_PER_OUT_E810T_NO_SMA; + return; + } + + info->n_per_out = N_PER_OUT_E810T; + info->n_ext_ts = N_EXT_TS_E810; + info->n_pins = NUM_PTP_PINS_E810T; + info->verify = ice_verify_pin_e810t; + + /* Complete setup of the SMA pins */ + ice_ptp_setup_sma_pins_e810t(pf, info); +} + +/** * ice_ptp_setup_pins_e810 - Setup PTP pins in sysfs * @info: PTP clock capabilities */ static void ice_ptp_setup_pins_e810(struct ptp_clock_info *info) { - info->n_per_out = E810_N_PER_OUT; - info->n_ext_ts = E810_N_EXT_TS; + info->n_per_out = N_PER_OUT_E810; + info->n_ext_ts = N_EXT_TS_E810; } /** @@ -1062,7 +1417,10 @@ ice_ptp_set_funcs_e810(struct ice_pf *pf, struct ptp_clock_info *info) { info->enable = ice_ptp_gpio_enable_e810; - ice_ptp_setup_pins_e810(info); + if (ice_is_e810t(&pf->hw)) + ice_ptp_setup_pins_e810t(pf, info); + else + ice_ptp_setup_pins_e810(info); } /** @@ -1313,22 +1671,21 @@ ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) { u8 idx; - spin_lock(&tx->lock); - for (idx = 0; idx < tx->len; idx++) { u8 phy_idx = idx + tx->quad_offset; - /* Clear any potential residual timestamp in the PHY block */ - if (!pf->hw.reset_ongoing) - ice_clear_phy_tstamp(&pf->hw, tx->quad, phy_idx); - + spin_lock(&tx->lock); if (tx->tstamps[idx].skb) { dev_kfree_skb_any(tx->tstamps[idx].skb); tx->tstamps[idx].skb = NULL; } - } + clear_bit(idx, tx->in_use); + spin_unlock(&tx->lock); - spin_unlock(&tx->lock); + /* Clear any potential residual timestamp in the PHY block */ + if (!pf->hw.reset_ongoing) + ice_clear_phy_tstamp(&pf->hw, tx->quad, phy_idx); + } } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index e1c787bd5b96..f71ad317d6c8 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -9,12 +9,21 @@ #include "ice_ptp_hw.h" -enum ice_ptp_pin { +enum ice_ptp_pin_e810 { GPIO_20 = 0, GPIO_21, GPIO_22, GPIO_23, - NUM_ICE_PTP_PIN + NUM_PTP_PIN_E810 +}; + +enum ice_ptp_pin_e810t { + GNSS = 0, + SMA1, + UFL1, + SMA2, + UFL2, + NUM_PTP_PINS_E810T }; struct ice_perout_channel { @@ -155,8 +164,11 @@ struct ice_ptp { #define PPS_CLK_SRC_CHAN 2 #define PPS_PIN_INDEX 5 #define TIME_SYNC_PIN_INDEX 4 -#define E810_N_EXT_TS 3 -#define E810_N_PER_OUT 4 +#define N_EXT_TS_E810 3 +#define N_PER_OUT_E810 4 +#define N_PER_OUT_E810T 3 +#define N_PER_OUT_E810T_NO_SMA 2 +#define N_EXT_TS_E810_NO_SMA 2 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) struct ice_pf; @@ -168,7 +180,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); void ice_ptp_process_ts(struct ice_pf *pf); void -ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring, +ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb); void ice_ptp_init(struct ice_pf *pf); void ice_ptp_release(struct ice_pf *pf); @@ -196,7 +208,7 @@ ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) static inline void ice_ptp_process_ts(struct ice_pf *pf) { } static inline void -ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring, +ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { } static inline void ice_ptp_init(struct ice_pf *pf) { } static inline void ice_ptp_release(struct ice_pf *pf) { } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 3eca0e4eab0b..29f947c0cd2e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -649,3 +649,154 @@ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) { return ice_clear_phy_tstamp_e810(hw, block, idx); } + +/* E810T SMA functions + * + * The following functions operate specifically on E810T hardware and are used + * to access the extended GPIOs available. + */ + +/** + * ice_get_pca9575_handle + * @hw: pointer to the hw struct + * @pca9575_handle: GPIO controller's handle + * + * Find and return the GPIO controller's handle in the netlist. + * When found - the value will be cached in the hw structure and following calls + * will return cached value + */ +static int +ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) +{ + struct ice_aqc_get_link_topo *cmd; + struct ice_aq_desc desc; + int status; + u8 idx; + + /* If handle was read previously return cached value */ + if (hw->io_expander_handle) { + *pca9575_handle = hw->io_expander_handle; + return 0; + } + + /* If handle was not detected read it from the netlist */ + cmd = &desc.params.get_link_topo; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + + /* Set node type to GPIO controller */ + cmd->addr.topo_params.node_type_ctx = + (ICE_AQC_LINK_TOPO_NODE_TYPE_M & + ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL); + +#define SW_PCA9575_SFP_TOPO_IDX 2 +#define SW_PCA9575_QSFP_TOPO_IDX 1 + + /* Check if the SW IO expander controlling SMA exists in the netlist. */ + if (hw->device_id == ICE_DEV_ID_E810C_SFP) + idx = SW_PCA9575_SFP_TOPO_IDX; + else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) + idx = SW_PCA9575_QSFP_TOPO_IDX; + else + return -EOPNOTSUPP; + + cmd->addr.topo_params.index = idx; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (status) + return -EOPNOTSUPP; + + /* Verify if we found the right IO expander type */ + if (desc.params.get_link_topo.node_part_num != + ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) + return -EOPNOTSUPP; + + /* If present save the handle and return it */ + hw->io_expander_handle = + le16_to_cpu(desc.params.get_link_topo.addr.handle); + *pca9575_handle = hw->io_expander_handle; + + return 0; +} + +/** + * ice_read_sma_ctrl_e810t + * @hw: pointer to the hw struct + * @data: pointer to data to be read from the GPIO controller + * + * Read the SMA controller state. It is connected to pins 3-7 of Port 1 of the + * PCA9575 expander, so only bits 3-7 in data are valid. + */ +int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data) +{ + int status; + u16 handle; + u8 i; + + status = ice_get_pca9575_handle(hw, &handle); + if (status) + return status; + + *data = 0; + + for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + bool pin; + + status = ice_aq_get_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, + &pin, NULL); + if (status) + break; + *data |= (u8)(!pin) << i; + } + + return status; +} + +/** + * ice_write_sma_ctrl_e810t + * @hw: pointer to the hw struct + * @data: data to be written to the GPIO controller + * + * Write the data to the SMA controller. It is connected to pins 3-7 of Port 1 + * of the PCA9575 expander, so only bits 3-7 in data are valid. + */ +int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data) +{ + int status; + u16 handle; + u8 i; + + status = ice_get_pca9575_handle(hw, &handle); + if (status) + return status; + + for (i = ICE_SMA_MIN_BIT_E810T; i <= ICE_SMA_MAX_BIT_E810T; i++) { + bool pin; + + pin = !(data & (1 << i)); + status = ice_aq_set_gpio(hw, handle, i + ICE_PCA9575_P1_OFFSET, + pin, NULL); + if (status) + break; + } + + return status; +} + +/** + * ice_is_pca9575_present + * @hw: pointer to the hw struct + * + * Check if the SW IO expander is present in the netlist + */ +bool ice_is_pca9575_present(struct ice_hw *hw) +{ + u16 handle = 0; + int status; + + if (!ice_is_e810t(hw)) + return false; + + status = ice_get_pca9575_handle(hw, &handle); + + return !status && handle; +} diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 55a414e87018..b2984b5c22c1 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -30,6 +30,9 @@ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx); /* E810 family functions */ int ice_ptp_init_phy_e810(struct ice_hw *hw); +int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data); +int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data); +bool ice_is_pca9575_present(struct ice_hw *hw); #define PFTSYN_SEM_BYTES 4 @@ -76,4 +79,23 @@ int ice_ptp_init_phy_e810(struct ice_hw *hw); #define LOW_TX_MEMORY_BANK_START 0x03090000 #define HIGH_TX_MEMORY_BANK_START 0x03090004 +/* E810T SMA controller pin control */ +#define ICE_SMA1_DIR_EN_E810T BIT(4) +#define ICE_SMA1_TX_EN_E810T BIT(5) +#define ICE_SMA2_UFL2_RX_DIS_E810T BIT(3) +#define ICE_SMA2_DIR_EN_E810T BIT(6) +#define ICE_SMA2_TX_EN_E810T BIT(7) + +#define ICE_SMA1_MASK_E810T (ICE_SMA1_DIR_EN_E810T | \ + ICE_SMA1_TX_EN_E810T) +#define ICE_SMA2_MASK_E810T (ICE_SMA2_UFL2_RX_DIS_E810T | \ + ICE_SMA2_DIR_EN_E810T | \ + ICE_SMA2_TX_EN_E810T) +#define ICE_ALL_SMA_MASK_E810T (ICE_SMA1_MASK_E810T | \ + ICE_SMA2_MASK_E810T) + +#define ICE_SMA_MIN_BIT_E810T 3 +#define ICE_SMA_MAX_BIT_E810T 7 +#define ICE_PCA9575_P1_OFFSET 8 + #endif /* _ICE_PTP_HW_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c new file mode 100644 index 000000000000..c49eeea7cb67 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -0,0 +1,386 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice.h" +#include "ice_eswitch.h" +#include "ice_devlink.h" +#include "ice_virtchnl_pf.h" +#include "ice_tc_lib.h" + +/** + * ice_repr_get_sw_port_id - get port ID associated with representor + * @repr: pointer to port representor + */ +static int ice_repr_get_sw_port_id(struct ice_repr *repr) +{ + return repr->vf->pf->hw.port_info->lport; +} + +/** + * ice_repr_get_phys_port_name - get phys port name + * @netdev: pointer to port representor netdev + * @buf: write here port name + * @len: max length of buf + */ +static int +ice_repr_get_phys_port_name(struct net_device *netdev, char *buf, size_t len) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_repr *repr = np->repr; + int res; + + /* Devlink port is registered and devlink core is taking care of name formatting. */ + if (repr->vf->devlink_port.devlink) + return -EOPNOTSUPP; + + res = snprintf(buf, len, "pf%dvfr%d", ice_repr_get_sw_port_id(repr), + repr->vf->vf_id); + if (res <= 0) + return -EOPNOTSUPP; + return 0; +} + +/** + * ice_repr_get_stats64 - get VF stats for VFPR use + * @netdev: pointer to port representor netdev + * @stats: pointer to struct where stats can be stored + */ +static void +ice_repr_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_eth_stats *eth_stats; + struct ice_vsi *vsi; + + if (ice_is_vf_disabled(np->repr->vf)) + return; + vsi = np->repr->src_vsi; + + ice_update_vsi_stats(vsi); + eth_stats = &vsi->eth_stats; + + stats->tx_packets = eth_stats->tx_unicast + eth_stats->tx_broadcast + + eth_stats->tx_multicast; + stats->rx_packets = eth_stats->rx_unicast + eth_stats->rx_broadcast + + eth_stats->rx_multicast; + stats->tx_bytes = eth_stats->tx_bytes; + stats->rx_bytes = eth_stats->rx_bytes; + stats->multicast = eth_stats->rx_multicast; + stats->tx_errors = eth_stats->tx_errors; + stats->tx_dropped = eth_stats->tx_discards; + stats->rx_dropped = eth_stats->rx_discards; +} + +/** + * ice_netdev_to_repr - Get port representor for given netdevice + * @netdev: pointer to port representor netdev + */ +struct ice_repr *ice_netdev_to_repr(struct net_device *netdev) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + + return np->repr; +} + +/** + * ice_repr_open - Enable port representor's network interface + * @netdev: network interface device structure + * + * The open entry point is called when a port representor's network + * interface is made active by the system (IFF_UP). Corresponding + * VF is notified about link status change. + * + * Returns 0 on success + */ +static int ice_repr_open(struct net_device *netdev) +{ + struct ice_repr *repr = ice_netdev_to_repr(netdev); + struct ice_vf *vf; + + vf = repr->vf; + vf->link_forced = true; + vf->link_up = true; + ice_vc_notify_vf_link_state(vf); + + netif_carrier_on(netdev); + netif_tx_start_all_queues(netdev); + + return 0; +} + +/** + * ice_repr_stop - Disable port representor's network interface + * @netdev: network interface device structure + * + * The stop entry point is called when a port representor's network + * interface is de-activated by the system. Corresponding + * VF is notified about link status change. + * + * Returns 0 on success + */ +static int ice_repr_stop(struct net_device *netdev) +{ + struct ice_repr *repr = ice_netdev_to_repr(netdev); + struct ice_vf *vf; + + vf = repr->vf; + vf->link_forced = true; + vf->link_up = false; + ice_vc_notify_vf_link_state(vf); + + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + + return 0; +} + +static struct devlink_port * +ice_repr_get_devlink_port(struct net_device *netdev) +{ + struct ice_repr *repr = ice_netdev_to_repr(netdev); + + return &repr->vf->devlink_port; +} + +static int +ice_repr_setup_tc_cls_flower(struct ice_repr *repr, + struct flow_cls_offload *flower) +{ + switch (flower->command) { + case FLOW_CLS_REPLACE: + return ice_add_cls_flower(repr->netdev, repr->src_vsi, flower); + case FLOW_CLS_DESTROY: + return ice_del_cls_flower(repr->src_vsi, flower); + default: + return -EINVAL; + } +} + +static int +ice_repr_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct flow_cls_offload *flower = (struct flow_cls_offload *)type_data; + struct ice_netdev_priv *np = (struct ice_netdev_priv *)cb_priv; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return ice_repr_setup_tc_cls_flower(np->repr, flower); + default: + return -EOPNOTSUPP; + } +} + +static LIST_HEAD(ice_repr_block_cb_list); + +static int +ice_repr_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + + switch (type) { + case TC_SETUP_BLOCK: + return flow_block_cb_setup_simple((struct flow_block_offload *) + type_data, + &ice_repr_block_cb_list, + ice_repr_setup_tc_block_cb, + np, np, true); + default: + return -EOPNOTSUPP; + } +} + +static const struct net_device_ops ice_repr_netdev_ops = { + .ndo_get_phys_port_name = ice_repr_get_phys_port_name, + .ndo_get_stats64 = ice_repr_get_stats64, + .ndo_open = ice_repr_open, + .ndo_stop = ice_repr_stop, + .ndo_start_xmit = ice_eswitch_port_start_xmit, + .ndo_get_devlink_port = ice_repr_get_devlink_port, + .ndo_setup_tc = ice_repr_setup_tc, +}; + +/** + * ice_is_port_repr_netdev - Check if a given netdevice is a port representor netdev + * @netdev: pointer to netdev + */ +bool ice_is_port_repr_netdev(struct net_device *netdev) +{ + return netdev && (netdev->netdev_ops == &ice_repr_netdev_ops); +} + +/** + * ice_repr_reg_netdev - register port representor netdev + * @netdev: pointer to port representor netdev + */ +static int +ice_repr_reg_netdev(struct net_device *netdev) +{ + eth_hw_addr_random(netdev); + netdev->netdev_ops = &ice_repr_netdev_ops; + ice_set_ethtool_repr_ops(netdev); + + netdev->hw_features |= NETIF_F_HW_TC; + + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + + return register_netdev(netdev); +} + +/** + * ice_repr_add - add representor for VF + * @vf: pointer to VF structure + */ +static int ice_repr_add(struct ice_vf *vf) +{ + struct ice_q_vector *q_vector; + struct ice_netdev_priv *np; + struct ice_repr *repr; + int err; + + repr = kzalloc(sizeof(*repr), GFP_KERNEL); + if (!repr) + return -ENOMEM; + + repr->netdev = alloc_etherdev(sizeof(struct ice_netdev_priv)); + if (!repr->netdev) { + err = -ENOMEM; + goto err_alloc; + } + + repr->src_vsi = ice_get_vf_vsi(vf); + repr->vf = vf; + vf->repr = repr; + np = netdev_priv(repr->netdev); + np->repr = repr; + + q_vector = kzalloc(sizeof(*q_vector), GFP_KERNEL); + if (!q_vector) { + err = -ENOMEM; + goto err_alloc_q_vector; + } + repr->q_vector = q_vector; + + err = ice_devlink_create_vf_port(vf); + if (err) + goto err_devlink; + + err = ice_repr_reg_netdev(repr->netdev); + if (err) + goto err_netdev; + + devlink_port_type_eth_set(&vf->devlink_port, repr->netdev); + + return 0; + +err_netdev: + ice_devlink_destroy_vf_port(vf); +err_devlink: + kfree(repr->q_vector); + vf->repr->q_vector = NULL; +err_alloc_q_vector: + free_netdev(repr->netdev); + repr->netdev = NULL; +err_alloc: + kfree(repr); + vf->repr = NULL; + return err; +} + +/** + * ice_repr_rem - remove representor from VF + * @vf: pointer to VF structure + */ +static void ice_repr_rem(struct ice_vf *vf) +{ + ice_devlink_destroy_vf_port(vf); + kfree(vf->repr->q_vector); + vf->repr->q_vector = NULL; + unregister_netdev(vf->repr->netdev); + free_netdev(vf->repr->netdev); + vf->repr->netdev = NULL; + kfree(vf->repr); + vf->repr = NULL; +} + +/** + * ice_repr_add_for_all_vfs - add port representor for all VFs + * @pf: pointer to PF structure + */ +int ice_repr_add_for_all_vfs(struct ice_pf *pf) +{ + int err; + int i; + + ice_for_each_vf(pf, i) { + struct ice_vf *vf = &pf->vf[i]; + + err = ice_repr_add(vf); + if (err) + goto err; + + ice_vc_change_ops_to_repr(&vf->vc_ops); + } + + return 0; + +err: + for (i = i - 1; i >= 0; i--) { + struct ice_vf *vf = &pf->vf[i]; + + ice_repr_rem(vf); + ice_vc_set_dflt_vf_ops(&vf->vc_ops); + } + + return err; +} + +/** + * ice_repr_rem_from_all_vfs - remove port representor for all VFs + * @pf: pointer to PF structure + */ +void ice_repr_rem_from_all_vfs(struct ice_pf *pf) +{ + int i; + + ice_for_each_vf(pf, i) { + struct ice_vf *vf = &pf->vf[i]; + + ice_repr_rem(vf); + ice_vc_set_dflt_vf_ops(&vf->vc_ops); + } +} + +/** + * ice_repr_start_tx_queues - start Tx queues of port representor + * @repr: pointer to repr structure + */ +void ice_repr_start_tx_queues(struct ice_repr *repr) +{ + netif_carrier_on(repr->netdev); + netif_tx_start_all_queues(repr->netdev); +} + +/** + * ice_repr_stop_tx_queues - stop Tx queues of port representor + * @repr: pointer to repr structure + */ +void ice_repr_stop_tx_queues(struct ice_repr *repr) +{ + netif_carrier_off(repr->netdev); + netif_tx_stop_all_queues(repr->netdev); +} + +/** + * ice_repr_set_traffic_vsi - set traffic VSI for port representor + * @repr: repr on with VSI will be set + * @vsi: pointer to VSI that will be used by port representor to pass traffic + */ +void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi) +{ + struct ice_netdev_priv *np = netdev_priv(repr->netdev); + + np->vsi = vsi; +} diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h new file mode 100644 index 000000000000..806de22933c6 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_repr.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_REPR_H_ +#define _ICE_REPR_H_ + +#include <net/dst_metadata.h> +#include "ice.h" + +struct ice_repr { + struct ice_vsi *src_vsi; + struct ice_vf *vf; + struct ice_q_vector *q_vector; + struct net_device *netdev; + struct metadata_dst *dst; +}; + +int ice_repr_add_for_all_vfs(struct ice_pf *pf); +void ice_repr_rem_from_all_vfs(struct ice_pf *pf); + +void ice_repr_start_tx_queues(struct ice_repr *repr); +void ice_repr_stop_tx_queues(struct ice_repr *repr); + +void ice_repr_set_traffic_vsi(struct ice_repr *repr, struct ice_vsi *vsi); + +struct ice_repr *ice_netdev_to_repr(struct net_device *netdev); +bool ice_is_port_repr_netdev(struct net_device *netdev); +#endif diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 3b6c1420aa7b..0d07547b40f1 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -8,6 +8,7 @@ #define ICE_ETH_ETHTYPE_OFFSET 12 #define ICE_ETH_VLAN_TCI_OFFSET 14 #define ICE_MAX_VLAN_ID 0xFFF +#define ICE_IPV6_ETHER_ID 0x86DD /* Dummy ethernet header needed in the ice_aqc_sw_rules_elem * struct to configure any switch filter rules. @@ -29,6 +30,290 @@ static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0, 0x2, 0, 0, 0, 0, 0, 0x81, 0, 0, 0}; +struct ice_dummy_pkt_offsets { + enum ice_protocol_type type; + u16 offset; /* ICE_PROTOCOL_LAST indicates end of list */ +}; + +/* offset info for MAC + IPv4 + UDP dummy packet */ +static const struct ice_dummy_pkt_offsets dummy_udp_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_UDP_ILOS, 34 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* Dummy packet for MAC + IPv4 + UDP */ +static const u8 dummy_udp_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ + + 0x45, 0x00, 0x00, 0x1c, /* ICE_IPV4_OFOS 14 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 34 */ + 0x00, 0x08, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* offset info for MAC + VLAN + IPv4 + UDP dummy packet */ +static const struct ice_dummy_pkt_offsets dummy_vlan_udp_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_VLAN_OFOS, 12 }, + { ICE_ETYPE_OL, 16 }, + { ICE_IPV4_OFOS, 18 }, + { ICE_UDP_ILOS, 38 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* C-tag (801.1Q), IPv4:UDP dummy packet */ +static const u8 dummy_vlan_udp_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x81, 0x00, 0x00, 0x00, /* ICE_VLAN_OFOS 12 */ + + 0x08, 0x00, /* ICE_ETYPE_OL 16 */ + + 0x45, 0x00, 0x00, 0x1c, /* ICE_IPV4_OFOS 18 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x11, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 38 */ + 0x00, 0x08, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* offset info for MAC + IPv4 + TCP dummy packet */ +static const struct ice_dummy_pkt_offsets dummy_tcp_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV4_OFOS, 14 }, + { ICE_TCP_IL, 34 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* Dummy packet for MAC + IPv4 + TCP */ +static const u8 dummy_tcp_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x08, 0x00, /* ICE_ETYPE_OL 12 */ + + 0x45, 0x00, 0x00, 0x28, /* ICE_IPV4_OFOS 14 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x06, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 34 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* offset info for MAC + VLAN (C-tag, 802.1Q) + IPv4 + TCP dummy packet */ +static const struct ice_dummy_pkt_offsets dummy_vlan_tcp_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_VLAN_OFOS, 12 }, + { ICE_ETYPE_OL, 16 }, + { ICE_IPV4_OFOS, 18 }, + { ICE_TCP_IL, 38 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* C-tag (801.1Q), IPv4:TCP dummy packet */ +static const u8 dummy_vlan_tcp_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x81, 0x00, 0x00, 0x00, /* ICE_VLAN_OFOS 12 */ + + 0x08, 0x00, /* ICE_ETYPE_OL 16 */ + + 0x45, 0x00, 0x00, 0x28, /* ICE_IPV4_OFOS 18 */ + 0x00, 0x01, 0x00, 0x00, + 0x00, 0x06, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 38 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +static const struct ice_dummy_pkt_offsets dummy_tcp_ipv6_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_TCP_IL, 54 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +static const u8 dummy_tcp_ipv6_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xDD, /* ICE_ETYPE_OL 12 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 40 */ + 0x00, 0x14, 0x06, 0x00, /* Next header is TCP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 54 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* C-tag (802.1Q): IPv6 + TCP */ +static const struct ice_dummy_pkt_offsets +dummy_vlan_tcp_ipv6_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_VLAN_OFOS, 12 }, + { ICE_ETYPE_OL, 16 }, + { ICE_IPV6_OFOS, 18 }, + { ICE_TCP_IL, 58 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* C-tag (802.1Q), IPv6 + TCP dummy packet */ +static const u8 dummy_vlan_tcp_ipv6_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x81, 0x00, 0x00, 0x00, /* ICE_VLAN_OFOS 12 */ + + 0x86, 0xDD, /* ICE_ETYPE_OL 16 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 18 */ + 0x00, 0x14, 0x06, 0x00, /* Next header is TCP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_TCP_IL 58 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x50, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* IPv6 + UDP */ +static const struct ice_dummy_pkt_offsets dummy_udp_ipv6_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_ETYPE_OL, 12 }, + { ICE_IPV6_OFOS, 14 }, + { ICE_UDP_ILOS, 54 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* IPv6 + UDP dummy packet */ +static const u8 dummy_udp_ipv6_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x86, 0xDD, /* ICE_ETYPE_OL 12 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 40 */ + 0x00, 0x10, 0x11, 0x00, /* Next header UDP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 54 */ + 0x00, 0x10, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* needed for ESP packets */ + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + +/* C-tag (802.1Q): IPv6 + UDP */ +static const struct ice_dummy_pkt_offsets +dummy_vlan_udp_ipv6_packet_offsets[] = { + { ICE_MAC_OFOS, 0 }, + { ICE_VLAN_OFOS, 12 }, + { ICE_ETYPE_OL, 16 }, + { ICE_IPV6_OFOS, 18 }, + { ICE_UDP_ILOS, 58 }, + { ICE_PROTOCOL_LAST, 0 }, +}; + +/* C-tag (802.1Q), IPv6 + UDP dummy packet */ +static const u8 dummy_vlan_udp_ipv6_packet[] = { + 0x00, 0x00, 0x00, 0x00, /* ICE_MAC_OFOS 0 */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x81, 0x00, 0x00, 0x00,/* ICE_VLAN_OFOS 12 */ + + 0x86, 0xDD, /* ICE_ETYPE_OL 16 */ + + 0x60, 0x00, 0x00, 0x00, /* ICE_IPV6_OFOS 18 */ + 0x00, 0x08, 0x11, 0x00, /* Next header UDP */ + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + + 0x00, 0x00, 0x00, 0x00, /* ICE_UDP_ILOS 58 */ + 0x00, 0x08, 0x00, 0x00, + + 0x00, 0x00, /* 2 bytes for 4 byte alignment */ +}; + #define ICE_SW_RULE_RX_TX_ETH_HDR_SIZE \ (offsetof(struct ice_aqc_sw_rules_elem, pdata.lkup_tx_rx.hdr) + \ (DUMMY_ETH_HDR_LEN * \ @@ -42,6 +327,14 @@ static const u8 dummy_eth_header[DUMMY_ETH_HDR_LEN] = { 0x2, 0, 0, 0, 0, 0, (offsetof(struct ice_aqc_sw_rules_elem, pdata.vsi_list.vsi) + \ ((n) * sizeof(((struct ice_sw_rule_vsi_list *)0)->vsi[0]))) +/* this is a recipe to profile association bitmap */ +static DECLARE_BITMAP(recipe_to_profile[ICE_MAX_NUM_RECIPES], + ICE_MAX_NUM_PROFILES); + +/* this is a profile to recipe association bitmap */ +static DECLARE_BITMAP(profile_to_recipe[ICE_MAX_NUM_PROFILES], + ICE_MAX_NUM_RECIPES); + /** * ice_init_def_sw_recp - initialize the recipe book keeping tables * @hw: pointer to the HW struct @@ -59,10 +352,11 @@ enum ice_status ice_init_def_sw_recp(struct ice_hw *hw) if (!recps) return ICE_ERR_NO_MEMORY; - for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) { recps[i].root_rid = i; INIT_LIST_HEAD(&recps[i].filt_rules); INIT_LIST_HEAD(&recps[i].filt_replay_rules); + INIT_LIST_HEAD(&recps[i].rg_list); mutex_init(&recps[i].filt_rule_lock); } @@ -518,7 +812,7 @@ ice_aq_alloc_free_vsi_list_exit: * * Add(0x02a0)/Update(0x02a1)/Remove(0x02a2) switch rules commands to firmware */ -static enum ice_status +enum ice_status ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, u8 num_rules, enum ice_adminq_opc opc, struct ice_sq_cd *cd) { @@ -543,6 +837,358 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, return status; } +/** + * ice_aq_add_recipe - add switch recipe + * @hw: pointer to the HW struct + * @s_recipe_list: pointer to switch rule population list + * @num_recipes: number of switch recipes in the list + * @cd: pointer to command details structure or NULL + * + * Add(0x0290) + */ +static enum ice_status +ice_aq_add_recipe(struct ice_hw *hw, + struct ice_aqc_recipe_data_elem *s_recipe_list, + u16 num_recipes, struct ice_sq_cd *cd) +{ + struct ice_aqc_add_get_recipe *cmd; + struct ice_aq_desc desc; + u16 buf_size; + + cmd = &desc.params.add_get_recipe; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_recipe); + + cmd->num_sub_recipes = cpu_to_le16(num_recipes); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + buf_size = num_recipes * sizeof(*s_recipe_list); + + return ice_aq_send_cmd(hw, &desc, s_recipe_list, buf_size, cd); +} + +/** + * ice_aq_get_recipe - get switch recipe + * @hw: pointer to the HW struct + * @s_recipe_list: pointer to switch rule population list + * @num_recipes: pointer to the number of recipes (input and output) + * @recipe_root: root recipe number of recipe(s) to retrieve + * @cd: pointer to command details structure or NULL + * + * Get(0x0292) + * + * On input, *num_recipes should equal the number of entries in s_recipe_list. + * On output, *num_recipes will equal the number of entries returned in + * s_recipe_list. + * + * The caller must supply enough space in s_recipe_list to hold all possible + * recipes and *num_recipes must equal ICE_MAX_NUM_RECIPES. + */ +static enum ice_status +ice_aq_get_recipe(struct ice_hw *hw, + struct ice_aqc_recipe_data_elem *s_recipe_list, + u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd) +{ + struct ice_aqc_add_get_recipe *cmd; + struct ice_aq_desc desc; + enum ice_status status; + u16 buf_size; + + if (*num_recipes != ICE_MAX_NUM_RECIPES) + return ICE_ERR_PARAM; + + cmd = &desc.params.add_get_recipe; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_recipe); + + cmd->return_index = cpu_to_le16(recipe_root); + cmd->num_sub_recipes = 0; + + buf_size = *num_recipes * sizeof(*s_recipe_list); + + status = ice_aq_send_cmd(hw, &desc, s_recipe_list, buf_size, cd); + *num_recipes = le16_to_cpu(cmd->num_sub_recipes); + + return status; +} + +/** + * ice_aq_map_recipe_to_profile - Map recipe to packet profile + * @hw: pointer to the HW struct + * @profile_id: package profile ID to associate the recipe with + * @r_bitmap: Recipe bitmap filled in and need to be returned as response + * @cd: pointer to command details structure or NULL + * Recipe to profile association (0x0291) + */ +static enum ice_status +ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, + struct ice_sq_cd *cd) +{ + struct ice_aqc_recipe_to_profile *cmd; + struct ice_aq_desc desc; + + cmd = &desc.params.recipe_to_profile; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_recipe_to_profile); + cmd->profile_id = cpu_to_le16(profile_id); + /* Set the recipe ID bit in the bitmask to let the device know which + * profile we are associating the recipe to + */ + memcpy(cmd->recipe_assoc, r_bitmap, sizeof(cmd->recipe_assoc)); + + return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); +} + +/** + * ice_aq_get_recipe_to_profile - Map recipe to packet profile + * @hw: pointer to the HW struct + * @profile_id: package profile ID to associate the recipe with + * @r_bitmap: Recipe bitmap filled in and need to be returned as response + * @cd: pointer to command details structure or NULL + * Associate profile ID with given recipe (0x0293) + */ +static enum ice_status +ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, + struct ice_sq_cd *cd) +{ + struct ice_aqc_recipe_to_profile *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + cmd = &desc.params.recipe_to_profile; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_recipe_to_profile); + cmd->profile_id = cpu_to_le16(profile_id); + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + if (!status) + memcpy(r_bitmap, cmd->recipe_assoc, sizeof(cmd->recipe_assoc)); + + return status; +} + +/** + * ice_alloc_recipe - add recipe resource + * @hw: pointer to the hardware structure + * @rid: recipe ID returned as response to AQ call + */ +static enum ice_status ice_alloc_recipe(struct ice_hw *hw, u16 *rid) +{ + struct ice_aqc_alloc_free_res_elem *sw_buf; + enum ice_status status; + u16 buf_len; + + buf_len = struct_size(sw_buf, elem, 1); + sw_buf = kzalloc(buf_len, GFP_KERNEL); + if (!sw_buf) + return ICE_ERR_NO_MEMORY; + + sw_buf->num_elems = cpu_to_le16(1); + sw_buf->res_type = cpu_to_le16((ICE_AQC_RES_TYPE_RECIPE << + ICE_AQC_RES_TYPE_S) | + ICE_AQC_RES_TYPE_FLAG_SHARED); + status = ice_aq_alloc_free_res(hw, 1, sw_buf, buf_len, + ice_aqc_opc_alloc_res, NULL); + if (!status) + *rid = le16_to_cpu(sw_buf->elem[0].e.sw_resp); + kfree(sw_buf); + + return status; +} + +/** + * ice_get_recp_to_prof_map - updates recipe to profile mapping + * @hw: pointer to hardware structure + * + * This function is used to populate recipe_to_profile matrix where index to + * this array is the recipe ID and the element is the mapping of which profiles + * is this recipe mapped to. + */ +static void ice_get_recp_to_prof_map(struct ice_hw *hw) +{ + DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + u16 i; + + for (i = 0; i < hw->switch_info->max_used_prof_index + 1; i++) { + u16 j; + + bitmap_zero(profile_to_recipe[i], ICE_MAX_NUM_RECIPES); + bitmap_zero(r_bitmap, ICE_MAX_NUM_RECIPES); + if (ice_aq_get_recipe_to_profile(hw, i, (u8 *)r_bitmap, NULL)) + continue; + bitmap_copy(profile_to_recipe[i], r_bitmap, + ICE_MAX_NUM_RECIPES); + for_each_set_bit(j, r_bitmap, ICE_MAX_NUM_RECIPES) + set_bit(i, recipe_to_profile[j]); + } +} + +/** + * ice_collect_result_idx - copy result index values + * @buf: buffer that contains the result index + * @recp: the recipe struct to copy data into + */ +static void +ice_collect_result_idx(struct ice_aqc_recipe_data_elem *buf, + struct ice_sw_recipe *recp) +{ + if (buf->content.result_indx & ICE_AQ_RECIPE_RESULT_EN) + set_bit(buf->content.result_indx & ~ICE_AQ_RECIPE_RESULT_EN, + recp->res_idxs); +} + +/** + * ice_get_recp_frm_fw - update SW bookkeeping from FW recipe entries + * @hw: pointer to hardware structure + * @recps: struct that we need to populate + * @rid: recipe ID that we are populating + * @refresh_required: true if we should get recipe to profile mapping from FW + * + * This function is used to populate all the necessary entries into our + * bookkeeping so that we have a current list of all the recipes that are + * programmed in the firmware. + */ +static enum ice_status +ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, + bool *refresh_required) +{ + DECLARE_BITMAP(result_bm, ICE_MAX_FV_WORDS); + struct ice_aqc_recipe_data_elem *tmp; + u16 num_recps = ICE_MAX_NUM_RECIPES; + struct ice_prot_lkup_ext *lkup_exts; + enum ice_status status; + u8 fv_word_idx = 0; + u16 sub_recps; + + bitmap_zero(result_bm, ICE_MAX_FV_WORDS); + + /* we need a buffer big enough to accommodate all the recipes */ + tmp = kcalloc(ICE_MAX_NUM_RECIPES, sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return ICE_ERR_NO_MEMORY; + + tmp[0].recipe_indx = rid; + status = ice_aq_get_recipe(hw, tmp, &num_recps, rid, NULL); + /* non-zero status meaning recipe doesn't exist */ + if (status) + goto err_unroll; + + /* Get recipe to profile map so that we can get the fv from lkups that + * we read for a recipe from FW. Since we want to minimize the number of + * times we make this FW call, just make one call and cache the copy + * until a new recipe is added. This operation is only required the + * first time to get the changes from FW. Then to search existing + * entries we don't need to update the cache again until another recipe + * gets added. + */ + if (*refresh_required) { + ice_get_recp_to_prof_map(hw); + *refresh_required = false; + } + + /* Start populating all the entries for recps[rid] based on lkups from + * firmware. Note that we are only creating the root recipe in our + * database. + */ + lkup_exts = &recps[rid].lkup_exts; + + for (sub_recps = 0; sub_recps < num_recps; sub_recps++) { + struct ice_aqc_recipe_data_elem root_bufs = tmp[sub_recps]; + struct ice_recp_grp_entry *rg_entry; + u8 i, prof, idx, prot = 0; + bool is_root; + u16 off = 0; + + rg_entry = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*rg_entry), + GFP_KERNEL); + if (!rg_entry) { + status = ICE_ERR_NO_MEMORY; + goto err_unroll; + } + + idx = root_bufs.recipe_indx; + is_root = root_bufs.content.rid & ICE_AQ_RECIPE_ID_IS_ROOT; + + /* Mark all result indices in this chain */ + if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) + set_bit(root_bufs.content.result_indx & ~ICE_AQ_RECIPE_RESULT_EN, + result_bm); + + /* get the first profile that is associated with rid */ + prof = find_first_bit(recipe_to_profile[idx], + ICE_MAX_NUM_PROFILES); + for (i = 0; i < ICE_NUM_WORDS_RECIPE; i++) { + u8 lkup_indx = root_bufs.content.lkup_indx[i + 1]; + + rg_entry->fv_idx[i] = lkup_indx; + rg_entry->fv_mask[i] = + le16_to_cpu(root_bufs.content.mask[i + 1]); + + /* If the recipe is a chained recipe then all its + * child recipe's result will have a result index. + * To fill fv_words we should not use those result + * index, we only need the protocol ids and offsets. + * We will skip all the fv_idx which stores result + * index in them. We also need to skip any fv_idx which + * has ICE_AQ_RECIPE_LKUP_IGNORE or 0 since it isn't a + * valid offset value. + */ + if (test_bit(rg_entry->fv_idx[i], hw->switch_info->prof_res_bm[prof]) || + rg_entry->fv_idx[i] & ICE_AQ_RECIPE_LKUP_IGNORE || + rg_entry->fv_idx[i] == 0) + continue; + + ice_find_prot_off(hw, ICE_BLK_SW, prof, + rg_entry->fv_idx[i], &prot, &off); + lkup_exts->fv_words[fv_word_idx].prot_id = prot; + lkup_exts->fv_words[fv_word_idx].off = off; + lkup_exts->field_mask[fv_word_idx] = + rg_entry->fv_mask[i]; + fv_word_idx++; + } + /* populate rg_list with the data from the child entry of this + * recipe + */ + list_add(&rg_entry->l_entry, &recps[rid].rg_list); + + /* Propagate some data to the recipe database */ + recps[idx].is_root = !!is_root; + recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority; + bitmap_zero(recps[idx].res_idxs, ICE_MAX_FV_WORDS); + if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) { + recps[idx].chain_idx = root_bufs.content.result_indx & + ~ICE_AQ_RECIPE_RESULT_EN; + set_bit(recps[idx].chain_idx, recps[idx].res_idxs); + } else { + recps[idx].chain_idx = ICE_INVAL_CHAIN_IND; + } + + if (!is_root) + continue; + + /* Only do the following for root recipes entries */ + memcpy(recps[idx].r_bitmap, root_bufs.recipe_bitmap, + sizeof(recps[idx].r_bitmap)); + recps[idx].root_rid = root_bufs.content.rid & + ~ICE_AQ_RECIPE_ID_IS_ROOT; + recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority; + } + + /* Complete initialization of the root recipe entry */ + lkup_exts->n_val_words = fv_word_idx; + recps[rid].big_recp = (num_recps > 1); + recps[rid].n_grp_count = (u8)num_recps; + recps[rid].root_buf = devm_kmemdup(ice_hw_to_dev(hw), tmp, + recps[rid].n_grp_count * sizeof(*recps[rid].root_buf), + GFP_KERNEL); + if (!recps[rid].root_buf) + goto err_unroll; + + /* Copy result indexes */ + bitmap_copy(recps[rid].res_idxs, result_bm, ICE_MAX_FV_WORDS); + recps[rid].recp_created = true; + +err_unroll: + kfree(tmp); + return status; +} + /* ice_init_port_info - Initialize port_info with switch configuration data * @pi: pointer to port_info * @vsi_port_num: VSI number or port number @@ -2037,6 +2683,27 @@ ice_rem_sw_rule_info(struct ice_hw *hw, struct list_head *rule_head) } /** + * ice_rem_adv_rule_info + * @hw: pointer to the hardware structure + * @rule_head: pointer to the switch list structure that we want to delete + */ +static void +ice_rem_adv_rule_info(struct ice_hw *hw, struct list_head *rule_head) +{ + struct ice_adv_fltr_mgmt_list_entry *tmp_entry; + struct ice_adv_fltr_mgmt_list_entry *lst_itr; + + if (list_empty(rule_head)) + return; + + list_for_each_entry_safe(lst_itr, tmp_entry, rule_head, list_entry) { + list_del(&lst_itr->list_entry); + devm_kfree(ice_hw_to_dev(hw), lst_itr->lkups); + devm_kfree(ice_hw_to_dev(hw), lst_itr); + } +} + +/** * ice_cfg_dflt_vsi - change state of VSI to set/clear default * @hw: pointer to the hardware structure * @vsi_handle: VSI handle to set as default @@ -2773,6 +3440,1452 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, return status; } +/* This is mapping table entry that maps every word within a given protocol + * structure to the real byte offset as per the specification of that + * protocol header. + * for example dst address is 3 words in ethertype header and corresponding + * bytes are 0, 2, 3 in the actual packet header and src address is at 4, 6, 8 + * IMPORTANT: Every structure part of "ice_prot_hdr" union should have a + * matching entry describing its field. This needs to be updated if new + * structure is added to that union. + */ +static const struct ice_prot_ext_tbl_entry ice_prot_ext[ICE_PROTOCOL_LAST] = { + { ICE_MAC_OFOS, { 0, 2, 4, 6, 8, 10, 12 } }, + { ICE_MAC_IL, { 0, 2, 4, 6, 8, 10, 12 } }, + { ICE_ETYPE_OL, { 0 } }, + { ICE_VLAN_OFOS, { 2, 0 } }, + { ICE_IPV4_OFOS, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18 } }, + { ICE_IPV4_IL, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18 } }, + { ICE_IPV6_OFOS, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, + 26, 28, 30, 32, 34, 36, 38 } }, + { ICE_IPV6_IL, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, + 26, 28, 30, 32, 34, 36, 38 } }, + { ICE_TCP_IL, { 0, 2 } }, + { ICE_UDP_OF, { 0, 2 } }, + { ICE_UDP_ILOS, { 0, 2 } }, +}; + +static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { + { ICE_MAC_OFOS, ICE_MAC_OFOS_HW }, + { ICE_MAC_IL, ICE_MAC_IL_HW }, + { ICE_ETYPE_OL, ICE_ETYPE_OL_HW }, + { ICE_VLAN_OFOS, ICE_VLAN_OL_HW }, + { ICE_IPV4_OFOS, ICE_IPV4_OFOS_HW }, + { ICE_IPV4_IL, ICE_IPV4_IL_HW }, + { ICE_IPV6_OFOS, ICE_IPV6_OFOS_HW }, + { ICE_IPV6_IL, ICE_IPV6_IL_HW }, + { ICE_TCP_IL, ICE_TCP_IL_HW }, + { ICE_UDP_OF, ICE_UDP_OF_HW }, + { ICE_UDP_ILOS, ICE_UDP_ILOS_HW }, +}; + +/** + * ice_find_recp - find a recipe + * @hw: pointer to the hardware structure + * @lkup_exts: extension sequence to match + * + * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found. + */ +static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts) +{ + bool refresh_required = true; + struct ice_sw_recipe *recp; + u8 i; + + /* Walk through existing recipes to find a match */ + recp = hw->switch_info->recp_list; + for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) { + /* If recipe was not created for this ID, in SW bookkeeping, + * check if FW has an entry for this recipe. If the FW has an + * entry update it in our SW bookkeeping and continue with the + * matching. + */ + if (!recp[i].recp_created) + if (ice_get_recp_frm_fw(hw, + hw->switch_info->recp_list, i, + &refresh_required)) + continue; + + /* Skip inverse action recipes */ + if (recp[i].root_buf && recp[i].root_buf->content.act_ctrl & + ICE_AQ_RECIPE_ACT_INV_ACT) + continue; + + /* if number of words we are looking for match */ + if (lkup_exts->n_val_words == recp[i].lkup_exts.n_val_words) { + struct ice_fv_word *ar = recp[i].lkup_exts.fv_words; + struct ice_fv_word *be = lkup_exts->fv_words; + u16 *cr = recp[i].lkup_exts.field_mask; + u16 *de = lkup_exts->field_mask; + bool found = true; + u8 pe, qr; + + /* ar, cr, and qr are related to the recipe words, while + * be, de, and pe are related to the lookup words + */ + for (pe = 0; pe < lkup_exts->n_val_words; pe++) { + for (qr = 0; qr < recp[i].lkup_exts.n_val_words; + qr++) { + if (ar[qr].off == be[pe].off && + ar[qr].prot_id == be[pe].prot_id && + cr[qr] == de[pe]) + /* Found the "pe"th word in the + * given recipe + */ + break; + } + /* After walking through all the words in the + * "i"th recipe if "p"th word was not found then + * this recipe is not what we are looking for. + * So break out from this loop and try the next + * recipe + */ + if (qr >= recp[i].lkup_exts.n_val_words) { + found = false; + break; + } + } + /* If for "i"th recipe the found was never set to false + * then it means we found our match + */ + if (found) + return i; /* Return the recipe ID */ + } + } + return ICE_MAX_NUM_RECIPES; +} + +/** + * ice_prot_type_to_id - get protocol ID from protocol type + * @type: protocol type + * @id: pointer to variable that will receive the ID + * + * Returns true if found, false otherwise + */ +static bool ice_prot_type_to_id(enum ice_protocol_type type, u8 *id) +{ + u8 i; + + for (i = 0; i < ARRAY_SIZE(ice_prot_id_tbl); i++) + if (ice_prot_id_tbl[i].type == type) { + *id = ice_prot_id_tbl[i].protocol_id; + return true; + } + return false; +} + +/** + * ice_fill_valid_words - count valid words + * @rule: advanced rule with lookup information + * @lkup_exts: byte offset extractions of the words that are valid + * + * calculate valid words in a lookup rule using mask value + */ +static u8 +ice_fill_valid_words(struct ice_adv_lkup_elem *rule, + struct ice_prot_lkup_ext *lkup_exts) +{ + u8 j, word, prot_id, ret_val; + + if (!ice_prot_type_to_id(rule->type, &prot_id)) + return 0; + + word = lkup_exts->n_val_words; + + for (j = 0; j < sizeof(rule->m_u) / sizeof(u16); j++) + if (((u16 *)&rule->m_u)[j] && + rule->type < ARRAY_SIZE(ice_prot_ext)) { + /* No more space to accommodate */ + if (word >= ICE_MAX_CHAIN_WORDS) + return 0; + lkup_exts->fv_words[word].off = + ice_prot_ext[rule->type].offs[j]; + lkup_exts->fv_words[word].prot_id = + ice_prot_id_tbl[rule->type].protocol_id; + lkup_exts->field_mask[word] = + be16_to_cpu(((__force __be16 *)&rule->m_u)[j]); + word++; + } + + ret_val = word - lkup_exts->n_val_words; + lkup_exts->n_val_words = word; + + return ret_val; +} + +/** + * ice_create_first_fit_recp_def - Create a recipe grouping + * @hw: pointer to the hardware structure + * @lkup_exts: an array of protocol header extractions + * @rg_list: pointer to a list that stores new recipe groups + * @recp_cnt: pointer to a variable that stores returned number of recipe groups + * + * Using first fit algorithm, take all the words that are still not done + * and start grouping them in 4-word groups. Each group makes up one + * recipe. + */ +static enum ice_status +ice_create_first_fit_recp_def(struct ice_hw *hw, + struct ice_prot_lkup_ext *lkup_exts, + struct list_head *rg_list, + u8 *recp_cnt) +{ + struct ice_pref_recipe_group *grp = NULL; + u8 j; + + *recp_cnt = 0; + + /* Walk through every word in the rule to check if it is not done. If so + * then this word needs to be part of a new recipe. + */ + for (j = 0; j < lkup_exts->n_val_words; j++) + if (!test_bit(j, lkup_exts->done)) { + if (!grp || + grp->n_val_pairs == ICE_NUM_WORDS_RECIPE) { + struct ice_recp_grp_entry *entry; + + entry = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*entry), + GFP_KERNEL); + if (!entry) + return ICE_ERR_NO_MEMORY; + list_add(&entry->l_entry, rg_list); + grp = &entry->r_group; + (*recp_cnt)++; + } + + grp->pairs[grp->n_val_pairs].prot_id = + lkup_exts->fv_words[j].prot_id; + grp->pairs[grp->n_val_pairs].off = + lkup_exts->fv_words[j].off; + grp->mask[grp->n_val_pairs] = lkup_exts->field_mask[j]; + grp->n_val_pairs++; + } + + return 0; +} + +/** + * ice_fill_fv_word_index - fill in the field vector indices for a recipe group + * @hw: pointer to the hardware structure + * @fv_list: field vector with the extraction sequence information + * @rg_list: recipe groupings with protocol-offset pairs + * + * Helper function to fill in the field vector indices for protocol-offset + * pairs. These indexes are then ultimately programmed into a recipe. + */ +static enum ice_status +ice_fill_fv_word_index(struct ice_hw *hw, struct list_head *fv_list, + struct list_head *rg_list) +{ + struct ice_sw_fv_list_entry *fv; + struct ice_recp_grp_entry *rg; + struct ice_fv_word *fv_ext; + + if (list_empty(fv_list)) + return 0; + + fv = list_first_entry(fv_list, struct ice_sw_fv_list_entry, + list_entry); + fv_ext = fv->fv_ptr->ew; + + list_for_each_entry(rg, rg_list, l_entry) { + u8 i; + + for (i = 0; i < rg->r_group.n_val_pairs; i++) { + struct ice_fv_word *pr; + bool found = false; + u16 mask; + u8 j; + + pr = &rg->r_group.pairs[i]; + mask = rg->r_group.mask[i]; + + for (j = 0; j < hw->blk[ICE_BLK_SW].es.fvw; j++) + if (fv_ext[j].prot_id == pr->prot_id && + fv_ext[j].off == pr->off) { + found = true; + + /* Store index of field vector */ + rg->fv_idx[i] = j; + rg->fv_mask[i] = mask; + break; + } + + /* Protocol/offset could not be found, caller gave an + * invalid pair + */ + if (!found) + return ICE_ERR_PARAM; + } + } + + return 0; +} + +/** + * ice_find_free_recp_res_idx - find free result indexes for recipe + * @hw: pointer to hardware structure + * @profiles: bitmap of profiles that will be associated with the new recipe + * @free_idx: pointer to variable to receive the free index bitmap + * + * The algorithm used here is: + * 1. When creating a new recipe, create a set P which contains all + * Profiles that will be associated with our new recipe + * + * 2. For each Profile p in set P: + * a. Add all recipes associated with Profile p into set R + * b. Optional : PossibleIndexes &= profile[p].possibleIndexes + * [initially PossibleIndexes should be 0xFFFFFFFFFFFFFFFF] + * i. Or just assume they all have the same possible indexes: + * 44, 45, 46, 47 + * i.e., PossibleIndexes = 0x0000F00000000000 + * + * 3. For each Recipe r in set R: + * a. UsedIndexes |= (bitwise or ) recipe[r].res_indexes + * b. FreeIndexes = UsedIndexes ^ PossibleIndexes + * + * FreeIndexes will contain the bits indicating the indexes free for use, + * then the code needs to update the recipe[r].used_result_idx_bits to + * indicate which indexes were selected for use by this recipe. + */ +static u16 +ice_find_free_recp_res_idx(struct ice_hw *hw, const unsigned long *profiles, + unsigned long *free_idx) +{ + DECLARE_BITMAP(possible_idx, ICE_MAX_FV_WORDS); + DECLARE_BITMAP(recipes, ICE_MAX_NUM_RECIPES); + DECLARE_BITMAP(used_idx, ICE_MAX_FV_WORDS); + u16 bit; + + bitmap_zero(possible_idx, ICE_MAX_FV_WORDS); + bitmap_zero(recipes, ICE_MAX_NUM_RECIPES); + bitmap_zero(used_idx, ICE_MAX_FV_WORDS); + bitmap_zero(free_idx, ICE_MAX_FV_WORDS); + + bitmap_set(possible_idx, 0, ICE_MAX_FV_WORDS); + + /* For each profile we are going to associate the recipe with, add the + * recipes that are associated with that profile. This will give us + * the set of recipes that our recipe may collide with. Also, determine + * what possible result indexes are usable given this set of profiles. + */ + for_each_set_bit(bit, profiles, ICE_MAX_NUM_PROFILES) { + bitmap_or(recipes, recipes, profile_to_recipe[bit], + ICE_MAX_NUM_RECIPES); + bitmap_and(possible_idx, possible_idx, + hw->switch_info->prof_res_bm[bit], + ICE_MAX_FV_WORDS); + } + + /* For each recipe that our new recipe may collide with, determine + * which indexes have been used. + */ + for_each_set_bit(bit, recipes, ICE_MAX_NUM_RECIPES) + bitmap_or(used_idx, used_idx, + hw->switch_info->recp_list[bit].res_idxs, + ICE_MAX_FV_WORDS); + + bitmap_xor(free_idx, used_idx, possible_idx, ICE_MAX_FV_WORDS); + + /* return number of free indexes */ + return (u16)bitmap_weight(free_idx, ICE_MAX_FV_WORDS); +} + +/** + * ice_add_sw_recipe - function to call AQ calls to create switch recipe + * @hw: pointer to hardware structure + * @rm: recipe management list entry + * @match_tun_mask: tunnel mask that needs to be programmed + * @profiles: bitmap of profiles that will be associated. + */ +static enum ice_status +ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, + u16 match_tun_mask, unsigned long *profiles) +{ + DECLARE_BITMAP(result_idx_bm, ICE_MAX_FV_WORDS); + struct ice_aqc_recipe_data_elem *tmp; + struct ice_aqc_recipe_data_elem *buf; + struct ice_recp_grp_entry *entry; + enum ice_status status; + u16 free_res_idx; + u16 recipe_count; + u8 chain_idx; + u8 recps = 0; + + /* When more than one recipe are required, another recipe is needed to + * chain them together. Matching a tunnel metadata ID takes up one of + * the match fields in the chaining recipe reducing the number of + * chained recipes by one. + */ + /* check number of free result indices */ + bitmap_zero(result_idx_bm, ICE_MAX_FV_WORDS); + free_res_idx = ice_find_free_recp_res_idx(hw, profiles, result_idx_bm); + + ice_debug(hw, ICE_DBG_SW, "Result idx slots: %d, need %d\n", + free_res_idx, rm->n_grp_count); + + if (rm->n_grp_count > 1) { + if (rm->n_grp_count > free_res_idx) + return ICE_ERR_MAX_LIMIT; + + rm->n_grp_count++; + } + + if (rm->n_grp_count > ICE_MAX_CHAIN_RECIPE) + return ICE_ERR_MAX_LIMIT; + + tmp = kcalloc(ICE_MAX_NUM_RECIPES, sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return ICE_ERR_NO_MEMORY; + + buf = devm_kcalloc(ice_hw_to_dev(hw), rm->n_grp_count, sizeof(*buf), + GFP_KERNEL); + if (!buf) { + status = ICE_ERR_NO_MEMORY; + goto err_mem; + } + + bitmap_zero(rm->r_bitmap, ICE_MAX_NUM_RECIPES); + recipe_count = ICE_MAX_NUM_RECIPES; + status = ice_aq_get_recipe(hw, tmp, &recipe_count, ICE_SW_LKUP_MAC, + NULL); + if (status || recipe_count == 0) + goto err_unroll; + + /* Allocate the recipe resources, and configure them according to the + * match fields from protocol headers and extracted field vectors. + */ + chain_idx = find_first_bit(result_idx_bm, ICE_MAX_FV_WORDS); + list_for_each_entry(entry, &rm->rg_list, l_entry) { + u8 i; + + status = ice_alloc_recipe(hw, &entry->rid); + if (status) + goto err_unroll; + + /* Clear the result index of the located recipe, as this will be + * updated, if needed, later in the recipe creation process. + */ + tmp[0].content.result_indx = 0; + + buf[recps] = tmp[0]; + buf[recps].recipe_indx = (u8)entry->rid; + /* if the recipe is a non-root recipe RID should be programmed + * as 0 for the rules to be applied correctly. + */ + buf[recps].content.rid = 0; + memset(&buf[recps].content.lkup_indx, 0, + sizeof(buf[recps].content.lkup_indx)); + + /* All recipes use look-up index 0 to match switch ID. */ + buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + buf[recps].content.mask[0] = + cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + /* Setup lkup_indx 1..4 to INVALID/ignore and set the mask + * to be 0 + */ + for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { + buf[recps].content.lkup_indx[i] = 0x80; + buf[recps].content.mask[i] = 0; + } + + for (i = 0; i < entry->r_group.n_val_pairs; i++) { + buf[recps].content.lkup_indx[i + 1] = entry->fv_idx[i]; + buf[recps].content.mask[i + 1] = + cpu_to_le16(entry->fv_mask[i]); + } + + if (rm->n_grp_count > 1) { + /* Checks to see if there really is a valid result index + * that can be used. + */ + if (chain_idx >= ICE_MAX_FV_WORDS) { + ice_debug(hw, ICE_DBG_SW, "No chain index available\n"); + status = ICE_ERR_MAX_LIMIT; + goto err_unroll; + } + + entry->chain_idx = chain_idx; + buf[recps].content.result_indx = + ICE_AQ_RECIPE_RESULT_EN | + ((chain_idx << ICE_AQ_RECIPE_RESULT_DATA_S) & + ICE_AQ_RECIPE_RESULT_DATA_M); + clear_bit(chain_idx, result_idx_bm); + chain_idx = find_first_bit(result_idx_bm, + ICE_MAX_FV_WORDS); + } + + /* fill recipe dependencies */ + bitmap_zero((unsigned long *)buf[recps].recipe_bitmap, + ICE_MAX_NUM_RECIPES); + set_bit(buf[recps].recipe_indx, + (unsigned long *)buf[recps].recipe_bitmap); + buf[recps].content.act_ctrl_fwd_priority = rm->priority; + recps++; + } + + if (rm->n_grp_count == 1) { + rm->root_rid = buf[0].recipe_indx; + set_bit(buf[0].recipe_indx, rm->r_bitmap); + buf[0].content.rid = rm->root_rid | ICE_AQ_RECIPE_ID_IS_ROOT; + if (sizeof(buf[0].recipe_bitmap) >= sizeof(rm->r_bitmap)) { + memcpy(buf[0].recipe_bitmap, rm->r_bitmap, + sizeof(buf[0].recipe_bitmap)); + } else { + status = ICE_ERR_BAD_PTR; + goto err_unroll; + } + /* Applicable only for ROOT_RECIPE, set the fwd_priority for + * the recipe which is getting created if specified + * by user. Usually any advanced switch filter, which results + * into new extraction sequence, ended up creating a new recipe + * of type ROOT and usually recipes are associated with profiles + * Switch rule referreing newly created recipe, needs to have + * either/or 'fwd' or 'join' priority, otherwise switch rule + * evaluation will not happen correctly. In other words, if + * switch rule to be evaluated on priority basis, then recipe + * needs to have priority, otherwise it will be evaluated last. + */ + buf[0].content.act_ctrl_fwd_priority = rm->priority; + } else { + struct ice_recp_grp_entry *last_chain_entry; + u16 rid, i; + + /* Allocate the last recipe that will chain the outcomes of the + * other recipes together + */ + status = ice_alloc_recipe(hw, &rid); + if (status) + goto err_unroll; + + buf[recps].recipe_indx = (u8)rid; + buf[recps].content.rid = (u8)rid; + buf[recps].content.rid |= ICE_AQ_RECIPE_ID_IS_ROOT; + /* the new entry created should also be part of rg_list to + * make sure we have complete recipe + */ + last_chain_entry = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*last_chain_entry), + GFP_KERNEL); + if (!last_chain_entry) { + status = ICE_ERR_NO_MEMORY; + goto err_unroll; + } + last_chain_entry->rid = rid; + memset(&buf[recps].content.lkup_indx, 0, + sizeof(buf[recps].content.lkup_indx)); + /* All recipes use look-up index 0 to match switch ID. */ + buf[recps].content.lkup_indx[0] = ICE_AQ_SW_ID_LKUP_IDX; + buf[recps].content.mask[0] = + cpu_to_le16(ICE_AQ_SW_ID_LKUP_MASK); + for (i = 1; i <= ICE_NUM_WORDS_RECIPE; i++) { + buf[recps].content.lkup_indx[i] = + ICE_AQ_RECIPE_LKUP_IGNORE; + buf[recps].content.mask[i] = 0; + } + + i = 1; + /* update r_bitmap with the recp that is used for chaining */ + set_bit(rid, rm->r_bitmap); + /* this is the recipe that chains all the other recipes so it + * should not have a chaining ID to indicate the same + */ + last_chain_entry->chain_idx = ICE_INVAL_CHAIN_IND; + list_for_each_entry(entry, &rm->rg_list, l_entry) { + last_chain_entry->fv_idx[i] = entry->chain_idx; + buf[recps].content.lkup_indx[i] = entry->chain_idx; + buf[recps].content.mask[i++] = cpu_to_le16(0xFFFF); + set_bit(entry->rid, rm->r_bitmap); + } + list_add(&last_chain_entry->l_entry, &rm->rg_list); + if (sizeof(buf[recps].recipe_bitmap) >= + sizeof(rm->r_bitmap)) { + memcpy(buf[recps].recipe_bitmap, rm->r_bitmap, + sizeof(buf[recps].recipe_bitmap)); + } else { + status = ICE_ERR_BAD_PTR; + goto err_unroll; + } + buf[recps].content.act_ctrl_fwd_priority = rm->priority; + + /* To differentiate among different UDP tunnels, a meta data ID + * flag is used. + */ + if (match_tun_mask) { + buf[recps].content.lkup_indx[i] = ICE_TUN_FLAG_FV_IND; + buf[recps].content.mask[i] = + cpu_to_le16(match_tun_mask); + } + + recps++; + rm->root_rid = (u8)rid; + } + status = ice_acquire_change_lock(hw, ICE_RES_WRITE); + if (status) + goto err_unroll; + + status = ice_aq_add_recipe(hw, buf, rm->n_grp_count, NULL); + ice_release_change_lock(hw); + if (status) + goto err_unroll; + + /* Every recipe that just got created add it to the recipe + * book keeping list + */ + list_for_each_entry(entry, &rm->rg_list, l_entry) { + struct ice_switch_info *sw = hw->switch_info; + bool is_root, idx_found = false; + struct ice_sw_recipe *recp; + u16 idx, buf_idx = 0; + + /* find buffer index for copying some data */ + for (idx = 0; idx < rm->n_grp_count; idx++) + if (buf[idx].recipe_indx == entry->rid) { + buf_idx = idx; + idx_found = true; + } + + if (!idx_found) { + status = ICE_ERR_OUT_OF_RANGE; + goto err_unroll; + } + + recp = &sw->recp_list[entry->rid]; + is_root = (rm->root_rid == entry->rid); + recp->is_root = is_root; + + recp->root_rid = entry->rid; + recp->big_recp = (is_root && rm->n_grp_count > 1); + + memcpy(&recp->ext_words, entry->r_group.pairs, + entry->r_group.n_val_pairs * sizeof(struct ice_fv_word)); + + memcpy(recp->r_bitmap, buf[buf_idx].recipe_bitmap, + sizeof(recp->r_bitmap)); + + /* Copy non-result fv index values and masks to recipe. This + * call will also update the result recipe bitmask. + */ + ice_collect_result_idx(&buf[buf_idx], recp); + + /* for non-root recipes, also copy to the root, this allows + * easier matching of a complete chained recipe + */ + if (!is_root) + ice_collect_result_idx(&buf[buf_idx], + &sw->recp_list[rm->root_rid]); + + recp->n_ext_words = entry->r_group.n_val_pairs; + recp->chain_idx = entry->chain_idx; + recp->priority = buf[buf_idx].content.act_ctrl_fwd_priority; + recp->n_grp_count = rm->n_grp_count; + recp->recp_created = true; + } + rm->root_buf = buf; + kfree(tmp); + return status; + +err_unroll: +err_mem: + kfree(tmp); + devm_kfree(ice_hw_to_dev(hw), buf); + return status; +} + +/** + * ice_create_recipe_group - creates recipe group + * @hw: pointer to hardware structure + * @rm: recipe management list entry + * @lkup_exts: lookup elements + */ +static enum ice_status +ice_create_recipe_group(struct ice_hw *hw, struct ice_sw_recipe *rm, + struct ice_prot_lkup_ext *lkup_exts) +{ + enum ice_status status; + u8 recp_count = 0; + + rm->n_grp_count = 0; + + /* Create recipes for words that are marked not done by packing them + * as best fit. + */ + status = ice_create_first_fit_recp_def(hw, lkup_exts, + &rm->rg_list, &recp_count); + if (!status) { + rm->n_grp_count += recp_count; + rm->n_ext_words = lkup_exts->n_val_words; + memcpy(&rm->ext_words, lkup_exts->fv_words, + sizeof(rm->ext_words)); + memcpy(rm->word_masks, lkup_exts->field_mask, + sizeof(rm->word_masks)); + } + + return status; +} + +/** + * ice_get_fv - get field vectors/extraction sequences for spec. lookup types + * @hw: pointer to hardware structure + * @lkups: lookup elements or match criteria for the advanced recipe, one + * structure per protocol header + * @lkups_cnt: number of protocols + * @bm: bitmap of field vectors to consider + * @fv_list: pointer to a list that holds the returned field vectors + */ +static enum ice_status +ice_get_fv(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, + unsigned long *bm, struct list_head *fv_list) +{ + enum ice_status status; + u8 *prot_ids; + u16 i; + + prot_ids = kcalloc(lkups_cnt, sizeof(*prot_ids), GFP_KERNEL); + if (!prot_ids) + return ICE_ERR_NO_MEMORY; + + for (i = 0; i < lkups_cnt; i++) + if (!ice_prot_type_to_id(lkups[i].type, &prot_ids[i])) { + status = ICE_ERR_CFG; + goto free_mem; + } + + /* Find field vectors that include all specified protocol types */ + status = ice_get_sw_fv_list(hw, prot_ids, lkups_cnt, bm, fv_list); + +free_mem: + kfree(prot_ids); + return status; +} + +/* ice_get_compat_fv_bitmap - Get compatible field vector bitmap for rule + * @hw: pointer to hardware structure + * @rinfo: other information regarding the rule e.g. priority and action info + * @bm: pointer to memory for returning the bitmap of field vectors + */ +static void +ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo, + unsigned long *bm) +{ + bitmap_zero(bm, ICE_MAX_NUM_PROFILES); + + ice_get_sw_fv_bitmap(hw, ICE_PROF_NON_TUN, bm); +} + +/** + * ice_add_adv_recipe - Add an advanced recipe that is not part of the default + * @hw: pointer to hardware structure + * @lkups: lookup elements or match criteria for the advanced recipe, one + * structure per protocol header + * @lkups_cnt: number of protocols + * @rinfo: other information regarding the rule e.g. priority and action info + * @rid: return the recipe ID of the recipe created + */ +static enum ice_status +ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, + u16 lkups_cnt, struct ice_adv_rule_info *rinfo, u16 *rid) +{ + DECLARE_BITMAP(fv_bitmap, ICE_MAX_NUM_PROFILES); + DECLARE_BITMAP(profiles, ICE_MAX_NUM_PROFILES); + struct ice_prot_lkup_ext *lkup_exts; + struct ice_recp_grp_entry *r_entry; + struct ice_sw_fv_list_entry *fvit; + struct ice_recp_grp_entry *r_tmp; + struct ice_sw_fv_list_entry *tmp; + enum ice_status status = 0; + struct ice_sw_recipe *rm; + u16 match_tun_mask = 0; + u8 i; + + if (!lkups_cnt) + return ICE_ERR_PARAM; + + lkup_exts = kzalloc(sizeof(*lkup_exts), GFP_KERNEL); + if (!lkup_exts) + return ICE_ERR_NO_MEMORY; + + /* Determine the number of words to be matched and if it exceeds a + * recipe's restrictions + */ + for (i = 0; i < lkups_cnt; i++) { + u16 count; + + if (lkups[i].type >= ICE_PROTOCOL_LAST) { + status = ICE_ERR_CFG; + goto err_free_lkup_exts; + } + + count = ice_fill_valid_words(&lkups[i], lkup_exts); + if (!count) { + status = ICE_ERR_CFG; + goto err_free_lkup_exts; + } + } + + rm = kzalloc(sizeof(*rm), GFP_KERNEL); + if (!rm) { + status = ICE_ERR_NO_MEMORY; + goto err_free_lkup_exts; + } + + /* Get field vectors that contain fields extracted from all the protocol + * headers being programmed. + */ + INIT_LIST_HEAD(&rm->fv_list); + INIT_LIST_HEAD(&rm->rg_list); + + /* Get bitmap of field vectors (profiles) that are compatible with the + * rule request; only these will be searched in the subsequent call to + * ice_get_fv. + */ + ice_get_compat_fv_bitmap(hw, rinfo, fv_bitmap); + + status = ice_get_fv(hw, lkups, lkups_cnt, fv_bitmap, &rm->fv_list); + if (status) + goto err_unroll; + + /* Group match words into recipes using preferred recipe grouping + * criteria. + */ + status = ice_create_recipe_group(hw, rm, lkup_exts); + if (status) + goto err_unroll; + + /* set the recipe priority if specified */ + rm->priority = (u8)rinfo->priority; + + /* Find offsets from the field vector. Pick the first one for all the + * recipes. + */ + status = ice_fill_fv_word_index(hw, &rm->fv_list, &rm->rg_list); + if (status) + goto err_unroll; + + /* get bitmap of all profiles the recipe will be associated with */ + bitmap_zero(profiles, ICE_MAX_NUM_PROFILES); + list_for_each_entry(fvit, &rm->fv_list, list_entry) { + ice_debug(hw, ICE_DBG_SW, "profile: %d\n", fvit->profile_id); + set_bit((u16)fvit->profile_id, profiles); + } + + /* Look for a recipe which matches our requested fv / mask list */ + *rid = ice_find_recp(hw, lkup_exts); + if (*rid < ICE_MAX_NUM_RECIPES) + /* Success if found a recipe that match the existing criteria */ + goto err_unroll; + + /* Recipe we need does not exist, add a recipe */ + status = ice_add_sw_recipe(hw, rm, match_tun_mask, profiles); + if (status) + goto err_unroll; + + /* Associate all the recipes created with all the profiles in the + * common field vector. + */ + list_for_each_entry(fvit, &rm->fv_list, list_entry) { + DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + u16 j; + + status = ice_aq_get_recipe_to_profile(hw, fvit->profile_id, + (u8 *)r_bitmap, NULL); + if (status) + goto err_unroll; + + bitmap_or(r_bitmap, r_bitmap, rm->r_bitmap, + ICE_MAX_NUM_RECIPES); + status = ice_acquire_change_lock(hw, ICE_RES_WRITE); + if (status) + goto err_unroll; + + status = ice_aq_map_recipe_to_profile(hw, fvit->profile_id, + (u8 *)r_bitmap, + NULL); + ice_release_change_lock(hw); + + if (status) + goto err_unroll; + + /* Update profile to recipe bitmap array */ + bitmap_copy(profile_to_recipe[fvit->profile_id], r_bitmap, + ICE_MAX_NUM_RECIPES); + + /* Update recipe to profile bitmap array */ + for_each_set_bit(j, rm->r_bitmap, ICE_MAX_NUM_RECIPES) + set_bit((u16)fvit->profile_id, recipe_to_profile[j]); + } + + *rid = rm->root_rid; + memcpy(&hw->switch_info->recp_list[*rid].lkup_exts, lkup_exts, + sizeof(*lkup_exts)); +err_unroll: + list_for_each_entry_safe(r_entry, r_tmp, &rm->rg_list, l_entry) { + list_del(&r_entry->l_entry); + devm_kfree(ice_hw_to_dev(hw), r_entry); + } + + list_for_each_entry_safe(fvit, tmp, &rm->fv_list, list_entry) { + list_del(&fvit->list_entry); + devm_kfree(ice_hw_to_dev(hw), fvit); + } + + if (rm->root_buf) + devm_kfree(ice_hw_to_dev(hw), rm->root_buf); + + kfree(rm); + +err_free_lkup_exts: + kfree(lkup_exts); + + return status; +} + +/** + * ice_find_dummy_packet - find dummy packet + * + * @lkups: lookup elements or match criteria for the advanced recipe, one + * structure per protocol header + * @lkups_cnt: number of protocols + * @pkt: dummy packet to fill according to filter match criteria + * @pkt_len: packet length of dummy packet + * @offsets: pointer to receive the pointer to the offsets for the packet + */ +static void +ice_find_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, + const u8 **pkt, u16 *pkt_len, + const struct ice_dummy_pkt_offsets **offsets) +{ + bool tcp = false, udp = false, ipv6 = false, vlan = false; + u16 i; + + for (i = 0; i < lkups_cnt; i++) { + if (lkups[i].type == ICE_UDP_ILOS) + udp = true; + else if (lkups[i].type == ICE_TCP_IL) + tcp = true; + else if (lkups[i].type == ICE_IPV6_OFOS) + ipv6 = true; + else if (lkups[i].type == ICE_VLAN_OFOS) + vlan = true; + else if (lkups[i].type == ICE_ETYPE_OL && + lkups[i].h_u.ethertype.ethtype_id == + cpu_to_be16(ICE_IPV6_ETHER_ID) && + lkups[i].m_u.ethertype.ethtype_id == + cpu_to_be16(0xFFFF)) + ipv6 = true; + } + + if (udp && !ipv6) { + if (vlan) { + *pkt = dummy_vlan_udp_packet; + *pkt_len = sizeof(dummy_vlan_udp_packet); + *offsets = dummy_vlan_udp_packet_offsets; + return; + } + *pkt = dummy_udp_packet; + *pkt_len = sizeof(dummy_udp_packet); + *offsets = dummy_udp_packet_offsets; + return; + } else if (udp && ipv6) { + if (vlan) { + *pkt = dummy_vlan_udp_ipv6_packet; + *pkt_len = sizeof(dummy_vlan_udp_ipv6_packet); + *offsets = dummy_vlan_udp_ipv6_packet_offsets; + return; + } + *pkt = dummy_udp_ipv6_packet; + *pkt_len = sizeof(dummy_udp_ipv6_packet); + *offsets = dummy_udp_ipv6_packet_offsets; + return; + } else if ((tcp && ipv6) || ipv6) { + if (vlan) { + *pkt = dummy_vlan_tcp_ipv6_packet; + *pkt_len = sizeof(dummy_vlan_tcp_ipv6_packet); + *offsets = dummy_vlan_tcp_ipv6_packet_offsets; + return; + } + *pkt = dummy_tcp_ipv6_packet; + *pkt_len = sizeof(dummy_tcp_ipv6_packet); + *offsets = dummy_tcp_ipv6_packet_offsets; + return; + } + + if (vlan) { + *pkt = dummy_vlan_tcp_packet; + *pkt_len = sizeof(dummy_vlan_tcp_packet); + *offsets = dummy_vlan_tcp_packet_offsets; + } else { + *pkt = dummy_tcp_packet; + *pkt_len = sizeof(dummy_tcp_packet); + *offsets = dummy_tcp_packet_offsets; + } +} + +/** + * ice_fill_adv_dummy_packet - fill a dummy packet with given match criteria + * + * @lkups: lookup elements or match criteria for the advanced recipe, one + * structure per protocol header + * @lkups_cnt: number of protocols + * @s_rule: stores rule information from the match criteria + * @dummy_pkt: dummy packet to fill according to filter match criteria + * @pkt_len: packet length of dummy packet + * @offsets: offset info for the dummy packet + */ +static enum ice_status +ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, + struct ice_aqc_sw_rules_elem *s_rule, + const u8 *dummy_pkt, u16 pkt_len, + const struct ice_dummy_pkt_offsets *offsets) +{ + u8 *pkt; + u16 i; + + /* Start with a packet with a pre-defined/dummy content. Then, fill + * in the header values to be looked up or matched. + */ + pkt = s_rule->pdata.lkup_tx_rx.hdr; + + memcpy(pkt, dummy_pkt, pkt_len); + + for (i = 0; i < lkups_cnt; i++) { + enum ice_protocol_type type; + u16 offset = 0, len = 0, j; + bool found = false; + + /* find the start of this layer; it should be found since this + * was already checked when search for the dummy packet + */ + type = lkups[i].type; + for (j = 0; offsets[j].type != ICE_PROTOCOL_LAST; j++) { + if (type == offsets[j].type) { + offset = offsets[j].offset; + found = true; + break; + } + } + /* this should never happen in a correct calling sequence */ + if (!found) + return ICE_ERR_PARAM; + + switch (lkups[i].type) { + case ICE_MAC_OFOS: + case ICE_MAC_IL: + len = sizeof(struct ice_ether_hdr); + break; + case ICE_ETYPE_OL: + len = sizeof(struct ice_ethtype_hdr); + break; + case ICE_VLAN_OFOS: + len = sizeof(struct ice_vlan_hdr); + break; + case ICE_IPV4_OFOS: + case ICE_IPV4_IL: + len = sizeof(struct ice_ipv4_hdr); + break; + case ICE_IPV6_OFOS: + case ICE_IPV6_IL: + len = sizeof(struct ice_ipv6_hdr); + break; + case ICE_TCP_IL: + case ICE_UDP_OF: + case ICE_UDP_ILOS: + len = sizeof(struct ice_l4_hdr); + break; + case ICE_SCTP_IL: + len = sizeof(struct ice_sctp_hdr); + break; + default: + return ICE_ERR_PARAM; + } + + /* the length should be a word multiple */ + if (len % ICE_BYTES_PER_WORD) + return ICE_ERR_CFG; + + /* We have the offset to the header start, the length, the + * caller's header values and mask. Use this information to + * copy the data into the dummy packet appropriately based on + * the mask. Note that we need to only write the bits as + * indicated by the mask to make sure we don't improperly write + * over any significant packet data. + */ + for (j = 0; j < len / sizeof(u16); j++) + if (((u16 *)&lkups[i].m_u)[j]) + ((u16 *)(pkt + offset))[j] = + (((u16 *)(pkt + offset))[j] & + ~((u16 *)&lkups[i].m_u)[j]) | + (((u16 *)&lkups[i].h_u)[j] & + ((u16 *)&lkups[i].m_u)[j]); + } + + s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(pkt_len); + + return 0; +} + +/** + * ice_find_adv_rule_entry - Search a rule entry + * @hw: pointer to the hardware structure + * @lkups: lookup elements or match criteria for the advanced recipe, one + * structure per protocol header + * @lkups_cnt: number of protocols + * @recp_id: recipe ID for which we are finding the rule + * @rinfo: other information regarding the rule e.g. priority and action info + * + * Helper function to search for a given advance rule entry + * Returns pointer to entry storing the rule if found + */ +static struct ice_adv_fltr_mgmt_list_entry * +ice_find_adv_rule_entry(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, + u16 lkups_cnt, u16 recp_id, + struct ice_adv_rule_info *rinfo) +{ + struct ice_adv_fltr_mgmt_list_entry *list_itr; + struct ice_switch_info *sw = hw->switch_info; + int i; + + list_for_each_entry(list_itr, &sw->recp_list[recp_id].filt_rules, + list_entry) { + bool lkups_matched = true; + + if (lkups_cnt != list_itr->lkups_cnt) + continue; + for (i = 0; i < list_itr->lkups_cnt; i++) + if (memcmp(&list_itr->lkups[i], &lkups[i], + sizeof(*lkups))) { + lkups_matched = false; + break; + } + if (rinfo->sw_act.flag == list_itr->rule_info.sw_act.flag && + lkups_matched) + return list_itr; + } + return NULL; +} + +/** + * ice_adv_add_update_vsi_list + * @hw: pointer to the hardware structure + * @m_entry: pointer to current adv filter management list entry + * @cur_fltr: filter information from the book keeping entry + * @new_fltr: filter information with the new VSI to be added + * + * Call AQ command to add or update previously created VSI list with new VSI. + * + * Helper function to do book keeping associated with adding filter information + * The algorithm to do the booking keeping is described below : + * When a VSI needs to subscribe to a given advanced filter + * if only one VSI has been added till now + * Allocate a new VSI list and add two VSIs + * to this list using switch rule command + * Update the previously created switch rule with the + * newly created VSI list ID + * if a VSI list was previously created + * Add the new VSI to the previously created VSI list set + * using the update switch rule command + */ +static enum ice_status +ice_adv_add_update_vsi_list(struct ice_hw *hw, + struct ice_adv_fltr_mgmt_list_entry *m_entry, + struct ice_adv_rule_info *cur_fltr, + struct ice_adv_rule_info *new_fltr) +{ + enum ice_status status; + u16 vsi_list_id = 0; + + if (cur_fltr->sw_act.fltr_act == ICE_FWD_TO_Q || + cur_fltr->sw_act.fltr_act == ICE_FWD_TO_QGRP || + cur_fltr->sw_act.fltr_act == ICE_DROP_PACKET) + return ICE_ERR_NOT_IMPL; + + if ((new_fltr->sw_act.fltr_act == ICE_FWD_TO_Q || + new_fltr->sw_act.fltr_act == ICE_FWD_TO_QGRP) && + (cur_fltr->sw_act.fltr_act == ICE_FWD_TO_VSI || + cur_fltr->sw_act.fltr_act == ICE_FWD_TO_VSI_LIST)) + return ICE_ERR_NOT_IMPL; + + if (m_entry->vsi_count < 2 && !m_entry->vsi_list_info) { + /* Only one entry existed in the mapping and it was not already + * a part of a VSI list. So, create a VSI list with the old and + * new VSIs. + */ + struct ice_fltr_info tmp_fltr; + u16 vsi_handle_arr[2]; + + /* A rule already exists with the new VSI being added */ + if (cur_fltr->sw_act.fwd_id.hw_vsi_id == + new_fltr->sw_act.fwd_id.hw_vsi_id) + return ICE_ERR_ALREADY_EXISTS; + + vsi_handle_arr[0] = cur_fltr->sw_act.vsi_handle; + vsi_handle_arr[1] = new_fltr->sw_act.vsi_handle; + status = ice_create_vsi_list_rule(hw, &vsi_handle_arr[0], 2, + &vsi_list_id, + ICE_SW_LKUP_LAST); + if (status) + return status; + + memset(&tmp_fltr, 0, sizeof(tmp_fltr)); + tmp_fltr.flag = m_entry->rule_info.sw_act.flag; + tmp_fltr.fltr_rule_id = cur_fltr->fltr_rule_id; + tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST; + tmp_fltr.fwd_id.vsi_list_id = vsi_list_id; + tmp_fltr.lkup_type = ICE_SW_LKUP_LAST; + + /* Update the previous switch rule of "forward to VSI" to + * "fwd to VSI list" + */ + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr); + if (status) + return status; + + cur_fltr->sw_act.fwd_id.vsi_list_id = vsi_list_id; + cur_fltr->sw_act.fltr_act = ICE_FWD_TO_VSI_LIST; + m_entry->vsi_list_info = + ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2, + vsi_list_id); + } else { + u16 vsi_handle = new_fltr->sw_act.vsi_handle; + + if (!m_entry->vsi_list_info) + return ICE_ERR_CFG; + + /* A rule already exists with the new VSI being added */ + if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map)) + return 0; + + /* Update the previously created VSI list set with + * the new VSI ID passed in + */ + vsi_list_id = cur_fltr->sw_act.fwd_id.vsi_list_id; + + status = ice_update_vsi_list_rule(hw, &vsi_handle, 1, + vsi_list_id, false, + ice_aqc_opc_update_sw_rules, + ICE_SW_LKUP_LAST); + /* update VSI list mapping info with new VSI ID */ + if (!status) + set_bit(vsi_handle, m_entry->vsi_list_info->vsi_map); + } + if (!status) + m_entry->vsi_count++; + return status; +} + +/** + * ice_add_adv_rule - helper function to create an advanced switch rule + * @hw: pointer to the hardware structure + * @lkups: information on the words that needs to be looked up. All words + * together makes one recipe + * @lkups_cnt: num of entries in the lkups array + * @rinfo: other information related to the rule that needs to be programmed + * @added_entry: this will return recipe_id, rule_id and vsi_handle. should be + * ignored is case of error. + * + * This function can program only 1 rule at a time. The lkups is used to + * describe the all the words that forms the "lookup" portion of the recipe. + * These words can span multiple protocols. Callers to this function need to + * pass in a list of protocol headers with lookup information along and mask + * that determines which words are valid from the given protocol header. + * rinfo describes other information related to this rule such as forwarding + * IDs, priority of this rule, etc. + */ +enum ice_status +ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, + u16 lkups_cnt, struct ice_adv_rule_info *rinfo, + struct ice_rule_query_data *added_entry) +{ + struct ice_adv_fltr_mgmt_list_entry *m_entry, *adv_fltr = NULL; + u16 rid = 0, i, pkt_len, rule_buf_sz, vsi_handle; + const struct ice_dummy_pkt_offsets *pkt_offsets; + struct ice_aqc_sw_rules_elem *s_rule = NULL; + struct list_head *rule_head; + struct ice_switch_info *sw; + enum ice_status status; + const u8 *pkt = NULL; + u16 word_cnt; + u32 act = 0; + u8 q_rgn; + + /* Initialize profile to result index bitmap */ + if (!hw->switch_info->prof_res_bm_init) { + hw->switch_info->prof_res_bm_init = 1; + ice_init_prof_result_bm(hw); + } + + if (!lkups_cnt) + return ICE_ERR_PARAM; + + /* get # of words we need to match */ + word_cnt = 0; + for (i = 0; i < lkups_cnt; i++) { + u16 j, *ptr; + + ptr = (u16 *)&lkups[i].m_u; + for (j = 0; j < sizeof(lkups->m_u) / sizeof(u16); j++) + if (ptr[j] != 0) + word_cnt++; + } + + if (!word_cnt || word_cnt > ICE_MAX_CHAIN_WORDS) + return ICE_ERR_PARAM; + + /* make sure that we can locate a dummy packet */ + ice_find_dummy_packet(lkups, lkups_cnt, &pkt, &pkt_len, + &pkt_offsets); + if (!pkt) { + status = ICE_ERR_PARAM; + goto err_ice_add_adv_rule; + } + + if (!(rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI || + rinfo->sw_act.fltr_act == ICE_FWD_TO_Q || + rinfo->sw_act.fltr_act == ICE_FWD_TO_QGRP || + rinfo->sw_act.fltr_act == ICE_DROP_PACKET)) + return ICE_ERR_CFG; + + vsi_handle = rinfo->sw_act.vsi_handle; + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + + if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI) + rinfo->sw_act.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, vsi_handle); + if (rinfo->sw_act.flag & ICE_FLTR_TX) + rinfo->sw_act.src = ice_get_hw_vsi_num(hw, vsi_handle); + + status = ice_add_adv_recipe(hw, lkups, lkups_cnt, rinfo, &rid); + if (status) + return status; + m_entry = ice_find_adv_rule_entry(hw, lkups, lkups_cnt, rid, rinfo); + if (m_entry) { + /* we have to add VSI to VSI_LIST and increment vsi_count. + * Also Update VSI list so that we can change forwarding rule + * if the rule already exists, we will check if it exists with + * same vsi_id, if not then add it to the VSI list if it already + * exists if not then create a VSI list and add the existing VSI + * ID and the new VSI ID to the list + * We will add that VSI to the list + */ + status = ice_adv_add_update_vsi_list(hw, m_entry, + &m_entry->rule_info, + rinfo); + if (added_entry) { + added_entry->rid = rid; + added_entry->rule_id = m_entry->rule_info.fltr_rule_id; + added_entry->vsi_handle = rinfo->sw_act.vsi_handle; + } + return status; + } + rule_buf_sz = ICE_SW_RULE_RX_TX_NO_HDR_SIZE + pkt_len; + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) + return ICE_ERR_NO_MEMORY; + act |= ICE_SINGLE_ACT_LB_ENABLE | ICE_SINGLE_ACT_LAN_ENABLE; + switch (rinfo->sw_act.fltr_act) { + case ICE_FWD_TO_VSI: + act |= (rinfo->sw_act.fwd_id.hw_vsi_id << + ICE_SINGLE_ACT_VSI_ID_S) & ICE_SINGLE_ACT_VSI_ID_M; + act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_VALID_BIT; + break; + case ICE_FWD_TO_Q: + act |= ICE_SINGLE_ACT_TO_Q; + act |= (rinfo->sw_act.fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & + ICE_SINGLE_ACT_Q_INDEX_M; + break; + case ICE_FWD_TO_QGRP: + q_rgn = rinfo->sw_act.qgrp_size > 0 ? + (u8)ilog2(rinfo->sw_act.qgrp_size) : 0; + act |= ICE_SINGLE_ACT_TO_Q; + act |= (rinfo->sw_act.fwd_id.q_id << ICE_SINGLE_ACT_Q_INDEX_S) & + ICE_SINGLE_ACT_Q_INDEX_M; + act |= (q_rgn << ICE_SINGLE_ACT_Q_REGION_S) & + ICE_SINGLE_ACT_Q_REGION_M; + break; + case ICE_DROP_PACKET: + act |= ICE_SINGLE_ACT_VSI_FORWARDING | ICE_SINGLE_ACT_DROP | + ICE_SINGLE_ACT_VALID_BIT; + break; + default: + status = ICE_ERR_CFG; + goto err_ice_add_adv_rule; + } + + /* set the rule LOOKUP type based on caller specified 'Rx' + * instead of hardcoding it to be either LOOKUP_TX/RX + * + * for 'Rx' set the source to be the port number + * for 'Tx' set the source to be the source HW VSI number (determined + * by caller) + */ + if (rinfo->rx) { + s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->pdata.lkup_tx_rx.src = + cpu_to_le16(hw->port_info->lport); + } else { + s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_TX); + s_rule->pdata.lkup_tx_rx.src = cpu_to_le16(rinfo->sw_act.src); + } + + s_rule->pdata.lkup_tx_rx.recipe_id = cpu_to_le16(rid); + s_rule->pdata.lkup_tx_rx.act = cpu_to_le32(act); + + status = ice_fill_adv_dummy_packet(lkups, lkups_cnt, s_rule, pkt, + pkt_len, pkt_offsets); + if (status) + goto err_ice_add_adv_rule; + + status = ice_aq_sw_rules(hw, (struct ice_aqc_sw_rules *)s_rule, + rule_buf_sz, 1, ice_aqc_opc_add_sw_rules, + NULL); + if (status) + goto err_ice_add_adv_rule; + adv_fltr = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(struct ice_adv_fltr_mgmt_list_entry), + GFP_KERNEL); + if (!adv_fltr) { + status = ICE_ERR_NO_MEMORY; + goto err_ice_add_adv_rule; + } + + adv_fltr->lkups = devm_kmemdup(ice_hw_to_dev(hw), lkups, + lkups_cnt * sizeof(*lkups), GFP_KERNEL); + if (!adv_fltr->lkups) { + status = ICE_ERR_NO_MEMORY; + goto err_ice_add_adv_rule; + } + + adv_fltr->lkups_cnt = lkups_cnt; + adv_fltr->rule_info = *rinfo; + adv_fltr->rule_info.fltr_rule_id = + le16_to_cpu(s_rule->pdata.lkup_tx_rx.index); + sw = hw->switch_info; + sw->recp_list[rid].adv_rule = true; + rule_head = &sw->recp_list[rid].filt_rules; + + if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI) + adv_fltr->vsi_count = 1; + + /* Add rule entry to book keeping list */ + list_add(&adv_fltr->list_entry, rule_head); + if (added_entry) { + added_entry->rid = rid; + added_entry->rule_id = adv_fltr->rule_info.fltr_rule_id; + added_entry->vsi_handle = rinfo->sw_act.vsi_handle; + } +err_ice_add_adv_rule: + if (status && adv_fltr) { + devm_kfree(ice_hw_to_dev(hw), adv_fltr->lkups); + devm_kfree(ice_hw_to_dev(hw), adv_fltr); + } + + kfree(s_rule); + + return status; +} + /** * ice_replay_vsi_fltr - Replay filters for requested VSI * @hw: pointer to the hardware structure @@ -2831,6 +4944,229 @@ end: } /** + * ice_adv_rem_update_vsi_list + * @hw: pointer to the hardware structure + * @vsi_handle: VSI handle of the VSI to remove + * @fm_list: filter management entry for which the VSI list management needs to + * be done + */ +static enum ice_status +ice_adv_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, + struct ice_adv_fltr_mgmt_list_entry *fm_list) +{ + struct ice_vsi_list_map_info *vsi_list_info; + enum ice_sw_lkup_type lkup_type; + enum ice_status status; + u16 vsi_list_id; + + if (fm_list->rule_info.sw_act.fltr_act != ICE_FWD_TO_VSI_LIST || + fm_list->vsi_count == 0) + return ICE_ERR_PARAM; + + /* A rule with the VSI being removed does not exist */ + if (!test_bit(vsi_handle, fm_list->vsi_list_info->vsi_map)) + return ICE_ERR_DOES_NOT_EXIST; + + lkup_type = ICE_SW_LKUP_LAST; + vsi_list_id = fm_list->rule_info.sw_act.fwd_id.vsi_list_id; + status = ice_update_vsi_list_rule(hw, &vsi_handle, 1, vsi_list_id, true, + ice_aqc_opc_update_sw_rules, + lkup_type); + if (status) + return status; + + fm_list->vsi_count--; + clear_bit(vsi_handle, fm_list->vsi_list_info->vsi_map); + vsi_list_info = fm_list->vsi_list_info; + if (fm_list->vsi_count == 1) { + struct ice_fltr_info tmp_fltr; + u16 rem_vsi_handle; + + rem_vsi_handle = find_first_bit(vsi_list_info->vsi_map, + ICE_MAX_VSI); + if (!ice_is_vsi_valid(hw, rem_vsi_handle)) + return ICE_ERR_OUT_OF_RANGE; + + /* Make sure VSI list is empty before removing it below */ + status = ice_update_vsi_list_rule(hw, &rem_vsi_handle, 1, + vsi_list_id, true, + ice_aqc_opc_update_sw_rules, + lkup_type); + if (status) + return status; + + memset(&tmp_fltr, 0, sizeof(tmp_fltr)); + tmp_fltr.flag = fm_list->rule_info.sw_act.flag; + tmp_fltr.fltr_rule_id = fm_list->rule_info.fltr_rule_id; + fm_list->rule_info.sw_act.fltr_act = ICE_FWD_TO_VSI; + tmp_fltr.fltr_act = ICE_FWD_TO_VSI; + tmp_fltr.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, rem_vsi_handle); + fm_list->rule_info.sw_act.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, rem_vsi_handle); + fm_list->rule_info.sw_act.vsi_handle = rem_vsi_handle; + + /* Update the previous switch rule of "MAC forward to VSI" to + * "MAC fwd to VSI list" + */ + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr); + if (status) { + ice_debug(hw, ICE_DBG_SW, "Failed to update pkt fwd rule to FWD_TO_VSI on HW VSI %d, error %d\n", + tmp_fltr.fwd_id.hw_vsi_id, status); + return status; + } + fm_list->vsi_list_info->ref_cnt--; + + /* Remove the VSI list since it is no longer used */ + status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type); + if (status) { + ice_debug(hw, ICE_DBG_SW, "Failed to remove VSI list %d, error %d\n", + vsi_list_id, status); + return status; + } + + list_del(&vsi_list_info->list_entry); + devm_kfree(ice_hw_to_dev(hw), vsi_list_info); + fm_list->vsi_list_info = NULL; + } + + return status; +} + +/** + * ice_rem_adv_rule - removes existing advanced switch rule + * @hw: pointer to the hardware structure + * @lkups: information on the words that needs to be looked up. All words + * together makes one recipe + * @lkups_cnt: num of entries in the lkups array + * @rinfo: Its the pointer to the rule information for the rule + * + * This function can be used to remove 1 rule at a time. The lkups is + * used to describe all the words that forms the "lookup" portion of the + * rule. These words can span multiple protocols. Callers to this function + * need to pass in a list of protocol headers with lookup information along + * and mask that determines which words are valid from the given protocol + * header. rinfo describes other information related to this rule such as + * forwarding IDs, priority of this rule, etc. + */ +static enum ice_status +ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, + u16 lkups_cnt, struct ice_adv_rule_info *rinfo) +{ + struct ice_adv_fltr_mgmt_list_entry *list_elem; + struct ice_prot_lkup_ext lkup_exts; + enum ice_status status = 0; + bool remove_rule = false; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + u16 i, rid, vsi_handle; + + memset(&lkup_exts, 0, sizeof(lkup_exts)); + for (i = 0; i < lkups_cnt; i++) { + u16 count; + + if (lkups[i].type >= ICE_PROTOCOL_LAST) + return ICE_ERR_CFG; + + count = ice_fill_valid_words(&lkups[i], &lkup_exts); + if (!count) + return ICE_ERR_CFG; + } + + rid = ice_find_recp(hw, &lkup_exts); + /* If did not find a recipe that match the existing criteria */ + if (rid == ICE_MAX_NUM_RECIPES) + return ICE_ERR_PARAM; + + rule_lock = &hw->switch_info->recp_list[rid].filt_rule_lock; + list_elem = ice_find_adv_rule_entry(hw, lkups, lkups_cnt, rid, rinfo); + /* the rule is already removed */ + if (!list_elem) + return 0; + mutex_lock(rule_lock); + if (list_elem->rule_info.sw_act.fltr_act != ICE_FWD_TO_VSI_LIST) { + remove_rule = true; + } else if (list_elem->vsi_count > 1) { + remove_rule = false; + vsi_handle = rinfo->sw_act.vsi_handle; + status = ice_adv_rem_update_vsi_list(hw, vsi_handle, list_elem); + } else { + vsi_handle = rinfo->sw_act.vsi_handle; + status = ice_adv_rem_update_vsi_list(hw, vsi_handle, list_elem); + if (status) { + mutex_unlock(rule_lock); + return status; + } + if (list_elem->vsi_count == 0) + remove_rule = true; + } + mutex_unlock(rule_lock); + if (remove_rule) { + struct ice_aqc_sw_rules_elem *s_rule; + u16 rule_buf_sz; + + rule_buf_sz = ICE_SW_RULE_RX_TX_NO_HDR_SIZE; + s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); + if (!s_rule) + return ICE_ERR_NO_MEMORY; + s_rule->pdata.lkup_tx_rx.act = 0; + s_rule->pdata.lkup_tx_rx.index = + cpu_to_le16(list_elem->rule_info.fltr_rule_id); + s_rule->pdata.lkup_tx_rx.hdr_len = 0; + status = ice_aq_sw_rules(hw, (struct ice_aqc_sw_rules *)s_rule, + rule_buf_sz, 1, + ice_aqc_opc_remove_sw_rules, NULL); + if (!status || status == ICE_ERR_DOES_NOT_EXIST) { + struct ice_switch_info *sw = hw->switch_info; + + mutex_lock(rule_lock); + list_del(&list_elem->list_entry); + devm_kfree(ice_hw_to_dev(hw), list_elem->lkups); + devm_kfree(ice_hw_to_dev(hw), list_elem); + mutex_unlock(rule_lock); + if (list_empty(&sw->recp_list[rid].filt_rules)) + sw->recp_list[rid].adv_rule = false; + } + kfree(s_rule); + } + return status; +} + +/** + * ice_rem_adv_rule_by_id - removes existing advanced switch rule by ID + * @hw: pointer to the hardware structure + * @remove_entry: data struct which holds rule_id, VSI handle and recipe ID + * + * This function is used to remove 1 rule at a time. The removal is based on + * the remove_entry parameter. This function will remove rule for a given + * vsi_handle with a given rule_id which is passed as parameter in remove_entry + */ +enum ice_status +ice_rem_adv_rule_by_id(struct ice_hw *hw, + struct ice_rule_query_data *remove_entry) +{ + struct ice_adv_fltr_mgmt_list_entry *list_itr; + struct list_head *list_head; + struct ice_adv_rule_info rinfo; + struct ice_switch_info *sw; + + sw = hw->switch_info; + if (!sw->recp_list[remove_entry->rid].recp_created) + return ICE_ERR_PARAM; + list_head = &sw->recp_list[remove_entry->rid].filt_rules; + list_for_each_entry(list_itr, list_head, list_entry) { + if (list_itr->rule_info.fltr_rule_id == + remove_entry->rule_id) { + rinfo = list_itr->rule_info; + rinfo.sw_act.vsi_handle = remove_entry->vsi_handle; + return ice_rem_adv_rule(hw, list_itr->lkups, + list_itr->lkups_cnt, &rinfo); + } + } + /* either list is empty or unable to find rule */ + return ICE_ERR_DOES_NOT_EXIST; +} + +/** * ice_replay_vsi_all_fltr - replay all filters stored in bookkeeping lists * @hw: pointer to the hardware structure * @vsi_handle: driver VSI handle @@ -2868,12 +5204,15 @@ void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw) if (!sw) return; - for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) { if (!list_empty(&sw->recp_list[i].filt_replay_rules)) { struct list_head *l_head; l_head = &sw->recp_list[i].filt_replay_rules; - ice_rem_sw_rule_info(hw, l_head); + if (!sw->recp_list[i].adv_rule) + ice_rem_sw_rule_info(hw, l_head); + else + ice_rem_adv_rule_info(hw, l_head); } } } diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index c5db8d56133f..34b7f74b1ab8 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -14,6 +14,9 @@ #define ICE_VSI_INVAL_ID 0xffff #define ICE_INVAL_Q_HANDLE 0xFFFF +#define ICE_SW_RULE_RX_TX_NO_HDR_SIZE \ + (offsetof(struct ice_aqc_sw_rules_elem, pdata.lkup_tx_rx.hdr)) + /* VSI context structure for add/get/update/free operations */ struct ice_vsi_ctx { u16 vsi_num; @@ -122,30 +125,110 @@ struct ice_fltr_info { u8 lan_en; /* Indicate if packet can be forwarded to the uplink */ }; +struct ice_adv_lkup_elem { + enum ice_protocol_type type; + union ice_prot_hdr h_u; /* Header values */ + union ice_prot_hdr m_u; /* Mask of header values to match */ +}; + +struct ice_sw_act_ctrl { + /* Source VSI for LOOKUP_TX or source port for LOOKUP_RX */ + u16 src; + u16 flag; + enum ice_sw_fwd_act_type fltr_act; + /* Depending on filter action */ + union { + /* This is a queue ID in case of ICE_FWD_TO_Q and starting + * queue ID in case of ICE_FWD_TO_QGRP. + */ + u16 q_id:11; + u16 vsi_id:10; + u16 hw_vsi_id:10; + u16 vsi_list_id:10; + } fwd_id; + /* software VSI handle */ + u16 vsi_handle; + u8 qgrp_size; +}; + +struct ice_rule_query_data { + /* Recipe ID for which the requested rule was added */ + u16 rid; + /* Rule ID that was added or is supposed to be removed */ + u16 rule_id; + /* vsi_handle for which Rule was added or is supposed to be removed */ + u16 vsi_handle; +}; + +struct ice_adv_rule_info { + struct ice_sw_act_ctrl sw_act; + u32 priority; + u8 rx; /* true means LOOKUP_RX otherwise LOOKUP_TX */ + u16 fltr_rule_id; +}; + +/* A collection of one or more four word recipe */ struct ice_sw_recipe { - struct list_head l_entry; + /* For a chained recipe the root recipe is what should be used for + * programming rules + */ + u8 is_root; + u8 root_rid; + u8 recp_created; - /* To protect modification of filt_rule list - * defined below + /* Number of extraction words */ + u8 n_ext_words; + /* Protocol ID and Offset pair (extraction word) to describe the + * recipe */ - struct mutex filt_rule_lock; + struct ice_fv_word ext_words[ICE_MAX_CHAIN_WORDS]; + u16 word_masks[ICE_MAX_CHAIN_WORDS]; + + /* if this recipe is a collection of other recipe */ + u8 big_recp; - /* List of type ice_fltr_mgmt_list_entry */ + /* if this recipe is part of another bigger recipe then chain index + * corresponding to this recipe + */ + u8 chain_idx; + + /* if this recipe is a collection of other recipe then count of other + * recipes and recipe IDs of those recipes + */ + u8 n_grp_count; + + /* Bit map specifying the IDs associated with this group of recipe */ + DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + + /* List of type ice_fltr_mgmt_list_entry or adv_rule */ + u8 adv_rule; struct list_head filt_rules; struct list_head filt_replay_rules; - /* linked list of type recipe_list_entry */ - struct list_head rg_list; - /* linked list of type ice_sw_fv_list_entry*/ + struct mutex filt_rule_lock; /* protect filter rule structure */ + + /* Profiles this recipe should be associated with */ struct list_head fv_list; - struct ice_aqc_recipe_data_elem *r_buf; - u8 recp_count; - u8 root_rid; - u8 num_profs; - u8 *prof_ids; - /* recipe bitmap: what all recipes makes this recipe */ - DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); + /* Profiles this recipe is associated with */ + u8 num_profs, *prof_ids; + + /* Bit map for possible result indexes */ + DECLARE_BITMAP(res_idxs, ICE_MAX_FV_WORDS); + + /* This allows user to specify the recipe priority. + * For now, this becomes 'fwd_priority' when recipe + * is created, usually recipes can have 'fwd' and 'join' + * priority. + */ + u8 priority; + + struct list_head rg_list; + + /* AQ buffer associated with this recipe */ + struct ice_aqc_recipe_data_elem *root_buf; + /* This struct saves the fv_words for a given lookup */ + struct ice_prot_lkup_ext lkup_exts; }; /* Bookkeeping structure to hold bitmap of VSIs corresponding to VSI list ID */ @@ -183,6 +266,16 @@ struct ice_fltr_mgmt_list_entry { u8 counter_index; }; +struct ice_adv_fltr_mgmt_list_entry { + struct list_head list_entry; + + struct ice_adv_lkup_elem *lkups; + struct ice_adv_rule_info rule_info; + u16 lkups_cnt; + struct ice_vsi_list_map_info *vsi_list_info; + u16 vsi_count; +}; + enum ice_promisc_flags { ICE_PROMISC_UCAST_RX = 0x1, ICE_PROMISC_UCAST_TX = 0x2, @@ -218,6 +311,10 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id); /* Switch/bridge related commands */ +enum ice_status +ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, + u16 lkups_cnt, struct ice_adv_rule_info *rinfo, + struct ice_rule_query_data *added_entry); enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw); enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_lst); enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst); @@ -245,10 +342,19 @@ enum ice_status ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, bool rm_vlan_promisc); +enum ice_status +ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle); +enum ice_status +ice_rem_adv_rule_by_id(struct ice_hw *hw, + struct ice_rule_query_data *remove_entry); + enum ice_status ice_init_def_sw_recp(struct ice_hw *hw); u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle); enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle); void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw); +enum ice_status +ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, + u8 num_rules, enum ice_adminq_opc opc, struct ice_sq_cd *cd); #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c new file mode 100644 index 000000000000..4c1daa1a02a1 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -0,0 +1,855 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#include "ice.h" +#include "ice_tc_lib.h" +#include "ice_lib.h" +#include "ice_fltr.h" + +/** + * ice_tc_count_lkups - determine lookup count for switch filter + * @flags: TC-flower flags + * @headers: Pointer to TC flower filter header structure + * @fltr: Pointer to outer TC filter structure + * + * Determine lookup count based on TC flower input for switch filter. + */ +static int +ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, + struct ice_tc_flower_fltr *fltr) +{ + int lkups_cnt = 0; + + if (flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) + lkups_cnt++; + + /* are MAC fields specified? */ + if (flags & (ICE_TC_FLWR_FIELD_DST_MAC | ICE_TC_FLWR_FIELD_SRC_MAC)) + lkups_cnt++; + + /* is VLAN specified? */ + if (flags & ICE_TC_FLWR_FIELD_VLAN) + lkups_cnt++; + + /* are IPv[4|6] fields specified? */ + if (flags & (ICE_TC_FLWR_FIELD_DEST_IPV4 | ICE_TC_FLWR_FIELD_SRC_IPV4)) + lkups_cnt++; + else if (flags & (ICE_TC_FLWR_FIELD_DEST_IPV6 | + ICE_TC_FLWR_FIELD_SRC_IPV6)) + lkups_cnt++; + + /* is L4 (TCP/UDP/any other L4 protocol fields) specified? */ + if (flags & (ICE_TC_FLWR_FIELD_DEST_L4_PORT | + ICE_TC_FLWR_FIELD_SRC_L4_PORT)) + lkups_cnt++; + + return lkups_cnt; +} + +/** + * ice_tc_fill_rules - fill filter rules based on TC fltr + * @hw: pointer to HW structure + * @flags: tc flower field flags + * @tc_fltr: pointer to TC flower filter + * @list: list of advance rule elements + * @rule_info: pointer to information about rule + * @l4_proto: pointer to information such as L4 proto type + * + * Fill ice_adv_lkup_elem list based on TC flower flags and + * TC flower headers. This list should be used to add + * advance filter in hardware. + */ +static int +ice_tc_fill_rules(struct ice_hw *hw, u32 flags, + struct ice_tc_flower_fltr *tc_fltr, + struct ice_adv_lkup_elem *list, + struct ice_adv_rule_info *rule_info, + u16 *l4_proto) +{ + struct ice_tc_flower_lyr_2_4_hdrs *headers = &tc_fltr->outer_headers; + int i = 0; + + if (flags & ICE_TC_FLWR_FIELD_ETH_TYPE_ID) { + list[i].type = ICE_ETYPE_OL; + list[i].h_u.ethertype.ethtype_id = headers->l2_key.n_proto; + list[i].m_u.ethertype.ethtype_id = headers->l2_mask.n_proto; + i++; + } + + if (flags & (ICE_TC_FLWR_FIELD_DST_MAC | + ICE_TC_FLWR_FIELD_SRC_MAC)) { + struct ice_tc_l2_hdr *l2_key, *l2_mask; + + l2_key = &headers->l2_key; + l2_mask = &headers->l2_mask; + + list[i].type = ICE_MAC_OFOS; + if (flags & ICE_TC_FLWR_FIELD_DST_MAC) { + ether_addr_copy(list[i].h_u.eth_hdr.dst_addr, + l2_key->dst_mac); + ether_addr_copy(list[i].m_u.eth_hdr.dst_addr, + l2_mask->dst_mac); + } + if (flags & ICE_TC_FLWR_FIELD_SRC_MAC) { + ether_addr_copy(list[i].h_u.eth_hdr.src_addr, + l2_key->src_mac); + ether_addr_copy(list[i].m_u.eth_hdr.src_addr, + l2_mask->src_mac); + } + i++; + } + + /* copy VLAN info */ + if (flags & ICE_TC_FLWR_FIELD_VLAN) { + list[i].type = ICE_VLAN_OFOS; + list[i].h_u.vlan_hdr.vlan = headers->vlan_hdr.vlan_id; + list[i].m_u.vlan_hdr.vlan = cpu_to_be16(0xFFFF); + i++; + } + + /* copy L3 (IPv[4|6]: src, dest) address */ + if (flags & (ICE_TC_FLWR_FIELD_DEST_IPV4 | + ICE_TC_FLWR_FIELD_SRC_IPV4)) { + struct ice_tc_l3_hdr *l3_key, *l3_mask; + + list[i].type = ICE_IPV4_OFOS; + l3_key = &headers->l3_key; + l3_mask = &headers->l3_mask; + if (flags & ICE_TC_FLWR_FIELD_DEST_IPV4) { + list[i].h_u.ipv4_hdr.dst_addr = l3_key->dst_ipv4; + list[i].m_u.ipv4_hdr.dst_addr = l3_mask->dst_ipv4; + } + if (flags & ICE_TC_FLWR_FIELD_SRC_IPV4) { + list[i].h_u.ipv4_hdr.src_addr = l3_key->src_ipv4; + list[i].m_u.ipv4_hdr.src_addr = l3_mask->src_ipv4; + } + i++; + } else if (flags & (ICE_TC_FLWR_FIELD_DEST_IPV6 | + ICE_TC_FLWR_FIELD_SRC_IPV6)) { + struct ice_ipv6_hdr *ipv6_hdr, *ipv6_mask; + struct ice_tc_l3_hdr *l3_key, *l3_mask; + + list[i].type = ICE_IPV6_OFOS; + ipv6_hdr = &list[i].h_u.ipv6_hdr; + ipv6_mask = &list[i].m_u.ipv6_hdr; + l3_key = &headers->l3_key; + l3_mask = &headers->l3_mask; + + if (flags & ICE_TC_FLWR_FIELD_DEST_IPV6) { + memcpy(&ipv6_hdr->dst_addr, &l3_key->dst_ipv6_addr, + sizeof(l3_key->dst_ipv6_addr)); + memcpy(&ipv6_mask->dst_addr, &l3_mask->dst_ipv6_addr, + sizeof(l3_mask->dst_ipv6_addr)); + } + if (flags & ICE_TC_FLWR_FIELD_SRC_IPV6) { + memcpy(&ipv6_hdr->src_addr, &l3_key->src_ipv6_addr, + sizeof(l3_key->src_ipv6_addr)); + memcpy(&ipv6_mask->src_addr, &l3_mask->src_ipv6_addr, + sizeof(l3_mask->src_ipv6_addr)); + } + i++; + } + + /* copy L4 (src, dest) port */ + if (flags & (ICE_TC_FLWR_FIELD_DEST_L4_PORT | + ICE_TC_FLWR_FIELD_SRC_L4_PORT)) { + struct ice_tc_l4_hdr *l4_key, *l4_mask; + + l4_key = &headers->l4_key; + l4_mask = &headers->l4_mask; + if (headers->l3_key.ip_proto == IPPROTO_TCP) { + list[i].type = ICE_TCP_IL; + /* detected L4 proto is TCP */ + if (l4_proto) + *l4_proto = IPPROTO_TCP; + } else if (headers->l3_key.ip_proto == IPPROTO_UDP) { + list[i].type = ICE_UDP_ILOS; + /* detected L4 proto is UDP */ + if (l4_proto) + *l4_proto = IPPROTO_UDP; + } + if (flags & ICE_TC_FLWR_FIELD_DEST_L4_PORT) { + list[i].h_u.l4_hdr.dst_port = l4_key->dst_port; + list[i].m_u.l4_hdr.dst_port = l4_mask->dst_port; + } + if (flags & ICE_TC_FLWR_FIELD_SRC_L4_PORT) { + list[i].h_u.l4_hdr.src_port = l4_key->src_port; + list[i].m_u.l4_hdr.src_port = l4_mask->src_port; + } + i++; + } + + return i; +} + +static int +ice_eswitch_tc_parse_action(struct ice_tc_flower_fltr *fltr, + struct flow_action_entry *act) +{ + struct ice_repr *repr; + + switch (act->id) { + case FLOW_ACTION_DROP: + fltr->action.fltr_act = ICE_DROP_PACKET; + break; + + case FLOW_ACTION_REDIRECT: + fltr->action.fltr_act = ICE_FWD_TO_VSI; + + if (ice_is_port_repr_netdev(act->dev)) { + repr = ice_netdev_to_repr(act->dev); + + fltr->dest_vsi = repr->src_vsi; + fltr->direction = ICE_ESWITCH_FLTR_INGRESS; + } else if (netif_is_ice(act->dev)) { + struct ice_netdev_priv *np = netdev_priv(act->dev); + + fltr->dest_vsi = np->vsi; + fltr->direction = ICE_ESWITCH_FLTR_EGRESS; + } else { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported netdevice in switchdev mode"); + return -EINVAL; + } + + break; + + default: + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported action in switchdev mode"); + return -EINVAL; + } + + return 0; +} + +static int +ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) +{ + struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers; + struct ice_adv_rule_info rule_info = { 0 }; + struct ice_rule_query_data rule_added; + struct ice_hw *hw = &vsi->back->hw; + struct ice_adv_lkup_elem *list; + u32 flags = fltr->flags; + enum ice_status status; + int lkups_cnt; + int ret = 0; + int i; + + if (!flags || (flags & (ICE_TC_FLWR_FIELD_ENC_DEST_IPV4 | + ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 | + ICE_TC_FLWR_FIELD_ENC_DEST_IPV6 | + ICE_TC_FLWR_FIELD_ENC_SRC_IPV6 | + ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT))) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported encap field(s)"); + return -EOPNOTSUPP; + } + + lkups_cnt = ice_tc_count_lkups(flags, headers, fltr); + list = kcalloc(lkups_cnt, sizeof(*list), GFP_ATOMIC); + if (!list) + return -ENOMEM; + + i = ice_tc_fill_rules(hw, flags, fltr, list, &rule_info, NULL); + if (i != lkups_cnt) { + ret = -EINVAL; + goto exit; + } + + rule_info.sw_act.fltr_act = fltr->action.fltr_act; + if (fltr->action.fltr_act != ICE_DROP_PACKET) + rule_info.sw_act.vsi_handle = fltr->dest_vsi->idx; + /* For now, making priority to be highest, and it also becomes + * the priority for recipe which will get created as a result of + * new extraction sequence based on input set. + * Priority '7' is max val for switch recipe, higher the number + * results into order of switch rule evaluation. + */ + rule_info.priority = 7; + + if (fltr->direction == ICE_ESWITCH_FLTR_INGRESS) { + rule_info.sw_act.flag |= ICE_FLTR_RX; + rule_info.sw_act.src = hw->pf_id; + rule_info.rx = true; + } else { + rule_info.sw_act.flag |= ICE_FLTR_TX; + rule_info.sw_act.src = vsi->idx; + rule_info.rx = false; + } + + /* specify the cookie as filter_rule_id */ + rule_info.fltr_rule_id = fltr->cookie; + + status = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); + if (status == ICE_ERR_ALREADY_EXISTS) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because it already exist"); + ret = -EINVAL; + goto exit; + } else if (status) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter due to error"); + ret = -EIO; + goto exit; + } + + /* store the output params, which are needed later for removing + * advanced switch filter + */ + fltr->rid = rule_added.rid; + fltr->rule_id = rule_added.rule_id; + + if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS) { + if (ice_fltr_update_flags(vsi, fltr->rule_id, fltr->rid, + ICE_SINGLE_ACT_LAN_ENABLE)) + ice_rem_adv_rule_by_id(hw, &rule_added); + } + +exit: + kfree(list); + return ret; +} + +/** + * ice_tc_set_ipv4 - Parse IPv4 addresses from TC flower filter + * @match: Pointer to flow match structure + * @fltr: Pointer to filter structure + * @headers: inner or outer header fields + */ +static int +ice_tc_set_ipv4(struct flow_match_ipv4_addrs *match, + struct ice_tc_flower_fltr *fltr, + struct ice_tc_flower_lyr_2_4_hdrs *headers) +{ + if (match->key->dst) { + fltr->flags |= ICE_TC_FLWR_FIELD_DEST_IPV4; + headers->l3_key.dst_ipv4 = match->key->dst; + headers->l3_mask.dst_ipv4 = match->mask->dst; + } + if (match->key->src) { + fltr->flags |= ICE_TC_FLWR_FIELD_SRC_IPV4; + headers->l3_key.src_ipv4 = match->key->src; + headers->l3_mask.src_ipv4 = match->mask->src; + } + return 0; +} + +/** + * ice_tc_set_ipv6 - Parse IPv6 addresses from TC flower filter + * @match: Pointer to flow match structure + * @fltr: Pointer to filter structure + * @headers: inner or outer header fields + */ +static int +ice_tc_set_ipv6(struct flow_match_ipv6_addrs *match, + struct ice_tc_flower_fltr *fltr, + struct ice_tc_flower_lyr_2_4_hdrs *headers) +{ + struct ice_tc_l3_hdr *l3_key, *l3_mask; + + /* src and dest IPV6 address should not be LOOPBACK + * (0:0:0:0:0:0:0:1), which can be represented as ::1 + */ + if (ipv6_addr_loopback(&match->key->dst) || + ipv6_addr_loopback(&match->key->src)) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Bad IPv6, addr is LOOPBACK"); + return -EINVAL; + } + /* if src/dest IPv6 address is *,* error */ + if (ipv6_addr_any(&match->mask->dst) && + ipv6_addr_any(&match->mask->src)) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Bad src/dest IPv6, addr is any"); + return -EINVAL; + } + if (!ipv6_addr_any(&match->mask->dst)) + fltr->flags |= ICE_TC_FLWR_FIELD_DEST_IPV6; + if (!ipv6_addr_any(&match->mask->src)) + fltr->flags |= ICE_TC_FLWR_FIELD_SRC_IPV6; + + l3_key = &headers->l3_key; + l3_mask = &headers->l3_mask; + + if (fltr->flags & ICE_TC_FLWR_FIELD_SRC_IPV6) { + memcpy(&l3_key->src_ipv6_addr, &match->key->src.s6_addr, + sizeof(match->key->src.s6_addr)); + memcpy(&l3_mask->src_ipv6_addr, &match->mask->src.s6_addr, + sizeof(match->mask->src.s6_addr)); + } + if (fltr->flags & ICE_TC_FLWR_FIELD_DEST_IPV6) { + memcpy(&l3_key->dst_ipv6_addr, &match->key->dst.s6_addr, + sizeof(match->key->dst.s6_addr)); + memcpy(&l3_mask->dst_ipv6_addr, &match->mask->dst.s6_addr, + sizeof(match->mask->dst.s6_addr)); + } + + return 0; +} + +/** + * ice_tc_set_port - Parse ports from TC flower filter + * @match: Flow match structure + * @fltr: Pointer to filter structure + * @headers: inner or outer header fields + */ +static int +ice_tc_set_port(struct flow_match_ports match, + struct ice_tc_flower_fltr *fltr, + struct ice_tc_flower_lyr_2_4_hdrs *headers) +{ + if (match.key->dst) { + fltr->flags |= ICE_TC_FLWR_FIELD_DEST_L4_PORT; + headers->l4_key.dst_port = match.key->dst; + headers->l4_mask.dst_port = match.mask->dst; + } + if (match.key->src) { + fltr->flags |= ICE_TC_FLWR_FIELD_SRC_L4_PORT; + headers->l4_key.src_port = match.key->src; + headers->l4_mask.src_port = match.mask->src; + } + return 0; +} + +/** + * ice_parse_cls_flower - Parse TC flower filters provided by kernel + * @vsi: Pointer to the VSI + * @filter_dev: Pointer to device on which filter is being added + * @f: Pointer to struct flow_cls_offload + * @fltr: Pointer to filter structure + */ +static int +ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, + struct flow_cls_offload *f, + struct ice_tc_flower_fltr *fltr) +{ + struct ice_tc_flower_lyr_2_4_hdrs *headers = &fltr->outer_headers; + struct flow_rule *rule = flow_cls_offload_flow_rule(f); + u16 n_proto_mask = 0, n_proto_key = 0, addr_type = 0; + struct flow_dissector *dissector; + + dissector = rule->match.dissector; + + if (dissector->used_keys & + ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_VLAN) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_ENC_IP) | + BIT(FLOW_DISSECTOR_KEY_PORTS))) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported key used"); + return -EOPNOTSUPP; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); + + n_proto_key = ntohs(match.key->n_proto); + n_proto_mask = ntohs(match.mask->n_proto); + + if (n_proto_key == ETH_P_ALL || n_proto_key == 0) { + n_proto_key = 0; + n_proto_mask = 0; + } else { + fltr->flags |= ICE_TC_FLWR_FIELD_ETH_TYPE_ID; + } + + headers->l2_key.n_proto = cpu_to_be16(n_proto_key); + headers->l2_mask.n_proto = cpu_to_be16(n_proto_mask); + headers->l3_key.ip_proto = match.key->ip_proto; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + + flow_rule_match_eth_addrs(rule, &match); + + if (!is_zero_ether_addr(match.key->dst)) { + ether_addr_copy(headers->l2_key.dst_mac, + match.key->dst); + ether_addr_copy(headers->l2_mask.dst_mac, + match.mask->dst); + fltr->flags |= ICE_TC_FLWR_FIELD_DST_MAC; + } + + if (!is_zero_ether_addr(match.key->src)) { + ether_addr_copy(headers->l2_key.src_mac, + match.key->src); + ether_addr_copy(headers->l2_mask.src_mac, + match.mask->src); + fltr->flags |= ICE_TC_FLWR_FIELD_SRC_MAC; + } + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN) || + is_vlan_dev(filter_dev)) { + struct flow_dissector_key_vlan mask; + struct flow_dissector_key_vlan key; + struct flow_match_vlan match; + + if (is_vlan_dev(filter_dev)) { + match.key = &key; + match.key->vlan_id = vlan_dev_vlan_id(filter_dev); + match.key->vlan_priority = 0; + match.mask = &mask; + memset(match.mask, 0xff, sizeof(*match.mask)); + match.mask->vlan_priority = 0; + } else { + flow_rule_match_vlan(rule, &match); + } + + if (match.mask->vlan_id) { + if (match.mask->vlan_id == VLAN_VID_MASK) { + fltr->flags |= ICE_TC_FLWR_FIELD_VLAN; + } else { + NL_SET_ERR_MSG_MOD(fltr->extack, "Bad VLAN mask"); + return -EINVAL; + } + } + + headers->vlan_hdr.vlan_id = + cpu_to_be16(match.key->vlan_id & VLAN_VID_MASK); + if (match.mask->vlan_priority) + headers->vlan_hdr.vlan_prio = match.key->vlan_priority; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_control(rule, &match); + + addr_type = match.key->addr_type; + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(rule, &match); + if (ice_tc_set_ipv4(&match, fltr, headers)) + return -EINVAL; + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); + if (ice_tc_set_ipv6(&match, fltr, headers)) + return -EINVAL; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + flow_rule_match_ports(rule, &match); + if (ice_tc_set_port(match, fltr, headers)) + return -EINVAL; + switch (headers->l3_key.ip_proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + break; + default: + NL_SET_ERR_MSG_MOD(fltr->extack, "Only UDP and TCP transport are supported"); + return -EINVAL; + } + } + return 0; +} + +/** + * ice_add_switch_fltr - Add TC flower filters + * @vsi: Pointer to VSI + * @fltr: Pointer to struct ice_tc_flower_fltr + * + * Add filter in HW switch block + */ +static int +ice_add_switch_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) +{ + if (ice_is_eswitch_mode_switchdev(vsi->back)) + return ice_eswitch_add_tc_fltr(vsi, fltr); + + return -EOPNOTSUPP; +} + +/** + * ice_handle_tclass_action - Support directing to a traffic class + * @vsi: Pointer to VSI + * @cls_flower: Pointer to TC flower offload structure + * @fltr: Pointer to TC flower filter structure + * + * Support directing traffic to a traffic class + */ +static int +ice_handle_tclass_action(struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, + struct ice_tc_flower_fltr *fltr) +{ + int tc = tc_classid_to_hwtc(vsi->netdev, cls_flower->classid); + + if (tc < 0) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because specified destination is invalid"); + return -EINVAL; + } + if (!tc) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because of invalid destination"); + return -EINVAL; + } + + if (!(vsi->tc_cfg.ena_tc & BIT(tc))) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because of non-existence destination"); + return -EINVAL; + } + + /* Redirect to a TC class or Queue Group */ + fltr->action.fltr_act = ICE_FWD_TO_QGRP; + fltr->action.tc_class = tc; + + return 0; +} + +/** + * ice_parse_tc_flower_actions - Parse the actions for a TC filter + * @vsi: Pointer to VSI + * @cls_flower: Pointer to TC flower offload structure + * @fltr: Pointer to TC flower filter structure + * + * Parse the actions for a TC filter + */ +static int +ice_parse_tc_flower_actions(struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower, + struct ice_tc_flower_fltr *fltr) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(cls_flower); + struct flow_action *flow_action = &rule->action; + struct flow_action_entry *act; + int i; + + if (cls_flower->classid) + return ice_handle_tclass_action(vsi, cls_flower, fltr); + + if (!flow_action_has_entries(flow_action)) + return -EINVAL; + + flow_action_for_each(i, act, flow_action) { + if (ice_is_eswitch_mode_switchdev(vsi->back)) { + int err = ice_eswitch_tc_parse_action(fltr, act); + + if (err) + return err; + continue; + } + /* Allow only one rule per filter */ + + /* Drop action */ + if (act->id == FLOW_ACTION_DROP) { + fltr->action.fltr_act = ICE_DROP_PACKET; + return 0; + } + fltr->action.fltr_act = ICE_FWD_TO_VSI; + } + return 0; +} + +/** + * ice_del_tc_fltr - deletes a filter from HW table + * @vsi: Pointer to VSI + * @fltr: Pointer to struct ice_tc_flower_fltr + * + * This function deletes a filter from HW table and manages book-keeping + */ +static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) +{ + struct ice_rule_query_data rule_rem; + struct ice_pf *pf = vsi->back; + int err; + + rule_rem.rid = fltr->rid; + rule_rem.rule_id = fltr->rule_id; + rule_rem.vsi_handle = fltr->dest_id; + err = ice_rem_adv_rule_by_id(&pf->hw, &rule_rem); + if (err) { + if (err == ICE_ERR_DOES_NOT_EXIST) { + NL_SET_ERR_MSG_MOD(fltr->extack, "Filter does not exist"); + return -ENOENT; + } + NL_SET_ERR_MSG_MOD(fltr->extack, "Failed to delete TC flower filter"); + return -EIO; + } + + return 0; +} + +/** + * ice_add_tc_fltr - adds a TC flower filter + * @netdev: Pointer to netdev + * @vsi: Pointer to VSI + * @f: Pointer to flower offload structure + * @__fltr: Pointer to struct ice_tc_flower_fltr + * + * This function parses TC-flower input fields, parses action, + * and adds a filter. + */ +static int +ice_add_tc_fltr(struct net_device *netdev, struct ice_vsi *vsi, + struct flow_cls_offload *f, + struct ice_tc_flower_fltr **__fltr) +{ + struct ice_tc_flower_fltr *fltr; + int err; + + /* by default, set output to be INVALID */ + *__fltr = NULL; + + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) + return -ENOMEM; + + fltr->cookie = f->cookie; + fltr->extack = f->common.extack; + fltr->src_vsi = vsi; + INIT_HLIST_NODE(&fltr->tc_flower_node); + + err = ice_parse_cls_flower(netdev, vsi, f, fltr); + if (err < 0) + goto err; + + err = ice_parse_tc_flower_actions(vsi, f, fltr); + if (err < 0) + goto err; + + err = ice_add_switch_fltr(vsi, fltr); + if (err < 0) + goto err; + + /* return the newly created filter */ + *__fltr = fltr; + + return 0; +err: + kfree(fltr); + return err; +} + +/** + * ice_find_tc_flower_fltr - Find the TC flower filter in the list + * @pf: Pointer to PF + * @cookie: filter specific cookie + */ +static struct ice_tc_flower_fltr * +ice_find_tc_flower_fltr(struct ice_pf *pf, unsigned long cookie) +{ + struct ice_tc_flower_fltr *fltr; + + hlist_for_each_entry(fltr, &pf->tc_flower_fltr_list, tc_flower_node) + if (cookie == fltr->cookie) + return fltr; + + return NULL; +} + +/** + * ice_add_cls_flower - add TC flower filters + * @netdev: Pointer to filter device + * @vsi: Pointer to VSI + * @cls_flower: Pointer to flower offload structure + */ +int +ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower) +{ + struct netlink_ext_ack *extack = cls_flower->common.extack; + struct net_device *vsi_netdev = vsi->netdev; + struct ice_tc_flower_fltr *fltr; + struct ice_pf *pf = vsi->back; + int err; + + if (ice_is_reset_in_progress(pf->state)) + return -EBUSY; + if (test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) + return -EINVAL; + + if (ice_is_port_repr_netdev(netdev)) + vsi_netdev = netdev; + + if (!(vsi_netdev->features & NETIF_F_HW_TC) && + !test_bit(ICE_FLAG_CLS_FLOWER, pf->flags)) { + /* Based on TC indirect notifications from kernel, all ice + * devices get an instance of rule from higher level device. + * Avoid triggering explicit error in this case. + */ + if (netdev == vsi_netdev) + NL_SET_ERR_MSG_MOD(extack, "can't apply TC flower filters, turn ON hw-tc-offload and try again"); + return -EINVAL; + } + + /* avoid duplicate entries, if exists - return error */ + fltr = ice_find_tc_flower_fltr(pf, cls_flower->cookie); + if (fltr) { + NL_SET_ERR_MSG_MOD(extack, "filter cookie already exists, ignoring"); + return -EEXIST; + } + + /* prep and add TC-flower filter in HW */ + err = ice_add_tc_fltr(netdev, vsi, cls_flower, &fltr); + if (err) + return err; + + /* add filter into an ordered list */ + hlist_add_head(&fltr->tc_flower_node, &pf->tc_flower_fltr_list); + return 0; +} + +/** + * ice_del_cls_flower - delete TC flower filters + * @vsi: Pointer to VSI + * @cls_flower: Pointer to struct flow_cls_offload + */ +int +ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower) +{ + struct ice_tc_flower_fltr *fltr; + struct ice_pf *pf = vsi->back; + int err; + + /* find filter */ + fltr = ice_find_tc_flower_fltr(pf, cls_flower->cookie); + if (!fltr) { + if (hlist_empty(&pf->tc_flower_fltr_list)) + return 0; + + NL_SET_ERR_MSG_MOD(cls_flower->common.extack, "failed to delete TC flower filter because unable to find it"); + return -EINVAL; + } + + fltr->extack = cls_flower->common.extack; + /* delete filter from HW */ + err = ice_del_tc_fltr(vsi, fltr); + if (err) + return err; + + /* delete filter from an ordered list */ + hlist_del(&fltr->tc_flower_node); + + /* free the filter node */ + kfree(fltr); + + return 0; +} + +/** + * ice_replay_tc_fltrs - replay TC filters + * @pf: pointer to PF struct + */ +void ice_replay_tc_fltrs(struct ice_pf *pf) +{ + struct ice_tc_flower_fltr *fltr; + struct hlist_node *node; + + hlist_for_each_entry_safe(fltr, node, + &pf->tc_flower_fltr_list, + tc_flower_node) { + fltr->extack = NULL; + ice_add_switch_fltr(fltr->src_vsi, fltr); + } +} diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h new file mode 100644 index 000000000000..d90e9e37ae25 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021, Intel Corporation. */ + +#ifndef _ICE_TC_LIB_H_ +#define _ICE_TC_LIB_H_ + +#define ICE_TC_FLWR_FIELD_DST_MAC BIT(0) +#define ICE_TC_FLWR_FIELD_SRC_MAC BIT(1) +#define ICE_TC_FLWR_FIELD_VLAN BIT(2) +#define ICE_TC_FLWR_FIELD_DEST_IPV4 BIT(3) +#define ICE_TC_FLWR_FIELD_SRC_IPV4 BIT(4) +#define ICE_TC_FLWR_FIELD_DEST_IPV6 BIT(5) +#define ICE_TC_FLWR_FIELD_SRC_IPV6 BIT(6) +#define ICE_TC_FLWR_FIELD_DEST_L4_PORT BIT(7) +#define ICE_TC_FLWR_FIELD_SRC_L4_PORT BIT(8) +#define ICE_TC_FLWR_FIELD_TENANT_ID BIT(9) +#define ICE_TC_FLWR_FIELD_ENC_DEST_IPV4 BIT(10) +#define ICE_TC_FLWR_FIELD_ENC_SRC_IPV4 BIT(11) +#define ICE_TC_FLWR_FIELD_ENC_DEST_IPV6 BIT(12) +#define ICE_TC_FLWR_FIELD_ENC_SRC_IPV6 BIT(13) +#define ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT BIT(14) +#define ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT BIT(15) +#define ICE_TC_FLWR_FIELD_ENC_DST_MAC BIT(16) +#define ICE_TC_FLWR_FIELD_ETH_TYPE_ID BIT(17) + +struct ice_tc_flower_action { + u32 tc_class; + enum ice_sw_fwd_act_type fltr_act; +}; + +struct ice_tc_vlan_hdr { + __be16 vlan_id; /* Only last 12 bits valid */ + u16 vlan_prio; /* Only last 3 bits valid (valid values: 0..7) */ +}; + +struct ice_tc_l2_hdr { + u8 dst_mac[ETH_ALEN]; + u8 src_mac[ETH_ALEN]; + __be16 n_proto; /* Ethernet Protocol */ +}; + +struct ice_tc_l3_hdr { + u8 ip_proto; /* IPPROTO value */ + union { + struct { + struct in_addr dst_ip; + struct in_addr src_ip; + } v4; + struct { + struct in6_addr dst_ip6; + struct in6_addr src_ip6; + } v6; + } ip; +#define dst_ipv6 ip.v6.dst_ip6.s6_addr32 +#define dst_ipv6_addr ip.v6.dst_ip6.s6_addr +#define src_ipv6 ip.v6.src_ip6.s6_addr32 +#define src_ipv6_addr ip.v6.src_ip6.s6_addr +#define dst_ipv4 ip.v4.dst_ip.s_addr +#define src_ipv4 ip.v4.src_ip.s_addr + + u8 tos; + u8 ttl; +}; + +struct ice_tc_l4_hdr { + __be16 dst_port; + __be16 src_port; +}; + +struct ice_tc_flower_lyr_2_4_hdrs { + /* L2 layer fields with their mask */ + struct ice_tc_l2_hdr l2_key; + struct ice_tc_l2_hdr l2_mask; + struct ice_tc_vlan_hdr vlan_hdr; + /* L3 (IPv4[6]) layer fields with their mask */ + struct ice_tc_l3_hdr l3_key; + struct ice_tc_l3_hdr l3_mask; + + /* L4 layer fields with their mask */ + struct ice_tc_l4_hdr l4_key; + struct ice_tc_l4_hdr l4_mask; +}; + +enum ice_eswitch_fltr_direction { + ICE_ESWITCH_FLTR_INGRESS, + ICE_ESWITCH_FLTR_EGRESS, +}; + +struct ice_tc_flower_fltr { + struct hlist_node tc_flower_node; + + /* cookie becomes filter_rule_id if rule is added successfully */ + unsigned long cookie; + + /* add_adv_rule returns information like recipe ID, rule_id. Store + * those values since they are needed to remove advanced rule + */ + u16 rid; + u16 rule_id; + /* this could be queue/vsi_idx (sw handle)/queue_group, depending upon + * destination type + */ + u16 dest_id; + /* if dest_id is vsi_idx, then need to store destination VSI ptr */ + struct ice_vsi *dest_vsi; + /* direction of fltr for eswitch use case */ + enum ice_eswitch_fltr_direction direction; + + /* Parsed TC flower configuration params */ + struct ice_tc_flower_lyr_2_4_hdrs outer_headers; + struct ice_tc_flower_lyr_2_4_hdrs inner_headers; + struct ice_vsi *src_vsi; + __be32 tenant_id; + u32 flags; + struct ice_tc_flower_action action; + + /* cache ptr which is used wherever needed to communicate netlink + * messages + */ + struct netlink_ext_ack *extack; +}; + +int +ice_add_cls_flower(struct net_device *netdev, struct ice_vsi *vsi, + struct flow_cls_offload *cls_flower); +int +ice_del_cls_flower(struct ice_vsi *vsi, struct flow_cls_offload *cls_flower); +void ice_replay_tc_fltrs(struct ice_pf *pf); + +#endif /* _ICE_TC_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h index 9bc0b8fdfc77..cf685247c07a 100644 --- a/drivers/net/ethernet/intel/ice/ice_trace.h +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -64,15 +64,15 @@ DECLARE_EVENT_CLASS(ice_rx_dim_template, TP_ARGS(q_vector, dim), TP_STRUCT__entry(__field(struct ice_q_vector *, q_vector) __field(struct dim *, dim) - __string(devname, q_vector->rx.ring->netdev->name)), + __string(devname, q_vector->rx.rx_ring->netdev->name)), TP_fast_assign(__entry->q_vector = q_vector; __entry->dim = dim; - __assign_str(devname, q_vector->rx.ring->netdev->name);), + __assign_str(devname, q_vector->rx.rx_ring->netdev->name);), TP_printk("netdev: %s Rx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", __get_str(devname), - __entry->q_vector->rx.ring->q_index, + __entry->q_vector->rx.rx_ring->q_index, __entry->dim->state, __entry->dim->profile_ix, __entry->dim->tune_state, @@ -91,15 +91,15 @@ DECLARE_EVENT_CLASS(ice_tx_dim_template, TP_ARGS(q_vector, dim), TP_STRUCT__entry(__field(struct ice_q_vector *, q_vector) __field(struct dim *, dim) - __string(devname, q_vector->tx.ring->netdev->name)), + __string(devname, q_vector->tx.tx_ring->netdev->name)), TP_fast_assign(__entry->q_vector = q_vector; __entry->dim = dim; - __assign_str(devname, q_vector->tx.ring->netdev->name);), + __assign_str(devname, q_vector->tx.tx_ring->netdev->name);), TP_printk("netdev: %s Tx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", __get_str(devname), - __entry->q_vector->tx.ring->q_index, + __entry->q_vector->tx.tx_ring->q_index, __entry->dim->state, __entry->dim->profile_ix, __entry->dim->tune_state, @@ -115,7 +115,7 @@ DEFINE_EVENT(ice_tx_dim_template, ice_tx_dim_work, /* Events related to a vsi & ring */ DECLARE_EVENT_CLASS(ice_tx_template, - TP_PROTO(struct ice_ring *ring, struct ice_tx_desc *desc, + TP_PROTO(struct ice_tx_ring *ring, struct ice_tx_desc *desc, struct ice_tx_buf *buf), TP_ARGS(ring, desc, buf), @@ -135,7 +135,7 @@ DECLARE_EVENT_CLASS(ice_tx_template, #define DEFINE_TX_TEMPLATE_OP_EVENT(name) \ DEFINE_EVENT(ice_tx_template, name, \ - TP_PROTO(struct ice_ring *ring, \ + TP_PROTO(struct ice_tx_ring *ring, \ struct ice_tx_desc *desc, \ struct ice_tx_buf *buf), \ TP_ARGS(ring, desc, buf)) @@ -145,7 +145,7 @@ DEFINE_TX_TEMPLATE_OP_EVENT(ice_clean_tx_irq_unmap); DEFINE_TX_TEMPLATE_OP_EVENT(ice_clean_tx_irq_unmap_eop); DECLARE_EVENT_CLASS(ice_rx_template, - TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc), + TP_PROTO(struct ice_rx_ring *ring, union ice_32b_rx_flex_desc *desc), TP_ARGS(ring, desc), @@ -161,12 +161,12 @@ DECLARE_EVENT_CLASS(ice_rx_template, __entry->ring, __entry->desc) ); DEFINE_EVENT(ice_rx_template, ice_clean_rx_irq, - TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc), + TP_PROTO(struct ice_rx_ring *ring, union ice_32b_rx_flex_desc *desc), TP_ARGS(ring, desc) ); DECLARE_EVENT_CLASS(ice_rx_indicate_template, - TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc, + TP_PROTO(struct ice_rx_ring *ring, union ice_32b_rx_flex_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb), @@ -186,13 +186,13 @@ DECLARE_EVENT_CLASS(ice_rx_indicate_template, ); DEFINE_EVENT(ice_rx_indicate_template, ice_clean_rx_irq_indicate, - TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc, + TP_PROTO(struct ice_rx_ring *ring, union ice_32b_rx_flex_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb) ); DECLARE_EVENT_CLASS(ice_xmit_template, - TP_PROTO(struct ice_ring *ring, struct sk_buff *skb), + TP_PROTO(struct ice_tx_ring *ring, struct sk_buff *skb), TP_ARGS(ring, skb), @@ -210,7 +210,7 @@ DECLARE_EVENT_CLASS(ice_xmit_template, #define DEFINE_XMIT_TEMPLATE_OP_EVENT(name) \ DEFINE_EVENT(ice_xmit_template, name, \ - TP_PROTO(struct ice_ring *ring, struct sk_buff *skb), \ + TP_PROTO(struct ice_tx_ring *ring, struct sk_buff *skb), \ TP_ARGS(ring, skb)) DEFINE_XMIT_TEMPLATE_OP_EVENT(ice_xmit_frame_ring); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 13b2bdc25b0d..01ae331927bd 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -14,6 +14,7 @@ #include "ice_trace.h" #include "ice_dcb_lib.h" #include "ice_xsk.h" +#include "ice_eswitch.h" #define ICE_RX_HDR_SIZE 256 @@ -33,7 +34,7 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc, struct ice_tx_buf *tx_buf, *first; struct ice_fltr_desc *f_desc; struct ice_tx_desc *tx_desc; - struct ice_ring *tx_ring; + struct ice_tx_ring *tx_ring; struct device *dev; dma_addr_t dma; u32 td_cmd; @@ -107,7 +108,7 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc, * @tx_buf: the buffer to free */ static void -ice_unmap_and_free_tx_buf(struct ice_ring *ring, struct ice_tx_buf *tx_buf) +ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf) { if (tx_buf->skb) { if (tx_buf->tx_flags & ICE_TX_FLAGS_DUMMY_PKT) @@ -134,7 +135,7 @@ ice_unmap_and_free_tx_buf(struct ice_ring *ring, struct ice_tx_buf *tx_buf) /* tx_buf must be completely set up in the transmit path */ } -static struct netdev_queue *txring_txq(const struct ice_ring *ring) +static struct netdev_queue *txring_txq(const struct ice_tx_ring *ring) { return netdev_get_tx_queue(ring->netdev, ring->q_index); } @@ -143,8 +144,9 @@ static struct netdev_queue *txring_txq(const struct ice_ring *ring) * ice_clean_tx_ring - Free any empty Tx buffers * @tx_ring: ring to be cleaned */ -void ice_clean_tx_ring(struct ice_ring *tx_ring) +void ice_clean_tx_ring(struct ice_tx_ring *tx_ring) { + u32 size; u16 i; if (ice_ring_is_xdp(tx_ring) && tx_ring->xsk_pool) { @@ -163,8 +165,10 @@ void ice_clean_tx_ring(struct ice_ring *tx_ring) tx_skip_free: memset(tx_ring->tx_buf, 0, sizeof(*tx_ring->tx_buf) * tx_ring->count); + size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc), + PAGE_SIZE); /* Zero out the descriptor ring */ - memset(tx_ring->desc, 0, tx_ring->size); + memset(tx_ring->desc, 0, size); tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; @@ -182,14 +186,18 @@ tx_skip_free: * * Free all transmit software resources */ -void ice_free_tx_ring(struct ice_ring *tx_ring) +void ice_free_tx_ring(struct ice_tx_ring *tx_ring) { + u32 size; + ice_clean_tx_ring(tx_ring); devm_kfree(tx_ring->dev, tx_ring->tx_buf); tx_ring->tx_buf = NULL; if (tx_ring->desc) { - dmam_free_coherent(tx_ring->dev, tx_ring->size, + size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc), + PAGE_SIZE); + dmam_free_coherent(tx_ring->dev, size, tx_ring->desc, tx_ring->dma); tx_ring->desc = NULL; } @@ -202,7 +210,7 @@ void ice_free_tx_ring(struct ice_ring *tx_ring) * * Returns true if there's any budget left (e.g. the clean is finished) */ -static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) +static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget) { unsigned int total_bytes = 0, total_pkts = 0; unsigned int budget = ICE_DFLT_IRQ_WORK; @@ -239,11 +247,8 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) total_bytes += tx_buf->bytecount; total_pkts += tx_buf->gso_segs; - if (ice_ring_is_xdp(tx_ring)) - page_frag_free(tx_buf->raw_buf); - else - /* free the skb */ - napi_consume_skb(tx_buf->skb, napi_budget); + /* free the skb */ + napi_consume_skb(tx_buf->skb, napi_budget); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -299,9 +304,6 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) ice_update_tx_ring_stats(tx_ring, total_pkts, total_bytes); - if (ice_ring_is_xdp(tx_ring)) - return !!budget; - netdev_tx_completed_queue(txring_txq(tx_ring), total_pkts, total_bytes); @@ -330,9 +332,10 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) * * Return 0 on success, negative on error */ -int ice_setup_tx_ring(struct ice_ring *tx_ring) +int ice_setup_tx_ring(struct ice_tx_ring *tx_ring) { struct device *dev = tx_ring->dev; + u32 size; if (!dev) return -ENOMEM; @@ -346,13 +349,13 @@ int ice_setup_tx_ring(struct ice_ring *tx_ring) return -ENOMEM; /* round up to nearest page */ - tx_ring->size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc), - PAGE_SIZE); - tx_ring->desc = dmam_alloc_coherent(dev, tx_ring->size, &tx_ring->dma, + size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc), + PAGE_SIZE); + tx_ring->desc = dmam_alloc_coherent(dev, size, &tx_ring->dma, GFP_KERNEL); if (!tx_ring->desc) { dev_err(dev, "Unable to allocate memory for the Tx descriptor ring, size=%d\n", - tx_ring->size); + size); goto err; } @@ -371,9 +374,10 @@ err: * ice_clean_rx_ring - Free Rx buffers * @rx_ring: ring to be cleaned */ -void ice_clean_rx_ring(struct ice_ring *rx_ring) +void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) { struct device *dev = rx_ring->dev; + u32 size; u16 i; /* ring already cleared, nothing to do */ @@ -418,7 +422,9 @@ rx_skip_free: memset(rx_ring->rx_buf, 0, sizeof(*rx_ring->rx_buf) * rx_ring->count); /* Zero out the descriptor ring */ - memset(rx_ring->desc, 0, rx_ring->size); + size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), + PAGE_SIZE); + memset(rx_ring->desc, 0, size); rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; @@ -431,8 +437,10 @@ rx_skip_free: * * Free all receive software resources */ -void ice_free_rx_ring(struct ice_ring *rx_ring) +void ice_free_rx_ring(struct ice_rx_ring *rx_ring) { + u32 size; + ice_clean_rx_ring(rx_ring); if (rx_ring->vsi->type == ICE_VSI_PF) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) @@ -442,7 +450,9 @@ void ice_free_rx_ring(struct ice_ring *rx_ring) rx_ring->rx_buf = NULL; if (rx_ring->desc) { - dmam_free_coherent(rx_ring->dev, rx_ring->size, + size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), + PAGE_SIZE); + dmam_free_coherent(rx_ring->dev, size, rx_ring->desc, rx_ring->dma); rx_ring->desc = NULL; } @@ -454,9 +464,10 @@ void ice_free_rx_ring(struct ice_ring *rx_ring) * * Return 0 on success, negative on error */ -int ice_setup_rx_ring(struct ice_ring *rx_ring) +int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) { struct device *dev = rx_ring->dev; + u32 size; if (!dev) return -ENOMEM; @@ -470,13 +481,13 @@ int ice_setup_rx_ring(struct ice_ring *rx_ring) return -ENOMEM; /* round up to nearest page */ - rx_ring->size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), - PAGE_SIZE); - rx_ring->desc = dmam_alloc_coherent(dev, rx_ring->size, &rx_ring->dma, + size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), + PAGE_SIZE); + rx_ring->desc = dmam_alloc_coherent(dev, size, &rx_ring->dma, GFP_KERNEL); if (!rx_ring->desc) { dev_err(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n", - rx_ring->size); + size); goto err; } @@ -500,7 +511,7 @@ err: } static unsigned int -ice_rx_frame_truesize(struct ice_ring *rx_ring, unsigned int __maybe_unused size) +ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, unsigned int __maybe_unused size) { unsigned int truesize; @@ -520,15 +531,15 @@ ice_rx_frame_truesize(struct ice_ring *rx_ring, unsigned int __maybe_unused size * @rx_ring: Rx ring * @xdp: xdp_buff used as input to the XDP program * @xdp_prog: XDP program to run + * @xdp_ring: ring to be used for XDP_TX action * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ static int -ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) +ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring) { - struct ice_ring *xdp_ring; - int err, result; + int err; u32 act; act = bpf_prog_run_xdp(xdp_prog, xdp); @@ -536,11 +547,14 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, case XDP_PASS: return ICE_XDP_PASS; case XDP_TX: - xdp_ring = rx_ring->vsi->xdp_rings[smp_processor_id()]; - result = ice_xmit_xdp_buff(xdp, xdp_ring); - if (result == ICE_XDP_CONSUMED) + if (static_branch_unlikely(&ice_xdp_locking_key)) + spin_lock(&xdp_ring->tx_lock); + err = ice_xmit_xdp_ring(xdp->data, xdp->data_end - xdp->data, xdp_ring); + if (static_branch_unlikely(&ice_xdp_locking_key)) + spin_unlock(&xdp_ring->tx_lock); + if (err == ICE_XDP_CONSUMED) goto out_failure; - return result; + return err; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); if (err) @@ -577,7 +591,7 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, struct ice_netdev_priv *np = netdev_priv(dev); unsigned int queue_index = smp_processor_id(); struct ice_vsi *vsi = np->vsi; - struct ice_ring *xdp_ring; + struct ice_tx_ring *xdp_ring; int nxmit = 0, i; if (test_bit(ICE_VSI_DOWN, vsi->state)) @@ -589,7 +603,14 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; - xdp_ring = vsi->xdp_rings[queue_index]; + if (static_branch_unlikely(&ice_xdp_locking_key)) { + queue_index %= vsi->num_xdp_txq; + xdp_ring = vsi->xdp_rings[queue_index]; + spin_lock(&xdp_ring->tx_lock); + } else { + xdp_ring = vsi->xdp_rings[queue_index]; + } + for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; int err; @@ -603,6 +624,9 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, if (unlikely(flags & XDP_XMIT_FLUSH)) ice_xdp_ring_update_tail(xdp_ring); + if (static_branch_unlikely(&ice_xdp_locking_key)) + spin_unlock(&xdp_ring->tx_lock); + return nxmit; } @@ -615,7 +639,7 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, * reused. */ static bool -ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi) +ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi) { struct page *page = bi->page; dma_addr_t dma; @@ -666,7 +690,7 @@ ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi) * buffers. Then bump tail at most one time. Grouping like this lets us avoid * multiple tail writes per call. */ -bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count) +bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, u16 cleaned_count) { union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; @@ -795,7 +819,7 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf, int rx_buf_pgcnt) * The function will then update the page offset. */ static void -ice_add_rx_frag(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, +ice_add_rx_frag(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, struct sk_buff *skb, unsigned int size) { #if (PAGE_SIZE >= 8192) @@ -821,7 +845,7 @@ ice_add_rx_frag(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * Synchronizes page for reuse by the adapter */ static void -ice_reuse_rx_page(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf) +ice_reuse_rx_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *old_buf) { u16 nta = rx_ring->next_to_alloc; struct ice_rx_buf *new_buf; @@ -852,7 +876,7 @@ ice_reuse_rx_page(struct ice_ring *rx_ring, struct ice_rx_buf *old_buf) * for use by the CPU. */ static struct ice_rx_buf * -ice_get_rx_buf(struct ice_ring *rx_ring, const unsigned int size, +ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, int *rx_buf_pgcnt) { struct ice_rx_buf *rx_buf; @@ -889,7 +913,7 @@ ice_get_rx_buf(struct ice_ring *rx_ring, const unsigned int size, * to set up the skb correctly and avoid any memcpy overhead. */ static struct sk_buff * -ice_build_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, +ice_build_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, struct xdp_buff *xdp) { u8 metasize = xdp->data - xdp->data_meta; @@ -941,7 +965,7 @@ ice_build_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * skb correctly. */ static struct sk_buff * -ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, +ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, struct xdp_buff *xdp) { unsigned int size = xdp->data_end - xdp->data; @@ -1001,7 +1025,7 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * the associated resources. */ static void -ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, +ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, int rx_buf_pgcnt) { u16 ntc = rx_ring->next_to_clean + 1; @@ -1037,7 +1061,7 @@ ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, * otherwise return true indicating that this is in fact a non-EOP buffer. */ static bool -ice_is_non_eop(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) +ice_is_non_eop(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) { /* if we are the last buffer then there is nothing else to do */ #define ICE_RXD_EOF BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S) @@ -1061,11 +1085,12 @@ ice_is_non_eop(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) * * Returns amount of work completed */ -int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) +int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_pkts = 0, frame_sz = 0; u16 cleaned_count = ICE_DESC_UNUSED(rx_ring); unsigned int offset = rx_ring->rx_offset; + struct ice_tx_ring *xdp_ring = NULL; unsigned int xdp_res, xdp_xmit = 0; struct sk_buff *skb = rx_ring->skb; struct bpf_prog *xdp_prog = NULL; @@ -1078,6 +1103,10 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) #endif xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq); + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + if (xdp_prog) + xdp_ring = rx_ring->xdp_ring; + /* start the loop to process Rx packets bounded by 'budget' */ while (likely(total_rx_pkts < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; @@ -1141,11 +1170,10 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) xdp.frame_sz = ice_rx_frame_truesize(rx_ring, size); #endif - xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (!xdp_prog) goto construct_skb; - xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog); + xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog, xdp_ring); if (!xdp_res) goto construct_skb; if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) { @@ -1222,7 +1250,7 @@ construct_skb: failure = ice_alloc_rx_bufs(rx_ring, cleaned_count); if (xdp_prog) - ice_finalize_xdp_rx(rx_ring, xdp_xmit); + ice_finalize_xdp_rx(xdp_ring, xdp_xmit); rx_ring->skb = skb; ice_update_rx_ring_stats(rx_ring, total_rx_pkts, total_rx_bytes); @@ -1248,9 +1276,9 @@ static void ice_net_dim(struct ice_q_vector *q_vector) if (ITR_IS_DYNAMIC(tx)) { struct dim_sample dim_sample = {}; u64 packets = 0, bytes = 0; - struct ice_ring *ring; + struct ice_tx_ring *ring; - ice_for_each_ring(ring, q_vector->tx) { + ice_for_each_tx_ring(ring, q_vector->tx) { packets += ring->stats.pkts; bytes += ring->stats.bytes; } @@ -1264,9 +1292,9 @@ static void ice_net_dim(struct ice_q_vector *q_vector) if (ITR_IS_DYNAMIC(rx)) { struct dim_sample dim_sample = {}; u64 packets = 0, bytes = 0; - struct ice_ring *ring; + struct ice_rx_ring *ring; - ice_for_each_ring(ring, q_vector->rx) { + ice_for_each_rx_ring(ring, q_vector->rx) { packets += ring->stats.pkts; bytes += ring->stats.bytes; } @@ -1388,18 +1416,24 @@ int ice_napi_poll(struct napi_struct *napi, int budget) { struct ice_q_vector *q_vector = container_of(napi, struct ice_q_vector, napi); + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; bool clean_complete = true; - struct ice_ring *ring; int budget_per_ring; int work_done = 0; /* Since the actual Tx work is minimal, we can give the Tx a larger * budget and be more aggressive about cleaning up the Tx descriptors. */ - ice_for_each_ring(ring, q_vector->tx) { - bool wd = ring->xsk_pool ? - ice_clean_tx_irq_zc(ring, budget) : - ice_clean_tx_irq(ring, budget); + ice_for_each_tx_ring(tx_ring, q_vector->tx) { + bool wd; + + if (tx_ring->xsk_pool) + wd = ice_clean_tx_irq_zc(tx_ring, budget); + else if (ice_ring_is_xdp(tx_ring)) + wd = true; + else + wd = ice_clean_tx_irq(tx_ring, budget); if (!wd) clean_complete = false; @@ -1420,16 +1454,16 @@ int ice_napi_poll(struct napi_struct *napi, int budget) /* Max of 1 Rx ring in this q_vector so give it the budget */ budget_per_ring = budget; - ice_for_each_ring(ring, q_vector->rx) { + ice_for_each_rx_ring(rx_ring, q_vector->rx) { int cleaned; /* A dedicated path for zero-copy allows making a single * comparison in the irq context instead of many inside the * ice_clean_rx_irq function and makes the codebase cleaner. */ - cleaned = ring->xsk_pool ? - ice_clean_rx_irq_zc(ring, budget_per_ring) : - ice_clean_rx_irq(ring, budget_per_ring); + cleaned = rx_ring->xsk_pool ? + ice_clean_rx_irq_zc(rx_ring, budget_per_ring) : + ice_clean_rx_irq(rx_ring, budget_per_ring); work_done += cleaned; /* if we clean as many as budgeted, we must not be done */ if (cleaned >= budget_per_ring) @@ -1463,7 +1497,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * * Returns -EBUSY if a stop is needed, else 0 */ -static int __ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size) +static int __ice_maybe_stop_tx(struct ice_tx_ring *tx_ring, unsigned int size) { netif_stop_subqueue(tx_ring->netdev, tx_ring->q_index); /* Memory barrier before checking head and tail */ @@ -1486,7 +1520,7 @@ static int __ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size) * * Returns 0 if stop is not needed */ -static int ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size) +static int ice_maybe_stop_tx(struct ice_tx_ring *tx_ring, unsigned int size) { if (likely(ICE_DESC_UNUSED(tx_ring) >= size)) return 0; @@ -1505,7 +1539,7 @@ static int ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size) * it and the length into the transmit descriptor. */ static void -ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first, +ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first, struct ice_tx_offload_params *off) { u64 td_offset, td_tag, td_cmd; @@ -1841,7 +1875,7 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) * related to VLAN tagging for the HW, such as VLAN, DCB, etc. */ static void -ice_tx_prepare_vlan_flags(struct ice_ring *tx_ring, struct ice_tx_buf *first) +ice_tx_prepare_vlan_flags(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first) { struct sk_buff *skb = first->skb; @@ -2147,7 +2181,7 @@ static bool ice_chk_linearize(struct sk_buff *skb, unsigned int count) * @off: Tx offload parameters */ static void -ice_tstamp(struct ice_ring *tx_ring, struct sk_buff *skb, +ice_tstamp(struct ice_tx_ring *tx_ring, struct sk_buff *skb, struct ice_tx_buf *first, struct ice_tx_offload_params *off) { s8 idx; @@ -2182,7 +2216,7 @@ ice_tstamp(struct ice_ring *tx_ring, struct sk_buff *skb, * Returns NETDEV_TX_OK if sent, else an error code */ static netdev_tx_t -ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) +ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) { struct ice_tx_offload_params offload = { 0 }; struct ice_vsi *vsi = tx_ring->vsi; @@ -2246,6 +2280,8 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) ICE_TXD_CTX_QW1_CMD_S); ice_tstamp(tx_ring, skb, first, &offload); + if (ice_is_switchdev_running(vsi->back)) + ice_eswitch_set_target_vsi(skb, &offload); if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) { struct ice_tx_ctx_desc *cdesc; @@ -2283,7 +2319,7 @@ netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - struct ice_ring *tx_ring; + struct ice_tx_ring *tx_ring; tx_ring = vsi->tx_rings[skb->queue_mapping]; @@ -2333,7 +2369,7 @@ ice_select_queue(struct net_device *netdev, struct sk_buff *skb, * ice_clean_ctrl_tx_irq - interrupt handler for flow director Tx queue * @tx_ring: tx_ring to clean */ -void ice_clean_ctrl_tx_irq(struct ice_ring *tx_ring) +void ice_clean_ctrl_tx_irq(struct ice_tx_ring *tx_ring) { struct ice_vsi *vsi = tx_ring->vsi; s16 i = tx_ring->next_to_clean; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index cce348c83da8..c759a02bfce4 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -13,6 +13,7 @@ #define ICE_MAX_CHAINED_RX_BUFS 5 #define ICE_MAX_BUF_TXD 8 #define ICE_MIN_TX_LEN 17 +#define ICE_TX_THRESH 32 /* The size limit for a transmit buffer in a descriptor is (16K - 1). * In order to align with the read requests we will align the value to @@ -154,7 +155,7 @@ struct ice_tx_buf { struct ice_tx_offload_params { u64 cd_qw1; - struct ice_ring *tx_ring; + struct ice_tx_ring *tx_ring; u32 td_cmd; u32 td_offset; u32 td_l2tag1; @@ -251,9 +252,9 @@ enum ice_dynamic_itr { #define ICE_TX_LEGACY 1 /* descriptor ring, associated with a VSI */ -struct ice_ring { +struct ice_rx_ring { /* CL1 - 1st cacheline starts here */ - struct ice_ring *next; /* pointer to next ring in q_vector */ + struct ice_rx_ring *next; /* pointer to next ring in q_vector */ void *desc; /* Descriptor ring memory */ struct device *dev; /* Used for DMA mapping */ struct net_device *netdev; /* netdev ring maps to */ @@ -261,15 +262,13 @@ struct ice_ring { struct ice_q_vector *q_vector; /* Backreference to associated vector */ u8 __iomem *tail; union { - struct ice_tx_buf *tx_buf; struct ice_rx_buf *rx_buf; struct xdp_buff **xdp_buf; }; /* CL2 - 2nd cacheline starts here */ + struct xdp_rxq_info xdp_rxq; + /* CL3 - 3rd cacheline starts here */ u16 q_index; /* Queue number of ring */ - u16 q_handle; /* Queue handle per TC */ - - u8 ring_active:1; /* is ring online or not */ u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ @@ -278,63 +277,97 @@ struct ice_ring { u16 next_to_use; u16 next_to_clean; u16 next_to_alloc; + u16 rx_offset; + u16 rx_buf_len; /* stats structs */ + struct ice_rxq_stats rx_stats; struct ice_q_stats stats; struct u64_stats_sync syncp; - union { - struct ice_txq_stats tx_stats; - struct ice_rxq_stats rx_stats; - }; struct rcu_head rcu; /* to avoid race on free */ - DECLARE_BITMAP(xps_state, ICE_TX_NBITS); /* XPS Config State */ + /* CL4 - 3rd cacheline starts here */ struct bpf_prog *xdp_prog; + struct ice_tx_ring *xdp_ring; struct xsk_buff_pool *xsk_pool; - u16 rx_offset; - /* CL3 - 3rd cacheline starts here */ - struct xdp_rxq_info xdp_rxq; struct sk_buff *skb; - /* CLX - the below items are only accessed infrequently and should be - * in their own cache line if possible - */ -#define ICE_TX_FLAGS_RING_XDP BIT(0) + dma_addr_t dma; /* physical address of ring */ #define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) + u64 cached_phctime; + u8 dcb_tc; /* Traffic class of ring */ + u8 ptp_rx; u8 flags; +} ____cacheline_internodealigned_in_smp; + +struct ice_tx_ring { + /* CL1 - 1st cacheline starts here */ + struct ice_tx_ring *next; /* pointer to next ring in q_vector */ + void *desc; /* Descriptor ring memory */ + struct device *dev; /* Used for DMA mapping */ + u8 __iomem *tail; + struct ice_tx_buf *tx_buf; + struct ice_q_vector *q_vector; /* Backreference to associated vector */ + struct net_device *netdev; /* netdev ring maps to */ + struct ice_vsi *vsi; /* Backreference to associated VSI */ + /* CL2 - 2nd cacheline starts here */ dma_addr_t dma; /* physical address of ring */ - unsigned int size; /* length of descriptor ring in bytes */ + struct xsk_buff_pool *xsk_pool; + u16 next_to_use; + u16 next_to_clean; + u16 next_rs; + u16 next_dd; + u16 q_handle; /* Queue handle per TC */ + u16 reg_idx; /* HW register index of the ring */ + u16 count; /* Number of descriptors */ + u16 q_index; /* Queue number of ring */ + /* stats structs */ + struct ice_q_stats stats; + struct u64_stats_sync syncp; + struct ice_txq_stats tx_stats; + + /* CL3 - 3rd cacheline starts here */ + struct rcu_head rcu; /* to avoid race on free */ + DECLARE_BITMAP(xps_state, ICE_TX_NBITS); /* XPS Config State */ + struct ice_ptp_tx *tx_tstamps; + spinlock_t tx_lock; u32 txq_teid; /* Added Tx queue TEID */ - u16 rx_buf_len; +#define ICE_TX_FLAGS_RING_XDP BIT(0) + u8 flags; u8 dcb_tc; /* Traffic class of ring */ - struct ice_ptp_tx *tx_tstamps; - u64 cached_phctime; - u8 ptp_rx:1; - u8 ptp_tx:1; + u8 ptp_tx; } ____cacheline_internodealigned_in_smp; -static inline bool ice_ring_uses_build_skb(struct ice_ring *ring) +static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring) { return !!(ring->flags & ICE_RX_FLAGS_RING_BUILD_SKB); } -static inline void ice_set_ring_build_skb_ena(struct ice_ring *ring) +static inline void ice_set_ring_build_skb_ena(struct ice_rx_ring *ring) { ring->flags |= ICE_RX_FLAGS_RING_BUILD_SKB; } -static inline void ice_clear_ring_build_skb_ena(struct ice_ring *ring) +static inline void ice_clear_ring_build_skb_ena(struct ice_rx_ring *ring) { ring->flags &= ~ICE_RX_FLAGS_RING_BUILD_SKB; } -static inline bool ice_ring_is_xdp(struct ice_ring *ring) +static inline bool ice_ring_is_xdp(struct ice_tx_ring *ring) { return !!(ring->flags & ICE_TX_FLAGS_RING_XDP); } +enum ice_container_type { + ICE_RX_CONTAINER, + ICE_TX_CONTAINER, +}; + struct ice_ring_container { /* head of linked-list of rings */ - struct ice_ring *ring; + union { + struct ice_rx_ring *rx_ring; + struct ice_tx_ring *tx_ring; + }; struct dim dim; /* data for net_dim algorithm */ u16 itr_idx; /* index in the interrupt vector */ /* this matches the maximum number of ITR bits, but in usec @@ -343,6 +376,7 @@ struct ice_ring_container { u16 itr_setting:13; u16 itr_reserved:2; u16 itr_mode:1; + enum ice_container_type type; }; struct ice_coalesce_stored { @@ -354,10 +388,13 @@ struct ice_coalesce_stored { }; /* iterator for handling rings in ring container */ -#define ice_for_each_ring(pos, head) \ - for (pos = (head).ring; pos; pos = pos->next) +#define ice_for_each_rx_ring(pos, head) \ + for (pos = (head).rx_ring; pos; pos = pos->next) + +#define ice_for_each_tx_ring(pos, head) \ + for (pos = (head).tx_ring; pos; pos = pos->next) -static inline unsigned int ice_rx_pg_order(struct ice_ring *ring) +static inline unsigned int ice_rx_pg_order(struct ice_rx_ring *ring) { #if (PAGE_SIZE < 8192) if (ring->rx_buf_len > (PAGE_SIZE / 2)) @@ -370,21 +407,21 @@ static inline unsigned int ice_rx_pg_order(struct ice_ring *ring) union ice_32b_rx_flex_desc; -bool ice_alloc_rx_bufs(struct ice_ring *rxr, u16 cleaned_count); +bool ice_alloc_rx_bufs(struct ice_rx_ring *rxr, u16 cleaned_count); netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev); u16 ice_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); -void ice_clean_tx_ring(struct ice_ring *tx_ring); -void ice_clean_rx_ring(struct ice_ring *rx_ring); -int ice_setup_tx_ring(struct ice_ring *tx_ring); -int ice_setup_rx_ring(struct ice_ring *rx_ring); -void ice_free_tx_ring(struct ice_ring *tx_ring); -void ice_free_rx_ring(struct ice_ring *rx_ring); +void ice_clean_tx_ring(struct ice_tx_ring *tx_ring); +void ice_clean_rx_ring(struct ice_rx_ring *rx_ring); +int ice_setup_tx_ring(struct ice_tx_ring *tx_ring); +int ice_setup_rx_ring(struct ice_rx_ring *rx_ring); +void ice_free_tx_ring(struct ice_tx_ring *tx_ring); +void ice_free_rx_ring(struct ice_rx_ring *rx_ring); int ice_napi_poll(struct napi_struct *napi, int budget); int ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc, u8 *raw_packet); -int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget); -void ice_clean_ctrl_tx_irq(struct ice_ring *tx_ring); +int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget); +void ice_clean_ctrl_tx_irq(struct ice_tx_ring *tx_ring); #endif /* _ICE_TXRX_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 171397dcf00a..1dd7e84f41f8 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -2,13 +2,15 @@ /* Copyright (c) 2019, Intel Corporation. */ #include "ice_txrx_lib.h" +#include "ice_eswitch.h" +#include "ice_lib.h" /** * ice_release_rx_desc - Store the new tail and head values * @rx_ring: ring to bump * @val: new head index */ -void ice_release_rx_desc(struct ice_ring *rx_ring, u16 val) +void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val) { u16 prev_ntu = rx_ring->next_to_use & ~0x7; @@ -66,7 +68,7 @@ static enum pkt_hash_types ice_ptype_to_htype(u16 ptype) * @rx_ptype: the ptype value from the descriptor */ static void -ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, +ice_rx_hash(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb, u16 rx_ptype) { struct ice_32b_rx_flex_desc_nic *nic_mdid; @@ -93,7 +95,7 @@ ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, * skb->protocol must be set before this function is called */ static void -ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb, +ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb, union ice_32b_rx_flex_desc *rx_desc, u16 ptype) { struct ice_rx_ptype_decoded decoded; @@ -178,14 +180,15 @@ checksum_fail: * other fields within the skb. */ void -ice_process_skb_fields(struct ice_ring *rx_ring, +ice_process_skb_fields(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb, u16 ptype) { ice_rx_hash(rx_ring, rx_desc, skb, ptype); /* modifies the skb - consumes the enet header */ - skb->protocol = eth_type_trans(skb, rx_ring->netdev); + skb->protocol = eth_type_trans(skb, ice_eswitch_get_target_netdev + (rx_ring, rx_desc)); ice_rx_csum(rx_ring, skb, rx_desc, ptype); @@ -203,7 +206,7 @@ ice_process_skb_fields(struct ice_ring *rx_ring, * gro receive functions (with/without VLAN tag) */ void -ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) +ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) { if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && (vlan_tag & VLAN_VID_MASK)) @@ -212,18 +215,67 @@ ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) } /** + * ice_clean_xdp_irq - Reclaim resources after transmit completes on XDP ring + * @xdp_ring: XDP ring to clean + */ +static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) +{ + unsigned int total_bytes = 0, total_pkts = 0; + u16 ntc = xdp_ring->next_to_clean; + struct ice_tx_desc *next_dd_desc; + u16 next_dd = xdp_ring->next_dd; + struct ice_tx_buf *tx_buf; + int i; + + next_dd_desc = ICE_TX_DESC(xdp_ring, next_dd); + if (!(next_dd_desc->cmd_type_offset_bsz & + cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) + return; + + for (i = 0; i < ICE_TX_THRESH; i++) { + tx_buf = &xdp_ring->tx_buf[ntc]; + + total_bytes += tx_buf->bytecount; + /* normally tx_buf->gso_segs was taken but at this point + * it's always 1 for us + */ + total_pkts++; + + page_frag_free(tx_buf->raw_buf); + dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); + dma_unmap_len_set(tx_buf, len, 0); + tx_buf->raw_buf = NULL; + + ntc++; + if (ntc >= xdp_ring->count) + ntc = 0; + } + + next_dd_desc->cmd_type_offset_bsz = 0; + xdp_ring->next_dd = xdp_ring->next_dd + ICE_TX_THRESH; + if (xdp_ring->next_dd > xdp_ring->count) + xdp_ring->next_dd = ICE_TX_THRESH - 1; + xdp_ring->next_to_clean = ntc; + ice_update_tx_ring_stats(xdp_ring, total_pkts, total_bytes); +} + +/** * ice_xmit_xdp_ring - submit single packet to XDP ring for transmission * @data: packet data pointer * @size: packet data size * @xdp_ring: XDP ring for transmission */ -int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring) +int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring) { u16 i = xdp_ring->next_to_use; struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; dma_addr_t dma; + if (ICE_DESC_UNUSED(xdp_ring) < ICE_TX_THRESH) + ice_clean_xdp_irq(xdp_ring); + if (!unlikely(ICE_DESC_UNUSED(xdp_ring))) { xdp_ring->tx_stats.tx_busy++; return ICE_XDP_CONSUMED; @@ -244,21 +296,26 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring) tx_desc = ICE_TX_DESC(xdp_ring, i); tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TXD_LAST_DESC_CMD, 0, + tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, 0, size, 0); - /* Make certain all of the status bits have been updated - * before next_to_watch is written. - */ - smp_wmb(); - i++; - if (i == xdp_ring->count) + if (i == xdp_ring->count) { i = 0; - - tx_buf->next_to_watch = tx_desc; + tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); + xdp_ring->next_rs = ICE_TX_THRESH - 1; + } xdp_ring->next_to_use = i; + if (i > xdp_ring->next_rs) { + tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); + xdp_ring->next_rs += ICE_TX_THRESH; + } + return ICE_XDP_TX; } @@ -269,7 +326,7 @@ int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring) * * Returns negative on failure, 0 on success. */ -int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_ring *xdp_ring) +int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring) { struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); @@ -281,22 +338,23 @@ int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_ring *xdp_ring) /** * ice_finalize_xdp_rx - Bump XDP Tx tail and/or flush redirect map - * @rx_ring: Rx ring + * @xdp_ring: XDP ring * @xdp_res: Result of the receive batch * * This function bumps XDP Tx tail and/or flush redirect map, and * should be called when a batch of packets has been processed in the * napi loop. */ -void ice_finalize_xdp_rx(struct ice_ring *rx_ring, unsigned int xdp_res) +void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res) { if (xdp_res & ICE_XDP_REDIR) xdp_do_flush_map(); if (xdp_res & ICE_XDP_TX) { - struct ice_ring *xdp_ring = - rx_ring->vsi->xdp_rings[rx_ring->q_index]; - + if (static_branch_unlikely(&ice_xdp_locking_key)) + spin_lock(&xdp_ring->tx_lock); ice_xdp_ring_update_tail(xdp_ring); + if (static_branch_unlikely(&ice_xdp_locking_key)) + spin_unlock(&xdp_ring->tx_lock); } } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 05ac30752902..11b6c1601986 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -37,7 +37,7 @@ ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag) * * This function updates the XDP Tx ring tail register. */ -static inline void ice_xdp_ring_update_tail(struct ice_ring *xdp_ring) +static inline void ice_xdp_ring_update_tail(struct ice_tx_ring *xdp_ring) { /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. @@ -46,14 +46,14 @@ static inline void ice_xdp_ring_update_tail(struct ice_ring *xdp_ring) writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail); } -void ice_finalize_xdp_rx(struct ice_ring *rx_ring, unsigned int xdp_res); -int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_ring *xdp_ring); -int ice_xmit_xdp_ring(void *data, u16 size, struct ice_ring *xdp_ring); -void ice_release_rx_desc(struct ice_ring *rx_ring, u16 val); +void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res); +int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring); +int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring); +void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val); void -ice_process_skb_fields(struct ice_ring *rx_ring, +ice_process_skb_fields(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb, u16 ptype); void -ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag); +ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag); #endif /* !_ICE_TXRX_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 6705f56be020..d5cb1c5a89c0 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -139,6 +139,7 @@ enum ice_vsi_type { ICE_VSI_VF = 1, ICE_VSI_CTRL = 3, /* equates to ICE_VSI_PF with 1 queue pair */ ICE_VSI_LB = 6, + ICE_VSI_SWITCHDEV_CTRL = 7, }; struct ice_link_status { @@ -676,6 +677,10 @@ struct ice_port_info { struct ice_switch_info { struct list_head vsi_list_map_head; struct ice_sw_recipe *recp_list; + u16 prof_res_bm_init; + u16 max_used_prof_index; + + DECLARE_BITMAP(prof_res_bm[ICE_MAX_NUM_PROFILES], ICE_MAX_FV_WORDS); }; /* FW logging configuration */ @@ -911,6 +916,7 @@ struct ice_hw { struct mutex rss_locks; /* protect RSS configuration */ struct list_head rss_list_head; struct ice_mbx_snapshot mbx_snapshot; + u16 io_expander_handle; }; /* Statistics collected by each port, VSI, VEB, and S-channel */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index e93430ab37f1..d90a3b7be713 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -6,6 +6,7 @@ #include "ice_lib.h" #include "ice_fltr.h" #include "ice_flow.h" +#include "ice_eswitch.h" #include "ice_virtchnl_allowlist.h" #define FIELD_SELECTOR(proto_hdr_field) \ @@ -251,7 +252,7 @@ ice_vc_hash_field_match_type ice_vc_hash_field_list_comms[] = { * ice_get_vf_vsi - get VF's VSI based on the stored index * @vf: VF used to get VSI */ -static struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf) +struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf) { return vf->pf->vsi[vf->lan_vsi_idx]; } @@ -412,7 +413,7 @@ static bool ice_is_vf_link_up(struct ice_vf *vf) * * send a link status message to a single VF */ -static void ice_vc_notify_vf_link_state(struct ice_vf *vf) +void ice_vc_notify_vf_link_state(struct ice_vf *vf) { struct virtchnl_pf_event pfe = { 0 }; struct ice_hw *hw = &vf->pf->hw; @@ -620,6 +621,8 @@ void ice_free_vfs(struct ice_pf *pf) if (!pf->vf) return; + ice_eswitch_release(pf); + while (test_and_set_bit(ICE_VF_DIS, pf->state)) usleep_range(1000, 2000); @@ -932,6 +935,9 @@ static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) enum ice_status status; u8 broadcast[ETH_ALEN]; + if (ice_is_eswitch_mode_switchdev(vf->pf)) + return 0; + eth_broadcast_addr(broadcast); status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); if (status) { @@ -1581,6 +1587,10 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) ice_vf_post_vsi_rebuild(vf); } + if (ice_is_eswitch_mode_switchdev(pf)) + if (ice_eswitch_rebuild(pf)) + dev_warn(dev, "eswitch rebuild failed\n"); + ice_flush(hw); clear_bit(ICE_VF_DIS, pf->state); @@ -1593,7 +1603,7 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) * * Returns true if the PF or VF is disabled, false otherwise. */ -static bool ice_is_vf_disabled(struct ice_vf *vf) +bool ice_is_vf_disabled(struct ice_vf *vf) { struct ice_pf *pf = vf->pf; @@ -1711,6 +1721,8 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) } ice_vf_post_vsi_rebuild(vf); + vsi = ice_get_vf_vsi(vf); + ice_eswitch_update_repr(vsi); /* if the VF has been reset allow it to come up again */ if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->malvfs, ICE_MAX_VF_COUNT, vf->vf_id)) @@ -1894,6 +1906,8 @@ static void ice_set_dflt_settings_vfs(struct ice_pf *pf) */ ice_vf_ctrl_invalidate_vsi(vf); ice_vf_fdir_init(vf); + + ice_vc_set_dflt_vf_ops(&vf->vc_ops); } } @@ -1960,6 +1974,10 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) } clear_bit(ICE_VF_DIS, pf->state); + + if (ice_eswitch_configure(pf)) + goto err_unroll_sriov; + return 0; err_unroll_sriov: @@ -2823,7 +2841,7 @@ static void ice_wait_on_vf_reset(struct ice_vf *vf) * disabled, and initialized so it can be configured and/or queried by a host * administrator. */ -static int ice_check_vf_ready_for_cfg(struct ice_vf *vf) +int ice_check_vf_ready_for_cfg(struct ice_vf *vf) { struct ice_pf *pf; @@ -3329,7 +3347,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - struct ice_ring *ring = vsi->tx_rings[vf_q_id]; + struct ice_tx_ring *ring = vsi->tx_rings[vf_q_id]; struct ice_txq_meta txq_meta = { 0 }; if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { @@ -3802,6 +3820,26 @@ static bool ice_is_legacy_umac_expired(struct ice_time_mac *last_added_umac) } /** + * ice_update_legacy_cached_mac - update cached hardware MAC for legacy VF + * @vf: VF to update + * @vc_ether_addr: structure from VIRTCHNL with MAC to check + * + * only update cached hardware MAC for legacy VF drivers on delete + * because we cannot guarantee order/type of MAC from the VF driver + */ +static void +ice_update_legacy_cached_mac(struct ice_vf *vf, + struct virtchnl_ether_addr *vc_ether_addr) +{ + if (!ice_is_vc_addr_legacy(vc_ether_addr) || + ice_is_legacy_umac_expired(&vf->legacy_last_added_umac)) + return; + + ether_addr_copy(vf->dev_lan_addr.addr, vf->legacy_last_added_umac.addr); + ether_addr_copy(vf->hw_lan_addr.addr, vf->legacy_last_added_umac.addr); +} + +/** * ice_vfhw_mac_del - update the VF's cached hardware MAC if allowed * @vf: VF to update * @vc_ether_addr: structure from VIRTCHNL with MAC to delete @@ -3822,16 +3860,7 @@ ice_vfhw_mac_del(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) */ eth_zero_addr(vf->dev_lan_addr.addr); - /* only update cached hardware MAC for legacy VF drivers on delete - * because we cannot guarantee order/type of MAC from the VF driver - */ - if (ice_is_vc_addr_legacy(vc_ether_addr) && - !ice_is_legacy_umac_expired(&vf->legacy_last_added_umac)) { - ether_addr_copy(vf->dev_lan_addr.addr, - vf->legacy_last_added_umac.addr); - ether_addr_copy(vf->hw_lan_addr.addr, - vf->legacy_last_added_umac.addr); - } + ice_update_legacy_cached_mac(vf, vc_ether_addr); } /** @@ -4400,6 +4429,133 @@ static int ice_vf_init_vlan_stripping(struct ice_vf *vf) return ice_vsi_manage_vlan_stripping(vsi, false); } +static struct ice_vc_vf_ops ice_vc_vf_dflt_ops = { + .get_ver_msg = ice_vc_get_ver_msg, + .get_vf_res_msg = ice_vc_get_vf_res_msg, + .reset_vf = ice_vc_reset_vf_msg, + .add_mac_addr_msg = ice_vc_add_mac_addr_msg, + .del_mac_addr_msg = ice_vc_del_mac_addr_msg, + .cfg_qs_msg = ice_vc_cfg_qs_msg, + .ena_qs_msg = ice_vc_ena_qs_msg, + .dis_qs_msg = ice_vc_dis_qs_msg, + .request_qs_msg = ice_vc_request_qs_msg, + .cfg_irq_map_msg = ice_vc_cfg_irq_map_msg, + .config_rss_key = ice_vc_config_rss_key, + .config_rss_lut = ice_vc_config_rss_lut, + .get_stats_msg = ice_vc_get_stats_msg, + .cfg_promiscuous_mode_msg = ice_vc_cfg_promiscuous_mode_msg, + .add_vlan_msg = ice_vc_add_vlan_msg, + .remove_vlan_msg = ice_vc_remove_vlan_msg, + .ena_vlan_stripping = ice_vc_ena_vlan_stripping, + .dis_vlan_stripping = ice_vc_dis_vlan_stripping, + .handle_rss_cfg_msg = ice_vc_handle_rss_cfg, + .add_fdir_fltr_msg = ice_vc_add_fdir_fltr, + .del_fdir_fltr_msg = ice_vc_del_fdir_fltr, +}; + +void ice_vc_set_dflt_vf_ops(struct ice_vc_vf_ops *ops) +{ + *ops = ice_vc_vf_dflt_ops; +} + +static int +ice_vc_repr_no_action_msg(struct ice_vf __always_unused *vf, + u8 __always_unused *msg) +{ + return 0; +} + +/** + * ice_vc_repr_add_mac + * @vf: pointer to VF + * @msg: virtchannel message + * + * When port representors are created, we do not add MAC rule + * to firmware, we store it so that PF could report same + * MAC as VF. + */ +static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_ether_addr_list *al = + (struct virtchnl_ether_addr_list *)msg; + struct ice_vsi *vsi; + struct ice_pf *pf; + int i; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) || + !ice_vc_isvalid_vsi_id(vf, al->vsi_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto handle_mac_exit; + } + + pf = vf->pf; + + vsi = ice_get_vf_vsi(vf); + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto handle_mac_exit; + } + + for (i = 0; i < al->num_elements; i++) { + u8 *mac_addr = al->list[i].addr; + + if (!is_unicast_ether_addr(mac_addr) || + ether_addr_equal(mac_addr, vf->hw_lan_addr.addr)) + continue; + + if (vf->pf_set_mac) { + dev_err(ice_pf_to_dev(pf), "VF attempting to override administratively set MAC address\n"); + v_ret = VIRTCHNL_STATUS_ERR_NOT_SUPPORTED; + goto handle_mac_exit; + } + + ice_vfhw_mac_add(vf, &al->list[i]); + vf->num_mac++; + break; + } + +handle_mac_exit: + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_ETH_ADDR, + v_ret, NULL, 0); +} + +/** + * ice_vc_repr_del_mac - response with success for deleting MAC + * @vf: pointer to VF + * @msg: virtchannel message + * + * Respond with success to not break normal VF flow. + * For legacy VF driver try to update cached MAC address. + */ +static int +ice_vc_repr_del_mac(struct ice_vf __always_unused *vf, u8 __always_unused *msg) +{ + struct virtchnl_ether_addr_list *al = + (struct virtchnl_ether_addr_list *)msg; + + ice_update_legacy_cached_mac(vf, &al->list[0]); + + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, + VIRTCHNL_STATUS_SUCCESS, NULL, 0); +} + +static int ice_vc_repr_no_action(struct ice_vf __always_unused *vf) +{ + return 0; +} + +void ice_vc_change_ops_to_repr(struct ice_vc_vf_ops *ops) +{ + ops->add_mac_addr_msg = ice_vc_repr_add_mac; + ops->del_mac_addr_msg = ice_vc_repr_del_mac; + ops->add_vlan_msg = ice_vc_repr_no_action_msg; + ops->remove_vlan_msg = ice_vc_repr_no_action_msg; + ops->ena_vlan_stripping = ice_vc_repr_no_action; + ops->dis_vlan_stripping = ice_vc_repr_no_action; + ops->cfg_promiscuous_mode_msg = ice_vc_repr_no_action_msg; +} + /** * ice_vc_process_vf_msg - Process request from VF * @pf: pointer to the PF structure @@ -4413,6 +4569,7 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) u32 v_opcode = le32_to_cpu(event->desc.cookie_high); s16 vf_id = le16_to_cpu(event->desc.retval); u16 msglen = event->msg_len; + struct ice_vc_vf_ops *ops; u8 *msg = event->msg_buf; struct ice_vf *vf = NULL; struct device *dev; @@ -4436,6 +4593,8 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) goto error_handler; } + ops = &vf->vc_ops; + /* Perform basic checks on the msg */ err = virtchnl_vc_validate_vf_msg(&vf->vf_ver, v_opcode, msg, msglen); if (err) { @@ -4463,75 +4622,75 @@ error_handler: switch (v_opcode) { case VIRTCHNL_OP_VERSION: - err = ice_vc_get_ver_msg(vf, msg); + err = ops->get_ver_msg(vf, msg); break; case VIRTCHNL_OP_GET_VF_RESOURCES: - err = ice_vc_get_vf_res_msg(vf, msg); + err = ops->get_vf_res_msg(vf, msg); if (ice_vf_init_vlan_stripping(vf)) dev_err(dev, "Failed to initialize VLAN stripping for VF %d\n", vf->vf_id); ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: - ice_vc_reset_vf_msg(vf); + ops->reset_vf(vf); break; case VIRTCHNL_OP_ADD_ETH_ADDR: - err = ice_vc_add_mac_addr_msg(vf, msg); + err = ops->add_mac_addr_msg(vf, msg); break; case VIRTCHNL_OP_DEL_ETH_ADDR: - err = ice_vc_del_mac_addr_msg(vf, msg); + err = ops->del_mac_addr_msg(vf, msg); break; case VIRTCHNL_OP_CONFIG_VSI_QUEUES: - err = ice_vc_cfg_qs_msg(vf, msg); + err = ops->cfg_qs_msg(vf, msg); break; case VIRTCHNL_OP_ENABLE_QUEUES: - err = ice_vc_ena_qs_msg(vf, msg); + err = ops->ena_qs_msg(vf, msg); ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_DISABLE_QUEUES: - err = ice_vc_dis_qs_msg(vf, msg); + err = ops->dis_qs_msg(vf, msg); break; case VIRTCHNL_OP_REQUEST_QUEUES: - err = ice_vc_request_qs_msg(vf, msg); + err = ops->request_qs_msg(vf, msg); break; case VIRTCHNL_OP_CONFIG_IRQ_MAP: - err = ice_vc_cfg_irq_map_msg(vf, msg); + err = ops->cfg_irq_map_msg(vf, msg); break; case VIRTCHNL_OP_CONFIG_RSS_KEY: - err = ice_vc_config_rss_key(vf, msg); + err = ops->config_rss_key(vf, msg); break; case VIRTCHNL_OP_CONFIG_RSS_LUT: - err = ice_vc_config_rss_lut(vf, msg); + err = ops->config_rss_lut(vf, msg); break; case VIRTCHNL_OP_GET_STATS: - err = ice_vc_get_stats_msg(vf, msg); + err = ops->get_stats_msg(vf, msg); break; case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE: - err = ice_vc_cfg_promiscuous_mode_msg(vf, msg); + err = ops->cfg_promiscuous_mode_msg(vf, msg); break; case VIRTCHNL_OP_ADD_VLAN: - err = ice_vc_add_vlan_msg(vf, msg); + err = ops->add_vlan_msg(vf, msg); break; case VIRTCHNL_OP_DEL_VLAN: - err = ice_vc_remove_vlan_msg(vf, msg); + err = ops->remove_vlan_msg(vf, msg); break; case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: - err = ice_vc_ena_vlan_stripping(vf); + err = ops->ena_vlan_stripping(vf); break; case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: - err = ice_vc_dis_vlan_stripping(vf); + err = ops->dis_vlan_stripping(vf); break; case VIRTCHNL_OP_ADD_FDIR_FILTER: - err = ice_vc_add_fdir_fltr(vf, msg); + err = ops->add_fdir_fltr_msg(vf, msg); break; case VIRTCHNL_OP_DEL_FDIR_FILTER: - err = ice_vc_del_fdir_fltr(vf, msg); + err = ops->del_fdir_fltr_msg(vf, msg); break; case VIRTCHNL_OP_ADD_RSS_CFG: - err = ice_vc_handle_rss_cfg(vf, msg, true); + err = ops->handle_rss_cfg_msg(vf, msg, true); break; case VIRTCHNL_OP_DEL_RSS_CFG: - err = ice_vc_handle_rss_cfg(vf, msg, false); + err = ops->handle_rss_cfg_msg(vf, msg, false); break; case VIRTCHNL_OP_UNKNOWN: default: @@ -4640,6 +4799,11 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) struct ice_vf *vf; int ret; + if (ice_is_eswitch_mode_switchdev(pf)) { + dev_info(ice_pf_to_dev(pf), "Trusted VF is forbidden in switchdev mode\n"); + return -EOPNOTSUPP; + } + if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 842cb077df86..3115284e5411 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -70,6 +70,32 @@ struct ice_mdd_vf_events { u16 last_printed; }; +struct ice_vf; + +struct ice_vc_vf_ops { + int (*get_ver_msg)(struct ice_vf *vf, u8 *msg); + int (*get_vf_res_msg)(struct ice_vf *vf, u8 *msg); + void (*reset_vf)(struct ice_vf *vf); + int (*add_mac_addr_msg)(struct ice_vf *vf, u8 *msg); + int (*del_mac_addr_msg)(struct ice_vf *vf, u8 *msg); + int (*cfg_qs_msg)(struct ice_vf *vf, u8 *msg); + int (*ena_qs_msg)(struct ice_vf *vf, u8 *msg); + int (*dis_qs_msg)(struct ice_vf *vf, u8 *msg); + int (*request_qs_msg)(struct ice_vf *vf, u8 *msg); + int (*cfg_irq_map_msg)(struct ice_vf *vf, u8 *msg); + int (*config_rss_key)(struct ice_vf *vf, u8 *msg); + int (*config_rss_lut)(struct ice_vf *vf, u8 *msg); + int (*get_stats_msg)(struct ice_vf *vf, u8 *msg); + int (*cfg_promiscuous_mode_msg)(struct ice_vf *vf, u8 *msg); + int (*add_vlan_msg)(struct ice_vf *vf, u8 *msg); + int (*remove_vlan_msg)(struct ice_vf *vf, u8 *msg); + int (*ena_vlan_stripping)(struct ice_vf *vf); + int (*dis_vlan_stripping)(struct ice_vf *vf); + int (*handle_rss_cfg_msg)(struct ice_vf *vf, u8 *msg, bool add); + int (*add_fdir_fltr_msg)(struct ice_vf *vf, u8 *msg); + int (*del_fdir_fltr_msg)(struct ice_vf *vf, u8 *msg); +}; + /* VF information structure */ struct ice_vf { struct ice_pf *pf; @@ -111,9 +137,17 @@ struct ice_vf { struct ice_mdd_vf_events mdd_rx_events; struct ice_mdd_vf_events mdd_tx_events; DECLARE_BITMAP(opcodes_allowlist, VIRTCHNL_OP_MAX); + + struct ice_repr *repr; + + struct ice_vc_vf_ops vc_ops; + + /* devlink port data */ + struct devlink_port devlink_port; }; #ifdef CONFIG_PCI_IOV +struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); void ice_process_vflr_event(struct ice_pf *pf); int ice_sriov_configure(struct pci_dev *pdev, int num_vfs); int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac); @@ -124,6 +158,9 @@ void ice_free_vfs(struct ice_pf *pf); void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event); void ice_vc_notify_link_state(struct ice_pf *pf); void ice_vc_notify_reset(struct ice_pf *pf); +void ice_vc_notify_vf_link_state(struct ice_vf *vf); +void ice_vc_change_ops_to_repr(struct ice_vc_vf_ops *ops); +void ice_vc_set_dflt_vf_ops(struct ice_vc_vf_ops *ops); bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr); bool ice_reset_vf(struct ice_vf *vf, bool is_vflr); void ice_restore_all_vfs_msi_state(struct pci_dev *pdev); @@ -139,6 +176,10 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted); int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state); +int ice_check_vf_ready_for_cfg(struct ice_vf *vf); + +bool ice_is_vf_disabled(struct ice_vf *vf); + int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena); int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector); @@ -164,6 +205,9 @@ static inline void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) { } static inline void ice_vc_notify_link_state(struct ice_pf *pf) { } static inline void ice_vc_notify_reset(struct ice_pf *pf) { } +static inline void ice_vc_notify_vf_link_state(struct ice_vf *vf) { } +static inline void ice_vc_change_ops_to_repr(struct ice_vc_vf_ops *ops) { } +static inline void ice_vc_set_dflt_vf_ops(struct ice_vc_vf_ops *ops) { } static inline void ice_set_vf_state_qs_dis(struct ice_vf *vf) { } static inline void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) { } @@ -171,6 +215,21 @@ static inline void ice_print_vfs_mdd_events(struct ice_pf *pf) { } static inline void ice_print_vf_rx_mdd_event(struct ice_vf *vf) { } static inline void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) { } +static inline int ice_check_vf_ready_for_cfg(struct ice_vf *vf) +{ + return -EOPNOTSUPP; +} + +static inline bool ice_is_vf_disabled(struct ice_vf *vf) +{ + return true; +} + +static inline struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf) +{ + return NULL; +} + static inline bool ice_is_malicious_vf(struct ice_pf __always_unused *pf, struct ice_rq_event_info __always_unused *event, diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 7682eaa9a9ec..d9dfcfc2c6f9 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -67,7 +67,7 @@ ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector, * @q_vector: queue vector */ static void -ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_ring *rx_ring, +ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring, struct ice_q_vector *q_vector) { struct ice_pf *pf = vsi->back; @@ -104,16 +104,17 @@ ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector) u16 reg_idx = q_vector->reg_idx; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - struct ice_ring *ring; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; ice_cfg_itr(hw, q_vector); - ice_for_each_ring(ring, q_vector->tx) - ice_cfg_txq_interrupt(vsi, ring->reg_idx, reg_idx, + ice_for_each_tx_ring(tx_ring, q_vector->tx) + ice_cfg_txq_interrupt(vsi, tx_ring->reg_idx, reg_idx, q_vector->tx.itr_idx); - ice_for_each_ring(ring, q_vector->rx) - ice_cfg_rxq_interrupt(vsi, ring->reg_idx, reg_idx, + ice_for_each_rx_ring(rx_ring, q_vector->rx) + ice_cfg_rxq_interrupt(vsi, rx_ring->reg_idx, reg_idx, q_vector->rx.itr_idx); ice_flush(hw); @@ -144,8 +145,9 @@ static void ice_qvec_ena_irq(struct ice_vsi *vsi, struct ice_q_vector *q_vector) static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) { struct ice_txq_meta txq_meta = { }; - struct ice_ring *tx_ring, *rx_ring; struct ice_q_vector *q_vector; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; int timeout = 50; int err; @@ -171,7 +173,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; if (ice_is_xdp_ena_vsi(vsi)) { - struct ice_ring *xdp_ring = vsi->xdp_rings[q_idx]; + struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; memset(&txq_meta, 0, sizeof(txq_meta)); ice_fill_txq_meta(vsi, xdp_ring, &txq_meta); @@ -201,8 +203,9 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) { struct ice_aqc_add_tx_qgrp *qg_buf; - struct ice_ring *tx_ring, *rx_ring; struct ice_q_vector *q_vector; + struct ice_tx_ring *tx_ring; + struct ice_rx_ring *rx_ring; u16 size; int err; @@ -225,7 +228,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) goto free_buf; if (ice_is_xdp_ena_vsi(vsi)) { - struct ice_ring *xdp_ring = vsi->xdp_rings[q_idx]; + struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx]; memset(qg_buf, 0, size); qg_buf->num_txqs = 1; @@ -233,7 +236,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) if (err) goto free_buf; ice_set_ring_xdp(xdp_ring); - xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring); + xdp_ring->xsk_pool = ice_tx_xsk_pool(xdp_ring); } err = ice_vsi_cfg_rxq(rx_ring); @@ -360,7 +363,7 @@ xsk_pool_if_up: * * Returns true if all allocations were successful, false if any fail. */ -bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count) { union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; @@ -403,7 +406,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) * ice_bump_ntc - Bump the next_to_clean counter of an Rx ring * @rx_ring: Rx ring */ -static void ice_bump_ntc(struct ice_ring *rx_ring) +static void ice_bump_ntc(struct ice_rx_ring *rx_ring) { int ntc = rx_ring->next_to_clean + 1; @@ -422,7 +425,7 @@ static void ice_bump_ntc(struct ice_ring *rx_ring) * Returns the skb on success, NULL on failure. */ static struct sk_buff * -ice_construct_skb_zc(struct ice_ring *rx_ring, struct xdp_buff **xdp_arr) +ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr) { struct xdp_buff *xdp = *xdp_arr; unsigned int metasize = xdp->data - xdp->data_meta; @@ -449,22 +452,18 @@ ice_construct_skb_zc(struct ice_ring *rx_ring, struct xdp_buff **xdp_arr) * ice_run_xdp_zc - Executes an XDP program in zero-copy path * @rx_ring: Rx ring * @xdp: xdp_buff used as input to the XDP program + * @xdp_prog: XDP program to run + * @xdp_ring: ring to be used for XDP_TX action * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ static int -ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) +ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring) { int err, result = ICE_XDP_PASS; - struct bpf_prog *xdp_prog; - struct ice_ring *xdp_ring; u32 act; - /* ZC patch is enabled only when XDP program is set, - * so here it can not be NULL - */ - xdp_prog = READ_ONCE(rx_ring->xdp_prog); - act = bpf_prog_run_xdp(xdp_prog, xdp); if (likely(act == XDP_REDIRECT)) { @@ -478,7 +477,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) case XDP_PASS: break; case XDP_TX: - xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->q_index]; result = ice_xmit_xdp_buff(xdp, xdp_ring); if (result == ICE_XDP_CONSUMED) goto out_failure; @@ -505,13 +503,21 @@ out_failure: * * Returns number of processed packets on success, remaining budget on failure. */ -int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) +int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; u16 cleaned_count = ICE_DESC_UNUSED(rx_ring); + struct ice_tx_ring *xdp_ring; unsigned int xdp_xmit = 0; + struct bpf_prog *xdp_prog; bool failure = false; + /* ZC patch is enabled only when XDP program is set, + * so here it can not be NULL + */ + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + xdp_ring = rx_ring->xdp_ring; + while (likely(total_rx_packets < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; unsigned int size, xdp_res = 0; @@ -542,7 +548,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) xsk_buff_set_size(*xdp, size); xsk_buff_dma_sync_for_cpu(*xdp, rx_ring->xsk_pool); - xdp_res = ice_run_xdp_zc(rx_ring, *xdp); + xdp_res = ice_run_xdp_zc(rx_ring, *xdp, xdp_prog, xdp_ring); if (xdp_res) { if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) xdp_xmit |= xdp_res; @@ -590,7 +596,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) if (cleaned_count >= ICE_RX_BUF_WRITE) failure = !ice_alloc_rx_bufs_zc(rx_ring, cleaned_count); - ice_finalize_xdp_rx(rx_ring, xdp_xmit); + ice_finalize_xdp_rx(xdp_ring, xdp_xmit); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { @@ -612,7 +618,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) * * Returns true if cleanup/transmission is done. */ -static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) +static bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, int budget) { struct ice_tx_desc *tx_desc = NULL; bool work_done = true; @@ -663,7 +669,7 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) * @tx_buf: Tx buffer to clean */ static void -ice_clean_xdp_tx_buf(struct ice_ring *xdp_ring, struct ice_tx_buf *tx_buf) +ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf) { xdp_return_frame((struct xdp_frame *)tx_buf->raw_buf); dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma), @@ -678,7 +684,7 @@ ice_clean_xdp_tx_buf(struct ice_ring *xdp_ring, struct ice_tx_buf *tx_buf) * * Returns true if cleanup/tranmission is done. */ -bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget) +bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget) { int total_packets = 0, total_bytes = 0; s16 ntc = xdp_ring->next_to_clean; @@ -751,7 +757,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_q_vector *q_vector; struct ice_vsi *vsi = np->vsi; - struct ice_ring *ring; + struct ice_tx_ring *ring; if (test_bit(ICE_DOWN, vsi->state)) return -ENETDOWN; @@ -802,7 +808,7 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi) * ice_xsk_clean_rx_ring - clean buffer pool queues connected to a given Rx ring * @rx_ring: ring to be cleaned */ -void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) +void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { u16 i; @@ -820,7 +826,7 @@ void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) * ice_xsk_clean_xdp_ring - Clean the XDP Tx ring and its buffer pool queues * @xdp_ring: XDP_Tx ring */ -void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) +void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) { u16 ntc = xdp_ring->next_to_clean, ntu = xdp_ring->next_to_use; u32 xsk_frames = 0; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index ea208808623a..4c7bd8e9dfc4 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -11,13 +11,13 @@ struct ice_vsi; #ifdef CONFIG_XDP_SOCKETS int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid); -int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget); -bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget); +int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget); +bool ice_clean_tx_irq_zc(struct ice_tx_ring *xdp_ring, int budget); int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags); -bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count); +bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count); bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); -void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring); -void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring); +void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring); +void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring); #else static inline int ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi, @@ -28,21 +28,21 @@ ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi, } static inline int -ice_clean_rx_irq_zc(struct ice_ring __always_unused *rx_ring, +ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring, int __always_unused budget) { return 0; } static inline bool -ice_clean_tx_irq_zc(struct ice_ring __always_unused *xdp_ring, +ice_clean_tx_irq_zc(struct ice_tx_ring __always_unused *xdp_ring, int __always_unused budget) { return false; } static inline bool -ice_alloc_rx_bufs_zc(struct ice_ring __always_unused *rx_ring, +ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring, u16 __always_unused count) { return false; @@ -60,7 +60,7 @@ ice_xsk_wakeup(struct net_device __always_unused *netdev, return -EOPNOTSUPP; } -static inline void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) { } -static inline void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) { } +static inline void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { } +static inline void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) { } #endif /* CONFIG_XDP_SOCKETS */ #endif /* !_ICE_XSK_H_ */ diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 0f021909b430..30568e3544cd 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -773,7 +773,7 @@ static bool igc_is_crosststamp_supported(struct igc_adapter *adapter) static struct system_counterval_t igc_device_tstamp_to_system(u64 tstamp) { -#if IS_ENABLED(CONFIG_X86_TSC) +#if IS_ENABLED(CONFIG_X86_TSC) && !defined(CONFIG_UML) return convert_art_ns_to_tsc(tstamp); #else return (struct system_counterval_t) { }; diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c index a430871d1c27..c8d1e815ec6b 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c @@ -549,7 +549,7 @@ ixgb_mta_set(struct ixgb_hw *hw, *****************************************************************************/ void ixgb_rar_set(struct ixgb_hw *hw, - u8 *addr, + const u8 *addr, u32 index) { u32 rar_low, rar_high; diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.h b/drivers/net/ethernet/intel/ixgb/ixgb_hw.h index 6064583095da..70bcff5fb3db 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.h +++ b/drivers/net/ethernet/intel/ixgb/ixgb_hw.h @@ -740,7 +740,7 @@ bool ixgb_adapter_start(struct ixgb_hw *hw); void ixgb_check_for_link(struct ixgb_hw *hw); bool ixgb_check_for_bad_link(struct ixgb_hw *hw); -void ixgb_rar_set(struct ixgb_hw *hw, u8 *addr, u32 index); +void ixgb_rar_set(struct ixgb_hw *hw, const u8 *addr, u32 index); /* Filters (multicast, vlan, receive) */ void ixgb_mc_addr_list_update(struct ixgb_hw *hw, u8 *mc_addr_list, diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 5e1e2f0db82a..99d481904ce6 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -362,6 +362,7 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct ixgb_adapter *adapter; static int cards_found = 0; int pci_using_dac; + u8 addr[ETH_ALEN]; int i; int err; @@ -461,7 +462,8 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_eeprom; } - ixgb_get_ee_mac_addr(&adapter->hw, netdev->dev_addr); + ixgb_get_ee_mac_addr(&adapter->hw, addr); + eth_hw_addr_set(netdev, addr); if (!is_valid_ether_addr(netdev->dev_addr)) { netif_err(adapter, probe, adapter->netdev, "Invalid MAC Address\n"); @@ -2227,6 +2229,7 @@ static pci_ers_result_t ixgb_io_slot_reset(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct ixgb_adapter *adapter = netdev_priv(netdev); + u8 addr[ETH_ALEN]; if (pci_enable_device(pdev)) { netif_err(adapter, probe, adapter->netdev, @@ -2250,7 +2253,8 @@ static pci_ers_result_t ixgb_io_slot_reset(struct pci_dev *pdev) "After reset, the EEPROM checksum is not valid\n"); return PCI_ERS_RESULT_DISCONNECT; } - ixgb_get_ee_mac_addr(&adapter->hw, netdev->dev_addr); + ixgb_get_ee_mac_addr(&adapter->hw, addr); + eth_hw_addr_set(netdev, addr); memcpy(netdev->perm_addr, netdev->dev_addr, netdev->addr_len); if (!is_valid_ether_addr(netdev->perm_addr)) { diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 654ec25e6705..a63d9a5c8059 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1770,7 +1770,7 @@ static void uc_addr_get(struct mv643xx_eth_private *mp, unsigned char *addr) addr[5] = mac_l & 0xff; } -static void uc_addr_set(struct mv643xx_eth_private *mp, unsigned char *addr) +static void uc_addr_set(struct mv643xx_eth_private *mp, const u8 *addr) { wrlp(mp, MAC_ADDR_HIGH, (addr[0] << 24) | (addr[1] << 16) | (addr[2] << 8) | addr[3]); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 761155af25d8..98f276c617fb 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1623,8 +1623,8 @@ static void mvneta_set_ucast_addr(struct mvneta_port *pp, u8 last_nibble, } /* Set mac address */ -static void mvneta_mac_addr_set(struct mvneta_port *pp, unsigned char *addr, - int queue) +static void mvneta_mac_addr_set(struct mvneta_port *pp, + const unsigned char *addr, int queue) { unsigned int mac_h; unsigned int mac_l; @@ -1914,7 +1914,7 @@ static int mvneta_rx_refill(struct mvneta_port *pp, } /* Handle tx checksum */ -static u32 mvneta_skb_tx_csum(struct mvneta_port *pp, struct sk_buff *skb) +static u32 mvneta_skb_tx_csum(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_PARTIAL) { int ip_hdr_len = 0; @@ -2595,8 +2595,7 @@ err_drop_frame: } static inline void -mvneta_tso_put_hdr(struct sk_buff *skb, - struct mvneta_port *pp, struct mvneta_tx_queue *txq) +mvneta_tso_put_hdr(struct sk_buff *skb, struct mvneta_tx_queue *txq) { int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); struct mvneta_tx_buf *buf = &txq->buf[txq->txq_put_index]; @@ -2604,7 +2603,7 @@ mvneta_tso_put_hdr(struct sk_buff *skb, tx_desc = mvneta_txq_next_desc_get(txq); tx_desc->data_size = hdr_len; - tx_desc->command = mvneta_skb_tx_csum(pp, skb); + tx_desc->command = mvneta_skb_tx_csum(skb); tx_desc->command |= MVNETA_TXD_F_DESC; tx_desc->buf_phys_addr = txq->tso_hdrs_phys + txq->txq_put_index * TSO_HEADER_SIZE; @@ -2681,7 +2680,7 @@ static int mvneta_tx_tso(struct sk_buff *skb, struct net_device *dev, hdr = txq->tso_hdrs + txq->txq_put_index * TSO_HEADER_SIZE; tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0); - mvneta_tso_put_hdr(skb, pp, txq); + mvneta_tso_put_hdr(skb, txq); while (data_left > 0) { int size; @@ -2799,7 +2798,7 @@ static netdev_tx_t mvneta_tx(struct sk_buff *skb, struct net_device *dev) /* Get a descriptor for the first part of the packet */ tx_desc = mvneta_txq_next_desc_get(txq); - tx_cmd = mvneta_skb_tx_csum(pp, skb); + tx_cmd = mvneta_skb_tx_csum(skb); tx_desc->data_size = skb_headlen(skb); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index d379a35c4618..186d00a9ab35 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1519,7 +1519,6 @@ static int cgx_lmac_exit(struct cgx *cgx) int i; if (cgx->cgx_cmd_workq) { - flush_workqueue(cgx->cgx_cmd_workq); destroy_workqueue(cgx->cgx_cmd_workq); cgx->cgx_cmd_workq = NULL; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index dfe487235007..4e79e918a161 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -191,6 +191,7 @@ M(CPT_INLINE_IPSEC_CFG, 0xA04, cpt_inline_ipsec_cfg, \ M(CPT_STATS, 0xA05, cpt_sts, cpt_sts_req, cpt_sts_rsp) \ M(CPT_RXC_TIME_CFG, 0xA06, cpt_rxc_time_cfg, cpt_rxc_time_cfg_req, \ msg_rsp) \ +M(CPT_CTX_CACHE_SYNC, 0xA07, cpt_ctx_cache_sync, msg_req, msg_rsp) \ /* SDP mbox IDs (range 0x1000 - 0x11FF) */ \ M(SET_SDP_CHAN_INFO, 0x1000, set_sdp_chan_info, sdp_chan_info_msg, msg_rsp) \ M(GET_SDP_CHAN_INFO, 0x1001, get_sdp_chan_info, msg_req, sdp_get_chan_info_msg) \ @@ -292,10 +293,14 @@ M(NIX_BANDPROF_GET_HWINFO, 0x801f, nix_bandprof_get_hwinfo, msg_req, \ #define MBOX_UP_CGX_MESSAGES \ M(CGX_LINK_EVENT, 0xC00, cgx_link_event, cgx_link_info_msg, msg_rsp) +#define MBOX_UP_CPT_MESSAGES \ +M(CPT_INST_LMTST, 0xD00, cpt_inst_lmtst, cpt_inst_lmtst_req, msg_rsp) + enum { #define M(_name, _id, _1, _2, _3) MBOX_MSG_ ## _name = _id, MBOX_MESSAGES MBOX_UP_CGX_MESSAGES +MBOX_UP_CPT_MESSAGES #undef M }; @@ -1562,6 +1567,13 @@ struct cpt_rxc_time_cfg_req { u16 active_limit; }; +/* Mailbox message request format to request for CPT_INST_S lmtst. */ +struct cpt_inst_lmtst_req { + struct mbox_msghdr hdr; + u64 inst[8]; + u64 rsvd; +}; + struct sdp_node_info { /* Node to which this PF belons to */ u8 node_id; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 4cb24e91e648..cb56e171ddd4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -854,6 +854,7 @@ static int rvu_setup_nix_hw_resource(struct rvu *rvu, int blkaddr) block->lfcfg_reg = NIX_PRIV_LFX_CFG; block->msixcfg_reg = NIX_PRIV_LFX_INT_CFG; block->lfreset_reg = NIX_AF_LF_RST; + block->rvu = rvu; sprintf(block->name, "NIX%d", blkid); rvu->nix_blkaddr[blkid] = blkaddr; return rvu_alloc_bitmap(&block->lf); @@ -883,6 +884,7 @@ static int rvu_setup_cpt_hw_resource(struct rvu *rvu, int blkaddr) block->lfcfg_reg = CPT_PRIV_LFX_CFG; block->msixcfg_reg = CPT_PRIV_LFX_INT_CFG; block->lfreset_reg = CPT_AF_LF_RST; + block->rvu = rvu; sprintf(block->name, "CPT%d", blkid); return rvu_alloc_bitmap(&block->lf); } @@ -940,6 +942,7 @@ static int rvu_setup_hw_resources(struct rvu *rvu) block->lfcfg_reg = NPA_PRIV_LFX_CFG; block->msixcfg_reg = NPA_PRIV_LFX_INT_CFG; block->lfreset_reg = NPA_AF_LF_RST; + block->rvu = rvu; sprintf(block->name, "NPA"); err = rvu_alloc_bitmap(&block->lf); if (err) { @@ -979,6 +982,7 @@ nix: block->lfcfg_reg = SSO_PRIV_LFX_HWGRP_CFG; block->msixcfg_reg = SSO_PRIV_LFX_HWGRP_INT_CFG; block->lfreset_reg = SSO_AF_LF_HWGRP_RST; + block->rvu = rvu; sprintf(block->name, "SSO GROUP"); err = rvu_alloc_bitmap(&block->lf); if (err) { @@ -1003,6 +1007,7 @@ ssow: block->lfcfg_reg = SSOW_PRIV_LFX_HWS_CFG; block->msixcfg_reg = SSOW_PRIV_LFX_HWS_INT_CFG; block->lfreset_reg = SSOW_AF_LF_HWS_RST; + block->rvu = rvu; sprintf(block->name, "SSOWS"); err = rvu_alloc_bitmap(&block->lf); if (err) { @@ -1028,6 +1033,7 @@ tim: block->lfcfg_reg = TIM_PRIV_LFX_CFG; block->msixcfg_reg = TIM_PRIV_LFX_INT_CFG; block->lfreset_reg = TIM_AF_LF_RST; + block->rvu = rvu; sprintf(block->name, "TIM"); err = rvu_alloc_bitmap(&block->lf); if (err) { @@ -2399,7 +2405,6 @@ static void rvu_mbox_destroy(struct mbox_wq_info *mw) int devid; if (mw->mbox_wq) { - flush_workqueue(mw->mbox_wq); destroy_workqueue(mw->mbox_wq); mw->mbox_wq = NULL; } @@ -2527,7 +2532,8 @@ static void rvu_blklf_teardown(struct rvu *rvu, u16 pcifunc, u8 blkaddr) rvu_npa_lf_teardown(rvu, pcifunc, lf); else if ((block->addr == BLKADDR_CPT0) || (block->addr == BLKADDR_CPT1)) - rvu_cpt_lf_teardown(rvu, pcifunc, lf, slot); + rvu_cpt_lf_teardown(rvu, pcifunc, block->addr, lf, + slot); err = rvu_lf_reset(rvu, block, lf); if (err) { @@ -2725,6 +2731,8 @@ static void rvu_unregister_interrupts(struct rvu *rvu) { int irq; + rvu_cpt_unregister_interrupts(rvu); + /* Disable the Mbox interrupt */ rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT_ENA_W1C, INTR_MASK(rvu->hw->total_pfs) & ~1ULL); @@ -2934,6 +2942,11 @@ static int rvu_register_interrupts(struct rvu *rvu) goto fail; } rvu->irq_allocated[offset] = true; + + ret = rvu_cpt_register_interrupts(rvu); + if (ret) + goto fail; + return 0; fail: @@ -2944,7 +2957,6 @@ fail: static void rvu_flr_wq_destroy(struct rvu *rvu) { if (rvu->flr_wq) { - flush_workqueue(rvu->flr_wq); destroy_workqueue(rvu->flr_wq); rvu->flr_wq = NULL; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 58b166698fa5..66e45d733824 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -101,6 +101,7 @@ struct rvu_block { u64 msixcfg_reg; u64 lfreset_reg; unsigned char name[NAME_SIZE]; + struct rvu *rvu; }; struct nix_mcast { @@ -812,7 +813,11 @@ bool is_mcam_entry_enabled(struct rvu *rvu, struct npc_mcam *mcam, int blkaddr, int index); /* CPT APIs */ -int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot); +int rvu_cpt_register_interrupts(struct rvu *rvu); +void rvu_cpt_unregister_interrupts(struct rvu *rvu); +int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, + int slot); +int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc); /* CN10K RVU */ int rvu_set_channels_base(struct rvu *rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index c3842e454657..2ca182a4ce82 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -324,7 +324,6 @@ static int cgx_lmac_event_handler_init(struct rvu *rvu) static void rvu_cgx_wq_destroy(struct rvu *rvu) { if (rvu->cgx_evh_wq) { - flush_workqueue(rvu->cgx_evh_wq); destroy_workqueue(rvu->cgx_evh_wq); rvu->cgx_evh_wq = NULL; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c index 267d092b8e97..45357deecabb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c @@ -37,6 +37,236 @@ (_rsp)->free_sts_##etype = free_sts; \ }) +static irqreturn_t rvu_cpt_af_flt_intr_handler(int irq, void *ptr) +{ + struct rvu_block *block = ptr; + struct rvu *rvu = block->rvu; + int blkaddr = block->addr; + u64 reg0, reg1, reg2; + + reg0 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(0)); + reg1 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(1)); + if (!is_rvu_otx2(rvu)) { + reg2 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(2)); + dev_err_ratelimited(rvu->dev, + "Received CPTAF FLT irq : 0x%llx, 0x%llx, 0x%llx", + reg0, reg1, reg2); + } else { + dev_err_ratelimited(rvu->dev, + "Received CPTAF FLT irq : 0x%llx, 0x%llx", + reg0, reg1); + } + + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(0), reg0); + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(1), reg1); + if (!is_rvu_otx2(rvu)) + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(2), reg2); + + return IRQ_HANDLED; +} + +static irqreturn_t rvu_cpt_af_rvu_intr_handler(int irq, void *ptr) +{ + struct rvu_block *block = ptr; + struct rvu *rvu = block->rvu; + int blkaddr = block->addr; + u64 reg; + + reg = rvu_read64(rvu, blkaddr, CPT_AF_RVU_INT); + dev_err_ratelimited(rvu->dev, "Received CPTAF RVU irq : 0x%llx", reg); + + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT, reg); + return IRQ_HANDLED; +} + +static irqreturn_t rvu_cpt_af_ras_intr_handler(int irq, void *ptr) +{ + struct rvu_block *block = ptr; + struct rvu *rvu = block->rvu; + int blkaddr = block->addr; + u64 reg; + + reg = rvu_read64(rvu, blkaddr, CPT_AF_RAS_INT); + dev_err_ratelimited(rvu->dev, "Received CPTAF RAS irq : 0x%llx", reg); + + rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT, reg); + return IRQ_HANDLED; +} + +static int rvu_cpt_do_register_interrupt(struct rvu_block *block, int irq_offs, + irq_handler_t handler, + const char *name) +{ + struct rvu *rvu = block->rvu; + int ret; + + ret = request_irq(pci_irq_vector(rvu->pdev, irq_offs), handler, 0, + name, block); + if (ret) { + dev_err(rvu->dev, "RVUAF: %s irq registration failed", name); + return ret; + } + + WARN_ON(rvu->irq_allocated[irq_offs]); + rvu->irq_allocated[irq_offs] = true; + return 0; +} + +static void cpt_10k_unregister_interrupts(struct rvu_block *block, int off) +{ + struct rvu *rvu = block->rvu; + int blkaddr = block->addr; + int i; + + /* Disable all CPT AF interrupts */ + for (i = 0; i < CPT_10K_AF_INT_VEC_RVU; i++) + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1); + + for (i = 0; i < CPT_10K_AF_INT_VEC_CNT; i++) + if (rvu->irq_allocated[off + i]) { + free_irq(pci_irq_vector(rvu->pdev, off + i), block); + rvu->irq_allocated[off + i] = false; + } +} + +static void cpt_unregister_interrupts(struct rvu *rvu, int blkaddr) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct rvu_block *block; + int i, offs; + + if (!is_block_implemented(rvu->hw, blkaddr)) + return; + offs = rvu_read64(rvu, blkaddr, CPT_PRIV_AF_INT_CFG) & 0x7FF; + if (!offs) { + dev_warn(rvu->dev, + "Failed to get CPT_AF_INT vector offsets\n"); + return; + } + block = &hw->block[blkaddr]; + if (!is_rvu_otx2(rvu)) + return cpt_10k_unregister_interrupts(block, offs); + + /* Disable all CPT AF interrupts */ + for (i = 0; i < CPT_AF_INT_VEC_RVU; i++) + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1); + rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1); + + for (i = 0; i < CPT_AF_INT_VEC_CNT; i++) + if (rvu->irq_allocated[offs + i]) { + free_irq(pci_irq_vector(rvu->pdev, offs + i), block); + rvu->irq_allocated[offs + i] = false; + } +} + +void rvu_cpt_unregister_interrupts(struct rvu *rvu) +{ + cpt_unregister_interrupts(rvu, BLKADDR_CPT0); + cpt_unregister_interrupts(rvu, BLKADDR_CPT1); +} + +static int cpt_10k_register_interrupts(struct rvu_block *block, int off) +{ + struct rvu *rvu = block->rvu; + int blkaddr = block->addr; + char irq_name[16]; + int i, ret; + + for (i = CPT_10K_AF_INT_VEC_FLT0; i < CPT_10K_AF_INT_VEC_RVU; i++) { + snprintf(irq_name, sizeof(irq_name), "CPTAF FLT%d", i); + ret = rvu_cpt_do_register_interrupt(block, off + i, + rvu_cpt_af_flt_intr_handler, + irq_name); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1); + } + + ret = rvu_cpt_do_register_interrupt(block, off + CPT_10K_AF_INT_VEC_RVU, + rvu_cpt_af_rvu_intr_handler, + "CPTAF RVU"); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1S, 0x1); + + ret = rvu_cpt_do_register_interrupt(block, off + CPT_10K_AF_INT_VEC_RAS, + rvu_cpt_af_ras_intr_handler, + "CPTAF RAS"); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1S, 0x1); + + return 0; +err: + rvu_cpt_unregister_interrupts(rvu); + return ret; +} + +static int cpt_register_interrupts(struct rvu *rvu, int blkaddr) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct rvu_block *block; + int i, offs, ret = 0; + char irq_name[16]; + + if (!is_block_implemented(rvu->hw, blkaddr)) + return 0; + + block = &hw->block[blkaddr]; + offs = rvu_read64(rvu, blkaddr, CPT_PRIV_AF_INT_CFG) & 0x7FF; + if (!offs) { + dev_warn(rvu->dev, + "Failed to get CPT_AF_INT vector offsets\n"); + return 0; + } + + if (!is_rvu_otx2(rvu)) + return cpt_10k_register_interrupts(block, offs); + + for (i = CPT_AF_INT_VEC_FLT0; i < CPT_AF_INT_VEC_RVU; i++) { + snprintf(irq_name, sizeof(irq_name), "CPTAF FLT%d", i); + ret = rvu_cpt_do_register_interrupt(block, offs + i, + rvu_cpt_af_flt_intr_handler, + irq_name); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1); + } + + ret = rvu_cpt_do_register_interrupt(block, offs + CPT_AF_INT_VEC_RVU, + rvu_cpt_af_rvu_intr_handler, + "CPTAF RVU"); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1S, 0x1); + + ret = rvu_cpt_do_register_interrupt(block, offs + CPT_AF_INT_VEC_RAS, + rvu_cpt_af_ras_intr_handler, + "CPTAF RAS"); + if (ret) + goto err; + rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1S, 0x1); + + return 0; +err: + rvu_cpt_unregister_interrupts(rvu); + return ret; +} + +int rvu_cpt_register_interrupts(struct rvu *rvu) +{ + int ret; + + ret = cpt_register_interrupts(rvu, BLKADDR_CPT0); + if (ret) + return ret; + + return cpt_register_interrupts(rvu, BLKADDR_CPT1); +} + static int get_cpt_pf_num(struct rvu *rvu) { int i, domain_nr, cpt_pf_num = -1; @@ -147,9 +377,13 @@ int rvu_mbox_handler_cpt_lf_alloc(struct rvu *rvu, rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), val); - /* Set CPT LF NIX_PF_FUNC and SSO_PF_FUNC */ - val = (u64)req->nix_pf_func << 48 | - (u64)req->sso_pf_func << 32; + /* Set CPT LF NIX_PF_FUNC and SSO_PF_FUNC. EXE_LDWB is set + * on reset. + */ + val = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf)); + val &= ~(GENMASK_ULL(63, 48) | GENMASK_ULL(47, 32)); + val |= ((u64)req->nix_pf_func << 48 | + (u64)req->sso_pf_func << 32); rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), val); } @@ -159,7 +393,7 @@ int rvu_mbox_handler_cpt_lf_alloc(struct rvu *rvu, static int cpt_lf_free(struct rvu *rvu, struct msg_req *req, int blkaddr) { u16 pcifunc = req->hdr.pcifunc; - int num_lfs, cptlf, slot; + int num_lfs, cptlf, slot, err; struct rvu_block *block; block = &rvu->hw->block[blkaddr]; @@ -173,10 +407,15 @@ static int cpt_lf_free(struct rvu *rvu, struct msg_req *req, int blkaddr) if (cptlf < 0) return CPT_AF_ERR_LF_INVALID; - /* Reset CPT LF group and priority */ - rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), 0x0); - /* Reset CPT LF NIX_PF_FUNC and SSO_PF_FUNC */ - rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), 0x0); + /* Perform teardown */ + rvu_cpt_lf_teardown(rvu, pcifunc, blkaddr, cptlf, slot); + + /* Reset LF */ + err = rvu_lf_reset(rvu, block, cptlf); + if (err) { + dev_err(rvu->dev, "Failed to reset blkaddr %d LF%d\n", + block->addr, cptlf); + } } return 0; @@ -556,6 +795,58 @@ int rvu_mbox_handler_cpt_rxc_time_cfg(struct rvu *rvu, return 0; } +int rvu_mbox_handler_cpt_ctx_cache_sync(struct rvu *rvu, struct msg_req *req, + struct msg_rsp *rsp) +{ + return rvu_cpt_ctx_flush(rvu, req->hdr.pcifunc); +} + +static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr) +{ + struct cpt_rxc_time_cfg_req req; + int timeout = 2000; + u64 reg; + + if (is_rvu_otx2(rvu)) + return; + + /* Set time limit to minimum values, so that rxc entries will be + * flushed out quickly. + */ + req.step = 1; + req.zombie_thres = 1; + req.zombie_limit = 1; + req.active_thres = 1; + req.active_limit = 1; + + cpt_rxc_time_cfg(rvu, &req, blkaddr); + + do { + reg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_ACTIVE_STS); + udelay(1); + if (FIELD_GET(RXC_ACTIVE_COUNT, reg)) + timeout--; + else + break; + } while (timeout); + + if (timeout == 0) + dev_warn(rvu->dev, "Poll for RXC active count hits hard loop counter\n"); + + timeout = 2000; + do { + reg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_ZOMBIE_STS); + udelay(1); + if (FIELD_GET(RXC_ZOMBIE_COUNT, reg)) + timeout--; + else + break; + } while (timeout); + + if (timeout == 0) + dev_warn(rvu->dev, "Poll for RXC zombie count hits hard loop counter\n"); +} + #define INPROG_INFLIGHT(reg) ((reg) & 0x1FF) #define INPROG_GRB_PARTIAL(reg) ((reg) & BIT_ULL(31)) #define INPROG_GRB(reg) (((reg) >> 32) & 0xFF) @@ -620,14 +911,12 @@ static void cpt_lf_disable_iqueue(struct rvu *rvu, int blkaddr, int slot) dev_warn(rvu->dev, "CPT FLR hits hard loop counter\n"); } -int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot) +int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int slot) { - int blkaddr; u64 reg; - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_CPT, pcifunc); - if (blkaddr != BLKADDR_CPT0 && blkaddr != BLKADDR_CPT1) - return -EINVAL; + if (is_cpt_pf(rvu, pcifunc) || is_cpt_vf(rvu, pcifunc)) + cpt_rxc_teardown(rvu, blkaddr); /* Enable BAR2 ALIAS for this pcifunc. */ reg = BIT_ULL(16) | pcifunc; @@ -644,3 +933,154 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot) return 0; } + +#define CPT_RES_LEN 16 +#define CPT_SE_IE_EGRP 1ULL + +static int cpt_inline_inb_lf_cmd_send(struct rvu *rvu, int blkaddr, + int nix_blkaddr) +{ + int cpt_pf_num = get_cpt_pf_num(rvu); + struct cpt_inst_lmtst_req *req; + dma_addr_t res_daddr; + int timeout = 3000; + u8 cpt_idx; + u64 *inst; + u16 *res; + int rc; + + res = kzalloc(CPT_RES_LEN, GFP_KERNEL); + if (!res) + return -ENOMEM; + + res_daddr = dma_map_single(rvu->dev, res, CPT_RES_LEN, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(rvu->dev, res_daddr)) { + dev_err(rvu->dev, "DMA mapping failed for CPT result\n"); + rc = -EFAULT; + goto res_free; + } + *res = 0xFFFF; + + /* Send mbox message to CPT PF */ + req = (struct cpt_inst_lmtst_req *) + otx2_mbox_alloc_msg_rsp(&rvu->afpf_wq_info.mbox_up, + cpt_pf_num, sizeof(*req), + sizeof(struct msg_rsp)); + if (!req) { + rc = -ENOMEM; + goto res_daddr_unmap; + } + req->hdr.sig = OTX2_MBOX_REQ_SIG; + req->hdr.id = MBOX_MSG_CPT_INST_LMTST; + + inst = req->inst; + /* Prepare CPT_INST_S */ + inst[0] = 0; + inst[1] = res_daddr; + /* AF PF FUNC */ + inst[2] = 0; + /* Set QORD */ + inst[3] = 1; + inst[4] = 0; + inst[5] = 0; + inst[6] = 0; + /* Set EGRP */ + inst[7] = CPT_SE_IE_EGRP << 61; + + /* Subtract 1 from the NIX-CPT credit count to preserve + * credit counts. + */ + cpt_idx = (blkaddr == BLKADDR_CPT0) ? 0 : 1; + rvu_write64(rvu, nix_blkaddr, NIX_AF_RX_CPTX_CREDIT(cpt_idx), + BIT_ULL(22) - 1); + + otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, cpt_pf_num); + rc = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, cpt_pf_num); + if (rc) + dev_warn(rvu->dev, "notification to pf %d failed\n", + cpt_pf_num); + /* Wait for CPT instruction to be completed */ + do { + mdelay(1); + if (*res == 0xFFFF) + timeout--; + else + break; + } while (timeout); + + if (timeout == 0) + dev_warn(rvu->dev, "Poll for result hits hard loop counter\n"); + +res_daddr_unmap: + dma_unmap_single(rvu->dev, res_daddr, CPT_RES_LEN, DMA_BIDIRECTIONAL); +res_free: + kfree(res); + + return 0; +} + +#define CTX_CAM_PF_FUNC GENMASK_ULL(61, 46) +#define CTX_CAM_CPTR GENMASK_ULL(45, 0) + +int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc) +{ + int nix_blkaddr, blkaddr; + u16 max_ctx_entries, i; + int slot = 0, num_lfs; + u64 reg, cam_data; + int rc; + + nix_blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); + if (nix_blkaddr < 0) + return -EINVAL; + + if (is_rvu_otx2(rvu)) + return 0; + + blkaddr = (nix_blkaddr == BLKADDR_NIX1) ? BLKADDR_CPT1 : BLKADDR_CPT0; + + /* Submit CPT_INST_S to track when all packets have been + * flushed through for the NIX PF FUNC in inline inbound case. + */ + rc = cpt_inline_inb_lf_cmd_send(rvu, blkaddr, nix_blkaddr); + if (rc) + return rc; + + /* Wait for rxc entries to be flushed out */ + cpt_rxc_teardown(rvu, blkaddr); + + reg = rvu_read64(rvu, blkaddr, CPT_AF_CONSTANTS0); + max_ctx_entries = (reg >> 48) & 0xFFF; + + mutex_lock(&rvu->rsrc_lock); + + num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, pcifunc), + blkaddr); + if (num_lfs == 0) { + dev_warn(rvu->dev, "CPT LF is not configured\n"); + goto unlock; + } + + /* Enable BAR2 ALIAS for this pcifunc. */ + reg = BIT_ULL(16) | pcifunc; + rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg); + + for (i = 0; i < max_ctx_entries; i++) { + cam_data = rvu_read64(rvu, blkaddr, CPT_AF_CTX_CAM_DATA(i)); + + if ((FIELD_GET(CTX_CAM_PF_FUNC, cam_data) == pcifunc) && + FIELD_GET(CTX_CAM_CPTR, cam_data)) { + reg = BIT_ULL(46) | FIELD_GET(CTX_CAM_CPTR, cam_data); + rvu_write64(rvu, blkaddr, + CPT_AF_BAR2_ALIASX(slot, CPT_LF_CTX_FLUSH), + reg); + } + } + rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0); + +unlock: + mutex_unlock(&rvu->rsrc_lock); + + return 0; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 67feb26792e4..7761dcf17b91 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4512,6 +4512,8 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, return rvu_cgx_start_stop_io(rvu, pcifunc, false); } +#define RX_SA_BASE GENMASK_ULL(52, 7) + void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); @@ -4519,6 +4521,7 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) int pf = rvu_get_pf(pcifunc); struct mac_ops *mac_ops; u8 cgx_id, lmac_id; + u64 sa_base; void *cgxd; int err; @@ -4575,6 +4578,14 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) nix_ctx_free(rvu, pfvf); nix_free_all_bandprof(rvu, pcifunc); + + sa_base = rvu_read64(rvu, blkaddr, NIX_AF_LFX_RX_IPSEC_SA_BASE(nixlf)); + if (FIELD_GET(RX_SA_BASE, sa_base)) { + err = rvu_cpt_ctx_flush(rvu, pcifunc); + if (err) + dev_err(rvu->dev, + "CPT ctx flush failed with error: %d\n", err); + } } #define NIX_AF_LFX_TX_CFG_PTP_EN BIT_ULL(32) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index dbaeb10de7c2..22cd751613cd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -527,6 +527,7 @@ #define CPT_AF_CTX_WBACK_LATENCY_PC (0x49448ull) #define CPT_AF_CTX_PSH_PC (0x49450ull) #define CPT_AF_CTX_PSH_LATENCY_PC (0x49458ull) +#define CPT_AF_CTX_CAM_DATA(a) (0x49800ull | (u64)(a) << 3) #define CPT_AF_RXC_TIME (0x50010ull) #define CPT_AF_RXC_TIME_CFG (0x50018ull) #define CPT_AF_RXC_DFRG (0x50020ull) @@ -544,6 +545,7 @@ #define CPT_LF_CTL 0x10 #define CPT_LF_INPROG 0x40 #define CPT_LF_Q_GRP_PTR 0x120 +#define CPT_LF_CTX_FLUSH 0x510 #define NPC_AF_BLK_RST (0x00040) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h index 77ac96693f04..edc9367b1b95 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h @@ -62,6 +62,24 @@ enum rvu_af_int_vec_e { RVU_AF_INT_VEC_CNT = 0x5, }; +/* CPT Admin function Interrupt Vector Enumeration */ +enum cpt_af_int_vec_e { + CPT_AF_INT_VEC_FLT0 = 0x0, + CPT_AF_INT_VEC_FLT1 = 0x1, + CPT_AF_INT_VEC_RVU = 0x2, + CPT_AF_INT_VEC_RAS = 0x3, + CPT_AF_INT_VEC_CNT = 0x4, +}; + +enum cpt_10k_af_int_vec_e { + CPT_10K_AF_INT_VEC_FLT0 = 0x0, + CPT_10K_AF_INT_VEC_FLT1 = 0x1, + CPT_10K_AF_INT_VEC_FLT2 = 0x2, + CPT_10K_AF_INT_VEC_RVU = 0x3, + CPT_10K_AF_INT_VEC_RAS = 0x4, + CPT_10K_AF_INT_VEC_CNT = 0x5, +}; + /* NPA Admin function Interrupt Vector Enumeration */ enum npa_af_int_vec_e { NPA_AF_INT_VEC_RVU = 0x0, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index aaf9accc40ed..0048b5946712 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -3,12 +3,12 @@ # Makefile for Marvell's RVU Ethernet device drivers # -obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o -obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o +obj-$(CONFIG_OCTEONTX2_PF) += rvu_nicpf.o otx2_ptp.o +obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ - otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ + otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ otx2_devlink.o -rvu_nicvf-y := otx2_vf.o otx2_devlink.o otx2_ptp.o +rvu_nicvf-y := otx2_vf.o otx2_devlink.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index 95f21dfdba48..fd4f083c699e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -88,7 +88,7 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) aq->sq.ena = 1; /* Only one SMQ is allocated, map all SQ's to that SMQ */ aq->sq.smq = pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][0]; - aq->sq.smq_rr_weight = mtu_to_dwrr_weight(pfvf, pfvf->max_frs); + 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.sqe_stype = NIX_STYPE_STF; /* Cache SQB */ aq->sq.sqb_aura = sqb_aura; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 0c89eb8a670b..66da31f30d3e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -231,7 +231,7 @@ int otx2_hw_set_mtu(struct otx2_nic *pfvf, int mtu) return -ENOMEM; } - req->maxlen = pfvf->max_frs; + req->maxlen = pfvf->netdev->mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; err = otx2_sync_mbox_msg(&pfvf->mbox); mutex_unlock(&pfvf->mbox.lock); @@ -590,7 +590,7 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl) u64 schq, parent; u64 dwrr_val; - dwrr_val = mtu_to_dwrr_weight(pfvf, pfvf->max_frs); + dwrr_val = mtu_to_dwrr_weight(pfvf, pfvf->tx_max_pktlen); req = otx2_mbox_alloc_msg_nix_txschq_cfg(&pfvf->mbox); if (!req) @@ -603,9 +603,7 @@ int otx2_txschq_config(struct otx2_nic *pfvf, int lvl) /* Set topology e.t.c configuration */ if (lvl == NIX_TXSCH_LVL_SMQ) { req->reg[0] = NIX_AF_SMQX_CFG(schq); - req->regval[0] = ((pfvf->netdev->max_mtu + OTX2_ETH_HLEN) << 8) - | OTX2_MIN_MTU; - + req->regval[0] = ((u64)pfvf->tx_max_pktlen << 8) | OTX2_MIN_MTU; req->regval[0] |= (0x20ULL << 51) | (0x80ULL << 39) | (0x2ULL << 36); req->num_regs++; @@ -800,7 +798,7 @@ int otx2_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) aq->sq.ena = 1; /* Only one SMQ is allocated, map all SQ's to that SMQ */ aq->sq.smq = pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][0]; - aq->sq.smq_rr_quantum = mtu_to_dwrr_weight(pfvf, pfvf->max_frs); + 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.sqe_stype = NIX_STYPE_STF; /* Cache SQB */ aq->sq.sqb_aura = sqb_aura; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index a05f6bdac01e..61e52812983f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -326,7 +326,7 @@ struct otx2_nic { struct net_device *netdev; struct dev_hw_ops *hw_ops; void *iommu_domain; - u16 max_frs; + u16 tx_max_pktlen; u16 rbsize; /* Receive buffer size */ #define OTX2_FLAG_RX_TSTAMP_ENABLED BIT_ULL(0) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index f24e920324eb..1e0d0c9c1dac 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1312,16 +1312,14 @@ static int otx2_get_rbuf_size(struct otx2_nic *pf, int mtu) * NIX transfers entire data using 6 segments/buffers and writes * a CQE_RX descriptor with those segment addresses. First segment * has additional data prepended to packet. Also software omits a - * headroom of 128 bytes and sizeof(struct skb_shared_info) in - * each segment. Hence the total size of memory needed - * to receive a packet with 'mtu' is: + * headroom of 128 bytes in each segment. Hence the total size of + * memory needed to receive a packet with 'mtu' is: * frame size = mtu + additional data; - * memory = frame_size + (headroom + struct skb_shared_info size) * 6; + * memory = frame_size + headroom * 6; * each receive buffer size = memory / 6; */ frame_size = mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; - total_size = frame_size + (OTX2_HEAD_ROOM + - OTX2_DATA_ALIGN(sizeof(struct skb_shared_info))) * 6; + total_size = frame_size + OTX2_HEAD_ROOM * 6; rbuf_size = total_size / 6; return ALIGN(rbuf_size, 2048); @@ -1343,7 +1341,8 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) hw->sqpool_cnt = hw->tot_tx_queues; hw->pool_cnt = hw->rqpool_cnt + hw->sqpool_cnt; - pf->max_frs = pf->netdev->mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; + /* 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); @@ -1807,7 +1806,7 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev) /* Check for minimum and maximum packet length */ if (skb->len <= ETH_HLEN || - (!skb_shinfo(skb)->gso_size && skb->len > pf->max_frs)) { + (!skb_shinfo(skb)->gso_size && skb->len > pf->tx_max_pktlen)) { dev_kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c index 85b1f140d3dd..0ef68fdd1f26 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c @@ -297,6 +297,7 @@ int otx2_ptp_init(struct otx2_nic *pfvf) error: return err; } +EXPORT_SYMBOL_GPL(otx2_ptp_init); void otx2_ptp_destroy(struct otx2_nic *pfvf) { @@ -309,6 +310,7 @@ void otx2_ptp_destroy(struct otx2_nic *pfvf) kfree(ptp); pfvf->ptp = NULL; } +EXPORT_SYMBOL_GPL(otx2_ptp_destroy); int otx2_ptp_clock_index(struct otx2_nic *pfvf) { @@ -317,6 +319,7 @@ int otx2_ptp_clock_index(struct otx2_nic *pfvf) return ptp_clock_index(pfvf->ptp->ptp_clock); } +EXPORT_SYMBOL_GPL(otx2_ptp_clock_index); int otx2_ptp_tstamp2time(struct otx2_nic *pfvf, u64 tstamp, u64 *tsns) { @@ -327,3 +330,8 @@ int otx2_ptp_tstamp2time(struct otx2_nic *pfvf, u64 tstamp, u64 *tsns) return 0; } +EXPORT_SYMBOL_GPL(otx2_ptp_tstamp2time); + +MODULE_AUTHOR("Sunil Goutham <sgoutham@marvell.com>"); +MODULE_DESCRIPTION("Marvell RVU NIC PTP Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 2d2b67319340..0cc6353254bf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -181,8 +181,9 @@ static void otx2_set_rxtstamp(struct otx2_nic *pfvf, skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(tsns); } -static void otx2_skb_add_frag(struct otx2_nic *pfvf, struct sk_buff *skb, - u64 iova, int len, struct nix_rx_parse_s *parse) +static bool otx2_skb_add_frag(struct otx2_nic *pfvf, struct sk_buff *skb, + u64 iova, int len, struct nix_rx_parse_s *parse, + int qidx) { struct page *page; int off = 0; @@ -203,11 +204,22 @@ static void otx2_skb_add_frag(struct otx2_nic *pfvf, struct sk_buff *skb, } page = virt_to_page(va); - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - va - page_address(page) + off, len - off, pfvf->rbsize); + if (likely(skb_shinfo(skb)->nr_frags < MAX_SKB_FRAGS)) { + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + va - page_address(page) + off, + len - off, pfvf->rbsize); + + otx2_dma_unmap_page(pfvf, iova - OTX2_HEAD_ROOM, + pfvf->rbsize, DMA_FROM_DEVICE); + return true; + } - otx2_dma_unmap_page(pfvf, iova - OTX2_HEAD_ROOM, - pfvf->rbsize, DMA_FROM_DEVICE); + /* If more than MAX_SKB_FRAGS fragments are received then + * give back those buffer pointers to hardware for reuse. + */ + pfvf->hw_ops->aura_freeptr(pfvf, qidx, iova & ~0x07ULL); + + return false; } static void otx2_set_rxhash(struct otx2_nic *pfvf, @@ -349,9 +361,9 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf, seg_addr = &sg->seg_addr; seg_size = (void *)sg; for (seg = 0; seg < sg->segs; seg++, seg_addr++) { - otx2_skb_add_frag(pfvf, skb, *seg_addr, seg_size[seg], - parse); - cq->pool_ptrs++; + if (otx2_skb_add_frag(pfvf, skb, *seg_addr, + seg_size[seg], parse, cq->cq_idx)) + cq->pool_ptrs++; } start += sizeof(*sg); } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index 5c05774a8d05..f1a04cf9210c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -39,9 +39,7 @@ #define RCV_FRAG_LEN(x) \ ((RCV_FRAG_LEN1(x) < 2048) ? 2048 : RCV_FRAG_LEN1(x)) -#define DMA_BUFFER_LEN(x) \ - ((x) - OTX2_HEAD_ROOM - \ - OTX2_DATA_ALIGN(sizeof(struct skb_shared_info))) +#define DMA_BUFFER_LEN(x) ((x) - OTX2_HEAD_ROOM) /* IRQ triggered when NIX_LF_CINTX_CNT[ECOUNT] * is equal to this value. diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 980219a7e6fe..e6cb8cd0787d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -279,7 +279,6 @@ static void otx2vf_vfaf_mbox_destroy(struct otx2_nic *vf) struct mbox *mbox = &vf->mbox; if (vf->mbox_wq) { - flush_workqueue(vf->mbox_wq); destroy_workqueue(vf->mbox_wq); vf->mbox_wq = NULL; } diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index 898b513f74e0..6c02e1740609 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -389,7 +389,7 @@ static void inverse_every_nibble(unsigned char *mac_addr) * Outputs * return the calculated entry. */ -static u32 hash_function(unsigned char *mac_addr_orig) +static u32 hash_function(const unsigned char *mac_addr_orig) { u32 hash_result; u32 addr0; @@ -434,7 +434,7 @@ static u32 hash_function(unsigned char *mac_addr_orig) * -ENOSPC if table full */ static int add_del_hash_entry(struct pxa168_eth_private *pep, - unsigned char *mac_addr, + const unsigned char *mac_addr, u32 rd, u32 skip, int del) { struct addr_table_entry *entry, *start; @@ -521,7 +521,7 @@ static int add_del_hash_entry(struct pxa168_eth_private *pep, */ static void update_hash_table_mac_address(struct pxa168_eth_private *pep, unsigned char *oaddr, - unsigned char *addr) + const unsigned char *addr) { /* Delete old entry */ if (oaddr) @@ -1436,9 +1436,13 @@ static int pxa168_eth_probe(struct platform_device *pdev) err = of_get_ethdev_address(pdev->dev.of_node, dev); if (err) { + u8 addr[ETH_ALEN]; + /* try reading the mac address, if set by the bootloader */ - pxa168_eth_get_mac_address(dev, dev->dev_addr); - if (!is_valid_ether_addr(dev->dev_addr)) { + pxa168_eth_get_mac_address(dev, addr); + if (is_valid_ether_addr(addr)) { + eth_hw_addr_set(dev, addr); + } else { dev_info(&pdev->dev, "Using random mac address\n"); eth_hw_addr_random(dev); } diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index 1d5dd2015453..89ca7960b225 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -523,7 +523,7 @@ static void mtk_star_dma_resume_tx(struct mtk_star_priv *priv) static void mtk_star_set_mac_addr(struct net_device *ndev) { struct mtk_star_priv *priv = netdev_priv(ndev); - u8 *mac_addr = ndev->dev_addr; + const u8 *mac_addr = ndev->dev_addr; unsigned int high, low; high = mac_addr[0] << 8 | mac_addr[1] << 0; @@ -1544,7 +1544,7 @@ static int mtk_star_probe(struct platform_device *pdev) if (ret) return ret; - ret = eth_platform_get_mac_address(dev, ndev->dev_addr); + ret = platform_get_ethdev_address(dev, ndev); if (ret || !is_valid_ether_addr(ndev->dev_addr)) eth_hw_addr_random(ndev); diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 94ead263081f..e10b7b04b894 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2480,7 +2480,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) return 0; err_thread: - flush_workqueue(priv->mfunc.master.comm_wq); destroy_workqueue(priv->mfunc.master.comm_wq); err_slaves: while (i--) { @@ -2587,7 +2586,6 @@ void mlx4_multi_func_cleanup(struct mlx4_dev *dev) int i, port; if (mlx4_is_master(dev)) { - flush_workqueue(priv->mfunc.master.comm_wq); destroy_workqueue(priv->mfunc.master.comm_wq); for (i = 0; i < dev->num_slaves; i++) { for (port = 1; port <= MLX4_MAX_PORTS; port++) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index 109472d6b61f..f1259bdb1a29 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -237,7 +237,6 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr) if (mdev->pndev[i]) mlx4_en_destroy_netdev(mdev->pndev[i]); - flush_workqueue(mdev->workqueue); destroy_workqueue(mdev->workqueue); (void) mlx4_mr_free(dev, &mdev->mr); iounmap(mdev->uar_map); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 9541f3a920c8..b187c210d4d6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4025,8 +4025,8 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_params_unregister; pci_save_state(pdev); + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); - devlink_reload_enable(devlink); return 0; err_params_unregister: @@ -4135,7 +4135,6 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(priv); int active_vfs = 0; - devlink_reload_disable(devlink); devlink_unregister(devlink); if (mlx4_is_slave(dev)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 63032cd6efb1..a151575be51f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -17,7 +17,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ fs_counters.o fs_ft_pool.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \ - fw_reset.o qos.o + fw_reset.o qos.o lib/tout.o # # Netdev basic diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 4dc3a822907a..f71ec4d9d68e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -45,6 +45,7 @@ #include "mlx5_core.h" #include "lib/eq.h" +#include "lib/tout.h" enum { CMD_IF_REV = 5, @@ -225,9 +226,13 @@ static void set_signature(struct mlx5_cmd_work_ent *ent, int csum) static void poll_timeout(struct mlx5_cmd_work_ent *ent) { - unsigned long poll_end = jiffies + msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC + 1000); + struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev, cmd); + u64 cmd_to_ms = mlx5_tout_ms(dev, CMD); + unsigned long poll_end; u8 own; + poll_end = jiffies + msecs_to_jiffies(cmd_to_ms + 1000); + do { own = READ_ONCE(ent->lay->status_own); if (!(own & CMD_OWNER_HW)) { @@ -925,15 +930,18 @@ static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); struct mlx5_cmd *cmd = ent->cmd; - struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd); - unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); + bool poll_cmd = ent->polling; struct mlx5_cmd_layout *lay; + struct mlx5_core_dev *dev; + unsigned long cb_timeout; struct semaphore *sem; unsigned long flags; - bool poll_cmd = ent->polling; int alloc_ret; int cmd_mode; + dev = container_of(cmd, struct mlx5_core_dev, cmd); + cb_timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); + complete(&ent->handling); sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); @@ -1073,7 +1081,7 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev, static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) { - unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); + unsigned long timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); struct mlx5_cmd *cmd = &dev->cmd; int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index cf97985628ab..02e77ffe5c3e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -155,6 +155,8 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {}; int err; + mlx5_debug_cq_remove(dev, cq); + mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq); mlx5_eq_del_cq(&cq->eq->core, cq); @@ -162,16 +164,13 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) MLX5_SET(destroy_cq_in, in, cqn, cq->cqn); MLX5_SET(destroy_cq_in, in, uid, cq->uid); err = mlx5_cmd_exec_in(dev, destroy_cq, in); - if (err) - return err; synchronize_irq(cq->irqn); - mlx5_debug_cq_remove(dev, cq); mlx5_cq_put(cq); wait_for_completion(&cq->free); - return 0; + return err; } EXPORT_SYMBOL(mlx5_core_destroy_cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index e8093c4e09d4..a8b84d53dfb0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -33,6 +33,7 @@ #include <linux/mlx5/driver.h> #include <linux/mlx5/eswitch.h> #include <linux/mlx5/mlx5_ifc_vdpa.h> +#include <linux/mlx5/vport.h> #include "mlx5_core.h" /* intf dev list mutex */ @@ -537,6 +538,16 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev) return add_drivers(dev); } +static bool mlx5_same_hw_devs(struct mlx5_core_dev *dev, struct mlx5_core_dev *peer_dev) +{ + u64 fsystem_guid, psystem_guid; + + fsystem_guid = mlx5_query_nic_system_image_guid(dev); + psystem_guid = mlx5_query_nic_system_image_guid(peer_dev); + + return (fsystem_guid && psystem_guid && fsystem_guid == psystem_guid); +} + static u32 mlx5_gen_pci_id(const struct mlx5_core_dev *dev) { return (u32)((pci_domain_nr(dev->pdev->bus) << 16) | @@ -556,7 +567,8 @@ static int next_phys_dev(struct device *dev, const void *data) if (mdev == curr) return 0; - if (mlx5_gen_pci_id(mdev) != mlx5_gen_pci_id(curr)) + if (!mlx5_same_hw_devs(mdev, (struct mlx5_core_dev *)curr) && + mlx5_gen_pci_id(mdev) != mlx5_gen_pci_id(curr)) return 0; return 1; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index b9a6cea03951..1c98652b244a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -454,7 +454,8 @@ static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id, struct mlx5_core_dev *dev = devlink_priv(devlink); bool new_state = val.vbool; - if (new_state && !MLX5_CAP_GEN(dev, roce)) { + if (new_state && !MLX5_CAP_GEN(dev, roce) && + !MLX5_CAP_GEN(dev, roce_rw_supported)) { NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE"); return -EOPNOTSUPP; } @@ -796,6 +797,7 @@ static void mlx5_devlink_traps_unregister(struct devlink *devlink) int mlx5_devlink_register(struct devlink *devlink) { + struct mlx5_core_dev *dev = devlink_priv(devlink); int err; err = devlink_params_register(devlink, mlx5_devlink_params, @@ -813,6 +815,9 @@ int mlx5_devlink_register(struct devlink *devlink) if (err) goto traps_reg_err; + if (!mlx5_core_is_mp_slave(dev)) + devlink_set_features(devlink, DEVLINK_F_RELOAD); + return 0; traps_reg_err: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index f9cf9fb31547..da1bec04efff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -1069,7 +1069,6 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) mlx5_fw_tracer_clean_saved_traces_array(tracer); mlx5_fw_tracer_free_strings_db(tracer); mlx5_fw_tracer_destroy_log_buf(tracer); - flush_workqueue(tracer->work_queue); destroy_workqueue(tracer->work_queue); kvfree(tracer); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index 86e079310ac3..ae52e7f38306 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -24,7 +24,7 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv) if (mlx5_core_is_pf(priv->mdev)) { attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = PCI_FUNC(priv->mdev->pdev->devfn); + attrs.phys.port_number = mlx5_get_dev_index(priv->mdev); if (MLX5_ESWITCH_MANAGER(priv->mdev)) { mlx5e_devlink_get_port_parent_id(priv->mdev, &ppid); memcpy(attrs.switch_id.id, ppid.id, ppid.id_len); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 41684a6c44e9..1c23453a041d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -125,15 +125,15 @@ struct mlx5e_ethtool_steering { void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv); void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv); -int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd); -int mlx5e_ethtool_get_rxnfc(struct net_device *dev, +int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd); +int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *info, u32 *rule_locs); #else static inline void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv) { } static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv) { } -static inline int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +static inline int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd) { return -EOPNOTSUPP; } -static inline int mlx5e_ethtool_get_rxnfc(struct net_device *dev, +static inline int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *info, u32 *rule_locs) { return -EOPNOTSUPP; } #endif /* CONFIG_MLX5_EN_RXNFC */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h index 018262d0164b..d5b7110a4265 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h @@ -32,7 +32,6 @@ void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq); void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq); #define MLX5E_REPORTER_PER_Q_MAX_LEN 256 -#define MLX5E_REPORTER_FLUSH_TIMEOUT_MSEC 2000 struct mlx5e_err_ctx { int (*recover)(void *ctx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index b5ddaa82755f..c6d2f8c78db7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -475,9 +475,6 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) esw_warn(mdev, "Failed to allocate bridge offloads workqueue\n"); goto err_alloc_wq; } - INIT_DELAYED_WORK(&br_offloads->update_work, mlx5_esw_bridge_update_work); - queue_delayed_work(br_offloads->wq, &br_offloads->update_work, - msecs_to_jiffies(MLX5_ESW_BRIDGE_UPDATE_INTERVAL)); br_offloads->nb.notifier_call = mlx5_esw_bridge_switchdev_event; err = register_switchdev_notifier(&br_offloads->nb); @@ -500,6 +497,9 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) err); goto err_register_netdev; } + INIT_DELAYED_WORK(&br_offloads->update_work, mlx5_esw_bridge_update_work); + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + msecs_to_jiffies(MLX5_ESW_BRIDGE_UPDATE_INTERVAL)); return; err_register_netdev: @@ -523,10 +523,10 @@ void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) if (!br_offloads) return; + cancel_delayed_work_sync(&br_offloads->update_work); unregister_netdevice_notifier(&br_offloads->netdev_nb); unregister_switchdev_blocking_notifier(&br_offloads->nb_blk); unregister_switchdev_notifier(&br_offloads->nb); - cancel_delayed_work(&br_offloads->update_work); destroy_workqueue(br_offloads->wq); rtnl_lock(); mlx5_esw_bridge_cleanup(esw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index 0eb125316fe2..74086eb556ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -6,6 +6,7 @@ #include "txrx.h" #include "devlink.h" #include "ptp.h" +#include "lib/tout.h" static int mlx5e_query_rq_state(struct mlx5_core_dev *dev, u32 rqn, u8 *state) { @@ -32,8 +33,10 @@ out: static int mlx5e_wait_for_icosq_flush(struct mlx5e_icosq *icosq) { - unsigned long exp_time = jiffies + - msecs_to_jiffies(MLX5E_REPORTER_FLUSH_TIMEOUT_MSEC); + struct mlx5_core_dev *dev = icosq->channel->mdev; + unsigned long exp_time; + + exp_time = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FLUSH_ON_ERROR)); while (time_before(jiffies, exp_time)) { if (icosq->cc == icosq->pc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index bb682fd751c9..4f4bc8726ec4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -4,11 +4,14 @@ #include "health.h" #include "en/ptp.h" #include "en/devlink.h" +#include "lib/tout.h" static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) { - unsigned long exp_time = jiffies + - msecs_to_jiffies(MLX5E_REPORTER_FLUSH_TIMEOUT_MSEC); + struct mlx5_core_dev *dev = sq->mdev; + unsigned long exp_time; + + exp_time = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FLUSH_ON_ERROR)); while (time_before(jiffies, exp_time)) { if (sq->cc == sq->pc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 225748a9e52a..740cd6f088b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -2141,6 +2141,7 @@ err_ct_tuples_nat_ht: err_ct_tuples_ht: rhashtable_destroy(&ct_priv->zone_ht); err_ct_zone_ht: + mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat); err_ct_nat_tbl: mlx5_chains_destroy_global_table(chains, ct_priv->ct); err_ct_tbl: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 7a97e0e21fd7..25926e581d18 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -2137,12 +2137,14 @@ int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, return 0; } - return mlx5e_ethtool_get_rxnfc(dev, info, rule_locs); + return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs); } int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) { - return mlx5e_ethtool_set_rxnfc(dev, cmd); + struct mlx5e_priv *priv = netdev_priv(dev); + + return mlx5e_ethtool_set_rxnfc(priv, cmd); } static int query_port_status_opcode(struct mlx5_core_dev *mdev, u32 *status_opcode) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index c06b4b938ae7..73a377c8a2da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -71,12 +71,12 @@ struct mlx5e_l2_hash_node { bool mpfs; }; -static inline int mlx5e_hash_l2(u8 *addr) +static inline int mlx5e_hash_l2(const u8 *addr) { return addr[5]; } -static void mlx5e_add_l2_to_hash(struct hlist_head *hash, u8 *addr) +static void mlx5e_add_l2_to_hash(struct hlist_head *hash, const u8 *addr) { struct mlx5e_l2_hash_node *hn; int ix = mlx5e_hash_l2(addr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 03693fa74a70..81ebf281cdb4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -937,9 +937,8 @@ static int mlx5e_get_rss_hash_opt(struct mlx5e_priv *priv, return 0; } -int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +int mlx5e_ethtool_set_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *cmd) { - struct mlx5e_priv *priv = netdev_priv(dev); int err = 0; switch (cmd->cmd) { @@ -960,10 +959,9 @@ int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return err; } -int mlx5e_ethtool_get_rxnfc(struct net_device *dev, +int mlx5e_ethtool_get_rxnfc(struct mlx5e_priv *priv, struct ethtool_rxnfc *info, u32 *rule_locs) { - struct mlx5e_priv *priv = netdev_priv(dev); int err = 0; switch (info->cmd) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e81e5505207c..6d8fde1314e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3032,8 +3032,8 @@ static int mlx5e_mqprio_channel_validate(struct mlx5e_priv *priv, agg_count += mqprio->qopt.count[i]; } - if (priv->channels.params.num_channels < agg_count) { - netdev_err(netdev, "Num of queues (%d) exceeds available (%d)\n", + if (priv->channels.params.num_channels != agg_count) { + netdev_err(netdev, "Num of queues (%d) does not match available (%d)\n", agg_count, priv->channels.params.num_channels); return -EINVAL; } @@ -3406,20 +3406,67 @@ static int set_feature_rx_all(struct net_device *netdev, bool enable) return mlx5_set_port_fcs(mdev, !enable); } +static int mlx5e_set_rx_port_ts(struct mlx5_core_dev *mdev, bool enable) +{ + u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {}; + bool supported, curr_state; + int err; + + if (!MLX5_CAP_GEN(mdev, ports_check)) + return 0; + + err = mlx5_query_ports_check(mdev, in, sizeof(in)); + if (err) + return err; + + supported = MLX5_GET(pcmr_reg, in, rx_ts_over_crc_cap); + curr_state = MLX5_GET(pcmr_reg, in, rx_ts_over_crc); + + if (!supported || enable == curr_state) + return 0; + + MLX5_SET(pcmr_reg, in, local_port, 1); + MLX5_SET(pcmr_reg, in, rx_ts_over_crc, enable); + + return mlx5_set_ports_check(mdev, in, sizeof(in)); +} + static int set_feature_rx_fcs(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_channels *chs = &priv->channels; + struct mlx5_core_dev *mdev = priv->mdev; int err; mutex_lock(&priv->state_lock); - priv->channels.params.scatter_fcs_en = enable; - err = mlx5e_modify_channels_scatter_fcs(&priv->channels, enable); - if (err) - priv->channels.params.scatter_fcs_en = !enable; + if (enable) { + err = mlx5e_set_rx_port_ts(mdev, false); + if (err) + goto out; - mutex_unlock(&priv->state_lock); + chs->params.scatter_fcs_en = true; + err = mlx5e_modify_channels_scatter_fcs(chs, true); + if (err) { + chs->params.scatter_fcs_en = false; + mlx5e_set_rx_port_ts(mdev, true); + } + } else { + chs->params.scatter_fcs_en = false; + err = mlx5e_modify_channels_scatter_fcs(chs, false); + if (err) { + chs->params.scatter_fcs_en = true; + goto out; + } + err = mlx5e_set_rx_port_ts(mdev, true); + if (err) { + mlx5_core_warn(mdev, "Failed to set RX port timestamp %d\n", err); + err = 0; + } + } +out: + mutex_unlock(&priv->state_lock); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 3dd1101cc693..0684ac6699b2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -618,6 +618,11 @@ static void mlx5e_build_rep_params(struct net_device *netdev) params->mqprio.num_tc = 1; params->tunneled_offload_en = false; + /* Set an initial non-zero value, so that mlx5e_select_queue won't + * divide by zero if called before first activating channels. + */ + priv->num_tc_x_num_ch = params->num_channels * params->mqprio.num_tc; + mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); } @@ -643,7 +648,6 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev, netdev->hw_features |= NETIF_F_RXCSUM; netdev->features |= netdev->hw_features; - netdev->features |= NETIF_F_VLAN_CHALLENGED; netdev->features |= NETIF_F_NETNS_LOCAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index d92ee2f37c22..420b3ec0eb04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1891,8 +1891,10 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, bool needs_mapping, sets_mapping; int err; - if (!mlx5e_is_eswitch_flow(flow)) + if (!mlx5e_is_eswitch_flow(flow)) { + NL_SET_ERR_MSG_MOD(extack, "Match on tunnel is not supported"); return -EOPNOTSUPP; + } needs_mapping = !!flow->attr->chain; sets_mapping = flow_requires_tunnel_mapping(flow->attr->chain, f); @@ -2264,8 +2266,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, addr_type = match.key->addr_type; /* the HW doesn't support frag first/later */ - if (match.mask->flags & FLOW_DIS_FIRST_FRAG) + if (match.mask->flags & FLOW_DIS_FIRST_FRAG) { + NL_SET_ERR_MSG_MOD(extack, "Match on frag first/later is not supported"); return -EOPNOTSUPP; + } if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); @@ -2432,8 +2436,11 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, switch (ip_proto) { case IPPROTO_ICMP: if (!(MLX5_CAP_GEN(priv->mdev, flex_parser_protocols) & - MLX5_FLEX_PROTO_ICMP)) + MLX5_FLEX_PROTO_ICMP)) { + NL_SET_ERR_MSG_MOD(extack, + "Match on Flex protocols for ICMP is not supported"); return -EOPNOTSUPP; + } MLX5_SET(fte_match_set_misc3, misc_c_3, icmp_type, match.mask->type); MLX5_SET(fte_match_set_misc3, misc_v_3, icmp_type, @@ -2445,8 +2452,11 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, break; case IPPROTO_ICMPV6: if (!(MLX5_CAP_GEN(priv->mdev, flex_parser_protocols) & - MLX5_FLEX_PROTO_ICMPV6)) + MLX5_FLEX_PROTO_ICMPV6)) { + NL_SET_ERR_MSG_MOD(extack, + "Match on Flex protocols for ICMPV6 is not supported"); return -EOPNOTSUPP; + } MLX5_SET(fte_match_set_misc3, misc_c_3, icmpv6_type, match.mask->type); MLX5_SET(fte_match_set_misc3, misc_v_3, icmpv6_type, @@ -2552,15 +2562,19 @@ static int pedit_header_offsets[] = { #define pedit_header(_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype]) static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset, - struct pedit_headers_action *hdrs) + struct pedit_headers_action *hdrs, + struct netlink_ext_ack *extack) { u32 *curr_pmask, *curr_pval; curr_pmask = (u32 *)(pedit_header(&hdrs->masks, hdr_type) + offset); curr_pval = (u32 *)(pedit_header(&hdrs->vals, hdr_type) + offset); - if (*curr_pmask & mask) /* disallow acting twice on the same location */ + if (*curr_pmask & mask) { /* disallow acting twice on the same location */ + NL_SET_ERR_MSG_MOD(extack, + "curr_pmask and new mask same. Acting twice on same location"); goto out_err; + } *curr_pmask |= mask; *curr_pval |= (val & mask); @@ -2893,7 +2907,7 @@ parse_pedit_to_modify_hdr(struct mlx5e_priv *priv, val = act->mangle.val; offset = act->mangle.offset; - err = set_pedit_val(htype, ~mask, val, offset, &hdrs[cmd]); + err = set_pedit_val(htype, ~mask, val, offset, &hdrs[cmd], extack); if (err) goto out_err; @@ -2912,8 +2926,10 @@ parse_pedit_to_reformat(const struct flow_action_entry *act, u32 mask, val, offset; u32 *p; - if (act->id != FLOW_ACTION_MANGLE) + if (act->id != FLOW_ACTION_MANGLE) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported action id"); return -EOPNOTSUPP; + } if (act->mangle.htype != FLOW_ACT_MANGLE_HDR_TYPE_ETH) { NL_SET_ERR_MSG_MOD(extack, "Only Ethernet modification is supported"); @@ -3429,12 +3445,16 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, u32 action = 0; int err, i; - if (!flow_action_has_entries(flow_action)) + if (!flow_action_has_entries(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action doesn't have any entries"); return -EINVAL; + } if (!flow_action_hw_stats_check(flow_action, extack, - FLOW_ACTION_HW_STATS_DELAYED_BIT)) + FLOW_ACTION_HW_STATS_DELAYED_BIT)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action HW stats type is not supported"); return -EOPNOTSUPP; + } nic_attr = attr->nic_attr; nic_attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; @@ -3524,7 +3544,8 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, flow_flag_set(flow, CT); break; default: - NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported"); + NL_SET_ERR_MSG_MOD(extack, + "The offload action is not supported in NIC action"); return -EOPNOTSUPP; } } @@ -3562,19 +3583,25 @@ static bool is_merged_eswitch_vfs(struct mlx5e_priv *priv, static int parse_tc_vlan_action(struct mlx5e_priv *priv, const struct flow_action_entry *act, struct mlx5_esw_flow_attr *attr, - u32 *action) + u32 *action, + struct netlink_ext_ack *extack) { u8 vlan_idx = attr->total_vlan; - if (vlan_idx >= MLX5_FS_VLAN_DEPTH) + if (vlan_idx >= MLX5_FS_VLAN_DEPTH) { + NL_SET_ERR_MSG_MOD(extack, "Total vlans used is greater than supported"); return -EOPNOTSUPP; + } switch (act->id) { case FLOW_ACTION_VLAN_POP: if (vlan_idx) { if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) + MLX5_FS_VLAN_DEPTH)) { + NL_SET_ERR_MSG_MOD(extack, + "vlan pop action is not supported"); return -EOPNOTSUPP; + } *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2; } else { @@ -3590,20 +3617,27 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv, if (vlan_idx) { if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) + MLX5_FS_VLAN_DEPTH)) { + NL_SET_ERR_MSG_MOD(extack, + "vlan push action is not supported for vlan depth > 1"); return -EOPNOTSUPP; + } *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2; } else { if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) && (act->vlan.proto != htons(ETH_P_8021Q) || - act->vlan.prio)) + act->vlan.prio)) { + NL_SET_ERR_MSG_MOD(extack, + "vlan push action is not supported"); return -EOPNOTSUPP; + } *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; } break; default: + NL_SET_ERR_MSG_MOD(extack, "Unexpected action id for VLAN"); return -EINVAL; } @@ -3637,7 +3671,8 @@ static struct net_device *get_fdb_out_dev(struct net_device *uplink_dev, static int add_vlan_push_action(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, struct net_device **out_dev, - u32 *action) + u32 *action, + struct netlink_ext_ack *extack) { struct net_device *vlan_dev = *out_dev; struct flow_action_entry vlan_act = { @@ -3648,7 +3683,7 @@ static int add_vlan_push_action(struct mlx5e_priv *priv, }; int err; - err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action); + err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action, extack); if (err) return err; @@ -3659,14 +3694,15 @@ static int add_vlan_push_action(struct mlx5e_priv *priv, return -ENODEV; if (is_vlan_dev(*out_dev)) - err = add_vlan_push_action(priv, attr, out_dev, action); + err = add_vlan_push_action(priv, attr, out_dev, action, extack); return err; } static int add_vlan_pop_action(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, - u32 *action) + u32 *action, + struct netlink_ext_ack *extack) { struct flow_action_entry vlan_act = { .id = FLOW_ACTION_VLAN_POP, @@ -3676,7 +3712,7 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv, nest_level = attr->parse_attr->filter_dev->lower_level - priv->netdev->lower_level; while (nest_level--) { - err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action); + err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, action, extack); if (err) return err; } @@ -3798,12 +3834,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, int err, i, if_count = 0; bool mpls_push = false; - if (!flow_action_has_entries(flow_action)) + if (!flow_action_has_entries(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action doesn't have any entries"); return -EINVAL; + } if (!flow_action_hw_stats_check(flow_action, extack, - FLOW_ACTION_HW_STATS_DELAYED_BIT)) + FLOW_ACTION_HW_STATS_DELAYED_BIT)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action HW stats type is not supported"); return -EOPNOTSUPP; + } esw_attr = attr->esw_attr; parse_attr = attr->parse_attr; @@ -3952,14 +3992,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (is_vlan_dev(out_dev)) { err = add_vlan_push_action(priv, attr, &out_dev, - &action); + &action, extack); if (err) return err; } if (is_vlan_dev(parse_attr->filter_dev)) { err = add_vlan_pop_action(priv, attr, - &action); + &action, extack); if (err) return err; } @@ -4008,10 +4048,13 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, break; case FLOW_ACTION_TUNNEL_ENCAP: info = act->tunnel; - if (info) + if (info) { encap = true; - else + } else { + NL_SET_ERR_MSG_MOD(extack, + "Zero tunnel attributes is not supported"); return -EOPNOTSUPP; + } break; case FLOW_ACTION_VLAN_PUSH: @@ -4025,7 +4068,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, act, parse_attr, hdrs, &action, extack); } else { - err = parse_tc_vlan_action(priv, act, esw_attr, &action); + err = parse_tc_vlan_action(priv, act, esw_attr, &action, extack); } if (err) return err; @@ -4079,7 +4122,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, flow_flag_set(flow, SAMPLE); break; default: - NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported"); + NL_SET_ERR_MSG_MOD(extack, + "The offload action is not supported in FDB action"); return -EOPNOTSUPP; } } @@ -4753,8 +4797,10 @@ static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (!flow_action_basic_hw_stats_check(flow_action, extack)) + if (!flow_action_basic_hw_stats_check(flow_action, extack)) { + NL_SET_ERR_MSG_MOD(extack, "Flow action HW stats type is not supported"); return -EOPNOTSUPP; + } flow_action_for_each(i, act, flow_action) { switch (act->id) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index ed72246d1d83..588622ba38c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -677,6 +677,10 @@ mlx5_esw_bridge_egress_flow_create(u16 vport_num, u16 esw_owner_vhca_id, const u if (!rule_spec) return ERR_PTR(-ENOMEM); + if (MLX5_CAP_ESW_FLOWTABLE(bridge->br_offloads->esw->dev, flow_source) && + vport_num == MLX5_VPORT_UPLINK) + rule_spec->flow_context.flow_source = + MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT; rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; dmac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, 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 20af557ae30c..7f9b96d9537e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -36,7 +36,7 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 return NULL; mlx5_esw_get_port_parent_id(dev, &ppid); - pfnum = PCI_FUNC(dev->pdev->devfn); + pfnum = mlx5_get_dev_index(dev); external = mlx5_core_is_ecpf_esw_manager(dev); if (external) controller_num = dev->priv.eswitch->offloads.host_number + 1; @@ -149,7 +149,7 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p if (IS_ERR(vport)) return PTR_ERR(vport); - pfnum = PCI_FUNC(dev->pdev->devfn); + pfnum = mlx5_get_dev_index(dev); mlx5_esw_get_port_parent_id(dev, &ppid); memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len); dl_port->attrs.switch_id.id_len = ppid.id_len; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index ca7e31a1a431..3e5a7d74020b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2798,7 +2798,7 @@ u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw) int id; /* Only 4 bits of pf_num */ - pf_num = PCI_FUNC(esw->dev->pdev->devfn); + pf_num = mlx5_get_dev_index(esw->dev); if (pf_num > max_pf_num) return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 016d26f809a5..f4f8993eac17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -35,6 +35,7 @@ #include <linux/module.h> #include "mlx5_core.h" #include "../../mlxfw/mlxfw.h" +#include "lib/tout.h" #include "accel/tls.h" enum { @@ -317,10 +318,9 @@ int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev) return 0; } -#define MLX5_FAST_TEARDOWN_WAIT_MS 3000 int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev) { - unsigned long end, delay_ms = MLX5_FAST_TEARDOWN_WAIT_MS; + unsigned long end, delay_ms = mlx5_tout_ms(dev, TEARDOWN); u32 out[MLX5_ST_SZ_DW(teardown_hca_out)] = {}; u32 in[MLX5_ST_SZ_DW(teardown_hca_in)] = {}; int state; @@ -618,17 +618,18 @@ static void mlx5_fsm_release(struct mlxfw_dev *mlxfw_dev, u32 fwhandle) fwhandle, 0); } -#define MLX5_FSM_REACTIVATE_TOUT 5000 /* msecs */ static int mlx5_fsm_reactivate(struct mlxfw_dev *mlxfw_dev, u8 *status) { - unsigned long exp_time = jiffies + msecs_to_jiffies(MLX5_FSM_REACTIVATE_TOUT); struct mlx5_mlxfw_dev *mlx5_mlxfw_dev = container_of(mlxfw_dev, struct mlx5_mlxfw_dev, mlxfw_dev); struct mlx5_core_dev *dev = mlx5_mlxfw_dev->mlx5_core_dev; u32 out[MLX5_ST_SZ_DW(mirc_reg)]; u32 in[MLX5_ST_SZ_DW(mirc_reg)]; + unsigned long exp_time; int err; + exp_time = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FSM_REACTIVATE)); + if (!MLX5_CAP_MCAM_REG2(dev, mirc)) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 106b50e42b46..eaca79cc7b9d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -3,6 +3,7 @@ #include "fw_reset.h" #include "diag/fw_tracer.h" +#include "lib/tout.h" enum { MLX5_FW_RESET_FLAGS_RESET_REQUESTED, @@ -228,8 +229,6 @@ static void mlx5_sync_reset_request_event(struct work_struct *work) mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack. Device reset is expected.\n"); } -#define MLX5_PCI_LINK_UP_TIMEOUT 2000 - static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) { struct pci_bus *bridge_bus = dev->pdev->bus; @@ -286,7 +285,7 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) goto restore; } - timeout = jiffies + msecs_to_jiffies(MLX5_PCI_LINK_UP_TIMEOUT); + timeout = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, PCI_TOGGLE)); do { err = pci_read_config_word(bridge, cap + PCI_EXP_LNKSTA, ®16); if (err) @@ -299,8 +298,8 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) if (reg16 & PCI_EXP_LNKSTA_DLLLA) { mlx5_core_info(dev, "PCI Link up\n"); } else { - mlx5_core_err(dev, "PCI link not ready (0x%04x) after %d ms\n", - reg16, MLX5_PCI_LINK_UP_TIMEOUT); + mlx5_core_err(dev, "PCI link not ready (0x%04x) after %llu ms\n", + reg16, mlx5_tout_ms(dev, PCI_TOGGLE)); err = -ETIMEDOUT; } @@ -395,16 +394,15 @@ static int fw_reset_event_notifier(struct notifier_block *nb, unsigned long acti return NOTIFY_OK; } -#define MLX5_FW_RESET_TIMEOUT_MSEC 5000 int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev) { - unsigned long timeout = msecs_to_jiffies(MLX5_FW_RESET_TIMEOUT_MSEC); + unsigned long timeout = msecs_to_jiffies(mlx5_tout_ms(dev, PCI_SYNC_UPDATE)); struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; int err; if (!wait_for_completion_timeout(&fw_reset->done, timeout)) { - mlx5_core_warn(dev, "FW sync reset timeout after %d seconds\n", - MLX5_FW_RESET_TIMEOUT_MSEC / 1000); + mlx5_core_warn(dev, "FW sync reset timeout after %llu seconds\n", + mlx5_tout_ms(dev, PCI_SYNC_UPDATE) / 1000); err = -ETIMEDOUT; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 037e18dd4be0..6a4dd7f78958 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -40,10 +40,10 @@ #include "lib/eq.h" #include "lib/mlx5.h" #include "lib/pci_vsc.h" +#include "lib/tout.h" #include "diag/fw_tracer.h" enum { - MLX5_HEALTH_POLL_INTERVAL = 2 * HZ, MAX_MISSES = 3, }; @@ -219,11 +219,9 @@ unlock: mutex_unlock(&dev->intf_state_mutex); } -#define MLX5_CRDUMP_WAIT_MS 60000 -#define MLX5_FW_RESET_WAIT_MS 1000 void mlx5_error_sw_reset(struct mlx5_core_dev *dev) { - unsigned long end, delay_ms = MLX5_FW_RESET_WAIT_MS; + unsigned long end, delay_ms = mlx5_tout_ms(dev, PCI_TOGGLE); int lock = -EBUSY; mutex_lock(&dev->intf_state_mutex); @@ -237,7 +235,7 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev) lock = lock_sem_sw_reset(dev, true); if (lock == -EBUSY) { - delay_ms = MLX5_CRDUMP_WAIT_MS; + delay_ms = mlx5_tout_ms(dev, FULL_CRDUMP); goto recover_from_sw_reset; } /* Execute SW reset */ @@ -307,13 +305,11 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) mlx5_disable_device(dev); } -/* How much time to wait until health resetting the driver (in msecs) */ -#define MLX5_RECOVERY_WAIT_MSECS 60000 int mlx5_health_wait_pci_up(struct mlx5_core_dev *dev) { unsigned long end; - end = jiffies + msecs_to_jiffies(MLX5_RECOVERY_WAIT_MSECS); + end = jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, FW_RESET)); while (sensor_pci_not_working(dev)) { if (time_after(jiffies, end)) return -ETIMEDOUT; @@ -674,13 +670,13 @@ static void mlx5_fw_reporters_destroy(struct mlx5_core_dev *dev) devlink_health_reporter_destroy(health->fw_fatal_reporter); } -static unsigned long get_next_poll_jiffies(void) +static unsigned long get_next_poll_jiffies(struct mlx5_core_dev *dev) { unsigned long next; get_random_bytes(&next, sizeof(next)); next %= HZ; - next += jiffies + MLX5_HEALTH_POLL_INTERVAL; + next += jiffies + msecs_to_jiffies(mlx5_tout_ms(dev, HEALTH_POLL_INTERVAL)); return next; } @@ -740,11 +736,12 @@ static void poll_health(struct timer_list *t) queue_work(health->wq, &health->report_work); out: - mod_timer(&health->timer, get_next_poll_jiffies()); + mod_timer(&health->timer, get_next_poll_jiffies(dev)); } void mlx5_start_health_poll(struct mlx5_core_dev *dev) { + u64 poll_interval_ms = mlx5_tout_ms(dev, HEALTH_POLL_INTERVAL); struct mlx5_core_health *health = &dev->priv.health; timer_setup(&health->timer, poll_health, 0); @@ -753,7 +750,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) health->health = &dev->iseg->health; health->health_counter = &dev->iseg->health_counter; - health->timer.expires = round_jiffies(jiffies + MLX5_HEALTH_POLL_INTERVAL); + health->timer.expires = jiffies + msecs_to_jiffies(poll_interval_ms); add_timer(&health->timer); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 0c8594c7df21..ee0eb4a4b819 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -33,6 +33,11 @@ #include "en.h" #include "ipoib.h" +static u32 mlx5i_flow_type_mask(u32 flow_type) +{ + return flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS); +} + static void mlx5i_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { @@ -217,6 +222,27 @@ static int mlx5i_get_link_ksettings(struct net_device *netdev, return 0; } +#ifdef CONFIG_MLX5_EN_RXNFC +static int mlx5i_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct ethtool_rx_flow_spec *fs = &cmd->fs; + + if (mlx5i_flow_type_mask(fs->flow_type) == ETHER_FLOW) + return -EINVAL; + + return mlx5e_ethtool_set_rxnfc(priv, cmd); +} + +static int mlx5i_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, + u32 *rule_locs) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + + return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs); +} +#endif + const struct ethtool_ops mlx5i_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | @@ -233,6 +259,10 @@ const struct ethtool_ops mlx5i_ethtool_ops = { .get_coalesce = mlx5i_get_coalesce, .set_coalesce = mlx5i_set_coalesce, .get_ts_info = mlx5i_get_ts_info, +#ifdef CONFIG_MLX5_EN_RXNFC + .get_rxnfc = mlx5i_get_rxnfc, + .set_rxnfc = mlx5i_set_rxnfc, +#endif .get_link_ksettings = mlx5i_get_link_ksettings, .get_link = ethtool_op_get_link, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 269ebb53eda6..3b8d8ada1a01 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -219,7 +219,7 @@ void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv) int mlx5i_create_underlay_qp(struct mlx5e_priv *priv) { - unsigned char *dev_addr = priv->netdev->dev_addr; + const unsigned char *dev_addr = priv->netdev->dev_addr; u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {}; u32 in[MLX5_ST_SZ_DW(create_qp_in)] = {}; struct mlx5i_priv *ipriv = priv->ppriv; @@ -336,6 +336,8 @@ static int mlx5i_create_flow_steering(struct mlx5e_priv *priv) goto err_destroy_arfs_tables; } + mlx5e_ethtool_init_steering(priv); + return 0; err_destroy_arfs_tables: @@ -348,6 +350,7 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) { mlx5e_destroy_ttc_table(priv); mlx5e_arfs_destroy_tables(priv); + mlx5e_ethtool_cleanup_steering(priv); } static int mlx5i_init_rx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index ca5690b0a7ab..f35c8ba48aac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -688,7 +688,7 @@ static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev, struct net_device *netdev) { - unsigned int fn = PCI_FUNC(dev->pdev->devfn); + unsigned int fn = mlx5_get_dev_index(dev); if (fn >= MLX5_MAX_PORTS) return; @@ -718,7 +718,7 @@ static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev, static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev) { - unsigned int fn = PCI_FUNC(dev->pdev->devfn); + unsigned int fn = mlx5_get_dev_index(dev); if (fn >= MLX5_MAX_PORTS) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c new file mode 100644 index 000000000000..0dd96a6b140d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include <linux/mlx5/driver.h> +#include "lib/tout.h" + +struct mlx5_timeouts { + u64 to[MAX_TIMEOUT_TYPES]; +}; + +static const u32 tout_def_sw_val[MAX_TIMEOUT_TYPES] = { + [MLX5_TO_FW_PRE_INIT_TIMEOUT_MS] = 120000, + [MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS] = 20000, + [MLX5_TO_FW_PRE_INIT_WAIT_MS] = 2, + [MLX5_TO_FW_INIT_MS] = 2000, + [MLX5_TO_CMD_MS] = 60000, + [MLX5_TO_PCI_TOGGLE_MS] = 2000, + [MLX5_TO_HEALTH_POLL_INTERVAL_MS] = 2000, + [MLX5_TO_FULL_CRDUMP_MS] = 60000, + [MLX5_TO_FW_RESET_MS] = 60000, + [MLX5_TO_FLUSH_ON_ERROR_MS] = 2000, + [MLX5_TO_PCI_SYNC_UPDATE_MS] = 5000, + [MLX5_TO_TEARDOWN_MS] = 3000, + [MLX5_TO_FSM_REACTIVATE_MS] = 5000, + [MLX5_TO_RECLAIM_PAGES_MS] = 5000, + [MLX5_TO_RECLAIM_VFS_PAGES_MS] = 120000 +}; + +static void tout_set(struct mlx5_core_dev *dev, u64 val, enum mlx5_timeouts_types type) +{ + dev->timeouts->to[type] = val; +} + +static void tout_set_def_val(struct mlx5_core_dev *dev) +{ + int i; + + for (i = MLX5_TO_FW_PRE_INIT_TIMEOUT_MS; i < MAX_TIMEOUT_TYPES; i++) + tout_set(dev, tout_def_sw_val[i], i); +} + +int mlx5_tout_init(struct mlx5_core_dev *dev) +{ + dev->timeouts = kmalloc(sizeof(*dev->timeouts), GFP_KERNEL); + if (!dev->timeouts) + return -ENOMEM; + + tout_set_def_val(dev); + return 0; +} + +void mlx5_tout_cleanup(struct mlx5_core_dev *dev) +{ + kfree(dev->timeouts); +} + +/* Time register consists of two fields to_multiplier(time out multiplier) + * and to_value(time out value). to_value is the quantity of the time units and + * to_multiplier is the type and should be one off these four values. + * 0x0: millisecond + * 0x1: seconds + * 0x2: minutes + * 0x3: hours + * this function converts the time stored in the two register fields into + * millisecond. + */ +static u64 tout_convert_reg_field_to_ms(u32 to_mul, u32 to_val) +{ + u64 msec = to_val; + + to_mul &= 0x3; + /* convert hours/minutes/seconds to miliseconds */ + if (to_mul) + msec *= 1000 * int_pow(60, to_mul - 1); + + return msec; +} + +static u64 tout_convert_iseg_to_ms(u32 iseg_to) +{ + return tout_convert_reg_field_to_ms(iseg_to >> 29, iseg_to & 0xfffff); +} + +static bool tout_is_supported(struct mlx5_core_dev *dev) +{ + return !!ioread32be(&dev->iseg->cmd_q_init_to); +} + +void mlx5_tout_query_iseg(struct mlx5_core_dev *dev) +{ + u32 to; + + if (!tout_is_supported(dev)) + return; + + to = ioread32be(&dev->iseg->cmd_q_init_to); + tout_set(dev, tout_convert_iseg_to_ms(to), MLX5_TO_FW_INIT_MS); + + to = ioread32be(&dev->iseg->cmd_exec_to); + tout_set(dev, tout_convert_iseg_to_ms(to), MLX5_TO_CMD_MS); +} + +u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type) +{ + return dev->timeouts->to[type]; +} + +#define MLX5_TIMEOUT_QUERY(fld, reg_out) \ + ({ \ + struct mlx5_ifc_default_timeout_bits *time_field; \ + u32 to_multi, to_value; \ + u64 to_val_ms; \ + \ + time_field = MLX5_ADDR_OF(dtor_reg, reg_out, fld); \ + to_multi = MLX5_GET(default_timeout, time_field, to_multiplier); \ + to_value = MLX5_GET(default_timeout, time_field, to_value); \ + to_val_ms = tout_convert_reg_field_to_ms(to_multi, to_value); \ + to_val_ms; \ + }) + +#define MLX5_TIMEOUT_FILL(fld, reg_out, dev, to_type, to_extra) \ + ({ \ + u64 fw_to = MLX5_TIMEOUT_QUERY(fld, reg_out); \ + tout_set(dev, fw_to + (to_extra), to_type); \ + fw_to; \ + }) + +static int tout_query_dtor(struct mlx5_core_dev *dev) +{ + u64 pcie_toggle_to_val, tear_down_to_val; + u32 out[MLX5_ST_SZ_DW(dtor_reg)] = {}; + u32 in[MLX5_ST_SZ_DW(dtor_reg)] = {}; + int err; + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_DTOR, 0, 0); + if (err) + return err; + + pcie_toggle_to_val = MLX5_TIMEOUT_FILL(pcie_toggle_to, out, dev, MLX5_TO_PCI_TOGGLE_MS, 0); + MLX5_TIMEOUT_FILL(fw_reset_to, out, dev, MLX5_TO_FW_RESET_MS, pcie_toggle_to_val); + + tear_down_to_val = MLX5_TIMEOUT_FILL(tear_down_to, out, dev, MLX5_TO_TEARDOWN_MS, 0); + MLX5_TIMEOUT_FILL(pci_sync_update_to, out, dev, MLX5_TO_PCI_SYNC_UPDATE_MS, + tear_down_to_val); + + MLX5_TIMEOUT_FILL(health_poll_to, out, dev, MLX5_TO_HEALTH_POLL_INTERVAL_MS, 0); + MLX5_TIMEOUT_FILL(full_crdump_to, out, dev, MLX5_TO_FULL_CRDUMP_MS, 0); + MLX5_TIMEOUT_FILL(flush_on_err_to, out, dev, MLX5_TO_FLUSH_ON_ERROR_MS, 0); + MLX5_TIMEOUT_FILL(fsm_reactivate_to, out, dev, MLX5_TO_FSM_REACTIVATE_MS, 0); + MLX5_TIMEOUT_FILL(reclaim_pages_to, out, dev, MLX5_TO_RECLAIM_PAGES_MS, 0); + MLX5_TIMEOUT_FILL(reclaim_vfs_pages_to, out, dev, MLX5_TO_RECLAIM_VFS_PAGES_MS, 0); + + return 0; +} + +int mlx5_tout_query_dtor(struct mlx5_core_dev *dev) +{ + if (tout_is_supported(dev)) + return tout_query_dtor(dev); + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h new file mode 100644 index 000000000000..31faa5c17aa9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef MLX5_TIMEOUTS_H +#define MLX5_TIMEOUTS_H + +enum mlx5_timeouts_types { + /* pre init timeouts (not read from FW) */ + MLX5_TO_FW_PRE_INIT_TIMEOUT_MS, + MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS, + MLX5_TO_FW_PRE_INIT_WAIT_MS, + + /* init segment timeouts */ + MLX5_TO_FW_INIT_MS, + MLX5_TO_CMD_MS, + + /* DTOR timeouts */ + MLX5_TO_PCI_TOGGLE_MS, + MLX5_TO_HEALTH_POLL_INTERVAL_MS, + MLX5_TO_FULL_CRDUMP_MS, + MLX5_TO_FW_RESET_MS, + MLX5_TO_FLUSH_ON_ERROR_MS, + MLX5_TO_PCI_SYNC_UPDATE_MS, + MLX5_TO_TEARDOWN_MS, + MLX5_TO_FSM_REACTIVATE_MS, + MLX5_TO_RECLAIM_PAGES_MS, + MLX5_TO_RECLAIM_VFS_PAGES_MS, + + MAX_TIMEOUT_TYPES +}; + +struct mlx5_core_dev; +int mlx5_tout_init(struct mlx5_core_dev *dev); +void mlx5_tout_cleanup(struct mlx5_core_dev *dev); +void mlx5_tout_query_iseg(struct mlx5_core_dev *dev); +int mlx5_tout_query_dtor(struct mlx5_core_dev *dev); +u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type); + +#define mlx5_tout_ms(dev, type) _mlx5_tout_ms(dev, MLX5_TO_##type##_MS) + +# endif /* MLX5_TIMEOUTS_H */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 5893fdd5aedb..47d92fb459ed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -60,6 +60,7 @@ #include "devlink.h" #include "fw_reset.h" #include "lib/mlx5.h" +#include "lib/tout.h" #include "fpga/core.h" #include "fpga/ipsec.h" #include "accel/ipsec.h" @@ -176,11 +177,6 @@ static struct mlx5_profile profile[] = { }, }; -#define FW_INIT_TIMEOUT_MILI 2000 -#define FW_INIT_WAIT_MS 2 -#define FW_PRE_INIT_TIMEOUT_MILI 120000 -#define FW_INIT_WARN_MESSAGE_INTERVAL 20000 - static int fw_initializing(struct mlx5_core_dev *dev) { return ioread32be(&dev->iseg->initializing) >> 31; @@ -193,8 +189,6 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili, unsigned long end = jiffies + msecs_to_jiffies(max_wait_mili); int err = 0; - BUILD_BUG_ON(FW_PRE_INIT_TIMEOUT_MILI < FW_INIT_WARN_MESSAGE_INTERVAL); - while (fw_initializing(dev)) { if (time_after(jiffies, end)) { err = -EBUSY; @@ -205,7 +199,7 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili, jiffies_to_msecs(end - warn) / 1000); warn = jiffies + msecs_to_jiffies(warn_time_mili); } - msleep(FW_INIT_WAIT_MS); + msleep(mlx5_tout_ms(dev, FW_PRE_INIT_WAIT)); } return err; @@ -564,15 +558,38 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) MLX5_SET(cmd_hca_cap, set_hca_cap, num_total_dynamic_vf_msix, MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix)); + if (MLX5_CAP_GEN(dev, roce_rw_supported)) + MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev)); + return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE); } +/* Cached MLX5_CAP_GEN(dev, roce) can be out of sync this early in the + * boot process. + * In case RoCE cap is writable in FW and user/devlink requested to change the + * cap, we are yet to query the final state of the above cap. + * Hence, the need for this function. + * + * Returns + * True: + * 1) RoCE cap is read only in FW and already disabled + * OR: + * 2) RoCE cap is writable in FW and user/devlink requested it off. + * + * In any other case, return False. + */ +static bool is_roce_fw_disabled(struct mlx5_core_dev *dev) +{ + return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_init_enabled(dev)) || + (!MLX5_CAP_GEN(dev, roce_rw_supported) && !MLX5_CAP_GEN(dev, roce)); +} + static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx) { void *set_hca_cap; int err; - if (!MLX5_CAP_GEN(dev, roce)) + if (is_roce_fw_disabled(dev)) return 0; err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE); @@ -975,25 +992,34 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) if (mlx5_core_is_pf(dev)) pcie_print_link_status(dev->pdev); + err = mlx5_tout_init(dev); + if (err) { + mlx5_core_err(dev, "Failed initializing timeouts, aborting\n"); + return err; + } + /* wait for firmware to accept initialization segments configurations */ - err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI, FW_INIT_WARN_MESSAGE_INTERVAL); + err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT), + mlx5_tout_ms(dev, FW_PRE_INIT_WARN_MESSAGE_INTERVAL)); if (err) { - mlx5_core_err(dev, "Firmware over %d MS in pre-initializing state, aborting\n", - FW_PRE_INIT_TIMEOUT_MILI); - return err; + mlx5_core_err(dev, "Firmware over %llu MS in pre-initializing state, aborting\n", + mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT)); + goto err_tout_cleanup; } err = mlx5_cmd_init(dev); if (err) { mlx5_core_err(dev, "Failed initializing command interface, aborting\n"); - return err; + goto err_tout_cleanup; } - err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI, 0); + mlx5_tout_query_iseg(dev); + + err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_INIT), 0); if (err) { - mlx5_core_err(dev, "Firmware over %d MS in initializing state, aborting\n", - FW_INIT_TIMEOUT_MILI); + mlx5_core_err(dev, "Firmware over %llu MS in initializing state, aborting\n", + mlx5_tout_ms(dev, FW_INIT)); goto err_cmd_cleanup; } @@ -1017,6 +1043,12 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) goto err_disable_hca; } + err = mlx5_tout_query_dtor(dev); + if (err) { + mlx5_core_err(dev, "failed to read dtor\n"); + goto reclaim_boot_pages; + } + err = set_hca_ctrl(dev); if (err) { mlx5_core_err(dev, "set_hca_ctrl failed\n"); @@ -1062,6 +1094,8 @@ err_disable_hca: err_cmd_cleanup: mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); +err_tout_cleanup: + mlx5_tout_cleanup(dev); return err; } @@ -1080,6 +1114,7 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot) mlx5_core_disable_hca(dev, 0); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); + mlx5_tout_cleanup(dev); return 0; } @@ -1538,8 +1573,6 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) pci_save_state(pdev); devlink_register(devlink); - if (!mlx5_core_is_mp_slave(dev)) - devlink_reload_enable(devlink); return 0; err_init_one: @@ -1559,7 +1592,6 @@ static void remove_one(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(pdev); struct devlink *devlink = priv_to_devlink(dev); - devlink_reload_disable(devlink); devlink_unregister(devlink); mlx5_crdump_disable(dev); mlx5_drain_health_wq(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 110c0837f95b..f6b5451328fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -38,6 +38,7 @@ #include <linux/xarray.h> #include "mlx5_core.h" #include "lib/eq.h" +#include "lib/tout.h" enum { MLX5_PAGES_CANT_GIVE = 0, @@ -65,11 +66,6 @@ struct fw_page { }; enum { - MAX_RECLAIM_TIME_MSECS = 5000, - MAX_RECLAIM_VFS_PAGES_TIME_MSECS = 2 * 1000 * 60, -}; - -enum { MLX5_MAX_RECLAIM_TIME_MILI = 5000, MLX5_NUM_4K_IN_PAGE = PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE, }; @@ -641,7 +637,8 @@ static int optimal_reclaimed_pages(void) static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev, struct rb_root *root, u16 func_id) { - unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS); + u64 recl_pages_to_jiffies = msecs_to_jiffies(mlx5_tout_ms(dev, RECLAIM_PAGES)); + unsigned long end = jiffies + recl_pages_to_jiffies; while (!RB_EMPTY_ROOT(root)) { int nclaimed; @@ -656,7 +653,7 @@ static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev, } if (nclaimed) - end = jiffies + msecs_to_jiffies(MAX_RECLAIM_TIME_MSECS); + end = jiffies + recl_pages_to_jiffies; if (time_after(jiffies, end)) { mlx5_core_warn(dev, "FW did not return all pages. giving up...\n"); @@ -727,7 +724,8 @@ void mlx5_pagealloc_stop(struct mlx5_core_dev *dev) int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages) { - unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); + u64 recl_vf_pages_to_jiffies = msecs_to_jiffies(mlx5_tout_ms(dev, RECLAIM_VFS_PAGES)); + unsigned long end = jiffies + recl_vf_pages_to_jiffies; int prev_pages = *pages; /* In case of internal error we will free the pages manually later */ @@ -743,7 +741,7 @@ int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages) return -ETIMEDOUT; } if (*pages < prev_pages) { - end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); + end = jiffies + recl_vf_pages_to_jiffies; prev_pages = *pages; } msleep(50); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index 3cf272fa2164..7b4783ce213e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -47,7 +47,6 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia goto init_one_err; } devlink_register(devlink); - devlink_reload_enable(devlink); return 0; init_one_err: @@ -62,10 +61,8 @@ mdev_err: static void mlx5_sf_dev_remove(struct auxiliary_device *adev) { struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); - struct devlink *devlink; + struct devlink *devlink = priv_to_devlink(sf_dev->mdev); - devlink = priv_to_devlink(sf_dev->mdev); - devlink_reload_disable(devlink); devlink_unregister(devlink); mlx5_uninit_one(sf_dev->mdev); iounmap(sf_dev->mdev->iseg); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index 13891fdc607e..e1bb3acf45e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -323,7 +323,7 @@ mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_ NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported"); return -EOPNOTSUPP; } - if (new_attr->pfnum != PCI_FUNC(dev->pdev->devfn)) { + if (new_attr->pfnum != mlx5_get_dev_index(dev)) { NL_SET_ERR_MSG_MOD(extack, "Invalid pfnum supplied"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 50630112c8ff..07936841ce99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -854,6 +854,7 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, struct mlx5dr_action *action; bool reformat_req = false; u32 num_of_ref = 0; + u32 ref_act_cnt; int ret; int i; @@ -862,11 +863,14 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, return NULL; } - hw_dests = kzalloc(sizeof(*hw_dests) * num_of_dests, GFP_KERNEL); + hw_dests = kcalloc(num_of_dests, sizeof(*hw_dests), GFP_KERNEL); if (!hw_dests) return NULL; - ref_actions = kzalloc(sizeof(*ref_actions) * num_of_dests * 2, GFP_KERNEL); + if (unlikely(check_mul_overflow(num_of_dests, 2u, &ref_act_cnt))) + goto free_hw_dests; + + ref_actions = kcalloc(ref_act_cnt, sizeof(*ref_actions), GFP_KERNEL); if (!ref_actions) goto free_hw_dests; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 4c1440a95ad7..8846d30a380a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -421,19 +421,21 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, { u32 *out; int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); + int err; out = kvzalloc(outlen, GFP_KERNEL); if (!out) return -ENOMEM; - mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, out); + if (err) + goto out; *system_image_guid = MLX5_GET64(query_nic_vport_context_out, out, nic_vport_context.system_image_guid); - +out: kvfree(out); - - return 0; + return err; } EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_system_image_guid); @@ -1133,19 +1135,20 @@ EXPORT_SYMBOL_GPL(mlx5_nic_vport_unaffiliate_multiport); u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev) { int port_type_cap = MLX5_CAP_GEN(mdev, port_type); - u64 tmp = 0; + u64 tmp; + int err; if (mdev->sys_image_guid) return mdev->sys_image_guid; if (port_type_cap == MLX5_CAP_PORT_TYPE_ETH) - mlx5_query_nic_vport_system_image_guid(mdev, &tmp); + err = mlx5_query_nic_vport_system_image_guid(mdev, &tmp); else - mlx5_query_hca_vport_system_image_guid(mdev, &tmp); + err = mlx5_query_hca_vport_system_image_guid(mdev, &tmp); - mdev->sys_image_guid = tmp; + mdev->sys_image_guid = err ? 0 : tmp; - return tmp; + return mdev->sys_image_guid; } EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid); diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h index 7654841a05c2..e6475ea77cd1 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h @@ -19,7 +19,7 @@ struct mlxfw_dev { static inline struct device *mlxfw_dev_dev(struct mlxfw_dev *mlxfw_dev) { - return mlxfw_dev->devlink->dev; + return devlink_to_dev(mlxfw_dev->devlink); } #define MLXFW_PRFX "mlxfw: " diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 9e831e8b607a..3fd3812b8f31 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -2008,10 +2008,9 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, } if (!reload) { + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); - devlink_reload_enable(devlink); } - return 0; err_driver_init: @@ -2075,10 +2074,9 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); - if (!reload) { - devlink_reload_disable(devlink); + if (!reload) devlink_unregister(devlink); - } + if (devlink_is_reload_failed(devlink)) { if (!reload) /* Only the parts that were not de-initialized in the diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index 0998dcc9cac0..b29824448aa8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -24,16 +24,8 @@ #define MLXSW_THERMAL_ZONE_MAX_NAME 16 #define MLXSW_THERMAL_TEMP_SCORE_MAX GENMASK(31, 0) #define MLXSW_THERMAL_MAX_STATE 10 +#define MLXSW_THERMAL_MIN_STATE 2 #define MLXSW_THERMAL_MAX_DUTY 255 -/* Minimum and maximum fan allowed speed in percent: from 20% to 100%. Values - * MLXSW_THERMAL_MAX_STATE + x, where x is between 2 and 10 are used for - * setting fan speed dynamic minimum. For example, if value is set to 14 (40%) - * cooling levels vector will be set to 4, 4, 4, 4, 4, 5, 6, 7, 8, 9, 10 to - * introduce PWM speed in percent: 40, 40, 40, 40, 40, 50, 60. 70, 80, 90, 100. - */ -#define MLXSW_THERMAL_SPEED_MIN (MLXSW_THERMAL_MAX_STATE + 2) -#define MLXSW_THERMAL_SPEED_MAX (MLXSW_THERMAL_MAX_STATE * 2) -#define MLXSW_THERMAL_SPEED_MIN_LEVEL 2 /* 20% */ /* External cooling devices, allowed for binding to mlxsw thermal zones. */ static char * const mlxsw_thermal_external_allowed_cdev[] = { @@ -646,49 +638,16 @@ static int mlxsw_thermal_set_cur_state(struct thermal_cooling_device *cdev, struct mlxsw_thermal *thermal = cdev->devdata; struct device *dev = thermal->bus_info->dev; char mfsc_pl[MLXSW_REG_MFSC_LEN]; - unsigned long cur_state, i; int idx; - u8 duty; int err; + if (state > MLXSW_THERMAL_MAX_STATE) + return -EINVAL; + idx = mlxsw_get_cooling_device_idx(thermal, cdev); if (idx < 0) return idx; - /* Verify if this request is for changing allowed fan dynamical - * minimum. If it is - update cooling levels accordingly and update - * state, if current state is below the newly requested minimum state. - * For example, if current state is 5, and minimal state is to be - * changed from 4 to 6, thermal->cooling_levels[0 to 5] will be changed - * all from 4 to 6. And state 5 (thermal->cooling_levels[4]) should be - * overwritten. - */ - if (state >= MLXSW_THERMAL_SPEED_MIN && - state <= MLXSW_THERMAL_SPEED_MAX) { - state -= MLXSW_THERMAL_MAX_STATE; - for (i = 0; i <= MLXSW_THERMAL_MAX_STATE; i++) - thermal->cooling_levels[i] = max(state, i); - - mlxsw_reg_mfsc_pack(mfsc_pl, idx, 0); - err = mlxsw_reg_query(thermal->core, MLXSW_REG(mfsc), mfsc_pl); - if (err) - return err; - - duty = mlxsw_reg_mfsc_pwm_duty_cycle_get(mfsc_pl); - cur_state = mlxsw_duty_to_state(duty); - - /* If current fan state is lower than requested dynamical - * minimum, increase fan speed up to dynamical minimum. - */ - if (state < cur_state) - return 0; - - state = cur_state; - } - - if (state > MLXSW_THERMAL_MAX_STATE) - return -EINVAL; - /* Normalize the state to the valid speed range. */ state = thermal->cooling_levels[state]; mlxsw_reg_mfsc_pack(mfsc_pl, idx, mlxsw_state_to_duty(state)); @@ -998,8 +957,7 @@ int mlxsw_thermal_init(struct mlxsw_core *core, /* Initialize cooling levels per PWM state. */ for (i = 0; i < MLXSW_THERMAL_MAX_STATE; i++) - thermal->cooling_levels[i] = max(MLXSW_THERMAL_SPEED_MIN_LEVEL, - i); + thermal->cooling_levels[i] = max(MLXSW_THERMAL_MIN_STATE, i); thermal->polling_delay = bus_info->low_frequency ? MLXSW_THERMAL_SLOW_POLL_INT : diff --git a/drivers/net/ethernet/mellanox/mlxsw/item.h b/drivers/net/ethernet/mellanox/mlxsw/item.h index e92cadc98128..ab70a873a01a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/item.h +++ b/drivers/net/ethernet/mellanox/mlxsw/item.h @@ -270,11 +270,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u8 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u8 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get8(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u8 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u8 val) \ { \ __mlxsw_item_set8(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -290,13 +292,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u8 \ +static inline u8 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get8(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u8 val) \ { \ @@ -311,11 +313,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u16 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u16 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get16(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u16 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u16 val) \ { \ __mlxsw_item_set16(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -331,13 +335,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u16 \ +static inline u16 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get16(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u16 val) \ { \ @@ -352,11 +356,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u32 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u32 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get32(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u32 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u32 val) \ { \ __mlxsw_item_set32(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -372,13 +378,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u32 \ +static inline u32 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get32(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u32 val) \ { \ @@ -393,11 +399,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u64 mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ +static inline u64 __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf) \ { \ return __mlxsw_item_get64(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u64 val)\ +static inline void __maybe_unused \ +mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u64 val) \ { \ __mlxsw_item_set64(buf, &__ITEM_NAME(_type, _cname, _iname), 0, val); \ } @@ -413,13 +421,13 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bits = _sizebits,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u64 \ +static inline u64 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, unsigned short index)\ { \ return __mlxsw_item_get64(buf, &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, unsigned short index, \ u64 val) \ { \ @@ -433,19 +441,19 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bytes = _sizebytes,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(const char *buf, char *dst) \ { \ __mlxsw_item_memcpy_from(buf, dst, \ &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, const char *src) \ { \ __mlxsw_item_memcpy_to(buf, src, \ &__ITEM_NAME(_type, _cname, _iname), 0); \ } \ -static inline char * \ +static inline char * __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_data(char *buf) \ { \ return __mlxsw_item_data(buf, &__ITEM_NAME(_type, _cname, _iname), 0); \ @@ -460,7 +468,7 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bytes = _sizebytes,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(const char *buf, \ unsigned short index, \ char *dst) \ @@ -468,7 +476,7 @@ mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(const char *buf, \ __mlxsw_item_memcpy_from(buf, dst, \ &__ITEM_NAME(_type, _cname, _iname), index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, \ unsigned short index, \ const char *src) \ @@ -476,7 +484,7 @@ mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, \ __mlxsw_item_memcpy_to(buf, src, \ &__ITEM_NAME(_type, _cname, _iname), index); \ } \ -static inline char * \ +static inline char * __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_data(char *buf, unsigned short index) \ { \ return __mlxsw_item_data(buf, \ @@ -491,14 +499,14 @@ static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \ .size = {.bytes = _sizebytes,}, \ .name = #_type "_" #_cname "_" #_iname, \ }; \ -static inline u8 \ +static inline u8 __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_get(const char *buf, u16 index) \ { \ return __mlxsw_item_bit_array_get(buf, \ &__ITEM_NAME(_type, _cname, _iname), \ index); \ } \ -static inline void \ +static inline void __maybe_unused \ mlxsw_##_type##_##_cname##_##_iname##_set(char *buf, u16 index, u8 val) \ { \ return __mlxsw_item_bit_array_set(buf, \ diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index ed6c3356e4eb..48b817ba6d4e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -4951,7 +4951,7 @@ enum mlxsw_reg_ppcnt_grp { MLXSW_REG_PPCNT_DISCARD_CNT = 0x6, MLXSW_REG_PPCNT_PRIO_CNT = 0x10, MLXSW_REG_PPCNT_TC_CNT = 0x11, - MLXSW_REG_PPCNT_TC_CONG_TC = 0x13, + MLXSW_REG_PPCNT_TC_CONG_CNT = 0x13, }; /* reg_ppcnt_grp @@ -5371,7 +5371,7 @@ MLXSW_ITEM64(reg, ppcnt, tx_pause_duration, MLXSW_ITEM64(reg, ppcnt, tx_pause_transition, MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64); -/* Ethernet Per Traffic Group Counters */ +/* Ethernet Per Traffic Class Counters */ /* reg_ppcnt_tc_transmit_queue * Contains the transmit queue depth in cells of traffic class @@ -5398,6 +5398,12 @@ MLXSW_ITEM64(reg, ppcnt, tc_no_buffer_discard_uc, MLXSW_ITEM64(reg, ppcnt, wred_discard, MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x00, 0, 64); +/* reg_ppcnt_ecn_marked_tc + * Access: RO + */ +MLXSW_ITEM64(reg, ppcnt, ecn_marked_tc, + MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x08, 0, 64); + static inline void mlxsw_reg_ppcnt_pack(char *payload, u8 local_port, enum mlxsw_reg_ppcnt_grp grp, u8 prio_tc) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index d366786ce0f8..d05850ff3a77 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -824,12 +824,16 @@ mlxsw_sp_port_get_hw_xstats(struct net_device *dev, for (i = 0; i < TC_MAX_QUEUE; i++) { err = mlxsw_sp_port_get_stats_raw(dev, - MLXSW_REG_PPCNT_TC_CONG_TC, + MLXSW_REG_PPCNT_TC_CONG_CNT, i, ppcnt_pl); - if (!err) - xstats->wred_drop[i] = - mlxsw_reg_ppcnt_wred_discard_get(ppcnt_pl); + if (err) + goto tc_cnt; + + xstats->wred_drop[i] = + mlxsw_reg_ppcnt_wred_discard_get(ppcnt_pl); + xstats->tc_ecn[i] = mlxsw_reg_ppcnt_ecn_marked_tc_get(ppcnt_pl); +tc_cnt: err = mlxsw_sp_port_get_stats_raw(dev, MLXSW_REG_PPCNT_TC_CNT, i, ppcnt_pl); if (err) @@ -1035,6 +1039,8 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_sp_setup_tc_block_clsact(mlxsw_sp_port, f, false); case FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP: return mlxsw_sp_setup_tc_block_qevent_early_drop(mlxsw_sp_port, f); + case FLOW_BLOCK_BINDER_TYPE_RED_MARK: + return mlxsw_sp_setup_tc_block_qevent_mark(mlxsw_sp_port, f); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 0ebbd9b04b89..3ab57e98cad2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -285,6 +285,7 @@ struct mlxsw_sp_port_vlan { /* No need an internal lock; At worse - miss a single periodic iteration */ struct mlxsw_sp_port_xstats { u64 ecn; + u64 tc_ecn[TC_MAX_QUEUE]; u64 wred_drop[TC_MAX_QUEUE]; u64 tail_drop[TC_MAX_QUEUE]; u64 backlog[TC_MAX_QUEUE]; @@ -1195,6 +1196,8 @@ int mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_fifo_qopt_offload *p); int mlxsw_sp_setup_tc_block_qevent_early_drop(struct mlxsw_sp_port *mlxsw_sp_port, struct flow_block_offload *f); +int mlxsw_sp_setup_tc_block_qevent_mark(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f); /* spectrum_fid.c */ bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index 9958d503bf0e..6d1431fa31d7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -519,6 +519,7 @@ mlxsw_sp_setup_tc_qdisc_red_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_qdisc->prio_bitmap, &stats_base->tx_packets, &stats_base->tx_bytes); + red_base->prob_mark = xstats->tc_ecn[tclass_num]; red_base->prob_drop = xstats->wred_drop[tclass_num]; red_base->pdrop = mlxsw_sp_xstats_tail_drop(xstats, tclass_num); @@ -618,19 +619,22 @@ mlxsw_sp_qdisc_get_red_xstats(struct mlxsw_sp_port *mlxsw_sp_port, int tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_port_xstats *xstats; struct red_stats *res = xstats_ptr; - int early_drops, pdrops; + int early_drops, marks, pdrops; xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; early_drops = xstats->wred_drop[tclass_num] - xstats_base->prob_drop; + marks = xstats->tc_ecn[tclass_num] - xstats_base->prob_mark; pdrops = mlxsw_sp_xstats_tail_drop(xstats, tclass_num) - xstats_base->pdrop; res->pdrop += pdrops; res->prob_drop += early_drops; + res->prob_mark += marks; xstats_base->pdrop += pdrops; xstats_base->prob_drop += early_drops; + xstats_base->prob_mark += marks; return 0; } @@ -648,7 +652,8 @@ mlxsw_sp_qdisc_get_red_stats(struct mlxsw_sp_port *mlxsw_sp_port, stats_base = &mlxsw_sp_qdisc->stats_base; mlxsw_sp_qdisc_get_tc_stats(mlxsw_sp_port, mlxsw_sp_qdisc, stats_ptr); - overlimits = xstats->wred_drop[tclass_num] - stats_base->overlimits; + overlimits = xstats->wred_drop[tclass_num] + + xstats->tc_ecn[tclass_num] - stats_base->overlimits; stats_ptr->qstats->overlimits += overlimits; stats_base->overlimits += overlimits; @@ -1472,6 +1477,7 @@ struct mlxsw_sp_qevent_binding { u32 handle; int tclass_num; enum mlxsw_sp_span_trigger span_trigger; + unsigned int action_mask; }; static LIST_HEAD(mlxsw_sp_qevent_block_cb_list); @@ -1482,8 +1488,10 @@ static int mlxsw_sp_qevent_span_configure(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_span_agent_parms *agent_parms, int *p_span_id) { + enum mlxsw_sp_span_trigger span_trigger = qevent_binding->span_trigger; struct mlxsw_sp_port *mlxsw_sp_port = qevent_binding->mlxsw_sp_port; struct mlxsw_sp_span_trigger_parms trigger_parms = {}; + bool ingress; int span_id; int err; @@ -1491,18 +1499,19 @@ static int mlxsw_sp_qevent_span_configure(struct mlxsw_sp *mlxsw_sp, if (err) return err; - err = mlxsw_sp_span_analyzed_port_get(mlxsw_sp_port, true); + ingress = mlxsw_sp_span_trigger_is_ingress(span_trigger); + err = mlxsw_sp_span_analyzed_port_get(mlxsw_sp_port, ingress); if (err) goto err_analyzed_port_get; trigger_parms.span_id = span_id; trigger_parms.probability_rate = 1; - err = mlxsw_sp_span_agent_bind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + err = mlxsw_sp_span_agent_bind(mlxsw_sp, span_trigger, mlxsw_sp_port, &trigger_parms); if (err) goto err_agent_bind; - err = mlxsw_sp_span_trigger_enable(mlxsw_sp_port, qevent_binding->span_trigger, + err = mlxsw_sp_span_trigger_enable(mlxsw_sp_port, span_trigger, qevent_binding->tclass_num); if (err) goto err_trigger_enable; @@ -1511,10 +1520,10 @@ static int mlxsw_sp_qevent_span_configure(struct mlxsw_sp *mlxsw_sp, return 0; err_trigger_enable: - mlxsw_sp_span_agent_unbind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + mlxsw_sp_span_agent_unbind(mlxsw_sp, span_trigger, mlxsw_sp_port, &trigger_parms); err_agent_bind: - mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, true); + mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, ingress); err_analyzed_port_get: mlxsw_sp_span_agent_put(mlxsw_sp, span_id); return err; @@ -1524,16 +1533,20 @@ static void mlxsw_sp_qevent_span_deconfigure(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_qevent_binding *qevent_binding, int span_id) { + enum mlxsw_sp_span_trigger span_trigger = qevent_binding->span_trigger; struct mlxsw_sp_port *mlxsw_sp_port = qevent_binding->mlxsw_sp_port; struct mlxsw_sp_span_trigger_parms trigger_parms = { .span_id = span_id, }; + bool ingress; - mlxsw_sp_span_trigger_disable(mlxsw_sp_port, qevent_binding->span_trigger, + ingress = mlxsw_sp_span_trigger_is_ingress(span_trigger); + + mlxsw_sp_span_trigger_disable(mlxsw_sp_port, span_trigger, qevent_binding->tclass_num); - mlxsw_sp_span_agent_unbind(mlxsw_sp, qevent_binding->span_trigger, mlxsw_sp_port, + mlxsw_sp_span_agent_unbind(mlxsw_sp, span_trigger, mlxsw_sp_port, &trigger_parms); - mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, true); + mlxsw_sp_span_analyzed_port_put(mlxsw_sp_port, ingress); mlxsw_sp_span_agent_put(mlxsw_sp, span_id); } @@ -1583,10 +1596,17 @@ static void mlxsw_sp_qevent_trap_deconfigure(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_qevent_span_deconfigure(mlxsw_sp, qevent_binding, mall_entry->trap.span_id); } -static int mlxsw_sp_qevent_entry_configure(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_mall_entry *mall_entry, - struct mlxsw_sp_qevent_binding *qevent_binding) +static int +mlxsw_sp_qevent_entry_configure(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mall_entry *mall_entry, + struct mlxsw_sp_qevent_binding *qevent_binding, + struct netlink_ext_ack *extack) { + if (!(BIT(mall_entry->type) & qevent_binding->action_mask)) { + NL_SET_ERR_MSG(extack, "Action not supported at this qevent"); + return -EOPNOTSUPP; + } + switch (mall_entry->type) { case MLXSW_SP_MALL_ACTION_TYPE_MIRROR: return mlxsw_sp_qevent_mirror_configure(mlxsw_sp, mall_entry, qevent_binding); @@ -1614,15 +1634,17 @@ static void mlxsw_sp_qevent_entry_deconfigure(struct mlxsw_sp *mlxsw_sp, } } -static int mlxsw_sp_qevent_binding_configure(struct mlxsw_sp_qevent_block *qevent_block, - struct mlxsw_sp_qevent_binding *qevent_binding) +static int +mlxsw_sp_qevent_binding_configure(struct mlxsw_sp_qevent_block *qevent_block, + struct mlxsw_sp_qevent_binding *qevent_binding, + struct netlink_ext_ack *extack) { struct mlxsw_sp_mall_entry *mall_entry; int err; list_for_each_entry(mall_entry, &qevent_block->mall_entry_list, list) { err = mlxsw_sp_qevent_entry_configure(qevent_block->mlxsw_sp, mall_entry, - qevent_binding); + qevent_binding, extack); if (err) goto err_entry_configure; } @@ -1646,13 +1668,17 @@ static void mlxsw_sp_qevent_binding_deconfigure(struct mlxsw_sp_qevent_block *qe qevent_binding); } -static int mlxsw_sp_qevent_block_configure(struct mlxsw_sp_qevent_block *qevent_block) +static int +mlxsw_sp_qevent_block_configure(struct mlxsw_sp_qevent_block *qevent_block, + struct netlink_ext_ack *extack) { struct mlxsw_sp_qevent_binding *qevent_binding; int err; list_for_each_entry(qevent_binding, &qevent_block->binding_list, list) { - err = mlxsw_sp_qevent_binding_configure(qevent_block, qevent_binding); + err = mlxsw_sp_qevent_binding_configure(qevent_block, + qevent_binding, + extack); if (err) goto err_binding_configure; } @@ -1737,7 +1763,7 @@ static int mlxsw_sp_qevent_mall_replace(struct mlxsw_sp *mlxsw_sp, list_add_tail(&mall_entry->list, &qevent_block->mall_entry_list); - err = mlxsw_sp_qevent_block_configure(qevent_block); + err = mlxsw_sp_qevent_block_configure(qevent_block, f->common.extack); if (err) goto err_block_configure; @@ -1825,7 +1851,8 @@ static void mlxsw_sp_qevent_block_release(void *cb_priv) static struct mlxsw_sp_qevent_binding * mlxsw_sp_qevent_binding_create(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, int tclass_num, - enum mlxsw_sp_span_trigger span_trigger) + enum mlxsw_sp_span_trigger span_trigger, + unsigned int action_mask) { struct mlxsw_sp_qevent_binding *binding; @@ -1837,6 +1864,7 @@ mlxsw_sp_qevent_binding_create(struct mlxsw_sp_port *mlxsw_sp_port, u32 handle, binding->handle = handle; binding->tclass_num = tclass_num; binding->span_trigger = span_trigger; + binding->action_mask = action_mask; return binding; } @@ -1862,9 +1890,11 @@ mlxsw_sp_qevent_binding_lookup(struct mlxsw_sp_qevent_block *block, return NULL; } -static int mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_port, - struct flow_block_offload *f, - enum mlxsw_sp_span_trigger span_trigger) +static int +mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f, + enum mlxsw_sp_span_trigger span_trigger, + unsigned int action_mask) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_qevent_binding *qevent_binding; @@ -1904,14 +1934,18 @@ static int mlxsw_sp_setup_tc_block_qevent_bind(struct mlxsw_sp_port *mlxsw_sp_po goto err_binding_exists; } - qevent_binding = mlxsw_sp_qevent_binding_create(mlxsw_sp_port, f->sch->handle, - qdisc->tclass_num, span_trigger); + qevent_binding = mlxsw_sp_qevent_binding_create(mlxsw_sp_port, + f->sch->handle, + qdisc->tclass_num, + span_trigger, + action_mask); if (IS_ERR(qevent_binding)) { err = PTR_ERR(qevent_binding); goto err_binding_create; } - err = mlxsw_sp_qevent_binding_configure(qevent_block, qevent_binding); + err = mlxsw_sp_qevent_binding_configure(qevent_block, qevent_binding, + f->extack); if (err) goto err_binding_configure; @@ -1963,15 +1997,19 @@ static void mlxsw_sp_setup_tc_block_qevent_unbind(struct mlxsw_sp_port *mlxsw_sp } } -static int mlxsw_sp_setup_tc_block_qevent(struct mlxsw_sp_port *mlxsw_sp_port, - struct flow_block_offload *f, - enum mlxsw_sp_span_trigger span_trigger) +static int +mlxsw_sp_setup_tc_block_qevent(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f, + enum mlxsw_sp_span_trigger span_trigger, + unsigned int action_mask) { f->driver_block_list = &mlxsw_sp_qevent_block_cb_list; switch (f->command) { case FLOW_BLOCK_BIND: - return mlxsw_sp_setup_tc_block_qevent_bind(mlxsw_sp_port, f, span_trigger); + return mlxsw_sp_setup_tc_block_qevent_bind(mlxsw_sp_port, f, + span_trigger, + action_mask); case FLOW_BLOCK_UNBIND: mlxsw_sp_setup_tc_block_qevent_unbind(mlxsw_sp_port, f, span_trigger); return 0; @@ -1983,7 +2021,22 @@ static int mlxsw_sp_setup_tc_block_qevent(struct mlxsw_sp_port *mlxsw_sp_port, int mlxsw_sp_setup_tc_block_qevent_early_drop(struct mlxsw_sp_port *mlxsw_sp_port, struct flow_block_offload *f) { - return mlxsw_sp_setup_tc_block_qevent(mlxsw_sp_port, f, MLXSW_SP_SPAN_TRIGGER_EARLY_DROP); + unsigned int action_mask = BIT(MLXSW_SP_MALL_ACTION_TYPE_MIRROR) | + BIT(MLXSW_SP_MALL_ACTION_TYPE_TRAP); + + return mlxsw_sp_setup_tc_block_qevent(mlxsw_sp_port, f, + MLXSW_SP_SPAN_TRIGGER_EARLY_DROP, + action_mask); +} + +int mlxsw_sp_setup_tc_block_qevent_mark(struct mlxsw_sp_port *mlxsw_sp_port, + struct flow_block_offload *f) +{ + unsigned int action_mask = BIT(MLXSW_SP_MALL_ACTION_TYPE_MIRROR); + + return mlxsw_sp_setup_tc_block_qevent(mlxsw_sp_port, f, + MLXSW_SP_SPAN_TRIGGER_ECN, + action_mask); } int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 3398cc01e5ec..f5f819aa9a65 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -1650,6 +1650,22 @@ void mlxsw_sp_span_trigger_disable(struct mlxsw_sp_port *mlxsw_sp_port, return trigger_entry->ops->disable(trigger_entry, mlxsw_sp_port, tc); } +bool mlxsw_sp_span_trigger_is_ingress(enum mlxsw_sp_span_trigger trigger) +{ + switch (trigger) { + case MLXSW_SP_SPAN_TRIGGER_INGRESS: + case MLXSW_SP_SPAN_TRIGGER_EARLY_DROP: + case MLXSW_SP_SPAN_TRIGGER_TAIL_DROP: + return true; + case MLXSW_SP_SPAN_TRIGGER_EGRESS: + case MLXSW_SP_SPAN_TRIGGER_ECN: + return false; + } + + WARN_ON_ONCE(1); + return false; +} + static int mlxsw_sp1_span_init(struct mlxsw_sp *mlxsw_sp) { size_t arr_size = ARRAY_SIZE(mlxsw_sp1_span_entry_ops_arr); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h index efaefd1ae863..82e711afb02b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h @@ -120,6 +120,7 @@ int mlxsw_sp_span_trigger_enable(struct mlxsw_sp_port *mlxsw_sp_port, enum mlxsw_sp_span_trigger trigger, u8 tc); void mlxsw_sp_span_trigger_disable(struct mlxsw_sp_port *mlxsw_sp_port, enum mlxsw_sp_span_trigger trigger, u8 tc); +bool mlxsw_sp_span_trigger_is_ingress(enum mlxsw_sp_span_trigger trigger); extern const struct mlxsw_sp_span_ops mlxsw_sp1_span_ops; extern const struct mlxsw_sp_span_ops mlxsw_sp2_span_ops; diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c index 37ccf8c570b5..c11b118dc415 100644 --- a/drivers/net/ethernet/micrel/ks8842.c +++ b/drivers/net/ethernet/micrel/ks8842.c @@ -348,13 +348,15 @@ static void ks8842_reset_hw(struct ks8842_adapter *adapter) ks8842_write16(adapter, 32, 0x1, REG_SW_ID_AND_ENABLE); } -static void ks8842_read_mac_addr(struct ks8842_adapter *adapter, u8 *dest) +static void ks8842_init_mac_addr(struct ks8842_adapter *adapter) { + u8 addr[ETH_ALEN]; int i; u16 mac; for (i = 0; i < ETH_ALEN; i++) - dest[ETH_ALEN - i - 1] = ks8842_read8(adapter, 2, REG_MARL + i); + addr[ETH_ALEN - i - 1] = ks8842_read8(adapter, 2, REG_MARL + i); + eth_hw_addr_set(adapter->netdev, addr); if (adapter->conf_flags & MICREL_KS884X) { /* @@ -380,7 +382,7 @@ static void ks8842_read_mac_addr(struct ks8842_adapter *adapter, u8 *dest) } } -static void ks8842_write_mac_addr(struct ks8842_adapter *adapter, u8 *mac) +static void ks8842_write_mac_addr(struct ks8842_adapter *adapter, const u8 *mac) { unsigned long flags; unsigned i; @@ -1195,7 +1197,7 @@ static int ks8842_probe(struct platform_device *pdev) } if (i == netdev->addr_len) { - ks8842_read_mac_addr(adapter, netdev->dev_addr); + ks8842_init_mac_addr(adapter); if (!is_valid_ether_addr(netdev->dev_addr)) eth_hw_addr_random(netdev); diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h index e2eb0caeac82..6f34a61739b6 100644 --- a/drivers/net/ethernet/micrel/ks8851.h +++ b/drivers/net/ethernet/micrel/ks8851.h @@ -427,7 +427,7 @@ struct ks8851_net { int ks8851_probe_common(struct net_device *netdev, struct device *dev, int msg_en); -int ks8851_remove_common(struct device *dev); +void ks8851_remove_common(struct device *dev); int ks8851_suspend(struct device *dev); int ks8851_resume(struct device *dev); diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 2c4e5e602be7..691206f19ea7 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -165,6 +165,7 @@ static void ks8851_read_mac_addr(struct net_device *dev) { struct ks8851_net *ks = netdev_priv(dev); unsigned long flags; + u8 addr[ETH_ALEN]; u16 reg; int i; @@ -172,9 +173,10 @@ static void ks8851_read_mac_addr(struct net_device *dev) for (i = 0; i < ETH_ALEN; i += 2) { reg = ks8851_rdreg16(ks, KS_MAR(i)); - dev->dev_addr[i] = reg >> 8; - dev->dev_addr[i + 1] = reg & 0xff; + addr[i] = reg >> 8; + addr[i + 1] = reg & 0xff; } + eth_hw_addr_set(dev, addr); ks8851_unlock(ks, &flags); } @@ -1247,7 +1249,7 @@ err_reg_io: } EXPORT_SYMBOL_GPL(ks8851_probe_common); -int ks8851_remove_common(struct device *dev) +void ks8851_remove_common(struct device *dev) { struct ks8851_net *priv = dev_get_drvdata(dev); @@ -1261,8 +1263,6 @@ int ks8851_remove_common(struct device *dev) gpio_set_value(priv->gpio, 0); regulator_disable(priv->vdd_reg); regulator_disable(priv->vdd_io); - - return 0; } EXPORT_SYMBOL_GPL(ks8851_remove_common); diff --git a/drivers/net/ethernet/micrel/ks8851_par.c b/drivers/net/ethernet/micrel/ks8851_par.c index 2e8fcce50f9d..2e25798c610e 100644 --- a/drivers/net/ethernet/micrel/ks8851_par.c +++ b/drivers/net/ethernet/micrel/ks8851_par.c @@ -327,7 +327,9 @@ static int ks8851_probe_par(struct platform_device *pdev) static int ks8851_remove_par(struct platform_device *pdev) { - return ks8851_remove_common(&pdev->dev); + ks8851_remove_common(&pdev->dev); + + return 0; } static const struct of_device_id ks8851_match_table[] = { diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c index 479406ecbaa3..0303e727e99f 100644 --- a/drivers/net/ethernet/micrel/ks8851_spi.c +++ b/drivers/net/ethernet/micrel/ks8851_spi.c @@ -454,7 +454,9 @@ static int ks8851_probe_spi(struct spi_device *spi) static int ks8851_remove_spi(struct spi_device *spi) { - return ks8851_remove_common(&spi->dev); + ks8851_remove_common(&spi->dev); + + return 0; } static const struct of_device_id ks8851_match_table[] = { diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index a1f7f45b9d08..99c0c1491af2 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -4033,7 +4033,7 @@ static void hw_set_add_addr(struct ksz_hw *hw) } } -static int hw_add_addr(struct ksz_hw *hw, u8 *mac_addr) +static int hw_add_addr(struct ksz_hw *hw, const u8 *mac_addr) { int i; int j = ADDITIONAL_ENTRIES; @@ -4054,7 +4054,7 @@ static int hw_add_addr(struct ksz_hw *hw, u8 *mac_addr) return -1; } -static int hw_del_addr(struct ksz_hw *hw, u8 *mac_addr) +static int hw_del_addr(struct ksz_hw *hw, const u8 *mac_addr) { int i; @@ -7007,9 +7007,12 @@ static int pcidev_init(struct pci_dev *pdev, const struct pci_device_id *id) if (MAIN_PORT == i) eth_hw_addr_set(dev, hw_priv->hw.override_addr); else { - eth_hw_addr_set(dev, sw->other_addr); + u8 addr[ETH_ALEN]; + + ether_addr_copy(addr, sw->other_addr); if (ether_addr_equal(sw->other_addr, hw->override_addr)) - dev->dev_addr[5] += port->first_port; + addr[5] += port->first_port; + eth_hw_addr_set(dev, addr); } dev->netdev_ops = &netdev_ops; diff --git a/drivers/net/ethernet/microchip/encx24j600-regmap.c b/drivers/net/ethernet/microchip/encx24j600-regmap.c index 796e46a53926..81a8ccca7e5e 100644 --- a/drivers/net/ethernet/microchip/encx24j600-regmap.c +++ b/drivers/net/ethernet/microchip/encx24j600-regmap.c @@ -497,13 +497,19 @@ static struct regmap_bus phymap_encx24j600 = { .reg_read = regmap_encx24j600_phy_reg_read, }; -void devm_regmap_init_encx24j600(struct device *dev, - struct encx24j600_context *ctx) +int devm_regmap_init_encx24j600(struct device *dev, + struct encx24j600_context *ctx) { mutex_init(&ctx->mutex); regcfg.lock_arg = ctx; ctx->regmap = devm_regmap_init(dev, ®map_encx24j600, ctx, ®cfg); + if (IS_ERR(ctx->regmap)) + return PTR_ERR(ctx->regmap); ctx->phymap = devm_regmap_init(dev, &phymap_encx24j600, ctx, &phycfg); + if (IS_ERR(ctx->phymap)) + return PTR_ERR(ctx->phymap); + + return 0; } EXPORT_SYMBOL_GPL(devm_regmap_init_encx24j600); diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index d4680113e249..b90efc80fb59 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -1001,6 +1001,7 @@ static int encx24j600_spi_probe(struct spi_device *spi) struct net_device *ndev; struct encx24j600_priv *priv; u16 eidled; + u8 addr[ETH_ALEN]; ndev = alloc_etherdev(sizeof(struct encx24j600_priv)); @@ -1023,10 +1024,13 @@ static int encx24j600_spi_probe(struct spi_device *spi) priv->speed = SPEED_100; priv->ctx.spi = spi; - devm_regmap_init_encx24j600(&spi->dev, &priv->ctx); ndev->irq = spi->irq; ndev->netdev_ops = &encx24j600_netdev_ops; + ret = devm_regmap_init_encx24j600(&spi->dev, &priv->ctx); + if (ret) + goto out_free; + mutex_init(&priv->lock); /* Reset device and check if it is connected */ @@ -1053,7 +1057,8 @@ static int encx24j600_spi_probe(struct spi_device *spi) } /* Get the MAC address from the chip */ - encx24j600_hw_get_macaddr(priv, ndev->dev_addr); + encx24j600_hw_get_macaddr(priv, addr); + eth_hw_addr_set(ndev, addr); ndev->ethtool_ops = &encx24j600_ethtool_ops; diff --git a/drivers/net/ethernet/microchip/encx24j600_hw.h b/drivers/net/ethernet/microchip/encx24j600_hw.h index fac61a8fbd02..34c5a289898c 100644 --- a/drivers/net/ethernet/microchip/encx24j600_hw.h +++ b/drivers/net/ethernet/microchip/encx24j600_hw.h @@ -15,8 +15,8 @@ struct encx24j600_context { int bank; }; -void devm_regmap_init_encx24j600(struct device *dev, - struct encx24j600_context *ctx); +int devm_regmap_init_encx24j600(struct device *dev, + struct encx24j600_context *ctx); /* Single-byte instructions */ #define BANK_SELECT(bank) (0xC0 | ((bank & (BANK_MASK >> BANK_SHIFT)) << 1)) diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 6080028c1df2..34c22eea0124 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -279,6 +279,7 @@ #define PTP_GENERAL_CONFIG_CLOCK_EVENT_1MS_ (3) #define PTP_GENERAL_CONFIG_CLOCK_EVENT_10MS_ (4) #define PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_ (5) +#define PTP_GENERAL_CONFIG_CLOCK_EVENT_TOGGLE_ (6) #define PTP_GENERAL_CONFIG_CLOCK_EVENT_X_SET_(channel, value) \ (((value) & 0x7) << (1 + ((channel) << 2))) #define PTP_GENERAL_CONFIG_RELOAD_ADD_X_(channel) (BIT((channel) << 2)) diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c index ab6d719d40f0..9380e396f648 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.c +++ b/drivers/net/ethernet/microchip/lan743x_ptp.c @@ -491,9 +491,10 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, int perout_pin = 0; unsigned int index = perout_request->index; struct lan743x_ptp_perout *perout = &ptp->perout[index]; + int ret = 0; /* Reject requests with unsupported flags */ - if (perout_request->flags) + if (perout_request->flags & ~PTP_PEROUT_DUTY_CYCLE) return -EOPNOTSUPP; if (on) { @@ -518,6 +519,7 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, netif_warn(adapter, drv, adapter->netdev, "Failed to reserve event channel %d for PEROUT\n", index); + ret = -EBUSY; goto failed; } @@ -529,6 +531,7 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, netif_warn(adapter, drv, adapter->netdev, "Failed to reserve gpio %d for PEROUT\n", perout_pin); + ret = -EBUSY; goto failed; } @@ -540,27 +543,93 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, period_sec += perout_request->period.nsec / 1000000000; period_nsec = perout_request->period.nsec % 1000000000; - if (period_sec == 0) { - if (period_nsec >= 400000000) { + if (perout_request->flags & PTP_PEROUT_DUTY_CYCLE) { + struct timespec64 ts_on, ts_period; + s64 wf_high, period64, half; + s32 reminder; + + ts_on.tv_sec = perout_request->on.sec; + ts_on.tv_nsec = perout_request->on.nsec; + wf_high = timespec64_to_ns(&ts_on); + ts_period.tv_sec = perout_request->period.sec; + ts_period.tv_nsec = perout_request->period.nsec; + period64 = timespec64_to_ns(&ts_period); + + if (period64 < 200) { + netif_warn(adapter, drv, adapter->netdev, + "perout period too small, minimum is 200nS\n"); + ret = -EOPNOTSUPP; + goto failed; + } + if (wf_high >= period64) { + netif_warn(adapter, drv, adapter->netdev, + "pulse width must be smaller than period\n"); + ret = -EINVAL; + goto failed; + } + + /* Check if we can do 50% toggle on an even value of period. + * If the period number is odd, then check if the requested + * pulse width is the same as one of pre-defined width values. + * Otherwise, return failure. + */ + half = div_s64_rem(period64, 2, &reminder); + if (!reminder) { + if (half == wf_high) { + /* It's 50% match. Use the toggle option */ + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_TOGGLE_; + /* In this case, devide period value by 2 */ + ts_period = ns_to_timespec64(div_s64(period64, 2)); + period_sec = ts_period.tv_sec; + period_nsec = ts_period.tv_nsec; + + goto program; + } + } + /* if we can't do toggle, then the width option needs to be the exact match */ + if (wf_high == 200000000) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_; - } else if (period_nsec >= 20000000) { + } else if (wf_high == 10000000) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10MS_; - } else if (period_nsec >= 2000000) { + } else if (wf_high == 1000000) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_1MS_; - } else if (period_nsec >= 200000) { + } else if (wf_high == 100000) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100US_; - } else if (period_nsec >= 20000) { + } else if (wf_high == 10000) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10US_; - } else if (period_nsec >= 200) { + } else if (wf_high == 100) { pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100NS_; } else { netif_warn(adapter, drv, adapter->netdev, - "perout period too small, minimum is 200nS\n"); + "duty cycle specified is not supported\n"); + ret = -EOPNOTSUPP; goto failed; } } else { - pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_; + if (period_sec == 0) { + if (period_nsec >= 400000000) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_; + } else if (period_nsec >= 20000000) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10MS_; + } else if (period_nsec >= 2000000) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_1MS_; + } else if (period_nsec >= 200000) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100US_; + } else if (period_nsec >= 20000) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10US_; + } else if (period_nsec >= 200) { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100NS_; + } else { + netif_warn(adapter, drv, adapter->netdev, + "perout period too small, minimum is 200nS\n"); + ret = -EOPNOTSUPP; + goto failed; + } + } else { + pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_; + } } +program: /* turn off by setting target far in future */ lan743x_csr_write(adapter, @@ -599,7 +668,7 @@ static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on, failed: lan743x_ptp_perout_off(adapter, index); - return -ENODEV; + return ret; } static int lan743x_ptpci_enable(struct ptp_clock_info *ptpci, diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 9a871192ca96..d65697c239c8 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1477,8 +1477,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, if (err) goto out; - if (cq->gdma_id >= gc->max_num_cqs) + if (WARN_ON(cq->gdma_id >= gc->max_num_cqs)) { + err = -EINVAL; goto out; + } gc->cq_table[cq->gdma_id] = cq->gdma_cq; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 05c456dbdd72..520a75b57866 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -472,9 +472,9 @@ void ocelot_phylink_mac_link_down(struct ocelot *ocelot, int port, !(quirks & OCELOT_QUIRK_QSGMII_PORTS_MUST_BE_UP)) ocelot_port_rmwl(ocelot_port, DEV_CLOCK_CFG_MAC_TX_RST | - DEV_CLOCK_CFG_MAC_TX_RST, + DEV_CLOCK_CFG_MAC_RX_RST, DEV_CLOCK_CFG_MAC_TX_RST | - DEV_CLOCK_CFG_MAC_TX_RST, + DEV_CLOCK_CFG_MAC_RX_RST, DEV_CLOCK_CFG); } EXPORT_SYMBOL_GPL(ocelot_phylink_mac_link_down); @@ -569,49 +569,44 @@ void ocelot_phylink_mac_link_up(struct ocelot *ocelot, int port, } EXPORT_SYMBOL_GPL(ocelot_phylink_mac_link_up); -static void ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port, - struct sk_buff *clone) +static int ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port, + struct sk_buff *clone) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + unsigned long flags; + + spin_lock_irqsave(&ocelot->ts_id_lock, flags); - spin_lock(&ocelot_port->ts_id_lock); + if (ocelot_port->ptp_skbs_in_flight == OCELOT_MAX_PTP_ID || + ocelot->ptp_skbs_in_flight == OCELOT_PTP_FIFO_SIZE) { + spin_unlock_irqrestore(&ocelot->ts_id_lock, flags); + return -EBUSY; + } skb_shinfo(clone)->tx_flags |= SKBTX_IN_PROGRESS; /* Store timestamp ID in OCELOT_SKB_CB(clone)->ts_id */ OCELOT_SKB_CB(clone)->ts_id = ocelot_port->ts_id; - ocelot_port->ts_id = (ocelot_port->ts_id + 1) % 4; - skb_queue_tail(&ocelot_port->tx_skbs, clone); - spin_unlock(&ocelot_port->ts_id_lock); -} + ocelot_port->ts_id++; + if (ocelot_port->ts_id == OCELOT_MAX_PTP_ID) + ocelot_port->ts_id = 0; -u32 ocelot_ptp_rew_op(struct sk_buff *skb) -{ - struct sk_buff *clone = OCELOT_SKB_CB(skb)->clone; - u8 ptp_cmd = OCELOT_SKB_CB(skb)->ptp_cmd; - u32 rew_op = 0; + ocelot_port->ptp_skbs_in_flight++; + ocelot->ptp_skbs_in_flight++; - if (ptp_cmd == IFH_REW_OP_TWO_STEP_PTP && clone) { - rew_op = ptp_cmd; - rew_op |= OCELOT_SKB_CB(clone)->ts_id << 3; - } else if (ptp_cmd == IFH_REW_OP_ORIGIN_PTP) { - rew_op = ptp_cmd; - } + skb_queue_tail(&ocelot_port->tx_skbs, clone); - return rew_op; + spin_unlock_irqrestore(&ocelot->ts_id_lock, flags); + + return 0; } -EXPORT_SYMBOL(ocelot_ptp_rew_op); -static bool ocelot_ptp_is_onestep_sync(struct sk_buff *skb) +static bool ocelot_ptp_is_onestep_sync(struct sk_buff *skb, + unsigned int ptp_class) { struct ptp_header *hdr; - unsigned int ptp_class; u8 msgtype, twostep; - ptp_class = ptp_classify_raw(skb); - if (ptp_class == PTP_CLASS_NONE) - return false; - hdr = ptp_parse_header(skb, ptp_class); if (!hdr) return false; @@ -631,10 +626,20 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port, { struct ocelot_port *ocelot_port = ocelot->ports[port]; u8 ptp_cmd = ocelot_port->ptp_cmd; + unsigned int ptp_class; + int err; + + /* Don't do anything if PTP timestamping not enabled */ + if (!ptp_cmd) + return 0; + + ptp_class = ptp_classify_raw(skb); + if (ptp_class == PTP_CLASS_NONE) + return -EINVAL; /* Store ptp_cmd in OCELOT_SKB_CB(skb)->ptp_cmd */ if (ptp_cmd == IFH_REW_OP_ORIGIN_PTP) { - if (ocelot_ptp_is_onestep_sync(skb)) { + if (ocelot_ptp_is_onestep_sync(skb, ptp_class)) { OCELOT_SKB_CB(skb)->ptp_cmd = ptp_cmd; return 0; } @@ -648,8 +653,12 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port, if (!(*clone)) return -ENOMEM; - ocelot_port_add_txtstamp_skb(ocelot, port, *clone); + err = ocelot_port_add_txtstamp_skb(ocelot, port, *clone); + if (err) + return err; + OCELOT_SKB_CB(skb)->ptp_cmd = ptp_cmd; + OCELOT_SKB_CB(*clone)->ptp_class = ptp_class; } return 0; @@ -683,6 +692,17 @@ static void ocelot_get_hwtimestamp(struct ocelot *ocelot, spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); } +static bool ocelot_validate_ptp_skb(struct sk_buff *clone, u16 seqid) +{ + struct ptp_header *hdr; + + hdr = ptp_parse_header(clone, OCELOT_SKB_CB(clone)->ptp_class); + if (WARN_ON(!hdr)) + return false; + + return seqid == ntohs(hdr->sequence_id); +} + void ocelot_get_txtstamp(struct ocelot *ocelot) { int budget = OCELOT_PTP_QUEUE_SZ; @@ -690,10 +710,10 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) while (budget--) { struct sk_buff *skb, *skb_tmp, *skb_match = NULL; struct skb_shared_hwtstamps shhwtstamps; + u32 val, id, seqid, txport; struct ocelot_port *port; struct timespec64 ts; unsigned long flags; - u32 val, id, txport; val = ocelot_read(ocelot, SYS_PTP_STATUS); @@ -706,10 +726,17 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) /* Retrieve the ts ID and Tx port */ id = SYS_PTP_STATUS_PTP_MESS_ID_X(val); txport = SYS_PTP_STATUS_PTP_MESS_TXPORT_X(val); + seqid = SYS_PTP_STATUS_PTP_MESS_SEQ_ID(val); - /* Retrieve its associated skb */ port = ocelot->ports[txport]; + spin_lock(&ocelot->ts_id_lock); + port->ptp_skbs_in_flight--; + ocelot->ptp_skbs_in_flight--; + spin_unlock(&ocelot->ts_id_lock); + + /* Retrieve its associated skb */ +try_again: spin_lock_irqsave(&port->tx_skbs.lock, flags); skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) { @@ -722,12 +749,20 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) spin_unlock_irqrestore(&port->tx_skbs.lock, flags); + if (WARN_ON(!skb_match)) + continue; + + if (!ocelot_validate_ptp_skb(skb_match, seqid)) { + dev_err_ratelimited(ocelot->dev, + "port %d received stale TX timestamp for seqid %d, discarding\n", + txport, seqid); + dev_kfree_skb_any(skb); + goto try_again; + } + /* Get the h/w timestamp */ ocelot_get_hwtimestamp(ocelot, &ts); - if (unlikely(!skb_match)) - continue; - /* Set the timestamp into the skb */ memset(&shhwtstamps, 0, sizeof(shhwtstamps)); shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); @@ -1948,7 +1983,6 @@ void ocelot_init_port(struct ocelot *ocelot, int port) struct ocelot_port *ocelot_port = ocelot->ports[port]; skb_queue_head_init(&ocelot_port->tx_skbs); - spin_lock_init(&ocelot_port->ts_id_lock); /* Basic L2 initialization */ @@ -2081,6 +2115,7 @@ int ocelot_init(struct ocelot *ocelot) mutex_init(&ocelot->stats_lock); mutex_init(&ocelot->ptp_lock); spin_lock_init(&ocelot->ptp_clock_lock); + spin_lock_init(&ocelot->ts_id_lock); snprintf(queue_name, sizeof(queue_name), "%s-stats", dev_name(ocelot->dev)); ocelot->stats_queue = create_singlethread_workqueue(queue_name); diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 2f2312715439..9992bf06311d 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -8,6 +8,7 @@ * Copyright 2020-2021 NXP */ +#include <linux/dsa/ocelot.h> #include <linux/if_bridge.h> #include <linux/of_net.h> #include <linux/phy/phy.h> @@ -1625,7 +1626,7 @@ static int ocelot_port_phylink_create(struct ocelot *ocelot, int port, if (phy_mode == PHY_INTERFACE_MODE_QSGMII) ocelot_port_rmwl(ocelot_port, 0, DEV_CLOCK_CFG_MAC_TX_RST | - DEV_CLOCK_CFG_MAC_TX_RST, + DEV_CLOCK_CFG_MAC_RX_RST, DEV_CLOCK_CFG); ocelot_port->phy_mode = phy_mode; diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index 7945393a0655..99d7376a70a7 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -998,8 +998,8 @@ ocelot_vcap_block_find_filter_by_index(struct ocelot_vcap_block *block, } struct ocelot_vcap_filter * -ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, int cookie, - bool tc_offload) +ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, + unsigned long cookie, bool tc_offload) { struct ocelot_vcap_filter *filter; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 32760f87bf8a..5736fcdafd7a 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -796,7 +796,8 @@ static int myri10ge_load_firmware(struct myri10ge_priv *mgp, int adopt) return status; } -static int myri10ge_update_mac_address(struct myri10ge_priv *mgp, u8 * addr) +static int myri10ge_update_mac_address(struct myri10ge_priv *mgp, + const u8 * addr) { struct myri10ge_cmd cmd; int status; @@ -3738,7 +3739,6 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *netdev; struct myri10ge_priv *mgp; struct device *dev = &pdev->dev; - int i; int status = -ENXIO; int dac_enabled; unsigned hdr_offset, ss_offset; @@ -3828,8 +3828,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (status) goto abort_with_ioremap; - for (i = 0; i < ETH_ALEN; i++) - netdev->dev_addr[i] = mgp->mac_addr[i]; + eth_hw_addr_set(netdev, mgp->mac_addr); myri10ge_select_firmware(mgp); diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c index 3f982033944b..82a22711ce45 100644 --- a/drivers/net/ethernet/natsemi/natsemi.c +++ b/drivers/net/ethernet/natsemi/natsemi.c @@ -809,6 +809,7 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) unsigned long iosize; void __iomem *ioaddr; const int pcibar = 1; /* PCI base address register */ + u8 addr[ETH_ALEN]; int prev_eedata; u32 tmp; @@ -859,10 +860,11 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) prev_eedata = eeprom_read(ioaddr, 6); for (i = 0; i < 3; i++) { int eedata = eeprom_read(ioaddr, i + 7); - dev->dev_addr[i*2] = (eedata << 1) + (prev_eedata >> 15); - dev->dev_addr[i*2+1] = eedata >> 7; + addr[i*2] = (eedata << 1) + (prev_eedata >> 15); + addr[i*2+1] = eedata >> 7; prev_eedata = eedata; } + eth_hw_addr_set(dev, addr); np = netdev_priv(dev); np->ioaddr = ioaddr; diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c index 72794d158871..49ea130c9067 100644 --- a/drivers/net/ethernet/natsemi/ns83820.c +++ b/drivers/net/ethernet/natsemi/ns83820.c @@ -1649,9 +1649,11 @@ failed: return ret; } -static void ns83820_getmac(struct ns83820 *dev, u8 *mac) +static void ns83820_getmac(struct ns83820 *dev, struct net_device *ndev) { + u8 mac[ETH_ALEN]; unsigned i; + for (i=0; i<3; i++) { u32 data; @@ -1661,9 +1663,10 @@ static void ns83820_getmac(struct ns83820 *dev, u8 *mac) writel(i*2, dev->base + RFCR); data = readl(dev->base + RFDR); - *mac++ = data; - *mac++ = data >> 8; + mac[i * 2] = data; + mac[i * 2 + 1] = data >> 8; } + eth_hw_addr_set(ndev, mac); } static void ns83820_set_multicast(struct net_device *ndev) @@ -2136,7 +2139,7 @@ static int ns83820_init_one(struct pci_dev *pci_dev, /* Disable Wake On Lan */ writel(0, dev->base + WCSR); - ns83820_getmac(dev, ndev->dev_addr); + ns83820_getmac(dev, ndev); /* Yes, we support dumb IP checksum on transmit */ ndev->features |= NETIF_F_SG; diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 5454c1c2f8ad..d1c32c65db05 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -5217,7 +5217,7 @@ static int s2io_set_mac_addr(struct net_device *dev, void *p) * as defined in errno.h file on failure. */ -static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr) +static int do_s2io_prog_unicast(struct net_device *dev, const u8 *addr) { struct s2io_nic *sp = netdev_priv(dev); register u64 mac_addr = 0, perm_addr = 0; @@ -8566,7 +8566,7 @@ static void s2io_io_resume(struct pci_dev *pdev) return; } - if (s2io_set_mac_addr(netdev, netdev->dev_addr) == FAILURE) { + if (do_s2io_prog_unicast(netdev, netdev->dev_addr) == FAILURE) { s2io_card_down(sp); pr_err("Can't restore mac addr after reset.\n"); return; diff --git a/drivers/net/ethernet/neterion/s2io.h b/drivers/net/ethernet/neterion/s2io.h index 5a6032212c19..a4266d1544ab 100644 --- a/drivers/net/ethernet/neterion/s2io.h +++ b/drivers/net/ethernet/neterion/s2io.h @@ -1073,7 +1073,7 @@ static void s2io_reset(struct s2io_nic * sp); static int s2io_poll_msix(struct napi_struct *napi, int budget); static int s2io_poll_inta(struct napi_struct *napi, int budget); static void s2io_init_pci(struct s2io_nic * sp); -static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr); +static int do_s2io_prog_unicast(struct net_device *dev, const u8 *addr); static void s2io_alarm_handle(struct timer_list *t); static irqreturn_t s2io_msix_ring_handle(int irq, void *dev_id); diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c index 2473fb5f75e5..2a5cc64227e9 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c +++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c @@ -458,7 +458,7 @@ nfp_abm_qdisc_graft(struct nfp_abm_link *alink, u32 handle, u32 child_handle, static void nfp_abm_stats_calculate(struct nfp_alink_stats *new, struct nfp_alink_stats *old, - struct gnet_stats_basic_packed *bstats, + struct gnet_stats_basic_sync *bstats, struct gnet_stats_queue *qstats) { _bstats_update(bstats, new->tx_bytes - old->tx_bytes, diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index c029950a81e2..ac1dcfa1d179 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -830,10 +830,6 @@ static int nfp_flower_init(struct nfp_app *app) if (err) goto err_cleanup; - err = flow_indr_dev_register(nfp_flower_indr_setup_tc_cb, app); - if (err) - goto err_cleanup; - if (app_priv->flower_ext_feats & NFP_FL_FEATS_VF_RLIM) nfp_flower_qos_init(app); @@ -942,7 +938,20 @@ static int nfp_flower_start(struct nfp_app *app) return err; } - return nfp_tunnel_config_start(app); + err = flow_indr_dev_register(nfp_flower_indr_setup_tc_cb, app); + if (err) + return err; + + err = nfp_tunnel_config_start(app); + if (err) + goto err_tunnel_config; + + return 0; + +err_tunnel_config: + flow_indr_dev_unregister(nfp_flower_indr_setup_tc_cb, app, + nfp_flower_setup_indr_tc_release); + return err; } static void nfp_flower_stop(struct nfp_app *app) diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index ab70179728f6..dfb4468fe287 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -837,7 +837,7 @@ nfp_tunnel_put_ipv6_off(struct nfp_app *app, struct nfp_ipv6_addr_entry *entry) } static int -__nfp_tunnel_offload_mac(struct nfp_app *app, u8 *mac, u16 idx, bool del) +__nfp_tunnel_offload_mac(struct nfp_app *app, const u8 *mac, u16 idx, bool del) { struct nfp_tun_mac_addr_offload payload; @@ -886,7 +886,7 @@ static bool nfp_tunnel_is_mac_idx_global(u16 nfp_mac_idx) } static struct nfp_tun_offloaded_mac * -nfp_tunnel_lookup_offloaded_macs(struct nfp_app *app, u8 *mac) +nfp_tunnel_lookup_offloaded_macs(struct nfp_app *app, const u8 *mac) { struct nfp_flower_priv *priv = app->priv; @@ -1005,7 +1005,7 @@ err_free_ida: static int nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev, - u8 *mac, bool mod) + const u8 *mac, bool mod) { struct nfp_flower_priv *priv = app->priv; struct nfp_flower_repr_priv *repr_priv; diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 3f269f914dac..9b530d7509a4 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -5711,6 +5711,7 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) u32 phystate_orig = 0, phystate; int phyinitialized = 0; static int printed_version; + u8 mac[ETH_ALEN]; if (!printed_version++) pr_info("Reverse Engineered nForce ethernet driver. Version %s.\n", @@ -5884,50 +5885,52 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) txreg = readl(base + NvRegTransmitPoll); if (id->driver_data & DEV_HAS_CORRECT_MACADDR) { /* mac address is already in correct order */ - dev->dev_addr[0] = (np->orig_mac[0] >> 0) & 0xff; - dev->dev_addr[1] = (np->orig_mac[0] >> 8) & 0xff; - dev->dev_addr[2] = (np->orig_mac[0] >> 16) & 0xff; - dev->dev_addr[3] = (np->orig_mac[0] >> 24) & 0xff; - dev->dev_addr[4] = (np->orig_mac[1] >> 0) & 0xff; - dev->dev_addr[5] = (np->orig_mac[1] >> 8) & 0xff; + mac[0] = (np->orig_mac[0] >> 0) & 0xff; + mac[1] = (np->orig_mac[0] >> 8) & 0xff; + mac[2] = (np->orig_mac[0] >> 16) & 0xff; + mac[3] = (np->orig_mac[0] >> 24) & 0xff; + mac[4] = (np->orig_mac[1] >> 0) & 0xff; + mac[5] = (np->orig_mac[1] >> 8) & 0xff; } else if (txreg & NVREG_TRANSMITPOLL_MAC_ADDR_REV) { /* mac address is already in correct order */ - dev->dev_addr[0] = (np->orig_mac[0] >> 0) & 0xff; - dev->dev_addr[1] = (np->orig_mac[0] >> 8) & 0xff; - dev->dev_addr[2] = (np->orig_mac[0] >> 16) & 0xff; - dev->dev_addr[3] = (np->orig_mac[0] >> 24) & 0xff; - dev->dev_addr[4] = (np->orig_mac[1] >> 0) & 0xff; - dev->dev_addr[5] = (np->orig_mac[1] >> 8) & 0xff; + mac[0] = (np->orig_mac[0] >> 0) & 0xff; + mac[1] = (np->orig_mac[0] >> 8) & 0xff; + mac[2] = (np->orig_mac[0] >> 16) & 0xff; + mac[3] = (np->orig_mac[0] >> 24) & 0xff; + mac[4] = (np->orig_mac[1] >> 0) & 0xff; + mac[5] = (np->orig_mac[1] >> 8) & 0xff; /* * Set orig mac address back to the reversed version. * This flag will be cleared during low power transition. * Therefore, we should always put back the reversed address. */ - np->orig_mac[0] = (dev->dev_addr[5] << 0) + (dev->dev_addr[4] << 8) + - (dev->dev_addr[3] << 16) + (dev->dev_addr[2] << 24); - np->orig_mac[1] = (dev->dev_addr[1] << 0) + (dev->dev_addr[0] << 8); + np->orig_mac[0] = (mac[5] << 0) + (mac[4] << 8) + + (mac[3] << 16) + (mac[2] << 24); + np->orig_mac[1] = (mac[1] << 0) + (mac[0] << 8); } else { /* need to reverse mac address to correct order */ - dev->dev_addr[0] = (np->orig_mac[1] >> 8) & 0xff; - dev->dev_addr[1] = (np->orig_mac[1] >> 0) & 0xff; - dev->dev_addr[2] = (np->orig_mac[0] >> 24) & 0xff; - dev->dev_addr[3] = (np->orig_mac[0] >> 16) & 0xff; - dev->dev_addr[4] = (np->orig_mac[0] >> 8) & 0xff; - dev->dev_addr[5] = (np->orig_mac[0] >> 0) & 0xff; + mac[0] = (np->orig_mac[1] >> 8) & 0xff; + mac[1] = (np->orig_mac[1] >> 0) & 0xff; + mac[2] = (np->orig_mac[0] >> 24) & 0xff; + mac[3] = (np->orig_mac[0] >> 16) & 0xff; + mac[4] = (np->orig_mac[0] >> 8) & 0xff; + mac[5] = (np->orig_mac[0] >> 0) & 0xff; writel(txreg|NVREG_TRANSMITPOLL_MAC_ADDR_REV, base + NvRegTransmitPoll); dev_dbg(&pci_dev->dev, "%s: set workaround bit for reversed mac addr\n", __func__); } - if (!is_valid_ether_addr(dev->dev_addr)) { + if (is_valid_ether_addr(mac)) { + eth_hw_addr_set(dev, mac); + } else { /* * Bad mac address. At least one bios sets the mac address * to 01:23:45:67:89:ab */ dev_err(&pci_dev->dev, "Invalid MAC address detected: %pM - Please complain to your hardware vendor.\n", - dev->dev_addr); + mac); eth_hw_addr_random(dev); dev_err(&pci_dev->dev, "Using random MAC address: %pM\n", dev->dev_addr); diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 43fd569aa5f1..fbfbf94e0377 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -419,7 +419,7 @@ struct netdata_local { /* * MAC support functions */ -static void __lpc_set_mac(struct netdata_local *pldat, u8 *mac) +static void __lpc_set_mac(struct netdata_local *pldat, const u8 *mac) { u32 tmp; diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c index 1a6336a56d3d..9c408328be0d 100644 --- a/drivers/net/ethernet/packetengines/hamachi.c +++ b/drivers/net/ethernet/packetengines/hamachi.c @@ -592,6 +592,7 @@ static int hamachi_init_one(struct pci_dev *pdev, void *ring_space; dma_addr_t ring_dma; int ret = -ENOMEM; + u8 addr[ETH_ALEN]; /* when built into the kernel, we only print version if device is found */ #ifndef MODULE @@ -628,8 +629,8 @@ static int hamachi_init_one(struct pci_dev *pdev, SET_NETDEV_DEV(dev, &pdev->dev); for (i = 0; i < 6; i++) - dev->dev_addr[i] = 1 ? read_eeprom(ioaddr, 4 + i) - : readb(ioaddr + StationAddr + i); + addr[i] = read_eeprom(ioaddr, 4 + i); + eth_hw_addr_set(dev, addr); #if ! defined(final_version) if (hamachi_debug > 4) diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c index f5cd8f51be7c..12105f62cbdd 100644 --- a/drivers/net/ethernet/packetengines/yellowfin.c +++ b/drivers/net/ethernet/packetengines/yellowfin.c @@ -384,6 +384,7 @@ static int yellowfin_init_one(struct pci_dev *pdev, #else int bar = 1; #endif + u8 addr[ETH_ALEN]; /* when built into the kernel, we only print version if device is found */ #ifndef MODULE @@ -416,12 +417,13 @@ static int yellowfin_init_one(struct pci_dev *pdev, if (drv_flags & DontUseEeprom) for (i = 0; i < 6; i++) - dev->dev_addr[i] = ioread8(ioaddr + StnAddr + i); + addr[i] = ioread8(ioaddr + StnAddr + i); else { int ee_offset = (read_eeprom(ioaddr, 6) == 0xff ? 0x100 : 0); for (i = 0; i < 6; i++) - dev->dev_addr[i] = read_eeprom(ioaddr, ee_offset + i); + addr[i] = read_eeprom(ioaddr, ee_offset + i); } + eth_hw_addr_set(dev, addr); /* Reset the chip. */ iowrite32(0x80000000, ioaddr + DMACtrl); diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c index 5512e43bafc1..f0ace3a0e85c 100644 --- a/drivers/net/ethernet/pasemi/pasemi_mac.c +++ b/drivers/net/ethernet/pasemi/pasemi_mac.c @@ -1722,7 +1722,7 @@ pasemi_mac_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = -ENODEV; goto out; } - memcpy(dev->dev_addr, mac->mac_addr, sizeof(mac->mac_addr)); + eth_hw_addr_set(dev, mac->mac_addr); ret = mac_to_intf(mac); if (ret < 0) { diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h index d570d03b23f6..5e25411ff02f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic.h +++ b/drivers/net/ethernet/pensando/ionic/ionic.h @@ -70,8 +70,13 @@ struct ionic_admin_ctx { }; int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx); -int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, int err); +int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, + const int err, const bool do_msg); int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx); +int ionic_adminq_post_wait_nomsg(struct ionic_lif *lif, struct ionic_admin_ctx *ctx); +void ionic_adminq_netdev_err_print(struct ionic_lif *lif, u8 opcode, + u8 status, int err); + int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_wait); int ionic_set_dma_mask(struct ionic *ionic); int ionic_setup(struct ionic *ionic); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c index 86b79430c2ad..c58217027564 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c @@ -226,6 +226,50 @@ static int netdev_show(struct seq_file *seq, void *v) } DEFINE_SHOW_ATTRIBUTE(netdev); +static int lif_filters_show(struct seq_file *seq, void *v) +{ + struct ionic_lif *lif = seq->private; + struct ionic_rx_filter *f; + struct hlist_head *head; + struct hlist_node *tmp; + unsigned int i; + + seq_puts(seq, "id flow state type filter\n"); + spin_lock_bh(&lif->rx_filters.lock); + for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) { + head = &lif->rx_filters.by_id[i]; + hlist_for_each_entry_safe(f, tmp, head, by_id) { + switch (le16_to_cpu(f->cmd.match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + seq_printf(seq, "0x%04x 0x%08x 0x%02x vlan 0x%04x\n", + f->filter_id, f->flow_id, f->state, + le16_to_cpu(f->cmd.vlan.vlan)); + break; + case IONIC_RX_FILTER_MATCH_MAC: + seq_printf(seq, "0x%04x 0x%08x 0x%02x mac %pM\n", + f->filter_id, f->flow_id, f->state, + f->cmd.mac.addr); + break; + case IONIC_RX_FILTER_MATCH_MAC_VLAN: + seq_printf(seq, "0x%04x 0x%08x 0x%02x macvl 0x%04x %pM\n", + f->filter_id, f->flow_id, f->state, + le16_to_cpu(f->cmd.vlan.vlan), + f->cmd.mac.addr); + break; + case IONIC_RX_FILTER_STEER_PKTCLASS: + seq_printf(seq, "0x%04x 0x%08x 0x%02x rxstr 0x%llx\n", + f->filter_id, f->flow_id, f->state, + le64_to_cpu(f->cmd.pkt_class)); + break; + } + } + } + spin_unlock_bh(&lif->rx_filters.lock); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(lif_filters); + void ionic_debugfs_add_lif(struct ionic_lif *lif) { struct dentry *lif_dentry; @@ -237,6 +281,8 @@ void ionic_debugfs_add_lif(struct ionic_lif *lif) debugfs_create_file("netdev", 0400, lif->dentry, lif->netdev, &netdev_fops); + debugfs_create_file("filters", 0400, lif->dentry, + lif, &lif_filters_fops); } void ionic_debugfs_del_lif(struct ionic_lif *lif) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c index 2267da95640b..4297ed9024c0 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -87,7 +87,6 @@ int ionic_devlink_register(struct ionic *ionic) err = devlink_port_register(dl, &ionic->dl_port, 0); if (err) { dev_err(ionic->dev, "devlink_port_register failed: %d\n", err); - devlink_unregister(dl); return err; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 5c020a263f0c..63f8a8163b5f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1242,135 +1242,6 @@ void ionic_get_stats64(struct net_device *netdev, ns->tx_errors = ns->tx_aborted_errors; } -int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr) -{ - struct ionic_admin_ctx ctx = { - .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), - .cmd.rx_filter_add = { - .opcode = IONIC_CMD_RX_FILTER_ADD, - .lif_index = cpu_to_le16(lif->index), - .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_MAC), - }, - }; - int nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters); - bool mc = is_multicast_ether_addr(addr); - struct ionic_rx_filter *f; - int err = 0; - - memcpy(ctx.cmd.rx_filter_add.mac.addr, addr, ETH_ALEN); - - spin_lock_bh(&lif->rx_filters.lock); - f = ionic_rx_filter_by_addr(lif, addr); - if (f) { - /* don't bother if we already have it and it is sync'd */ - if (f->state == IONIC_FILTER_STATE_SYNCED) { - spin_unlock_bh(&lif->rx_filters.lock); - return 0; - } - - /* mark preemptively as sync'd to block any parallel attempts */ - f->state = IONIC_FILTER_STATE_SYNCED; - } else { - /* save as SYNCED to catch any DEL requests while processing */ - err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, - IONIC_FILTER_STATE_SYNCED); - } - spin_unlock_bh(&lif->rx_filters.lock); - if (err) - return err; - - netdev_dbg(lif->netdev, "rx_filter add ADDR %pM\n", addr); - - /* Don't bother with the write to FW if we know there's no room, - * we can try again on the next sync attempt. - */ - if ((lif->nucast + lif->nmcast) >= nfilters) - err = -ENOSPC; - else - err = ionic_adminq_post_wait(lif, &ctx); - - spin_lock_bh(&lif->rx_filters.lock); - if (err && err != -EEXIST) { - /* set the state back to NEW so we can try again later */ - f = ionic_rx_filter_by_addr(lif, addr); - if (f && f->state == IONIC_FILTER_STATE_SYNCED) - f->state = IONIC_FILTER_STATE_NEW; - - spin_unlock_bh(&lif->rx_filters.lock); - - if (err == -ENOSPC) - return 0; - else - return err; - } - - if (mc) - lif->nmcast++; - else - lif->nucast++; - - f = ionic_rx_filter_by_addr(lif, addr); - if (f && f->state == IONIC_FILTER_STATE_OLD) { - /* Someone requested a delete while we were adding - * so update the filter info with the results from the add - * and the data will be there for the delete on the next - * sync cycle. - */ - err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, - IONIC_FILTER_STATE_OLD); - } else { - err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, - IONIC_FILTER_STATE_SYNCED); - } - - spin_unlock_bh(&lif->rx_filters.lock); - - return err; -} - -int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr) -{ - struct ionic_admin_ctx ctx = { - .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), - .cmd.rx_filter_del = { - .opcode = IONIC_CMD_RX_FILTER_DEL, - .lif_index = cpu_to_le16(lif->index), - }, - }; - struct ionic_rx_filter *f; - int state; - int err; - - spin_lock_bh(&lif->rx_filters.lock); - f = ionic_rx_filter_by_addr(lif, addr); - if (!f) { - spin_unlock_bh(&lif->rx_filters.lock); - return -ENOENT; - } - - netdev_dbg(lif->netdev, "rx_filter del ADDR %pM (id %d)\n", - addr, f->filter_id); - - state = f->state; - ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); - ionic_rx_filter_free(lif, f); - - if (is_multicast_ether_addr(addr) && lif->nmcast) - lif->nmcast--; - else if (!is_multicast_ether_addr(addr) && lif->nucast) - lif->nucast--; - - spin_unlock_bh(&lif->rx_filters.lock); - - if (state != IONIC_FILTER_STATE_NEW) { - err = ionic_adminq_post_wait(lif, &ctx); - if (err && err != -EEXIST) - return err; - } - - return 0; -} - static int ionic_addr_add(struct net_device *netdev, const u8 *addr) { return ionic_lif_list_addr(netdev_priv(netdev), addr, ADD_ADDR); @@ -1378,6 +1249,10 @@ static int ionic_addr_add(struct net_device *netdev, const u8 *addr) static int ionic_addr_del(struct net_device *netdev, const u8 *addr) { + /* Don't delete our own address from the uc list */ + if (ether_addr_equal(addr, netdev->dev_addr)) + return 0; + return ionic_lif_list_addr(netdev_priv(netdev), addr, DEL_ADDR); } @@ -1402,7 +1277,7 @@ void ionic_lif_rx_mode(struct ionic_lif *lif) rx_mode |= (nd_flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0; rx_mode |= (nd_flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0; - /* sync the mac filters */ + /* sync the filters */ ionic_rx_filter_sync(lif); /* check for overflow state @@ -1412,14 +1287,12 @@ void ionic_lif_rx_mode(struct ionic_lif *lif) * to see if we can disable NIC PROMISC */ nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters); - if ((lif->nucast + lif->nmcast) >= nfilters) { + + if (((lif->nucast + lif->nmcast) >= nfilters) || + (lif->max_vlans && lif->nvlans >= lif->max_vlans)) { rx_mode |= IONIC_RX_MODE_F_PROMISC; rx_mode |= IONIC_RX_MODE_F_ALLMULTI; - lif->uc_overflow = true; - lif->mc_overflow = true; - } else if (lif->uc_overflow) { - lif->uc_overflow = false; - lif->mc_overflow = false; + } else { if (!(nd_flags & IFF_PROMISC)) rx_mode &= ~IONIC_RX_MODE_F_PROMISC; if (!(nd_flags & IFF_ALLMULTI)) @@ -1804,59 +1677,30 @@ static int ionic_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ionic_lif *lif = netdev_priv(netdev); - struct ionic_admin_ctx ctx = { - .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), - .cmd.rx_filter_add = { - .opcode = IONIC_CMD_RX_FILTER_ADD, - .lif_index = cpu_to_le16(lif->index), - .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_VLAN), - .vlan.vlan = cpu_to_le16(vid), - }, - }; int err; - netdev_dbg(netdev, "rx_filter add VLAN %d\n", vid); - err = ionic_adminq_post_wait(lif, &ctx); + err = ionic_lif_vlan_add(lif, vid); if (err) return err; - spin_lock_bh(&lif->rx_filters.lock); - err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, - IONIC_FILTER_STATE_SYNCED); - spin_unlock_bh(&lif->rx_filters.lock); + ionic_lif_rx_mode(lif); - return err; + return 0; } static int ionic_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct ionic_lif *lif = netdev_priv(netdev); - struct ionic_admin_ctx ctx = { - .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), - .cmd.rx_filter_del = { - .opcode = IONIC_CMD_RX_FILTER_DEL, - .lif_index = cpu_to_le16(lif->index), - }, - }; - struct ionic_rx_filter *f; - - spin_lock_bh(&lif->rx_filters.lock); - - f = ionic_rx_filter_by_vlan(lif, vid); - if (!f) { - spin_unlock_bh(&lif->rx_filters.lock); - return -ENOENT; - } + int err; - netdev_dbg(netdev, "rx_filter del VLAN %d (id %d)\n", - vid, f->filter_id); + err = ionic_lif_vlan_del(lif, vid); + if (err) + return err; - ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); - ionic_rx_filter_free(lif, f); - spin_unlock_bh(&lif->rx_filters.lock); + ionic_lif_rx_mode(lif); - return ionic_adminq_post_wait(lif, &ctx); + return 0; } int ionic_lif_rss_config(struct ionic_lif *lif, const u16 types, diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 41f28154745f..9f7ab2f17f93 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -189,11 +189,11 @@ struct ionic_lif { u16 rx_mode; u64 hw_features; bool registered; - bool mc_overflow; - bool uc_overflow; u16 lif_type; unsigned int nmcast; unsigned int nucast; + unsigned int nvlans; + unsigned int max_vlans; char name[IONIC_LIF_NAME_MAX_SZ]; union ionic_lif_identity *identity; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index bb49f1b8ef67..875f4ec42efe 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -212,24 +212,28 @@ static void ionic_adminq_flush(struct ionic_lif *lif) spin_unlock_irqrestore(&lif->adminq_lock, irqflags); } +void ionic_adminq_netdev_err_print(struct ionic_lif *lif, u8 opcode, + u8 status, int err) +{ + netdev_err(lif->netdev, "%s (%d) failed: %s (%d)\n", + ionic_opcode_to_str(opcode), opcode, + ionic_error_to_str(status), err); +} + static int ionic_adminq_check_err(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, - bool timeout) + const bool timeout, + const bool do_msg) { - struct net_device *netdev = lif->netdev; - const char *opcode_str; - const char *status_str; int err = 0; if (ctx->comp.comp.status || timeout) { - opcode_str = ionic_opcode_to_str(ctx->cmd.cmd.opcode); - status_str = ionic_error_to_str(ctx->comp.comp.status); err = timeout ? -ETIMEDOUT : ionic_error_to_errno(ctx->comp.comp.status); - netdev_err(netdev, "%s (%d) failed: %s (%d)\n", - opcode_str, ctx->cmd.cmd.opcode, - timeout ? "TIMEOUT" : status_str, err); + if (do_msg) + ionic_adminq_netdev_err_print(lif, ctx->cmd.cmd.opcode, + ctx->comp.comp.status, err); if (timeout) ionic_adminq_flush(lif); @@ -298,7 +302,8 @@ err_out: return err; } -int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, int err) +int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, + const int err, const bool do_msg) { struct net_device *netdev = lif->netdev; unsigned long time_limit; @@ -310,7 +315,7 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, int er name = ionic_opcode_to_str(ctx->cmd.cmd.opcode); if (err) { - if (!test_bit(IONIC_LIF_F_FW_RESET, lif->state)) + if (do_msg && !test_bit(IONIC_LIF_F_FW_RESET, lif->state)) netdev_err(netdev, "Posting of %s (%d) failed: %d\n", name, ctx->cmd.cmd.opcode, err); return err; @@ -328,8 +333,9 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, int er /* interrupt the wait if FW stopped */ if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) { - netdev_err(netdev, "%s (%d) interrupted, FW in reset\n", - name, ctx->cmd.cmd.opcode); + if (do_msg) + netdev_err(netdev, "%s (%d) interrupted, FW in reset\n", + name, ctx->cmd.cmd.opcode); return -ENXIO; } @@ -339,7 +345,9 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, int er dev_dbg(lif->ionic->dev, "%s: elapsed %d msecs\n", __func__, jiffies_to_msecs(time_done - time_start)); - return ionic_adminq_check_err(lif, ctx, time_after_eq(time_done, time_limit)); + return ionic_adminq_check_err(lif, ctx, + time_after_eq(time_done, time_limit), + do_msg); } int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) @@ -348,7 +356,16 @@ int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) err = ionic_adminq_post(lif, ctx); - return ionic_adminq_wait(lif, ctx, err); + return ionic_adminq_wait(lif, ctx, err, true); +} + +int ionic_adminq_post_wait_nomsg(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) +{ + int err; + + err = ionic_adminq_post(lif, ctx); + + return ionic_adminq_wait(lif, ctx, err, false); } static void ionic_dev_cmd_clean(struct ionic *ionic) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_phc.c b/drivers/net/ethernet/pensando/ionic/ionic_phc.c index eed2db69d708..887046838b3b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_phc.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_phc.c @@ -348,7 +348,7 @@ static int ionic_phc_adjfine(struct ptp_clock_info *info, long scaled_ppm) spin_unlock_irqrestore(&phc->lock, irqflags); - return ionic_adminq_wait(phc->lif, &ctx, err); + return ionic_adminq_wait(phc->lif, &ctx, err, true); } static int ionic_phc_adjtime(struct ptp_clock_info *info, s64 delta) @@ -373,7 +373,7 @@ static int ionic_phc_adjtime(struct ptp_clock_info *info, s64 delta) spin_unlock_irqrestore(&phc->lock, irqflags); - return ionic_adminq_wait(phc->lif, &ctx, err); + return ionic_adminq_wait(phc->lif, &ctx, err, true); } static int ionic_phc_settime64(struct ptp_clock_info *info, @@ -402,7 +402,7 @@ static int ionic_phc_settime64(struct ptp_clock_info *info, spin_unlock_irqrestore(&phc->lock, irqflags); - return ionic_adminq_wait(phc->lif, &ctx, err); + return ionic_adminq_wait(phc->lif, &ctx, err, true); } static int ionic_phc_gettimex64(struct ptp_clock_info *info, @@ -459,7 +459,7 @@ static long ionic_phc_aux_work(struct ptp_clock_info *info) spin_unlock_irqrestore(&phc->lock, irqflags); - ionic_adminq_wait(phc->lif, &ctx, err); + ionic_adminq_wait(phc->lif, &ctx, err, true); return phc->aux_work_delay; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c index 25ecfcfa1281..f6e785f949f9 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c @@ -239,6 +239,21 @@ struct ionic_rx_filter *ionic_rx_filter_rxsteer(struct ionic_lif *lif) return NULL; } +static struct ionic_rx_filter *ionic_rx_filter_find(struct ionic_lif *lif, + struct ionic_rx_filter_add_cmd *ac) +{ + switch (le16_to_cpu(ac->match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + return ionic_rx_filter_by_vlan(lif, le16_to_cpu(ac->vlan.vlan)); + case IONIC_RX_FILTER_MATCH_MAC: + return ionic_rx_filter_by_addr(lif, ac->mac.addr); + default: + netdev_err(lif->netdev, "unsupported filter match %d", + le16_to_cpu(ac->match)); + return NULL; + } +} + int ionic_lif_list_addr(struct ionic_lif *lif, const u8 *addr, bool mode) { struct ionic_rx_filter *f; @@ -286,6 +301,228 @@ int ionic_lif_list_addr(struct ionic_lif *lif, const u8 *addr, bool mode) return 0; } +static int ionic_lif_filter_add(struct ionic_lif *lif, + struct ionic_rx_filter_add_cmd *ac) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + }; + struct ionic_rx_filter *f; + int nfilters; + int err = 0; + + ctx.cmd.rx_filter_add = *ac; + ctx.cmd.rx_filter_add.opcode = IONIC_CMD_RX_FILTER_ADD, + ctx.cmd.rx_filter_add.lif_index = cpu_to_le16(lif->index), + + spin_lock_bh(&lif->rx_filters.lock); + f = ionic_rx_filter_find(lif, &ctx.cmd.rx_filter_add); + if (f) { + /* don't bother if we already have it and it is sync'd */ + if (f->state == IONIC_FILTER_STATE_SYNCED) { + spin_unlock_bh(&lif->rx_filters.lock); + return 0; + } + + /* mark preemptively as sync'd to block any parallel attempts */ + f->state = IONIC_FILTER_STATE_SYNCED; + } else { + /* save as SYNCED to catch any DEL requests while processing */ + err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, + IONIC_FILTER_STATE_SYNCED); + } + spin_unlock_bh(&lif->rx_filters.lock); + if (err) + return err; + + /* Don't bother with the write to FW if we know there's no room, + * we can try again on the next sync attempt. + * Since the FW doesn't have a way to tell us the vlan limit, + * we start max_vlans at 0 until we hit the ENOSPC error. + */ + switch (le16_to_cpu(ctx.cmd.rx_filter_add.match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + netdev_dbg(lif->netdev, "%s: rx_filter add VLAN %d\n", + __func__, ctx.cmd.rx_filter_add.vlan.vlan); + if (lif->max_vlans && lif->nvlans >= lif->max_vlans) + err = -ENOSPC; + break; + case IONIC_RX_FILTER_MATCH_MAC: + netdev_dbg(lif->netdev, "%s: rx_filter add ADDR %pM\n", + __func__, ctx.cmd.rx_filter_add.mac.addr); + nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters); + if ((lif->nucast + lif->nmcast) >= nfilters) + err = -ENOSPC; + break; + } + + if (err != -ENOSPC) + err = ionic_adminq_post_wait_nomsg(lif, &ctx); + + spin_lock_bh(&lif->rx_filters.lock); + + if (err && err != -EEXIST) { + /* set the state back to NEW so we can try again later */ + f = ionic_rx_filter_find(lif, &ctx.cmd.rx_filter_add); + if (f && f->state == IONIC_FILTER_STATE_SYNCED) { + f->state = IONIC_FILTER_STATE_NEW; + + /* If -ENOSPC we won't waste time trying to sync again + * until there is a delete that might make room + */ + if (err != -ENOSPC) + set_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state); + } + + spin_unlock_bh(&lif->rx_filters.lock); + + if (err == -ENOSPC) { + if (le16_to_cpu(ctx.cmd.rx_filter_add.match) == IONIC_RX_FILTER_MATCH_VLAN) + lif->max_vlans = lif->nvlans; + return 0; + } + + ionic_adminq_netdev_err_print(lif, ctx.cmd.cmd.opcode, + ctx.comp.comp.status, err); + switch (le16_to_cpu(ctx.cmd.rx_filter_add.match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + netdev_info(lif->netdev, "rx_filter add failed: VLAN %d\n", + ctx.cmd.rx_filter_add.vlan.vlan); + break; + case IONIC_RX_FILTER_MATCH_MAC: + netdev_info(lif->netdev, "rx_filter add failed: ADDR %pM\n", + ctx.cmd.rx_filter_add.mac.addr); + break; + } + + return err; + } + + switch (le16_to_cpu(ctx.cmd.rx_filter_add.match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + lif->nvlans++; + break; + case IONIC_RX_FILTER_MATCH_MAC: + if (is_multicast_ether_addr(ctx.cmd.rx_filter_add.mac.addr)) + lif->nmcast++; + else + lif->nucast++; + break; + } + + f = ionic_rx_filter_find(lif, &ctx.cmd.rx_filter_add); + if (f && f->state == IONIC_FILTER_STATE_OLD) { + /* Someone requested a delete while we were adding + * so update the filter info with the results from the add + * and the data will be there for the delete on the next + * sync cycle. + */ + err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, + IONIC_FILTER_STATE_OLD); + } else { + err = ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx, + IONIC_FILTER_STATE_SYNCED); + } + + spin_unlock_bh(&lif->rx_filters.lock); + + return err; +} + +int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr) +{ + struct ionic_rx_filter_add_cmd ac = { + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_MAC), + }; + + memcpy(&ac.mac.addr, addr, ETH_ALEN); + + return ionic_lif_filter_add(lif, &ac); +} + +int ionic_lif_vlan_add(struct ionic_lif *lif, const u16 vid) +{ + struct ionic_rx_filter_add_cmd ac = { + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_VLAN), + .vlan.vlan = cpu_to_le16(vid), + }; + + return ionic_lif_filter_add(lif, &ac); +} + +static int ionic_lif_filter_del(struct ionic_lif *lif, + struct ionic_rx_filter_add_cmd *ac) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_del = { + .opcode = IONIC_CMD_RX_FILTER_DEL, + .lif_index = cpu_to_le16(lif->index), + }, + }; + struct ionic_rx_filter *f; + int state; + int err; + + spin_lock_bh(&lif->rx_filters.lock); + f = ionic_rx_filter_find(lif, ac); + if (!f) { + spin_unlock_bh(&lif->rx_filters.lock); + return -ENOENT; + } + + switch (le16_to_cpu(ac->match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + netdev_dbg(lif->netdev, "%s: rx_filter del VLAN %d id %d\n", + __func__, ac->vlan.vlan, f->filter_id); + lif->nvlans--; + break; + case IONIC_RX_FILTER_MATCH_MAC: + netdev_dbg(lif->netdev, "%s: rx_filter del ADDR %pM id %d\n", + __func__, ac->mac.addr, f->filter_id); + if (is_multicast_ether_addr(ac->mac.addr) && lif->nmcast) + lif->nmcast--; + else if (!is_multicast_ether_addr(ac->mac.addr) && lif->nucast) + lif->nucast--; + break; + } + + state = f->state; + ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); + ionic_rx_filter_free(lif, f); + + spin_unlock_bh(&lif->rx_filters.lock); + + if (state != IONIC_FILTER_STATE_NEW) { + err = ionic_adminq_post_wait(lif, &ctx); + if (err && err != -EEXIST) + return err; + } + + return 0; +} + +int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr) +{ + struct ionic_rx_filter_add_cmd ac = { + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_MAC), + }; + + memcpy(&ac.mac.addr, addr, ETH_ALEN); + + return ionic_lif_filter_del(lif, &ac); +} + +int ionic_lif_vlan_del(struct ionic_lif *lif, const u16 vid) +{ + struct ionic_rx_filter_add_cmd ac = { + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_VLAN), + .vlan.vlan = cpu_to_le16(vid), + }; + + return ionic_lif_filter_del(lif, &ac); +} + struct sync_item { struct list_head list; struct ionic_rx_filter f; @@ -340,17 +577,14 @@ loop_out: * they can clear room for some new filters */ list_for_each_entry_safe(sync_item, spos, &sync_del_list, list) { - (void)ionic_lif_addr_del(lif, sync_item->f.cmd.mac.addr); + (void)ionic_lif_filter_del(lif, &sync_item->f.cmd); list_del(&sync_item->list); devm_kfree(dev, sync_item); } list_for_each_entry_safe(sync_item, spos, &sync_add_list, list) { - (void)ionic_lif_addr_add(lif, sync_item->f.cmd.mac.addr); - - if (sync_item->f.state != IONIC_FILTER_STATE_SYNCED) - set_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state); + (void)ionic_lif_filter_add(lif, &sync_item->f.cmd); list_del(&sync_item->list); devm_kfree(dev, sync_item); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h index a66e35f0833b..87b2666f248b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h @@ -44,5 +44,7 @@ struct ionic_rx_filter *ionic_rx_filter_rxsteer(struct ionic_lif *lif); void ionic_rx_filter_sync(struct ionic_lif *lif); int ionic_lif_list_addr(struct ionic_lif *lif, const u8 *addr, bool mode); int ionic_rx_filters_need_sync(struct ionic_lif *lif); +int ionic_lif_vlan_add(struct ionic_lif *lif, const u16 vid); +int ionic_lif_vlan_del(struct ionic_lif *lif, const u16 vid); #endif /* _IONIC_RX_FILTER_H_ */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 6d693ee380f1..e3edca187ddf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -1315,7 +1315,6 @@ static u32 qed_dump_common_global_params(struct qed_hwfn *p_hwfn, u8 num_specific_global_params) { struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; - char sw_platform_str[MAX_SW_PLTAFORM_STR_SIZE]; u32 offset = 0; u8 num_params; @@ -1341,8 +1340,6 @@ static u32 qed_dump_common_global_params(struct qed_hwfn *p_hwfn, dump, "platform", s_hw_type_defs[dev_data->hw_type].name); - offset += qed_dump_str_param(dump_buf + offset, - dump, "sw-platform", sw_platform_str); offset += qed_dump_num_param(dump_buf + offset, dump, "pci-func", p_hwfn->abs_pf_id); offset += qed_dump_num_param(dump_buf + offset, @@ -5259,7 +5256,7 @@ enum dbg_status qed_dbg_grc_config(struct qed_hwfn *p_hwfn, */ qed_dbg_grc_init_params(p_hwfn); - if (grc_param >= MAX_DBG_GRC_PARAMS || grc_param < 0) + if (grc_param >= MAX_DBG_GRC_PARAMS) return DBG_STATUS_INVALID_ARGS; if (val < s_grc_param_defs[grc_param].min || val > s_grc_param_defs[grc_param].max) diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 6823016ab5a3..18f3bf7c4dfe 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -952,7 +952,7 @@ qed_llh_remove_filter(struct qed_hwfn *p_hwfn, } int qed_llh_add_mac_filter(struct qed_dev *cdev, - u8 ppfid, u8 mac_addr[ETH_ALEN]) + u8 ppfid, const u8 mac_addr[ETH_ALEN]) { struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h index 6582bfc1b4a9..f8682356d0cf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h +++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h @@ -364,7 +364,7 @@ int qed_llh_set_roce_affinity(struct qed_dev *cdev, enum qed_eng eng); * Return: Int. */ int qed_llh_add_mac_filter(struct qed_dev *cdev, - u8 ppfid, u8 mac_addr[ETH_ALEN]); + u8 ppfid, const u8 mac_addr[ETH_ALEN]); /** * qed_llh_remove_mac_filter(): Remove a LLH MAC filter from the given diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index a116fbc59725..2edd6bf64a3c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2848,7 +2848,7 @@ static int qed_fp_cqe_completion(struct qed_dev *dev, cqe); } -static int qed_req_bulletin_update_mac(struct qed_dev *cdev, u8 *mac) +static int qed_req_bulletin_update_mac(struct qed_dev *cdev, const u8 *mac) { int i, ret; diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 5e7242304ee2..7673b3e07736 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -1295,6 +1295,7 @@ static int qed_slowpath_start(struct qed_dev *cdev, } else { DP_NOTICE(cdev, "Failed to acquire PTT for aRFS\n"); + rc = -EINVAL; goto err; } } @@ -2887,7 +2888,7 @@ static int qed_update_drv_state(struct qed_dev *cdev, bool active) return status; } -static int qed_update_mac(struct qed_dev *cdev, u8 *mac) +static int qed_update_mac(struct qed_dev *cdev, const u8 *mac) { struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); struct qed_ptt *ptt; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 11a52a4a673b..64678a256f3b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -2851,7 +2851,7 @@ int qed_mcp_ov_update_mtu(struct qed_hwfn *p_hwfn, } int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, u8 *mac) + struct qed_ptt *p_ptt, const u8 *mac) { struct qed_mcp_mb_params mb_params; u32 mfw_mac[2]; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 9e1de1191bd4..564723800d15 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -536,7 +536,7 @@ int qed_mcp_ov_update_mtu(struct qed_hwfn *p_hwfn, * Return: Int - 0 - Operation was successul. */ int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, u8 *mac); + struct qed_ptt *p_ptt, const u8 *mac); /** * qed_mcp_ov_update_wol(): Send WOL mode to MFW. diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index fe0bb11d0e43..7f3e84b8622d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -1965,7 +1965,7 @@ static void qed_rdma_remove_user(void *rdma_cxt, u16 dpi) static int qed_roce_ll2_set_mac_filter(struct qed_dev *cdev, u8 *old_mac_address, - u8 *new_mac_address) + const u8 *new_mac_address) { int rc = 0; diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index f88f58ec2a20..8ac38828ba45 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -5224,7 +5224,6 @@ void qed_iov_wq_stop(struct qed_dev *cdev, bool schedule_first) cancel_delayed_work_sync(&cdev->hwfns[i].iov_task); } - flush_workqueue(cdev->hwfns[i].iov_wq); destroy_workqueue(cdev->hwfns[i].iov_wq); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h index 1edf9c44dc67..f448e3dd6c8b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h @@ -478,6 +478,18 @@ static inline int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled) static inline void qed_inform_vf_link_state(struct qed_hwfn *hwfn) { } + +static inline void qed_sriov_vfpf_malicious(struct qed_hwfn *p_hwfn, + struct fw_err_data *p_data) +{ +} + +static inline int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn, u8 opcode, + __le16 echo, union event_ring_data *data, + u8 fw_return_code) +{ + return 0; +} #endif #define qed_for_each_vf(_p_hwfn, _i) \ diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 220a95fa96e1..597cd9cd57b5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -1373,7 +1373,7 @@ exit: int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, - u8 *p_mac) + const u8 *p_mac) { struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info; struct vfpf_bulletin_update_mac_tlv *p_req; diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h index 8718760443be..306b5f4bc632 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.h +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h @@ -1070,7 +1070,7 @@ u32 qed_vf_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id); * * Return: Int. */ -int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, u8 *p_mac); +int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, const u8 *p_mac); #else static inline void qed_vf_get_link_params(struct qed_hwfn *p_hwfn, @@ -1259,7 +1259,7 @@ static inline int qed_vf_pf_tunnel_param_update(struct qed_hwfn *p_hwfn, } static inline int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, - u8 *p_mac) + const u8 *p_mac) { return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 03c51dd37e1f..3010833ddde3 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -617,7 +617,7 @@ void qede_fill_rss_params(struct qede_dev *edev, static int qede_set_ucast_rx_mac(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, - unsigned char mac[ETH_ALEN]) + const unsigned char mac[ETH_ALEN]) { struct qed_filter_ucast_params ucast; diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 395f054e9e0c..1e6d72adfe43 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -508,10 +508,12 @@ static void eeprom_readword(struct ql3_adapter *qdev, static void ql_set_mac_addr(struct net_device *ndev, u16 *addr) { - __le16 *p = (__le16 *)ndev->dev_addr; - p[0] = cpu_to_le16(addr[0]); - p[1] = cpu_to_le16(addr[1]); - p[2] = cpu_to_le16(addr[2]); + __le16 buf[ETH_ALEN / 2]; + + buf[0] = cpu_to_le16(addr[0]); + buf[1] = cpu_to_le16(addr[1]); + buf[2] = cpu_to_le16(addr[2]); + eth_hw_addr_set(ndev, (u8 *)buf); } static int ql_get_nvram_params(struct ql3_adapter *qdev) diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 87b8c032195d..06104d2ff5b3 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -420,7 +420,7 @@ static void emac_mac_dma_config(struct emac_adapter *adpt) } /* set MAC address */ -static void emac_set_mac_address(struct emac_adapter *adpt, u8 *addr) +static void emac_set_mac_address(struct emac_adapter *adpt, const u8 *addr) { u32 sta; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 13d8eb43a485..1b2119b1d48a 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -224,7 +224,7 @@ void rmnet_vnd_setup(struct net_device *rmnet_dev) rmnet_dev->netdev_ops = &rmnet_vnd_ops; rmnet_dev->mtu = RMNET_DFLT_PACKET_SIZE; rmnet_dev->needed_headroom = RMNET_NEEDED_HEADROOM; - eth_random_addr(rmnet_dev->dev_addr); + eth_hw_addr_random(rmnet_dev); rmnet_dev->tx_queue_len = RMNET_TX_QUEUE_LEN; /* Raw IP mode */ diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index 01ef5efd7bc2..a6bf7d505178 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -453,7 +453,7 @@ static void r6040_down(struct net_device *dev) { struct r6040_private *lp = netdev_priv(dev); void __iomem *ioaddr = lp->base; - u16 *adrp; + const u16 *adrp; /* Stop MAC */ iowrite16(MSK_INT, ioaddr + MIER); /* Mask Off Interrupt */ @@ -462,7 +462,7 @@ static void r6040_down(struct net_device *dev) r6040_reset_mac(lp); /* Restore MAC Address to MIDx */ - adrp = (u16 *) dev->dev_addr; + adrp = (const u16 *) dev->dev_addr; iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); @@ -731,13 +731,13 @@ static void r6040_mac_address(struct net_device *dev) { struct r6040_private *lp = netdev_priv(dev); void __iomem *ioaddr = lp->base; - u16 *adrp; + const u16 *adrp; /* Reset MAC */ r6040_reset_mac(lp); /* Restore MAC Address */ - adrp = (u16 *) dev->dev_addr; + adrp = (const u16 *) dev->dev_addr; iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); @@ -849,13 +849,13 @@ static void r6040_multicast_list(struct net_device *dev) unsigned long flags; struct netdev_hw_addr *ha; int i; - u16 *adrp; + const u16 *adrp; u16 hash_table[4] = { 0 }; spin_lock_irqsave(&lp->lock, flags); /* Keep our MAC Address */ - adrp = (u16 *)dev->dev_addr; + adrp = (const u16 *)dev->dev_addr; iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); @@ -1031,8 +1031,8 @@ static int r6040_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) void __iomem *ioaddr; int err, io_size = R6040_IO_SIZE; static int card_idx = -1; + u16 addr[ETH_ALEN / 2]; int bar = 0; - u16 *adrp; pr_info("%s\n", version); @@ -1102,14 +1102,14 @@ static int r6040_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* Set MAC address */ card_idx++; - adrp = (u16 *)dev->dev_addr; - adrp[0] = ioread16(ioaddr + MID_0L); - adrp[1] = ioread16(ioaddr + MID_0M); - adrp[2] = ioread16(ioaddr + MID_0H); + addr[0] = ioread16(ioaddr + MID_0L); + addr[1] = ioread16(ioaddr + MID_0M); + addr[2] = ioread16(ioaddr + MID_0H); + eth_hw_addr_set(dev, (u8 *)addr); /* Some bootloader/BIOSes do not initialize * MAC address, warn about that */ - if (!(adrp[0] || adrp[1] || adrp[2])) { + if (!(addr[0] || addr[1] || addr[2])) { netdev_warn(dev, "MAC address not initialized, " "generating random\n"); eth_hw_addr_random(dev); diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 614aac780b6b..4f39f843bb3a 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -1889,6 +1889,7 @@ static int cp_init_one (struct pci_dev *pdev, const struct pci_device_id *ent) void __iomem *regs; resource_size_t pciaddr; unsigned int addr_len, i, pci_using_dac; + __le16 addr[ETH_ALEN / 2]; pr_info_once("%s", version); @@ -1979,8 +1980,8 @@ static int cp_init_one (struct pci_dev *pdev, const struct pci_device_id *ent) /* read MAC address from EEPROM */ addr_len = read_eeprom (regs, 0, 8) == 0x8129 ? 8 : 6; for (i = 0; i < 3; i++) - ((__le16 *) (dev->dev_addr))[i] = - cpu_to_le16(read_eeprom (regs, i + 7, addr_len)); + addr[i] = cpu_to_le16(read_eeprom (regs, i + 7, addr_len)); + eth_hw_addr_set(dev, (u8 *)addr); dev->netdev_ops = &cp_netdev_ops; netif_napi_add(dev, &cp->napi, cp_rx_poll, 16); diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index 75b5ac91132b..15b40fd93cd2 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -945,6 +945,7 @@ static int rtl8139_init_one(struct pci_dev *pdev, { struct net_device *dev = NULL; struct rtl8139_private *tp; + __le16 addr[ETH_ALEN / 2]; int i, addr_len, option; void __iomem *ioaddr; static int board_idx = -1; @@ -994,8 +995,8 @@ static int rtl8139_init_one(struct pci_dev *pdev, addr_len = read_eeprom (ioaddr, 0, 8) == 0x8129 ? 8 : 6; for (i = 0; i < 3; i++) - ((__le16 *) (dev->dev_addr))[i] = - cpu_to_le16(read_eeprom (ioaddr, i + 7, addr_len)); + addr[i] = cpu_to_le16(read_eeprom (ioaddr, i + 7, addr_len)); + eth_hw_addr_set(dev, (u8 *)addr); /* The Rtl8139-specific entries in the device structure. */ dev->netdev_ops = &rtl8139_netdev_ops; diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c index b6c849b258a0..6cbcb3164367 100644 --- a/drivers/net/ethernet/realtek/atp.c +++ b/drivers/net/ethernet/realtek/atp.c @@ -368,6 +368,7 @@ static int __init atp_probe1(long ioaddr) static void __init get_node_ID(struct net_device *dev) { long ioaddr = dev->base_addr; + __be16 addr[ETH_ALEN / 2]; int sa_offset = 0; int i; @@ -379,8 +380,9 @@ static void __init get_node_ID(struct net_device *dev) sa_offset = 15; for (i = 0; i < 3; i++) - ((__be16 *)dev->dev_addr)[i] = + addr[i] = cpu_to_be16(eeprom_op(ioaddr, EE_READ(sa_offset + i))); + eth_hw_addr_set(dev, (u8 *)addr); write_reg(ioaddr, CMR2, CMR2_NULL); } diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 5dc1324786e0..08062d73df10 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -196,12 +196,15 @@ enum ravb_reg { MAHR = 0x05c0, MALR = 0x05c8, TROCR = 0x0700, /* R-Car Gen3 and RZ/G2L only */ + CXR41 = 0x0708, /* RZ/G2L only */ + CXR42 = 0x0710, /* RZ/G2L only */ CEFCR = 0x0740, FRECR = 0x0748, TSFRCR = 0x0750, TLFRCR = 0x0758, RFCR = 0x0760, MAFCR = 0x0778, + CSR0 = 0x0800, /* RZ/G2L only */ }; @@ -826,7 +829,7 @@ enum ECSR_BIT { ECSR_MPD = 0x00000002, ECSR_LCHNG = 0x00000004, ECSR_PHYI = 0x00000008, - ECSR_PFRI = 0x00000010, + ECSR_PFRI = 0x00000010, /* Documented for R-Car Gen3 and RZ/G2L */ }; /* ECSIPR */ @@ -962,6 +965,11 @@ enum CXR31_BIT { CXR31_SEL_LINK1 = 0x00000008, }; +enum CSR0_BIT { + CSR0_TPE = 0x00000010, + CSR0_RPE = 0x00000020, +}; + #define DBAT_ENTRY_NUM 22 #define RX_QUEUE_OFFSET 4 #define NUM_RX_QUEUE 2 @@ -970,6 +978,7 @@ enum CXR31_BIT { #define RX_BUF_SZ (2048 - ETH_FCS_LEN + sizeof(__sum16)) #define GBETH_RX_BUFF_MAX 8192 +#define GBETH_RX_DESC_DATA_SIZE 4080 struct ravb_tstamp_skb { struct list_head list; @@ -1009,16 +1018,18 @@ struct ravb_hw_info { netdev_features_t net_features; int stats_len; size_t max_rx_len; - u32 tsrq; + u32 tccr_mask; + u32 rx_max_buf_size; unsigned aligned_tx: 1; /* hardware features */ unsigned internal_delay:1; /* AVB-DMAC has internal delays */ unsigned tx_counters:1; /* E-MAC has TX counters */ + unsigned carrier_counters:1; /* E-MAC has carrier counters */ unsigned multi_irqs:1; /* AVB-DMAC and E-MAC has multiple irqs */ unsigned gptp:1; /* AVB-DMAC has gPTP support */ unsigned ccc_gac:1; /* AVB-DMAC has gPTP support active in config mode */ - unsigned nc_queue:1; /* AVB-DMAC has NC queue */ + unsigned nc_queues:1; /* AVB-DMAC has RX and TX NC queues */ unsigned magic_pkt:1; /* E-MAC supports magic packet detection */ unsigned half_duplex:1; /* E-MAC supports half duplex mode */ }; @@ -1037,9 +1048,11 @@ struct ravb_private { struct ravb_desc *desc_bat; dma_addr_t rx_desc_dma[NUM_RX_QUEUE]; dma_addr_t tx_desc_dma[NUM_TX_QUEUE]; + struct ravb_rx_desc *gbeth_rx_ring; struct ravb_ex_rx_desc *rx_ring[NUM_RX_QUEUE]; struct ravb_tx_desc *tx_ring[NUM_TX_QUEUE]; void *tx_align[NUM_TX_QUEUE]; + struct sk_buff *rx_1st_skb; struct sk_buff **rx_skb[NUM_RX_QUEUE]; struct sk_buff **tx_skb[NUM_TX_QUEUE]; u32 rx_over_errors; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 50038e76c72f..e5243cc87a19 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -236,10 +236,30 @@ static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only) static void ravb_rx_ring_free_gbeth(struct net_device *ndev, int q) { - /* Place holder */ + struct ravb_private *priv = netdev_priv(ndev); + unsigned int ring_size; + unsigned int i; + + if (!priv->gbeth_rx_ring) + return; + + for (i = 0; i < priv->num_rx_ring[q]; i++) { + struct ravb_rx_desc *desc = &priv->gbeth_rx_ring[i]; + + if (!dma_mapping_error(ndev->dev.parent, + le32_to_cpu(desc->dptr))) + dma_unmap_single(ndev->dev.parent, + le32_to_cpu(desc->dptr), + GBETH_RX_BUFF_MAX, + DMA_FROM_DEVICE); + } + ring_size = sizeof(struct ravb_rx_desc) * (priv->num_rx_ring[q] + 1); + dma_free_coherent(ndev->dev.parent, ring_size, priv->gbeth_rx_ring, + priv->rx_desc_dma[q]); + priv->gbeth_rx_ring = NULL; } -static void ravb_rx_ring_free(struct net_device *ndev, int q) +static void ravb_rx_ring_free_rcar(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); unsigned int ring_size; @@ -307,10 +327,36 @@ static void ravb_ring_free(struct net_device *ndev, int q) static void ravb_rx_ring_format_gbeth(struct net_device *ndev, int q) { - /* Place holder */ + struct ravb_private *priv = netdev_priv(ndev); + struct ravb_rx_desc *rx_desc; + unsigned int rx_ring_size; + dma_addr_t dma_addr; + unsigned int i; + + rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q]; + memset(priv->gbeth_rx_ring, 0, rx_ring_size); + /* Build RX ring buffer */ + for (i = 0; i < priv->num_rx_ring[q]; i++) { + /* RX descriptor */ + rx_desc = &priv->gbeth_rx_ring[i]; + rx_desc->ds_cc = cpu_to_le16(GBETH_RX_DESC_DATA_SIZE); + dma_addr = dma_map_single(ndev->dev.parent, priv->rx_skb[q][i]->data, + GBETH_RX_BUFF_MAX, + DMA_FROM_DEVICE); + /* We just set the data size to 0 for a failed mapping which + * should prevent DMA from happening... + */ + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + rx_desc->ds_cc = cpu_to_le16(0); + rx_desc->dptr = cpu_to_le32(dma_addr); + rx_desc->die_dt = DT_FEMPTY; + } + rx_desc = &priv->gbeth_rx_ring[i]; + rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]); + rx_desc->die_dt = DT_LINKFIX; /* type */ } -static void ravb_rx_ring_format(struct net_device *ndev, int q) +static void ravb_rx_ring_format_rcar(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); struct ravb_ex_rx_desc *rx_desc; @@ -385,11 +431,18 @@ static void ravb_ring_format(struct net_device *ndev, int q) static void *ravb_alloc_rx_desc_gbeth(struct net_device *ndev, int q) { - /* Place holder */ - return NULL; + struct ravb_private *priv = netdev_priv(ndev); + unsigned int ring_size; + + ring_size = sizeof(struct ravb_rx_desc) * (priv->num_rx_ring[q] + 1); + + priv->gbeth_rx_ring = dma_alloc_coherent(ndev->dev.parent, ring_size, + &priv->rx_desc_dma[q], + GFP_KERNEL); + return priv->gbeth_rx_ring; } -static void *ravb_alloc_rx_desc(struct net_device *ndev, int q) +static void *ravb_alloc_rx_desc_rcar(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); unsigned int ring_size; @@ -466,10 +519,10 @@ static void ravb_emac_init_gbeth(struct net_device *ndev) /* Receive frame limit set register */ ravb_write(ndev, GBETH_RX_BUFF_MAX + ETH_FCS_LEN, RFLR); - /* PAUSE prohibition */ + /* EMAC Mode: PAUSE prohibition; Duplex; TX; RX; CRC Pass Through */ ravb_write(ndev, ECMR_ZPF | ((priv->duplex > 0) ? ECMR_DM : 0) | ECMR_TE | ECMR_RE | ECMR_RCPT | - ECMR_TXF | ECMR_RXF | ECMR_PRM, ECMR); + ECMR_TXF | ECMR_RXF, ECMR); ravb_set_rate_gbeth(ndev); @@ -481,12 +534,12 @@ static void ravb_emac_init_gbeth(struct net_device *ndev) /* E-MAC status register clear */ ravb_write(ndev, ECSR_ICD | ECSR_LCHNG | ECSR_PFRI, ECSR); + ravb_write(ndev, CSR0_TPE | CSR0_RPE, CSR0); /* E-MAC interrupt enable register */ ravb_write(ndev, ECSIPR_ICDIP, ECSIPR); - ravb_modify(ndev, CXR31, CXR31_SEL_LINK1, 0); - ravb_modify(ndev, CXR31, CXR31_SEL_LINK0, CXR31_SEL_LINK0); + ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1, CXR31_SEL_LINK0); } static void ravb_emac_init_rcar(struct net_device *ndev) @@ -535,7 +588,7 @@ static int ravb_dmac_init_gbeth(struct net_device *ndev) /* Descriptor format */ ravb_ring_format(ndev, RAVB_BE); - /* Set AVB RX */ + /* Set DMAC RX */ ravb_write(ndev, 0x60000000, RCR); /* Set Max Frame Length (RTC) */ @@ -681,15 +734,151 @@ static void ravb_rx_csum(struct sk_buff *skb) skb_trim(skb, skb->len - sizeof(__sum16)); } +static struct sk_buff *ravb_get_skb_gbeth(struct net_device *ndev, int entry, + struct ravb_rx_desc *desc) +{ + struct ravb_private *priv = netdev_priv(ndev); + struct sk_buff *skb; + + skb = priv->rx_skb[RAVB_BE][entry]; + priv->rx_skb[RAVB_BE][entry] = NULL; + dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), + ALIGN(GBETH_RX_BUFF_MAX, 16), DMA_FROM_DEVICE); + + return skb; +} + /* Packet receive function for Gigabit Ethernet */ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) { - /* Place holder */ - return true; + struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; + struct net_device_stats *stats; + struct ravb_rx_desc *desc; + struct sk_buff *skb; + dma_addr_t dma_addr; + u8 desc_status; + int boguscnt; + u16 pkt_len; + u8 die_dt; + int entry; + int limit; + + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + boguscnt = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; + stats = &priv->stats[q]; + + boguscnt = min(boguscnt, *quota); + limit = boguscnt; + desc = &priv->gbeth_rx_ring[entry]; + while (desc->die_dt != DT_FEMPTY) { + /* Descriptor type must be checked before all other reads */ + dma_rmb(); + desc_status = desc->msc; + pkt_len = le16_to_cpu(desc->ds_cc) & RX_DS; + + if (--boguscnt < 0) + break; + + /* We use 0-byte descriptors to mark the DMA mapping errors */ + if (!pkt_len) + continue; + + if (desc_status & MSC_MC) + stats->multicast++; + + if (desc_status & (MSC_CRC | MSC_RFE | MSC_RTSF | MSC_RTLF | MSC_CEEF)) { + stats->rx_errors++; + if (desc_status & MSC_CRC) + stats->rx_crc_errors++; + if (desc_status & MSC_RFE) + stats->rx_frame_errors++; + if (desc_status & (MSC_RTLF | MSC_RTSF)) + stats->rx_length_errors++; + if (desc_status & MSC_CEEF) + stats->rx_missed_errors++; + } else { + die_dt = desc->die_dt & 0xF0; + switch (die_dt) { + case DT_FSINGLE: + skb = ravb_get_skb_gbeth(ndev, entry, desc); + skb_put(skb, pkt_len); + skb->protocol = eth_type_trans(skb, ndev); + napi_gro_receive(&priv->napi[q], skb); + stats->rx_packets++; + stats->rx_bytes += pkt_len; + break; + case DT_FSTART: + priv->rx_1st_skb = ravb_get_skb_gbeth(ndev, entry, desc); + skb_put(priv->rx_1st_skb, pkt_len); + break; + case DT_FMID: + skb = ravb_get_skb_gbeth(ndev, entry, desc); + skb_copy_to_linear_data_offset(priv->rx_1st_skb, + priv->rx_1st_skb->len, + skb->data, + pkt_len); + skb_put(priv->rx_1st_skb, pkt_len); + dev_kfree_skb(skb); + break; + case DT_FEND: + skb = ravb_get_skb_gbeth(ndev, entry, desc); + skb_copy_to_linear_data_offset(priv->rx_1st_skb, + priv->rx_1st_skb->len, + skb->data, + pkt_len); + skb_put(priv->rx_1st_skb, pkt_len); + dev_kfree_skb(skb); + priv->rx_1st_skb->protocol = + eth_type_trans(priv->rx_1st_skb, ndev); + napi_gro_receive(&priv->napi[q], + priv->rx_1st_skb); + stats->rx_packets++; + stats->rx_bytes += priv->rx_1st_skb->len; + break; + } + } + + entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; + desc = &priv->gbeth_rx_ring[entry]; + } + + /* Refill the RX ring buffers. */ + for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) { + entry = priv->dirty_rx[q] % priv->num_rx_ring[q]; + desc = &priv->gbeth_rx_ring[entry]; + desc->ds_cc = cpu_to_le16(GBETH_RX_DESC_DATA_SIZE); + + if (!priv->rx_skb[q][entry]) { + skb = netdev_alloc_skb(ndev, info->max_rx_len); + if (!skb) + break; + ravb_set_buffer_align(skb); + dma_addr = dma_map_single(ndev->dev.parent, + skb->data, + GBETH_RX_BUFF_MAX, + DMA_FROM_DEVICE); + skb_checksum_none_assert(skb); + /* We just set the data size to 0 for a failed mapping + * which should prevent DMA from happening... + */ + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + desc->ds_cc = cpu_to_le16(0); + desc->dptr = cpu_to_le32(dma_addr); + priv->rx_skb[q][entry] = skb; + } + /* Descriptor type must be set after all the above writes */ + dma_wmb(); + desc->die_dt = DT_FEMPTY; + } + + *quota -= limit - (++boguscnt); + + return boguscnt <= 0; } /* Packet receive function for Ethernet AVB */ -static bool ravb_rcar_rx(struct net_device *ndev, int *quota, int q) +static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; @@ -832,7 +1021,7 @@ static int ravb_stop_dma(struct net_device *ndev) int error; /* Wait for stopping the hardware TX process */ - error = ravb_wait(ndev, TCCR, info->tsrq, 0); + error = ravb_wait(ndev, TCCR, info->tccr_mask, 0); if (error) return error; @@ -988,7 +1177,7 @@ static irqreturn_t ravb_interrupt(int irq, void *dev_id) result = IRQ_HANDLED; /* Network control and best effort queue RX/TX */ - if (info->nc_queue) { + if (info->nc_queues) { for (q = RAVB_NC; q >= RAVB_BE; q--) { if (ravb_queue_interrupt(ndev, q)) result = IRQ_HANDLED; @@ -1084,16 +1273,25 @@ static int ravb_poll(struct napi_struct *napi, int budget) struct net_device *ndev = napi->dev; struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; + bool gptp = info->gptp || info->ccc_gac; + struct ravb_rx_desc *desc; unsigned long flags; int q = napi - priv->napi; int mask = BIT(q); int quota = budget; + unsigned int entry; + if (!gptp) { + entry = priv->cur_rx[q] % priv->num_rx_ring[q]; + desc = &priv->gbeth_rx_ring[entry]; + } /* Processing RX Descriptor Ring */ /* Clear RX interrupt */ ravb_write(ndev, ~(mask | RIS0_RESERVED), RIS0); - if (ravb_rx(ndev, "a, q)) - goto out; + if (gptp || desc->die_dt != DT_FEMPTY) { + if (ravb_rx(ndev, "a, q)) + goto out; + } /* Processing TX Descriptor Ring */ spin_lock_irqsave(&priv->lock, flags); @@ -1118,7 +1316,7 @@ static int ravb_poll(struct napi_struct *napi, int budget) /* Receive error message handling */ priv->rx_over_errors = priv->stats[RAVB_BE].rx_over_errors; - if (info->nc_queue) + if (info->nc_queues) priv->rx_over_errors += priv->stats[RAVB_NC].rx_over_errors; if (priv->rx_over_errors != ndev->stats.rx_over_errors) ndev->stats.rx_over_errors = priv->rx_over_errors; @@ -1295,6 +1493,24 @@ static void ravb_set_msglevel(struct net_device *ndev, u32 value) priv->msg_enable = value; } +static const char ravb_gstrings_stats_gbeth[][ETH_GSTRING_LEN] = { + "rx_queue_0_current", + "tx_queue_0_current", + "rx_queue_0_dirty", + "tx_queue_0_dirty", + "rx_queue_0_packets", + "tx_queue_0_packets", + "rx_queue_0_bytes", + "tx_queue_0_bytes", + "rx_queue_0_mcast_packets", + "rx_queue_0_errors", + "rx_queue_0_crc_errors", + "rx_queue_0_frame_errors", + "rx_queue_0_length_errors", + "rx_queue_0_csum_offload_errors", + "rx_queue_0_over_errors", +}; + static const char ravb_gstrings_stats[][ETH_GSTRING_LEN] = { "rx_queue_0_current", "tx_queue_0_current", @@ -1351,7 +1567,7 @@ static void ravb_get_ethtool_stats(struct net_device *ndev, int i = 0; int q; - num_rx_q = info->nc_queue ? NUM_RX_QUEUE : 1; + num_rx_q = info->nc_queues ? NUM_RX_QUEUE : 1; /* Device-specific stats */ for (q = RAVB_BE; q < num_rx_q; q++) { struct net_device_stats *stats = &priv->stats[q]; @@ -1428,7 +1644,7 @@ static int ravb_set_ringparam(struct net_device *ndev, /* Free all the skb's in the RX queue and the DMA buffers. */ ravb_ring_free(ndev, RAVB_BE); - if (info->nc_queue) + if (info->nc_queues) ravb_ring_free(ndev, RAVB_NC); } @@ -1548,7 +1764,7 @@ static int ravb_open(struct net_device *ndev) int error; napi_enable(&priv->napi[RAVB_BE]); - if (info->nc_queue) + if (info->nc_queues) napi_enable(&priv->napi[RAVB_NC]); if (!info->multi_irqs) { @@ -1623,7 +1839,7 @@ out_free_irq_emac: out_free_irq: free_irq(ndev->irq, ndev); out_napi_off: - if (info->nc_queue) + if (info->nc_queues) napi_disable(&priv->napi[RAVB_NC]); napi_disable(&priv->napi[RAVB_BE]); return error; @@ -1673,7 +1889,7 @@ static void ravb_tx_timeout_work(struct work_struct *work) } ravb_ring_free(ndev, RAVB_BE); - if (info->nc_queue) + if (info->nc_queues) ravb_ring_free(ndev, RAVB_NC); /* Device init */ @@ -1855,6 +2071,13 @@ static struct net_device_stats *ravb_get_stats(struct net_device *ndev) ravb_write(ndev, 0, TROCR); /* (write clear) */ } + if (info->carrier_counters) { + nstats->collisions += ravb_read(ndev, CXR41); + ravb_write(ndev, 0, CXR41); /* (write clear) */ + nstats->tx_carrier_errors += ravb_read(ndev, CXR42); + ravb_write(ndev, 0, CXR42); /* (write clear) */ + } + nstats->rx_packets = stats0->rx_packets; nstats->tx_packets = stats0->tx_packets; nstats->rx_bytes = stats0->rx_bytes; @@ -1866,7 +2089,7 @@ static struct net_device_stats *ravb_get_stats(struct net_device *ndev) nstats->rx_length_errors = stats0->rx_length_errors; nstats->rx_missed_errors = stats0->rx_missed_errors; nstats->rx_over_errors = stats0->rx_over_errors; - if (info->nc_queue) { + if (info->nc_queues) { stats1 = &priv->stats[RAVB_NC]; nstats->rx_packets += stats1->rx_packets; @@ -1947,13 +2170,13 @@ static int ravb_close(struct net_device *ndev) } free_irq(ndev->irq, ndev); - if (info->nc_queue) + if (info->nc_queues) napi_disable(&priv->napi[RAVB_NC]); napi_disable(&priv->napi[RAVB_BE]); /* Free all the skb's in the RX queue and the DMA buffers. */ ravb_ring_free(ndev, RAVB_BE); - if (info->nc_queue) + if (info->nc_queues) ravb_ring_free(ndev, RAVB_NC); return 0; @@ -2173,10 +2396,10 @@ static int ravb_mdio_release(struct ravb_private *priv) } static const struct ravb_hw_info ravb_gen3_hw_info = { - .rx_ring_free = ravb_rx_ring_free, - .rx_ring_format = ravb_rx_ring_format, - .alloc_rx_desc = ravb_alloc_rx_desc, - .receive = ravb_rcar_rx, + .rx_ring_free = ravb_rx_ring_free_rcar, + .rx_ring_format = ravb_rx_ring_format_rcar, + .alloc_rx_desc = ravb_alloc_rx_desc_rcar, + .receive = ravb_rx_rcar, .set_rate = ravb_set_rate_rcar, .set_feature = ravb_set_features_rcar, .dmac_init = ravb_dmac_init_rcar, @@ -2187,20 +2410,21 @@ static const struct ravb_hw_info ravb_gen3_hw_info = { .net_features = NETIF_F_RXCSUM, .stats_len = ARRAY_SIZE(ravb_gstrings_stats), .max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1, - .tsrq = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, + .tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, + .rx_max_buf_size = SZ_2K, .internal_delay = 1, .tx_counters = 1, .multi_irqs = 1, .ccc_gac = 1, - .nc_queue = 1, + .nc_queues = 1, .magic_pkt = 1, }; static const struct ravb_hw_info ravb_gen2_hw_info = { - .rx_ring_free = ravb_rx_ring_free, - .rx_ring_format = ravb_rx_ring_format, - .alloc_rx_desc = ravb_alloc_rx_desc, - .receive = ravb_rcar_rx, + .rx_ring_free = ravb_rx_ring_free_rcar, + .rx_ring_format = ravb_rx_ring_format_rcar, + .alloc_rx_desc = ravb_alloc_rx_desc_rcar, + .receive = ravb_rx_rcar, .set_rate = ravb_set_rate_rcar, .set_feature = ravb_set_features_rcar, .dmac_init = ravb_dmac_init_rcar, @@ -2211,10 +2435,11 @@ static const struct ravb_hw_info ravb_gen2_hw_info = { .net_features = NETIF_F_RXCSUM, .stats_len = ARRAY_SIZE(ravb_gstrings_stats), .max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1, - .tsrq = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, + .tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, + .rx_max_buf_size = SZ_2K, .aligned_tx = 1, .gptp = 1, - .nc_queue = 1, + .nc_queues = 1, .magic_pkt = 1, }; @@ -2227,10 +2452,15 @@ static const struct ravb_hw_info gbeth_hw_info = { .set_feature = ravb_set_features_gbeth, .dmac_init = ravb_dmac_init_gbeth, .emac_init = ravb_emac_init_gbeth, - .max_rx_len = GBETH_RX_BUFF_MAX + RAVB_ALIGN - 1, - .tsrq = TCCR_TSRQ0, + .gstrings_stats = ravb_gstrings_stats_gbeth, + .gstrings_size = sizeof(ravb_gstrings_stats_gbeth), + .stats_len = ARRAY_SIZE(ravb_gstrings_stats_gbeth), + .max_rx_len = ALIGN(GBETH_RX_BUFF_MAX, RAVB_ALIGN), + .tccr_mask = TCCR_TSRQ0, + .rx_max_buf_size = SZ_8K, .aligned_tx = 1, .tx_counters = 1, + .carrier_counters = 1, .half_duplex = 1, }; @@ -2389,7 +2619,7 @@ static int ravb_probe(struct platform_device *pdev) priv->pdev = pdev; priv->num_tx_ring[RAVB_BE] = BE_TX_RING_SIZE; priv->num_rx_ring[RAVB_BE] = BE_RX_RING_SIZE; - if (info->nc_queue) { + if (info->nc_queues) { priv->num_tx_ring[RAVB_NC] = NC_TX_RING_SIZE; priv->num_rx_ring[RAVB_NC] = NC_RX_RING_SIZE; } @@ -2452,7 +2682,7 @@ static int ravb_probe(struct platform_device *pdev) } clk_prepare_enable(priv->refclk); - ndev->max_mtu = 2048 - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); + ndev->max_mtu = info->rx_max_buf_size - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); ndev->min_mtu = ETH_MIN_MTU; /* FIXME: R-Car Gen2 has 4byte alignment restriction for tx buffer @@ -2525,7 +2755,7 @@ static int ravb_probe(struct platform_device *pdev) } netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64); - if (info->nc_queue) + if (info->nc_queues) netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64); /* Network device register */ @@ -2544,7 +2774,7 @@ static int ravb_probe(struct platform_device *pdev) return 0; out_napi_del: - if (info->nc_queue) + if (info->nc_queues) netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); @@ -2585,7 +2815,7 @@ static int ravb_remove(struct platform_device *pdev) ravb_write(ndev, CCC_OPC_RESET, CCC); pm_runtime_put_sync(&pdev->dev); unregister_netdev(ndev); - if (info->nc_queue) + if (info->nc_queues) netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); ravb_mdio_release(priv); @@ -2609,7 +2839,7 @@ static int ravb_wol_setup(struct net_device *ndev) /* Only allow ECI interrupts */ synchronize_irq(priv->emac_irq); - if (info->nc_queue) + if (info->nc_queues) napi_disable(&priv->napi[RAVB_NC]); napi_disable(&priv->napi[RAVB_BE]); ravb_write(ndev, ECSIPR_MPDIP, ECSIPR); @@ -2626,7 +2856,7 @@ static int ravb_wol_restore(struct net_device *ndev) const struct ravb_hw_info *info = priv->info; int ret; - if (info->nc_queue) + if (info->nc_queues) napi_enable(&priv->napi[RAVB_NC]); napi_enable(&priv->napi[RAVB_BE]); diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h index 049dc6cf4611..0f45107db8dd 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h @@ -329,7 +329,7 @@ struct sxgbe_core_ops { /* Set power management mode (e.g. magic frame) */ void (*pmt)(void __iomem *ioaddr, unsigned long mode); /* Set/Get Unicast MAC addresses */ - void (*set_umac_addr)(void __iomem *ioaddr, unsigned char *addr, + void (*set_umac_addr)(void __iomem *ioaddr, const unsigned char *addr, unsigned int reg_n); void (*get_umac_addr)(void __iomem *ioaddr, unsigned char *addr, unsigned int reg_n); diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c index e96e2bd295ef..7d9f257de92a 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c @@ -85,7 +85,8 @@ static void sxgbe_core_pmt(void __iomem *ioaddr, unsigned long mode) } /* Set/Get Unicast MAC addresses */ -static void sxgbe_core_set_umac_addr(void __iomem *ioaddr, unsigned char *addr, +static void sxgbe_core_set_umac_addr(void __iomem *ioaddr, + const unsigned char *addr, unsigned int reg_n) { u32 high_word, low_word; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index e7e2223aebbf..cf366ed2557c 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1038,7 +1038,7 @@ int efx_ef10_vadaptor_free(struct efx_nic *efx, unsigned int port_id) } int efx_ef10_vport_add_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac) + unsigned int port_id, const u8 *mac) { MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_LEN); @@ -1050,7 +1050,7 @@ int efx_ef10_vport_add_mac(struct efx_nic *efx, } int efx_ef10_vport_del_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac) + unsigned int port_id, const u8 *mac) { MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_LEN); diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c index 06d23c708a5f..7f5aa4a8c451 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.c +++ b/drivers/net/ethernet/sfc/ef10_sriov.c @@ -480,7 +480,7 @@ static int efx_ef10_vport_del_vf_mac(struct efx_nic *efx, unsigned int port_id, return rc; } -int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, u8 *mac) +int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, const u8 *mac) { struct efx_ef10_nic_data *nic_data = efx->nic_data; struct ef10_vf *vf; diff --git a/drivers/net/ethernet/sfc/ef10_sriov.h b/drivers/net/ethernet/sfc/ef10_sriov.h index cfe556d17313..3c703ca878b0 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.h +++ b/drivers/net/ethernet/sfc/ef10_sriov.h @@ -39,7 +39,7 @@ static inline void efx_ef10_sriov_reset(struct efx_nic *efx) {} void efx_ef10_sriov_fini(struct efx_nic *efx); static inline void efx_ef10_sriov_flr(struct efx_nic *efx, unsigned vf_i) {} -int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf, u8 *mac); +int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf, const u8 *mac); int efx_ef10_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i, u16 vlan, u8 qos); @@ -60,9 +60,9 @@ int efx_ef10_vswitching_restore_vf(struct efx_nic *efx); void efx_ef10_vswitching_remove_pf(struct efx_nic *efx); void efx_ef10_vswitching_remove_vf(struct efx_nic *efx); int efx_ef10_vport_add_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac); + unsigned int port_id, const u8 *mac); int efx_ef10_vport_del_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac); + unsigned int port_id, const u8 *mac); int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id); int efx_ef10_vadaptor_query(struct efx_nic *efx, unsigned int port_id, u32 *port_flags, u32 *vadaptor_flags, diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index f6981810039d..cc15ee8812d9 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -1440,7 +1440,7 @@ struct efx_nic_type { bool (*sriov_wanted)(struct efx_nic *efx); void (*sriov_reset)(struct efx_nic *efx); void (*sriov_flr)(struct efx_nic *efx, unsigned vf_i); - int (*sriov_set_vf_mac)(struct efx_nic *efx, int vf_i, u8 *mac); + int (*sriov_set_vf_mac)(struct efx_nic *efx, int vf_i, const u8 *mac); int (*sriov_set_vf_vlan)(struct efx_nic *efx, int vf_i, u16 vlan, u8 qos); int (*sriov_set_vf_spoofchk)(struct efx_nic *efx, int vf_i, diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c index 83dcfcae3d4b..e9095cf06368 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.c +++ b/drivers/net/ethernet/sfc/siena_sriov.c @@ -1591,7 +1591,7 @@ void efx_fini_sriov(void) destroy_workqueue(vfdi_workqueue); } -int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, u8 *mac) +int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, const u8 *mac) { struct siena_nic_data *nic_data = efx->nic_data; struct siena_vf *vf; diff --git a/drivers/net/ethernet/sfc/siena_sriov.h b/drivers/net/ethernet/sfc/siena_sriov.h index e441c89c25ce..e548c4daf189 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.h +++ b/drivers/net/ethernet/sfc/siena_sriov.h @@ -46,7 +46,7 @@ bool efx_siena_sriov_wanted(struct efx_nic *efx); void efx_siena_sriov_reset(struct efx_nic *efx); void efx_siena_sriov_flr(struct efx_nic *efx, unsigned flr); -int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf, u8 *mac); +int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf, const u8 *mac); int efx_siena_sriov_set_vf_vlan(struct efx_nic *efx, int vf, u16 vlan, u8 qos); int efx_siena_sriov_set_vf_spoofchk(struct efx_nic *efx, int vf, diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c index 1fd08a04bd4e..ff4197f5e46d 100644 --- a/drivers/net/ethernet/silan/sc92031.c +++ b/drivers/net/ethernet/silan/sc92031.c @@ -1400,6 +1400,7 @@ static int sc92031_probe(struct pci_dev *pdev, const struct pci_device_id *id) void __iomem* port_base; struct net_device *dev; struct sc92031_priv *priv; + u8 addr[ETH_ALEN]; u32 mac0, mac1; err = pci_enable_device(pdev); @@ -1458,12 +1459,13 @@ static int sc92031_probe(struct pci_dev *pdev, const struct pci_device_id *id) mac0 = ioread32(port_base + MAC0); mac1 = ioread32(port_base + MAC0 + 4); - dev->dev_addr[0] = mac0 >> 24; - dev->dev_addr[1] = mac0 >> 16; - dev->dev_addr[2] = mac0 >> 8; - dev->dev_addr[3] = mac0; - dev->dev_addr[4] = mac1 >> 8; - dev->dev_addr[5] = mac1; + addr[0] = mac0 >> 24; + addr[1] = mac0 >> 16; + addr[2] = mac0 >> 8; + addr[3] = mac0; + addr[4] = mac1 >> 8; + addr[5] = mac1; + eth_hw_addr_set(dev, addr); err = register_netdev(dev); if (err < 0) diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c index be4d772e68cf..5e66e3f3aafc 100644 --- a/drivers/net/ethernet/sis/sis190.c +++ b/drivers/net/ethernet/sis/sis190.c @@ -1586,6 +1586,7 @@ static int sis190_get_mac_addr_from_eeprom(struct pci_dev *pdev, { struct sis190_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->mmio_addr; + __le16 addr[ETH_ALEN / 2]; u16 sig; int i; @@ -1606,8 +1607,9 @@ static int sis190_get_mac_addr_from_eeprom(struct pci_dev *pdev, for (i = 0; i < ETH_ALEN / 2; i++) { u16 w = sis190_read_eeprom(ioaddr, EEPROMMACAddr + i); - ((__le16 *)dev->dev_addr)[i] = cpu_to_le16(w); + addr[i] = cpu_to_le16(w); } + eth_hw_addr_set(dev, (u8 *)addr); sis190_set_rgmii(tp, sis190_read_eeprom(ioaddr, EEPROMInfo)); diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 60a0c0e9ded2..3f5717a1874f 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -258,6 +258,7 @@ static int sis900_get_mac_addr(struct pci_dev *pci_dev, { struct sis900_private *sis_priv = netdev_priv(net_dev); void __iomem *ioaddr = sis_priv->ioaddr; + u16 addr[ETH_ALEN / 2]; u16 signature; int i; @@ -271,7 +272,8 @@ static int sis900_get_mac_addr(struct pci_dev *pci_dev, /* get MAC address from EEPROM */ for (i = 0; i < 3; i++) - ((u16 *)(net_dev->dev_addr))[i] = read_eeprom(ioaddr, i+EEPROMMACAddr); + addr[i] = read_eeprom(ioaddr, i+EEPROMMACAddr); + eth_hw_addr_set(net_dev, (u8 *)addr); return 1; } @@ -331,6 +333,7 @@ static int sis635_get_mac_addr(struct pci_dev *pci_dev, { struct sis900_private *sis_priv = netdev_priv(net_dev); void __iomem *ioaddr = sis_priv->ioaddr; + u16 addr[ETH_ALEN / 2]; u32 rfcrSave; u32 i; @@ -345,8 +348,9 @@ static int sis635_get_mac_addr(struct pci_dev *pci_dev, /* load MAC addr to filter data register */ for (i = 0 ; i < 3 ; i++) { sw32(rfcr, (i << RFADDR_shift)); - *( ((u16 *)net_dev->dev_addr) + i) = sr16(rfdr); + addr[i] = sr16(rfdr); } + eth_hw_addr_set(net_dev, (u8 *)addr); /* enable packet filtering */ sw32(rfcr, rfcrSave | RFEN); @@ -375,17 +379,18 @@ static int sis96x_get_mac_addr(struct pci_dev *pci_dev, { struct sis900_private *sis_priv = netdev_priv(net_dev); void __iomem *ioaddr = sis_priv->ioaddr; + u16 addr[ETH_ALEN / 2]; int wait, rc = 0; sw32(mear, EEREQ); for (wait = 0; wait < 2000; wait++) { if (sr32(mear) & EEGNT) { - u16 *mac = (u16 *)net_dev->dev_addr; int i; /* get MAC address from EEPROM */ for (i = 0; i < 3; i++) - mac[i] = read_eeprom(ioaddr, i + EEPROMMACAddr); + addr[i] = read_eeprom(ioaddr, i + EEPROMMACAddr); + eth_hw_addr_set(net_dev, (u8 *)addr); rc = 1; break; @@ -1098,7 +1103,7 @@ sis900_init_rxfilter (struct net_device * net_dev) /* load MAC addr to filter data register */ for (i = 0 ; i < 3 ; i++) { - u32 w = (u32) *((u16 *)(net_dev->dev_addr)+i); + u32 w = (u32) *((const u16 *)(net_dev->dev_addr)+i); sw32(rfcr, i << RFADDR_shift); sw32(rfdr, w); diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index 44daf79a8f97..a0654e88444c 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -325,6 +325,7 @@ static int epic_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *dev; struct epic_private *ep; int i, ret, option = 0, duplex = 0; + __le16 addr[ETH_ALEN / 2]; void *ring_space; dma_addr_t ring_dma; @@ -416,7 +417,8 @@ static int epic_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* Note: the '175 does not have a serial EEPROM. */ for (i = 0; i < 3; i++) - ((__le16 *)dev->dev_addr)[i] = cpu_to_le16(er16(LAN0 + i*4)); + addr[i] = cpu_to_le16(er16(LAN0 + i*4)); + eth_hw_addr_set(dev, (u8 *)addr); if (debug > 2) { dev_dbg(&pdev->dev, "EEPROM contents:\n"); diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c index 42fc37c7887a..37c822e27207 100644 --- a/drivers/net/ethernet/smsc/smc91c92_cs.c +++ b/drivers/net/ethernet/smsc/smc91c92_cs.c @@ -347,6 +347,7 @@ static void smc91c92_detach(struct pcmcia_device *link) static int cvt_ascii_address(struct net_device *dev, char *s) { + u8 mac[ETH_ALEN]; int i, j, da, c; if (strlen(s) != 12) @@ -359,8 +360,9 @@ static int cvt_ascii_address(struct net_device *dev, char *s) da += ((c >= '0') && (c <= '9')) ? (c - '0') : ((c & 0x0f) + 9); } - dev->dev_addr[i] = da; + mac[i] = da; } + eth_hw_addr_set(dev, mac); return 0; } @@ -539,6 +541,7 @@ static int mot_setup(struct pcmcia_device *link) struct net_device *dev = link->priv; unsigned int ioaddr = dev->base_addr; int i, wait, loop; + u8 mac[ETH_ALEN]; u_int addr; /* Read Ethernet address from Serial EEPROM */ @@ -559,9 +562,10 @@ static int mot_setup(struct pcmcia_device *link) return -1; addr = inw(ioaddr + GENERAL); - dev->dev_addr[2*i] = addr & 0xff; - dev->dev_addr[2*i+1] = (addr >> 8) & 0xff; + mac[2*i] = addr & 0xff; + mac[2*i+1] = (addr >> 8) & 0xff; } + eth_hw_addr_set(dev, mac); return 0; } @@ -666,14 +670,13 @@ static int pcmcia_osi_mac(struct pcmcia_device *p_dev, void *priv) { struct net_device *dev = priv; - int i; if (tuple->TupleDataLen < 8) return -EINVAL; if (tuple->TupleData[0] != 0x04) return -EINVAL; - for (i = 0; i < 6; i++) - dev->dev_addr[i] = tuple->TupleData[i+2]; + + eth_hw_addr_set(dev, &tuple->TupleData[2]); return 0; }; diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index fa387510c189..73bcc6f2bb6e 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -1503,7 +1503,7 @@ static int smsc911x_soft_reset(struct smsc911x_data *pdata) /* Sets the device MAC address to dev_addr, called with mac_lock held */ static void -smsc911x_set_hw_mac_address(struct smsc911x_data *pdata, u8 dev_addr[6]) +smsc911x_set_hw_mac_address(struct smsc911x_data *pdata, const u8 dev_addr[6]) { u32 mac_high16 = (dev_addr[5] << 8) | dev_addr[4]; u32 mac_low32 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index 3d1176588f7d..d207c0b463ab 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -404,7 +404,7 @@ static const struct ethtool_ops smsc9420_ethtool_ops = { static void smsc9420_set_mac_address(struct net_device *dev) { struct smsc9420_pdata *pd = netdev_priv(dev); - u8 *dev_addr = dev->dev_addr; + const u8 *dev_addr = dev->dev_addr; u32 mac_high16 = (dev_addr[5] << 8) | dev_addr[4]; u32 mac_low32 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 4b0fe0f58bbf..2c48f8b8ab71 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1935,6 +1935,17 @@ static const struct ave_soc_data ave_pxs3_data = { .get_pinmode = ave_pxs3_get_pinmode, }; +static const struct ave_soc_data ave_nx1_data = { + .is_desc_64bit = true, + .clock_names = { + "ether", + }, + .reset_names = { + "ether", + }, + .get_pinmode = ave_pxs3_get_pinmode, +}; + static const struct of_device_id of_ave_match[] = { { .compatible = "socionext,uniphier-pro4-ave4", @@ -1956,6 +1967,10 @@ static const struct of_device_id of_ave_match[] = { .compatible = "socionext,uniphier-pxs3-ave4", .data = &ave_pxs3_data, }, + { + .compatible = "socionext,uniphier-nx1-ave4", + .data = &ave_nx1_data, + }, { /* Sentinel */ } }; MODULE_DEVICE_TABLE(of, of_ave_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index b6d945ea903d..9160f9ed363a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -546,13 +546,13 @@ int dwmac4_setup(struct stmmac_priv *priv); int dwxgmac2_setup(struct stmmac_priv *priv); int dwxlgmac2_setup(struct stmmac_priv *priv); -void stmmac_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low); void stmmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr, unsigned int high, unsigned int low); void stmmac_set_mac(void __iomem *ioaddr, bool enable); -void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low); void stmmac_dwmac4_get_mac_addr(void __iomem *ioaddr, unsigned char *addr, unsigned int high, unsigned int low); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c index fbfda55b4c52..5e731a72cce8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c @@ -71,6 +71,7 @@ err_remove_config_dt: static const struct of_device_id dwmac_generic_match[] = { { .compatible = "st,spear600-gmac"}, + { .compatible = "snps,dwmac-3.40a"}, { .compatible = "snps,dwmac-3.50a"}, { .compatible = "snps,dwmac-3.610"}, { .compatible = "snps,dwmac-3.70a"}, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index ed817011a94a..6924a6aacbd5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -21,6 +21,7 @@ #include <linux/delay.h> #include <linux/mfd/syscon.h> #include <linux/regmap.h> +#include <linux/pm_runtime.h> #include "stmmac_platform.h" @@ -1528,6 +1529,8 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv) return ret; } + pm_runtime_get_sync(dev); + if (bsp_priv->integrated_phy) rk_gmac_integrated_phy_powerup(bsp_priv); @@ -1539,6 +1542,8 @@ static void rk_gmac_powerdown(struct rk_priv_data *gmac) if (gmac->integrated_phy) rk_gmac_integrated_phy_powerdown(gmac); + pm_runtime_put_sync(&gmac->pdev->dev); + phy_power_on(gmac, false); gmac_clk_enable(gmac, false); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 4422baeed3d8..617d0e4c6495 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -634,7 +634,7 @@ static void sun8i_dwmac_set_mac(void __iomem *ioaddr, bool enable) * If addr is NULL, clear the slot */ static void sun8i_dwmac_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index fc8759f146c7..76edb9b72675 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -104,7 +104,7 @@ static void dwmac1000_dump_regs(struct mac_device_info *hw, u32 *reg_space) } static void dwmac1000_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index 90383abafa66..f5581db0ba9b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -218,11 +218,18 @@ static void dwmac1000_dump_dma_regs(void __iomem *ioaddr, u32 *reg_space) readl(ioaddr + DMA_BUS_MODE + i * 4); } -static void dwmac1000_get_hw_feature(void __iomem *ioaddr, - struct dma_features *dma_cap) +static int dwmac1000_get_hw_feature(void __iomem *ioaddr, + struct dma_features *dma_cap) { u32 hw_cap = readl(ioaddr + DMA_HW_FEATURE); + if (!hw_cap) { + /* 0x00000000 is the value read on old hardware that does not + * implement this register + */ + return -EOPNOTSUPP; + } + dma_cap->mbps_10_100 = (hw_cap & DMA_HW_FEAT_MIISEL); dma_cap->mbps_1000 = (hw_cap & DMA_HW_FEAT_GMIISEL) >> 1; dma_cap->half_duplex = (hw_cap & DMA_HW_FEAT_HDSEL) >> 2; @@ -252,6 +259,8 @@ static void dwmac1000_get_hw_feature(void __iomem *ioaddr, dma_cap->number_tx_channel = (hw_cap & DMA_HW_FEAT_TXCHCNT) >> 22; /* Alternate (enhanced) DESC mode */ dma_cap->enh_desc = (hw_cap & DMA_HW_FEAT_ENHDESSEL) >> 24; + + return 0; } static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index ebcad8dd99db..75071a7d551a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -68,7 +68,7 @@ static int dwmac100_irq_status(struct mac_device_info *hw, } static void dwmac100_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index b21745368983..fd41db65fe1d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -322,7 +322,7 @@ static void dwmac4_pmt(struct mac_device_info *hw, unsigned long mode) } static void dwmac4_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, unsigned int reg_n) + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 5be8e6a631d9..d99fa028c646 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -347,8 +347,8 @@ static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode, writel(mtl_tx_op, ioaddr + MTL_CHAN_TX_OP_MODE(channel)); } -static void dwmac4_get_hw_feature(void __iomem *ioaddr, - struct dma_features *dma_cap) +static int dwmac4_get_hw_feature(void __iomem *ioaddr, + struct dma_features *dma_cap) { u32 hw_cap = readl(ioaddr + GMAC_HW_FEATURE0); @@ -437,6 +437,8 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr, dma_cap->frpbs = (hw_cap & GMAC_HW_FEAT_FRPBS) >> 11; dma_cap->frpsel = (hw_cap & GMAC_HW_FEAT_FRPSEL) >> 10; dma_cap->dvlan = (hw_cap & GMAC_HW_FEAT_DVLAN) >> 5; + + return 0; } /* Enable/disable TSO feature and set MSS */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 9292a1fab7d3..d1c605777985 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -187,7 +187,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr, return ret; } -void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low) { unsigned long data; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index d1c31200bb91..caa4bfc4c1d6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -239,7 +239,7 @@ void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr) do {} while ((readl(ioaddr + DMA_CONTROL) & DMA_CONTROL_FTF)); } -void stmmac_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low) { unsigned long data; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index c4d78fa93663..c6c4d7948fe5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -335,7 +335,8 @@ static void dwxgmac2_pmt(struct mac_device_info *hw, unsigned long mode) } static void dwxgmac2_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, unsigned int reg_n) + const unsigned char *addr, + unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; u32 value; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 906e985441a9..5e98355f422b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -371,8 +371,8 @@ static int dwxgmac2_dma_interrupt(void __iomem *ioaddr, return ret; } -static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, - struct dma_features *dma_cap) +static int dwxgmac2_get_hw_feature(void __iomem *ioaddr, + struct dma_features *dma_cap) { u32 hw_cap; @@ -445,6 +445,8 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, dma_cap->frpes = (hw_cap & XGMAC_HWFEAT_FRPES) >> 11; dma_cap->frpbs = (hw_cap & XGMAC_HWFEAT_FRPPB) >> 9; dma_cap->frpsel = (hw_cap & XGMAC_HWFEAT_FRPSEL) >> 3; + + return 0; } static void dwxgmac2_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 queue) diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 6dc1c98ebec8..f7dc447f05a0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -203,8 +203,8 @@ struct stmmac_dma_ops { int (*dma_interrupt) (void __iomem *ioaddr, struct stmmac_extra_stats *x, u32 chan, u32 dir); /* If supported then get the optional core features */ - void (*get_hw_feature)(void __iomem *ioaddr, - struct dma_features *dma_cap); + int (*get_hw_feature)(void __iomem *ioaddr, + struct dma_features *dma_cap); /* Program the HW RX Watchdog */ void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 queue); void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan); @@ -255,7 +255,7 @@ struct stmmac_dma_ops { #define stmmac_dma_interrupt_status(__priv, __args...) \ stmmac_do_callback(__priv, dma, dma_interrupt, __args) #define stmmac_get_hw_feature(__priv, __args...) \ - stmmac_do_void_callback(__priv, dma, get_hw_feature, __args) + stmmac_do_callback(__priv, dma, get_hw_feature, __args) #define stmmac_rx_watchdog(__priv, __args...) \ stmmac_do_void_callback(__priv, dma, rx_watchdog, __args) #define stmmac_set_tx_ring_len(__priv, __args...) \ @@ -330,7 +330,8 @@ struct stmmac_ops { /* Set power management mode (e.g. magic frame) */ void (*pmt)(struct mac_device_info *hw, unsigned long mode); /* Set/Get Unicast MAC addresses */ - void (*set_umac_addr)(struct mac_device_info *hw, unsigned char *addr, + void (*set_umac_addr)(struct mac_device_info *hw, + const unsigned char *addr, unsigned int reg_n); void (*get_umac_addr)(struct mac_device_info *hw, unsigned char *addr, unsigned int reg_n); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4415226263e6..b720539ccb0a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -477,6 +477,10 @@ bool stmmac_eee_init(struct stmmac_priv *priv) stmmac_lpi_entry_timer_config(priv, 0); del_timer_sync(&priv->eee_ctrl_timer); stmmac_set_eee_timer(priv, priv->hw, 0, eee_tw_timer); + if (priv->hw->xpcs) + xpcs_config_eee(priv->hw->xpcs, + priv->plat->mult_fact_100ns, + false); } mutex_unlock(&priv->lock); return false; @@ -1038,7 +1042,7 @@ static void stmmac_mac_link_down(struct phylink_config *config, stmmac_mac_set(priv, priv->ioaddr, false); priv->eee_active = false; priv->tx_lpi_enabled = false; - stmmac_eee_init(priv); + priv->eee_enabled = stmmac_eee_init(priv); stmmac_set_eee_pls(priv, priv->hw, false); if (priv->dma_cap.fpesel) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 62cec9bfcd33..232ac98943cd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -508,6 +508,14 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->pmt = 1; } + if (of_device_is_compatible(np, "snps,dwmac-3.40a")) { + plat->has_gmac = 1; + plat->enh_desc = 1; + plat->tx_coe = 1; + plat->bugged_jumbo = 1; + plat->pmt = 1; + } + if (of_device_is_compatible(np, "snps,dwmac-4.00") || of_device_is_compatible(np, "snps,dwmac-4.10a") || of_device_is_compatible(np, "snps,dwmac-4.20a") || diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index e649a3e6a529..be3cb63675a5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -36,7 +36,7 @@ struct stmmac_packet_attrs { int vlan_id_in; int vlan_id_out; unsigned char *src; - unsigned char *dst; + const unsigned char *dst; u32 ip_src; u32 ip_dst; int tcp; @@ -249,8 +249,8 @@ static int stmmac_test_loopback_validate(struct sk_buff *skb, struct net_device *orig_ndev) { struct stmmac_test_priv *tpriv = pt->af_packet_priv; + const unsigned char *dst = tpriv->packet->dst; unsigned char *src = tpriv->packet->src; - unsigned char *dst = tpriv->packet->dst; struct stmmachdr *shdr; struct ethhdr *ehdr; struct udphdr *uhdr; diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 287ae4c538aa..d2d4f47c7e28 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -3027,7 +3027,7 @@ static void cas_mac_reset(struct cas *cp) /* Must be invoked under cp->lock. */ static void cas_init_mac(struct cas *cp) { - unsigned char *e = &cp->dev->dev_addr[0]; + const unsigned char *e = &cp->dev->dev_addr[0]; int i; cas_mac_reset(cp); @@ -3379,6 +3379,7 @@ static void cas_check_pci_invariants(struct cas *cp) static int cas_check_invariants(struct cas *cp) { struct pci_dev *pdev = cp->pdev; + u8 addr[ETH_ALEN]; u32 cfg; int i; @@ -3407,8 +3408,8 @@ static int cas_check_invariants(struct cas *cp) /* finish phy determination. MDIO1 takes precedence over MDIO0 if * they're both connected. */ - cp->phy_type = cas_get_vpd_info(cp, cp->dev->dev_addr, - PCI_SLOT(pdev->devfn)); + cp->phy_type = cas_get_vpd_info(cp, addr, PCI_SLOT(pdev->devfn)); + eth_hw_addr_set(cp->dev, addr); if (cp->phy_type & CAS_PHY_SERDES) { cp->cas_flags |= CAS_FLAG_1000MB_CAP; return 0; /* no more checking needed */ diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 50bd4e3b0af9..6b59b14e74b1 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -230,7 +230,6 @@ static struct net_device *vsw_alloc_netdev(u8 hwaddr[], { struct net_device *dev; struct vnet_port *port; - int i; dev = alloc_etherdev_mqs(sizeof(*port), VNET_MAX_TXQS, 1); if (!dev) @@ -238,10 +237,8 @@ static struct net_device *vsw_alloc_netdev(u8 hwaddr[], dev->needed_headroom = VNET_PACKET_SKIP + 8; dev->needed_tailroom = 8; - for (i = 0; i < ETH_ALEN; i++) { - dev->dev_addr[i] = hwaddr[i]; - dev->perm_addr[i] = dev->dev_addr[i]; - } + eth_hw_addr_set(dev, hwaddr); + ether_addr_copy(dev->perm_addr, dev->dev_addr); sprintf(dev->name, "vif%d.%d", (int)handle, (int)port_id); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 1a73a9401347..ba8ad76313a9 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -2603,7 +2603,7 @@ static int niu_init_link(struct niu *np) return 0; } -static void niu_set_primary_mac(struct niu *np, unsigned char *addr) +static void niu_set_primary_mac(struct niu *np, const unsigned char *addr) { u16 reg0 = addr[4] << 8 | addr[5]; u16 reg1 = addr[2] << 8 | addr[3]; @@ -8312,6 +8312,7 @@ static void niu_pci_vpd_validate(struct niu *np) { struct net_device *dev = np->dev; struct niu_vpd *vpd = &np->vpd; + u8 addr[ETH_ALEN]; u8 val8; if (!is_valid_ether_addr(&vpd->local_mac[0])) { @@ -8344,17 +8345,20 @@ static void niu_pci_vpd_validate(struct niu *np) return; } - eth_hw_addr_set(dev, vpd->local_mac); + ether_addr_copy(addr, vpd->local_mac); - val8 = dev->dev_addr[5]; - dev->dev_addr[5] += np->port; - if (dev->dev_addr[5] < val8) - dev->dev_addr[4]++; + val8 = addr[5]; + addr[5] += np->port; + if (addr[5] < val8) + addr[4]++; + + eth_hw_addr_set(dev, addr); } static int niu_pci_probe_sprom(struct niu *np) { struct net_device *dev = np->dev; + u8 addr[ETH_ALEN]; int len, i; u64 val, sum; u8 val8; @@ -8446,27 +8450,29 @@ static int niu_pci_probe_sprom(struct niu *np) val = nr64(ESPC_MAC_ADDR0); netif_printk(np, probe, KERN_DEBUG, np->dev, "SPROM: MAC_ADDR0[%08llx]\n", (unsigned long long)val); - dev->dev_addr[0] = (val >> 0) & 0xff; - dev->dev_addr[1] = (val >> 8) & 0xff; - dev->dev_addr[2] = (val >> 16) & 0xff; - dev->dev_addr[3] = (val >> 24) & 0xff; + addr[0] = (val >> 0) & 0xff; + addr[1] = (val >> 8) & 0xff; + addr[2] = (val >> 16) & 0xff; + addr[3] = (val >> 24) & 0xff; val = nr64(ESPC_MAC_ADDR1); netif_printk(np, probe, KERN_DEBUG, np->dev, "SPROM: MAC_ADDR1[%08llx]\n", (unsigned long long)val); - dev->dev_addr[4] = (val >> 0) & 0xff; - dev->dev_addr[5] = (val >> 8) & 0xff; + addr[4] = (val >> 0) & 0xff; + addr[5] = (val >> 8) & 0xff; - if (!is_valid_ether_addr(&dev->dev_addr[0])) { + if (!is_valid_ether_addr(addr)) { dev_err(np->device, "SPROM MAC address invalid [ %pM ]\n", - dev->dev_addr); + addr); return -EINVAL; } - val8 = dev->dev_addr[5]; - dev->dev_addr[5] += np->port; - if (dev->dev_addr[5] < val8) - dev->dev_addr[4]++; + val8 = addr[5]; + addr[5] += np->port; + if (addr[5] < val8) + addr[4]++; + + eth_hw_addr_set(dev, addr); val = nr64(ESPC_MOD_STR_LEN); netif_printk(np, probe, KERN_DEBUG, np->dev, diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index c646575e79d5..531a6f449afa 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -623,7 +623,7 @@ static int bigmac_init_hw(struct bigmac *bp, bool non_blocking) void __iomem *cregs = bp->creg; void __iomem *bregs = bp->bregs; __u32 bblk_dvma = (__u32)bp->bblock_dvma; - unsigned char *e = &bp->dev->dev_addr[0]; + const unsigned char *e = &bp->dev->dev_addr[0]; /* Latch current counters into statistics. */ bigmac_get_counters(bp, bregs); @@ -1076,7 +1076,6 @@ static int bigmac_ether_init(struct platform_device *op, struct net_device *dev; u8 bsizes, bsizes_more; struct bigmac *bp; - int i; /* Get a new device struct for this interface. */ dev = alloc_etherdev(sizeof(struct bigmac)); @@ -1086,8 +1085,7 @@ static int bigmac_ether_init(struct platform_device *op, if (version_printed++ == 0) printk(KERN_INFO "%s", version); - for (i = 0; i < 6; i++) - dev->dev_addr[i] = idprom->id_ethaddr[i]; + eth_hw_addr_set(dev, idprom->id_ethaddr); /* Setup softc, with backpointers to QEC and BigMAC SBUS device structs. */ bp = netdev_priv(dev); diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index 5f786d6fa150..036856102c50 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -1810,7 +1810,7 @@ static u32 gem_setup_multicast(struct gem *gp) static void gem_init_mac(struct gem *gp) { - unsigned char *e = &gp->dev->dev_addr[0]; + const unsigned char *e = &gp->dev->dev_addr[0]; writel(0x1bf0, gp->regs + MAC_SNDPAUSE); @@ -2087,7 +2087,7 @@ static void gem_stop_phy(struct gem *gp, int wol) writel(mifcfg, gp->regs + MIF_CFG); if (wol && gp->has_wol) { - unsigned char *e = &gp->dev->dev_addr[0]; + const unsigned char *e = &gp->dev->dev_addr[0]; u32 csr; /* Setup wake-on-lan for MAGIC packet */ @@ -2431,8 +2431,8 @@ static struct net_device_stats *gem_get_stats(struct net_device *dev) static int gem_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *macaddr = (struct sockaddr *) addr; + const unsigned char *e = &dev->dev_addr[0]; struct gem *gp = netdev_priv(dev); - unsigned char *e = &dev->dev_addr[0]; if (!is_valid_ether_addr(macaddr->sa_data)) return -EADDRNOTAVAIL; @@ -2799,7 +2799,10 @@ static int gem_get_device_address(struct gem *gp) } eth_hw_addr_set(dev, addr); #else - get_gem_mac_nonobp(gp->pdev, gp->dev->dev_addr); + u8 addr[ETH_ALEN]; + + get_gem_mac_nonobp(gp->pdev, addr); + eth_hw_addr_set(gp->dev, addr); #endif return 0; } diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index fe5482b1872f..ad9029ae6848 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -1395,13 +1395,13 @@ force_link: /* hp->happy_lock must be held */ static int happy_meal_init(struct happy_meal *hp) { + const unsigned char *e = &hp->dev->dev_addr[0]; void __iomem *gregs = hp->gregs; void __iomem *etxregs = hp->etxregs; void __iomem *erxregs = hp->erxregs; void __iomem *bregs = hp->bigmacregs; void __iomem *tregs = hp->tcvregs; u32 regtmp, rxcfg; - unsigned char *e = &hp->dev->dev_addr[0]; /* If auto-negotiation timer is running, kill it. */ del_timer(&hp->happy_timer); @@ -2661,6 +2661,7 @@ static int happy_meal_sbus_probe_one(struct platform_device *op, int is_qfe) struct happy_meal *hp; struct net_device *dev; int i, qfe_slot = -1; + u8 addr[ETH_ALEN]; int err = -ENODEV; sbus_dp = op->dev.parent->of_node; @@ -2698,7 +2699,8 @@ static int happy_meal_sbus_probe_one(struct platform_device *op, int is_qfe) } if (i < 6) { /* a mac address was given */ for (i = 0; i < 6; i++) - dev->dev_addr[i] = macaddr[i]; + addr[i] = macaddr[i]; + eth_hw_addr_set(dev, addr); macaddr[5]++; } else { const unsigned char *addr; @@ -2969,6 +2971,7 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, unsigned long hpreg_res; int i, qfe_slot = -1; char prom_name[64]; + u8 addr[ETH_ALEN]; int err; /* Now make sure pci_dev cookie is there. */ @@ -3044,7 +3047,8 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, } if (i < 6) { /* a mac address was given */ for (i = 0; i < 6; i++) - dev->dev_addr[i] = macaddr[i]; + addr[i] = macaddr[i]; + eth_hw_addr_set(dev, addr); macaddr[5]++; } else { #ifdef CONFIG_SPARC @@ -3060,7 +3064,10 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, eth_hw_addr_set(dev, idprom->id_ethaddr); } #else - get_hme_mac_nonsparc(pdev, &dev->dev_addr[0]); + u8 addr[ETH_ALEN]; + + get_hme_mac_nonsparc(pdev, addr); + eth_hw_addr_set(dev, addr); #endif } diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c index 52b1053a0a77..efe0d33f6024 100644 --- a/drivers/net/ethernet/sun/sunqe.c +++ b/drivers/net/ethernet/sun/sunqe.c @@ -144,7 +144,7 @@ static int qe_init(struct sunqe *qep, int from_irq) void __iomem *cregs = qep->qcregs; void __iomem *mregs = qep->mregs; void __iomem *gregs = qecp->gregs; - unsigned char *e = &qep->dev->dev_addr[0]; + const unsigned char *e = &qep->dev->dev_addr[0]; __u32 qblk_dvma = (__u32)qep->qblock_dvma; u32 tmp; int i; diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 58ee89223951..da8119625cf3 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -285,6 +285,7 @@ static struct vnet *vnet_new(const u64 *local_mac, struct vio_dev *vdev) { struct net_device *dev; + u8 addr[ETH_ALEN]; struct vnet *vp; int err, i; @@ -295,7 +296,8 @@ static struct vnet *vnet_new(const u64 *local_mac, dev->needed_tailroom = 8; for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = (*local_mac >> (5 - i) * 8) & 0xff; + addr[i] = (*local_mac >> (5 - i) * 8) & 0xff; + eth_hw_addr_set(dev, addr); vp = netdev_priv(dev); diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c index bf6c1c6779ff..76eb7db80f13 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c @@ -57,7 +57,7 @@ static int xlgmac_enable_rx_csum(struct xlgmac_pdata *pdata) return 0; } -static int xlgmac_set_mac_address(struct xlgmac_pdata *pdata, u8 *addr) +static int xlgmac_set_mac_address(struct xlgmac_pdata *pdata, const u8 *addr) { unsigned int mac_addr_hi, mac_addr_lo; diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac.h b/drivers/net/ethernet/synopsys/dwc-xlgmac.h index 8598aaf3ec99..98e3a271e017 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac.h +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac.h @@ -410,7 +410,7 @@ struct xlgmac_hw_ops { void (*dev_xmit)(struct xlgmac_channel *channel); int (*dev_read)(struct xlgmac_channel *channel); - int (*set_mac_address)(struct xlgmac_pdata *pdata, u8 *addr); + int (*set_mac_address)(struct xlgmac_pdata *pdata, const u8 *addr); int (*config_rx_mode)(struct xlgmac_pdata *pdata); int (*enable_rx_csum)(struct xlgmac_pdata *pdata); int (*disable_rx_csum)(struct xlgmac_pdata *pdata); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 6904bfaa5777..c092cb61416a 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1918,7 +1918,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) port->port_id, port->slave.mac_addr); if (!is_valid_ether_addr(port->slave.mac_addr)) { - random_ether_addr(port->slave.mac_addr); + eth_random_addr(port->slave.mac_addr); dev_err(dev, "Use random MAC address\n"); } } diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index 02d4e51f7306..7449436fc87c 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -1112,7 +1112,7 @@ static int cpmac_probe(struct platform_device *pdev) priv->dev = dev; priv->ring_size = 64; priv->msg_enable = netif_msg_init(debug_level, 0xff); - memcpy(dev->dev_addr, pdata->dev_addr, sizeof(pdata->dev_addr)); + eth_hw_addr_set(dev, pdata->dev_addr); snprintf(priv->phy_name, MII_BUS_ID_SIZE, PHY_ID_FMT, mdio_bus_id, phy_id); diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 4538e597eefe..2d2dcf70563f 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1402,7 +1402,6 @@ static int match_first_device(struct device *dev, const void *data) static int emac_dev_open(struct net_device *ndev) { struct device *emac_dev = &ndev->dev; - u32 cnt; struct resource *res; int q, m, ret; int res_num = 0, irq_num = 0; @@ -1420,8 +1419,7 @@ static int emac_dev_open(struct net_device *ndev) } netif_carrier_off(ndev); - for (cnt = 0; cnt < ETH_ALEN; cnt++) - ndev->dev_addr[cnt] = priv->mac_addr[cnt]; + eth_hw_addr_set(ndev, priv->mac_addr); /* Configuration items */ priv->rx_buf_size = EMAC_DEF_MAX_FRAME_SIZE + NET_IP_ALIGN; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index b666e1b53c5f..b818e4579f6f 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -2030,14 +2030,14 @@ static int netcp_create_interface(struct netcp_device *netcp_device, if (is_valid_ether_addr(efuse_mac_addr)) eth_hw_addr_set(ndev, efuse_mac_addr); else - eth_random_addr(ndev->dev_addr); + eth_hw_addr_random(ndev); devm_iounmap(dev, efuse); devm_release_mem_region(dev, res.start, size); } else { ret = of_get_ethdev_address(node_interface, ndev); if (ret) - eth_random_addr(ndev->dev_addr); + eth_hw_addr_random(ndev); } ret = of_property_read_string(node_interface, "rx-channel", diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index 77c448ad67ce..eab7d78d7c72 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -184,7 +184,7 @@ static void tlan_print_list(struct tlan_list *, char *, int); static void tlan_read_and_clear_stats(struct net_device *, int); static void tlan_reset_adapter(struct net_device *); static void tlan_finish_reset(struct net_device *); -static void tlan_set_mac(struct net_device *, int areg, char *mac); +static void tlan_set_mac(struct net_device *, int areg, const char *mac); static void __tlan_phy_print(struct net_device *); static void tlan_phy_print(struct net_device *); @@ -2346,7 +2346,7 @@ tlan_finish_reset(struct net_device *dev) * **************************************************************/ -static void tlan_set_mac(struct net_device *dev, int areg, char *mac) +static void tlan_set_mac(struct net_device *dev, int areg, const char *mac) { int i; diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index 93453e5713b2..ce38f7515225 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -725,6 +725,7 @@ static int tc35815_init_dev_addr(struct net_device *dev) { struct tc35815_regs __iomem *tr = (struct tc35815_regs __iomem *)dev->base_addr; + u8 addr[ETH_ALEN]; int i; while (tc_readl(&tr->PROM_Ctl) & PROM_Busy) @@ -735,9 +736,10 @@ static int tc35815_init_dev_addr(struct net_device *dev) while (tc_readl(&tr->PROM_Ctl) & PROM_Busy) ; data = tc_readl(&tr->PROM_Data); - dev->dev_addr[i] = data & 0xff; - dev->dev_addr[i+1] = data >> 8; + addr[i] = data & 0xff; + addr[i+1] = data >> 8; } + eth_hw_addr_set(dev, addr); if (!is_valid_ether_addr(dev->dev_addr)) return tc35815_read_plat_dev_addr(dev); return 0; @@ -1859,7 +1861,8 @@ static struct net_device_stats *tc35815_get_stats(struct net_device *dev) return &dev->stats; } -static void tc35815_set_cam_entry(struct net_device *dev, int index, unsigned char *addr) +static void tc35815_set_cam_entry(struct net_device *dev, int index, + const unsigned char *addr) { struct tc35815_local *lp = netdev_priv(dev); struct tc35815_regs __iomem *tr = diff --git a/drivers/net/ethernet/wiznet/w5100-spi.c b/drivers/net/ethernet/wiznet/w5100-spi.c index 2b84848dc26a..7779a36da3c8 100644 --- a/drivers/net/ethernet/wiznet/w5100-spi.c +++ b/drivers/net/ethernet/wiznet/w5100-spi.c @@ -463,7 +463,9 @@ static int w5100_spi_probe(struct spi_device *spi) static int w5100_spi_remove(struct spi_device *spi) { - return w5100_remove(&spi->dev); + w5100_remove(&spi->dev); + + return 0; } static const struct spi_device_id w5100_spi_ids[] = { diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c index 88fc65ed0017..ae24d6b86803 100644 --- a/drivers/net/ethernet/wiznet/w5100.c +++ b/drivers/net/ethernet/wiznet/w5100.c @@ -1064,7 +1064,9 @@ static int w5100_mmio_probe(struct platform_device *pdev) static int w5100_mmio_remove(struct platform_device *pdev) { - return w5100_remove(&pdev->dev); + w5100_remove(&pdev->dev); + + return 0; } void *w5100_ops_priv(const struct net_device *ndev) @@ -1210,7 +1212,7 @@ err_register: } EXPORT_SYMBOL_GPL(w5100_probe); -int w5100_remove(struct device *dev) +void w5100_remove(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct w5100_priv *priv = netdev_priv(ndev); @@ -1226,7 +1228,6 @@ int w5100_remove(struct device *dev) unregister_netdev(ndev); free_netdev(ndev); - return 0; } EXPORT_SYMBOL_GPL(w5100_remove); diff --git a/drivers/net/ethernet/wiznet/w5100.h b/drivers/net/ethernet/wiznet/w5100.h index 5d3d4b541fec..481af3b6d9e8 100644 --- a/drivers/net/ethernet/wiznet/w5100.h +++ b/drivers/net/ethernet/wiznet/w5100.h @@ -31,6 +31,6 @@ void *w5100_ops_priv(const struct net_device *ndev); int w5100_probe(struct device *dev, const struct w5100_ops *ops, int sizeof_ops_priv, const void *mac_addr, int irq, int link_gpio); -int w5100_remove(struct device *dev); +void w5100_remove(struct device *dev); extern const struct dev_pm_ops w5100_pm_ops; diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index b95aee8607a4..0815de581c7f 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -206,12 +206,13 @@ static void xemaclite_disable_interrupts(struct net_local *drvdata) * This function writes data from a 16-bit aligned buffer to a 32-bit aligned * address in the EmacLite device. */ -static void xemaclite_aligned_write(void *src_ptr, u32 *dest_ptr, +static void xemaclite_aligned_write(const void *src_ptr, u32 *dest_ptr, unsigned length) { + const u16 *from_u16_ptr; u32 align_buffer; u32 *to_u32_ptr; - u16 *from_u16_ptr, *to_u16_ptr; + u16 *to_u16_ptr; to_u32_ptr = dest_ptr; from_u16_ptr = src_ptr; @@ -470,7 +471,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen) * buffers (if configured). */ static void xemaclite_update_address(struct net_local *drvdata, - u8 *address_ptr) + const u8 *address_ptr) { void __iomem *addr; u32 reg_data; diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index ae611e46da6a..f9587e55b842 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -671,7 +671,6 @@ static int pcmcia_get_mac_ce(struct pcmcia_device *p_dev, void *priv) { struct net_device *dev = priv; - int i; if (tuple->TupleDataLen != 13) return -EINVAL; @@ -679,8 +678,7 @@ static int pcmcia_get_mac_ce(struct pcmcia_device *p_dev, (tuple->TupleData[2] != 6)) return -EINVAL; /* another try (James Lehmer's CE2 version 4.1)*/ - for (i = 2; i < 6; i++) - dev->dev_addr[i] = tuple->TupleData[i+2]; + dev_addr_mod(dev, 2, &tuple->TupleData[2], 4); return 0; }; @@ -742,11 +740,9 @@ xirc2ps_config(struct pcmcia_device * link) len = pcmcia_get_tuple(link, 0x89, &buf); /* data layout looks like tuple 0x22 */ if (buf && len == 8) { - if (*buf == CISTPL_FUNCE_LAN_NODE_ID) { - int i; - for (i = 2; i < 6; i++) - dev->dev_addr[i] = buf[i+2]; - } else + if (*buf == CISTPL_FUNCE_LAN_NODE_ID) + dev_addr_mod(dev, 2, &buf[2], 4); + else err = -1; } kfree(buf); @@ -1271,7 +1267,7 @@ struct set_address_info { unsigned int ioaddr; }; -static void set_address(struct set_address_info *sa_info, char *addr) +static void set_address(struct set_address_info *sa_info, const char *addr) { unsigned int ioaddr = sa_info->ioaddr; int i; diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 6192244b304a..f4e8793e995d 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -288,7 +288,7 @@ static int sp_set_mac_address(struct net_device *dev, void *addr) netif_tx_lock_bh(dev); netif_addr_lock(dev); - memcpy(dev->dev_addr, &sa->sax25_call, AX25_ADDR_LEN); + __dev_addr_set(dev, &sa->sax25_call, AX25_ADDR_LEN); netif_addr_unlock(dev); netif_tx_unlock_bh(dev); @@ -317,7 +317,7 @@ static void sp_setup(struct net_device *dev) /* Only activated in AX.25 mode */ memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); dev->flags = 0; } @@ -726,7 +726,7 @@ static int sixpack_ioctl(struct tty_struct *tty, struct file *file, } netif_tx_lock_bh(dev); - memcpy(dev->dev_addr, &addr, AX25_ADDR_LEN); + __dev_addr_set(dev, &addr, AX25_ADDR_LEN); netif_tx_unlock_bh(dev); err = 0; break; diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index 775dcf4ebde5..62da837cc707 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -791,7 +791,7 @@ static int baycom_set_mac_address(struct net_device *dev, void *addr) struct sockaddr *sa = (struct sockaddr *)addr; /* addr is an AX.25 shifted ASCII mac address */ - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -1159,7 +1159,7 @@ static void baycom_probe(struct net_device *dev) dev->mtu = AX25_DEF_PACLEN; /* eth_mtu is the default */ dev->addr_len = AX25_ADDR_LEN; /* sizeof an ax.25 address */ memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &null_ax25_address, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&null_ax25_address); dev->tx_queue_len = 16; /* New style flags */ diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index d967b0748773..30af0081e2be 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -302,7 +302,7 @@ static int bpq_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = (struct sockaddr *)addr; - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -457,9 +457,6 @@ static void bpq_setup(struct net_device *dev) dev->netdev_ops = &bpq_netdev_ops; dev->needs_free_netdev = true; - memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); - dev->flags = 0; dev->features = NETIF_F_LLTX; /* Allow recursion */ @@ -472,6 +469,8 @@ static void bpq_setup(struct net_device *dev) dev->mtu = AX25_DEF_PACLEN; dev->addr_len = AX25_ADDR_LEN; + memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); } /* diff --git a/drivers/net/hamradio/dmascc.c b/drivers/net/hamradio/dmascc.c index f4c3efc3e074..7e527499d3ad 100644 --- a/drivers/net/hamradio/dmascc.c +++ b/drivers/net/hamradio/dmascc.c @@ -426,7 +426,7 @@ static void __init dev_setup(struct net_device *dev) dev->addr_len = AX25_ADDR_LEN; dev->tx_queue_len = 64; memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); } static const struct net_device_ops scc_netdev_ops = { @@ -956,8 +956,7 @@ static int scc_send_packet(struct sk_buff *skb, struct net_device *dev) static int scc_set_mac_address(struct net_device *dev, void *sa) { - memcpy(dev->dev_addr, ((struct sockaddr *) sa)->sa_data, - dev->addr_len); + dev_addr_set(dev, ((struct sockaddr *)sa)->sa_data); return 0; } diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c index 5805cfc83854..b0edb91bb10a 100644 --- a/drivers/net/hamradio/hdlcdrv.c +++ b/drivers/net/hamradio/hdlcdrv.c @@ -415,7 +415,7 @@ static int hdlcdrv_set_mac_address(struct net_device *dev, void *addr) struct sockaddr *sa = (struct sockaddr *)addr; /* addr is an AX.25 shifted ASCII mac address */ - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -675,7 +675,7 @@ static void hdlcdrv_setup(struct net_device *dev) dev->mtu = AX25_DEF_PACLEN; /* eth_mtu is the default */ dev->addr_len = AX25_ADDR_LEN; /* sizeof an ax.25 address */ memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); dev->tx_queue_len = 16; } diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 8666110bec55..867252a0247b 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -344,7 +344,7 @@ static int ax_set_mac_address(struct net_device *dev, void *addr) netif_tx_lock_bh(dev); netif_addr_lock(dev); - memcpy(dev->dev_addr, &sa->sax25_call, AX25_ADDR_LEN); + __dev_addr_set(dev, &sa->sax25_call, AX25_ADDR_LEN); netif_addr_unlock(dev); netif_tx_unlock_bh(dev); @@ -647,7 +647,7 @@ static void ax_setup(struct net_device *dev) memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); dev->flags = IFF_BROADCAST | IFF_MULTICAST; } @@ -850,7 +850,7 @@ static int mkiss_ioctl(struct tty_struct *tty, struct file *file, } netif_tx_lock_bh(dev); - memcpy(dev->dev_addr, addr, AX25_ADDR_LEN); + __dev_addr_set(dev, addr, AX25_ADDR_LEN); netif_tx_unlock_bh(dev); err = 0; diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c index e0bb131a33d7..3d59dac063ac 100644 --- a/drivers/net/hamradio/scc.c +++ b/drivers/net/hamradio/scc.c @@ -1563,9 +1563,6 @@ static void scc_net_setup(struct net_device *dev) dev->netdev_ops = &scc_netdev_ops; dev->header_ops = &ax25_header_ops; - memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); - dev->flags = 0; dev->type = ARPHRD_AX25; @@ -1573,6 +1570,8 @@ static void scc_net_setup(struct net_device *dev) dev->mtu = AX25_DEF_PACLEN; dev->addr_len = AX25_ADDR_LEN; + memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); } /* ----> open network device <---- */ @@ -1951,7 +1950,7 @@ static int scc_net_siocdevprivate(struct net_device *dev, static int scc_net_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = (struct sockaddr *) addr; - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 6ddacbdb224b..6376b8485976 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -1063,7 +1063,7 @@ static int yam_set_mac_address(struct net_device *dev, void *addr) struct sockaddr *sa = (struct sockaddr *) addr; /* addr is an AX.25 shifted ASCII mac address */ - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -1107,7 +1107,7 @@ static void yam_setup(struct net_device *dev) dev->mtu = AX25_MTU; dev->addr_len = AX25_ADDR_LEN; memcpy(dev->broadcast, &ax25_bcast, AX25_ADDR_LEN); - memcpy(dev->dev_addr, &ax25_defaddr, AX25_ADDR_LEN); + dev_addr_set(dev, (u8 *)&ax25_defaddr); } static int __init yam_init_driver(void) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 479d2835a220..7e66ae1d2a59 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -803,6 +803,7 @@ void netvsc_linkstatus_callback(struct net_device *net, schedule_delayed_work(&ndev_ctx->dwork, 0); } +/* This function should only be called after skb_record_rx_queue() */ static void netvsc_xdp_xmit(struct sk_buff *skb, struct net_device *ndev) { int rc; @@ -2742,8 +2743,7 @@ static int netvsc_netdev_event(struct notifier_block *this, return NOTIFY_DONE; /* Avoid Bonding master dev with same MAC registering as VF */ - if ((event_dev->priv_flags & IFF_BONDING) && - (event_dev->flags & IFF_MASTER)) + if (netif_is_bond_master(event_dev)) return NOTIFY_DONE; switch (event) { diff --git a/drivers/net/ipa/Kconfig b/drivers/net/ipa/Kconfig index 8f99cfa14680..d037682fb7ad 100644 --- a/drivers/net/ipa/Kconfig +++ b/drivers/net/ipa/Kconfig @@ -4,6 +4,7 @@ config QCOM_IPA depends on ARCH_QCOM || COMPILE_TEST depends on QCOM_RPROC_COMMON || (QCOM_RPROC_COMMON=n && COMPILE_TEST) select QCOM_MDT_LOADER if ARCH_QCOM + select QCOM_SCM select QCOM_QMI_HELPERS help Choose Y or M here to include support for the Qualcomm diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index 1cedb634f4f7..ef02f2cf5ce1 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -162,7 +162,7 @@ static int ipvtap_device_event(struct notifier_block *unused, devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); classdev = device_create(&ipvtap_class, &dev->dev, devt, - dev, tap_name); + dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(ipvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 694e2f5dbbe5..6b12902a803f 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -169,7 +169,7 @@ static int macvtap_device_event(struct notifier_block *unused, devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); classdev = device_create(&macvtap_class, &dev->dev, devt, - dev, tap_name); + dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(macvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 2a4892402ed8..86ec5aae4289 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -748,8 +748,7 @@ struct failover *net_failover_create(struct net_device *standby_dev) failover_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; failover_dev->features |= failover_dev->hw_features; - memcpy(failover_dev->dev_addr, standby_dev->dev_addr, - failover_dev->addr_len); + dev_addr_set(failover_dev, standby_dev->dev_addr); failover_dev->min_mtu = standby_dev->min_mtu; failover_dev->max_mtu = standby_dev->max_mtu; diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index cb6645012a30..9661aca35703 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -1511,8 +1511,8 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) goto err_psample_exit; nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY; + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); - devlink_reload_enable(devlink); return 0; err_psample_exit: @@ -1566,9 +1566,7 @@ void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev) struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); struct devlink *devlink = priv_to_devlink(nsim_dev); - devlink_reload_disable(devlink); devlink_unregister(devlink); - nsim_dev_reload_destroy(nsim_dev); nsim_bpf_dev_exit(nsim_dev); diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index a5bab614ff84..98ca6b18415e 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -428,7 +428,7 @@ static int ntb_netdev_probe(struct device *client_dev) ndev->watchdog_timeo = msecs_to_jiffies(NTB_TX_TIMEOUT_MS); eth_random_addr(ndev->perm_addr); - memcpy(ndev->dev_addr, ndev->perm_addr, ndev->addr_len); + dev_addr_set(ndev, ndev->perm_addr); ndev->netdev_ops = &ntb_netdev_ops; ndev->ethtool_ops = &ntb_ethtool_ops; diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index fb0a83dc09ac..7de631f5356f 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -666,6 +666,10 @@ int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable) { int ret; + ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0); + if (ret < 0) + return ret; + if (enable) { /* Enable EEE */ ret = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN | @@ -673,9 +677,6 @@ int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable) DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL | mult_fact_100ns << DW_VR_MII_EEE_MULT_FACT_100NS_SHIFT; } else { - ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0); - if (ret < 0) - return ret; ret &= ~(DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN | DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN | DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL | @@ -690,21 +691,28 @@ int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable) if (ret < 0) return ret; - ret |= DW_VR_MII_EEE_TRN_LPI; + if (enable) + ret |= DW_VR_MII_EEE_TRN_LPI; + else + ret &= ~DW_VR_MII_EEE_TRN_LPI; + return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1, ret); } EXPORT_SYMBOL_GPL(xpcs_config_eee); static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs, unsigned int mode) { - int ret; + int ret, mdio_ctrl; /* For AN for C37 SGMII mode, the settings are :- - * 1) VR_MII_AN_CTRL Bit(2:1)[PCS_MODE] = 10b (SGMII AN) - * 2) VR_MII_AN_CTRL Bit(3) [TX_CONFIG] = 0b (MAC side SGMII) + * 1) VR_MII_MMD_CTRL Bit(12) [AN_ENABLE] = 0b (Disable SGMII AN in case + it is already enabled) + * 2) VR_MII_AN_CTRL Bit(2:1)[PCS_MODE] = 10b (SGMII AN) + * 3) VR_MII_AN_CTRL Bit(3) [TX_CONFIG] = 0b (MAC side SGMII) * DW xPCS used with DW EQoS MAC is always MAC side SGMII. - * 3) VR_MII_DIG_CTRL1 Bit(9) [MAC_AUTO_SW] = 1b (Automatic + * 4) VR_MII_DIG_CTRL1 Bit(9) [MAC_AUTO_SW] = 1b (Automatic * speed/duplex mode change by HW after SGMII AN complete) + * 5) VR_MII_MMD_CTRL Bit(12) [AN_ENABLE] = 1b (Enable SGMII AN) * * Note: Since it is MAC side SGMII, there is no need to set * SR_MII_AN_ADV. MAC side SGMII receives AN Tx Config from @@ -712,6 +720,17 @@ static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs, unsigned int mode) * between PHY and Link Partner. There is also no need to * trigger AN restart for MAC-side SGMII. */ + mdio_ctrl = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_MMD_CTRL); + if (mdio_ctrl < 0) + return mdio_ctrl; + + if (mdio_ctrl & AN_CL37_EN) { + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_MMD_CTRL, + mdio_ctrl & ~AN_CL37_EN); + if (ret < 0) + return ret; + } + ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_CTRL); if (ret < 0) return ret; @@ -736,7 +755,15 @@ static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs, unsigned int mode) else ret &= ~DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; - return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret); + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret); + if (ret < 0) + return ret; + + if (phylink_autoneg_inband(mode)) + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_MMD_CTRL, + mdio_ctrl | AN_CL37_EN); + + return ret; } static int xpcs_config_2500basex(struct dw_xpcs *xpcs) diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index ae7e1f1c59f0..69da011e82c8 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -86,15 +86,22 @@ #define AT803X_PSSR 0x11 /*PHY-Specific Status Register*/ #define AT803X_PSSR_MR_AN_COMPLETE 0x0200 -#define AT803X_DEBUG_REG_0 0x00 +#define AT803X_DEBUG_ANALOG_TEST_CTRL 0x00 +#define QCA8327_DEBUG_MANU_CTRL_EN BIT(2) +#define QCA8337_DEBUG_MANU_CTRL_EN GENMASK(3, 2) #define AT803X_DEBUG_RX_CLK_DLY_EN BIT(15) -#define AT803X_DEBUG_REG_5 0x05 +#define AT803X_DEBUG_SYSTEM_CTRL_MODE 0x05 #define AT803X_DEBUG_TX_CLK_DLY_EN BIT(8) +#define AT803X_DEBUG_REG_HIB_CTRL 0x0b +#define AT803X_DEBUG_HIB_CTRL_SEL_RST_80U BIT(10) +#define AT803X_DEBUG_HIB_CTRL_EN_ANY_CHANGE BIT(13) + #define AT803X_DEBUG_REG_3C 0x3C -#define AT803X_DEBUG_REG_3D 0x3D +#define AT803X_DEBUG_REG_GREEN 0x3D +#define AT803X_DEBUG_GATE_CLK_IN1000 BIT(6) #define AT803X_DEBUG_REG_1F 0x1F #define AT803X_DEBUG_PLL_ON BIT(2) @@ -278,25 +285,25 @@ static int at803x_read_page(struct phy_device *phydev) static int at803x_enable_rx_delay(struct phy_device *phydev) { - return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_0, 0, + return at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, 0, AT803X_DEBUG_RX_CLK_DLY_EN); } static int at803x_enable_tx_delay(struct phy_device *phydev) { - return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_5, 0, + return at803x_debug_reg_mask(phydev, AT803X_DEBUG_SYSTEM_CTRL_MODE, 0, AT803X_DEBUG_TX_CLK_DLY_EN); } static int at803x_disable_rx_delay(struct phy_device *phydev) { - return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_0, + return at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, AT803X_DEBUG_RX_CLK_DLY_EN, 0); } static int at803x_disable_tx_delay(struct phy_device *phydev) { - return at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_5, + return at803x_debug_reg_mask(phydev, AT803X_DEBUG_SYSTEM_CTRL_MODE, AT803X_DEBUG_TX_CLK_DLY_EN, 0); } @@ -1296,9 +1303,9 @@ static int qca83xx_config_init(struct phy_device *phydev) switch (switch_revision) { case 1: /* For 100M waveform */ - at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_0, 0x02ea); + at803x_debug_reg_write(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, 0x02ea); /* Turn on Gigabit clock */ - at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3D, 0x68a0); + at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_GREEN, 0x68a0); break; case 2: @@ -1306,12 +1313,95 @@ static int qca83xx_config_init(struct phy_device *phydev) fallthrough; case 4: phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_AZ_DEBUG, 0x803f); - at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3D, 0x6860); - at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_5, 0x2c46); + at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_GREEN, 0x6860); + at803x_debug_reg_write(phydev, AT803X_DEBUG_SYSTEM_CTRL_MODE, 0x2c46); at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3C, 0x6000); break; } + /* QCA8327 require DAC amplitude adjustment for 100m set to +6%. + * Disable on init and enable only with 100m speed following + * qca original source code. + */ + if (phydev->drv->phy_id == QCA8327_A_PHY_ID || + phydev->drv->phy_id == QCA8327_B_PHY_ID) + at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, + QCA8327_DEBUG_MANU_CTRL_EN, 0); + + /* Following original QCA sourcecode set port to prefer master */ + phy_set_bits(phydev, MII_CTRL1000, CTL1000_PREFER_MASTER); + + return 0; +} + +static void qca83xx_link_change_notify(struct phy_device *phydev) +{ + /* QCA8337 doesn't require DAC Amplitude adjustement */ + if (phydev->drv->phy_id == QCA8337_PHY_ID) + return; + + /* Set DAC Amplitude adjustment to +6% for 100m on link running */ + if (phydev->state == PHY_RUNNING) { + if (phydev->speed == SPEED_100) + at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, + QCA8327_DEBUG_MANU_CTRL_EN, + QCA8327_DEBUG_MANU_CTRL_EN); + } else { + /* Reset DAC Amplitude adjustment */ + at803x_debug_reg_mask(phydev, AT803X_DEBUG_ANALOG_TEST_CTRL, + QCA8327_DEBUG_MANU_CTRL_EN, 0); + } +} + +static int qca83xx_resume(struct phy_device *phydev) +{ + int ret, val; + + /* Skip reset if not suspended */ + if (!phydev->suspended) + return 0; + + /* Reinit the port, reset values set by suspend */ + qca83xx_config_init(phydev); + + /* Reset the port on port resume */ + phy_set_bits(phydev, MII_BMCR, BMCR_RESET | BMCR_ANENABLE); + + /* On resume from suspend the switch execute a reset and + * restart auto-negotiation. Wait for reset to complete. + */ + ret = phy_read_poll_timeout(phydev, MII_BMCR, val, !(val & BMCR_RESET), + 50000, 600000, true); + if (ret) + return ret; + + msleep(1); + + return 0; +} + +static int qca83xx_suspend(struct phy_device *phydev) +{ + u16 mask = 0; + + /* Only QCA8337 support actual suspend. + * QCA8327 cause port unreliability when phy suspend + * is set. + */ + if (phydev->drv->phy_id == QCA8337_PHY_ID) { + genphy_suspend(phydev); + } else { + mask |= ~(BMCR_SPEED1000 | BMCR_FULLDPLX); + phy_modify(phydev, MII_BMCR, mask, 0); + } + + at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_GREEN, + AT803X_DEBUG_GATE_CLK_IN1000, 0); + + at803x_debug_reg_mask(phydev, AT803X_DEBUG_REG_HIB_CTRL, + AT803X_DEBUG_HIB_CTRL_EN_ANY_CHANGE | + AT803X_DEBUG_HIB_CTRL_SEL_RST_80U, 0); + return 0; } @@ -1432,6 +1522,7 @@ static struct phy_driver at803x_driver[] = { .phy_id_mask = QCA8K_PHY_ID_MASK, .name = "Qualcomm Atheros 8337 internal PHY", /* PHY_GBIT_FEATURES */ + .link_change_notify = qca83xx_link_change_notify, .probe = at803x_probe, .flags = PHY_IS_INTERNAL, .config_init = qca83xx_config_init, @@ -1439,14 +1530,15 @@ static struct phy_driver at803x_driver[] = { .get_sset_count = at803x_get_sset_count, .get_strings = at803x_get_strings, .get_stats = at803x_get_stats, - .suspend = genphy_suspend, - .resume = genphy_resume, + .suspend = qca83xx_suspend, + .resume = qca83xx_resume, }, { /* QCA8327-A from switch QCA8327-AL1A */ .phy_id = QCA8327_A_PHY_ID, .phy_id_mask = QCA8K_PHY_ID_MASK, .name = "Qualcomm Atheros 8327-A internal PHY", /* PHY_GBIT_FEATURES */ + .link_change_notify = qca83xx_link_change_notify, .probe = at803x_probe, .flags = PHY_IS_INTERNAL, .config_init = qca83xx_config_init, @@ -1454,14 +1546,15 @@ static struct phy_driver at803x_driver[] = { .get_sset_count = at803x_get_sset_count, .get_strings = at803x_get_strings, .get_stats = at803x_get_stats, - .suspend = genphy_suspend, - .resume = genphy_resume, + .suspend = qca83xx_suspend, + .resume = qca83xx_resume, }, { /* QCA8327-B from switch QCA8327-BL1A */ .phy_id = QCA8327_B_PHY_ID, .phy_id_mask = QCA8K_PHY_ID_MASK, .name = "Qualcomm Atheros 8327-B internal PHY", /* PHY_GBIT_FEATURES */ + .link_change_notify = qca83xx_link_change_notify, .probe = at803x_probe, .flags = PHY_IS_INTERNAL, .config_init = qca83xx_config_init, @@ -1469,8 +1562,8 @@ static struct phy_driver at803x_driver[] = { .get_sset_count = at803x_get_sset_count, .get_strings = at803x_get_strings, .get_stats = at803x_get_stats, - .suspend = genphy_suspend, - .resume = genphy_resume, + .suspend = qca83xx_suspend, + .resume = qca83xx_resume, }, }; module_phy_driver(at803x_driver); diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 6bbc81ad295f..914619f3f0e3 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -619,6 +619,25 @@ static int dp83867_of_init(struct phy_device *phydev) #else static int dp83867_of_init(struct phy_device *phydev) { + struct dp83867_private *dp83867 = phydev->priv; + u16 delay; + + /* For non-OF device, the RX and TX ID values are either strapped + * or take from default value. So, we init RX & TX ID values here + * so that the RGMIIDCTL is configured correctly later in + * dp83867_config_init(); + */ + delay = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIIDCTL); + dp83867->rx_id_delay = delay & DP83867_RGMII_RX_CLK_DELAY_MAX; + dp83867->tx_id_delay = (delay >> DP83867_RGMII_TX_CLK_DELAY_SHIFT) & + DP83867_RGMII_TX_CLK_DELAY_MAX; + + /* Per datasheet, IO impedance is default to 50-ohm, so we set the + * same here or else the default '0' means highest IO impedance + * which is wrong. + */ + dp83867->io_impedance = DP83867_IO_MUX_CFG_IO_IMPEDANCE_MIN / 2; + return 0; } #endif /* CONFIG_OF_MDIO */ diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index d8b68145f6b4..c204067f1890 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -525,6 +525,10 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) NULL == bus->read || NULL == bus->write) return -EINVAL; + if (bus->parent && bus->parent->of_node) + bus->parent->of_node->fwnode.flags |= + FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD; + BUG_ON(bus->state != MDIOBUS_ALLOCATED && bus->state != MDIOBUS_UNREGISTERED); @@ -534,10 +538,16 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) bus->dev.groups = NULL; dev_set_name(&bus->dev, "%s", bus->id); + /* We need to set state to MDIOBUS_UNREGISTERED to correctly release + * the device in mdiobus_free() + * + * State will be updated later in this function in case of success + */ + bus->state = MDIOBUS_UNREGISTERED; + err = device_register(&bus->dev); if (err) { pr_err("mii_bus %s failed to register\n", bus->id); - put_device(&bus->dev); return -EINVAL; } @@ -961,8 +971,14 @@ EXPORT_SYMBOL_GPL(mdiobus_modify_changed); */ static int mdio_bus_match(struct device *dev, struct device_driver *drv) { + struct mdio_driver *mdiodrv = to_mdio_driver(drv); struct mdio_device *mdio = to_mdio_device(dev); + /* Both the driver and device must type-match */ + if (!(mdiodrv->mdiodrv.flags & MDIO_DEVICE_IS_PHY) != + !(mdio->flags & MDIO_DEVICE_FLAG_PHY)) + return 0; + if (of_driver_match_device(dev, drv)) return 1; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index c330a5a9f665..ff452669130a 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -863,9 +863,9 @@ static int ksz9031_config_init(struct phy_device *phydev) MII_KSZ9031RN_TX_DATA_PAD_SKEW, 4, tx_data_skews, 4, &update); - if (update && phydev->interface != PHY_INTERFACE_MODE_RGMII) + if (update && !phy_interface_is_rgmii(phydev)) phydev_warn(phydev, - "*-skew-ps values should be used only with phy-mode = \"rgmii\"\n"); + "*-skew-ps values should be used only with RGMII PHY modes\n"); /* Silicon Errata Sheet (DS80000691D or DS80000692D): * When the device links in the 1000BASE-T slave mode only, @@ -1003,6 +1003,26 @@ static int ksz9131_config_rgmii_delay(struct phy_device *phydev) txcdll_val); } +/* Silicon Errata DS80000693B + * + * When LEDs are configured in Individual Mode, LED1 is ON in a no-link + * condition. Workaround is to set register 0x1e, bit 9, this way LED1 behaves + * according to the datasheet (off if there is no link). + */ +static int ksz9131_led_errata(struct phy_device *phydev) +{ + int reg; + + reg = phy_read_mmd(phydev, 2, 0); + if (reg < 0) + return reg; + + if (!(reg & BIT(4))) + return 0; + + return phy_set_bits(phydev, 0x1e, BIT(9)); +} + static int ksz9131_config_init(struct phy_device *phydev) { struct device_node *of_node; @@ -1058,6 +1078,10 @@ static int ksz9131_config_init(struct phy_device *phydev) if (ret < 0) return ret; + ret = ksz9131_led_errata(phydev); + if (ret < 0) + return ret; + return 0; } diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index 6e32da28e138..ebfeeb3c67c1 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -273,12 +273,12 @@ static int vsc85xx_downshift_set(struct phy_device *phydev, u8 count) static int vsc85xx_wol_set(struct phy_device *phydev, struct ethtool_wolinfo *wol) { + const u8 *mac_addr = phydev->attached_dev->dev_addr; int rc; u16 reg_val; u8 i; u16 pwd[3] = {0, 0, 0}; struct ethtool_wolinfo *wol_conf = wol; - u8 *mac_addr = phydev->attached_dev->dev_addr; mutex_lock(&phydev->lock); rc = phy_select_page(phydev, MSCC_PHY_PAGE_EXTENDED_2); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index ba5ad86ec826..74d8e1dc125f 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3125,6 +3125,9 @@ static void phy_shutdown(struct device *dev) { struct phy_device *phydev = to_phy_device(dev); + if (phydev->state == PHY_READY || !phydev->attached_dev) + return; + phy_disable_interrupts(phydev); } @@ -3146,6 +3149,16 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner) return -EINVAL; } + /* PHYLIB device drivers must not match using a DT compatible table + * as this bypasses our checks that the mdiodev that is being matched + * is backed by a struct phy_device. If such a case happens, we will + * make out-of-bounds accesses and lockup in phydev->lock. + */ + if (WARN(new_driver->mdiodrv.driver.of_match_table, + "%s: driver must not provide a DT match table\n", + new_driver->name)) + return -EINVAL; + new_driver->mdiodrv.flags |= MDIO_DEVICE_IS_PHY; new_driver->mdiodrv.driver.name = new_driver->name; new_driver->mdiodrv.driver.bus = &mdio_bus_type; diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 11be60333fa8..a5671ab896b3 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -1023,6 +1023,14 @@ static struct phy_driver realtek_drvs[] = { .resume = genphy_resume, .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, + }, { + PHY_ID_MATCH_EXACT(0x001cc942), + .name = "RTL8365MB-VC Gigabit Ethernet", + /* Interrupt handling analogous to RTL8366RB */ + .config_intr = genphy_no_config_intr, + .handle_interrupt = genphy_handle_interrupt_no_ack, + .suspend = genphy_suspend, + .resume = genphy_resume, }, }; diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 34e90216bd2c..ab77a9f439ef 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -134,7 +134,7 @@ static const char * const sm_state_strings[] = { [SFP_S_LINK_UP] = "link_up", [SFP_S_TX_FAULT] = "tx_fault", [SFP_S_REINIT] = "reinit", - [SFP_S_TX_DISABLE] = "rx_disable", + [SFP_S_TX_DISABLE] = "tx_disable", }; static const char *sm_state_to_str(unsigned short sm_state) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index fb52cd175b45..1180a0e2445f 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1161,7 +1161,7 @@ static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) if (!ifname_is_set) { while (1) { snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ret); - if (!__dev_get_by_name(ppp->ppp_net, ppp->dev->name)) + if (!netdev_name_in_use(ppp->ppp_net, ppp->dev->name)) break; unit_put(&pn->units_idr, ret); ret = unit_get(&pn->units_idr, ppp, ret + 1); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index dd7917cab2b1..8b2adc56b92a 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1790,7 +1790,7 @@ static int team_set_mac_address(struct net_device *dev, void *p) if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + dev_addr_set(dev, addr->sa_data); mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) if (team->ops.port_change_dev_addr) diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index 4c5d69732a7e..f87f17503373 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -99,6 +99,10 @@ config USB_RTL8150 config USB_RTL8152 tristate "Realtek RTL8152/RTL8153 Based USB Ethernet Adapters" select MII + select CRC32 + select CRYPTO + select CRYPTO_HASH + select CRYPTO_SHA256 help This option adds support for Realtek RTL8152 based USB 2.0 10/100 Ethernet adapters and RTL8153 based USB 3.0 10/100/1000 diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index 981ac1c33780..ea06d10e1c21 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -119,7 +119,7 @@ static int aqc111_write_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value, } static int aqc111_write_cmd(struct usbnet *dev, u8 cmd, u16 value, - u16 index, u16 size, void *data) + u16 index, u16 size, const void *data) { int ret; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 5ed59d9dd631..ea8aa8c33241 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -209,7 +209,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, } static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, - u16 size, void *data, int in_pm) + u16 size, const void *data, int in_pm) { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16); @@ -272,7 +272,7 @@ static int ax88179_read_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value, } static int ax88179_write_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value, - u16 index, u16 size, void *data) + u16 index, u16 size, const void *data) { int ret; @@ -313,7 +313,7 @@ static int ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, } static int ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, - u16 size, void *data) + u16 size, const void *data) { int ret; @@ -463,7 +463,7 @@ static int ax88179_auto_detach(struct usbnet *dev, int in_pm) u16 tmp16; u8 tmp8; int (*fnr)(struct usbnet *, u8, u16, u16, u16, void *); - int (*fnw)(struct usbnet *, u8, u16, u16, u16, void *); + int (*fnw)(struct usbnet *, u8, u16, u16, u16, const void *); if (!in_pm) { fnr = ax88179_read_cmd; diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 97ba67042d12..24db5768a3c0 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -615,7 +615,7 @@ static void catc_stats_timer(struct timer_list *t) * Receive modes. Broadcast, Multicast, Promisc. */ -static void catc_multicast(unsigned char *addr, u8 *multicast) +static void catc_multicast(const unsigned char *addr, u8 *multicast) { u32 crc; diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index e1da9102a540..ad5121e9cf5d 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -275,6 +275,8 @@ static const struct net_device_ops usbpn_ops = { static void usbpn_setup(struct net_device *dev) { + const u8 addr = PN_MEDIA_USB; + dev->features = 0; dev->netdev_ops = &usbpn_ops; dev->header_ops = &phonet_header_ops; @@ -284,8 +286,8 @@ static void usbpn_setup(struct net_device *dev) dev->min_mtu = PHONET_MIN_MTU; dev->max_mtu = PHONET_MAX_MTU; dev->hard_header_len = 1; - dev->dev_addr[0] = PN_MEDIA_USB; dev->addr_len = 1; + dev_addr_set(dev, &addr); dev->tx_queue_len = 3; dev->needs_free_netdev = true; diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index dcdb46314685..48d7d278631e 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -93,7 +93,8 @@ static int dm_write_reg(struct usbnet *dev, u8 reg, u8 value) value, reg, NULL, 0); } -static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, void *data) +static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, + const void *data) { usbnet_write_cmd_async(dev, DM_WRITE_REGS, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c index cead742da381..5f42db26d200 100644 --- a/drivers/net/usb/mcs7830.c +++ b/drivers/net/usb/mcs7830.c @@ -132,7 +132,8 @@ static int mcs7830_hif_get_mac_address(struct usbnet *dev, unsigned char *addr) return 0; } -static int mcs7830_hif_set_mac_address(struct usbnet *dev, unsigned char *addr) +static int mcs7830_hif_set_mac_address(struct usbnet *dev, + const unsigned char *addr) { int ret = mcs7830_set_reg(dev, HIF_REG_ETHERNET_ADDR, ETH_ALEN, addr); diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index 6a92a3fef75e..c4cd40b090fd 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -357,7 +357,7 @@ static void set_ethernet_addr(pegasus_t *pegasus) goto err; } - memcpy(pegasus->net->dev_addr, node_id, sizeof(node_id)); + eth_hw_addr_set(pegasus->net, node_id); return; err: diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index b7fde8d448ff..4a02f33f0643 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -767,6 +767,7 @@ enum rtl8152_flags { PHY_RESET, SCHEDULE_TASKLET, GREEN_ETHERNET, + RX_EPROTO, }; #define DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2 0x3082 @@ -1770,6 +1771,14 @@ static void read_bulk_callback(struct urb *urb) rtl_set_unplug(tp); netif_device_detach(tp->netdev); return; + case -EPROTO: + urb->actual_length = 0; + spin_lock_irqsave(&tp->rx_lock, flags); + list_add_tail(&agg->list, &tp->rx_done); + spin_unlock_irqrestore(&tp->rx_lock, flags); + set_bit(RX_EPROTO, &tp->flags); + schedule_delayed_work(&tp->schedule, 1); + return; case -ENOENT: return; /* the urb is in unlink state */ case -ETIME: @@ -2425,6 +2434,7 @@ static int rx_bottom(struct r8152 *tp, int budget) if (list_empty(&tp->rx_done)) goto out1; + clear_bit(RX_EPROTO, &tp->flags); INIT_LIST_HEAD(&rx_queue); spin_lock_irqsave(&tp->rx_lock, flags); list_splice_init(&tp->rx_done, &rx_queue); @@ -2441,7 +2451,7 @@ static int rx_bottom(struct r8152 *tp, int budget) agg = list_entry(cursor, struct rx_agg, list); urb = agg->urb; - if (urb->actual_length < ETH_ZLEN) + if (urb->status != 0 || urb->actual_length < ETH_ZLEN) goto submit; agg_free = rtl_get_free_rx(tp, GFP_ATOMIC); @@ -6643,6 +6653,10 @@ static void rtl_work_func_t(struct work_struct *work) netif_carrier_ok(tp->netdev)) tasklet_schedule(&tp->tx_tl); + if (test_and_clear_bit(RX_EPROTO, &tp->flags) && + !list_empty(&tp->rx_done)) + napi_schedule(&tp->napi); + mutex_unlock(&tp->control); out1: diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 76f7af161313..3b6987bb4fbe 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -758,8 +758,7 @@ static int smsc75xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) static void smsc75xx_init_mac_address(struct usbnet *dev) { /* maybe the boot loader passed the MAC address in devicetree */ - if (!eth_platform_get_mac_address(&dev->udev->dev, - dev->net->dev_addr)) { + if (!platform_get_ethdev_address(&dev->udev->dev, dev->net)) { if (is_valid_ether_addr(dev->net->dev_addr)) { /* device tree values are valid so use them */ netif_dbg(dev, ifup, dev->net, "MAC address read from the device tree\n"); diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 26b1bd8e845b..21a42a6527dc 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -756,8 +756,7 @@ static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) static void smsc95xx_init_mac_address(struct usbnet *dev) { /* maybe the boot loader passed the MAC address in devicetree */ - if (!eth_platform_get_mac_address(&dev->udev->dev, - dev->net->dev_addr)) { + if (!platform_get_ethdev_address(&dev->udev->dev, dev->net)) { if (is_valid_ether_addr(dev->net->dev_addr)) { /* device tree values are valid so use them */ netif_dbg(dev, ifup, dev->net, "MAC address read from the device tree\n"); diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 068f197f1786..15209de1849e 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -56,7 +56,8 @@ static int sr_write_reg(struct usbnet *dev, u8 reg, u8 value) value, reg, NULL, 0); } -static void sr_write_async(struct usbnet *dev, u8 reg, u16 length, void *data) +static void sr_write_async(struct usbnet *dev, u8 reg, u16 length, + const void *data) { usbnet_write_cmd_async(dev, SR_WR_REGS, SR_REQ_WR_REG, 0, reg, data, length); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 2ed49884565f..c501b5974aee 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -408,7 +408,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, * add_recvbuf_mergeable() + get_mergeable_buf_len() */ truesize = headroom ? PAGE_SIZE : truesize; - tailroom = truesize - len - headroom; + tailroom = truesize - len - headroom - (hdr_padded_len - hdr_len); buf = p - headroom; len -= hdr_len; @@ -734,6 +734,12 @@ static struct sk_buff *receive_small(struct net_device *dev, dev->stats.rx_length_errors++; goto err_len; } + + if (likely(!vi->xdp_enabled)) { + xdp_prog = NULL; + goto skip_xdp; + } + rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { @@ -816,6 +822,7 @@ static struct sk_buff *receive_small(struct net_device *dev, } rcu_read_unlock(); +skip_xdp: skb = build_skb(buf, buflen); if (!skb) { put_page(page); @@ -897,6 +904,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, dev->stats.rx_length_errors++; goto err_skb; } + + if (likely(!vi->xdp_enabled)) { + xdp_prog = NULL; + goto skip_xdp; + } + rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { @@ -1024,6 +1037,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, } rcu_read_unlock(); +skip_xdp: head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog, metasize, headroom); curr_skb = head_skb; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 142f70670f5c..7a205ddf0060 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -2824,7 +2824,7 @@ vmxnet3_set_mac_addr(struct net_device *netdev, void *p) struct sockaddr *addr = p; struct vmxnet3_adapter *adapter = netdev_priv(netdev); - memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); + dev_addr_set(netdev, addr->sa_data); vmxnet3_write_mac_addr(adapter, addr->sa_data); return 0; @@ -3638,7 +3638,7 @@ vmxnet3_probe_device(struct pci_dev *pdev, #endif vmxnet3_read_mac_addr(adapter, mac); - memcpy(netdev->dev_addr, mac, netdev->addr_len); + dev_addr_set(netdev, mac); netdev->netdev_ops = &vmxnet3_netdev_ops; vmxnet3_set_ethtool_ops(netdev); diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 89d31adc3809..282192b82404 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -301,7 +301,7 @@ static int lapbeth_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = addr; - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } diff --git a/drivers/net/wireless/ath/ath10k/Kconfig b/drivers/net/wireless/ath/ath10k/Kconfig index 741289e385d5..ca007b800f75 100644 --- a/drivers/net/wireless/ath/ath10k/Kconfig +++ b/drivers/net/wireless/ath/ath10k/Kconfig @@ -44,7 +44,7 @@ config ATH10K_SNOC tristate "Qualcomm ath10k SNOC support" depends on ATH10K depends on ARCH_QCOM || COMPILE_TEST - depends on QCOM_SCM || !QCOM_SCM #if QCOM_SCM=m this can't be =y + select QCOM_SCM select QCOM_QMI_HELPERS help This module adds support for integrated WCN3990 chip connected diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 31f0cfba5bf5..da850f4b2919 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -2076,8 +2076,8 @@ static void ath11k_peer_assoc_h_smps(struct ieee80211_sta *sta, smps = ht_cap->cap & IEEE80211_HT_CAP_SM_PS; smps >>= IEEE80211_HT_CAP_SM_PS_SHIFT; } else { - smps = FIELD_GET(IEEE80211_HE_6GHZ_CAP_SM_PS, - le16_to_cpu(sta->he_6ghz_capa.capa)); + smps = le16_get_bits(sta->he_6ghz_capa.capa, + IEEE80211_HE_6GHZ_CAP_SM_PS); } switch (smps) { diff --git a/drivers/net/wireless/ath/ath5k/Kconfig b/drivers/net/wireless/ath/ath5k/Kconfig index f35cd8de228e..6914b37bb0fb 100644 --- a/drivers/net/wireless/ath/ath5k/Kconfig +++ b/drivers/net/wireless/ath/ath5k/Kconfig @@ -3,9 +3,7 @@ config ATH5K tristate "Atheros 5xxx wireless cards support" depends on (PCI || ATH25) && MAC80211 select ATH_COMMON - select MAC80211_LEDS - select LEDS_CLASS - select NEW_LEDS + select MAC80211_LEDS if LEDS_CLASS=y || LEDS_CLASS=MAC80211 select ATH5K_AHB if ATH25 select ATH5K_PCI if !ATH25 help diff --git a/drivers/net/wireless/ath/ath5k/led.c b/drivers/net/wireless/ath/ath5k/led.c index 6a2a16856763..33e9928af363 100644 --- a/drivers/net/wireless/ath/ath5k/led.c +++ b/drivers/net/wireless/ath/ath5k/led.c @@ -89,7 +89,8 @@ static const struct pci_device_id ath5k_led_devices[] = { void ath5k_led_enable(struct ath5k_hw *ah) { - if (test_bit(ATH_STAT_LEDSOFT, ah->status)) { + if (IS_ENABLED(CONFIG_MAC80211_LEDS) && + test_bit(ATH_STAT_LEDSOFT, ah->status)) { ath5k_hw_set_gpio_output(ah, ah->led_pin); ath5k_led_off(ah); } @@ -104,7 +105,8 @@ static void ath5k_led_on(struct ath5k_hw *ah) void ath5k_led_off(struct ath5k_hw *ah) { - if (!test_bit(ATH_STAT_LEDSOFT, ah->status)) + if (!IS_ENABLED(CONFIG_MAC80211_LEDS) || + !test_bit(ATH_STAT_LEDSOFT, ah->status)) return; ath5k_hw_set_gpio(ah, ah->led_pin, !ah->led_on); } @@ -146,7 +148,7 @@ ath5k_register_led(struct ath5k_hw *ah, struct ath5k_led *led, static void ath5k_unregister_led(struct ath5k_led *led) { - if (!led->ah) + if (!IS_ENABLED(CONFIG_MAC80211_LEDS) || !led->ah) return; led_classdev_unregister(&led->led_dev); ath5k_led_off(led->ah); @@ -169,7 +171,7 @@ int ath5k_init_leds(struct ath5k_hw *ah) char name[ATH5K_LED_MAX_NAME_LEN + 1]; const struct pci_device_id *match; - if (!ah->pdev) + if (!IS_ENABLED(CONFIG_MAC80211_LEDS) || !ah->pdev) return 0; #ifdef CONFIG_ATH5K_AHB diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 6e9618865490..fb727778312c 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -7463,23 +7463,18 @@ static s32 brcmf_translate_country_code(struct brcmf_pub *drvr, char alpha2[2], s32 found_index; int i; + country_codes = drvr->settings->country_codes; + if (!country_codes) { + brcmf_dbg(TRACE, "No country codes configured for device\n"); + return -EINVAL; + } + if ((alpha2[0] == ccreq->country_abbrev[0]) && (alpha2[1] == ccreq->country_abbrev[1])) { brcmf_dbg(TRACE, "Country code already set\n"); return -EAGAIN; } - country_codes = drvr->settings->country_codes; - if (!country_codes) { - brcmf_dbg(TRACE, "No country codes configured for device, using ISO3166 code and 0 rev\n"); - memset(ccreq, 0, sizeof(*ccreq)); - ccreq->country_abbrev[0] = alpha2[0]; - ccreq->country_abbrev[1] = alpha2[1]; - ccreq->ccode[0] = alpha2[0]; - ccreq->ccode[1] = alpha2[1]; - return 0; - } - found_index = -1; for (i = 0; i < country_codes->table_size; i++) { cc = &country_codes->table[i]; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 0e97d5e6c644..9f706fffb592 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -160,6 +160,7 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw, mvm->ptk_icvlen = key->icv_len; mvm->gtk_ivlen = key->iv_len; mvm->gtk_icvlen = key->icv_len; + mutex_unlock(&mvm->mutex); /* don't upload key again */ return; @@ -360,11 +361,11 @@ static void iwl_mvm_wowlan_get_rsc_v5_data(struct ieee80211_hw *hw, if (sta) { rsc = data->rsc->ucast_rsc; } else { - if (WARN_ON(data->gtks > ARRAY_SIZE(data->gtk_ids))) + if (WARN_ON(data->gtks >= ARRAY_SIZE(data->gtk_ids))) return; data->gtk_ids[data->gtks] = key->keyidx; rsc = data->rsc->mcast_rsc[data->gtks % 2]; - if (WARN_ON(key->keyidx > + if (WARN_ON(key->keyidx >= ARRAY_SIZE(data->rsc->mcast_key_id_map))) return; data->rsc->mcast_key_id_map[key->keyidx] = data->gtks % 2; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 25af88a3edce..e91f8e889df7 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -662,12 +662,13 @@ static bool __iwl_mvm_remove_time_event(struct iwl_mvm *mvm, u32 *uid) { u32 id; - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif); + struct iwl_mvm_vif *mvmvif; enum nl80211_iftype iftype; if (!te_data->vif) return false; + mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif); iftype = te_data->vif->type; /* diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 61b2797a34a8..e3996ff99bad 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -547,6 +547,8 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_DEV_INFO(0x43F0, 0x0074, iwl_ax201_cfg_qu_hr, NULL), IWL_DEV_INFO(0x43F0, 0x0078, iwl_ax201_cfg_qu_hr, NULL), IWL_DEV_INFO(0x43F0, 0x007C, iwl_ax201_cfg_qu_hr, NULL), + IWL_DEV_INFO(0x43F0, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0, iwl_ax201_killer_1650s_name), + IWL_DEV_INFO(0x43F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0, iwl_ax201_killer_1650i_name), IWL_DEV_INFO(0x43F0, 0x2074, iwl_ax201_cfg_qu_hr, NULL), IWL_DEV_INFO(0x43F0, 0x4070, iwl_ax201_cfg_qu_hr, NULL), IWL_DEV_INFO(0xA0F0, 0x0070, iwl_ax201_cfg_qu_hr, NULL), diff --git a/drivers/net/wireless/marvell/mwifiex/sta_tx.c b/drivers/net/wireless/marvell/mwifiex/sta_tx.c index 241305377e20..a9b5eb992220 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_tx.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_tx.c @@ -62,8 +62,8 @@ void *mwifiex_process_sta_txpd(struct mwifiex_private *priv, pkt_type = mwifiex_is_skb_mgmt_frame(skb) ? PKT_TYPE_MGMT : 0; - pad = ((void *)skb->data - (sizeof(*local_tx_pd) + hroom)- - NULL) & (MWIFIEX_DMA_ALIGN_SZ - 1); + pad = ((uintptr_t)skb->data - (sizeof(*local_tx_pd) + hroom)) & + (MWIFIEX_DMA_ALIGN_SZ - 1); skb_push(skb, sizeof(*local_tx_pd) + pad); local_tx_pd = (struct txpd *) skb->data; diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c index 9bbdb8dfce62..245ff644f81e 100644 --- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c +++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c @@ -475,8 +475,8 @@ void *mwifiex_process_uap_txpd(struct mwifiex_private *priv, pkt_type = mwifiex_is_skb_mgmt_frame(skb) ? PKT_TYPE_MGMT : 0; - pad = ((void *)skb->data - (sizeof(*txpd) + hroom) - NULL) & - (MWIFIEX_DMA_ALIGN_SZ - 1); + pad = ((uintptr_t)skb->data - (sizeof(*txpd) + hroom)) & + (MWIFIEX_DMA_ALIGN_SZ - 1); skb_push(skb, sizeof(*txpd) + pad); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 32d5bc4919d8..0f7fd159f0f2 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1474,7 +1474,7 @@ int xenvif_map_frontend_data_rings(struct xenvif_queue *queue, struct xen_netif_tx_sring *txs; struct xen_netif_rx_sring *rxs; RING_IDX rsp_prod, req_prod; - int err = -ENOMEM; + int err; err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif), &tx_ring_ref, 1, &addr); diff --git a/drivers/nfc/microread/i2c.c b/drivers/nfc/microread/i2c.c index 86f593c73ed6..067295124eb9 100644 --- a/drivers/nfc/microread/i2c.c +++ b/drivers/nfc/microread/i2c.c @@ -237,8 +237,6 @@ static int microread_i2c_probe(struct i2c_client *client, struct microread_i2c_phy *phy; int r; - dev_dbg(&client->dev, "client %p\n", client); - phy = devm_kzalloc(&client->dev, sizeof(struct microread_i2c_phy), GFP_KERNEL); if (!phy) @@ -262,8 +260,6 @@ static int microread_i2c_probe(struct i2c_client *client, if (r < 0) goto err_irq; - nfc_info(&client->dev, "Probed\n"); - return 0; err_irq: diff --git a/drivers/nfc/microread/mei.c b/drivers/nfc/microread/mei.c index 00689e18dc46..e2a77a5fc887 100644 --- a/drivers/nfc/microread/mei.c +++ b/drivers/nfc/microread/mei.c @@ -23,8 +23,6 @@ static int microread_mei_probe(struct mei_cl_device *cldev, struct nfc_mei_phy *phy; int r; - pr_info("Probing NFC microread\n"); - phy = nfc_mei_phy_alloc(cldev); if (!phy) return -ENOMEM; diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c index 1af7a1e632cf..c20fdbac51c5 100644 --- a/drivers/nfc/s3fwrn5/firmware.c +++ b/drivers/nfc/s3fwrn5/firmware.c @@ -357,6 +357,7 @@ s3fwrn5_fw_is_custom(const struct s3fwrn5_fw_cmd_get_bootinfo_rsp *bootinfo) int s3fwrn5_fw_setup(struct s3fwrn5_fw_info *fw_info) { + struct device *dev = &fw_info->ndev->nfc_dev->dev; struct s3fwrn5_fw_cmd_get_bootinfo_rsp bootinfo; int ret; @@ -364,8 +365,7 @@ int s3fwrn5_fw_setup(struct s3fwrn5_fw_info *fw_info) ret = s3fwrn5_fw_get_bootinfo(fw_info, &bootinfo); if (ret < 0) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Failed to get bootinfo, ret=%02x\n", ret); + dev_err(dev, "Failed to get bootinfo, ret=%02x\n", ret); goto err; } @@ -373,8 +373,7 @@ int s3fwrn5_fw_setup(struct s3fwrn5_fw_info *fw_info) ret = s3fwrn5_fw_get_base_addr(&bootinfo, &fw_info->base_addr); if (ret < 0) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Unknown hardware version\n"); + dev_err(dev, "Unknown hardware version\n"); goto err; } @@ -409,6 +408,7 @@ bool s3fwrn5_fw_check_version(const struct s3fwrn5_fw_info *fw_info, u32 version int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info) { + struct device *dev = &fw_info->ndev->nfc_dev->dev; struct s3fwrn5_fw_image *fw = &fw_info->fw; u8 hash_data[SHA1_DIGEST_SIZE]; struct crypto_shash *tfm; @@ -421,8 +421,7 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info) tfm = crypto_alloc_shash("sha1", 0, 0); if (IS_ERR(tfm)) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Cannot allocate shash (code=%pe)\n", tfm); + dev_err(dev, "Cannot allocate shash (code=%pe)\n", tfm); return PTR_ERR(tfm); } @@ -430,21 +429,18 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info) crypto_free_shash(tfm); if (ret) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Cannot compute hash (code=%d)\n", ret); + dev_err(dev, "Cannot compute hash (code=%d)\n", ret); return ret; } /* Firmware update process */ - dev_info(&fw_info->ndev->nfc_dev->dev, - "Firmware update: %s\n", fw_info->fw_name); + dev_info(dev, "Firmware update: %s\n", fw_info->fw_name); ret = s3fwrn5_fw_enter_update_mode(fw_info, hash_data, SHA1_DIGEST_SIZE, fw_info->sig, fw_info->sig_size); if (ret < 0) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Unable to enter update mode\n"); + dev_err(dev, "Unable to enter update mode\n"); return ret; } @@ -452,21 +448,18 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info) ret = s3fwrn5_fw_update_sector(fw_info, fw_info->base_addr + off, fw->image + off); if (ret < 0) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Firmware update error (code=%d)\n", ret); + dev_err(dev, "Firmware update error (code=%d)\n", ret); return ret; } } ret = s3fwrn5_fw_complete_update_mode(fw_info); if (ret < 0) { - dev_err(&fw_info->ndev->nfc_dev->dev, - "Unable to complete update mode\n"); + dev_err(dev, "Unable to complete update mode\n"); return ret; } - dev_info(&fw_info->ndev->nfc_dev->dev, - "Firmware update: success\n"); + dev_info(dev, "Firmware update: success\n"); return ret; } diff --git a/drivers/nfc/s3fwrn5/nci.c b/drivers/nfc/s3fwrn5/nci.c index e374e670b36b..ca6828f55ba0 100644 --- a/drivers/nfc/s3fwrn5/nci.c +++ b/drivers/nfc/s3fwrn5/nci.c @@ -47,6 +47,7 @@ const struct nci_driver_ops s3fwrn5_nci_prop_ops[4] = { int s3fwrn5_nci_rf_configure(struct s3fwrn5_info *info, const char *fw_name) { + struct device *dev = &info->ndev->nfc_dev->dev; const struct firmware *fw; struct nci_prop_fw_cfg_cmd fw_cfg; struct nci_prop_set_rfreg_cmd set_rfreg; @@ -55,7 +56,7 @@ int s3fwrn5_nci_rf_configure(struct s3fwrn5_info *info, const char *fw_name) int i, len; int ret; - ret = request_firmware(&fw, fw_name, &info->ndev->nfc_dev->dev); + ret = request_firmware(&fw, fw_name, dev); if (ret < 0) return ret; @@ -77,13 +78,11 @@ int s3fwrn5_nci_rf_configure(struct s3fwrn5_info *info, const char *fw_name) /* Start rfreg configuration */ - dev_info(&info->ndev->nfc_dev->dev, - "rfreg configuration update: %s\n", fw_name); + dev_info(dev, "rfreg configuration update: %s\n", fw_name); ret = nci_prop_cmd(info->ndev, NCI_PROP_START_RFREG, 0, NULL); if (ret < 0) { - dev_err(&info->ndev->nfc_dev->dev, - "Unable to start rfreg update\n"); + dev_err(dev, "Unable to start rfreg update\n"); goto out; } @@ -97,8 +96,7 @@ int s3fwrn5_nci_rf_configure(struct s3fwrn5_info *info, const char *fw_name) ret = nci_prop_cmd(info->ndev, NCI_PROP_SET_RFREG, len+1, (__u8 *)&set_rfreg); if (ret < 0) { - dev_err(&info->ndev->nfc_dev->dev, - "rfreg update error (code=%d)\n", ret); + dev_err(dev, "rfreg update error (code=%d)\n", ret); goto out; } set_rfreg.index++; @@ -110,13 +108,11 @@ int s3fwrn5_nci_rf_configure(struct s3fwrn5_info *info, const char *fw_name) ret = nci_prop_cmd(info->ndev, NCI_PROP_STOP_RFREG, sizeof(stop_rfreg), (__u8 *)&stop_rfreg); if (ret < 0) { - dev_err(&info->ndev->nfc_dev->dev, - "Unable to stop rfreg update\n"); + dev_err(dev, "Unable to stop rfreg update\n"); goto out; } - dev_info(&info->ndev->nfc_dev->dev, - "rfreg configuration update: success\n"); + dev_info(dev, "rfreg configuration update: success\n"); out: release_firmware(fw); return ret; diff --git a/drivers/nfc/st-nci/i2c.c b/drivers/nfc/st-nci/i2c.c index ccf6152ebb9f..cbd968f013c7 100644 --- a/drivers/nfc/st-nci/i2c.c +++ b/drivers/nfc/st-nci/i2c.c @@ -157,7 +157,6 @@ static int st_nci_i2c_read(struct st_nci_i2c_phy *phy, static irqreturn_t st_nci_irq_thread_fn(int irq, void *phy_id) { struct st_nci_i2c_phy *phy = phy_id; - struct i2c_client *client; struct sk_buff *skb = NULL; int r; @@ -166,9 +165,6 @@ static irqreturn_t st_nci_irq_thread_fn(int irq, void *phy_id) return IRQ_NONE; } - client = phy->i2c_dev; - dev_dbg(&client->dev, "IRQ\n"); - if (phy->ndlc->hard_fault) return IRQ_HANDLED; diff --git a/drivers/nfc/st-nci/ndlc.c b/drivers/nfc/st-nci/ndlc.c index e9dc313b333e..755460a73c0d 100644 --- a/drivers/nfc/st-nci/ndlc.c +++ b/drivers/nfc/st-nci/ndlc.c @@ -239,8 +239,6 @@ static void ndlc_t1_timeout(struct timer_list *t) { struct llt_ndlc *ndlc = from_timer(ndlc, t, t1_timer); - pr_debug("\n"); - schedule_work(&ndlc->sm_work); } @@ -248,8 +246,6 @@ static void ndlc_t2_timeout(struct timer_list *t) { struct llt_ndlc *ndlc = from_timer(ndlc, t, t2_timer); - pr_debug("\n"); - schedule_work(&ndlc->sm_work); } diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index 5fd89f72969d..7764b1a4c3cf 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -638,8 +638,6 @@ int st_nci_se_io(struct nci_dev *ndev, u32 se_idx, { struct st_nci_info *info = nci_get_drvdata(ndev); - pr_debug("\n"); - switch (se_idx) { case ST_NCI_ESE_HOST_ID: info->se_info.cb = cb; @@ -671,8 +669,6 @@ static void st_nci_se_wt_timeout(struct timer_list *t) u8 param = 0x01; struct st_nci_info *info = from_timer(info, t, se_info.bwi_timer); - pr_debug("\n"); - info->se_info.bwi_active = false; if (!info->se_info.xch_error) { @@ -692,8 +688,6 @@ static void st_nci_se_activation_timeout(struct timer_list *t) struct st_nci_info *info = from_timer(info, t, se_info.se_active_timer); - pr_debug("\n"); - info->se_info.se_active = false; complete(&info->se_info.req_completion); diff --git a/drivers/nfc/st-nci/spi.c b/drivers/nfc/st-nci/spi.c index 0875b773fb41..4e723992e74c 100644 --- a/drivers/nfc/st-nci/spi.c +++ b/drivers/nfc/st-nci/spi.c @@ -169,7 +169,6 @@ static int st_nci_spi_read(struct st_nci_spi_phy *phy, static irqreturn_t st_nci_irq_thread_fn(int irq, void *phy_id) { struct st_nci_spi_phy *phy = phy_id; - struct spi_device *dev; struct sk_buff *skb = NULL; int r; @@ -178,9 +177,6 @@ static irqreturn_t st_nci_irq_thread_fn(int irq, void *phy_id) return IRQ_NONE; } - dev = phy->spi_dev; - dev_dbg(&dev->dev, "IRQ\n"); - if (phy->ndlc->hard_fault) return IRQ_HANDLED; diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c index 279d88128b2e..f126ce96a7df 100644 --- a/drivers/nfc/st21nfca/i2c.c +++ b/drivers/nfc/st21nfca/i2c.c @@ -421,7 +421,6 @@ static int st21nfca_hci_i2c_read(struct st21nfca_i2c_phy *phy, static irqreturn_t st21nfca_hci_irq_thread_fn(int irq, void *phy_id) { struct st21nfca_i2c_phy *phy = phy_id; - struct i2c_client *client; int r; @@ -430,9 +429,6 @@ static irqreturn_t st21nfca_hci_irq_thread_fn(int irq, void *phy_id) return IRQ_NONE; } - client = phy->i2c_dev; - dev_dbg(&client->dev, "IRQ\n"); - if (phy->hard_fault != 0) return IRQ_HANDLED; diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c index c8bdf078d111..a43fc4117fa5 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -257,8 +257,6 @@ static void st21nfca_se_wt_timeout(struct timer_list *t) struct st21nfca_hci_info *info = from_timer(info, t, se_info.bwi_timer); - pr_debug("\n"); - info->se_info.bwi_active = false; if (!info->se_info.xch_error) { @@ -278,8 +276,6 @@ static void st21nfca_se_activation_timeout(struct timer_list *t) struct st21nfca_hci_info *info = from_timer(info, t, se_info.se_active_timer); - pr_debug("\n"); - info->se_info.se_active = false; complete(&info->se_info.req_completion); diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c index 8890fcd59c39..29ca9c328df2 100644 --- a/drivers/nfc/trf7970a.c +++ b/drivers/nfc/trf7970a.c @@ -2170,8 +2170,6 @@ static int trf7970a_suspend(struct device *dev) struct spi_device *spi = to_spi_device(dev); struct trf7970a *trf = spi_get_drvdata(spi); - dev_dbg(dev, "Suspend\n"); - mutex_lock(&trf->lock); trf7970a_shutdown(trf); @@ -2187,8 +2185,6 @@ static int trf7970a_resume(struct device *dev) struct trf7970a *trf = spi_get_drvdata(spi); int ret; - dev_dbg(dev, "Resume\n"); - mutex_lock(&trf->lock); ret = trf7970a_startup(trf); @@ -2206,8 +2202,6 @@ static int trf7970a_pm_runtime_suspend(struct device *dev) struct trf7970a *trf = spi_get_drvdata(spi); int ret; - dev_dbg(dev, "Runtime suspend\n"); - mutex_lock(&trf->lock); ret = trf7970a_power_down(trf); @@ -2223,8 +2217,6 @@ static int trf7970a_pm_runtime_resume(struct device *dev) struct trf7970a *trf = spi_get_drvdata(spi); int ret; - dev_dbg(dev, "Runtime resume\n"); - ret = trf7970a_power_up(trf); if (!ret) pm_runtime_mark_last_busy(dev); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 72de88ff0d30..ef4950f80832 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -380,7 +380,6 @@ static int pmem_attach_disk(struct device *dev, struct nd_pfn_sb *pfn_sb; struct pmem_device *pmem; struct request_queue *q; - struct device *gendev; struct gendisk *disk; void *addr; int rc; @@ -489,10 +488,8 @@ static int pmem_attach_disk(struct device *dev, } dax_write_cache(dax_dev, nvdimm_has_cache(nd_region)); pmem->dax_dev = dax_dev; - gendev = disk_to_dev(disk); - gendev->groups = pmem_attribute_groups; - device_add_disk(dev, disk, NULL); + device_add_disk(dev, disk, pmem_attribute_groups); if (devm_add_action_or_reset(dev, pmem_release_disk, pmem)) return -ENOMEM; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e486845d2c7e..7712a8f78337 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -978,6 +978,7 @@ EXPORT_SYMBOL_GPL(nvme_cleanup_cmd); blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req) { struct nvme_command *cmd = nvme_req(req)->cmd; + struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; blk_status_t ret = BLK_STS_OK; if (!(req->rq_flags & RQF_DONTPREP)) { @@ -1026,7 +1027,8 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req) return BLK_STS_IOERR; } - nvme_req(req)->genctr++; + if (!(ctrl->quirks & NVME_QUIRK_SKIP_CID_GEN)) + nvme_req(req)->genctr++; cmd->common.command_id = nvme_cid(req); trace_nvme_setup_cmd(req, cmd); return ret; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9871c0c9374c..ed79a6c7e804 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -138,6 +138,12 @@ enum nvme_quirks { * 48 bits. */ NVME_QUIRK_DMA_ADDRESS_BITS_48 = (1 << 16), + + /* + * The controller requires the command_id value be be limited, so skip + * encoding the generation sequence number. + */ + NVME_QUIRK_SKIP_CID_GEN = (1 << 17), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b82492cd7503..456a0e8a5718 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3369,7 +3369,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005), .driver_data = NVME_QUIRK_SINGLE_VECTOR | NVME_QUIRK_128_BYTES_SQES | - NVME_QUIRK_SHARED_TAGS }, + NVME_QUIRK_SHARED_TAGS | + NVME_QUIRK_SKIP_CID_GEN }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { 0, } diff --git a/drivers/of/base.c b/drivers/of/base.c index f720c0d246f2..0ac17256258d 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -36,6 +36,7 @@ LIST_HEAD(aliases_lookup); struct device_node *of_root; EXPORT_SYMBOL(of_root); struct device_node *of_chosen; +EXPORT_SYMBOL(of_chosen); struct device_node *of_aliases; struct device_node *of_stdout; static const char *of_stdout_options; diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index eaec915ffe62..67c46e52c0dc 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3301,9 +3301,17 @@ static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs) return 0; if (!keep_devs) { - /* Delete any children which might still exist. */ + struct list_head removed; + + /* Move all present children to the list on stack */ + INIT_LIST_HEAD(&removed); spin_lock_irqsave(&hbus->device_list_lock, flags); - list_for_each_entry_safe(hpdev, tmp, &hbus->children, list_entry) { + list_for_each_entry_safe(hpdev, tmp, &hbus->children, list_entry) + list_move_tail(&hpdev->list_entry, &removed); + spin_unlock_irqrestore(&hbus->device_list_lock, flags); + + /* Remove all children in the list */ + list_for_each_entry_safe(hpdev, tmp, &removed, list_entry) { list_del(&hpdev->list_entry); if (hpdev->pci_slot) pci_destroy_slot(hpdev->pci_slot); @@ -3311,7 +3319,6 @@ static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs) put_pcichild(hpdev); put_pcichild(hpdev); } - spin_unlock_irqrestore(&hbus->device_list_lock, flags); } ret = hv_send_resources_released(hdev); diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index 014868752cd4..dcefdb42ac46 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -62,14 +62,7 @@ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev, hotplug_slot); - switch (zdev->state) { - case ZPCI_FN_STATE_STANDBY: - *value = 0; - break; - default: - *value = 1; - break; - } + *value = zpci_is_device_configured(zdev) ? 1 : 0; return 0; } diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 0f40943a9a18..260a06fb78a6 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -1249,6 +1249,9 @@ static struct acpi_device *acpi_pci_find_companion(struct device *dev) bool check_children; u64 addr; + if (!dev->parent) + return NULL; + down_read(&pci_acpi_companion_lookup_sem); adev = pci_acpi_find_companion_hook ? diff --git a/drivers/pcmcia/pcmcia_cis.c b/drivers/pcmcia/pcmcia_cis.c index d2d0ed4b27c8..f650e19a315c 100644 --- a/drivers/pcmcia/pcmcia_cis.c +++ b/drivers/pcmcia/pcmcia_cis.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> +#include <linux/etherdevice.h> #include <pcmcia/cisreg.h> #include <pcmcia/cistpl.h> @@ -398,7 +399,6 @@ static int pcmcia_do_get_mac(struct pcmcia_device *p_dev, tuple_t *tuple, void *priv) { struct net_device *dev = priv; - int i; if (tuple->TupleData[0] != CISTPL_FUNCE_LAN_NODE_ID) return -EINVAL; @@ -412,8 +412,7 @@ static int pcmcia_do_get_mac(struct pcmcia_device *p_dev, tuple_t *tuple, dev_warn(&p_dev->dev, "Invalid header for LAN_NODE_ID\n"); return -EINVAL; } - for (i = 0; i < 6; i++) - dev->dev_addr[i] = tuple->TupleData[i+2]; + eth_hw_addr_set(dev, &tuple->TupleData[2]); return 0; } diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index 32ea2a8ec02b..5ff4207df66e 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -3,7 +3,8 @@ if (ARCH_QCOM || COMPILE_TEST) config PINCTRL_MSM tristate "Qualcomm core pin controller driver" - depends on GPIOLIB && (QCOM_SCM || !QCOM_SCM) #if QCOM_SCM=m this can't be =y + depends on GPIOLIB + select QCOM_SCM select PINMUX select PINCONF select GENERIC_PINCONF diff --git a/drivers/platform/mellanox/mlxreg-io.c b/drivers/platform/mellanox/mlxreg-io.c index 7646708d57e4..a916cd89cbbe 100644 --- a/drivers/platform/mellanox/mlxreg-io.c +++ b/drivers/platform/mellanox/mlxreg-io.c @@ -98,7 +98,7 @@ mlxreg_io_get_reg(void *regmap, struct mlxreg_core_data *data, u32 in_val, if (ret) goto access_error; - *regval |= rol32(val, regsize * i); + *regval |= rol32(val, regsize * i * 8); } } @@ -141,7 +141,7 @@ mlxreg_io_attr_store(struct device *dev, struct device_attribute *attr, return -EINVAL; /* Convert buffer to input value. */ - ret = kstrtou32(buf, len, &input_val); + ret = kstrtou32(buf, 0, &input_val); if (ret) return ret; diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index d6a7c896ac86..fc95620101e8 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -476,6 +476,7 @@ static const struct acpi_device_id amd_pmc_acpi_ids[] = { {"AMDI0006", 0}, {"AMDI0007", 0}, {"AMD0004", 0}, + {"AMD0005", 0}, { } }; MODULE_DEVICE_TABLE(acpi, amd_pmc_acpi_ids); diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig index 42513eab1d06..2fffa57e596e 100644 --- a/drivers/platform/x86/dell/Kconfig +++ b/drivers/platform/x86/dell/Kconfig @@ -167,6 +167,7 @@ config DELL_WMI config DELL_WMI_PRIVACY bool "Dell WMI Hardware Privacy Support" depends on LEDS_TRIGGER_AUDIO = y || DELL_WMI = LEDS_TRIGGER_AUDIO + depends on DELL_WMI help This option adds integration with the "Dell Hardware Privacy" feature of Dell laptops to the dell-wmi driver. diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index d53634c8a6e0..658bab4b7964 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -141,6 +141,7 @@ static u8 gigabyte_wmi_detect_sensor_usability(struct wmi_device *wdev) static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M S2H V2"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE AX V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 GAMING X V2"), diff --git a/drivers/platform/x86/intel/int1092/intel_sar.c b/drivers/platform/x86/intel/int1092/intel_sar.c index 379560fe5df9..e03943e6380a 100644 --- a/drivers/platform/x86/intel/int1092/intel_sar.c +++ b/drivers/platform/x86/intel/int1092/intel_sar.c @@ -42,12 +42,20 @@ static void update_sar_data(struct wwan_sar_context *context) if (config->device_mode_info && context->sar_data.device_mode < config->total_dev_mode) { - struct wwan_device_mode_info *dev_mode = - &config->device_mode_info[context->sar_data.device_mode]; - - context->sar_data.antennatable_index = dev_mode->antennatable_index; - context->sar_data.bandtable_index = dev_mode->bandtable_index; - context->sar_data.sartable_index = dev_mode->sartable_index; + int itr = 0; + + for (itr = 0; itr < config->total_dev_mode; itr++) { + if (context->sar_data.device_mode == + config->device_mode_info[itr].device_mode) { + struct wwan_device_mode_info *dev_mode = + &config->device_mode_info[itr]; + + context->sar_data.antennatable_index = dev_mode->antennatable_index; + context->sar_data.bandtable_index = dev_mode->bandtable_index; + context->sar_data.sartable_index = dev_mode->sartable_index; + break; + } + } } } @@ -305,7 +313,6 @@ static struct platform_driver sar_driver = { .remove = sar_remove, .driver = { .name = DRVNAME, - .owner = THIS_MODULE, .acpi_match_table = ACPI_PTR(sar_device_ids) } }; @@ -313,4 +320,4 @@ module_platform_driver(sar_driver); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Platform device driver for INTEL MODEM BIOS SAR"); -MODULE_AUTHOR("Shravan S <s.shravan@intel.com>"); +MODULE_AUTHOR("Shravan Sudhakar <s.shravan@intel.com>"); diff --git a/drivers/platform/x86/intel/int3472/intel_skl_int3472_discrete.c b/drivers/platform/x86/intel/int3472/intel_skl_int3472_discrete.c index 9fe0a2527e1c..e59d79c7e82f 100644 --- a/drivers/platform/x86/intel/int3472/intel_skl_int3472_discrete.c +++ b/drivers/platform/x86/intel/int3472/intel_skl_int3472_discrete.c @@ -401,7 +401,7 @@ int skl_int3472_discrete_remove(struct platform_device *pdev) gpiod_remove_lookup_table(&int3472->gpios); - if (int3472->clock.ena_gpio) + if (int3472->clock.cl) skl_int3472_unregister_clock(int3472); gpiod_put(int3472->clock.ena_gpio); diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index bfa0cc20750d..7cc9089d1e14 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -75,7 +75,7 @@ struct intel_scu_ipc_dev { #define IPC_READ_BUFFER 0x90 /* Timeout in jiffies */ -#define IPC_TIMEOUT (5 * HZ) +#define IPC_TIMEOUT (10 * HZ) static struct intel_scu_ipc_dev *ipcdev; /* Only one for now */ static DEFINE_MUTEX(ipclock); /* lock used to prevent multiple call to SCU */ @@ -232,7 +232,7 @@ static inline u32 ipc_data_readl(struct intel_scu_ipc_dev *scu, u32 offset) /* Wait till scu status is busy */ static inline int busy_loop(struct intel_scu_ipc_dev *scu) { - unsigned long end = jiffies + msecs_to_jiffies(IPC_TIMEOUT); + unsigned long end = jiffies + IPC_TIMEOUT; do { u32 status; @@ -247,7 +247,7 @@ static inline int busy_loop(struct intel_scu_ipc_dev *scu) return -ETIMEDOUT; } -/* Wait till ipc ioc interrupt is received or timeout in 3 HZ */ +/* Wait till ipc ioc interrupt is received or timeout in 10 HZ */ static inline int ipc_wait_for_interrupt(struct intel_scu_ipc_dev *scu) { int status; diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c index 3dd519dfc473..d0096cd7096a 100644 --- a/drivers/ptp/ptp_kvm_x86.c +++ b/drivers/ptp/ptp_kvm_x86.c @@ -15,8 +15,6 @@ #include <linux/ptp_clock_kernel.h> #include <linux/ptp_kvm.h> -struct pvclock_vsyscall_time_info *hv_clock; - static phys_addr_t clock_pair_gpa; static struct kvm_clock_pairing clock_pair; @@ -28,8 +26,7 @@ int kvm_arch_ptp_init(void) return -ENODEV; clock_pair_gpa = slow_virt_to_phys(&clock_pair); - hv_clock = pvclock_get_pvti_cpu0_va(); - if (!hv_clock) + if (!pvclock_get_pvti_cpu0_va()) return -ENODEV; ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa, @@ -64,10 +61,8 @@ int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *tspec, struct pvclock_vcpu_time_info *src; unsigned int version; long ret; - int cpu; - cpu = smp_processor_id(); - src = &hv_clock[cpu].pvti; + src = this_cpu_pvti(); do { /* diff --git a/drivers/ptp/ptp_pch.c b/drivers/ptp/ptp_pch.c index a17e8cc642c5..8070f3fd98f0 100644 --- a/drivers/ptp/ptp_pch.c +++ b/drivers/ptp/ptp_pch.c @@ -644,6 +644,7 @@ static const struct pci_device_id pch_ieee1588_pcidev_id[] = { }, {0} }; +MODULE_DEVICE_TABLE(pci, pch_ieee1588_pcidev_id); static SIMPLE_DEV_PM_OPS(pch_pm_ops, pch_suspend, pch_resume); diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c index f3c656975e05..93695d535380 100644 --- a/drivers/s390/cio/blacklist.c +++ b/drivers/s390/cio/blacklist.c @@ -262,10 +262,12 @@ static int blacklist_parse_proc_parameters(char *buf) if (strcmp("free", parm) == 0) { rc = blacklist_parse_parameters(buf, free, 0); - /* There could be subchannels without proper devices connected. - * evaluate all the entries + /* + * Evaluate the subchannels without an online device. This way, + * no path-verification will be triggered on those subchannels + * and it avoids unnecessary delays. */ - css_schedule_eval_all(); + css_schedule_eval_cond(CSS_EVAL_NOT_ONLINE, 0); } else if (strcmp("add", parm) == 0) rc = blacklist_parse_parameters(buf, add, 0); else if (strcmp("purge", parm) == 0) diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 3377097e65de..44461928aab8 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -788,27 +788,49 @@ static int __unset_registered(struct device *dev, void *data) return 0; } -void css_schedule_eval_all_unreg(unsigned long delay) +static int __unset_online(struct device *dev, void *data) +{ + struct idset *set = data; + struct subchannel *sch = to_subchannel(dev); + struct ccw_device *cdev = sch_get_cdev(sch); + + if (cdev && cdev->online) + idset_sch_del(set, sch->schid); + + return 0; +} + +void css_schedule_eval_cond(enum css_eval_cond cond, unsigned long delay) { unsigned long flags; - struct idset *unreg_set; + struct idset *set; /* Find unregistered subchannels. */ - unreg_set = idset_sch_new(); - if (!unreg_set) { + set = idset_sch_new(); + if (!set) { /* Fallback. */ css_schedule_eval_all(); return; } - idset_fill(unreg_set); - bus_for_each_dev(&css_bus_type, NULL, unreg_set, __unset_registered); + idset_fill(set); + switch (cond) { + case CSS_EVAL_UNREG: + bus_for_each_dev(&css_bus_type, NULL, set, __unset_registered); + break; + case CSS_EVAL_NOT_ONLINE: + bus_for_each_dev(&css_bus_type, NULL, set, __unset_online); + break; + default: + break; + } + /* Apply to slow_subchannel_set. */ spin_lock_irqsave(&slow_subchannel_lock, flags); - idset_add_set(slow_subchannel_set, unreg_set); + idset_add_set(slow_subchannel_set, set); atomic_set(&css_eval_scheduled, 1); queue_delayed_work(cio_work_q, &slow_path_work, delay); spin_unlock_irqrestore(&slow_subchannel_lock, flags); - idset_free(unreg_set); + idset_free(set); } void css_wait_for_slow_path(void) @@ -820,7 +842,7 @@ void css_wait_for_slow_path(void) void css_schedule_reprobe(void) { /* Schedule with a delay to allow merging of subsequent calls. */ - css_schedule_eval_all_unreg(1 * HZ); + css_schedule_eval_cond(CSS_EVAL_UNREG, 1 * HZ); } EXPORT_SYMBOL_GPL(css_schedule_reprobe); diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h index c98522cbe276..ede0b905bc6f 100644 --- a/drivers/s390/cio/css.h +++ b/drivers/s390/cio/css.h @@ -34,6 +34,14 @@ #define SNID_STATE3_MULTI_PATH 1 #define SNID_STATE3_SINGLE_PATH 0 +/* + * Conditions used to specify which subchannels need evaluation + */ +enum css_eval_cond { + CSS_EVAL_UNREG, /* unregistered subchannels */ + CSS_EVAL_NOT_ONLINE /* sch without an online-device */ +}; + struct path_state { __u8 state1 : 2; /* path state value 1 */ __u8 state2 : 2; /* path state value 2 */ @@ -136,7 +144,7 @@ static inline struct channel_subsystem *css_by_id(u8 cssid) /* Helper functions to build lists for the slow path. */ void css_schedule_eval(struct subchannel_id schid); void css_schedule_eval_all(void); -void css_schedule_eval_all_unreg(unsigned long delay); +void css_schedule_eval_cond(enum css_eval_cond, unsigned long delay); int css_complete_work(void); int sch_is_pseudo_sch(struct subchannel *); diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c index b4cb5fb19998..0cc62c1b0825 100644 --- a/drivers/scsi/arm/acornscsi.c +++ b/drivers/scsi/arm/acornscsi.c @@ -1776,7 +1776,7 @@ int acornscsi_reconnect_finish(AS_Host *host) host->scsi.disconnectable = 0; if (host->SCpnt->device->id == host->scsi.reconnected.target && host->SCpnt->device->lun == host->scsi.reconnected.lun && - scsi_cmd_to_tag(host->SCpnt) == host->scsi.reconnected.tag) { + scsi_cmd_to_rq(host->SCpnt)->tag == host->scsi.reconnected.tag) { #if (DEBUG & (DEBUG_QUEUES|DEBUG_DISCON)) DBG(host->SCpnt, printk("scsi%d.%c: reconnected", host->host->host_no, acornscsi_target(host))); diff --git a/drivers/scsi/csiostor/csio_init.c b/drivers/scsi/csiostor/csio_init.c index 390b07bf92b9..ccbded3353bd 100644 --- a/drivers/scsi/csiostor/csio_init.c +++ b/drivers/scsi/csiostor/csio_init.c @@ -1254,3 +1254,4 @@ MODULE_DEVICE_TABLE(pci, csio_pci_tbl); MODULE_VERSION(CSIO_DRV_VERSION); MODULE_FIRMWARE(FW_FNAME_T5); MODULE_FIRMWARE(FW_FNAME_T6); +MODULE_SOFTDEP("pre: cxgb4"); diff --git a/drivers/scsi/elx/efct/efct_scsi.c b/drivers/scsi/elx/efct/efct_scsi.c index 40fb3a724c76..cf2e41dd354c 100644 --- a/drivers/scsi/elx/efct/efct_scsi.c +++ b/drivers/scsi/elx/efct/efct_scsi.c @@ -32,7 +32,7 @@ efct_scsi_io_alloc(struct efct_node *node) struct efct *efct; struct efct_xport *xport; struct efct_io *io; - unsigned long flags = 0; + unsigned long flags; efct = node->efct; @@ -44,7 +44,6 @@ efct_scsi_io_alloc(struct efct_node *node) if (!io) { efc_log_err(efct, "IO alloc Failed\n"); atomic_add_return(1, &xport->io_alloc_failed_count); - spin_unlock_irqrestore(&node->active_ios_lock, flags); return NULL; } diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 4683c183e9d4..5bc91d34df63 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -2281,11 +2281,6 @@ int iscsi_eh_abort(struct scsi_cmnd *sc) return FAILED; } - conn = session->leadconn; - iscsi_get_conn(conn->cls_conn); - conn->eh_abort_cnt++; - age = session->age; - spin_lock(&session->back_lock); task = (struct iscsi_task *)sc->SCp.ptr; if (!task || !task->sc) { @@ -2293,8 +2288,16 @@ int iscsi_eh_abort(struct scsi_cmnd *sc) ISCSI_DBG_EH(session, "sc completed while abort in progress\n"); spin_unlock(&session->back_lock); - goto success; + spin_unlock_bh(&session->frwd_lock); + mutex_unlock(&session->eh_mutex); + return SUCCESS; } + + conn = session->leadconn; + iscsi_get_conn(conn->cls_conn); + conn->eh_abort_cnt++; + age = session->age; + ISCSI_DBG_EH(session, "aborting [sc %p itt 0x%x]\n", sc, task->itt); __iscsi_get_task(task); spin_unlock(&session->back_lock); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 78ce38d7251c..026a1196a54d 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -12292,12 +12292,12 @@ void lpfc_ignore_els_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, struct lpfc_iocbq *rspiocb) { - struct lpfc_nodelist *ndlp = (struct lpfc_nodelist *) cmdiocb->context1; + struct lpfc_nodelist *ndlp = NULL; IOCB_t *irsp = &rspiocb->iocb; /* ELS cmd tag <ulpIoTag> completes */ lpfc_printf_log(phba, KERN_INFO, LOG_ELS, - "0139 Ignoring ELS cmd tag x%x completion Data: " + "0139 Ignoring ELS cmd code x%x completion Data: " "x%x x%x x%x\n", irsp->ulpIoTag, irsp->ulpStatus, irsp->un.ulpWord[4], irsp->ulpTimeout); @@ -12305,10 +12305,13 @@ lpfc_ignore_els_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, * Deref the ndlp after free_iocb. sli_release_iocb will access the ndlp * if exchange is busy. */ - if (cmdiocb->iocb.ulpCommand == CMD_GEN_REQUEST64_CR) + if (cmdiocb->iocb.ulpCommand == CMD_GEN_REQUEST64_CR) { + ndlp = cmdiocb->context_un.ndlp; lpfc_ct_free_iocb(phba, cmdiocb); - else + } else { + ndlp = (struct lpfc_nodelist *) cmdiocb->context1; lpfc_els_free_iocb(phba, cmdiocb); + } lpfc_nlp_put(ndlp); } diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index ece60267b971..b26f2699adb2 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2634,7 +2634,7 @@ static void qla24xx_nvme_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, } if (unlikely(logit)) - ql_log(ql_log_warn, fcport->vha, 0x5060, + ql_log(ql_dbg_io, fcport->vha, 0x5060, "NVME-%s ERR Handling - hdl=%x status(%x) tr_len:%x resid=%x ox_id=%x\n", sp->name, sp->handle, comp_status, fd->transferred_length, le32_to_cpu(sts->residual_len), @@ -3491,7 +3491,7 @@ check_scsi_status: out: if (logit) - ql_log(ql_log_warn, fcport->vha, 0x3022, + ql_log(ql_dbg_io, fcport->vha, 0x3022, "FCP command status: 0x%x-0x%x (0x%x) nexus=%ld:%d:%llu portid=%02x%02x%02x oxid=0x%x cdb=%10phN len=0x%x rsp_info=0x%x resid=0x%x fw_resid=0x%x sp=%p cp=%p.\n", comp_status, scsi_status, res, vha->host_no, cp->device->id, cp->device->lun, fcport->d_id.b.domain, diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 43e682297fd5..0a1734f34587 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -118,7 +118,7 @@ static int ses_recv_diag(struct scsi_device *sdev, int page_code, static int ses_send_diag(struct scsi_device *sdev, int page_code, void *buf, int bufflen) { - u32 result; + int result; unsigned char cmd[] = { SEND_DIAGNOSTIC, diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 029c9631ec2b..95be7ecdfe10 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -318,8 +318,7 @@ static void ufshcd_add_query_upiu_trace(struct ufs_hba *hba, static void ufshcd_add_tm_upiu_trace(struct ufs_hba *hba, unsigned int tag, enum ufs_trace_str_t str_t) { - int off = (int)tag - hba->nutrs; - struct utp_task_req_desc *descp = &hba->utmrdl_base_addr[off]; + struct utp_task_req_desc *descp = &hba->utmrdl_base_addr[tag]; if (!trace_ufshcd_upiu_enabled()) return; @@ -6378,27 +6377,6 @@ static irqreturn_t ufshcd_check_errors(struct ufs_hba *hba, u32 intr_status) return retval; } -struct ctm_info { - struct ufs_hba *hba; - unsigned long pending; - unsigned int ncpl; -}; - -static bool ufshcd_compl_tm(struct request *req, void *priv, bool reserved) -{ - struct ctm_info *const ci = priv; - struct completion *c; - - WARN_ON_ONCE(reserved); - if (test_bit(req->tag, &ci->pending)) - return true; - ci->ncpl++; - c = req->end_io_data; - if (c) - complete(c); - return true; -} - /** * ufshcd_tmc_handler - handle task management function completion * @hba: per adapter instance @@ -6409,18 +6387,24 @@ static bool ufshcd_compl_tm(struct request *req, void *priv, bool reserved) */ static irqreturn_t ufshcd_tmc_handler(struct ufs_hba *hba) { - unsigned long flags; - struct request_queue *q = hba->tmf_queue; - struct ctm_info ci = { - .hba = hba, - }; + unsigned long flags, pending, issued; + irqreturn_t ret = IRQ_NONE; + int tag; + + pending = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL); spin_lock_irqsave(hba->host->host_lock, flags); - ci.pending = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL); - blk_mq_tagset_busy_iter(q->tag_set, ufshcd_compl_tm, &ci); + issued = hba->outstanding_tasks & ~pending; + for_each_set_bit(tag, &issued, hba->nutmrs) { + struct request *req = hba->tmf_rqs[tag]; + struct completion *c = req->end_io_data; + + complete(c); + ret = IRQ_HANDLED; + } spin_unlock_irqrestore(hba->host->host_lock, flags); - return ci.ncpl ? IRQ_HANDLED : IRQ_NONE; + return ret; } /** @@ -6543,9 +6527,9 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, ufshcd_hold(hba, false); spin_lock_irqsave(host->host_lock, flags); - blk_mq_start_request(req); task_tag = req->tag; + hba->tmf_rqs[req->tag] = req; treq->upiu_req.req_header.dword_0 |= cpu_to_be32(task_tag); memcpy(hba->utmrdl_base_addr + task_tag, treq, sizeof(*treq)); @@ -6586,6 +6570,7 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, } spin_lock_irqsave(hba->host->host_lock, flags); + hba->tmf_rqs[req->tag] = NULL; __clear_bit(task_tag, &hba->outstanding_tasks); spin_unlock_irqrestore(hba->host->host_lock, flags); @@ -9636,6 +9621,12 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) err = PTR_ERR(hba->tmf_queue); goto free_tmf_tag_set; } + hba->tmf_rqs = devm_kcalloc(hba->dev, hba->nutmrs, + sizeof(*hba->tmf_rqs), GFP_KERNEL); + if (!hba->tmf_rqs) { + err = -ENOMEM; + goto free_tmf_queue; + } /* Reset the attached device */ ufshcd_device_reset(hba); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index f0da5d3db1fa..41f6e06f9185 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -828,6 +828,7 @@ struct ufs_hba { struct blk_mq_tag_set tmf_tag_set; struct request_queue *tmf_queue; + struct request **tmf_rqs; struct uic_command *active_uic_cmd; struct mutex uic_cmd_mutex; diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index c25ce8f0e0af..07d0250f17c3 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -300,7 +300,7 @@ static void virtscsi_handle_transport_reset(struct virtio_scsi *vscsi, } break; default: - pr_info("Unsupport virtio scsi event reason %x\n", event->reason); + pr_info("Unsupported virtio scsi event reason %x\n", event->reason); } } @@ -392,7 +392,7 @@ static void virtscsi_handle_event(struct work_struct *work) virtscsi_handle_param_change(vscsi, event); break; default: - pr_err("Unsupport virtio scsi event %x\n", event->event); + pr_err("Unsupported virtio scsi event %x\n", event->event); } virtscsi_kick_event(vscsi, event_node); } diff --git a/drivers/soc/fsl/Kconfig b/drivers/soc/fsl/Kconfig index 4df32bc4c7a6..07d52cafbb31 100644 --- a/drivers/soc/fsl/Kconfig +++ b/drivers/soc/fsl/Kconfig @@ -24,6 +24,7 @@ config FSL_MC_DPIO tristate "QorIQ DPAA2 DPIO driver" depends on FSL_MC_BUS select SOC_BUS + select DIMLIB help Driver for the DPAA2 DPIO object. A DPIO provides queue and buffer management facilities for software to interact with diff --git a/drivers/soc/fsl/dpio/dpio-cmd.h b/drivers/soc/fsl/dpio/dpio-cmd.h index e13fd3ac1939..2fbcb78cdaaf 100644 --- a/drivers/soc/fsl/dpio/dpio-cmd.h +++ b/drivers/soc/fsl/dpio/dpio-cmd.h @@ -46,6 +46,9 @@ struct dpio_rsp_get_attr { __le64 qbman_portal_ci_addr; /* cmd word 3 */ __le32 qbman_version; + __le32 pad1; + /* cmd word 4 */ + __le32 clk; }; struct dpio_stashing_dest { diff --git a/drivers/soc/fsl/dpio/dpio-driver.c b/drivers/soc/fsl/dpio/dpio-driver.c index 7f397b4ad878..dd948889eeab 100644 --- a/drivers/soc/fsl/dpio/dpio-driver.c +++ b/drivers/soc/fsl/dpio/dpio-driver.c @@ -162,6 +162,7 @@ static int dpaa2_dpio_probe(struct fsl_mc_device *dpio_dev) goto err_get_attr; } desc.qman_version = dpio_attrs.qbman_version; + desc.qman_clk = dpio_attrs.clk; err = dpio_enable(dpio_dev->mc_io, 0, dpio_dev->mc_handle); if (err) { diff --git a/drivers/soc/fsl/dpio/dpio-service.c b/drivers/soc/fsl/dpio/dpio-service.c index 7351f3030550..3fd0d0840287 100644 --- a/drivers/soc/fsl/dpio/dpio-service.c +++ b/drivers/soc/fsl/dpio/dpio-service.c @@ -12,6 +12,7 @@ #include <linux/platform_device.h> #include <linux/interrupt.h> #include <linux/dma-mapping.h> +#include <linux/dim.h> #include <linux/slab.h> #include "dpio.h" @@ -28,6 +29,14 @@ struct dpaa2_io { spinlock_t lock_notifications; struct list_head notifications; struct device *dev; + + /* Net DIM */ + struct dim rx_dim; + /* protect against concurrent Net DIM updates */ + spinlock_t dim_lock; + u16 event_ctr; + u64 bytes; + u64 frames; }; struct dpaa2_io_store { @@ -100,6 +109,17 @@ struct dpaa2_io *dpaa2_io_service_select(int cpu) } EXPORT_SYMBOL_GPL(dpaa2_io_service_select); +static void dpaa2_io_dim_work(struct work_struct *w) +{ + struct dim *dim = container_of(w, struct dim, work); + struct dim_cq_moder moder = + net_dim_get_rx_moderation(dim->mode, dim->profile_ix); + struct dpaa2_io *d = container_of(dim, struct dpaa2_io, rx_dim); + + dpaa2_io_set_irq_coalescing(d, moder.usec); + dim->state = DIM_START_MEASURE; +} + /** * dpaa2_io_create() - create a dpaa2_io object. * @desc: the dpaa2_io descriptor @@ -114,6 +134,7 @@ struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, struct device *dev) { struct dpaa2_io *obj = kmalloc(sizeof(*obj), GFP_KERNEL); + u32 qman_256_cycles_per_ns; if (!obj) return NULL; @@ -127,7 +148,15 @@ struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, obj->dpio_desc = *desc; obj->swp_desc.cena_bar = obj->dpio_desc.regs_cena; obj->swp_desc.cinh_bar = obj->dpio_desc.regs_cinh; + obj->swp_desc.qman_clk = obj->dpio_desc.qman_clk; obj->swp_desc.qman_version = obj->dpio_desc.qman_version; + + /* Compute how many 256 QBMAN cycles fit into one ns. This is because + * the interrupt timeout period register needs to be specified in QBMAN + * clock cycles in increments of 256. + */ + qman_256_cycles_per_ns = 256000 / (obj->swp_desc.qman_clk / 1000000); + obj->swp_desc.qman_256_cycles_per_ns = qman_256_cycles_per_ns; obj->swp = qbman_swp_init(&obj->swp_desc); if (!obj->swp) { @@ -138,6 +167,7 @@ struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, INIT_LIST_HEAD(&obj->node); spin_lock_init(&obj->lock_mgmt_cmd); spin_lock_init(&obj->lock_notifications); + spin_lock_init(&obj->dim_lock); INIT_LIST_HEAD(&obj->notifications); /* For now only enable DQRR interrupts */ @@ -155,6 +185,12 @@ struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, obj->dev = dev; + memset(&obj->rx_dim, 0, sizeof(obj->rx_dim)); + INIT_WORK(&obj->rx_dim.work, dpaa2_io_dim_work); + obj->event_ctr = 0; + obj->bytes = 0; + obj->frames = 0; + return obj; } @@ -194,6 +230,8 @@ irqreturn_t dpaa2_io_irq(struct dpaa2_io *obj) struct qbman_swp *swp; u32 status; + obj->event_ctr++; + swp = obj->swp; status = qbman_swp_interrupt_read_status(swp); if (!status) @@ -779,3 +817,82 @@ int dpaa2_io_query_bp_count(struct dpaa2_io *d, u16 bpid, u32 *num) return 0; } EXPORT_SYMBOL_GPL(dpaa2_io_query_bp_count); + +/** + * dpaa2_io_set_irq_coalescing() - Set new IRQ coalescing values + * @d: the given DPIO object + * @irq_holdoff: interrupt holdoff (timeout) period in us + * + * Return 0 for success, or negative error code on error. + */ +int dpaa2_io_set_irq_coalescing(struct dpaa2_io *d, u32 irq_holdoff) +{ + struct qbman_swp *swp = d->swp; + + return qbman_swp_set_irq_coalescing(swp, swp->dqrr.dqrr_size - 1, + irq_holdoff); +} +EXPORT_SYMBOL(dpaa2_io_set_irq_coalescing); + +/** + * dpaa2_io_get_irq_coalescing() - Get the current IRQ coalescing parameters + * @d: the given DPIO object + * @irq_holdoff: interrupt holdoff (timeout) period in us + */ +void dpaa2_io_get_irq_coalescing(struct dpaa2_io *d, u32 *irq_holdoff) +{ + struct qbman_swp *swp = d->swp; + + qbman_swp_get_irq_coalescing(swp, NULL, irq_holdoff); +} +EXPORT_SYMBOL(dpaa2_io_get_irq_coalescing); + +/** + * dpaa2_io_set_adaptive_coalescing() - Enable/disable adaptive coalescing + * @d: the given DPIO object + * @use_adaptive_rx_coalesce: adaptive coalescing state + */ +void dpaa2_io_set_adaptive_coalescing(struct dpaa2_io *d, + int use_adaptive_rx_coalesce) +{ + d->swp->use_adaptive_rx_coalesce = use_adaptive_rx_coalesce; +} +EXPORT_SYMBOL(dpaa2_io_set_adaptive_coalescing); + +/** + * dpaa2_io_get_adaptive_coalescing() - Query adaptive coalescing state + * @d: the given DPIO object + * + * Return 1 when adaptive coalescing is enabled on the DPIO object and 0 + * otherwise. + */ +int dpaa2_io_get_adaptive_coalescing(struct dpaa2_io *d) +{ + return d->swp->use_adaptive_rx_coalesce; +} +EXPORT_SYMBOL(dpaa2_io_get_adaptive_coalescing); + +/** + * dpaa2_io_update_net_dim() - Update Net DIM + * @d: the given DPIO object + * @frames: how many frames have been dequeued by the user since the last call + * @bytes: how many bytes have been dequeued by the user since the last call + */ +void dpaa2_io_update_net_dim(struct dpaa2_io *d, __u64 frames, __u64 bytes) +{ + struct dim_sample dim_sample = {}; + + if (!d->swp->use_adaptive_rx_coalesce) + return; + + spin_lock(&d->dim_lock); + + d->bytes += bytes; + d->frames += frames; + + dim_update_sample(d->event_ctr, d->frames, d->bytes, &dim_sample); + net_dim(&d->rx_dim, dim_sample); + + spin_unlock(&d->dim_lock); +} +EXPORT_SYMBOL(dpaa2_io_update_net_dim); diff --git a/drivers/soc/fsl/dpio/dpio.c b/drivers/soc/fsl/dpio/dpio.c index af74c597a675..8ed606ffaac5 100644 --- a/drivers/soc/fsl/dpio/dpio.c +++ b/drivers/soc/fsl/dpio/dpio.c @@ -162,6 +162,7 @@ int dpio_get_attributes(struct fsl_mc_io *mc_io, attr->qbman_portal_ci_offset = le64_to_cpu(dpio_rsp->qbman_portal_ci_addr); attr->qbman_version = le32_to_cpu(dpio_rsp->qbman_version); + attr->clk = le32_to_cpu(dpio_rsp->clk); return 0; } diff --git a/drivers/soc/fsl/dpio/dpio.h b/drivers/soc/fsl/dpio/dpio.h index da06f7258098..7fda44f0d7f4 100644 --- a/drivers/soc/fsl/dpio/dpio.h +++ b/drivers/soc/fsl/dpio/dpio.h @@ -59,6 +59,7 @@ int dpio_disable(struct fsl_mc_io *mc_io, * @num_priorities: Number of priorities for the notification channel (1-8); * relevant only if 'channel_mode = DPIO_LOCAL_CHANNEL' * @qbman_version: QBMAN version + * @clk: QBMAN clock frequency value in Hz */ struct dpio_attr { int id; @@ -68,6 +69,7 @@ struct dpio_attr { enum dpio_channel_mode channel_mode; u8 num_priorities; u32 qbman_version; + u32 clk; }; int dpio_get_attributes(struct fsl_mc_io *mc_io, diff --git a/drivers/soc/fsl/dpio/qbman-portal.c b/drivers/soc/fsl/dpio/qbman-portal.c index f13da4d7d1c5..d3c58df6240d 100644 --- a/drivers/soc/fsl/dpio/qbman-portal.c +++ b/drivers/soc/fsl/dpio/qbman-portal.c @@ -29,6 +29,7 @@ #define QBMAN_CINH_SWP_EQCR_AM_RT 0x980 #define QBMAN_CINH_SWP_RCR_AM_RT 0x9c0 #define QBMAN_CINH_SWP_DQPI 0xa00 +#define QBMAN_CINH_SWP_DQRR_ITR 0xa80 #define QBMAN_CINH_SWP_DCAP 0xac0 #define QBMAN_CINH_SWP_SDQCR 0xb00 #define QBMAN_CINH_SWP_EQCR_AM_RT2 0xb40 @@ -38,6 +39,7 @@ #define QBMAN_CINH_SWP_IER 0xe40 #define QBMAN_CINH_SWP_ISDR 0xe80 #define QBMAN_CINH_SWP_IIR 0xec0 +#define QBMAN_CINH_SWP_ITPR 0xf40 /* CENA register offsets */ #define QBMAN_CENA_SWP_EQCR(n) (0x000 + ((u32)(n) << 6)) @@ -355,6 +357,9 @@ struct qbman_swp *qbman_swp_init(const struct qbman_swp_desc *d) & p->eqcr.pi_ci_mask; p->eqcr.available = p->eqcr.pi_ring_size; + /* Initialize the software portal with a irq timeout period of 0us */ + qbman_swp_set_irq_coalescing(p, p->dqrr.dqrr_size - 1, 0); + return p; } @@ -1796,3 +1801,57 @@ u32 qbman_bp_info_num_free_bufs(struct qbman_bp_query_rslt *a) { return le32_to_cpu(a->fill); } + +/** + * qbman_swp_set_irq_coalescing() - Set new IRQ coalescing values + * @p: the software portal object + * @irq_threshold: interrupt threshold + * @irq_holdoff: interrupt holdoff (timeout) period in us + * + * Return 0 for success, or negative error code on error. + */ +int qbman_swp_set_irq_coalescing(struct qbman_swp *p, u32 irq_threshold, + u32 irq_holdoff) +{ + u32 itp, max_holdoff; + + /* Convert irq_holdoff value from usecs to 256 QBMAN clock cycles + * increments. This depends to the QBMAN internal frequency. + */ + itp = (irq_holdoff * 1000) / p->desc->qman_256_cycles_per_ns; + if (itp < 0 || itp > 4096) { + max_holdoff = (p->desc->qman_256_cycles_per_ns * 4096) / 1000; + pr_err("irq_holdoff must be between 0..%dus\n", max_holdoff); + return -EINVAL; + } + + if (irq_threshold >= p->dqrr.dqrr_size || irq_threshold < 0) { + pr_err("irq_threshold must be between 0..%d\n", + p->dqrr.dqrr_size - 1); + return -EINVAL; + } + + p->irq_threshold = irq_threshold; + p->irq_holdoff = irq_holdoff; + + qbman_write_register(p, QBMAN_CINH_SWP_DQRR_ITR, irq_threshold); + qbman_write_register(p, QBMAN_CINH_SWP_ITPR, itp); + + return 0; +} + +/** + * qbman_swp_get_irq_coalescing() - Get the current IRQ coalescing parameters + * @p: the software portal object + * @irq_threshold: interrupt threshold (an IRQ is generated when there are more + * DQRR entries in the portal than the threshold) + * @irq_holdoff: interrupt holdoff (timeout) period in us + */ +void qbman_swp_get_irq_coalescing(struct qbman_swp *p, u32 *irq_threshold, + u32 *irq_holdoff) +{ + if (irq_threshold) + *irq_threshold = p->irq_threshold; + if (irq_holdoff) + *irq_holdoff = p->irq_holdoff; +} diff --git a/drivers/soc/fsl/dpio/qbman-portal.h b/drivers/soc/fsl/dpio/qbman-portal.h index c7c2225b7d91..b23883dd2725 100644 --- a/drivers/soc/fsl/dpio/qbman-portal.h +++ b/drivers/soc/fsl/dpio/qbman-portal.h @@ -24,6 +24,8 @@ struct qbman_swp_desc { void *cena_bar; /* Cache-enabled portal base address */ void __iomem *cinh_bar; /* Cache-inhibited portal base address */ u32 qman_version; + u32 qman_clk; + u32 qman_256_cycles_per_ns; }; #define QBMAN_SWP_INTERRUPT_EQRI 0x01 @@ -156,6 +158,11 @@ struct qbman_swp { } eqcr; spinlock_t access_spinlock; + + /* Interrupt coalescing */ + u32 irq_threshold; + u32 irq_holdoff; + int use_adaptive_rx_coalesce; }; /* Function pointers */ @@ -648,4 +655,10 @@ static inline const struct dpaa2_dq *qbman_swp_dqrr_next(struct qbman_swp *s) return qbman_swp_dqrr_next_ptr(s); } +int qbman_swp_set_irq_coalescing(struct qbman_swp *p, u32 irq_threshold, + u32 irq_holdoff); + +void qbman_swp_get_irq_coalescing(struct qbman_swp *p, u32 *irq_threshold, + u32 *irq_holdoff); + #endif /* __FSL_QBMAN_PORTAL_H */ diff --git a/drivers/soc/qcom/mdt_loader.c b/drivers/soc/qcom/mdt_loader.c index bda170d7b4a2..72fc2b539213 100644 --- a/drivers/soc/qcom/mdt_loader.c +++ b/drivers/soc/qcom/mdt_loader.c @@ -98,7 +98,7 @@ void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len) if (ehdr->e_phnum < 2) return ERR_PTR(-EINVAL); - if (phdrs[0].p_type == PT_LOAD || phdrs[1].p_type == PT_LOAD) + if (phdrs[0].p_type == PT_LOAD) return ERR_PTR(-EINVAL); if ((phdrs[1].p_flags & QCOM_MDT_TYPE_MASK) != QCOM_MDT_TYPE_HASH) diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c index 9faf48302f4b..52e581167115 100644 --- a/drivers/soc/qcom/socinfo.c +++ b/drivers/soc/qcom/socinfo.c @@ -628,7 +628,7 @@ static int qcom_socinfo_probe(struct platform_device *pdev) /* Feed the soc specific unique data into entropy pool */ add_device_randomness(info, item_size); - platform_set_drvdata(pdev, qs->soc_dev); + platform_set_drvdata(pdev, qs); return 0; } diff --git a/drivers/soc/ti/omap_prm.c b/drivers/soc/ti/omap_prm.c index ea64e187854e..f32e1cbbe8c5 100644 --- a/drivers/soc/ti/omap_prm.c +++ b/drivers/soc/ti/omap_prm.c @@ -825,25 +825,28 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, writel_relaxed(v, reset->prm->base + reset->prm->data->rstctrl); spin_unlock_irqrestore(&reset->lock, flags); - if (!has_rstst) - goto exit; + /* wait for the reset bit to clear */ + ret = readl_relaxed_poll_timeout_atomic(reset->prm->base + + reset->prm->data->rstctrl, + v, !(v & BIT(id)), 1, + OMAP_RESET_MAX_WAIT); + if (ret) + pr_err("%s: timedout waiting for %s:%lu\n", __func__, + reset->prm->data->name, id); /* wait for the status to be set */ - ret = readl_relaxed_poll_timeout_atomic(reset->prm->base + + if (has_rstst) { + ret = readl_relaxed_poll_timeout_atomic(reset->prm->base + reset->prm->data->rstst, v, v & BIT(st_bit), 1, OMAP_RESET_MAX_WAIT); - if (ret) - pr_err("%s: timedout waiting for %s:%lu\n", __func__, - reset->prm->data->name, id); + if (ret) + pr_err("%s: timedout waiting for %s:%lu\n", __func__, + reset->prm->data->name, id); + } -exit: - if (reset->clkdm) { - /* At least dra7 iva needs a delay before clkdm idle */ - if (has_rstst) - udelay(1); + if (reset->clkdm) pdata->clkdm_allow_idle(reset->clkdm); - } return ret; } diff --git a/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/input_system.c b/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/input_system.c index 8e085dda0c18..712e01c37870 100644 --- a/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/input_system.c +++ b/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/input_system.c @@ -1646,6 +1646,8 @@ static input_system_err_t input_system_configure_channel_sensor( default: return INPUT_SYSTEM_ERR_PARAMETER_NOT_SUPPORTED; } + + return INPUT_SYSTEM_ERR_NO_ERROR; } // Test flags and set structure. diff --git a/drivers/tee/optee/shm_pool.c b/drivers/tee/optee/shm_pool.c index c41a9a501a6e..d167039af519 100644 --- a/drivers/tee/optee/shm_pool.c +++ b/drivers/tee/optee/shm_pool.c @@ -35,7 +35,7 @@ static int pool_op_alloc(struct tee_shm_pool_mgr *poolm, unsigned int nr_pages = 1 << order, i; struct page **pages; - pages = kcalloc(nr_pages, sizeof(pages), GFP_KERNEL); + pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL); if (!pages) { rc = -ENOMEM; goto err; diff --git a/drivers/thunderbolt/Makefile b/drivers/thunderbolt/Makefile index da19d7987d00..78fd365893c1 100644 --- a/drivers/thunderbolt/Makefile +++ b/drivers/thunderbolt/Makefile @@ -7,6 +7,7 @@ thunderbolt-objs += usb4_port.o nvm.o retimer.o quirks.o thunderbolt-${CONFIG_ACPI} += acpi.o thunderbolt-$(CONFIG_DEBUG_FS) += debugfs.o thunderbolt-${CONFIG_USB4_KUNIT_TEST} += test.o +CFLAGS_test.o += $(DISABLE_STRUCTLEAK_PLUGIN) thunderbolt_dma_test-${CONFIG_USB4_DMA_TEST} += dma_test.o obj-$(CONFIG_USB4_DMA_TEST) += thunderbolt_dma_test.o diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index 8f143c09a169..f0bf01ea069a 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -618,10 +618,8 @@ static int __init xenboot_console_setup(struct console *console, char *string) { static struct xencons_info xenboot; - if (xen_initial_domain()) + if (xen_initial_domain() || !xen_pv_domain()) return 0; - if (!xen_pv_domain()) - return -ENODEV; return xencons_info_pv_init(&xenboot, 0); } @@ -632,17 +630,16 @@ static void xenboot_write_console(struct console *console, const char *string, unsigned int linelen, off = 0; const char *pos; + if (dom0_write_console(0, string, len) >= 0) + return; + if (!xen_pv_domain()) { xen_hvm_early_write(0, string, len); return; } - dom0_write_console(0, string, len); - - if (xen_initial_domain()) + if (domU_write_console(0, "(early) ", 8) < 0) return; - - domU_write_console(0, "(early) ", 8); while (off < len && NULL != (pos = strchr(string+off, '\n'))) { linelen = pos-string+off; if (off + linelen > len) diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index 8b7bc10b6e8b..f1d100671ee6 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -420,11 +420,16 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) data->phy = devm_usb_get_phy_by_phandle(dev, "fsl,usbphy", 0); if (IS_ERR(data->phy)) { ret = PTR_ERR(data->phy); - /* Return -EINVAL if no usbphy is available */ - if (ret == -ENODEV) - data->phy = NULL; - else - goto err_clk; + if (ret == -ENODEV) { + data->phy = devm_usb_get_phy_by_phandle(dev, "phys", 0); + if (IS_ERR(data->phy)) { + ret = PTR_ERR(data->phy); + if (ret == -ENODEV) + data->phy = NULL; + else + goto err_clk; + } + } } pdata.usb_phy = data->phy; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 4e2f1552f4b7..7b2e2420ecae 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -340,6 +340,9 @@ static void acm_process_notification(struct acm *acm, unsigned char *buf) acm->iocount.overrun++; spin_unlock_irqrestore(&acm->read_lock, flags); + if (newctrl & ACM_CTRL_BRK) + tty_flip_buffer_push(&acm->port); + if (difference) wake_up_all(&acm->wioctl); @@ -475,11 +478,16 @@ static int acm_submit_read_urbs(struct acm *acm, gfp_t mem_flags) static void acm_process_read_urb(struct acm *acm, struct urb *urb) { + unsigned long flags; + if (!urb->actual_length) return; + spin_lock_irqsave(&acm->read_lock, flags); tty_insert_flip_string(&acm->port, urb->transfer_buffer, urb->actual_length); + spin_unlock_irqrestore(&acm->read_lock, flags); + tty_flip_buffer_push(&acm->port); } diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index 35d5908b5478..fdf79bcf7eb0 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -824,7 +824,7 @@ static struct usb_class_driver wdm_class = { }; /* --- WWAN framework integration --- */ -#ifdef CONFIG_WWAN_CORE +#ifdef CONFIG_WWAN static int wdm_wwan_port_start(struct wwan_port *port) { struct wdm_device *desc = wwan_port_get_drvdata(port); @@ -963,11 +963,11 @@ static void wdm_wwan_rx(struct wdm_device *desc, int length) /* inbuf has been copied, it is safe to check for outstanding data */ schedule_work(&desc->service_outs_intr); } -#else /* CONFIG_WWAN_CORE */ +#else /* CONFIG_WWAN */ static void wdm_wwan_init(struct wdm_device *desc) {} static void wdm_wwan_deinit(struct wdm_device *desc) {} static void wdm_wwan_rx(struct wdm_device *desc, int length) {} -#endif /* CONFIG_WWAN_CORE */ +#endif /* CONFIG_WWAN */ /* --- error handling --- */ static void wdm_rxwork(struct work_struct *work) diff --git a/drivers/usb/common/Kconfig b/drivers/usb/common/Kconfig index 5e8a04e3dd3c..b856622431a7 100644 --- a/drivers/usb/common/Kconfig +++ b/drivers/usb/common/Kconfig @@ -6,8 +6,7 @@ config USB_COMMON config USB_LED_TRIG bool "USB LED Triggers" - depends on LEDS_CLASS && LEDS_TRIGGERS - select USB_COMMON + depends on LEDS_CLASS && USB_COMMON && LEDS_TRIGGERS help This option adds LED triggers for USB host and/or gadget activity. diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 804b50548163..4519d06c9ca2 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4243,7 +4243,7 @@ int dwc3_gadget_init(struct dwc3 *dwc) } - usb_initialize_gadget(dwc->sysdev, dwc->gadget, dwc_gadget_release); + usb_initialize_gadget(dwc->dev, dwc->gadget, dwc_gadget_release); dev = &dwc->gadget->dev; dev->platform_data = dwc; dwc->gadget->ops = &dwc3_gadget_ops; diff --git a/drivers/usb/gadget/function/f_phonet.c b/drivers/usb/gadget/function/f_phonet.c index 0b468f5d55bc..068ed8417e5a 100644 --- a/drivers/usb/gadget/function/f_phonet.c +++ b/drivers/usb/gadget/function/f_phonet.c @@ -267,6 +267,8 @@ static const struct net_device_ops pn_netdev_ops = { static void pn_net_setup(struct net_device *dev) { + const u8 addr = PN_MEDIA_USB; + dev->features = 0; dev->type = ARPHRD_PHONET; dev->flags = IFF_POINTOPOINT | IFF_NOARP; @@ -274,8 +276,9 @@ static void pn_net_setup(struct net_device *dev) dev->min_mtu = PHONET_MIN_MTU; dev->max_mtu = PHONET_MAX_MTU; dev->hard_header_len = 1; - dev->dev_addr[0] = PN_MEDIA_USB; dev->addr_len = 1; + dev_addr_set(dev, &addr); + dev->tx_queue_len = 1; dev->netdev_ops = &pn_netdev_ops; diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index be864560bfea..ef55b8bb5870 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -674,11 +674,17 @@ static int set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts, ssize = uac2_opts->c_ssize; } - if (!is_playback && (uac2_opts->c_sync == USB_ENDPOINT_SYNC_ASYNC)) + if (!is_playback && (uac2_opts->c_sync == USB_ENDPOINT_SYNC_ASYNC)) { + // Win10 requires max packet size + 1 frame srate = srate * (1000 + uac2_opts->fb_max) / 1000; - - max_size_bw = num_channels(chmask) * ssize * - DIV_ROUND_UP(srate, factor / (1 << (ep_desc->bInterval - 1))); + // updated srate is always bigger, therefore DIV_ROUND_UP always yields +1 + max_size_bw = num_channels(chmask) * ssize * + (DIV_ROUND_UP(srate, factor / (1 << (ep_desc->bInterval - 1)))); + } else { + // adding 1 frame provision for Win10 + max_size_bw = num_channels(chmask) * ssize * + (DIV_ROUND_UP(srate, factor / (1 << (ep_desc->bInterval - 1))) + 1); + } ep_desc->wMaxPacketSize = cpu_to_le16(min_t(u16, max_size_bw, max_size_ep)); diff --git a/drivers/usb/host/ohci-omap.c b/drivers/usb/host/ohci-omap.c index 0b3722770760..ded9738392e4 100644 --- a/drivers/usb/host/ohci-omap.c +++ b/drivers/usb/host/ohci-omap.c @@ -40,17 +40,6 @@ #include <mach/usb.h> -/* OMAP-1510 OHCI has its own MMU for DMA */ -#define OMAP1510_LB_MEMSIZE 32 /* Should be same as SDRAM size */ -#define OMAP1510_LB_CLOCK_DIV 0xfffec10c -#define OMAP1510_LB_MMU_CTL 0xfffec208 -#define OMAP1510_LB_MMU_LCK 0xfffec224 -#define OMAP1510_LB_MMU_LD_TLB 0xfffec228 -#define OMAP1510_LB_MMU_CAM_H 0xfffec22c -#define OMAP1510_LB_MMU_CAM_L 0xfffec230 -#define OMAP1510_LB_MMU_RAM_H 0xfffec234 -#define OMAP1510_LB_MMU_RAM_L 0xfffec238 - #define DRIVER_DESC "OHCI OMAP driver" struct ohci_omap_priv { @@ -104,61 +93,6 @@ static int omap_ohci_transceiver_power(struct ohci_omap_priv *priv, int on) return 0; } -#ifdef CONFIG_ARCH_OMAP15XX -/* - * OMAP-1510 specific Local Bus clock on/off - */ -static int omap_1510_local_bus_power(int on) -{ - if (on) { - omap_writel((1 << 1) | (1 << 0), OMAP1510_LB_MMU_CTL); - udelay(200); - } else { - omap_writel(0, OMAP1510_LB_MMU_CTL); - } - - return 0; -} - -/* - * OMAP-1510 specific Local Bus initialization - * NOTE: This assumes 32MB memory size in OMAP1510LB_MEMSIZE. - * See also arch/mach-omap/memory.h for __virt_to_dma() and - * __dma_to_virt() which need to match with the physical - * Local Bus address below. - */ -static int omap_1510_local_bus_init(void) -{ - unsigned int tlb; - unsigned long lbaddr, physaddr; - - omap_writel((omap_readl(OMAP1510_LB_CLOCK_DIV) & 0xfffffff8) | 0x4, - OMAP1510_LB_CLOCK_DIV); - - /* Configure the Local Bus MMU table */ - for (tlb = 0; tlb < OMAP1510_LB_MEMSIZE; tlb++) { - lbaddr = tlb * 0x00100000 + OMAP1510_LB_OFFSET; - physaddr = tlb * 0x00100000 + PHYS_OFFSET; - omap_writel((lbaddr & 0x0fffffff) >> 22, OMAP1510_LB_MMU_CAM_H); - omap_writel(((lbaddr & 0x003ffc00) >> 6) | 0xc, - OMAP1510_LB_MMU_CAM_L); - omap_writel(physaddr >> 16, OMAP1510_LB_MMU_RAM_H); - omap_writel((physaddr & 0x0000fc00) | 0x300, OMAP1510_LB_MMU_RAM_L); - omap_writel(tlb << 4, OMAP1510_LB_MMU_LCK); - omap_writel(0x1, OMAP1510_LB_MMU_LD_TLB); - } - - /* Enable the walking table */ - omap_writel(omap_readl(OMAP1510_LB_MMU_CTL) | (1 << 3), OMAP1510_LB_MMU_CTL); - udelay(200); - - return 0; -} -#else -#define omap_1510_local_bus_power(x) {} -#define omap_1510_local_bus_init() {} -#endif - #ifdef CONFIG_USB_OTG static void start_hnp(struct ohci_hcd *ohci) @@ -229,10 +163,8 @@ static int ohci_omap_reset(struct usb_hcd *hcd) omap_ohci_clock_power(priv, 1); - if (cpu_is_omap15xx()) { - omap_1510_local_bus_power(1); - omap_1510_local_bus_init(); - } + if (config->lb_reset) + config->lb_reset(); ret = ohci_setup(hcd); if (ret < 0) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 575fa89a783f..1bf494b649bd 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1787,7 +1787,6 @@ static int tegra_xusb_remove(struct platform_device *pdev) return 0; } -#if IS_ENABLED(CONFIG_PM) || IS_ENABLED(CONFIG_PM_SLEEP) static bool xhci_hub_ports_suspended(struct xhci_hub *hub) { struct device *dev = hub->hcd->self.controller; @@ -2102,7 +2101,7 @@ out: return err; } -static int tegra_xusb_suspend(struct device *dev) +static __maybe_unused int tegra_xusb_suspend(struct device *dev) { struct tegra_xusb *tegra = dev_get_drvdata(dev); int err; @@ -2144,7 +2143,7 @@ out: return err; } -static int tegra_xusb_resume(struct device *dev) +static __maybe_unused int tegra_xusb_resume(struct device *dev) { struct tegra_xusb *tegra = dev_get_drvdata(dev); int err; @@ -2174,10 +2173,8 @@ static int tegra_xusb_resume(struct device *dev) return 0; } -#endif -#ifdef CONFIG_PM -static int tegra_xusb_runtime_suspend(struct device *dev) +static __maybe_unused int tegra_xusb_runtime_suspend(struct device *dev) { struct tegra_xusb *tegra = dev_get_drvdata(dev); int ret; @@ -2190,7 +2187,7 @@ static int tegra_xusb_runtime_suspend(struct device *dev) return ret; } -static int tegra_xusb_runtime_resume(struct device *dev) +static __maybe_unused int tegra_xusb_runtime_resume(struct device *dev) { struct tegra_xusb *tegra = dev_get_drvdata(dev); int err; @@ -2201,7 +2198,6 @@ static int tegra_xusb_runtime_resume(struct device *dev) return err; } -#endif static const struct dev_pm_ops tegra_xusb_pm_ops = { SET_RUNTIME_PM_OPS(tegra_xusb_runtime_suspend, diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index 9858716698df..c15eec9cc460 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -696,7 +696,7 @@ irqreturn_t tcpci_irq(struct tcpci *tcpci) tcpm_pd_receive(tcpci->port, &msg); } - if (status & TCPC_ALERT_EXTENDED_STATUS) { + if (tcpci->data->vbus_vsafe0v && (status & TCPC_ALERT_EXTENDED_STATUS)) { ret = regmap_read(tcpci->regmap, TCPC_EXTENDED_STATUS, &raw); if (!ret && (raw & TCPC_EXTENDED_STATUS_VSAFE0V)) tcpm_vbus_change(tcpci->port); diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index a4d37205df54..7f2f3ff1b391 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4876,6 +4876,7 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1, tcpm_set_state(port, SRC_ATTACH_WAIT, 0); break; case SRC_ATTACHED: + case SRC_STARTUP: case SRC_SEND_CAPABILITIES: case SRC_READY: if (tcpm_port_is_disconnected(port) || diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 21b3ae25c76d..ea4cc0a6e40c 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -625,10 +625,6 @@ static int tps6598x_probe(struct i2c_client *client) if (ret < 0) return ret; - fwnode = device_get_named_child_node(&client->dev, "connector"); - if (!fwnode) - return -ENODEV; - /* * This fwnode has a "compatible" property, but is never populated as a * struct device. Instead we simply parse it to read the properties. @@ -636,7 +632,9 @@ static int tps6598x_probe(struct i2c_client *client) * with existing DT files, we work around this by deleting any * fwnode_links to/from this fwnode. */ - fw_devlink_purge_absent_suppliers(fwnode); + fwnode = device_get_named_child_node(&client->dev, "connector"); + if (fwnode) + fw_devlink_purge_absent_suppliers(fwnode); tps->role_sw = fwnode_usb_role_switch_get(fwnode); if (IS_ERR(tps->role_sw)) { diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index b26b79dfcac9..6ed5e608dd04 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -2193,8 +2193,9 @@ config FB_HYPERV This framebuffer driver supports Microsoft Hyper-V Synthetic Video. config FB_SIMPLE - bool "Simple framebuffer support" - depends on (FB = y) && !DRM_SIMPLEDRM + tristate "Simple framebuffer support" + depends on FB + depends on !DRM_SIMPLEDRM select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT diff --git a/drivers/video/fbdev/gbefb.c b/drivers/video/fbdev/gbefb.c index c5b99a4861e8..6b4d5a7f3e15 100644 --- a/drivers/video/fbdev/gbefb.c +++ b/drivers/video/fbdev/gbefb.c @@ -1267,7 +1267,7 @@ static struct platform_device *gbefb_device; static int __init gbefb_init(void) { int ret = platform_driver_register(&gbefb_driver); - if (!ret) { + if (IS_ENABLED(CONFIG_SGI_IP32) && !ret) { gbefb_device = platform_device_alloc("gbefb", 0); if (gbefb_device) { ret = platform_device_add(gbefb_device); diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 22f5aff0c136..1b2c3aca6887 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -241,7 +241,7 @@ config XEN_PRIVCMD config XEN_ACPI_PROCESSOR tristate "Xen ACPI processor" - depends on XEN && XEN_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ + depends on XEN && XEN_PV_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ default m help This ACPI processor uploads Power Management information to the Xen @@ -259,7 +259,7 @@ config XEN_ACPI_PROCESSOR config XEN_MCE_LOG bool "Xen platform mcelog" - depends on XEN_DOM0 && X86_MCE + depends on XEN_PV_DOM0 && X86_MCE help Allow kernel fetching MCE error from Xen platform and converting it into Linux mcelog format for mcelog tools diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 43ebfe36ac27..3a50f097ed3e 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -491,12 +491,12 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) } /* - * Stop waiting if either state is not BP_EAGAIN and ballooning action is - * needed, or if the credit has changed while state is BP_EAGAIN. + * Stop waiting if either state is BP_DONE and ballooning action is + * needed, or if the credit has changed while state is not BP_DONE. */ static bool balloon_thread_cond(enum bp_state state, long credit) { - if (state != BP_EAGAIN) + if (state == BP_DONE) credit = 0; return current_credit() != credit || kthread_should_stop(); @@ -516,10 +516,19 @@ static int balloon_thread(void *unused) set_freezable(); for (;;) { - if (state == BP_EAGAIN) - timeout = balloon_stats.schedule_delay * HZ; - else + switch (state) { + case BP_DONE: + case BP_ECANCELED: timeout = 3600 * HZ; + break; + case BP_EAGAIN: + timeout = balloon_stats.schedule_delay * HZ; + break; + case BP_WAIT: + timeout = HZ; + break; + } + credit = current_credit(); wait_event_freezable_timeout(balloon_thread_wq, diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 720a7b7abd46..3369734108af 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -257,7 +257,7 @@ static long privcmd_ioctl_mmap(struct file *file, void __user *udata) LIST_HEAD(pagelist); struct mmap_gfn_state state; - /* We only support privcmd_ioctl_mmap_batch for auto translated. */ + /* We only support privcmd_ioctl_mmap_batch for non-auto-translated. */ if (xen_feature(XENFEAT_auto_translated_physmap)) return -ENOSYS; @@ -420,7 +420,7 @@ static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs) int rc; struct page **pages; - pages = kcalloc(numpgs, sizeof(pages[0]), GFP_KERNEL); + pages = kvcalloc(numpgs, sizeof(pages[0]), GFP_KERNEL); if (pages == NULL) return -ENOMEM; @@ -428,7 +428,7 @@ static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs) if (rc != 0) { pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__, numpgs, rc); - kfree(pages); + kvfree(pages); return -ENOMEM; } BUG_ON(vma->vm_private_data != NULL); @@ -803,21 +803,21 @@ static long privcmd_ioctl_mmap_resource(struct file *file, unsigned int domid = (xdata.flags & XENMEM_rsrc_acq_caller_owned) ? DOMID_SELF : kdata.dom; - int num; + int num, *errs = (int *)pfns; + BUILD_BUG_ON(sizeof(*errs) > sizeof(*pfns)); num = xen_remap_domain_mfn_array(vma, kdata.addr & PAGE_MASK, - pfns, kdata.num, (int *)pfns, + pfns, kdata.num, errs, vma->vm_page_prot, - domid, - vma->vm_private_data); + domid); if (num < 0) rc = num; else if (num != kdata.num) { unsigned int i; for (i = 0; i < num; i++) { - rc = pfns[i]; + rc = errs[i]; if (rc < 0) break; } @@ -912,7 +912,7 @@ static void privcmd_close(struct vm_area_struct *vma) else pr_crit("unable to unmap MFN range: leaking %d pages. rc=%d\n", numpgs, rc); - kfree(pages); + kvfree(pages); } static vm_fault_t privcmd_fault(struct vm_fault *vmf) diff --git a/fs/9p/cache.c b/fs/9p/cache.c index eb2151fb6049..1769a44f4819 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -23,7 +23,7 @@ struct fscache_netfs v9fs_cache_netfs = { .version = 0, }; -/** +/* * v9fs_random_cachetag - Generate a random tag to be associated * with a new cache session. * @@ -233,7 +233,7 @@ static void v9fs_vfs_readpage_complete(struct page *page, void *data, unlock_page(page); } -/** +/* * __v9fs_readpage_from_fscache - read a page from cache * * Returns 0 if the pages are in cache and a BIO is submitted, @@ -268,7 +268,7 @@ int __v9fs_readpage_from_fscache(struct inode *inode, struct page *page) } } -/** +/* * __v9fs_readpages_from_fscache - read multiple pages from cache * * Returns 0 if the pages are in cache and a BIO is submitted, @@ -308,7 +308,7 @@ int __v9fs_readpages_from_fscache(struct inode *inode, } } -/** +/* * __v9fs_readpage_to_fscache - write a page to the cache * */ diff --git a/fs/9p/fid.c b/fs/9p/fid.c index 9d9de62592be..b8863dd0de5c 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -19,18 +19,18 @@ #include "v9fs_vfs.h" #include "fid.h" +static inline void __add_fid(struct dentry *dentry, struct p9_fid *fid) +{ + hlist_add_head(&fid->dlist, (struct hlist_head *)&dentry->d_fsdata); +} + + /** * v9fs_fid_add - add a fid to a dentry * @dentry: dentry that the fid is being added to * @fid: fid to add * */ - -static inline void __add_fid(struct dentry *dentry, struct p9_fid *fid) -{ - hlist_add_head(&fid->dlist, (struct hlist_head *)&dentry->d_fsdata); -} - void v9fs_fid_add(struct dentry *dentry, struct p9_fid *fid) { spin_lock(&dentry->d_lock); @@ -67,7 +67,7 @@ static struct p9_fid *v9fs_fid_find_inode(struct inode *inode, kuid_t uid) /** * v9fs_open_fid_add - add an open fid to an inode - * @dentry: inode that the fid is being added to + * @inode: inode that the fid is being added to * @fid: fid to add * */ diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index cdb99507ef33..2e0fa7c932db 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -155,6 +155,7 @@ int v9fs_show_options(struct seq_file *m, struct dentry *root) /** * v9fs_parse_options - parse mount options into session structure * @v9ses: existing v9fs session information + * @opts: The mount option string * * Return 0 upon success, -ERRNO upon failure. */ @@ -542,12 +543,9 @@ extern int v9fs_error_init(void); static struct kobject *v9fs_kobj; #ifdef CONFIG_9P_FSCACHE -/** - * caches_show - list caches associated with a session - * - * Returns the size of buffer written. +/* + * List caches associated with a session */ - static ssize_t caches_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index cce9ace651a2..1c4f1b39cc95 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -30,8 +30,7 @@ /** * v9fs_fid_readpage - read an entire page in from 9P - * - * @fid: fid being read + * @data: Opaque pointer to the fid being read * @page: structure to page * */ @@ -116,6 +115,8 @@ static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping, /** * v9fs_release_page - release the private state associated with a page + * @page: The page to be released + * @gfp: The caller's allocation restrictions * * Returns 1 if the page can be released, false otherwise. */ @@ -129,9 +130,9 @@ static int v9fs_release_page(struct page *page, gfp_t gfp) /** * v9fs_invalidate_page - Invalidate a page completely or partially - * - * @page: structure to page - * @offset: offset in the page + * @page: The page to be invalidated + * @offset: offset of the invalidated region + * @length: length of the invalidated region */ static void v9fs_invalidate_page(struct page *page, unsigned int offset, @@ -199,6 +200,8 @@ static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc) /** * v9fs_launder_page - Writeback a dirty page + * @page: The page to be cleaned up + * * Returns 0 on success. */ @@ -219,6 +222,7 @@ static int v9fs_launder_page(struct page *page) /** * v9fs_direct_IO - 9P address space operation for direct I/O * @iocb: target I/O control block + * @iter: The data/buffer to use * * The presence of v9fs_direct_IO() in the address space ops vector * allowes open() O_DIRECT flags which would have failed otherwise. diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index aab5e6538660..246235ebdb70 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -359,14 +359,11 @@ out_err: } /** - * v9fs_file_read - read from a file - * @filp: file pointer to read - * @udata: user data buffer to read data into - * @count: size of buffer - * @offset: offset at which to read data + * v9fs_file_read_iter - read from a file + * @iocb: The operation parameters + * @to: The buffer to read into * */ - static ssize_t v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { @@ -388,11 +385,9 @@ v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) } /** - * v9fs_file_write - write to a file - * @filp: file pointer to write - * @data: data buffer to write data from - * @count: size of buffer - * @offset: offset at which to write data + * v9fs_file_write_iter - write to a file + * @iocb: The operation parameters + * @from: The data to write * */ static ssize_t @@ -561,11 +556,9 @@ out_unlock: } /** - * v9fs_mmap_file_read - read from a file - * @filp: file pointer to read - * @data: user data buffer to read data into - * @count: size of buffer - * @offset: offset at which to read data + * v9fs_mmap_file_read_iter - read from a file + * @iocb: The operation parameters + * @to: The buffer to read into * */ static ssize_t @@ -576,11 +569,9 @@ v9fs_mmap_file_read_iter(struct kiocb *iocb, struct iov_iter *to) } /** - * v9fs_mmap_file_write - write to a file - * @filp: file pointer to write - * @data: data buffer to write data from - * @count: size of buffer - * @offset: offset at which to write data + * v9fs_mmap_file_write_iter - write to a file + * @iocb: The operation parameters + * @from: The data to write * */ static ssize_t diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 795706520b5e..08f48b70a741 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -218,7 +218,7 @@ v9fs_blank_wstat(struct p9_wstat *wstat) /** * v9fs_alloc_inode - helper function to allocate an inode - * + * @sb: The superblock to allocate the inode from */ struct inode *v9fs_alloc_inode(struct super_block *sb) { @@ -238,7 +238,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb) /** * v9fs_free_inode - destroy an inode - * + * @inode: The inode to be freed */ void v9fs_free_inode(struct inode *inode) @@ -343,7 +343,7 @@ error: * v9fs_get_inode - helper function to setup an inode * @sb: superblock * @mode: mode to setup inode with - * + * @rdev: The device numbers to set */ struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev) @@ -369,7 +369,7 @@ struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev) } /** - * v9fs_clear_inode - release an inode + * v9fs_evict_inode - Remove an inode from the inode cache * @inode: inode to release * */ @@ -665,14 +665,15 @@ error: /** * v9fs_vfs_create - VFS hook to create a regular file + * @mnt_userns: The user namespace of the mount + * @dir: The parent directory + * @dentry: The name of file to be created + * @mode: The UNIX file mode to set + * @excl: True if the file must not yet exist * * open(.., O_CREAT) is handled in v9fs_vfs_atomic_open(). This is only called * for mknod(2). * - * @dir: directory inode that is being created - * @dentry: dentry that is being deleted - * @mode: create permissions - * */ static int @@ -696,6 +697,7 @@ v9fs_vfs_create(struct user_namespace *mnt_userns, struct inode *dir, /** * v9fs_vfs_mkdir - VFS mkdir hook to create a directory + * @mnt_userns: The user namespace of the mount * @dir: inode that is being unlinked * @dentry: dentry that is being unlinked * @mode: mode for new directory @@ -900,10 +902,12 @@ int v9fs_vfs_rmdir(struct inode *i, struct dentry *d) /** * v9fs_vfs_rename - VFS hook to rename an inode + * @mnt_userns: The user namespace of the mount * @old_dir: old dir inode * @old_dentry: old dentry * @new_dir: new dir inode * @new_dentry: new dentry + * @flags: RENAME_* flags * */ @@ -1009,6 +1013,7 @@ done: /** * v9fs_vfs_getattr - retrieve file metadata + * @mnt_userns: The user namespace of the mount * @path: Object to query * @stat: metadata structure to populate * @request_mask: Mask of STATX_xxx flags indicating the caller's interests @@ -1050,6 +1055,7 @@ v9fs_vfs_getattr(struct user_namespace *mnt_userns, const struct path *path, /** * v9fs_vfs_setattr - set file metadata + * @mnt_userns: The user namespace of the mount * @dentry: file whose metadata to set * @iattr: metadata assignment structure * @@ -1285,6 +1291,7 @@ static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry, /** * v9fs_vfs_symlink - helper function to create symlinks + * @mnt_userns: The user namespace of the mount * @dir: directory inode containing symlink * @dentry: dentry for symlink * @symname: symlink data @@ -1340,6 +1347,7 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir, /** * v9fs_vfs_mknod - create a special file + * @mnt_userns: The user namespace of the mount * @dir: inode destination for new link * @dentry: dentry for file * @mode: mode for creation diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index e1c0240b51c0..01b9e1281a29 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -37,7 +37,10 @@ v9fs_vfs_mknod_dotl(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, umode_t omode, dev_t rdev); /** - * v9fs_get_fsgid_for_create - Helper function to get the gid for creating a + * v9fs_get_fsgid_for_create - Helper function to get the gid for a new object + * @dir_inode: The directory inode + * + * Helper function to get the gid for creating a * new file system object. This checks the S_ISGID to determine the owning * group of the new file system object. */ @@ -211,12 +214,13 @@ int v9fs_open_to_dotl_flags(int flags) /** * v9fs_vfs_create_dotl - VFS hook to create files for 9P2000.L protocol. + * @mnt_userns: The user namespace of the mount * @dir: directory inode that is being created * @dentry: dentry that is being deleted * @omode: create permissions + * @excl: True if the file must not yet exist * */ - static int v9fs_vfs_create_dotl(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, umode_t omode, bool excl) @@ -361,6 +365,7 @@ err_clunk_old_fid: /** * v9fs_vfs_mkdir_dotl - VFS mkdir hook to create a directory + * @mnt_userns: The user namespace of the mount * @dir: inode that is being unlinked * @dentry: dentry that is being unlinked * @omode: mode for new directory @@ -537,6 +542,7 @@ static int v9fs_mapped_iattr_valid(int iattr_valid) /** * v9fs_vfs_setattr_dotl - set file metadata + * @mnt_userns: The user namespace of the mount * @dentry: file whose metadata to set * @iattr: metadata assignment structure * @@ -816,6 +822,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, /** * v9fs_vfs_mknod_dotl - create a special file + * @mnt_userns: The user namespace of the mount * @dir: inode destination for new link * @dentry: dentry for file * @omode: mode for creation diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c index dae9a57d7ec0..45cfd50a9521 100644 --- a/fs/afs/dir_silly.c +++ b/fs/afs/dir_silly.c @@ -86,8 +86,8 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode return afs_do_sync_operation(op); } -/** - * afs_sillyrename - Perform a silly-rename of a dentry +/* + * Perform silly-rename of a dentry. * * AFS is stateless and the server doesn't know when the client is holding a * file open. To prevent application problems when a file is unlinked while diff --git a/fs/afs/write.c b/fs/afs/write.c index 2dfe3b3a53d6..f24370f5c774 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -974,8 +974,7 @@ int afs_launder_page(struct page *page) iov_iter_bvec(&iter, WRITE, bv, 1, bv[0].bv_len); trace_afs_page_dirty(vnode, tracepoint_string("launder"), page); - ret = afs_store_data(vnode, &iter, (loff_t)page->index * PAGE_SIZE, - true); + ret = afs_store_data(vnode, &iter, page_offset(page) + f, true); } trace_afs_page_dirty(vnode, tracepoint_string("laundered"), page); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 69d900a8473d..a813b70f594e 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -630,7 +630,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, vaddr = eppnt->p_vaddr; if (interp_elf_ex->e_type == ET_EXEC || load_addr_set) - elf_type |= MAP_FIXED_NOREPLACE; + elf_type |= MAP_FIXED; else if (no_base && interp_elf_ex->e_type == ET_DYN) load_addr = -vaddr; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index dff2c8a3e059..c0cebcf745ce 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3030,7 +3030,7 @@ struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 objectid, const char *name, int name_len, + u64 index, const char *name, int name_len, int mod); struct btrfs_dir_item * btrfs_search_dir_index_item(struct btrfs_root *root, diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index f1274d5c3805..7721ce0c0604 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -190,9 +190,20 @@ static struct btrfs_dir_item *btrfs_lookup_match_dir( } /* - * lookup a directory item based on name. 'dir' is the objectid - * we're searching in, and 'mod' tells us if you plan on deleting the - * item (use mod < 0) or changing the options (use mod > 0) + * Lookup for a directory item by name. + * + * @trans: The transaction handle to use. Can be NULL if @mod is 0. + * @root: The root of the target tree. + * @path: Path to use for the search. + * @dir: The inode number (objectid) of the directory. + * @name: The name associated to the directory entry we are looking for. + * @name_len: The length of the name. + * @mod: Used to indicate if the tree search is meant for a read only + * lookup, for a modification lookup or for a deletion lookup, so + * its value should be 0, 1 or -1, respectively. + * + * Returns: NULL if the dir item does not exists, an error pointer if an error + * happened, or a pointer to a dir item if a dir item exists for the given name. */ struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -273,27 +284,42 @@ out: } /* - * lookup a directory item based on index. 'dir' is the objectid - * we're searching in, and 'mod' tells us if you plan on deleting the - * item (use mod < 0) or changing the options (use mod > 0) + * Lookup for a directory index item by name and index number. * - * The name is used to make sure the index really points to the name you were - * looking for. + * @trans: The transaction handle to use. Can be NULL if @mod is 0. + * @root: The root of the target tree. + * @path: Path to use for the search. + * @dir: The inode number (objectid) of the directory. + * @index: The index number. + * @name: The name associated to the directory entry we are looking for. + * @name_len: The length of the name. + * @mod: Used to indicate if the tree search is meant for a read only + * lookup, for a modification lookup or for a deletion lookup, so + * its value should be 0, 1 or -1, respectively. + * + * Returns: NULL if the dir index item does not exists, an error pointer if an + * error happened, or a pointer to a dir item if the dir index item exists and + * matches the criteria (name and index number). */ struct btrfs_dir_item * btrfs_lookup_dir_index_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 dir, - u64 objectid, const char *name, int name_len, + u64 index, const char *name, int name_len, int mod) { + struct btrfs_dir_item *di; struct btrfs_key key; key.objectid = dir; key.type = BTRFS_DIR_INDEX_KEY; - key.offset = objectid; + key.offset = index; - return btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + di = btrfs_lookup_match_dir(trans, root, path, &key, name, name_len, mod); + if (di == ERR_PTR(-ENOENT)) + return NULL; + + return di; } struct btrfs_dir_item * diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index fc3da7585fb7..0ab456cb4bf8 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4859,6 +4859,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, out_free_delayed: btrfs_free_delayed_extent_op(extent_op); out_free_buf: + btrfs_tree_unlock(buf); free_extent_buffer(buf); out_free_reserved: btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 0); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 7ff577005d0f..a1762363f61f 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -734,8 +734,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, if (args->start >= inode->disk_i_size && !args->replace_extent) modify_tree = 0; - update_refs = (test_bit(BTRFS_ROOT_SHAREABLE, &root->state) || - root == fs_info->tree_root); + update_refs = (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID); while (1) { recow = 0; ret = btrfs_lookup_file_extent(trans, root, path, ino, @@ -2704,14 +2703,16 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode, drop_args.bytes_found); if (ret != -ENOSPC) { /* - * When cloning we want to avoid transaction aborts when - * nothing was done and we are attempting to clone parts - * of inline extents, in such cases -EOPNOTSUPP is - * returned by __btrfs_drop_extents() without having - * changed anything in the file. + * The only time we don't want to abort is if we are + * attempting to clone a partial inline extent, in which + * case we'll get EOPNOTSUPP. However if we aren't + * clone we need to abort no matter what, because if we + * got EOPNOTSUPP via prealloc then we messed up and + * need to abort. */ - if (extent_info && !extent_info->is_new_extent && - ret && ret != -EOPNOTSUPP) + if (ret && + (ret != -EOPNOTSUPP || + (extent_info && extent_info->is_new_extent))) btrfs_abort_transaction(trans, ret); break; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index f7efc26aa82a..b415c5ec03ea 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -939,9 +939,11 @@ out: } /* - * helper function to see if a given name and sequence number found - * in an inode back reference are already in a directory and correctly - * point to this inode + * See if a given name and sequence number found in an inode back reference are + * already in a directory and correctly point to this inode. + * + * Returns: < 0 on error, 0 if the directory entry does not exists and 1 if it + * exists. */ static noinline int inode_in_dir(struct btrfs_root *root, struct btrfs_path *path, @@ -950,29 +952,34 @@ static noinline int inode_in_dir(struct btrfs_root *root, { struct btrfs_dir_item *di; struct btrfs_key location; - int match = 0; + int ret = 0; di = btrfs_lookup_dir_index_item(NULL, root, path, dirid, index, name, name_len, 0); - if (di && !IS_ERR(di)) { + if (IS_ERR(di)) { + ret = PTR_ERR(di); + goto out; + } else if (di) { btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); if (location.objectid != objectid) goto out; - } else + } else { goto out; - btrfs_release_path(path); + } + btrfs_release_path(path); di = btrfs_lookup_dir_item(NULL, root, path, dirid, name, name_len, 0); - if (di && !IS_ERR(di)) { - btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); - if (location.objectid != objectid) - goto out; - } else + if (IS_ERR(di)) { + ret = PTR_ERR(di); goto out; - match = 1; + } else if (di) { + btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location); + if (location.objectid == objectid) + ret = 1; + } out: btrfs_release_path(path); - return match; + return ret; } /* @@ -1182,7 +1189,9 @@ next: /* look for a conflicting sequence number */ di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir), ref_index, name, namelen, 0); - if (di && !IS_ERR(di)) { + if (IS_ERR(di)) { + return PTR_ERR(di); + } else if (di) { ret = drop_one_dir_item(trans, root, path, dir, di); if (ret) return ret; @@ -1192,7 +1201,9 @@ next: /* look for a conflicting name */ di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir), name, namelen, 0); - if (di && !IS_ERR(di)) { + if (IS_ERR(di)) { + return PTR_ERR(di); + } else if (di) { ret = drop_one_dir_item(trans, root, path, dir, di); if (ret) return ret; @@ -1517,10 +1528,12 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, if (ret) goto out; - /* if we already have a perfect match, we're done */ - if (!inode_in_dir(root, path, btrfs_ino(BTRFS_I(dir)), - btrfs_ino(BTRFS_I(inode)), ref_index, - name, namelen)) { + ret = inode_in_dir(root, path, btrfs_ino(BTRFS_I(dir)), + btrfs_ino(BTRFS_I(inode)), ref_index, + name, namelen); + if (ret < 0) { + goto out; + } else if (ret == 0) { /* * look for a conflicting back reference in the * metadata. if we find one we have to unlink that name @@ -1580,6 +1593,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, if (ret) goto out; } + /* Else, ret == 1, we already have a perfect match, we're done. */ ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + namelen; kfree(name); @@ -1936,8 +1950,8 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, struct btrfs_key log_key; struct inode *dir; u8 log_type; - int exists; - int ret = 0; + bool exists; + int ret; bool update_size = (key->type == BTRFS_DIR_INDEX_KEY); bool name_added = false; @@ -1957,12 +1971,12 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, name_len); btrfs_dir_item_key_to_cpu(eb, di, &log_key); - exists = btrfs_lookup_inode(trans, root, path, &log_key, 0); - if (exists == 0) - exists = 1; - else - exists = 0; + ret = btrfs_lookup_inode(trans, root, path, &log_key, 0); btrfs_release_path(path); + if (ret < 0) + goto out; + exists = (ret == 0); + ret = 0; if (key->type == BTRFS_DIR_ITEM_KEY) { dst_di = btrfs_lookup_dir_item(trans, root, path, key->objectid, @@ -1977,7 +1991,11 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, ret = -EINVAL; goto out; } - if (IS_ERR_OR_NULL(dst_di)) { + + if (IS_ERR(dst_di)) { + ret = PTR_ERR(dst_di); + goto out; + } else if (!dst_di) { /* we need a sequence number to insert, so we only * do inserts for the BTRFS_DIR_INDEX_KEY types */ @@ -2281,7 +2299,7 @@ again: dir_key->offset, name, name_len, 0); } - if (!log_di || log_di == ERR_PTR(-ENOENT)) { + if (!log_di) { btrfs_dir_item_key_to_cpu(eb, di, &location); btrfs_release_path(path); btrfs_release_path(log_path); @@ -3540,8 +3558,7 @@ out_unlock: if (err == -ENOSPC) { btrfs_set_log_full_commit(trans); err = 0; - } else if (err < 0 && err != -ENOENT) { - /* ENOENT can be returned if the entry hasn't been fsynced yet */ + } else if (err < 0) { btrfs_abort_transaction(trans, err); } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 8129a430d789..2f117c57160d 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -528,7 +528,7 @@ void debugfs_create_file_size(const char *name, umode_t mode, { struct dentry *de = debugfs_create_file(name, mode, parent, data, fops); - if (de) + if (!IS_ERR(de)) d_inode(de)->i_size = file_size; } EXPORT_SYMBOL_GPL(debugfs_create_file_size); diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index ffb295aa891c..74b172a4adda 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -551,7 +551,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) struct dir_private_info *info = file->private_data; struct inode *inode = file_inode(file); struct fname *fname; - int ret; + int ret = 0; if (!info) { info = ext4_htree_create_dir_info(file, ctx->pos); @@ -599,7 +599,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) info->curr_minor_hash, &info->next_hash); if (ret < 0) - return ret; + goto finished; if (ret == 0) { ctx->pos = ext4_get_htree_eof(file); break; @@ -630,7 +630,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx) } finished: info->last_pos = ctx->pos; - return 0; + return ret < 0 ? ret : 0; } static int ext4_release_dir(struct inode *inode, struct file *filp) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 90ff5acaf11f..3825195539d7 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3593,9 +3593,6 @@ extern int ext4_da_write_inline_data_begin(struct address_space *mapping, unsigned flags, struct page **pagep, void **fsdata); -extern int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, - unsigned len, unsigned copied, - struct page *page); extern int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c0de30f25185..0e02571f2f82 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5916,7 +5916,7 @@ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) } /* Check if *cur is a hole and if it is, skip it */ -static void skip_hole(struct inode *inode, ext4_lblk_t *cur) +static int skip_hole(struct inode *inode, ext4_lblk_t *cur) { int ret; struct ext4_map_blocks map; @@ -5925,9 +5925,12 @@ static void skip_hole(struct inode *inode, ext4_lblk_t *cur) map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur; ret = ext4_map_blocks(NULL, inode, &map, 0); + if (ret < 0) + return ret; if (ret != 0) - return; + return 0; *cur = *cur + map.m_len; + return 0; } /* Count number of blocks used by this inode and update i_blocks */ @@ -5976,7 +5979,9 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) * iblocks by total number of differences found. */ cur = 0; - skip_hole(inode, &cur); + ret = skip_hole(inode, &cur); + if (ret < 0) + goto out; path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) goto out; @@ -5995,8 +6000,12 @@ int ext4_ext_replay_set_iblocks(struct inode *inode) } cur = max(cur + 1, le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)); - skip_hole(inode, &cur); - + ret = skip_hole(inode, &cur); + if (ret < 0) { + ext4_ext_drop_refs(path); + kfree(path); + break; + } path2 = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path2)) { ext4_ext_drop_refs(path); diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 8e610a381862..8ea5a81e6554 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -892,6 +892,12 @@ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc) sizeof(lrange), (u8 *)&lrange, crc)) return -ENOSPC; } else { + unsigned int max = (map.m_flags & EXT4_MAP_UNWRITTEN) ? + EXT_UNWRITTEN_MAX_LEN : EXT_INIT_MAX_LEN; + + /* Limit the number of blocks in one extent */ + map.m_len = min(max, map.m_len); + fc_ext.fc_ino = cpu_to_le32(inode->i_ino); ex = (struct ext4_extent *)&fc_ext.fc_ex; ex->ee_block = cpu_to_le32(map.m_lblk); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 82bf4ff6be28..39a1ab129fdc 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -7,6 +7,7 @@ #include <linux/iomap.h> #include <linux/fiemap.h> #include <linux/iversion.h> +#include <linux/backing-dev.h> #include "ext4_jbd2.h" #include "ext4.h" @@ -733,45 +734,83 @@ convert: int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page) { - int ret, no_expand; + handle_t *handle = ext4_journal_current_handle(); + int no_expand; void *kaddr; struct ext4_iloc iloc; + int ret = 0, ret2; + + if (unlikely(copied < len) && !PageUptodate(page)) + copied = 0; - if (unlikely(copied < len)) { - if (!PageUptodate(page)) { - copied = 0; + if (likely(copied)) { + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) { + unlock_page(page); + put_page(page); + ext4_std_error(inode->i_sb, ret); goto out; } - } + ext4_write_lock_xattr(inode, &no_expand); + BUG_ON(!ext4_has_inline_data(inode)); - ret = ext4_get_inode_loc(inode, &iloc); - if (ret) { - ext4_std_error(inode->i_sb, ret); - copied = 0; - goto out; - } + /* + * ei->i_inline_off may have changed since + * ext4_write_begin() called + * ext4_try_to_write_inline_data() + */ + (void) ext4_find_inline_data_nolock(inode); - ext4_write_lock_xattr(inode, &no_expand); - BUG_ON(!ext4_has_inline_data(inode)); + kaddr = kmap_atomic(page); + ext4_write_inline_data(inode, &iloc, kaddr, pos, copied); + kunmap_atomic(kaddr); + SetPageUptodate(page); + /* clear page dirty so that writepages wouldn't work for us. */ + ClearPageDirty(page); - /* - * ei->i_inline_off may have changed since ext4_write_begin() - * called ext4_try_to_write_inline_data() - */ - (void) ext4_find_inline_data_nolock(inode); + ext4_write_unlock_xattr(inode, &no_expand); + brelse(iloc.bh); - kaddr = kmap_atomic(page); - ext4_write_inline_data(inode, &iloc, kaddr, pos, len); - kunmap_atomic(kaddr); - SetPageUptodate(page); - /* clear page dirty so that writepages wouldn't work for us. */ - ClearPageDirty(page); + /* + * It's important to update i_size while still holding page + * lock: page writeout could otherwise come in and zero + * beyond i_size. + */ + ext4_update_inode_size(inode, pos + copied); + } + unlock_page(page); + put_page(page); - ext4_write_unlock_xattr(inode, &no_expand); - brelse(iloc.bh); - mark_inode_dirty(inode); + /* + * Don't mark the inode dirty under page lock. First, it unnecessarily + * makes the holding time of page lock longer. Second, it forces lock + * ordering of page lock and transaction start for journaling + * filesystems. + */ + if (likely(copied)) + mark_inode_dirty(inode); out: - return copied; + /* + * If we didn't copy as much data as expected, we need to trim back + * size of xattr containing inline data. + */ + if (pos + len > inode->i_size && ext4_can_truncate(inode)) + ext4_orphan_add(handle, inode); + + ret2 = ext4_journal_stop(handle); + if (!ret) + ret = ret2; + if (pos + len > inode->i_size) { + ext4_truncate_failed_write(inode); + /* + * If truncate failed early the inode might still be + * on the orphan list; we need to make sure the inode + * is removed from the orphan list in that case. + */ + if (inode->i_nlink) + ext4_orphan_del(NULL, inode); + } + return ret ? ret : copied; } struct buffer_head * @@ -953,43 +992,6 @@ out: return ret; } -int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, - unsigned len, unsigned copied, - struct page *page) -{ - int ret; - - ret = ext4_write_inline_data_end(inode, pos, len, copied, page); - if (ret < 0) { - unlock_page(page); - put_page(page); - return ret; - } - copied = ret; - - /* - * No need to use i_size_read() here, the i_size - * cannot change under us because we hold i_mutex. - * - * But it's important to update i_size while still holding page lock: - * page writeout could otherwise come in and zero beyond i_size. - */ - if (pos+copied > inode->i_size) - i_size_write(inode, pos+copied); - unlock_page(page); - put_page(page); - - /* - * Don't mark the inode dirty under page lock. First, it unnecessarily - * makes the holding time of page lock longer. Second, it forces lock - * ordering of page lock and transaction start for journaling - * filesystems. - */ - mark_inode_dirty(inode); - - return copied; -} - #ifdef INLINE_DIR_DEBUG void ext4_show_inline_dir(struct inode *dir, struct buffer_head *bh, void *inline_start, int inline_size) @@ -1917,6 +1919,24 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) EXT4_I(inode)->i_disksize = i_size; if (i_size < inline_size) { + /* + * if there's inline data to truncate and this file was + * converted to extents after that inline data was written, + * the extent status cache must be cleared to avoid leaving + * behind stale delayed allocated extent entries + */ + if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { +retry: + err = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); + if (err == -ENOMEM) { + cond_resched(); + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; + } + if (err) + goto out_error; + } + /* Clear the content in the xattr space. */ if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) { if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d18852d6029c..0f06305167d5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1284,22 +1284,14 @@ static int ext4_write_end(struct file *file, loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; - int inline_data = ext4_has_inline_data(inode); bool verity = ext4_verity_in_progress(inode); trace_ext4_write_end(inode, pos, len, copied); - if (inline_data) { - ret = ext4_write_inline_data_end(inode, pos, len, - copied, page); - if (ret < 0) { - unlock_page(page); - put_page(page); - goto errout; - } - copied = ret; - } else - copied = block_write_end(file, mapping, pos, - len, copied, page, fsdata); + + if (ext4_has_inline_data(inode)) + return ext4_write_inline_data_end(inode, pos, len, copied, page); + + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); /* * it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. @@ -1320,7 +1312,7 @@ static int ext4_write_end(struct file *file, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed || inline_data) + if (i_size_changed) ret = ext4_mark_inode_dirty(handle, inode); if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) @@ -1329,7 +1321,7 @@ static int ext4_write_end(struct file *file, * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); -errout: + ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; @@ -1395,7 +1387,6 @@ static int ext4_journalled_write_end(struct file *file, int partial = 0; unsigned from, to; int size_changed = 0; - int inline_data = ext4_has_inline_data(inode); bool verity = ext4_verity_in_progress(inode); trace_ext4_journalled_write_end(inode, pos, len, copied); @@ -1404,16 +1395,10 @@ static int ext4_journalled_write_end(struct file *file, BUG_ON(!ext4_handle_valid(handle)); - if (inline_data) { - ret = ext4_write_inline_data_end(inode, pos, len, - copied, page); - if (ret < 0) { - unlock_page(page); - put_page(page); - goto errout; - } - copied = ret; - } else if (unlikely(copied < len) && !PageUptodate(page)) { + if (ext4_has_inline_data(inode)) + return ext4_write_inline_data_end(inode, pos, len, copied, page); + + if (unlikely(copied < len) && !PageUptodate(page)) { copied = 0; ext4_journalled_zero_new_buffers(handle, inode, page, from, to); } else { @@ -1436,7 +1421,7 @@ static int ext4_journalled_write_end(struct file *file, if (old_size < pos && !verity) pagecache_isize_extended(inode, old_size, pos); - if (size_changed || inline_data) { + if (size_changed) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; @@ -1449,7 +1434,6 @@ static int ext4_journalled_write_end(struct file *file, */ ext4_orphan_add(handle, inode); -errout: ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; @@ -1644,6 +1628,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int ret; bool allocated = false; + bool reserved = false; /* * If the cluster containing lblk is shared with a delayed, @@ -1660,6 +1645,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) ret = ext4_da_reserve_space(inode); if (ret != 0) /* ENOSPC */ goto errout; + reserved = true; } else { /* bigalloc */ if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) { if (!ext4_es_scan_clu(inode, @@ -1672,6 +1658,7 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) ret = ext4_da_reserve_space(inode); if (ret != 0) /* ENOSPC */ goto errout; + reserved = true; } else { allocated = true; } @@ -1682,6 +1669,8 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk) } ret = ext4_es_insert_delayed_block(inode, lblk, allocated); + if (ret && reserved) + ext4_da_release_space(inode, 1); errout: return ret; @@ -1722,13 +1711,16 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, } /* - * Delayed extent could be allocated by fallocate. - * So we need to check it. + * the buffer head associated with a delayed and not unwritten + * block found in the extent status cache must contain an + * invalid block number and have its BH_New and BH_Delay bits + * set, reflecting the state assigned when the block was + * initially delayed allocated */ - if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) { - map_bh(bh, inode->i_sb, invalid_block); - set_buffer_new(bh); - set_buffer_delay(bh); + if (ext4_es_is_delonly(&es)) { + BUG_ON(bh->b_blocknr != invalid_block); + BUG_ON(!buffer_new(bh)); + BUG_ON(!buffer_delay(bh)); return 0; } @@ -2932,19 +2924,6 @@ static int ext4_nonda_switch(struct super_block *sb) return 0; } -/* We always reserve for an inode update; the superblock could be there too */ -static int ext4_da_write_credits(struct inode *inode, loff_t pos, unsigned len) -{ - if (likely(ext4_has_feature_large_file(inode->i_sb))) - return 1; - - if (pos + len <= 0x7fffffffULL) - return 1; - - /* We might need to update the superblock to set LARGE_FILE */ - return 2; -} - static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -2953,7 +2932,6 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, struct page *page; pgoff_t index; struct inode *inode = mapping->host; - handle_t *handle; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; @@ -2979,41 +2957,11 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, return 0; } - /* - * grab_cache_page_write_begin() can take a long time if the - * system is thrashing due to memory pressure, or if the page - * is being written back. So grab it first before we start - * the transaction handle. This also allows us to allocate - * the page (if needed) without using GFP_NOFS. - */ -retry_grab: +retry: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; - unlock_page(page); - /* - * With delayed allocation, we don't log the i_disksize update - * if there is delayed block allocation. But we still need - * to journalling the i_disksize update if writes to the end - * of file which has an already mapped buffer. - */ -retry_journal: - handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, - ext4_da_write_credits(inode, pos, len)); - if (IS_ERR(handle)) { - put_page(page); - return PTR_ERR(handle); - } - - lock_page(page); - if (page->mapping != mapping) { - /* The page got truncated from under us */ - unlock_page(page); - put_page(page); - ext4_journal_stop(handle); - goto retry_grab; - } /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); @@ -3025,20 +2973,18 @@ retry_journal: #endif if (ret < 0) { unlock_page(page); - ext4_journal_stop(handle); + put_page(page); /* * block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need - * i_size_read because we hold i_mutex. + * i_size_read because we hold inode lock. */ if (pos + len > inode->i_size) ext4_truncate_failed_write(inode); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) - goto retry_journal; - - put_page(page); + goto retry; return ret; } @@ -3075,8 +3021,6 @@ static int ext4_da_write_end(struct file *file, struct page *page, void *fsdata) { struct inode *inode = mapping->host; - int ret = 0, ret2; - handle_t *handle = ext4_journal_current_handle(); loff_t new_i_size; unsigned long start, end; int write_mode = (int)(unsigned long)fsdata; @@ -3086,44 +3030,36 @@ static int ext4_da_write_end(struct file *file, len, copied, page, fsdata); trace_ext4_da_write_end(inode, pos, len, copied); + + if (write_mode != CONVERT_INLINE_DATA && + ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && + ext4_has_inline_data(inode)) + return ext4_write_inline_data_end(inode, pos, len, copied, page); + start = pos & (PAGE_SIZE - 1); end = start + copied - 1; /* - * generic_write_end() will run mark_inode_dirty() if i_size - * changes. So let's piggyback the i_disksize mark_inode_dirty - * into that. + * Since we are holding inode lock, we are sure i_disksize <= + * i_size. We also know that if i_disksize < i_size, there are + * delalloc writes pending in the range upto i_size. If the end of + * the current write is <= i_size, there's no need to touch + * i_disksize since writeback will push i_disksize upto i_size + * eventually. If the end of the current write is > i_size and + * inside an allocated block (ext4_da_should_update_i_disksize() + * check), we need to update i_disksize here as neither + * ext4_writepage() nor certain ext4_writepages() paths not + * allocating blocks update i_disksize. + * + * Note that we defer inode dirtying to generic_write_end() / + * ext4_da_write_inline_data_end(). */ new_i_size = pos + copied; - if (copied && new_i_size > EXT4_I(inode)->i_disksize) { - if (ext4_has_inline_data(inode) || - ext4_da_should_update_i_disksize(page, end)) { - ext4_update_i_disksize(inode, new_i_size); - /* We need to mark inode dirty even if - * new_i_size is less that inode->i_size - * bu greater than i_disksize.(hint delalloc) - */ - ret = ext4_mark_inode_dirty(handle, inode); - } - } + if (copied && new_i_size > inode->i_size && + ext4_da_should_update_i_disksize(page, end)) + ext4_update_i_disksize(inode, new_i_size); - if (write_mode != CONVERT_INLINE_DATA && - ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && - ext4_has_inline_data(inode)) - ret2 = ext4_da_write_inline_data_end(inode, pos, len, copied, - page); - else - ret2 = generic_write_end(file, mapping, pos, len, copied, - page, fsdata); - - copied = ret2; - if (ret2 < 0) - ret = ret2; - ret2 = ext4_journal_stop(handle); - if (unlikely(ret2 && !ret)) - ret = ret2; - - return ret ? ret : copied; + return generic_write_end(file, mapping, pos, len, copied, page, fsdata); } /* @@ -4340,6 +4276,12 @@ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino, goto has_buffer; lock_buffer(bh); + if (ext4_buffer_uptodate(bh)) { + /* Someone brought it uptodate while we waited */ + unlock_buffer(bh); + goto has_buffer; + } + /* * If we have all information of the inode in memory and this * is the only valid inode in the block, we need not read the diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0775950ee84e..88d5d274a868 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -658,7 +658,7 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, * constraints, it may not be safe to do it right here so we * defer superblock flushing to a workqueue. */ - if (continue_fs) + if (continue_fs && journal) schedule_work(&EXT4_SB(sb)->s_error_work); else ext4_commit_super(sb); @@ -1350,6 +1350,12 @@ static void ext4_destroy_inode(struct inode *inode) true); dump_stack(); } + + if (EXT4_I(inode)->i_reserved_data_blocks) + ext4_msg(inode->i_sb, KERN_ERR, + "Inode %lu (%p): i_reserved_data_blocks (%u) not cleared!", + inode->i_ino, EXT4_I(inode), + EXT4_I(inode)->i_reserved_data_blocks); } static void init_once(void *foo) @@ -3021,17 +3027,17 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files) */ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) { - loff_t res = EXT4_NDIR_BLOCKS; + unsigned long long upper_limit, res = EXT4_NDIR_BLOCKS; int meta_blocks; - loff_t upper_limit; - /* This is calculated to be the largest file size for a dense, block + + /* + * This is calculated to be the largest file size for a dense, block * mapped file such that the file's total number of 512-byte sectors, * including data and all indirect blocks, does not exceed (2^48 - 1). * * __u32 i_blocks_lo and _u16 i_blocks_high represent the total * number of 512-byte sectors of the file. */ - if (!has_huge_files) { /* * !has_huge_files or implies that the inode i_block field @@ -3074,7 +3080,7 @@ static loff_t ext4_max_bitmap_size(int bits, int has_huge_files) if (res > MAX_LFS_FILESIZE) res = MAX_LFS_FILESIZE; - return res; + return (loff_t)res; } static ext4_fsblk_t descriptor_loc(struct super_block *sb, @@ -5042,12 +5048,15 @@ failed_mount_wq: sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { + /* flush s_error_work before journal destroy. */ + flush_work(&sbi->s_error_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: + /* flush s_error_work before sbi destroy */ flush_work(&sbi->s_error_work); del_timer_sync(&sbi->s_err_report); ext4_stop_mmpd(sbi); diff --git a/fs/fscache/object.c b/fs/fscache/object.c index f346a78f4bd6..6a675652129b 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -77,7 +77,6 @@ static WORK_STATE(INIT_OBJECT, "INIT", fscache_initialise_object); static WORK_STATE(PARENT_READY, "PRDY", fscache_parent_ready); static WORK_STATE(ABORT_INIT, "ABRT", fscache_abort_initialisation); static WORK_STATE(LOOK_UP_OBJECT, "LOOK", fscache_look_up_object); -static WORK_STATE(CREATE_OBJECT, "CRTO", fscache_look_up_object); static WORK_STATE(OBJECT_AVAILABLE, "AVBL", fscache_object_available); static WORK_STATE(JUMPSTART_DEPS, "JUMP", fscache_jumpstart_dependents); @@ -907,6 +906,7 @@ static void fscache_dequeue_object(struct fscache_object *object) * @object: The object to ask about * @data: The auxiliary data for the object * @datalen: The size of the auxiliary data + * @object_size: The size of the object according to the server. * * This function consults the netfs about the coherency state of an object. * The caller must be holding a ref on cookie->n_active (held by diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index 433877107700..e002cdfaf3cc 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -22,7 +22,10 @@ static void fscache_operation_dummy_cancel(struct fscache_operation *op) /** * fscache_operation_init - Do basic initialisation of an operation + * @cookie: The cookie to operate on * @op: The operation to initialise + * @processor: The function to perform the operation + * @cancel: A function to handle operation cancellation * @release: The release function to assign * * Do basic initialisation of an operation. The caller must still set flags, diff --git a/fs/io-wq.c b/fs/io-wq.c index c2360cdc403d..5bf8aa81715e 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -584,10 +584,7 @@ loop: if (!get_signal(&ksig)) continue; - if (fatal_signal_pending(current) || - signal_group_exit(current->signal)) - break; - continue; + break; } last_timeout = !ret; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 82f867983bb3..6b9e70208782 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -403,7 +403,6 @@ struct io_ring_ctx { struct wait_queue_head cq_wait; unsigned cq_extra; atomic_t cq_timeouts; - struct fasync_struct *cq_fasync; unsigned cq_last_tm_flush; } ____cacheline_aligned_in_smp; @@ -1614,10 +1613,8 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) wake_up(&ctx->sq_data->wait); if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); - if (waitqueue_active(&ctx->poll_wait)) { + if (waitqueue_active(&ctx->poll_wait)) wake_up_interruptible(&ctx->poll_wait); - kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); - } } static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) @@ -1631,10 +1628,8 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) } if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); - if (waitqueue_active(&ctx->poll_wait)) { + if (waitqueue_active(&ctx->poll_wait)) wake_up_interruptible(&ctx->poll_wait); - kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); - } } /* Returns true if there are no backlogged entries after the flush */ @@ -9345,13 +9340,6 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) return mask; } -static int io_uring_fasync(int fd, struct file *file, int on) -{ - struct io_ring_ctx *ctx = file->private_data; - - return fasync_helper(fd, file, on, &ctx->cq_fasync); -} - static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) { const struct cred *creds; @@ -10145,7 +10133,6 @@ static const struct file_operations io_uring_fops = { .mmap_capabilities = io_uring_nommu_mmap_capabilities, #endif .poll = io_uring_poll, - .fasync = io_uring_fasync, #ifdef CONFIG_PROC_FS .show_fdinfo = io_uring_show_fdinfo, #endif diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index ba581429bf7b..cfc3ce8b815a 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1116,8 +1116,13 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, if (!inode) inode = ERR_PTR(-ENOMEM); } - /* Needed only for negative dentry validation */ - if (!inode) + /* + * Needed for negative dentry validation. + * The negative dentry can be created in kernfs_iop_lookup() + * or transforms from positive dentry in dentry_unlink_inode() + * called from vfs_rmdir(). + */ + if (!IS_ERR(inode)) kernfs_set_rev(parent, dentry); up_read(&kernfs_rwsem); diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index de36f12070bf..71c989f1568d 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -68,125 +68,6 @@ void ksmbd_copy_gss_neg_header(void *buf) memcpy(buf, NEGOTIATE_GSS_HEADER, AUTH_GSS_LENGTH); } -static void -str_to_key(unsigned char *str, unsigned char *key) -{ - int i; - - key[0] = str[0] >> 1; - key[1] = ((str[0] & 0x01) << 6) | (str[1] >> 2); - key[2] = ((str[1] & 0x03) << 5) | (str[2] >> 3); - key[3] = ((str[2] & 0x07) << 4) | (str[3] >> 4); - key[4] = ((str[3] & 0x0F) << 3) | (str[4] >> 5); - key[5] = ((str[4] & 0x1F) << 2) | (str[5] >> 6); - key[6] = ((str[5] & 0x3F) << 1) | (str[6] >> 7); - key[7] = str[6] & 0x7F; - for (i = 0; i < 8; i++) - key[i] = (key[i] << 1); -} - -static int -smbhash(unsigned char *out, const unsigned char *in, unsigned char *key) -{ - unsigned char key2[8]; - struct des_ctx ctx; - - if (fips_enabled) { - ksmbd_debug(AUTH, "FIPS compliance enabled: DES not permitted\n"); - return -ENOENT; - } - - str_to_key(key, key2); - des_expand_key(&ctx, key2, DES_KEY_SIZE); - des_encrypt(&ctx, out, in); - memzero_explicit(&ctx, sizeof(ctx)); - return 0; -} - -static int ksmbd_enc_p24(unsigned char *p21, const unsigned char *c8, unsigned char *p24) -{ - int rc; - - rc = smbhash(p24, c8, p21); - if (rc) - return rc; - rc = smbhash(p24 + 8, c8, p21 + 7); - if (rc) - return rc; - return smbhash(p24 + 16, c8, p21 + 14); -} - -/* produce a md4 message digest from data of length n bytes */ -static int ksmbd_enc_md4(unsigned char *md4_hash, unsigned char *link_str, - int link_len) -{ - int rc; - struct ksmbd_crypto_ctx *ctx; - - ctx = ksmbd_crypto_ctx_find_md4(); - if (!ctx) { - ksmbd_debug(AUTH, "Crypto md4 allocation error\n"); - return -ENOMEM; - } - - rc = crypto_shash_init(CRYPTO_MD4(ctx)); - if (rc) { - ksmbd_debug(AUTH, "Could not init md4 shash\n"); - goto out; - } - - rc = crypto_shash_update(CRYPTO_MD4(ctx), link_str, link_len); - if (rc) { - ksmbd_debug(AUTH, "Could not update with link_str\n"); - goto out; - } - - rc = crypto_shash_final(CRYPTO_MD4(ctx), md4_hash); - if (rc) - ksmbd_debug(AUTH, "Could not generate md4 hash\n"); -out: - ksmbd_release_crypto_ctx(ctx); - return rc; -} - -static int ksmbd_enc_update_sess_key(unsigned char *md5_hash, char *nonce, - char *server_challenge, int len) -{ - int rc; - struct ksmbd_crypto_ctx *ctx; - - ctx = ksmbd_crypto_ctx_find_md5(); - if (!ctx) { - ksmbd_debug(AUTH, "Crypto md5 allocation error\n"); - return -ENOMEM; - } - - rc = crypto_shash_init(CRYPTO_MD5(ctx)); - if (rc) { - ksmbd_debug(AUTH, "Could not init md5 shash\n"); - goto out; - } - - rc = crypto_shash_update(CRYPTO_MD5(ctx), server_challenge, len); - if (rc) { - ksmbd_debug(AUTH, "Could not update with challenge\n"); - goto out; - } - - rc = crypto_shash_update(CRYPTO_MD5(ctx), nonce, len); - if (rc) { - ksmbd_debug(AUTH, "Could not update with nonce\n"); - goto out; - } - - rc = crypto_shash_final(CRYPTO_MD5(ctx), md5_hash); - if (rc) - ksmbd_debug(AUTH, "Could not generate md5 hash\n"); -out: - ksmbd_release_crypto_ctx(ctx); - return rc; -} - /** * ksmbd_gen_sess_key() - function to generate session key * @sess: session of connection @@ -325,43 +206,6 @@ out: } /** - * ksmbd_auth_ntlm() - NTLM authentication handler - * @sess: session of connection - * @pw_buf: NTLM challenge response - * @passkey: user password - * - * Return: 0 on success, error number on error - */ -int ksmbd_auth_ntlm(struct ksmbd_session *sess, char *pw_buf) -{ - int rc; - unsigned char p21[21]; - char key[CIFS_AUTH_RESP_SIZE]; - - memset(p21, '\0', 21); - memcpy(p21, user_passkey(sess->user), CIFS_NTHASH_SIZE); - rc = ksmbd_enc_p24(p21, sess->ntlmssp.cryptkey, key); - if (rc) { - pr_err("password processing failed\n"); - return rc; - } - - ksmbd_enc_md4(sess->sess_key, user_passkey(sess->user), - CIFS_SMB1_SESSKEY_SIZE); - memcpy(sess->sess_key + CIFS_SMB1_SESSKEY_SIZE, key, - CIFS_AUTH_RESP_SIZE); - sess->sequence_number = 1; - - if (strncmp(pw_buf, key, CIFS_AUTH_RESP_SIZE) != 0) { - ksmbd_debug(AUTH, "ntlmv1 authentication failed\n"); - return -EINVAL; - } - - ksmbd_debug(AUTH, "ntlmv1 authentication pass\n"); - return 0; -} - -/** * ksmbd_auth_ntlmv2() - NTLMv2 authentication handler * @sess: session of connection * @ntlmv2: NTLMv2 challenge response @@ -442,44 +286,6 @@ out: } /** - * __ksmbd_auth_ntlmv2() - NTLM2(extended security) authentication handler - * @sess: session of connection - * @client_nonce: client nonce from LM response. - * @ntlm_resp: ntlm response data from client. - * - * Return: 0 on success, error number on error - */ -static int __ksmbd_auth_ntlmv2(struct ksmbd_session *sess, char *client_nonce, - char *ntlm_resp) -{ - char sess_key[CIFS_SMB1_SESSKEY_SIZE] = {0}; - int rc; - unsigned char p21[21]; - char key[CIFS_AUTH_RESP_SIZE]; - - rc = ksmbd_enc_update_sess_key(sess_key, - client_nonce, - (char *)sess->ntlmssp.cryptkey, 8); - if (rc) { - pr_err("password processing failed\n"); - goto out; - } - - memset(p21, '\0', 21); - memcpy(p21, user_passkey(sess->user), CIFS_NTHASH_SIZE); - rc = ksmbd_enc_p24(p21, sess_key, key); - if (rc) { - pr_err("password processing failed\n"); - goto out; - } - - if (memcmp(ntlm_resp, key, CIFS_AUTH_RESP_SIZE) != 0) - rc = -EINVAL; -out: - return rc; -} - -/** * ksmbd_decode_ntlmssp_auth_blob() - helper function to construct * authenticate blob * @authblob: authenticate blob source pointer @@ -512,17 +318,6 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, nt_off = le32_to_cpu(authblob->NtChallengeResponse.BufferOffset); nt_len = le16_to_cpu(authblob->NtChallengeResponse.Length); - /* process NTLM authentication */ - if (nt_len == CIFS_AUTH_RESP_SIZE) { - if (le32_to_cpu(authblob->NegotiateFlags) & - NTLMSSP_NEGOTIATE_EXTENDED_SEC) - return __ksmbd_auth_ntlmv2(sess, (char *)authblob + - lm_off, (char *)authblob + nt_off); - else - return ksmbd_auth_ntlm(sess, (char *)authblob + - nt_off); - } - /* TODO : use domain name that imported from configuration file */ domain_name = smb_strndup_from_utf16((const char *)authblob + le32_to_cpu(authblob->DomainName.BufferOffset), diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index af086d35398a..48b18b4ec117 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -296,10 +296,12 @@ int ksmbd_conn_handler_loop(void *p) pdu_size = get_rfc1002_len(hdr_buf); ksmbd_debug(CONN, "RFC1002 header %u bytes\n", pdu_size); - /* make sure we have enough to get to SMB header end */ - if (!ksmbd_pdu_size_has_room(pdu_size)) { - ksmbd_debug(CONN, "SMB request too short (%u bytes)\n", - pdu_size); + /* + * Check if pdu size is valid (min : smb header size, + * max : 0x00FFFFFF). + */ + if (pdu_size < __SMB2_HEADER_STRUCTURE_SIZE || + pdu_size > MAX_STREAM_PROT_LEN) { continue; } diff --git a/fs/ksmbd/crypto_ctx.c b/fs/ksmbd/crypto_ctx.c index 5f4b1008d17e..81488d04199d 100644 --- a/fs/ksmbd/crypto_ctx.c +++ b/fs/ksmbd/crypto_ctx.c @@ -81,12 +81,6 @@ static struct shash_desc *alloc_shash_desc(int id) case CRYPTO_SHASH_SHA512: tfm = crypto_alloc_shash("sha512", 0, 0); break; - case CRYPTO_SHASH_MD4: - tfm = crypto_alloc_shash("md4", 0, 0); - break; - case CRYPTO_SHASH_MD5: - tfm = crypto_alloc_shash("md5", 0, 0); - break; default: return NULL; } @@ -214,16 +208,6 @@ struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha512(void) return ____crypto_shash_ctx_find(CRYPTO_SHASH_SHA512); } -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md4(void) -{ - return ____crypto_shash_ctx_find(CRYPTO_SHASH_MD4); -} - -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md5(void) -{ - return ____crypto_shash_ctx_find(CRYPTO_SHASH_MD5); -} - static struct ksmbd_crypto_ctx *____crypto_aead_ctx_find(int id) { struct ksmbd_crypto_ctx *ctx; diff --git a/fs/ksmbd/crypto_ctx.h b/fs/ksmbd/crypto_ctx.h index ef11154b43df..4a367c62f653 100644 --- a/fs/ksmbd/crypto_ctx.h +++ b/fs/ksmbd/crypto_ctx.h @@ -15,8 +15,6 @@ enum { CRYPTO_SHASH_CMACAES, CRYPTO_SHASH_SHA256, CRYPTO_SHASH_SHA512, - CRYPTO_SHASH_MD4, - CRYPTO_SHASH_MD5, CRYPTO_SHASH_MAX, }; @@ -43,8 +41,6 @@ struct ksmbd_crypto_ctx { #define CRYPTO_CMACAES(c) ((c)->desc[CRYPTO_SHASH_CMACAES]) #define CRYPTO_SHA256(c) ((c)->desc[CRYPTO_SHASH_SHA256]) #define CRYPTO_SHA512(c) ((c)->desc[CRYPTO_SHASH_SHA512]) -#define CRYPTO_MD4(c) ((c)->desc[CRYPTO_SHASH_MD4]) -#define CRYPTO_MD5(c) ((c)->desc[CRYPTO_SHASH_MD5]) #define CRYPTO_HMACMD5_TFM(c) ((c)->desc[CRYPTO_SHASH_HMACMD5]->tfm) #define CRYPTO_HMACSHA256_TFM(c)\ @@ -52,8 +48,6 @@ struct ksmbd_crypto_ctx { #define CRYPTO_CMACAES_TFM(c) ((c)->desc[CRYPTO_SHASH_CMACAES]->tfm) #define CRYPTO_SHA256_TFM(c) ((c)->desc[CRYPTO_SHASH_SHA256]->tfm) #define CRYPTO_SHA512_TFM(c) ((c)->desc[CRYPTO_SHASH_SHA512]->tfm) -#define CRYPTO_MD4_TFM(c) ((c)->desc[CRYPTO_SHASH_MD4]->tfm) -#define CRYPTO_MD5_TFM(c) ((c)->desc[CRYPTO_SHASH_MD5]->tfm) #define CRYPTO_GCM(c) ((c)->ccmaes[CRYPTO_AEAD_AES_GCM]) #define CRYPTO_CCM(c) ((c)->ccmaes[CRYPTO_AEAD_AES_CCM]) @@ -64,8 +58,6 @@ struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_hmacsha256(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_cmacaes(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha512(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_sha256(void); -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md4(void); -struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_md5(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_gcm(void); struct ksmbd_crypto_ctx *ksmbd_crypto_ctx_find_ccm(void); void ksmbd_crypto_destroy(void); diff --git a/fs/ksmbd/glob.h b/fs/ksmbd/glob.h index 49a5a3afa118..5b8f3e0ebdb3 100644 --- a/fs/ksmbd/glob.h +++ b/fs/ksmbd/glob.h @@ -12,7 +12,7 @@ #include "unicode.h" #include "vfs_cache.h" -#define KSMBD_VERSION "3.1.9" +#define KSMBD_VERSION "3.4.2" extern int ksmbd_debug_types; diff --git a/fs/ksmbd/misc.c b/fs/ksmbd/misc.c index 6a19f4bc692d..60e7ac62c917 100644 --- a/fs/ksmbd/misc.c +++ b/fs/ksmbd/misc.c @@ -162,17 +162,14 @@ char *convert_to_nt_pathname(char *filename) { char *ab_pathname; - if (strlen(filename) == 0) { - ab_pathname = kmalloc(2, GFP_KERNEL); - ab_pathname[0] = '\\'; - ab_pathname[1] = '\0'; - } else { - ab_pathname = kstrdup(filename, GFP_KERNEL); - if (!ab_pathname) - return NULL; + if (strlen(filename) == 0) + filename = "\\"; - ksmbd_conv_path_to_windows(ab_pathname); - } + ab_pathname = kstrdup(filename, GFP_KERNEL); + if (!ab_pathname) + return NULL; + + ksmbd_conv_path_to_windows(ab_pathname); return ab_pathname; } diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 16b6236d1bd2..f9dae6ef2115 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -1451,26 +1451,47 @@ struct lease_ctx_info *parse_lease_state(void *open_req) */ struct create_context *smb2_find_context_vals(void *open_req, const char *tag) { - char *data_offset; struct create_context *cc; unsigned int next = 0; char *name; struct smb2_create_req *req = (struct smb2_create_req *)open_req; + unsigned int remain_len, name_off, name_len, value_off, value_len, + cc_len; - data_offset = (char *)req + 4 + le32_to_cpu(req->CreateContextsOffset); - cc = (struct create_context *)data_offset; + /* + * CreateContextsOffset and CreateContextsLength are guaranteed to + * be valid because of ksmbd_smb2_check_message(). + */ + cc = (struct create_context *)((char *)req + 4 + + le32_to_cpu(req->CreateContextsOffset)); + remain_len = le32_to_cpu(req->CreateContextsLength); do { - int val; - cc = (struct create_context *)((char *)cc + next); - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - val = le16_to_cpu(cc->NameLength); - if (val < 4) + if (remain_len < offsetof(struct create_context, Buffer)) return ERR_PTR(-EINVAL); - if (memcmp(name, tag, val) == 0) - return cc; next = le32_to_cpu(cc->Next); + name_off = le16_to_cpu(cc->NameOffset); + name_len = le16_to_cpu(cc->NameLength); + value_off = le16_to_cpu(cc->DataOffset); + value_len = le32_to_cpu(cc->DataLength); + cc_len = next ? next : remain_len; + + if ((next & 0x7) != 0 || + next > remain_len || + name_off != offsetof(struct create_context, Buffer) || + name_len < 4 || + name_off + name_len > cc_len || + (value_off & 0x7) != 0 || + (value_off && (value_off < name_off + name_len)) || + ((u64)value_off + value_len > cc_len)) + return ERR_PTR(-EINVAL); + + name = (char *)cc + name_off; + if (memcmp(name, tag, name_len) == 0) + return cc; + + remain_len -= next; } while (next != 0); return NULL; diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c index 9aa46bb3e10d..9edd9c161b27 100644 --- a/fs/ksmbd/smb2misc.c +++ b/fs/ksmbd/smb2misc.c @@ -80,18 +80,21 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = { }; /* - * Returns the pointer to the beginning of the data area. Length of the data - * area and the offset to it (from the beginning of the smb are also returned. + * Set length of the data area and the offset to arguments. + * if they are invalid, return error. */ -static char *smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr) +static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, + struct smb2_hdr *hdr) { + int ret = 0; + *off = 0; *len = 0; /* error reqeusts do not have data area */ if (hdr->Status && hdr->Status != STATUS_MORE_PROCESSING_REQUIRED && (((struct smb2_err_rsp *)hdr)->StructureSize) == SMB2_ERROR_STRUCTURE_SIZE2_LE) - return NULL; + return ret; /* * Following commands have data areas so we have to get the location @@ -165,69 +168,60 @@ static char *smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr) case SMB2_IOCTL: *off = le32_to_cpu(((struct smb2_ioctl_req *)hdr)->InputOffset); *len = le32_to_cpu(((struct smb2_ioctl_req *)hdr)->InputCount); - break; default: ksmbd_debug(SMB, "no length check for command\n"); break; } - /* - * Invalid length or offset probably means data area is invalid, but - * we have little choice but to ignore the data area in this case. - */ if (*off > 4096) { - ksmbd_debug(SMB, "offset %d too large, data area ignored\n", - *off); - *len = 0; - *off = 0; - } else if (*off < 0) { - ksmbd_debug(SMB, - "negative offset %d to data invalid ignore data area\n", - *off); - *off = 0; - *len = 0; - } else if (*len < 0) { - ksmbd_debug(SMB, - "negative data length %d invalid, data area ignored\n", - *len); - *len = 0; - } else if (*len > 128 * 1024) { - ksmbd_debug(SMB, "data area larger than 128K: %d\n", *len); - *len = 0; + ksmbd_debug(SMB, "offset %d too large\n", *off); + ret = -EINVAL; + } else if ((u64)*off + *len > MAX_STREAM_PROT_LEN) { + ksmbd_debug(SMB, "Request is larger than maximum stream protocol length(%u): %llu\n", + MAX_STREAM_PROT_LEN, (u64)*off + *len); + ret = -EINVAL; } - /* return pointer to beginning of data area, ie offset from SMB start */ - if ((*off != 0) && (*len != 0)) - return (char *)hdr + *off; - else - return NULL; + return ret; } /* * Calculate the size of the SMB message based on the fixed header * portion, the number of word parameters and the data portion of the message. */ -static unsigned int smb2_calc_size(void *buf) +static int smb2_calc_size(void *buf, unsigned int *len) { struct smb2_pdu *pdu = (struct smb2_pdu *)buf; struct smb2_hdr *hdr = &pdu->hdr; - int offset; /* the offset from the beginning of SMB to data area */ - int data_length; /* the length of the variable length data area */ + unsigned int offset; /* the offset from the beginning of SMB to data area */ + unsigned int data_length; /* the length of the variable length data area */ + int ret; + /* Structure Size has already been checked to make sure it is 64 */ - int len = le16_to_cpu(hdr->StructureSize); + *len = le16_to_cpu(hdr->StructureSize); /* * StructureSize2, ie length of fixed parameter area has already * been checked to make sure it is the correct length. */ - len += le16_to_cpu(pdu->StructureSize2); + *len += le16_to_cpu(pdu->StructureSize2); + /* + * StructureSize2 of smb2_lock pdu is set to 48, indicating + * the size of smb2 lock request with single smb2_lock_element + * regardless of number of locks. Subtract single + * smb2_lock_element for correct buffer size check. + */ + if (hdr->Command == SMB2_LOCK) + *len -= sizeof(struct smb2_lock_element); if (has_smb2_data_area[le16_to_cpu(hdr->Command)] == false) goto calc_size_exit; - smb2_get_data_area_len(&offset, &data_length, hdr); - ksmbd_debug(SMB, "SMB2 data length %d offset %d\n", data_length, + ret = smb2_get_data_area_len(&offset, &data_length, hdr); + if (ret) + return ret; + ksmbd_debug(SMB, "SMB2 data length %u offset %u\n", data_length, offset); if (data_length > 0) { @@ -237,16 +231,19 @@ static unsigned int smb2_calc_size(void *buf) * for some commands, typically those with odd StructureSize, * so we must add one to the calculation. */ - if (offset + 1 < len) + if (offset + 1 < *len) { ksmbd_debug(SMB, - "data area offset %d overlaps SMB2 header %d\n", - offset + 1, len); - else - len = offset + data_length; + "data area offset %d overlaps SMB2 header %u\n", + offset + 1, *len); + return -EINVAL; + } + + *len = offset + data_length; } + calc_size_exit: - ksmbd_debug(SMB, "SMB2 len %d\n", len); - return len; + ksmbd_debug(SMB, "SMB2 len %u\n", *len); + return 0; } static inline int smb2_query_info_req_len(struct smb2_query_info_req *h) @@ -391,9 +388,11 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) return 1; } - clc_len = smb2_calc_size(hdr); + if (smb2_calc_size(hdr, &clc_len)) + return 1; + if (len != clc_len) { - /* server can return one byte more due to implied bcc[0] */ + /* client can return one byte more due to implied bcc[0] */ if (clc_len == len + 1) return 0; @@ -418,9 +417,6 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) return 0; } - if (command == SMB2_LOCK_HE && len == 88) - return 0; - ksmbd_debug(SMB, "cli req too short, len %d not %d. cmd:%d mid:%llu\n", len, clc_len, command, diff --git a/fs/ksmbd/smb2ops.c b/fs/ksmbd/smb2ops.c index 197473871aa4..b06456eb587b 100644 --- a/fs/ksmbd/smb2ops.c +++ b/fs/ksmbd/smb2ops.c @@ -187,11 +187,6 @@ static struct smb_version_cmds smb2_0_server_cmds[NUMBER_OF_SMB2_COMMANDS] = { [SMB2_CHANGE_NOTIFY_HE] = { .proc = smb2_notify}, }; -int init_smb2_0_server(struct ksmbd_conn *conn) -{ - return -EOPNOTSUPP; -} - /** * init_smb2_1_server() - initialize a smb server connection with smb2.1 * command dispatcher diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 761e12171dc4..005aa93a49d6 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -236,9 +236,6 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) if (conn->need_neg == false) return -EINVAL; - if (!(conn->dialect >= SMB20_PROT_ID && - conn->dialect <= SMB311_PROT_ID)) - return -EINVAL; rsp_hdr = work->response_buf; @@ -459,13 +456,22 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) bool is_chained_smb2_message(struct ksmbd_work *work) { struct smb2_hdr *hdr = work->request_buf; - unsigned int len; + unsigned int len, next_cmd; if (hdr->ProtocolId != SMB2_PROTO_NUMBER) return false; hdr = ksmbd_req_buf_next(work); - if (le32_to_cpu(hdr->NextCommand) > 0) { + next_cmd = le32_to_cpu(hdr->NextCommand); + if (next_cmd > 0) { + if ((u64)work->next_smb2_rcv_hdr_off + next_cmd + + __SMB2_HEADER_STRUCTURE_SIZE > + get_rfc1002_len(work->request_buf)) { + pr_err("next command(%u) offset exceeds smb msg size\n", + next_cmd); + return false; + } + ksmbd_debug(SMB, "got SMB2 chained command\n"); init_chained_smb2_rsp(work); return true; @@ -1058,6 +1064,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) struct smb2_negotiate_req *req = work->request_buf; struct smb2_negotiate_rsp *rsp = work->response_buf; int rc = 0; + unsigned int smb2_buf_len, smb2_neg_size; __le32 status; ksmbd_debug(SMB, "Received negotiate request\n"); @@ -1075,6 +1082,44 @@ int smb2_handle_negotiate(struct ksmbd_work *work) goto err_out; } + smb2_buf_len = get_rfc1002_len(work->request_buf); + smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects) - 4; + if (smb2_neg_size > smb2_buf_len) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + + if (conn->dialect == SMB311_PROT_ID) { + unsigned int nego_ctxt_off = le32_to_cpu(req->NegotiateContextOffset); + + if (smb2_buf_len < nego_ctxt_off) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + + if (smb2_neg_size > nego_ctxt_off) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + + if (smb2_neg_size + le16_to_cpu(req->DialectCount) * sizeof(__le16) > + nego_ctxt_off) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + } else { + if (smb2_neg_size + le16_to_cpu(req->DialectCount) * sizeof(__le16) > + smb2_buf_len) { + rsp->hdr.Status = STATUS_INVALID_PARAMETER; + rc = -EINVAL; + goto err_out; + } + } + conn->cli_cap = le32_to_cpu(req->Capabilities); switch (conn->dialect) { case SMB311_PROT_ID: @@ -1118,13 +1163,6 @@ int smb2_handle_negotiate(struct ksmbd_work *work) case SMB21_PROT_ID: init_smb2_1_server(conn); break; - case SMB20_PROT_ID: - rc = init_smb2_0_server(conn); - if (rc) { - rsp->hdr.Status = STATUS_NOT_SUPPORTED; - goto err_out; - } - break; case SMB2X_PROT_ID: case BAD_PROT_ID: default: @@ -1143,11 +1181,9 @@ int smb2_handle_negotiate(struct ksmbd_work *work) rsp->MaxReadSize = cpu_to_le32(conn->vals->max_read_size); rsp->MaxWriteSize = cpu_to_le32(conn->vals->max_write_size); - if (conn->dialect > SMB20_PROT_ID) { - memcpy(conn->ClientGUID, req->ClientGUID, - SMB2_CLIENT_GUID_SIZE); - conn->cli_sec_mode = le16_to_cpu(req->SecurityMode); - } + memcpy(conn->ClientGUID, req->ClientGUID, + SMB2_CLIENT_GUID_SIZE); + conn->cli_sec_mode = le16_to_cpu(req->SecurityMode); rsp->StructureSize = cpu_to_le16(65); rsp->DialectRevision = cpu_to_le16(conn->dialect); @@ -1489,11 +1525,9 @@ binding_session: } } - if (conn->dialect > SMB20_PROT_ID) { - if (!ksmbd_conn_lookup_dialect(conn)) { - pr_err("fail to verify the dialect\n"); - return -ENOENT; - } + if (!ksmbd_conn_lookup_dialect(conn)) { + pr_err("fail to verify the dialect\n"); + return -ENOENT; } return 0; } @@ -1575,11 +1609,9 @@ static int krb5_authenticate(struct ksmbd_work *work) } } - if (conn->dialect > SMB20_PROT_ID) { - if (!ksmbd_conn_lookup_dialect(conn)) { - pr_err("fail to verify the dialect\n"); - return -ENOENT; - } + if (!ksmbd_conn_lookup_dialect(conn)) { + pr_err("fail to verify the dialect\n"); + return -ENOENT; } return 0; } @@ -2093,16 +2125,22 @@ out: * smb2_set_ea() - handler for setting extended attributes using set * info command * @eabuf: set info command buffer + * @buf_len: set info command buffer length * @path: dentry path for get ea * * Return: 0 on success, otherwise error */ -static int smb2_set_ea(struct smb2_ea_info *eabuf, struct path *path) +static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, + struct path *path) { struct user_namespace *user_ns = mnt_user_ns(path->mnt); char *attr_name = NULL, *value; int rc = 0; - int next = 0; + unsigned int next = 0; + + if (buf_len < sizeof(struct smb2_ea_info) + eabuf->EaNameLength + + le16_to_cpu(eabuf->EaValueLength)) + return -EINVAL; attr_name = kmalloc(XATTR_NAME_MAX + 1, GFP_KERNEL); if (!attr_name) @@ -2167,7 +2205,13 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, struct path *path) next: next = le32_to_cpu(eabuf->NextEntryOffset); + if (next == 0 || buf_len < next) + break; + buf_len -= next; eabuf = (struct smb2_ea_info *)((char *)eabuf + next); + if (next < (u32)eabuf->EaNameLength + le16_to_cpu(eabuf->EaValueLength)) + break; + } while (next != 0); kfree(attr_name); @@ -2367,6 +2411,10 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work, ksmbd_debug(SMB, "Set ACLs using SMB2_CREATE_SD_BUFFER context\n"); sd_buf = (struct create_sd_buf_req *)context; + if (le16_to_cpu(context->DataOffset) + + le32_to_cpu(context->DataLength) < + sizeof(struct create_sd_buf_req)) + return -EINVAL; return set_info_sec(work->conn, work->tcon, path, &sd_buf->ntsd, le32_to_cpu(sd_buf->ccontext.DataLength), true); } @@ -2561,6 +2609,12 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } else if (context) { ea_buf = (struct create_ea_buf_req *)context; + if (le16_to_cpu(context->DataOffset) + + le32_to_cpu(context->DataLength) < + sizeof(struct create_ea_buf_req)) { + rc = -EINVAL; + goto err_out1; + } if (req->CreateOptions & FILE_NO_EA_KNOWLEDGE_LE) { rsp->hdr.Status = STATUS_ACCESS_DENIED; rc = -EACCES; @@ -2599,6 +2653,12 @@ int smb2_open(struct ksmbd_work *work) } else if (context) { struct create_posix *posix = (struct create_posix *)context; + if (le16_to_cpu(context->DataOffset) + + le32_to_cpu(context->DataLength) < + sizeof(struct create_posix)) { + rc = -EINVAL; + goto err_out1; + } ksmbd_debug(SMB, "get posix context\n"); posix_mode = le32_to_cpu(posix->Mode); @@ -2748,7 +2808,15 @@ int smb2_open(struct ksmbd_work *work) created = true; user_ns = mnt_user_ns(path.mnt); if (ea_buf) { - rc = smb2_set_ea(&ea_buf->ea, &path); + if (le32_to_cpu(ea_buf->ccontext.DataLength) < + sizeof(struct smb2_ea_info)) { + rc = -EINVAL; + goto err_out; + } + + rc = smb2_set_ea(&ea_buf->ea, + le32_to_cpu(ea_buf->ccontext.DataLength), + &path); if (rc == -EOPNOTSUPP) rc = 0; else if (rc) @@ -2981,9 +3049,16 @@ int smb2_open(struct ksmbd_work *work) rc = PTR_ERR(az_req); goto err_out; } else if (az_req) { - loff_t alloc_size = le64_to_cpu(az_req->AllocationSize); + loff_t alloc_size; int err; + if (le16_to_cpu(az_req->ccontext.DataOffset) + + le32_to_cpu(az_req->ccontext.DataLength) < + sizeof(struct create_alloc_size_req)) { + rc = -EINVAL; + goto err_out; + } + alloc_size = le64_to_cpu(az_req->AllocationSize); ksmbd_debug(SMB, "request smb2 create allocate size : %llu\n", alloc_size); @@ -4152,7 +4227,7 @@ static void get_file_access_info(struct smb2_query_info_rsp *rsp, static int get_file_basic_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { - struct smb2_file_all_info *basic_info; + struct smb2_file_basic_info *basic_info; struct kstat stat; u64 time; @@ -4162,7 +4237,7 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return -EACCES; } - basic_info = (struct smb2_file_all_info *)rsp->Buffer; + basic_info = (struct smb2_file_basic_info *)rsp->Buffer; generic_fillattr(file_mnt_user_ns(fp->filp), file_inode(fp->filp), &stat); basic_info->CreationTime = cpu_to_le64(fp->create_time); @@ -4175,9 +4250,8 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, basic_info->Attributes = fp->f_ci->m_fattr; basic_info->Pad1 = 0; rsp->OutputBufferLength = - cpu_to_le32(offsetof(struct smb2_file_all_info, AllocationSize)); - inc_rfc1001_len(rsp_org, offsetof(struct smb2_file_all_info, - AllocationSize)); + cpu_to_le32(sizeof(struct smb2_file_basic_info)); + inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_basic_info)); return 0; } @@ -5333,7 +5407,7 @@ out: static int smb2_create_link(struct ksmbd_work *work, struct ksmbd_share_config *share, struct smb2_file_link_info *file_info, - struct file *filp, + unsigned int buf_len, struct file *filp, struct nls_table *local_nls) { char *link_name = NULL, *target_name = NULL, *pathname = NULL; @@ -5341,6 +5415,10 @@ static int smb2_create_link(struct ksmbd_work *work, bool file_present = true; int rc; + if (buf_len < (u64)sizeof(struct smb2_file_link_info) + + le32_to_cpu(file_info->FileNameLength)) + return -EINVAL; + ksmbd_debug(SMB, "setting FILE_LINK_INFORMATION\n"); pathname = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathname) @@ -5400,12 +5478,11 @@ out: return rc; } -static int set_file_basic_info(struct ksmbd_file *fp, char *buf, +static int set_file_basic_info(struct ksmbd_file *fp, + struct smb2_file_basic_info *file_info, struct ksmbd_share_config *share) { - struct smb2_file_all_info *file_info; struct iattr attrs; - struct timespec64 ctime; struct file *filp; struct inode *inode; struct user_namespace *user_ns; @@ -5414,7 +5491,6 @@ static int set_file_basic_info(struct ksmbd_file *fp, char *buf, if (!(fp->daccess & FILE_WRITE_ATTRIBUTES_LE)) return -EACCES; - file_info = (struct smb2_file_all_info *)buf; attrs.ia_valid = 0; filp = fp->filp; inode = file_inode(filp); @@ -5428,13 +5504,11 @@ static int set_file_basic_info(struct ksmbd_file *fp, char *buf, attrs.ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET); } - if (file_info->ChangeTime) { + attrs.ia_valid |= ATTR_CTIME; + if (file_info->ChangeTime) attrs.ia_ctime = ksmbd_NTtimeToUnix(file_info->ChangeTime); - ctime = attrs.ia_ctime; - attrs.ia_valid |= ATTR_CTIME; - } else { - ctime = inode->i_ctime; - } + else + attrs.ia_ctime = inode->i_ctime; if (file_info->LastWriteTime) { attrs.ia_mtime = ksmbd_NTtimeToUnix(file_info->LastWriteTime); @@ -5480,18 +5554,17 @@ static int set_file_basic_info(struct ksmbd_file *fp, char *buf, return -EACCES; inode_lock(inode); + inode->i_ctime = attrs.ia_ctime; + attrs.ia_valid &= ~ATTR_CTIME; rc = notify_change(user_ns, dentry, &attrs, NULL); - if (!rc) { - inode->i_ctime = ctime; - mark_inode_dirty(inode); - } inode_unlock(inode); } return rc; } static int set_file_allocation_info(struct ksmbd_work *work, - struct ksmbd_file *fp, char *buf) + struct ksmbd_file *fp, + struct smb2_file_alloc_info *file_alloc_info) { /* * TODO : It's working fine only when store dos attributes @@ -5499,7 +5572,6 @@ static int set_file_allocation_info(struct ksmbd_work *work, * properly with any smb.conf option */ - struct smb2_file_alloc_info *file_alloc_info; loff_t alloc_blks; struct inode *inode; int rc; @@ -5507,7 +5579,6 @@ static int set_file_allocation_info(struct ksmbd_work *work, if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; - file_alloc_info = (struct smb2_file_alloc_info *)buf; alloc_blks = (le64_to_cpu(file_alloc_info->AllocationSize) + 511) >> 9; inode = file_inode(fp->filp); @@ -5543,9 +5614,8 @@ static int set_file_allocation_info(struct ksmbd_work *work, } static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, - char *buf) + struct smb2_file_eof_info *file_eof_info) { - struct smb2_file_eof_info *file_eof_info; loff_t newsize; struct inode *inode; int rc; @@ -5553,7 +5623,6 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; - file_eof_info = (struct smb2_file_eof_info *)buf; newsize = le64_to_cpu(file_eof_info->EndOfFile); inode = file_inode(fp->filp); @@ -5580,7 +5649,8 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, } static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, - char *buf) + struct smb2_file_rename_info *rename_info, + unsigned int buf_len) { struct user_namespace *user_ns; struct ksmbd_file *parent_fp; @@ -5593,6 +5663,10 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, return -EACCES; } + if (buf_len < (u64)sizeof(struct smb2_file_rename_info) + + le32_to_cpu(rename_info->FileNameLength)) + return -EINVAL; + user_ns = file_mnt_user_ns(fp->filp); if (ksmbd_stream_fd(fp)) goto next; @@ -5615,14 +5689,13 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, } } next: - return smb2_rename(work, fp, user_ns, - (struct smb2_file_rename_info *)buf, + return smb2_rename(work, fp, user_ns, rename_info, work->sess->conn->local_nls); } -static int set_file_disposition_info(struct ksmbd_file *fp, char *buf) +static int set_file_disposition_info(struct ksmbd_file *fp, + struct smb2_file_disposition_info *file_info) { - struct smb2_file_disposition_info *file_info; struct inode *inode; if (!(fp->daccess & FILE_DELETE_LE)) { @@ -5631,7 +5704,6 @@ static int set_file_disposition_info(struct ksmbd_file *fp, char *buf) } inode = file_inode(fp->filp); - file_info = (struct smb2_file_disposition_info *)buf; if (file_info->DeletePending) { if (S_ISDIR(inode->i_mode) && ksmbd_vfs_empty_dir(fp) == -ENOTEMPTY) @@ -5643,15 +5715,14 @@ static int set_file_disposition_info(struct ksmbd_file *fp, char *buf) return 0; } -static int set_file_position_info(struct ksmbd_file *fp, char *buf) +static int set_file_position_info(struct ksmbd_file *fp, + struct smb2_file_pos_info *file_info) { - struct smb2_file_pos_info *file_info; loff_t current_byte_offset; unsigned long sector_size; struct inode *inode; inode = file_inode(fp->filp); - file_info = (struct smb2_file_pos_info *)buf; current_byte_offset = le64_to_cpu(file_info->CurrentByteOffset); sector_size = inode->i_sb->s_blocksize; @@ -5667,12 +5738,11 @@ static int set_file_position_info(struct ksmbd_file *fp, char *buf) return 0; } -static int set_file_mode_info(struct ksmbd_file *fp, char *buf) +static int set_file_mode_info(struct ksmbd_file *fp, + struct smb2_file_mode_info *file_info) { - struct smb2_file_mode_info *file_info; __le32 mode; - file_info = (struct smb2_file_mode_info *)buf; mode = file_info->Mode; if ((mode & ~FILE_MODE_INFO_MASK) || @@ -5702,40 +5772,74 @@ static int set_file_mode_info(struct ksmbd_file *fp, char *buf) * TODO: need to implement an error handling for STATUS_INFO_LENGTH_MISMATCH */ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, - int info_class, char *buf, + struct smb2_set_info_req *req, struct ksmbd_share_config *share) { - switch (info_class) { + unsigned int buf_len = le32_to_cpu(req->BufferLength); + + switch (req->FileInfoClass) { case FILE_BASIC_INFORMATION: - return set_file_basic_info(fp, buf, share); + { + if (buf_len < sizeof(struct smb2_file_basic_info)) + return -EINVAL; + return set_file_basic_info(fp, (struct smb2_file_basic_info *)req->Buffer, share); + } case FILE_ALLOCATION_INFORMATION: - return set_file_allocation_info(work, fp, buf); + { + if (buf_len < sizeof(struct smb2_file_alloc_info)) + return -EINVAL; + return set_file_allocation_info(work, fp, + (struct smb2_file_alloc_info *)req->Buffer); + } case FILE_END_OF_FILE_INFORMATION: - return set_end_of_file_info(work, fp, buf); + { + if (buf_len < sizeof(struct smb2_file_eof_info)) + return -EINVAL; + return set_end_of_file_info(work, fp, + (struct smb2_file_eof_info *)req->Buffer); + } case FILE_RENAME_INFORMATION: + { if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { ksmbd_debug(SMB, "User does not have write permission\n"); return -EACCES; } - return set_rename_info(work, fp, buf); + if (buf_len < sizeof(struct smb2_file_rename_info)) + return -EINVAL; + + return set_rename_info(work, fp, + (struct smb2_file_rename_info *)req->Buffer, + buf_len); + } case FILE_LINK_INFORMATION: + { + if (buf_len < sizeof(struct smb2_file_link_info)) + return -EINVAL; + return smb2_create_link(work, work->tcon->share_conf, - (struct smb2_file_link_info *)buf, fp->filp, + (struct smb2_file_link_info *)req->Buffer, + buf_len, fp->filp, work->sess->conn->local_nls); - + } case FILE_DISPOSITION_INFORMATION: + { if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { ksmbd_debug(SMB, "User does not have write permission\n"); return -EACCES; } - return set_file_disposition_info(fp, buf); + if (buf_len < sizeof(struct smb2_file_disposition_info)) + return -EINVAL; + + return set_file_disposition_info(fp, + (struct smb2_file_disposition_info *)req->Buffer); + } case FILE_FULL_EA_INFORMATION: { if (!(fp->daccess & FILE_WRITE_EA_LE)) { @@ -5744,18 +5848,29 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EACCES; } - return smb2_set_ea((struct smb2_ea_info *)buf, - &fp->filp->f_path); - } + if (buf_len < sizeof(struct smb2_ea_info)) + return -EINVAL; + return smb2_set_ea((struct smb2_ea_info *)req->Buffer, + buf_len, &fp->filp->f_path); + } case FILE_POSITION_INFORMATION: - return set_file_position_info(fp, buf); + { + if (buf_len < sizeof(struct smb2_file_pos_info)) + return -EINVAL; + return set_file_position_info(fp, (struct smb2_file_pos_info *)req->Buffer); + } case FILE_MODE_INFORMATION: - return set_file_mode_info(fp, buf); + { + if (buf_len < sizeof(struct smb2_file_mode_info)) + return -EINVAL; + + return set_file_mode_info(fp, (struct smb2_file_mode_info *)req->Buffer); + } } - pr_err("Unimplemented Fileinfoclass :%d\n", info_class); + pr_err("Unimplemented Fileinfoclass :%d\n", req->FileInfoClass); return -EOPNOTSUPP; } @@ -5816,8 +5931,7 @@ int smb2_set_info(struct ksmbd_work *work) switch (req->InfoType) { case SMB2_O_INFO_FILE: ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n"); - rc = smb2_set_info_file(work, fp, req->FileInfoClass, - req->Buffer, work->tcon->share_conf); + rc = smb2_set_info_file(work, fp, req, work->tcon->share_conf); break; case SMB2_O_INFO_SECURITY: ksmbd_debug(SMB, "GOT SMB2_O_INFO_SECURITY\n"); @@ -8171,7 +8285,8 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work) WORK_BUFFERS(work, req, rsp); - if (le16_to_cpu(req->Command) == SMB2_NEGOTIATE_HE) + if (le16_to_cpu(req->Command) == SMB2_NEGOTIATE_HE && + conn->preauth_info) ksmbd_gen_preauth_integrity_hash(conn, (char *)rsp, conn->preauth_info->Preauth_HashValue); @@ -8275,31 +8390,29 @@ int smb3_decrypt_req(struct ksmbd_work *work) struct smb2_hdr *hdr; unsigned int pdu_length = get_rfc1002_len(buf); struct kvec iov[2]; - unsigned int buf_data_size = pdu_length + 4 - + int buf_data_size = pdu_length + 4 - sizeof(struct smb2_transform_hdr); struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf; - unsigned int orig_len = le32_to_cpu(tr_hdr->OriginalMessageSize); int rc = 0; - sess = ksmbd_session_lookup_all(conn, le64_to_cpu(tr_hdr->SessionId)); - if (!sess) { - pr_err("invalid session id(%llx) in transform header\n", - le64_to_cpu(tr_hdr->SessionId)); - return -ECONNABORTED; - } - - if (pdu_length + 4 < - sizeof(struct smb2_transform_hdr) + sizeof(struct smb2_hdr)) { + if (buf_data_size < sizeof(struct smb2_hdr)) { pr_err("Transform message is too small (%u)\n", pdu_length); return -ECONNABORTED; } - if (pdu_length + 4 < orig_len + sizeof(struct smb2_transform_hdr)) { + if (buf_data_size < le32_to_cpu(tr_hdr->OriginalMessageSize)) { pr_err("Transform message is broken\n"); return -ECONNABORTED; } + sess = ksmbd_session_lookup_all(conn, le64_to_cpu(tr_hdr->SessionId)); + if (!sess) { + pr_err("invalid session id(%llx) in transform header\n", + le64_to_cpu(tr_hdr->SessionId)); + return -ECONNABORTED; + } + iov[0].iov_base = buf; iov[0].iov_len = sizeof(struct smb2_transform_hdr); iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr); diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index bcec845b03f3..a6dec5ec6a54 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -1464,6 +1464,15 @@ struct smb2_file_all_info { /* data block encoding of response to level 18 */ char FileName[1]; } __packed; /* level 18 Query */ +struct smb2_file_basic_info { /* data block encoding of response to level 18 */ + __le64 CreationTime; /* Beginning of FILE_BASIC_INFO equivalent */ + __le64 LastAccessTime; + __le64 LastWriteTime; + __le64 ChangeTime; + __le32 Attributes; + __u32 Pad1; /* End of FILE_BASIC_INFO_INFO equivalent */ +} __packed; + struct smb2_file_alt_name_info { __le32 FileNameLength; char FileName[0]; @@ -1628,7 +1637,6 @@ struct smb2_posix_info { } __packed; /* functions */ -int init_smb2_0_server(struct ksmbd_conn *conn); void init_smb2_1_server(struct ksmbd_conn *conn); void init_smb3_0_server(struct ksmbd_conn *conn); void init_smb3_02_server(struct ksmbd_conn *conn); diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index 40f4fafa2e11..707490ab1f4c 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -21,7 +21,6 @@ static const char basechars[43] = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_-!@#$%"; #define MAGIC_CHAR '~' #define PERIOD '.' #define mangle(V) ((char)(basechars[(V) % MANGLE_BASE])) -#define KSMBD_MIN_SUPPORTED_HEADER_SIZE (sizeof(struct smb2_hdr)) struct smb_protocol { int index; @@ -89,7 +88,7 @@ unsigned int ksmbd_server_side_copy_max_total_size(void) inline int ksmbd_min_protocol(void) { - return SMB2_PROT; + return SMB21_PROT; } inline int ksmbd_max_protocol(void) @@ -155,20 +154,7 @@ int ksmbd_verify_smb_message(struct ksmbd_work *work) */ bool ksmbd_smb_request(struct ksmbd_conn *conn) { - int type = *(char *)conn->request_buf; - - switch (type) { - case RFC1002_SESSION_MESSAGE: - /* Regular SMB request */ - return true; - case RFC1002_SESSION_KEEP_ALIVE: - ksmbd_debug(SMB, "RFC 1002 session keep alive\n"); - break; - default: - ksmbd_debug(SMB, "RFC 1002 unknown request type 0x%x\n", type); - } - - return false; + return conn->request_buf[0] == 0; } static bool supported_protocol(int idx) @@ -182,10 +168,12 @@ static bool supported_protocol(int idx) idx <= server_conf.max_protocol); } -static char *next_dialect(char *dialect, int *next_off) +static char *next_dialect(char *dialect, int *next_off, int bcount) { dialect = dialect + *next_off; - *next_off = strlen(dialect); + *next_off = strnlen(dialect, bcount); + if (dialect[*next_off] != '\0') + return NULL; return dialect; } @@ -200,7 +188,9 @@ static int ksmbd_lookup_dialect_by_name(char *cli_dialects, __le16 byte_count) dialect = cli_dialects; bcount = le16_to_cpu(byte_count); do { - dialect = next_dialect(dialect, &next); + dialect = next_dialect(dialect, &next, bcount); + if (!dialect) + break; ksmbd_debug(SMB, "client requested dialect %s\n", dialect); if (!strcmp(dialect, smb1_protos[i].name)) { @@ -248,13 +238,22 @@ int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count) static int ksmbd_negotiate_smb_dialect(void *buf) { - __le32 proto; + int smb_buf_length = get_rfc1002_len(buf); + __le32 proto = ((struct smb2_hdr *)buf)->ProtocolId; - proto = ((struct smb2_hdr *)buf)->ProtocolId; if (proto == SMB2_PROTO_NUMBER) { struct smb2_negotiate_req *req; + int smb2_neg_size = + offsetof(struct smb2_negotiate_req, Dialects) - 4; req = (struct smb2_negotiate_req *)buf; + if (smb2_neg_size > smb_buf_length) + goto err_out; + + if (smb2_neg_size + le16_to_cpu(req->DialectCount) * sizeof(__le16) > + smb_buf_length) + goto err_out; + return ksmbd_lookup_dialect_by_id(req->Dialects, req->DialectCount); } @@ -264,10 +263,19 @@ static int ksmbd_negotiate_smb_dialect(void *buf) struct smb_negotiate_req *req; req = (struct smb_negotiate_req *)buf; + if (le16_to_cpu(req->ByteCount) < 2) + goto err_out; + + if (offsetof(struct smb_negotiate_req, DialectsArray) - 4 + + le16_to_cpu(req->ByteCount) > smb_buf_length) { + goto err_out; + } + return ksmbd_lookup_dialect_by_name(req->DialectsArray, req->ByteCount); } +err_out: return BAD_PROT_ID; } @@ -285,11 +293,6 @@ int ksmbd_init_smb_server(struct ksmbd_work *work) return 0; } -bool ksmbd_pdu_size_has_room(unsigned int pdu) -{ - return (pdu >= KSMBD_MIN_SUPPORTED_HEADER_SIZE - 4); -} - int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, struct ksmbd_file *dir, struct ksmbd_dir_info *d_info, @@ -424,7 +427,7 @@ int ksmbd_extract_shortname(struct ksmbd_conn *conn, const char *longname, static int __smb2_negotiate(struct ksmbd_conn *conn) { - return (conn->dialect >= SMB20_PROT_ID && + return (conn->dialect >= SMB21_PROT_ID && conn->dialect <= SMB311_PROT_ID); } @@ -454,7 +457,7 @@ int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command) } } - if (command == SMB2_NEGOTIATE_HE) { + if (command == SMB2_NEGOTIATE_HE && __smb2_negotiate(conn)) { ret = smb2_handle_negotiate(work); init_smb2_neg_rsp(work); return ret; diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h index 0a6af447cc45..6e79e7577f6b 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/ksmbd/smb_common.h @@ -48,13 +48,7 @@ #define CIFS_DEFAULT_IOSIZE (64 * 1024) #define MAX_CIFS_SMALL_BUFFER_SIZE 448 /* big enough for most */ -/* RFC 1002 session packet types */ -#define RFC1002_SESSION_MESSAGE 0x00 -#define RFC1002_SESSION_REQUEST 0x81 -#define RFC1002_POSITIVE_SESSION_RESPONSE 0x82 -#define RFC1002_NEGATIVE_SESSION_RESPONSE 0x83 -#define RFC1002_RETARGET_SESSION_RESPONSE 0x84 -#define RFC1002_SESSION_KEEP_ALIVE 0x85 +#define MAX_STREAM_PROT_LEN 0x00FFFFFF /* Responses when opening a file. */ #define F_SUPERSEDED 0 @@ -501,8 +495,6 @@ int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count); int ksmbd_init_smb_server(struct ksmbd_work *work); -bool ksmbd_pdu_size_has_room(unsigned int pdu); - struct ksmbd_kstat; int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, diff --git a/fs/ksmbd/smbacl.c b/fs/ksmbd/smbacl.c index 0a95cdec8c80..bd792db32623 100644 --- a/fs/ksmbd/smbacl.c +++ b/fs/ksmbd/smbacl.c @@ -380,7 +380,7 @@ static void parse_dacl(struct user_namespace *user_ns, { int i, ret; int num_aces = 0; - int acl_size; + unsigned int acl_size; char *acl_base; struct smb_ace **ppace; struct posix_acl_entry *cf_pace, *cf_pdace; @@ -392,7 +392,7 @@ static void parse_dacl(struct user_namespace *user_ns, return; /* validate that we do not go past end of acl */ - if (end_of_acl <= (char *)pdacl || + if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) || end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) { pr_err("ACL too small to parse DACL\n"); return; @@ -431,8 +431,22 @@ static void parse_dacl(struct user_namespace *user_ns, * user/group/other have no permissions */ for (i = 0; i < num_aces; ++i) { + if (end_of_acl - acl_base < acl_size) + break; + ppace[i] = (struct smb_ace *)(acl_base + acl_size); acl_base = (char *)ppace[i]; + acl_size = offsetof(struct smb_ace, sid) + + offsetof(struct smb_sid, sub_auth); + + if (end_of_acl - acl_base < acl_size || + ppace[i]->sid.num_subauth > SID_MAX_SUB_AUTHORITIES || + (end_of_acl - acl_base < + acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) || + (le16_to_cpu(ppace[i]->size) < + acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth)) + break; + acl_size = le16_to_cpu(ppace[i]->size); ppace[i]->access_req = smb_map_generic_desired_access(ppace[i]->access_req); @@ -807,6 +821,9 @@ int parse_sec_desc(struct user_namespace *user_ns, struct smb_ntsd *pntsd, if (!pntsd) return -EIO; + if (acl_len < sizeof(struct smb_ntsd)) + return -EINVAL; + owner_sid_ptr = (struct smb_sid *)((char *)pntsd + le32_to_cpu(pntsd->osidoffset)); group_sid_ptr = (struct smb_sid *)((char *)pntsd + diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c index dc15a5ecd2e0..c14320e03b69 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/ksmbd/transport_tcp.c @@ -215,7 +215,7 @@ out_error: * ksmbd_kthread_fn() - listen to new SMB connections and callback server * @p: arguments to forker thread * - * Return: Returns a task_struct or ERR_PTR + * Return: 0 on success, error number otherwise */ static int ksmbd_kthread_fn(void *p) { @@ -387,7 +387,7 @@ static void tcp_destroy_socket(struct socket *ksmbd_socket) /** * create_socket - create socket for ksmbd/0 * - * Return: Returns a task_struct or ERR_PTR + * Return: 0 on success, error number otherwise */ static int create_socket(struct interface *iface) { diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 0b6cd3b8734c..994ec22d4040 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -150,7 +150,7 @@ static void netfs_clear_unread(struct netfs_read_subrequest *subreq) { struct iov_iter iter; - iov_iter_xarray(&iter, WRITE, &subreq->rreq->mapping->i_pages, + iov_iter_xarray(&iter, READ, &subreq->rreq->mapping->i_pages, subreq->start + subreq->transferred, subreq->len - subreq->transferred); iov_iter_zero(iov_iter_count(&iter), &iter); diff --git a/fs/nfs_common/grace.c b/fs/nfs_common/grace.c index edec45831585..0a9b72685f98 100644 --- a/fs/nfs_common/grace.c +++ b/fs/nfs_common/grace.c @@ -42,7 +42,6 @@ EXPORT_SYMBOL_GPL(locks_start_grace); /** * locks_end_grace - * @net: net namespace that this lock manager belongs to * @lm: who this grace period is for * * Call this function to state that the given lock manager is ready to diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 7629248fdd53..be3c1aad50ea 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -542,7 +542,7 @@ nfsd_file_close_inode_sync(struct inode *inode) } /** - * nfsd_file_close_inode_sync - attempt to forcibly close a nfsd_file + * nfsd_file_close_inode - attempt a delayed close of a nfsd_file * @inode: inode of the file to attempt to remove * * Walk the whole hash bucket, looking for any files that correspond to "inode". diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 7abeccb975b2..cf030ebe2827 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3544,15 +3544,18 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, goto fail; cd->rd_maxcount -= entry_bytes; /* - * RFC 3530 14.2.24 describes rd_dircount as only a "hint", so - * let's always let through the first entry, at least: + * RFC 3530 14.2.24 describes rd_dircount as only a "hint", and + * notes that it could be zero. If it is zero, then the server + * should enforce only the rd_maxcount value. */ - if (!cd->rd_dircount) - goto fail; - name_and_cookie = 4 + 4 * XDR_QUADLEN(namlen) + 8; - if (name_and_cookie > cd->rd_dircount && cd->cookie_offset) - goto fail; - cd->rd_dircount -= min(cd->rd_dircount, name_and_cookie); + if (cd->rd_dircount) { + name_and_cookie = 4 + 4 * XDR_QUADLEN(namlen) + 8; + if (name_and_cookie > cd->rd_dircount && cd->cookie_offset) + goto fail; + cd->rd_dircount -= min(cd->rd_dircount, name_and_cookie); + if (!cd->rd_dircount) + cd->rd_maxcount = 0; + } cd->cookie_offset = cookie_offset; skip_entry: diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index c2c3d9077dc5..070e5dd03e26 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -793,7 +793,10 @@ out_close: svc_xprt_put(xprt); } out_err: - nfsd_destroy(net); + if (!list_empty(&nn->nfsd_serv->sv_permsocks)) + nn->nfsd_serv->sv_nrthreads--; + else + nfsd_destroy(net); return err; } @@ -1545,7 +1548,7 @@ static int __init init_nfsd(void) goto out_free_all; return 0; out_free_all: - unregister_pernet_subsys(&nfsd_net_ops); + unregister_filesystem(&nfsd_fs_type); out_free_exports: remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 1fefb2b8960e..93c7c267de93 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -1219,9 +1219,13 @@ static int ovl_rename(struct user_namespace *mnt_userns, struct inode *olddir, goto out_dput; } } else { - if (!d_is_negative(newdentry) && - (!new_opaque || !ovl_is_whiteout(newdentry))) - goto out_dput; + if (!d_is_negative(newdentry)) { + if (!new_opaque || !ovl_is_whiteout(newdentry)) + goto out_dput; + } else { + if (flags & RENAME_EXCHANGE) + goto out_dput; + } } if (olddentry == trap) diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index d081faa55e83..c88ac571593d 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -296,6 +296,12 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (ret) return ret; + ret = -EINVAL; + if (iocb->ki_flags & IOCB_DIRECT && + (!real.file->f_mapping->a_ops || + !real.file->f_mapping->a_ops->direct_IO)) + goto out_fdput; + old_cred = ovl_override_creds(file_inode(file)->i_sb); if (is_sync_kiocb(iocb)) { ret = vfs_iter_read(real.file, iter, &iocb->ki_pos, @@ -320,7 +326,7 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) out: revert_creds(old_cred); ovl_file_accessed(file); - +out_fdput: fdput(real); return ret; @@ -349,6 +355,12 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) if (ret) goto out_unlock; + ret = -EINVAL; + if (iocb->ki_flags & IOCB_DIRECT && + (!real.file->f_mapping->a_ops || + !real.file->f_mapping->a_ops->direct_IO)) + goto out_fdput; + if (!ovl_should_sync(OVL_FS(inode->i_sb))) ifl &= ~(IOCB_DSYNC | IOCB_SYNC); @@ -384,6 +396,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) } out: revert_creds(old_cred); +out_fdput: fdput(real); out_unlock: diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index cc7338f9e0d1..7ce93aaf69f8 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -957,7 +957,7 @@ static inline void __iomem *ioremap(phys_addr_t offset, size_t size) #ifndef iounmap #define iounmap iounmap -static inline void iounmap(void __iomem *addr) +static inline void iounmap(volatile void __iomem *addr) { } #endif diff --git a/include/kunit/test.h b/include/kunit/test.h index 24b40e5c160b..018e776a34b9 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -613,7 +613,7 @@ void kunit_remove_resource(struct kunit *test, struct kunit_resource *res); * and is automatically cleaned up after the test case concludes. See &struct * kunit_resource for more information. */ -void *kunit_kmalloc_array(struct kunit *test, size_t n, size_t size, gfp_t flags); +void *kunit_kmalloc_array(struct kunit *test, size_t n, size_t size, gfp_t gfp); /** * kunit_kmalloc() - Like kmalloc() except the allocation is *test managed*. @@ -657,9 +657,9 @@ static inline void *kunit_kzalloc(struct kunit *test, size_t size, gfp_t gfp) * * See kcalloc() and kunit_kmalloc_array() for more information. */ -static inline void *kunit_kcalloc(struct kunit *test, size_t n, size_t size, gfp_t flags) +static inline void *kunit_kcalloc(struct kunit *test, size_t n, size_t size, gfp_t gfp) { - return kunit_kmalloc_array(test, n, size, flags | __GFP_ZERO); + return kunit_kmalloc_array(test, n, size, gfp | __GFP_ZERO); } void kunit_cleanup(struct kunit *test); diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 7d1cabe15262..63ccb5252190 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -321,10 +321,20 @@ asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0); * from register 0 to 3 on return from the SMC instruction. An optional * quirk structure provides vendor specific behavior. */ +#ifdef CONFIG_HAVE_ARM_SMCCC asmlinkage void __arm_smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3, unsigned long a4, unsigned long a5, unsigned long a6, unsigned long a7, struct arm_smccc_res *res, struct arm_smccc_quirk *quirk); +#else +static inline void __arm_smccc_smc(unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, unsigned long a4, + unsigned long a5, unsigned long a6, unsigned long a7, + struct arm_smccc_res *res, struct arm_smccc_quirk *quirk) +{ + *res = (struct arm_smccc_res){}; +} +#endif /** * __arm_smccc_hvc() - make HVC calls diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 5d4d07a9e1ed..1e7399fc69c0 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -996,14 +996,15 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * - * Returns the length of how many bytes have been copied. + * Returns the length of how many bytes have been copied, excluding + * terminating '\0'. */ static inline ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), - nr_cpu_ids, off, count); + nr_cpu_ids, off, count) - 1; } /** @@ -1018,7 +1019,7 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), - nr_cpu_ids, off, count); + nr_cpu_ids, off, count) - 1; } #if NR_CPUS <= BITS_PER_LONG diff --git a/include/linux/dsa/mv88e6xxx.h b/include/linux/dsa/mv88e6xxx.h new file mode 100644 index 000000000000..8c3d45eca46b --- /dev/null +++ b/include/linux/dsa/mv88e6xxx.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright 2021 NXP + */ + +#ifndef _NET_DSA_TAG_MV88E6XXX_H +#define _NET_DSA_TAG_MV88E6XXX_H + +#include <linux/if_vlan.h> + +#define MV88E6XXX_VID_STANDALONE 0 +#define MV88E6XXX_VID_BRIDGED (VLAN_N_VID - 1) + +#endif diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index 0fe101e8e190..d42010cf5468 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -5,7 +5,28 @@ #ifndef _NET_DSA_TAG_OCELOT_H #define _NET_DSA_TAG_OCELOT_H +#include <linux/kthread.h> #include <linux/packing.h> +#include <linux/skbuff.h> + +struct ocelot_skb_cb { + struct sk_buff *clone; + unsigned int ptp_class; /* valid only for clones */ + u8 ptp_cmd; + u8 ts_id; +}; + +#define OCELOT_SKB_CB(skb) \ + ((struct ocelot_skb_cb *)((skb)->cb)) + +#define IFH_TAG_TYPE_C 0 +#define IFH_TAG_TYPE_S 1 + +#define IFH_REW_OP_NOOP 0x0 +#define IFH_REW_OP_DSCP 0x1 +#define IFH_REW_OP_ONE_STEP_PTP 0x2 +#define IFH_REW_OP_TWO_STEP_PTP 0x3 +#define IFH_REW_OP_ORIGIN_PTP 0x5 #define OCELOT_TAG_LEN 16 #define OCELOT_SHORT_PREFIX_LEN 4 @@ -140,6 +161,17 @@ * +------+------+------+------+------+------+------+------+ */ +struct felix_deferred_xmit_work { + struct dsa_port *dp; + struct sk_buff *skb; + struct kthread_work work; +}; + +struct felix_port { + void (*xmit_work_fn)(struct kthread_work *work); + struct kthread_worker *xmit_worker; +}; + static inline void ocelot_xfh_get_rew_val(void *extraction, u64 *rew_val) { packing(extraction, rew_val, 116, 85, OCELOT_TAG_LEN, UNPACK, 0); @@ -215,4 +247,21 @@ static inline void ocelot_ifh_set_vlan_tci(void *injection, u64 vlan_tci) packing(injection, &vlan_tci, 15, 0, OCELOT_TAG_LEN, PACK, 0); } +/* Determine the PTP REW_OP to use for injecting the given skb */ +static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb) +{ + struct sk_buff *clone = OCELOT_SKB_CB(skb)->clone; + u8 ptp_cmd = OCELOT_SKB_CB(skb)->ptp_cmd; + u32 rew_op = 0; + + if (ptp_cmd == IFH_REW_OP_TWO_STEP_PTP && clone) { + rew_op = ptp_cmd; + rew_op |= OCELOT_SKB_CB(clone)->ts_id << 3; + } else if (ptp_cmd == IFH_REW_OP_ORIGIN_PTP) { + rew_op = ptp_cmd; + } + + return rew_op; +} + #endif diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index a8bb64cf4079..23681c3d3b8a 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -29,6 +29,7 @@ struct device; struct fwnode_handle; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); +int platform_get_ethdev_address(struct device *dev, struct net_device *netdev); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); int device_get_mac_address(struct device *dev, char *addr); @@ -233,8 +234,6 @@ static inline void eth_random_addr(u8 *addr) addr[0] |= 0x02; /* set local assignment bit (IEEE802) */ } -#define random_ether_addr(addr) eth_random_addr(addr) - /** * eth_broadcast_addr - Assign broadcast address * @addr: Pointer to a six-byte array containing the Ethernet address @@ -268,8 +267,11 @@ static inline void eth_zero_addr(u8 *addr) */ static inline void eth_hw_addr_random(struct net_device *dev) { + u8 addr[ETH_ALEN]; + + eth_random_addr(addr); + __dev_addr_set(dev, addr, ETH_ALEN); dev->addr_assign_type = NET_ADDR_RANDOM; - eth_random_addr(dev->dev_addr); } /** @@ -314,7 +316,7 @@ static inline void ether_addr_copy(u8 *dst, const u8 *src) */ static inline void eth_hw_addr_set(struct net_device *dev, const u8 *addr) { - ether_addr_copy(dev->dev_addr, addr); + __dev_addr_set(dev, addr, ETH_ALEN); } /** diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 59828516ebaf..9f4ad719bfe3 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -22,10 +22,15 @@ struct device; * LINKS_ADDED: The fwnode has already be parsed to add fwnode links. * NOT_DEVICE: The fwnode will never be populated as a struct device. * INITIALIZED: The hardware corresponding to fwnode has been initialized. + * NEEDS_CHILD_BOUND_ON_ADD: For this fwnode/device to probe successfully, its + * driver needs its child devices to be bound with + * their respective drivers as soon as they are + * added. */ -#define FWNODE_FLAG_LINKS_ADDED BIT(0) -#define FWNODE_FLAG_NOT_DEVICE BIT(1) -#define FWNODE_FLAG_INITIALIZED BIT(2) +#define FWNODE_FLAG_LINKS_ADDED BIT(0) +#define FWNODE_FLAG_NOT_DEVICE BIT(1) +#define FWNODE_FLAG_INITIALIZED BIT(2) +#define FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD BIT(3) struct fwnode_handle { struct fwnode_handle *secondary; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 66eaf0aa7f69..109cc8106d16 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -577,7 +577,9 @@ struct mlx5_init_seg { __be32 rsvd1[120]; __be32 initializing; struct health_buffer health; - __be32 rsvd2[880]; + __be32 rsvd2[878]; + __be32 cmd_exec_to; + __be32 cmd_q_init_to; __be32 internal_timer_h; __be32 internal_timer_l; __be32 rsvd3[2]; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 0ca719c00824..cf508685abca 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -66,10 +66,6 @@ enum { }; enum { - /* one minute for the sake of bringup. Generally, commands must always - * complete and we may need to increase this timeout value - */ - MLX5_CMD_TIMEOUT_MSEC = 60 * 1000, MLX5_CMD_WQ_MAX_NAME = 32, }; @@ -156,6 +152,7 @@ enum { MLX5_REG_MIRC = 0x9162, MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, + MLX5_REG_DTOR = 0xC00E, }; enum mlx5_qpts_trust_state { @@ -754,6 +751,7 @@ struct mlx5_core_dev { u32 qcam[MLX5_ST_SZ_DW(qcam_reg)]; u8 embedded_cpu; } caps; + struct mlx5_timeouts *timeouts; u64 sys_image_guid; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; @@ -1245,6 +1243,16 @@ static inline int mlx5_core_native_port_num(struct mlx5_core_dev *dev) return MLX5_CAP_GEN(dev, native_port_num); } +static inline int mlx5_get_dev_index(struct mlx5_core_dev *dev) +{ + int idx = MLX5_CAP_GEN(dev, native_port_num); + + if (idx >= 1 && idx <= MLX5_MAX_PORTS) + return idx - 1; + else + return PCI_FUNC(dev->pdev->devfn); +} + enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; @@ -1253,11 +1261,12 @@ static inline bool mlx5_is_roce_init_enabled(struct mlx5_core_dev *dev) { struct devlink *devlink = priv_to_devlink(dev); union devlink_param_value val; + int err; - devlink_param_driverinit_value_get(devlink, - DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, - &val); - return val.vbool; + err = devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + &val); + return err ? MLX5_CAP_GEN(dev, roce) : val.vbool; } #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f3638d09ba77..c614ad1da44d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1306,7 +1306,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vhca_resource_manager[0x1]; u8 hca_cap_2[0x1]; - u8 reserved_at_21[0x2]; + u8 reserved_at_21[0x1]; + u8 dtor[0x1]; u8 event_on_vhca_state_teardown_request[0x1]; u8 event_on_vhca_state_in_use[0x1]; u8 event_on_vhca_state_active[0x1]; @@ -1587,7 +1588,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_tis_per_sq[0x5]; u8 ext_stride_num_range[0x1]; - u8 reserved_at_3a1[0x2]; + u8 roce_rw_supported[0x1]; + u8 reserved_at_3a2[0x1]; u8 log_max_stride_sz_rq[0x5]; u8 reserved_at_3a8[0x3]; u8 log_min_stride_sz_rq[0x5]; @@ -2807,6 +2809,40 @@ struct mlx5_ifc_dropped_packet_logged_bits { u8 reserved_at_0[0xe0]; }; +struct mlx5_ifc_default_timeout_bits { + u8 to_multiplier[0x3]; + u8 reserved_at_3[0x9]; + u8 to_value[0x14]; +}; + +struct mlx5_ifc_dtor_reg_bits { + u8 reserved_at_0[0x20]; + + struct mlx5_ifc_default_timeout_bits pcie_toggle_to; + + u8 reserved_at_40[0x60]; + + struct mlx5_ifc_default_timeout_bits health_poll_to; + + struct mlx5_ifc_default_timeout_bits full_crdump_to; + + struct mlx5_ifc_default_timeout_bits fw_reset_to; + + struct mlx5_ifc_default_timeout_bits flush_on_err_to; + + struct mlx5_ifc_default_timeout_bits pci_sync_update_to; + + struct mlx5_ifc_default_timeout_bits tear_down_to; + + struct mlx5_ifc_default_timeout_bits fsm_reactivate_to; + + struct mlx5_ifc_default_timeout_bits reclaim_pages_to; + + struct mlx5_ifc_default_timeout_bits reclaim_vfs_pages_to; + + u8 reserved_at_1c0[0x40]; +}; + enum { MLX5_CQ_ERROR_SYNDROME_CQ_OVERRUN = 0x1, MLX5_CQ_ERROR_SYNDROME_CQ_ACCESS_VIOLATION_ERROR = 0x2, @@ -9475,16 +9511,22 @@ struct mlx5_ifc_pcmr_reg_bits { u8 reserved_at_0[0x8]; u8 local_port[0x8]; u8 reserved_at_10[0x10]; + u8 entropy_force_cap[0x1]; u8 entropy_calc_cap[0x1]; u8 entropy_gre_calc_cap[0x1]; - u8 reserved_at_23[0x1b]; + u8 reserved_at_23[0xf]; + u8 rx_ts_over_crc_cap[0x1]; + u8 reserved_at_33[0xb]; u8 fcs_cap[0x1]; u8 reserved_at_3f[0x1]; + u8 entropy_force[0x1]; u8 entropy_calc[0x1]; u8 entropy_gre_calc[0x1]; - u8 reserved_at_43[0x1b]; + u8 reserved_at_43[0xf]; + u8 rx_ts_over_crc[0x1]; + u8 reserved_at_53[0xb]; u8 fcs_chk[0x1]; u8 reserved_at_5f[0x1]; }; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f8ee09c711f..436e0946d691 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -104,18 +104,7 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - union { - /** - * dma_addr_upper: might require a 64-bit - * value on 32-bit architectures. - */ - unsigned long dma_addr_upper; - /** - * For frag page support, not supported in - * 32-bit architectures with 64-bit DMA. - */ - atomic_long_t pp_frag_count; - }; + atomic_long_t pp_frag_count; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e9a48068f306..3ec42495a43a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1917,7 +1917,6 @@ enum netdev_ml_priv_type { * @sfp_bus: attached &struct sfp_bus structure. * * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock - * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the @@ -2254,7 +2253,6 @@ struct net_device { struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; - struct lock_class_key *qdisc_running_key; bool proto_down; unsigned wol_enabled:1; unsigned threaded:1; @@ -2364,13 +2362,11 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, #define netdev_lockdep_set_classes(dev) \ { \ static struct lock_class_key qdisc_tx_busylock_key; \ - static struct lock_class_key qdisc_running_key; \ static struct lock_class_key qdisc_xmit_lock_key; \ static struct lock_class_key dev_addr_list_lock_key; \ unsigned int i; \ \ (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ - (dev)->qdisc_running_key = &qdisc_running_key; \ lockdep_set_class(&(dev)->addr_list_lock, \ &dev_addr_list_lock_key); \ for (i = 0; i < (dev)->num_tx_queues; i++) \ @@ -2959,6 +2955,7 @@ struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, struct net_device *dev_get_by_name(struct net *net, const char *name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); +bool netdev_name_in_use(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); void dev_close(struct net_device *dev); @@ -4646,7 +4643,7 @@ void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ static inline void -__dev_addr_set(struct net_device *dev, const u8 *addr, size_t len) +__dev_addr_set(struct net_device *dev, const void *addr, size_t len) { memcpy(dev->dev_addr, addr, len); } @@ -4658,7 +4655,7 @@ static inline void dev_addr_set(struct net_device *dev, const u8 *addr) static inline void dev_addr_mod(struct net_device *dev, unsigned int offset, - const u8 *addr, size_t len) + const void *addr, size_t len) { memcpy(&dev->dev_addr[offset], addr, len); } @@ -4804,8 +4801,6 @@ struct netdev_nested_priv { bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); -struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, - struct list_head **iter); #ifdef CONFIG_LOCKDEP static LIST_HEAD(net_unlink_list); @@ -5240,7 +5235,7 @@ static inline void netif_keep_dst(struct net_device *dev) static inline bool netif_reduces_vlan_mtu(struct net_device *dev) { /* TODO: reserve and use an additional IFF bit, if we get more users */ - return dev->priv_flags & IFF_MACSEC; + return netif_is_macsec(dev); } extern struct pernet_operations __net_initdata loopback_net_ops; diff --git a/include/linux/of_net.h b/include/linux/of_net.h index 0797e2edb8c2..0484b613ca64 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -8,7 +8,7 @@ #include <linux/phy.h> -#ifdef CONFIG_OF +#if defined(CONFIG_OF) && defined(CONFIG_NET) #include <linux/of.h> struct net_device; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0cbc5dfe1110..2c41c8da1515 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -684,7 +684,9 @@ struct perf_event { /* * timestamp shadows the actual context timing but it can * be safely used in NMI interrupt context. It reflects the - * context time as it was when the event was last scheduled in. + * context time as it was when the event was last scheduled in, + * or when ctx_sched_in failed to schedule the event because we + * run out of PMC. * * ctx_time already accounts for ctx->timestamp. Therefore to * compute ctx_time for a sample, simply add perf_clock(). diff --git a/include/linux/platform_data/usb-omap1.h b/include/linux/platform_data/usb-omap1.h index 43b5ce139c37..878e572a78bf 100644 --- a/include/linux/platform_data/usb-omap1.h +++ b/include/linux/platform_data/usb-omap1.h @@ -48,6 +48,8 @@ struct omap_usb_config { u32 (*usb2_init)(unsigned nwires, unsigned alt_pingroup); int (*ocpi_enable)(void); + + void (*lb_reset)(void); }; #endif /* __LINUX_USB_OMAP1_H */ diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index c0475d1c9885..81cad9e1e412 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -61,7 +61,6 @@ enum qcom_scm_ice_cipher { #define QCOM_SCM_PERM_RW (QCOM_SCM_PERM_READ | QCOM_SCM_PERM_WRITE) #define QCOM_SCM_PERM_RWX (QCOM_SCM_PERM_RW | QCOM_SCM_PERM_EXEC) -#if IS_ENABLED(CONFIG_QCOM_SCM) extern bool qcom_scm_is_available(void); extern int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus); @@ -115,74 +114,4 @@ extern int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, extern int qcom_scm_lmh_profile_change(u32 profile_id); extern bool qcom_scm_lmh_dcvsh_available(void); -#else - -#include <linux/errno.h> - -static inline bool qcom_scm_is_available(void) { return false; } - -static inline int qcom_scm_set_cold_boot_addr(void *entry, - const cpumask_t *cpus) { return -ENODEV; } -static inline int qcom_scm_set_warm_boot_addr(void *entry, - const cpumask_t *cpus) { return -ENODEV; } -static inline void qcom_scm_cpu_power_down(u32 flags) {} -static inline u32 qcom_scm_set_remote_state(u32 state,u32 id) - { return -ENODEV; } - -static inline int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, - size_t size) { return -ENODEV; } -static inline int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, - phys_addr_t size) { return -ENODEV; } -static inline int qcom_scm_pas_auth_and_reset(u32 peripheral) - { return -ENODEV; } -static inline int qcom_scm_pas_shutdown(u32 peripheral) { return -ENODEV; } -static inline bool qcom_scm_pas_supported(u32 peripheral) { return false; } - -static inline int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val) - { return -ENODEV; } -static inline int qcom_scm_io_writel(phys_addr_t addr, unsigned int val) - { return -ENODEV; } - -static inline bool qcom_scm_restore_sec_cfg_available(void) { return false; } -static inline int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) - { return -ENODEV; } -static inline int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size) - { return -ENODEV; } -static inline int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare) - { return -ENODEV; } -extern inline int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size, - u32 cp_nonpixel_start, - u32 cp_nonpixel_size) - { return -ENODEV; } -static inline int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, - unsigned int *src, const struct qcom_scm_vmperm *newvm, - unsigned int dest_cnt) { return -ENODEV; } - -static inline bool qcom_scm_ocmem_lock_available(void) { return false; } -static inline int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, - u32 size, u32 mode) { return -ENODEV; } -static inline int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, - u32 offset, u32 size) { return -ENODEV; } - -static inline bool qcom_scm_ice_available(void) { return false; } -static inline int qcom_scm_ice_invalidate_key(u32 index) { return -ENODEV; } -static inline int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size, - enum qcom_scm_ice_cipher cipher, - u32 data_unit_size) { return -ENODEV; } - -static inline bool qcom_scm_hdcp_available(void) { return false; } -static inline int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, - u32 *resp) { return -ENODEV; } - -static inline int qcom_scm_qsmmu500_wait_safe_toggle(bool en) - { return -ENODEV; } - -static inline int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, - u64 limit_node, u32 node_id, u64 version) - { return -ENODEV; } - -static inline int qcom_scm_lmh_profile_change(u32 profile_id) { return -ENODEV; } - -static inline bool qcom_scm_lmh_dcvsh_available(void) { return -ENODEV; } -#endif #endif diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 4df0bf0a0864..e1bf3219b4e6 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -331,7 +331,7 @@ struct qed_eth_ops { int (*configure_arfs_searcher)(struct qed_dev *cdev, enum qed_filter_config_mode mode); int (*get_coalesce)(struct qed_dev *cdev, u16 *coal, void *handle); - int (*req_bulletin_update_mac)(struct qed_dev *cdev, u8 *mac); + int (*req_bulletin_update_mac)(struct qed_dev *cdev, const u8 *mac); }; const struct qed_eth_ops *qed_get_eth_ops(void); diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index ad220d5da18f..0dae7fcc5ef2 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1113,7 +1113,7 @@ struct qed_common_ops { * * Return: Int. */ - int (*update_mac)(struct qed_dev *cdev, u8 *mac); + int (*update_mac)(struct qed_dev *cdev, const u8 *mac); /** * update_mtu(): API to inform the change in the mtu. diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index aeb242cefebf..3b76c07fbcf8 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -662,7 +662,8 @@ struct qed_rdma_ops { u8 connection_handle, struct qed_ll2_stats *p_stats); int (*ll2_set_mac_filter)(struct qed_dev *cdev, - u8 *old_mac_address, u8 *new_mac_address); + u8 *old_mac_address, + const u8 *new_mac_address); int (*iwarp_set_engine_affin)(struct qed_dev *cdev, bool b_reset); diff --git a/include/linux/sched.h b/include/linux/sched.h index 39039ce8ac4c..c1a927ddec64 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1720,7 +1720,7 @@ extern struct pid *cad_pid; #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) -static inline bool is_percpu_thread(void) +static __always_inline bool is_percpu_thread(void) { #ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && diff --git a/include/linux/soc/marvell/octeontx2/asm.h b/include/linux/soc/marvell/octeontx2/asm.h index 0f79fd7f81a1..d683251a0b40 100644 --- a/include/linux/soc/marvell/octeontx2/asm.h +++ b/include/linux/soc/marvell/octeontx2/asm.h @@ -5,6 +5,7 @@ #ifndef __SOC_OTX2_ASM_H #define __SOC_OTX2_ASM_H +#include <linux/types.h> #if defined(CONFIG_ARM64) /* * otx2_lmt_flush is used for LMT store operation. diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index e81856c0ba13..e8ec116c916b 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -83,6 +83,11 @@ static inline u64 u64_stats_read(const u64_stats_t *p) return local64_read(&p->v); } +static inline void u64_stats_set(u64_stats_t *p, u64 val) +{ + local64_set(&p->v, val); +} + static inline void u64_stats_add(u64_stats_t *p, unsigned long val) { local64_add(val, &p->v); @@ -104,6 +109,11 @@ static inline u64 u64_stats_read(const u64_stats_t *p) return p->v; } +static inline void u64_stats_set(u64_stats_t *p, u64 val) +{ + p->v = val; +} + static inline void u64_stats_add(u64_stats_t *p, unsigned long val) { p->v += val; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 2ebef6b1a3d6..74d3c1efd9bb 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -399,9 +399,8 @@ extern struct workqueue_struct *system_freezable_power_efficient_wq; * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ -struct workqueue_struct *alloc_workqueue(const char *fmt, - unsigned int flags, - int max_active, ...); +__printf(1, 4) struct workqueue_struct * +alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); /** * alloc_ordered_workqueue - allocate an ordered workqueue diff --git a/include/net/act_api.h b/include/net/act_api.h index f19f7f4a463c..b5b624c7e488 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -30,13 +30,13 @@ struct tc_action { atomic_t tcfa_bindcnt; int tcfa_action; struct tcf_t tcfa_tm; - struct gnet_stats_basic_packed tcfa_bstats; - struct gnet_stats_basic_packed tcfa_bstats_hw; + struct gnet_stats_basic_sync tcfa_bstats; + struct gnet_stats_basic_sync tcfa_bstats_hw; struct gnet_stats_queue tcfa_qstats; struct net_rate_estimator __rcu *tcfa_rate_est; spinlock_t tcfa_lock; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; - struct gnet_stats_basic_cpu __percpu *cpu_bstats_hw; + struct gnet_stats_basic_sync __percpu *cpu_bstats; + struct gnet_stats_basic_sync __percpu *cpu_bstats_hw; struct gnet_stats_queue __percpu *cpu_qstats; struct tc_cookie __rcu *act_cookie; struct tcf_chain __rcu *goto_chain; @@ -206,7 +206,7 @@ static inline void tcf_action_update_bstats(struct tc_action *a, struct sk_buff *skb) { if (likely(a->cpu_bstats)) { - bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), skb); + bstats_update(this_cpu_ptr(a->cpu_bstats), skb); return; } spin_lock(&a->tcfa_lock); diff --git a/include/net/ax25.h b/include/net/ax25.h index 8b7eb46ad72d..03d409de61ad 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -304,7 +304,7 @@ extern spinlock_t ax25_list_lock; void ax25_cb_add(ax25_cb *); struct sock *ax25_find_listener(ax25_address *, int, struct net_device *, int); struct sock *ax25_get_socket(ax25_address *, ax25_address *, int); -ax25_cb *ax25_find_cb(ax25_address *, ax25_address *, ax25_digi *, +ax25_cb *ax25_find_cb(const ax25_address *, ax25_address *, ax25_digi *, struct net_device *); void ax25_send_to_raw(ax25_address *, struct sk_buff *, int); void ax25_destroy_socket(ax25_cb *); @@ -384,10 +384,11 @@ struct ax25_linkfail { void ax25_linkfail_register(struct ax25_linkfail *lf); void ax25_linkfail_release(struct ax25_linkfail *lf); -int __must_check ax25_listen_register(ax25_address *, struct net_device *); -void ax25_listen_release(ax25_address *, struct net_device *); +int __must_check ax25_listen_register(const ax25_address *, + struct net_device *); +void ax25_listen_release(const ax25_address *, struct net_device *); int(*ax25_protocol_function(unsigned int))(struct sk_buff *, ax25_cb *); -int ax25_listen_mine(ax25_address *, struct net_device *); +int ax25_listen_mine(const ax25_address *, struct net_device *); void ax25_link_failed(ax25_cb *, int); int ax25_protocol_is_registered(unsigned int); @@ -401,8 +402,8 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb); extern const struct header_ops ax25_header_ops; /* ax25_out.c */ -ax25_cb *ax25_send_frame(struct sk_buff *, int, ax25_address *, ax25_address *, - ax25_digi *, struct net_device *); +ax25_cb *ax25_send_frame(struct sk_buff *, int, const ax25_address *, + ax25_address *, ax25_digi *, struct net_device *); void ax25_output(ax25_cb *, int, struct sk_buff *); void ax25_kick(ax25_cb *); void ax25_transmit_buffer(ax25_cb *, struct sk_buff *, int); diff --git a/include/net/codel.h b/include/net/codel.h index a6e428f80135..5e8b181b76b8 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -102,6 +102,7 @@ static inline u32 codel_time_to_us(codel_time_t val) * @interval: width of moving time window * @mtu: device mtu, or minimal queue backlog in bytes. * @ecn: is Explicit Congestion Notification enabled + * @ce_threshold_ect1: if ce_threshold only marks ECT(1) packets */ struct codel_params { codel_time_t target; @@ -109,6 +110,7 @@ struct codel_params { codel_time_t interval; u32 mtu; bool ecn; + bool ce_threshold_ect1; }; /** diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h index d289b91dcd65..7af2c3eb3c43 100644 --- a/include/net/codel_impl.h +++ b/include/net/codel_impl.h @@ -54,6 +54,7 @@ static void codel_params_init(struct codel_params *params) params->interval = MS2TIME(100); params->target = MS2TIME(5); params->ce_threshold = CODEL_DISABLED_THRESHOLD; + params->ce_threshold_ect1 = false; params->ecn = false; } @@ -246,9 +247,20 @@ static struct sk_buff *codel_dequeue(void *ctx, vars->rec_inv_sqrt); } end: - if (skb && codel_time_after(vars->ldelay, params->ce_threshold) && - INET_ECN_set_ce(skb)) - stats->ce_mark++; + if (skb && codel_time_after(vars->ldelay, params->ce_threshold)) { + bool set_ce = true; + + if (params->ce_threshold_ect1) { + /* Note: if skb_get_dsfield() returns -1, following + * gives INET_ECN_MASK, which is != INET_ECN_ECT_1. + */ + u8 ecn = skb_get_dsfield(skb) & INET_ECN_MASK; + + set_ce = (ecn == INET_ECN_ECT_1); + } + if (set_ce && INET_ECN_set_ce(skb)) + stats->ce_mark++; + } return skb; } diff --git a/include/net/datalink.h b/include/net/datalink.h index a9663229b913..d9b7faaa539f 100644 --- a/include/net/datalink.h +++ b/include/net/datalink.h @@ -12,7 +12,7 @@ struct datalink_proto { int (*rcvfunc)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); int (*request)(struct datalink_proto *, struct sk_buff *, - unsigned char *); + const unsigned char *); struct list_head node; }; diff --git a/include/net/devlink.h b/include/net/devlink.h index a7852a257bf6..da3ceeb8b87b 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -21,45 +21,7 @@ #include <linux/xarray.h> #include <linux/firmware.h> -#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ - (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) - -struct devlink_dev_stats { - u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; - u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; -}; - -struct devlink_ops; - -struct devlink { - u32 index; - struct list_head port_list; - struct list_head rate_list; - struct list_head sb_list; - struct list_head dpipe_table_list; - struct list_head resource_list; - struct list_head param_list; - struct list_head region_list; - struct list_head reporter_list; - struct mutex reporters_lock; /* protects reporter_list */ - struct devlink_dpipe_headers *dpipe_headers; - struct list_head trap_list; - struct list_head trap_group_list; - struct list_head trap_policer_list; - const struct devlink_ops *ops; - struct xarray snapshot_ids; - struct devlink_dev_stats stats; - struct device *dev; - possible_net_t _net; - struct mutex lock; /* Serializes access to devlink instance specific objects such as - * port, sb, dpipe, resource, params, region, traps and more. - */ - u8 reload_failed:1, - reload_enabled:1; - refcount_t refcount; - struct completion comp; - char priv[0] __aligned(NETDEV_ALIGN); -}; +struct devlink; struct devlink_port_phys_attrs { u32 port_number; /* Same value as "split group". @@ -1224,6 +1186,11 @@ enum devlink_trap_group_generic_id { .min_burst = _min_burst, \ } +enum { + /* device supports reload operations */ + DEVLINK_F_RELOAD = 1UL << 0, +}; + struct devlink_ops { /** * @supported_flash_update_params: @@ -1520,34 +1487,9 @@ struct devlink_ops { struct netlink_ext_ack *extack); }; -static inline void *devlink_priv(struct devlink *devlink) -{ - BUG_ON(!devlink); - return &devlink->priv; -} - -static inline struct devlink *priv_to_devlink(void *priv) -{ - BUG_ON(!priv); - return container_of(priv, struct devlink, priv); -} - -static inline struct devlink_port * -netdev_to_devlink_port(struct net_device *dev) -{ - if (dev->netdev_ops->ndo_get_devlink_port) - return dev->netdev_ops->ndo_get_devlink_port(dev); - return NULL; -} - -static inline struct devlink *netdev_to_devlink(struct net_device *dev) -{ - struct devlink_port *devlink_port = netdev_to_devlink_port(dev); - - if (devlink_port) - return devlink_port->devlink; - return NULL; -} +void *devlink_priv(struct devlink *devlink); +struct devlink *priv_to_devlink(void *priv); +struct device *devlink_to_dev(const struct devlink *devlink); struct ib_device; @@ -1566,10 +1508,9 @@ static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, { return devlink_alloc_ns(ops, priv_size, &init_net, dev); } +void devlink_set_features(struct devlink *devlink, u64 features); void devlink_register(struct devlink *devlink); void devlink_unregister(struct devlink *devlink); -void devlink_reload_enable(struct devlink *devlink); -void devlink_reload_disable(struct devlink *devlink); void devlink_free(struct devlink *devlink); int devlink_port_register(struct devlink *devlink, struct devlink_port *devlink_port, diff --git a/include/net/dn.h b/include/net/dn.h index 56ab0726c641..ba9655b0098a 100644 --- a/include/net/dn.h +++ b/include/net/dn.h @@ -166,7 +166,7 @@ struct dn_skb_cb { int iif; }; -static inline __le16 dn_eth2dn(unsigned char *ethaddr) +static inline __le16 dn_eth2dn(const unsigned char *ethaddr) { return get_unaligned((__le16 *)(ethaddr + 4)); } diff --git a/include/net/dsa.h b/include/net/dsa.h index d784e76113b8..05ebdd8d5321 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -51,6 +51,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 +#define DSA_TAG_PROTO_RTL8_4_VALUE 24 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -77,6 +78,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, + DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, }; struct dsa_switch; @@ -645,6 +647,12 @@ struct dsa_switch_ops { int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); + void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, + struct ethtool_eth_phy_stats *phy_stats); + void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, + struct ethtool_eth_mac_stats *mac_stats); + void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, + struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*self_test)(struct dsa_switch *ds, int port, diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 1424e02cef90..7aa2b8e1fb29 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -7,14 +7,17 @@ #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> -/* Note: this used to be in include/uapi/linux/gen_stats.h */ -struct gnet_stats_basic_packed { - __u64 bytes; - __u64 packets; -}; - -struct gnet_stats_basic_cpu { - struct gnet_stats_basic_packed bstats; +/* Throughput stats. + * Must be initialized beforehand with gnet_stats_basic_sync_init(). + * + * If no reads can ever occur parallel to writes (e.g. stack-allocated + * bstats), then the internal stat values can be written to and read + * from directly. Otherwise, use _bstats_set/update() for writes and + * gnet_stats_add_basic() for reads. + */ +struct gnet_stats_basic_sync { + u64_stats_t bytes; + u64_stats_t packets; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); @@ -34,6 +37,7 @@ struct gnet_dump { struct tc_stats tc_stats; }; +void gnet_stats_basic_sync_init(struct gnet_stats_basic_sync *b); int gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr); @@ -42,41 +46,38 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr); -int gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b); -void __gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b); -int gnet_stats_copy_basic_hw(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b); +int gnet_stats_copy_basic(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running); +void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running); +int gnet_stats_copy_basic_hw(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running); int gnet_stats_copy_rate_est(struct gnet_dump *d, struct net_rate_estimator __rcu **ptr); int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue __percpu *cpu_q, struct gnet_stats_queue *q, __u32 qlen); -void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats, - const struct gnet_stats_queue __percpu *cpu_q, - const struct gnet_stats_queue *q, __u32 qlen); +void gnet_stats_add_queue(struct gnet_stats_queue *qstats, + const struct gnet_stats_queue __percpu *cpu_q, + const struct gnet_stats_queue *q); int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len); int gnet_stats_finish_copy(struct gnet_dump *d); -int gen_new_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu_bstats, +int gen_new_estimator(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt); + bool running, struct nlattr *opt); void gen_kill_estimator(struct net_rate_estimator __rcu **ptr); -int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu_bstats, +int gen_replace_estimator(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **ptr, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt); + bool running, struct nlattr *opt); bool gen_estimator_active(struct net_rate_estimator __rcu **ptr); bool gen_estimator_read(struct net_rate_estimator __rcu **ptr, struct gnet_stats_rate_est64 *sample); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index b06c2d02ec84..fa6a87246a7b 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -289,7 +289,7 @@ static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) { /* The below has to be done to allow calling inet_csk_destroy_sock */ sock_set_flag(sk, SOCK_DEAD); - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(*sk->sk_prot->orphan_count); } void inet_csk_destroy_sock(struct sock *sk); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index ba77f47ef61e..ea32393464a2 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -188,6 +188,23 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) return 0; } +static inline int skb_get_dsfield(struct sk_buff *skb) +{ + switch (skb_protocol(skb, true)) { + case cpu_to_be16(ETH_P_IP): + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + break; + return ipv4_get_dsfield(ip_hdr(skb)); + + case cpu_to_be16(ETH_P_IPV6): + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) + break; + return ipv6_get_dsfield(ipv6_hdr(skb)); + } + + return -1; +} + static inline int INET_ECN_set_ect1(struct sk_buff *skb) { switch (skb_protocol(skb, true)) { diff --git a/include/net/llc.h b/include/net/llc.h index df282d9b4017..fd1f9a3fd8dd 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -133,7 +133,7 @@ static inline void llc_sap_put(struct llc_sap *sap) struct llc_sap *llc_sap_find(unsigned char sap_value); int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, - unsigned char *dmac, unsigned char dsap); + const unsigned char *dmac, unsigned char dsap); void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb); diff --git a/include/net/llc_if.h b/include/net/llc_if.h index 8d5c543cd620..c72570a21a4f 100644 --- a/include/net/llc_if.h +++ b/include/net/llc_if.h @@ -62,7 +62,8 @@ #define LLC_STATUS_CONFLICT 7 /* disconnect conn */ #define LLC_STATUS_RESET_DONE 8 /* */ -int llc_establish_connection(struct sock *sk, u8 *lmac, u8 *dmac, u8 dsap); +int llc_establish_connection(struct sock *sk, const u8 *lmac, u8 *dmac, + u8 dsap); int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb); int llc_send_disc(struct sock *sk); #endif /* LLC_IF_H */ diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 38e4094960ce..04341d86585d 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -137,7 +137,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts); -void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, +void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, int data_len, int pad); #define NDISC_OPS_REDIRECT_DATA_SPACE 2 diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 22ced1381ede..e8e48be66755 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -144,17 +144,18 @@ struct neighbour { struct timer_list timer; unsigned long used; atomic_t probes; - __u8 flags; - __u8 nud_state; - __u8 type; - __u8 dead; + u8 nud_state; + u8 type; + u8 dead; u8 protocol; + u32 flags; seqlock_t ha_lock; unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8); struct hh_cache hh; int (*output)(struct neighbour *, struct sk_buff *); const struct neigh_ops *ops; struct list_head gc_list; + struct list_head managed_list; struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; @@ -172,7 +173,7 @@ struct pneigh_entry { struct pneigh_entry *next; possible_net_t net; struct net_device *dev; - u8 flags; + u32 flags; u8 protocol; u8 key[]; }; @@ -216,11 +217,13 @@ struct neigh_table { int gc_thresh3; unsigned long last_flush; struct delayed_work gc_work; + struct delayed_work managed_work; struct timer_list proxy_timer; struct sk_buff_head proxy_queue; atomic_t entries; atomic_t gc_entries; struct list_head gc_list; + struct list_head managed_list; rwlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; @@ -250,12 +253,21 @@ static inline void *neighbour_priv(const struct neighbour *n) } /* flags for neigh_update() */ -#define NEIGH_UPDATE_F_OVERRIDE 0x00000001 -#define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002 -#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER 0x00000004 -#define NEIGH_UPDATE_F_EXT_LEARNED 0x20000000 -#define NEIGH_UPDATE_F_ISROUTER 0x40000000 -#define NEIGH_UPDATE_F_ADMIN 0x80000000 +#define NEIGH_UPDATE_F_OVERRIDE BIT(0) +#define NEIGH_UPDATE_F_WEAK_OVERRIDE BIT(1) +#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER BIT(2) +#define NEIGH_UPDATE_F_USE BIT(3) +#define NEIGH_UPDATE_F_MANAGED BIT(4) +#define NEIGH_UPDATE_F_EXT_LEARNED BIT(5) +#define NEIGH_UPDATE_F_ISROUTER BIT(6) +#define NEIGH_UPDATE_F_ADMIN BIT(7) + +/* In-kernel representation for NDA_FLAGS_EXT flags: */ +#define NTF_OLD_MASK 0xff +#define NTF_EXT_SHIFT 8 +#define NTF_EXT_MASK (NTF_EXT_MANAGED) + +#define NTF_MANAGED (NTF_EXT_MANAGED << NTF_EXT_SHIFT) extern const struct nla_policy nda_policy[]; diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index 0fd8a4159662..ceadf8ba25a4 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -17,7 +17,6 @@ struct inet_frags_ctl; struct nft_ct_frag6_pernet { struct ctl_table_header *nf_frag_frags_hdr; struct fqdir *fqdir; - unsigned int users; }; #endif /* _NF_DEFRAG_IPV6_H */ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 148f5d8ee5ab..a16171c5fd9e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1202,7 +1202,7 @@ struct nft_object *nft_obj_lookup(const struct net *net, void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, - int event, int family, int report, gfp_t gfp); + int event, u16 flags, int family, int report, gfp_t gfp); /** * struct nft_object_type - stateful object type diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h index 832ab69efda5..4c3809e141f4 100644 --- a/include/net/netfilter/xt_rateest.h +++ b/include/net/netfilter/xt_rateest.h @@ -6,7 +6,7 @@ struct xt_rateest { /* keep lock and bstats on same cache line to speedup xt_rateest_tg() */ - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; spinlock_t lock; diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 986a2a9cfdfa..b593f95e9991 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -27,5 +27,11 @@ struct netns_nf { #if IS_ENABLED(CONFIG_DECNET) struct nf_hook_entries __rcu *hooks_decnet[NF_DN_NUMHOOKS]; #endif +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) + unsigned int defrag_ipv4_users; +#endif +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + unsigned int defrag_ipv6_users; +#endif }; #endif diff --git a/include/net/page_pool.h b/include/net/page_pool.h index a4082406a003..3855f069627f 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -216,24 +216,14 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } -#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ - (sizeof(dma_addr_t) > sizeof(unsigned long)) - static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - dma_addr_t ret = page->dma_addr; - - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) - ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; - - return ret; + return page->dma_addr; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { page->dma_addr = addr; - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) - page->dma_addr_upper = upper_32_bits(addr); } static inline void page_pool_set_frag_count(struct page *page, long nr) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 83a6d0792180..4a5833108083 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -765,7 +765,7 @@ struct tc_cookie { }; struct tc_qopt_offload_stats { - struct gnet_stats_basic_packed *bstats; + struct gnet_stats_basic_sync *bstats; struct gnet_stats_queue *qstats; }; @@ -885,7 +885,7 @@ struct tc_gred_qopt_offload_params { }; struct tc_gred_qopt_offload_stats { - struct gnet_stats_basic_packed bstats[MAX_DPs]; + struct gnet_stats_basic_sync bstats[MAX_DPs]; struct gnet_stats_queue qstats[MAX_DPs]; struct red_stats *xstats[MAX_DPs]; }; diff --git a/include/net/rose.h b/include/net/rose.h index cf517d306a28..0f0a4ce0fee7 100644 --- a/include/net/rose.h +++ b/include/net/rose.h @@ -162,8 +162,8 @@ extern int sysctl_rose_link_fail_timeout; extern int sysctl_rose_maximum_vcs; extern int sysctl_rose_window_size; -int rosecmp(rose_address *, rose_address *); -int rosecmpm(rose_address *, rose_address *, unsigned short); +int rosecmp(const rose_address *, const rose_address *); +int rosecmpm(const rose_address *, const rose_address *, unsigned short); char *rose2asc(char *buf, const rose_address *); struct sock *rose_find_socket(unsigned int, struct rose_neigh *); void rose_kill_by_neigh(struct rose_neigh *); @@ -205,8 +205,8 @@ extern const struct seq_operations rose_node_seqops; extern struct seq_operations rose_route_seqops; void rose_add_loopback_neigh(void); -int __must_check rose_add_loopback_node(rose_address *); -void rose_del_loopback_node(rose_address *); +int __must_check rose_add_loopback_node(const rose_address *); +void rose_del_loopback_node(const rose_address *); void rose_rt_device_down(struct net_device *); void rose_link_device_down(struct net_device *); struct net_device *rose_dev_first(void); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 5a011f8d394e..baad2ab4d971 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -38,6 +38,10 @@ enum qdisc_state_t { __QDISC_STATE_DEACTIVATED, __QDISC_STATE_MISSED, __QDISC_STATE_DRAINING, + /* Only for !TCQ_F_NOLOCK qdisc. Never access it directly. + * Use qdisc_run_begin/end() or qdisc_is_running() instead. + */ + __QDISC_STATE_RUNNING, }; #define QDISC_STATE_MISSED BIT(__QDISC_STATE_MISSED) @@ -97,7 +101,7 @@ struct Qdisc { struct netdev_queue *dev_queue; struct net_rate_estimator __rcu *rate_est; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; + struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; int pad; refcount_t refcnt; @@ -107,8 +111,7 @@ struct Qdisc { */ struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; struct qdisc_skb_head q; - struct gnet_stats_basic_packed bstats; - seqcount_t running; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; unsigned long state; struct Qdisc *next_sched; @@ -143,11 +146,15 @@ static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc) return NULL; } +/* For !TCQ_F_NOLOCK qdisc: callers must either call this within a qdisc + * root_lock section, or provide their own memory barriers -- ordering + * against qdisc_run_begin/end() atomic bit operations. + */ static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) return spin_is_locked(&qdisc->seqlock); - return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; + return test_bit(__QDISC_STATE_RUNNING, &qdisc->state); } static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc) @@ -167,6 +174,9 @@ static inline bool qdisc_is_empty(const struct Qdisc *qdisc) return !READ_ONCE(qdisc->q.qlen); } +/* For !TCQ_F_NOLOCK qdisc, qdisc_run_begin/end() must be invoked with + * the qdisc root lock acquired. + */ static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { @@ -206,15 +216,8 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) * after it releases the lock at the end of qdisc_run_end(). */ return spin_trylock(&qdisc->seqlock); - } else if (qdisc_is_running(qdisc)) { - return false; } - /* Variant of write_seqcount_begin() telling lockdep a trylock - * was attempted. - */ - raw_write_seqcount_begin(&qdisc->running); - seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_); - return true; + return test_and_set_bit(__QDISC_STATE_RUNNING, &qdisc->state); } static inline void qdisc_run_end(struct Qdisc *qdisc) @@ -226,7 +229,7 @@ static inline void qdisc_run_end(struct Qdisc *qdisc) &qdisc->state))) __netif_schedule(qdisc); } else { - write_seqcount_end(&qdisc->running); + clear_bit(__QDISC_STATE_RUNNING, &qdisc->state); } } @@ -592,14 +595,6 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) return qdisc_lock(root); } -static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) -{ - struct Qdisc *root = qdisc_root_sleeping(qdisc); - - ASSERT_RTNL(); - return &root->running; -} - static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc) { return qdisc->dev_queue->dev; @@ -849,14 +844,16 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, return sch->enqueue(skb, sch, to_free); } -static inline void _bstats_update(struct gnet_stats_basic_packed *bstats, +static inline void _bstats_update(struct gnet_stats_basic_sync *bstats, __u64 bytes, __u32 packets) { - bstats->bytes += bytes; - bstats->packets += packets; + u64_stats_update_begin(&bstats->syncp); + u64_stats_add(&bstats->bytes, bytes); + u64_stats_add(&bstats->packets, packets); + u64_stats_update_end(&bstats->syncp); } -static inline void bstats_update(struct gnet_stats_basic_packed *bstats, +static inline void bstats_update(struct gnet_stats_basic_sync *bstats, const struct sk_buff *skb) { _bstats_update(bstats, @@ -864,26 +861,10 @@ static inline void bstats_update(struct gnet_stats_basic_packed *bstats, skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1); } -static inline void _bstats_cpu_update(struct gnet_stats_basic_cpu *bstats, - __u64 bytes, __u32 packets) -{ - u64_stats_update_begin(&bstats->syncp); - _bstats_update(&bstats->bstats, bytes, packets); - u64_stats_update_end(&bstats->syncp); -} - -static inline void bstats_cpu_update(struct gnet_stats_basic_cpu *bstats, - const struct sk_buff *skb) -{ - u64_stats_update_begin(&bstats->syncp); - bstats_update(&bstats->bstats, skb); - u64_stats_update_end(&bstats->syncp); -} - static inline void qdisc_bstats_cpu_update(struct Qdisc *sch, const struct sk_buff *skb) { - bstats_cpu_update(this_cpu_ptr(sch->cpu_bstats), skb); + bstats_update(this_cpu_ptr(sch->cpu_bstats), skb); } static inline void qdisc_bstats_update(struct Qdisc *sch, @@ -972,10 +953,9 @@ static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen, __u32 *backlog) { struct gnet_stats_queue qstats = { 0 }; - __u32 len = qdisc_qlen_sum(sch); - __gnet_stats_copy_queue(&qstats, sch->cpu_qstats, &sch->qstats, len); - *qlen = qstats.qlen; + gnet_stats_add_queue(&qstats, sch->cpu_qstats, &sch->qstats); + *qlen = qstats.qlen + qdisc_qlen(sch); *backlog = qstats.backlog; } @@ -1316,7 +1296,7 @@ void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64); struct mini_Qdisc { struct tcf_proto *filter_list; struct tcf_block *block; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; + struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; struct rcu_head rcu; }; @@ -1324,7 +1304,7 @@ struct mini_Qdisc { static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq, const struct sk_buff *skb) { - bstats_cpu_update(this_cpu_ptr(miniq->cpu_bstats), skb); + bstats_update(this_cpu_ptr(miniq->cpu_bstats), skb); } static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq) diff --git a/include/net/sock.h b/include/net/sock.h index b0724665fa39..596ba85611bc 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -307,6 +307,7 @@ struct bpf_local_storage; * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family + * @sk_peer_lock: lock protecting @sk_peer_pid and @sk_peer_cred * @sk_peer_pid: &struct pid for this socket's peer * @sk_peer_cred: %SO_PEERCRED setting * @sk_rcvlowat: %SO_RCVLOWAT setting @@ -1234,7 +1235,7 @@ struct proto { unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ - struct percpu_counter *orphan_count; + unsigned int __percpu *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; @@ -2835,4 +2836,8 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); +int sock_get_timeout(long timeo, void *optval, bool old_timeval); +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval); + #endif /* _SOCK_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 4c2898ac6569..af77e6453b1b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -48,7 +48,9 @@ extern struct inet_hashinfo tcp_hashinfo; -extern struct percpu_counter tcp_orphan_count; +DECLARE_PER_CPU(unsigned int, tcp_orphan_count); +int tcp_orphan_count_sum(void); + void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) @@ -290,19 +292,6 @@ static inline bool tcp_out_of_memory(struct sock *sk) void sk_forced_mem_schedule(struct sock *sk, int size); -static inline bool tcp_too_many_orphans(struct sock *sk, int shift) -{ - struct percpu_counter *ocp = sk->sk_prot->orphan_count; - int orphans = percpu_counter_read_positive(ocp); - - if (orphans << shift > sysctl_tcp_max_orphans) { - orphans = percpu_counter_sum_positive(ocp); - if (orphans << shift > sysctl_tcp_max_orphans) - return true; - } - return false; -} - bool tcp_check_oom(struct sock *sk, int shift); diff --git a/include/soc/fsl/dpaa2-io.h b/include/soc/fsl/dpaa2-io.h index c9d849924f89..4bf62de2e00e 100644 --- a/include/soc/fsl/dpaa2-io.h +++ b/include/soc/fsl/dpaa2-io.h @@ -44,6 +44,7 @@ struct device; * @regs_cinh: The cache inhibited regs * @dpio_id: The dpio index * @qman_version: The qman version + * @qman_clk: The qman clock frequency in Hz * * Describes the attributes and features of the DPIO object. */ @@ -55,6 +56,7 @@ struct dpaa2_io_desc { void __iomem *regs_cinh; int dpio_id; u32 qman_version; + u32 qman_clk; }; struct dpaa2_io *dpaa2_io_create(const struct dpaa2_io_desc *desc, @@ -129,4 +131,11 @@ int dpaa2_io_query_fq_count(struct dpaa2_io *d, u32 fqid, u32 *fcnt, u32 *bcnt); int dpaa2_io_query_bp_count(struct dpaa2_io *d, u16 bpid, u32 *num); + +int dpaa2_io_set_irq_coalescing(struct dpaa2_io *d, u32 irq_holdoff); +void dpaa2_io_get_irq_coalescing(struct dpaa2_io *d, u32 *irq_holdoff); +void dpaa2_io_set_adaptive_coalescing(struct dpaa2_io *d, + int use_adaptive_rx_coalesce); +int dpaa2_io_get_adaptive_coalescing(struct dpaa2_io *d); +void dpaa2_io_update_net_dim(struct dpaa2_io *d, __u64 frames, __u64 bytes); #endif /* __FSL_DPAA2_IO_H */ diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 06706a9fd5b1..d7055b41982d 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -89,15 +89,6 @@ /* Source PGIDs, one per physical port */ #define PGID_SRC 80 -#define IFH_TAG_TYPE_C 0 -#define IFH_TAG_TYPE_S 1 - -#define IFH_REW_OP_NOOP 0x0 -#define IFH_REW_OP_DSCP 0x1 -#define IFH_REW_OP_ONE_STEP_PTP 0x2 -#define IFH_REW_OP_TWO_STEP_PTP 0x3 -#define IFH_REW_OP_ORIGIN_PTP 0x5 - #define OCELOT_NUM_TC 8 #define OCELOT_SPEED_2500 0 @@ -603,10 +594,10 @@ struct ocelot_port { /* The VLAN ID that will be transmitted as untagged, on egress */ struct ocelot_vlan native_vlan; + unsigned int ptp_skbs_in_flight; u8 ptp_cmd; struct sk_buff_head tx_skbs; u8 ts_id; - spinlock_t ts_id_lock; phy_interface_t phy_mode; @@ -680,6 +671,9 @@ struct ocelot { struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_info; struct hwtstamp_config hwtstamp_config; + unsigned int ptp_skbs_in_flight; + /* Protects the 2-step TX timestamp ID logic */ + spinlock_t ts_id_lock; /* Protects the PTP interface state */ struct mutex ptp_lock; /* Protects the PTP clock */ @@ -692,15 +686,6 @@ struct ocelot_policer { u32 burst; /* bytes */ }; -struct ocelot_skb_cb { - struct sk_buff *clone; - u8 ptp_cmd; - u8 ts_id; -}; - -#define OCELOT_SKB_CB(skb) \ - ((struct ocelot_skb_cb *)((skb)->cb)) - #define ocelot_read_ix(ocelot, reg, gi, ri) __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri)) #define ocelot_read_gix(ocelot, reg, gi) __ocelot_read_ix(ocelot, reg, reg##_GSZ * (gi)) #define ocelot_read_rix(ocelot, reg, ri) __ocelot_read_ix(ocelot, reg, reg##_RSZ * (ri)) @@ -752,8 +737,6 @@ u32 __ocelot_target_read_ix(struct ocelot *ocelot, enum ocelot_target target, void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, u32 val, u32 reg, u32 offset); -#if IS_ENABLED(CONFIG_MSCC_OCELOT_SWITCH_LIB) - /* Packet I/O */ bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, @@ -761,36 +744,6 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp); -u32 ocelot_ptp_rew_op(struct sk_buff *skb); -#else - -static inline bool ocelot_can_inject(struct ocelot *ocelot, int grp) -{ - return false; -} - -static inline void ocelot_port_inject_frame(struct ocelot *ocelot, int port, - int grp, u32 rew_op, - struct sk_buff *skb) -{ -} - -static inline int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, - struct sk_buff **skb) -{ - return -EIO; -} - -static inline void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp) -{ -} - -static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb) -{ - return 0; -} -#endif - /* Hardware initialization */ int ocelot_regfields_init(struct ocelot *ocelot, const struct reg_field *const regfields); diff --git a/include/soc/mscc/ocelot_ptp.h b/include/soc/mscc/ocelot_ptp.h index ded497d72bdb..f085884b1fa2 100644 --- a/include/soc/mscc/ocelot_ptp.h +++ b/include/soc/mscc/ocelot_ptp.h @@ -13,6 +13,9 @@ #include <linux/ptp_clock_kernel.h> #include <soc/mscc/ocelot.h> +#define OCELOT_MAX_PTP_ID 63 +#define OCELOT_PTP_FIFO_SIZE 128 + #define PTP_PIN_CFG_RSZ 0x20 #define PTP_PIN_TOD_SEC_MSB_RSZ PTP_PIN_CFG_RSZ #define PTP_PIN_TOD_SEC_LSB_RSZ PTP_PIN_CFG_RSZ diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index d45608fc4baf..eeb1142aa1b1 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -704,7 +704,7 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot, int ocelot_vcap_filter_del(struct ocelot *ocelot, struct ocelot_vcap_filter *rule); struct ocelot_vcap_filter * -ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, int id, - bool tc_offload); +ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, + unsigned long cookie, bool tc_offload); #endif /* _OCELOT_VCAP_H_ */ diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index 01570dbda503..0e45963bb767 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -224,6 +224,7 @@ struct hda_codec { #endif /* misc flags */ + unsigned int configured:1; /* codec was configured */ unsigned int in_freeing:1; /* being released */ unsigned int registered:1; /* codec was registered */ unsigned int display_power_control:1; /* needs display power */ diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 9a448fe9355d..920b6a303d60 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -178,7 +178,7 @@ TRACE_EVENT(cachefiles_unlink, ), TP_fast_assign( - __entry->obj = obj->fscache.debug_id; + __entry->obj = obj ? obj->fscache.debug_id : UINT_MAX; __entry->de = de; __entry->why = why; ), @@ -205,7 +205,7 @@ TRACE_EVENT(cachefiles_rename, ), TP_fast_assign( - __entry->obj = obj->fscache.debug_id; + __entry->obj = obj ? obj->fscache.debug_id : UINT_MAX; __entry->de = de; __entry->to = to; __entry->why = why; @@ -305,7 +305,7 @@ TRACE_EVENT(cachefiles_mark_buried, ), TP_fast_assign( - __entry->obj = obj->fscache.debug_id; + __entry->obj = obj ? obj->fscache.debug_id : UINT_MAX; __entry->de = de; __entry->why = why; ), diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h index 44d8e2981065..2814f188d98c 100644 --- a/include/trace/events/devlink.h +++ b/include/trace/events/devlink.h @@ -21,9 +21,9 @@ TRACE_EVENT(devlink_hwmsg, TP_ARGS(devlink, incoming, type, buf, len), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __field(bool, incoming) __field(unsigned long, type) __dynamic_array(u8, buf, len) @@ -31,9 +31,9 @@ TRACE_EVENT(devlink_hwmsg, ), TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __entry->incoming = incoming; __entry->type = type; memcpy(__get_dynamic_array(buf), buf, len); @@ -55,17 +55,17 @@ TRACE_EVENT(devlink_hwerr, TP_ARGS(devlink, err, msg), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __field(int, err) __string(msg, msg) ), TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __entry->err = err; __assign_str(msg, msg); ), @@ -85,17 +85,17 @@ TRACE_EVENT(devlink_health_report, TP_ARGS(devlink, reporter_name, msg), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __string(reporter_name, msg) __string(msg, msg) ), TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __assign_str(reporter_name, reporter_name); __assign_str(msg, msg); ), @@ -116,18 +116,18 @@ TRACE_EVENT(devlink_health_recover_aborted, TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __string(reporter_name, reporter_name) __field(bool, health_state) __field(u64, time_since_last_recover) ), TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __assign_str(reporter_name, reporter_name); __entry->health_state = health_state; __entry->time_since_last_recover = time_since_last_recover; @@ -150,17 +150,17 @@ TRACE_EVENT(devlink_health_reporter_state_update, TP_ARGS(devlink, reporter_name, new_state), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __string(reporter_name, reporter_name) __field(u8, new_state) ), TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __assign_str(reporter_name, reporter_name); __entry->new_state = new_state; ), @@ -181,9 +181,9 @@ TRACE_EVENT(devlink_trap_report, TP_ARGS(devlink, skb, metadata), TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) + __string(bus_name, devlink_to_dev(devlink)->bus->name) + __string(dev_name, dev_name(devlink_to_dev(devlink))) + __string(driver_name, devlink_to_dev(devlink)->driver->name) __string(trap_name, metadata->trap_name) __string(trap_group_name, metadata->trap_group_name) __dynamic_array(char, input_dev_name, IFNAMSIZ) @@ -192,9 +192,9 @@ TRACE_EVENT(devlink_trap_report, TP_fast_assign( struct net_device *input_dev = metadata->input_dev; - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(bus_name, devlink_to_dev(devlink)->bus->name); + __assign_str(dev_name, dev_name(devlink_to_dev(devlink))); + __assign_str(driver_name, devlink_to_dev(devlink)->driver->name); __assign_str(trap_name, metadata->trap_name); __assign_str(trap_group_name, metadata->trap_group_name); __assign_str(input_dev_name, diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h index 6135d92e0d47..daf82a230c0e 100644 --- a/include/uapi/linux/hyperv.h +++ b/include/uapi/linux/hyperv.h @@ -26,7 +26,7 @@ #ifndef _UAPI_HYPERV_H #define _UAPI_HYPERV_H -#include <linux/uuid.h> +#include <linux/types.h> /* * Framework version for util services. diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 5f589c7a8382..5da4ee234e0b 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -86,6 +86,7 @@ * over Ethernet */ #define ETH_P_PAE 0x888E /* Port Access Entity (IEEE 802.1X) */ +#define ETH_P_REALTEK 0x8899 /* Multiple proprietary protocols */ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 00a60695fa53..db05fb55055e 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -31,6 +31,7 @@ enum { NDA_PROTOCOL, /* Originator of entry */ NDA_NH_ID, NDA_FDB_EXT_ATTRS, + NDA_FLAGS_EXT, __NDA_MAX }; @@ -40,14 +41,16 @@ enum { * Neighbor Cache Entry Flags */ -#define NTF_USE 0x01 -#define NTF_SELF 0x02 -#define NTF_MASTER 0x04 -#define NTF_PROXY 0x08 /* == ATF_PUBL */ -#define NTF_EXT_LEARNED 0x10 -#define NTF_OFFLOADED 0x20 -#define NTF_STICKY 0x40 -#define NTF_ROUTER 0x80 +#define NTF_USE (1 << 0) +#define NTF_SELF (1 << 1) +#define NTF_MASTER (1 << 2) +#define NTF_PROXY (1 << 3) /* == ATF_PUBL */ +#define NTF_EXT_LEARNED (1 << 4) +#define NTF_OFFLOADED (1 << 5) +#define NTF_STICKY (1 << 6) +#define NTF_ROUTER (1 << 7) +/* Extended flags under NDA_FLAGS_EXT: */ +#define NTF_EXT_MANAGED (1 << 0) /* * Neighbor Cache Entry States. @@ -65,12 +68,22 @@ enum { #define NUD_PERMANENT 0x80 #define NUD_NONE 0x00 -/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change - * and make no address resolution or NUD. - * NUD_PERMANENT also cannot be deleted by garbage collectors. +/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change and make no + * address resolution or NUD. + * + * NUD_PERMANENT also cannot be deleted by garbage collectors. This holds true + * for dynamic entries with NTF_EXT_LEARNED flag as well. However, upon carrier + * down event, NUD_PERMANENT entries are not flushed whereas NTF_EXT_LEARNED + * flagged entries explicitly are (which is also consistent with the routing + * subsystem). + * * When NTF_EXT_LEARNED is set for a bridge fdb entry the different cache entry * states don't make sense and thus are ignored. Such entries don't age and * can roam. + * + * NTF_EXT_MANAGED flagged neigbor entries are managed by the kernel on behalf + * of a user space control plane, and automatically refreshed so that (if + * possible) they remain in NUD_REACHABLE state. */ struct nda_cacheinfo { diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index ec88590b3198..6be9a84cccfa 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -840,6 +840,7 @@ enum { TCA_FQ_CODEL_CE_THRESHOLD, TCA_FQ_CODEL_DROP_BATCH_SIZE, TCA_FQ_CODEL_MEMORY_LIMIT, + TCA_FQ_CODEL_CE_THRESHOLD_ECT1, __TCA_FQ_CODEL_MAX }; diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index b175bd0165a1..20f33b27787f 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -84,17 +84,28 @@ enum { SMC_NLA_SYS_IS_ISM_V2, /* u8 */ SMC_NLA_SYS_LOCAL_HOST, /* string */ SMC_NLA_SYS_SEID, /* string */ + SMC_NLA_SYS_IS_SMCR_V2, /* u8 */ __SMC_NLA_SYS_MAX, SMC_NLA_SYS_MAX = __SMC_NLA_SYS_MAX - 1 }; -/* SMC_NLA_LGR_V2 nested attributes */ +/* SMC_NLA_LGR_D_V2_COMMON and SMC_NLA_LGR_R_V2_COMMON nested attributes */ enum { SMC_NLA_LGR_V2_VER, /* u8 */ SMC_NLA_LGR_V2_REL, /* u8 */ SMC_NLA_LGR_V2_OS, /* u8 */ SMC_NLA_LGR_V2_NEG_EID, /* string */ SMC_NLA_LGR_V2_PEER_HOST, /* string */ + __SMC_NLA_LGR_V2_MAX, + SMC_NLA_LGR_V2_MAX = __SMC_NLA_LGR_V2_MAX - 1 +}; + +/* SMC_NLA_LGR_R_V2 nested attributes */ +enum { + SMC_NLA_LGR_R_V2_UNSPEC, + SMC_NLA_LGR_R_V2_DIRECT, /* u8 */ + __SMC_NLA_LGR_R_V2_MAX, + SMC_NLA_LGR_R_V2_MAX = __SMC_NLA_LGR_R_V2_MAX - 1 }; /* SMC_GEN_LGR_SMCR attributes */ @@ -106,6 +117,8 @@ enum { SMC_NLA_LGR_R_PNETID, /* string */ SMC_NLA_LGR_R_VLAN_ID, /* u8 */ SMC_NLA_LGR_R_CONNS_NUM, /* u32 */ + SMC_NLA_LGR_R_V2_COMMON, /* nest */ + SMC_NLA_LGR_R_V2, /* nest */ __SMC_NLA_LGR_R_MAX, SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1 }; @@ -138,7 +151,7 @@ enum { SMC_NLA_LGR_D_PNETID, /* string */ SMC_NLA_LGR_D_CHID, /* u16 */ SMC_NLA_LGR_D_PAD, /* flag */ - SMC_NLA_LGR_V2, /* nest */ + SMC_NLA_LGR_D_V2_COMMON, /* nest */ __SMC_NLA_LGR_D_MAX, SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1 }; diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index 46918a1852d7..c60ca33eac59 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -64,7 +64,7 @@ * timeout for a STREAM socket. */ -#define SO_VM_SOCKETS_CONNECT_TIMEOUT 6 +#define SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD 6 /* Option name for using non-blocking send/receive. Use as the option name * for setsockopt(3) or getsockopt(3) to set or get the non-blocking @@ -81,6 +81,17 @@ #define SO_VM_SOCKETS_NONBLOCK_TXRX 7 +#define SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW 8 + +#if !defined(__KERNEL__) +#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) +#define SO_VM_SOCKETS_CONNECT_TIMEOUT SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD +#else +#define SO_VM_SOCKETS_CONNECT_TIMEOUT \ + (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD : SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW) +#endif +#endif + /* The vSocket equivalent of INADDR_ANY. This works for the svm_cid field of * sockaddr_vm and indicates the context ID of the current endpoint. */ diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index b96c1ea7166d..eda0426ec4c2 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -213,13 +213,13 @@ enum { XFRM_MSG_GETSPDINFO, #define XFRM_MSG_GETSPDINFO XFRM_MSG_GETSPDINFO + XFRM_MSG_MAPPING, +#define XFRM_MSG_MAPPING XFRM_MSG_MAPPING + XFRM_MSG_SETDEFAULT, #define XFRM_MSG_SETDEFAULT XFRM_MSG_SETDEFAULT XFRM_MSG_GETDEFAULT, #define XFRM_MSG_GETDEFAULT XFRM_MSG_GETDEFAULT - - XFRM_MSG_MAPPING, -#define XFRM_MSG_MAPPING XFRM_MSG_MAPPING __XFRM_MSG_MAX }; #define XFRM_MSG_MAX (__XFRM_MSG_MAX - 1) @@ -514,9 +514,12 @@ struct xfrm_user_offload { #define XFRM_OFFLOAD_INBOUND 2 struct xfrm_userpolicy_default { -#define XFRM_USERPOLICY_DIRMASK_MAX (sizeof(__u8) * 8) - __u8 dirmask; - __u8 action; +#define XFRM_USERPOLICY_UNSPEC 0 +#define XFRM_USERPOLICY_BLOCK 1 +#define XFRM_USERPOLICY_ACCEPT 2 + __u8 in; + __u8 fwd; + __u8 out; }; #ifndef __KERNEL__ diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index db28e79b77ee..a3584a357f35 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -52,12 +52,12 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order); #if defined(CONFIG_XEN_PV) int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages); + unsigned int domid, bool no_translate); #else static inline int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, unsigned int domid, - bool no_translate, struct page **pages) + bool no_translate) { BUG(); return 0; @@ -134,7 +134,7 @@ static inline int xen_remap_domain_gfn_array(struct vm_area_struct *vma, */ BUG_ON(err_ptr == NULL); return xen_remap_pfn(vma, addr, gfn, nr, err_ptr, prot, domid, - false, pages); + false); } /* @@ -146,7 +146,6 @@ static inline int xen_remap_domain_gfn_array(struct vm_area_struct *vma, * @err_ptr: Returns per-MFN error status. * @prot: page protection mask * @domid: Domain owning the pages - * @pages: Array of pages if this domain has an auto-translated physmap * * @mfn and @err_ptr may point to the same buffer, the MFNs will be * overwritten by the error codes after they are mapped. @@ -157,14 +156,13 @@ static inline int xen_remap_domain_gfn_array(struct vm_area_struct *vma, static inline int xen_remap_domain_mfn_array(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *mfn, int nr, int *err_ptr, - pgprot_t prot, unsigned int domid, - struct page **pages) + pgprot_t prot, unsigned int domid) { if (xen_feature(XENFEAT_auto_translated_physmap)) return -EOPNOTSUPP; return xen_remap_pfn(vma, addr, mfn, nr, err_ptr, prot, domid, - true, pages); + true); } /* xen_remap_domain_gfn_range() - map a range of foreign frames @@ -188,8 +186,7 @@ static inline int xen_remap_domain_gfn_range(struct vm_area_struct *vma, if (xen_feature(XENFEAT_auto_translated_physmap)) return -EOPNOTSUPP; - return xen_remap_pfn(vma, addr, &gfn, nr, NULL, prot, domid, false, - pages); + return xen_remap_pfn(vma, addr, &gfn, nr, NULL, prot, domid, false); } int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 09a3fd97d329..6e75bbee39f0 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -63,7 +63,8 @@ static inline int stack_map_data_size(struct bpf_map *map) static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) { - u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; + u64 elem_size = sizeof(struct stack_map_bucket) + + (u64)smap->map.value_size; int err; smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries, diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index df1ccf4558f8..2a9695ccb65f 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -311,17 +311,19 @@ static struct cpuset top_cpuset = { if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* - * There are two global locks guarding cpuset structures - cpuset_mutex and + * There are two global locks guarding cpuset structures - cpuset_rwsem and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this - * comment. + * comment. The cpuset code uses only cpuset_rwsem write lock. Other + * kernel subsystems can use cpuset_read_lock()/cpuset_read_unlock() to + * prevent change to cpuset structures. * * A task must hold both locks to modify cpusets. If a task holds - * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it + * cpuset_rwsem, it blocks others wanting that rwsem, ensuring that it * is the only task able to also acquire callback_lock and be able to * modify cpusets. It can perform various checks on the cpuset structure * first, knowing nothing will change. It can also allocate memory while - * just holding cpuset_mutex. While it is performing these checks, various + * just holding cpuset_rwsem. While it is performing these checks, various * callback routines can briefly acquire callback_lock to query cpusets. * Once it is ready to make the changes, it takes callback_lock, blocking * everyone else. @@ -393,7 +395,7 @@ static inline bool is_in_v2_mode(void) * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * - * Call with callback_lock or cpuset_mutex held. + * Call with callback_lock or cpuset_rwsem held. */ static void guarantee_online_cpus(struct task_struct *tsk, struct cpumask *pmask) @@ -435,7 +437,7 @@ out_unlock: * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * - * Call with callback_lock or cpuset_mutex held. + * Call with callback_lock or cpuset_rwsem held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { @@ -447,7 +449,7 @@ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) /* * update task's spread flag if cpuset's page/slab spread flag is set * - * Call with callback_lock or cpuset_mutex held. + * Call with callback_lock or cpuset_rwsem held. */ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) @@ -468,7 +470,7 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs, * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags - * are only set if the other's are set. Call holding cpuset_mutex. + * are only set if the other's are set. Call holding cpuset_rwsem. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) @@ -577,7 +579,7 @@ static inline void free_cpuset(struct cpuset *cs) * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes - * cpuset_mutex held. + * cpuset_rwsem held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the @@ -700,7 +702,7 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, rcu_read_unlock(); } -/* Must be called with cpuset_mutex held. */ +/* Must be called with cpuset_rwsem held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ @@ -726,7 +728,7 @@ static inline int nr_cpusets(void) * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * - * Must be called with cpuset_mutex held. + * Must be called with cpuset_rwsem held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a @@ -1005,7 +1007,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * - * Call with cpuset_mutex held. Takes cpus_read_lock(). + * Call with cpuset_rwsem held. Takes cpus_read_lock(). */ static void rebuild_sched_domains_locked(void) { @@ -1078,7 +1080,7 @@ void rebuild_sched_domains(void) * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed * * Iterate through each task of @cs updating its cpus_allowed to the - * effective cpuset's. As this function is called with cpuset_mutex held, + * effective cpuset's. As this function is called with cpuset_rwsem held, * cpuset membership stays stable. */ static void update_tasks_cpumask(struct cpuset *cs) @@ -1347,7 +1349,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, * * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. * - * Called with cpuset_mutex held + * Called with cpuset_rwsem held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) { @@ -1704,12 +1706,12 @@ static void *cpuset_being_rebound; * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the - * effective cpuset's. As this function is called with cpuset_mutex held, + * effective cpuset's. As this function is called with cpuset_rwsem held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { - static nodemask_t newmems; /* protected by cpuset_mutex */ + static nodemask_t newmems; /* protected by cpuset_rwsem */ struct css_task_iter it; struct task_struct *task; @@ -1722,7 +1724,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold - * the global cpuset_mutex, we know that no other rebind effort + * the global cpuset_rwsem, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. @@ -1768,7 +1770,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * * On legacy hierarchy, effective_mems will be the same with mems_allowed. * - * Called with cpuset_mutex held + * Called with cpuset_rwsem held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { @@ -1821,7 +1823,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * - * Call with cpuset_mutex held. May take callback_lock during call. + * Call with cpuset_rwsem held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. @@ -1911,7 +1913,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this - * function is called with cpuset_mutex held, cpuset membership stays + * function is called with cpuset_rwsem held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) @@ -1931,7 +1933,7 @@ static void update_tasks_flags(struct cpuset *cs) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * - * Call with cpuset_mutex held. + * Call with cpuset_rwsem held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, @@ -1980,7 +1982,7 @@ out: * cs: the cpuset to update * new_prs: new partition root state * - * Call with cpuset_mutex held. + * Call with cpuset_rwsem held. */ static int update_prstate(struct cpuset *cs, int new_prs) { @@ -2167,7 +2169,7 @@ static int fmeter_getrate(struct fmeter *fmp) static struct cpuset *cpuset_attach_old_cs; -/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ +/* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; @@ -2219,7 +2221,7 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset) } /* - * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach() + * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ @@ -2227,7 +2229,7 @@ static cpumask_var_t cpus_attach; static void cpuset_attach(struct cgroup_taskset *tset) { - /* static buf protected by cpuset_mutex */ + /* static buf protected by cpuset_rwsem */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; @@ -2417,7 +2419,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after - * grabbing cpuset_mutex anyway. This only happens on the legacy + * grabbing cpuset_rwsem anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); @@ -3672,7 +3674,7 @@ void __cpuset_memory_pressure_bump(void) * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, - * and we take cpuset_mutex, keeping cpuset_attach() from changing it + * and we take cpuset_rwsem, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, diff --git a/kernel/events/core.c b/kernel/events/core.c index 20367196fa9a..ef29882c9dc4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3707,6 +3707,29 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx, return 0; } +static inline bool event_update_userpage(struct perf_event *event) +{ + if (likely(!atomic_read(&event->mmap_count))) + return false; + + perf_event_update_time(event); + perf_set_shadow_time(event, event->ctx); + perf_event_update_userpage(event); + + return true; +} + +static inline void group_update_userpage(struct perf_event *group_event) +{ + struct perf_event *event; + + if (!event_update_userpage(group_event)) + return; + + for_each_sibling_event(event, group_event) + event_update_userpage(event); +} + static int merge_sched_in(struct perf_event *event, void *data) { struct perf_event_context *ctx = event->ctx; @@ -3725,14 +3748,15 @@ static int merge_sched_in(struct perf_event *event, void *data) } if (event->state == PERF_EVENT_STATE_INACTIVE) { + *can_add_hw = 0; if (event->attr.pinned) { perf_cgroup_event_disable(event, ctx); perf_event_set_state(event, PERF_EVENT_STATE_ERROR); + } else { + ctx->rotate_necessary = 1; + perf_mux_hrtimer_restart(cpuctx); + group_update_userpage(event); } - - *can_add_hw = 0; - ctx->rotate_necessary = 1; - perf_mux_hrtimer_restart(cpuctx); } return 0; @@ -6324,6 +6348,8 @@ accounting: ring_buffer_attach(event, rb); + perf_event_update_time(event); + perf_set_shadow_time(event, event->ctx); perf_event_init_userpage(event); perf_event_update_userpage(event); } else { diff --git a/kernel/module.c b/kernel/module.c index 40ec9a030eec..5c26a76e800b 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -4489,8 +4489,10 @@ static void cfi_init(struct module *mod) /* Fix init/exit functions to point to the CFI jump table */ if (init) mod->init = *init; +#ifdef CONFIG_MODULE_UNLOAD if (exit) mod->exit = *exit; +#endif cfi_module_add(mod, module_addr_min); #endif diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 49716228efb4..17a653b67006 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -173,16 +173,22 @@ static ssize_t sched_scaling_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { char buf[16]; + unsigned int scaling; if (cnt > 15) cnt = 15; if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; + buf[cnt] = '\0'; - if (kstrtouint(buf, 10, &sysctl_sched_tunable_scaling)) + if (kstrtouint(buf, 10, &scaling)) return -EINVAL; + if (scaling >= SCHED_TUNABLESCALING_END) + return -EINVAL; + + sysctl_sched_tunable_scaling = scaling; if (sched_update_scaling()) return -EINVAL; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ff69f245b939..f6a05d9b5443 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4936,8 +4936,12 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) /* update hierarchical throttle state */ walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); - if (!cfs_rq->load.weight) + /* Nothing to run but something to decay (on_list)? Complete the branch */ + if (!cfs_rq->load.weight) { + if (cfs_rq->on_list) + goto unthrottle_throttle; return; + } task_delta = cfs_rq->h_nr_running; idle_task_delta = cfs_rq->idle_h_nr_running; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 33a6b4a2443d..1b3eb1e9531f 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4830,8 +4830,16 @@ void show_workqueue_state(void) for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, flags); - if (pwq->nr_active || !list_empty(&pwq->inactive_works)) + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { + /* + * Defer printing to avoid deadlocks in console + * drivers that queue work while holding locks + * also taken in their write paths. + */ + printk_deferred_enter(); show_pwq(pwq); + printk_deferred_exit(); + } raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); /* * We could be printing a lot from atomic context, e.g. @@ -4849,7 +4857,12 @@ void show_workqueue_state(void) raw_spin_lock_irqsave(&pool->lock, flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; - + /* + * Defer printing to avoid deadlocks in console drivers that + * queue work while holding locks also taken in their write + * paths. + */ + printk_deferred_enter(); pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" hung=%us workers=%d", @@ -4864,6 +4877,7 @@ void show_workqueue_state(void) first = false; } pr_cont("\n"); + printk_deferred_exit(); next_pool: raw_spin_unlock_irqrestore(&pool->lock, flags); /* diff --git a/lib/Makefile b/lib/Makefile index 5efd1b435a37..a841be5244ac 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -351,7 +351,7 @@ obj-$(CONFIG_OBJAGG) += objagg.o obj-$(CONFIG_PLDMFW) += pldmfw/ # KUnit tests -CFLAGS_bitfield_kunit.o := $(call cc-option,-Wframe-larger-than=10240) +CFLAGS_bitfield_kunit.o := $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_BITFIELD_KUNIT) += bitfield_kunit.o obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o diff --git a/lib/kunit/executor_test.c b/lib/kunit/executor_test.c index cdbe54b16501..e14a18af573d 100644 --- a/lib/kunit/executor_test.c +++ b/lib/kunit/executor_test.c @@ -116,8 +116,8 @@ static void kfree_at_end(struct kunit *test, const void *to_free) /* kfree() handles NULL already, but avoid allocating a no-op cleanup. */ if (IS_ERR_OR_NULL(to_free)) return; - kunit_alloc_and_get_resource(test, NULL, kfree_res_free, GFP_KERNEL, - (void *)to_free); + kunit_alloc_resource(test, NULL, kfree_res_free, GFP_KERNEL, + (void *)to_free); } static struct kunit_suite *alloc_fake_suite(struct kunit *test, diff --git a/net/802/hippi.c b/net/802/hippi.c index f80b33a8f7e0..887e73d520e4 100644 --- a/net/802/hippi.c +++ b/net/802/hippi.c @@ -121,7 +121,7 @@ int hippi_mac_addr(struct net_device *dev, void *p) struct sockaddr *addr = p; if (netif_running(dev)) return -EBUSY; - memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + dev_addr_set(dev, addr->sa_data); return 0; } EXPORT_SYMBOL(hippi_mac_addr); diff --git a/net/802/p8022.c b/net/802/p8022.c index a6585627051d..79c23173116c 100644 --- a/net/802/p8022.c +++ b/net/802/p8022.c @@ -23,7 +23,7 @@ #include <net/p8022.h> static int p8022_request(struct datalink_proto *dl, struct sk_buff *skb, - unsigned char *dest) + const unsigned char *dest) { llc_build_and_send_ui_pkt(dl->sap, skb, dest, dl->sap->laddr.lsap); return 0; diff --git a/net/802/psnap.c b/net/802/psnap.c index 4492e8d7ad20..1406bfdbda13 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -79,7 +79,7 @@ drop: * Put a SNAP header on a frame and pass to 802.2 */ static int snap_request(struct datalink_proto *dl, - struct sk_buff *skb, u8 *dest) + struct sk_buff *skb, const u8 *dest) { memcpy(skb_push(skb, 5), dl->type, 5); llc_build_and_send_ui_pkt(snap_sap, skb, dest, snap_sap->laddr.lsap); diff --git a/net/atm/br2684.c b/net/atm/br2684.c index dd2a8dabed84..11854fde52db 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -578,7 +578,7 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) if (list_empty(&brdev->brvccs) && !brdev->mac_was_set) { unsigned char *esi = atmvcc->dev->esi; if (esi[0] | esi[1] | esi[2] | esi[3] | esi[4] | esi[5]) - memcpy(net_dev->dev_addr, esi, net_dev->addr_len); + dev_addr_set(net_dev, esi); else net_dev->dev_addr[2] = 1; } diff --git a/net/atm/lec.c b/net/atm/lec.c index 7226c784dbe0..8eaea4a4bbd6 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -355,8 +355,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) pr_debug("%s: msg from zeppelin:%d\n", dev->name, mesg->type); switch (mesg->type) { case l_set_mac_addr: - for (i = 0; i < 6; i++) - dev->dev_addr[i] = mesg->content.normal.mac_addr[i]; + eth_hw_addr_set(dev, mesg->content.normal.mac_addr); break; case l_del_mac_addr: for (i = 0; i < 6; i++) diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 2631efc6e359..2f34bbdde0e8 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -202,7 +202,7 @@ struct sock *ax25_get_socket(ax25_address *my_addr, ax25_address *dest_addr, * Find an AX.25 control block given both ends. It will only pick up * floating AX.25 control blocks or non Raw socket bound control blocks. */ -ax25_cb *ax25_find_cb(ax25_address *src_addr, ax25_address *dest_addr, +ax25_cb *ax25_find_cb(const ax25_address *src_addr, ax25_address *dest_addr, ax25_digi *digi, struct net_device *dev) { ax25_cb *s; diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index 4ac2e0847652..d0a043a51848 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -35,7 +35,7 @@ ax25_dev *ax25_addr_ax25dev(ax25_address *addr) spin_lock_bh(&ax25_dev_lock); for (ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next) - if (ax25cmp(addr, (ax25_address *)ax25_dev->dev->dev_addr) == 0) { + if (ax25cmp(addr, (const ax25_address *)ax25_dev->dev->dev_addr) == 0) { res = ax25_dev; } spin_unlock_bh(&ax25_dev_lock); diff --git a/net/ax25/ax25_iface.c b/net/ax25/ax25_iface.c index b4083f30af0d..979bc4b828a0 100644 --- a/net/ax25/ax25_iface.c +++ b/net/ax25/ax25_iface.c @@ -98,7 +98,7 @@ void ax25_linkfail_release(struct ax25_linkfail *lf) EXPORT_SYMBOL(ax25_linkfail_release); -int ax25_listen_register(ax25_address *callsign, struct net_device *dev) +int ax25_listen_register(const ax25_address *callsign, struct net_device *dev) { struct listen_struct *listen; @@ -121,7 +121,7 @@ int ax25_listen_register(ax25_address *callsign, struct net_device *dev) EXPORT_SYMBOL(ax25_listen_register); -void ax25_listen_release(ax25_address *callsign, struct net_device *dev) +void ax25_listen_release(const ax25_address *callsign, struct net_device *dev) { struct listen_struct *s, *listen; @@ -171,7 +171,7 @@ int (*ax25_protocol_function(unsigned int pid))(struct sk_buff *, ax25_cb *) return res; } -int ax25_listen_mine(ax25_address *callsign, struct net_device *dev) +int ax25_listen_mine(const ax25_address *callsign, struct net_device *dev) { struct listen_struct *listen; diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c index cd6afe895db9..1cac25aca637 100644 --- a/net/ax25/ax25_in.c +++ b/net/ax25/ax25_in.c @@ -181,7 +181,7 @@ static int ax25_process_rx_frame(ax25_cb *ax25, struct sk_buff *skb, int type, i } static int ax25_rcv(struct sk_buff *skb, struct net_device *dev, - ax25_address *dev_addr, struct packet_type *ptype) + const ax25_address *dev_addr, struct packet_type *ptype) { ax25_address src, dest, *next_digi = NULL; int type = 0, mine = 0, dama; @@ -447,5 +447,5 @@ int ax25_kiss_rcv(struct sk_buff *skb, struct net_device *dev, skb_pull(skb, AX25_KISS_HEADER_LEN); /* Remove the KISS byte */ - return ax25_rcv(skb, dev, (ax25_address *)dev->dev_addr, ptype); + return ax25_rcv(skb, dev, (const ax25_address *)dev->dev_addr, ptype); } diff --git a/net/ax25/ax25_out.c b/net/ax25/ax25_out.c index 22f2f66c6e0a..3db76d2470e9 100644 --- a/net/ax25/ax25_out.c +++ b/net/ax25/ax25_out.c @@ -29,7 +29,7 @@ static DEFINE_SPINLOCK(ax25_frag_lock); -ax25_cb *ax25_send_frame(struct sk_buff *skb, int paclen, ax25_address *src, ax25_address *dest, ax25_digi *digi, struct net_device *dev) +ax25_cb *ax25_send_frame(struct sk_buff *skb, int paclen, const ax25_address *src, ax25_address *dest, ax25_digi *digi, struct net_device *dev) { ax25_dev *ax25_dev; ax25_cb *ax25; diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index a3b6658ed789..433901dcf0c3 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -89,7 +89,7 @@ static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface) rcu_read_lock(); do { upper = netdev_master_upper_dev_get_rcu(upper); - } while (upper && !(upper->priv_flags & IFF_EBRIDGE)); + } while (upper && !netif_is_bridge_master(upper)); dev_hold(upper); rcu_read_unlock(); diff --git a/net/bridge/br.c b/net/bridge/br.c index d3a32c6813e0..1fac72cc617f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -36,7 +36,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v bool changed_addr; int err; - if (dev->priv_flags & IFF_EBRIDGE) { + if (netif_is_bridge_master(dev)) { err = br_vlan_bridge_event(dev, event, ptr); if (err) return notifier_from_errno(err); @@ -349,7 +349,7 @@ static void __net_exit br_net_exit(struct net *net) rtnl_lock(); for_each_netdev(net, dev) - if (dev->priv_flags & IFF_EBRIDGE) + if (netif_is_bridge_master(dev)) br_dev_delete(dev, &list); unregister_netdevice_many(&list); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 46812b659710..a6a68e18c70a 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -825,7 +825,7 @@ int br_fdb_dump(struct sk_buff *skb, struct net_bridge_fdb_entry *f; int err = 0; - if (!(dev->priv_flags & IFF_EBRIDGE)) + if (!netif_is_bridge_master(dev)) return err; if (!filter_dev) { @@ -1076,7 +1076,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -EINVAL; } - if (dev->priv_flags & IFF_EBRIDGE) { + if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group(br); } else { @@ -1173,7 +1173,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_bridge *br; int err; - if (dev->priv_flags & IFF_EBRIDGE) { + if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group(br); } else { diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 4a02f8bb278a..c11bba3e7ec0 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -471,7 +471,7 @@ int br_del_bridge(struct net *net, const char *name) if (dev == NULL) ret = -ENXIO; /* Could not find device */ - else if (!(dev->priv_flags & IFF_EBRIDGE)) { + else if (!netif_is_bridge_master(dev)) { /* Attempt to delete non bridge device! */ ret = -EPERM; } diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 49c268871fc1..db4ab2c2ce18 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -26,7 +26,7 @@ static int get_bridge_ifindices(struct net *net, int *indices, int num) for_each_netdev_rcu(net, dev) { if (i >= num) break; - if (dev->priv_flags & IFF_EBRIDGE) + if (netif_is_bridge_master(dev)) indices[i++] = dev->ifindex; } rcu_read_unlock(); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 0281453f7766..61ccf46fcc21 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -422,7 +422,7 @@ static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = net->dev_base_seq; for_each_netdev_rcu(net, dev) { - if (dev->priv_flags & IFF_EBRIDGE) { + if (netif_is_bridge_master(dev)) { struct net_bridge *br = netdev_priv(dev); struct br_port_msg *bpm; @@ -1016,7 +1016,7 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENODEV; } - if (!(dev->priv_flags & IFF_EBRIDGE)) { + if (!netif_is_bridge_master(dev)) { NL_SET_ERR_MSG_MOD(extack, "Device is not a bridge"); return -EOPNOTSUPP; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 8edfb98ae1d5..b5af68c105a8 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -968,7 +968,7 @@ static int brnf_device_event(struct notifier_block *unused, unsigned long event, struct net *net; int ret; - if (event != NETDEV_REGISTER || !(dev->priv_flags & IFF_EBRIDGE)) + if (event != NETDEV_REGISTER || !netif_is_bridge_master(dev)) return NOTIFY_DONE; ASSERT_RTNL(); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 6c58fc14d2cb..0c8b5f1a15bc 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -106,7 +106,7 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev, p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); - } else if (dev->priv_flags & IFF_EBRIDGE) { + } else if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); } @@ -1050,7 +1050,7 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself as well */ - if (!p && !(dev->priv_flags & IFF_EBRIDGE)) + if (!p && !netif_is_bridge_master(dev)) return -EINVAL; err = br_afspec(br, p, afspec, RTM_DELLINK, &changed, NULL); @@ -1666,7 +1666,8 @@ static size_t br_get_linkxstats_size(const struct net_device *dev, int attr) } return numvls * nla_total_size(sizeof(struct bridge_vlan_xstats)) + - nla_total_size(sizeof(struct br_mcast_stats)) + + nla_total_size_64bit(sizeof(struct br_mcast_stats)) + + (p ? nla_total_size_64bit(sizeof(p->stp_xstats)) : 0) + nla_total_size(0); } diff --git a/net/core/dev.c b/net/core/dev.c index 09d74798b440..26cdf971ca95 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -303,6 +303,12 @@ static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, return NULL; } +bool netdev_name_in_use(struct net *net, const char *name) +{ + return netdev_name_node_lookup(net, name); +} +EXPORT_SYMBOL(netdev_name_in_use); + int netdev_name_node_alt_create(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; @@ -1133,7 +1139,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) } snprintf(buf, IFNAMSIZ, name, i); - if (!__dev_get_by_name(net, buf)) + if (!netdev_name_in_use(net, buf)) return i; /* It is possible to run out of possible slots @@ -1187,7 +1193,7 @@ static int dev_get_valid_name(struct net *net, struct net_device *dev, if (strchr(name, '%')) return dev_alloc_name_ns(net, dev, name); - else if (__dev_get_by_name(net, name)) + else if (netdev_name_in_use(net, name)) return -EEXIST; else if (dev->name != name) strlcpy(dev->name, name, IFNAMSIZ); @@ -9170,14 +9176,11 @@ int dev_get_port_parent_id(struct net_device *dev, } err = devlink_compat_switch_id_get(dev, ppid); - if (!err || err != -EOPNOTSUPP) + if (!recurse || err != -EOPNOTSUPP) return err; - if (!recurse) - return -EOPNOTSUPP; - netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = dev_get_port_parent_id(lower_dev, ppid, recurse); + err = dev_get_port_parent_id(lower_dev, ppid, true); if (err) break; if (!first.id_len) @@ -11164,7 +11167,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, * we can use it in the destination network namespace. */ err = -EEXIST; - if (__dev_get_by_name(net, dev->name)) { + if (netdev_name_in_use(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) goto out; @@ -11517,7 +11520,7 @@ static void __net_exit default_device_exit(struct net *net) /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); - if (__dev_get_by_name(&init_net, fb_name)) + if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { diff --git a/net/core/devlink.c b/net/core/devlink.c index 4917112406a0..3ce6147a2fe8 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -30,6 +30,63 @@ #define CREATE_TRACE_POINTS #include <trace/events/devlink.h> +#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ + (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) + +struct devlink_dev_stats { + u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; +}; + +struct devlink { + u32 index; + struct list_head port_list; + struct list_head rate_list; + struct list_head sb_list; + struct list_head dpipe_table_list; + struct list_head resource_list; + struct list_head param_list; + struct list_head region_list; + struct list_head reporter_list; + struct mutex reporters_lock; /* protects reporter_list */ + struct devlink_dpipe_headers *dpipe_headers; + struct list_head trap_list; + struct list_head trap_group_list; + struct list_head trap_policer_list; + const struct devlink_ops *ops; + u64 features; + struct xarray snapshot_ids; + struct devlink_dev_stats stats; + struct device *dev; + possible_net_t _net; + /* Serializes access to devlink instance specific objects such as + * port, sb, dpipe, resource, params, region, traps and more. + */ + struct mutex lock; + u8 reload_failed:1; + refcount_t refcount; + struct completion comp; + char priv[0] __aligned(NETDEV_ALIGN); +}; + +void *devlink_priv(struct devlink *devlink) +{ + return &devlink->priv; +} +EXPORT_SYMBOL_GPL(devlink_priv); + +struct devlink *priv_to_devlink(void *priv) +{ + return container_of(priv, struct devlink, priv); +} +EXPORT_SYMBOL_GPL(priv_to_devlink); + +struct device *devlink_to_dev(const struct devlink *devlink) +{ + return devlink->dev; +} +EXPORT_SYMBOL_GPL(devlink_to_dev); + static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = { { .name = "destination mac", @@ -95,6 +152,22 @@ static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ static DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC); #define DEVLINK_REGISTERED XA_MARK_1 +/* devlink instances are open to the access from the user space after + * devlink_register() call. Such logical barrier allows us to have certain + * expectations related to locking. + * + * Before *_register() - we are in initialization stage and no parallel + * access possible to the devlink instance. All drivers perform that phase + * by implicitly holding device_lock. + * + * After *_register() - users and driver can access devlink instance at + * the same time. + */ +#define ASSERT_DEVLINK_REGISTERED(d) \ + WARN_ON_ONCE(!xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) +#define ASSERT_DEVLINK_NOT_REGISTERED(d) \ + WARN_ON_ONCE(xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) + /* devlink_mutex * * An overall lock guarding every operation coming from userspace. @@ -3959,9 +4032,6 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, struct net *curr_net; int err; - if (!devlink->reload_enabled) - return -EOPNOTSUPP; - memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, sizeof(remote_reload_stats)); @@ -4029,7 +4099,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) u32 actions_performed; int err; - if (!devlink_reload_supported(devlink->ops)) + if (!(devlink->features & DEVLINK_F_RELOAD)) return -EOPNOTSUPP; err = devlink_resources_validate(devlink, NULL, info); @@ -8913,6 +8983,25 @@ static bool devlink_reload_actions_valid(const struct devlink_ops *ops) } /** + * devlink_set_features - Set devlink supported features + * + * @devlink: devlink + * @features: devlink support features + * + * This interface allows us to set reload ops separatelly from + * the devlink_alloc. + */ +void devlink_set_features(struct devlink *devlink, u64 features) +{ + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + + WARN_ON(features & DEVLINK_F_RELOAD && + !devlink_reload_supported(devlink->ops)); + devlink->features = features; +} +EXPORT_SYMBOL_GPL(devlink_set_features); + +/** * devlink_alloc_ns - Allocate new devlink instance resources * in specific namespace * @@ -9056,6 +9145,10 @@ static void devlink_notify_unregister(struct devlink *devlink) */ void devlink_register(struct devlink *devlink) { + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + /* Make sure that we are in .probe() routine */ + device_lock_assert(devlink->dev); + mutex_lock(&devlink_mutex); xa_set_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); devlink_notify_register(devlink); @@ -9070,12 +9163,14 @@ EXPORT_SYMBOL_GPL(devlink_register); */ void devlink_unregister(struct devlink *devlink) { + ASSERT_DEVLINK_REGISTERED(devlink); + /* Make sure that we are in .remove() routine */ + device_lock_assert(devlink->dev); + devlink_put(devlink); wait_for_completion(&devlink->comp); mutex_lock(&devlink_mutex); - WARN_ON(devlink_reload_supported(devlink->ops) && - devlink->reload_enabled); devlink_notify_unregister(devlink); xa_clear_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); mutex_unlock(&devlink_mutex); @@ -9083,47 +9178,14 @@ void devlink_unregister(struct devlink *devlink) EXPORT_SYMBOL_GPL(devlink_unregister); /** - * devlink_reload_enable - Enable reload of devlink instance - * - * @devlink: devlink - * - * Should be called at end of device initialization - * process when reload operation is supported. - */ -void devlink_reload_enable(struct devlink *devlink) -{ - mutex_lock(&devlink_mutex); - devlink->reload_enabled = true; - mutex_unlock(&devlink_mutex); -} -EXPORT_SYMBOL_GPL(devlink_reload_enable); - -/** - * devlink_reload_disable - Disable reload of devlink instance - * - * @devlink: devlink - * - * Should be called at the beginning of device cleanup - * process when reload operation is supported. - */ -void devlink_reload_disable(struct devlink *devlink) -{ - mutex_lock(&devlink_mutex); - /* Mutex is taken which ensures that no reload operation is in - * progress while setting up forbidded flag. - */ - devlink->reload_enabled = false; - mutex_unlock(&devlink_mutex); -} -EXPORT_SYMBOL_GPL(devlink_reload_disable); - -/** * devlink_free - Free devlink instance resources * * @devlink: devlink */ void devlink_free(struct devlink *devlink) { + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + mutex_destroy(&devlink->reporters_lock); mutex_destroy(&devlink->lock); WARN_ON(!list_empty(&devlink->trap_policer_list)); @@ -11324,6 +11386,24 @@ free_msg: nlmsg_free(msg); } +static struct devlink_port *netdev_to_devlink_port(struct net_device *dev) +{ + if (!dev->netdev_ops->ndo_get_devlink_port) + return NULL; + + return dev->netdev_ops->ndo_get_devlink_port(dev); +} + +static struct devlink *netdev_to_devlink(struct net_device *dev) +{ + struct devlink_port *devlink_port = netdev_to_devlink_port(dev); + + if (!devlink_port) + return NULL; + + return devlink_port->devlink; +} + void devlink_compat_running_version(struct net_device *dev, char *buf, size_t len) { @@ -11433,7 +11513,7 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net) if (!net_eq(devlink_net(devlink), net)) goto retry; - WARN_ON(!devlink_reload_supported(devlink->ops)); + WARN_ON(!(devlink->features & DEVLINK_F_RELOAD)); err = devlink_reload(devlink, &init_net, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, DEVLINK_RELOAD_LIMIT_UNSPEC, diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 8e582e29a41e..4fcbdd71c59f 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -40,10 +40,10 @@ */ struct net_rate_estimator { - struct gnet_stats_basic_packed *bstats; + struct gnet_stats_basic_sync *bstats; spinlock_t *stats_lock; - seqcount_t *running; - struct gnet_stats_basic_cpu __percpu *cpu_bstats; + bool running; + struct gnet_stats_basic_sync __percpu *cpu_bstats; u8 ewma_log; u8 intvl_log; /* period : (250ms << intvl_log) */ @@ -60,13 +60,13 @@ struct net_rate_estimator { }; static void est_fetch_counters(struct net_rate_estimator *e, - struct gnet_stats_basic_packed *b) + struct gnet_stats_basic_sync *b) { - memset(b, 0, sizeof(*b)); + gnet_stats_basic_sync_init(b); if (e->stats_lock) spin_lock(e->stats_lock); - __gnet_stats_copy_basic(e->running, b, e->cpu_bstats, e->bstats); + gnet_stats_add_basic(b, e->cpu_bstats, e->bstats, e->running); if (e->stats_lock) spin_unlock(e->stats_lock); @@ -76,14 +76,18 @@ static void est_fetch_counters(struct net_rate_estimator *e, static void est_timer(struct timer_list *t) { struct net_rate_estimator *est = from_timer(est, t, timer); - struct gnet_stats_basic_packed b; + struct gnet_stats_basic_sync b; + u64 b_bytes, b_packets; u64 rate, brate; est_fetch_counters(est, &b); - brate = (b.bytes - est->last_bytes) << (10 - est->intvl_log); + b_bytes = u64_stats_read(&b.bytes); + b_packets = u64_stats_read(&b.packets); + + brate = (b_bytes - est->last_bytes) << (10 - est->intvl_log); brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log); - rate = (b.packets - est->last_packets) << (10 - est->intvl_log); + rate = (b_packets - est->last_packets) << (10 - est->intvl_log); rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log); write_seqcount_begin(&est->seq); @@ -91,8 +95,8 @@ static void est_timer(struct timer_list *t) est->avpps += rate; write_seqcount_end(&est->seq); - est->last_bytes = b.bytes; - est->last_packets = b.packets; + est->last_bytes = b_bytes; + est->last_packets = b_packets; est->next_jiffies += ((HZ/4) << est->intvl_log); @@ -109,7 +113,9 @@ static void est_timer(struct timer_list *t) * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path - * @running: qdisc running seqcount + * @running: true if @bstats represents a running qdisc, thus @bstats' + * internal values might change during basic reads. Only used + * if @bstats_cpu is NULL * @opt: rate estimator configuration TLV * * Creates a new rate estimator with &bstats as source and &rate_est @@ -121,16 +127,16 @@ static void est_timer(struct timer_list *t) * Returns 0 on success or a negative error code. * */ -int gen_new_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu_bstats, +int gen_new_estimator(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, + bool running, struct nlattr *opt) { struct gnet_estimator *parm = nla_data(opt); struct net_rate_estimator *old, *est; - struct gnet_stats_basic_packed b; + struct gnet_stats_basic_sync b; int intvl_log; if (nla_len(opt) < sizeof(*parm)) @@ -164,8 +170,8 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, est_fetch_counters(est, &b); if (lock) local_bh_enable(); - est->last_bytes = b.bytes; - est->last_packets = b.packets; + est->last_bytes = u64_stats_read(&b.bytes); + est->last_packets = u64_stats_read(&b.packets); if (lock) spin_lock_bh(lock); @@ -214,7 +220,9 @@ EXPORT_SYMBOL(gen_kill_estimator); * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path - * @running: qdisc running seqcount (might be NULL) + * @running: true if @bstats represents a running qdisc, thus @bstats' + * internal values might change during basic reads. Only used + * if @cpu_bstats is NULL * @opt: rate estimator configuration TLV * * Replaces the configuration of a rate estimator by calling @@ -222,11 +230,11 @@ EXPORT_SYMBOL(gen_kill_estimator); * * Returns 0 on success or a negative error code. */ -int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu_bstats, +int gen_replace_estimator(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt) + bool running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, lock, running, opt); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index e491b083b348..5516ea0d5da0 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -18,7 +18,7 @@ #include <linux/gen_stats.h> #include <net/netlink.h> #include <net/gen_stats.h> - +#include <net/sch_generic.h> static inline int gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size, int padattr) @@ -114,63 +114,81 @@ gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, } EXPORT_SYMBOL(gnet_stats_start_copy); -static void -__gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu) +/* Must not be inlined, due to u64_stats seqcount_t lockdep key */ +void gnet_stats_basic_sync_init(struct gnet_stats_basic_sync *b) { + u64_stats_set(&b->bytes, 0); + u64_stats_set(&b->packets, 0); + u64_stats_init(&b->syncp); +} +EXPORT_SYMBOL(gnet_stats_basic_sync_init); + +static void gnet_stats_add_basic_cpu(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu) +{ + u64 t_bytes = 0, t_packets = 0; int i; for_each_possible_cpu(i) { - struct gnet_stats_basic_cpu *bcpu = per_cpu_ptr(cpu, i); + struct gnet_stats_basic_sync *bcpu = per_cpu_ptr(cpu, i); unsigned int start; u64 bytes, packets; do { start = u64_stats_fetch_begin_irq(&bcpu->syncp); - bytes = bcpu->bstats.bytes; - packets = bcpu->bstats.packets; + bytes = u64_stats_read(&bcpu->bytes); + packets = u64_stats_read(&bcpu->packets); } while (u64_stats_fetch_retry_irq(&bcpu->syncp, start)); - bstats->bytes += bytes; - bstats->packets += packets; + t_bytes += bytes; + t_packets += packets; } + _bstats_update(bstats, t_bytes, t_packets); } -void -__gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_stats_basic_packed *bstats, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b) +void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, bool running) { - unsigned int seq; + unsigned int start; + u64 bytes = 0; + u64 packets = 0; + + WARN_ON_ONCE((cpu || running) && !in_task()); if (cpu) { - __gnet_stats_copy_basic_cpu(bstats, cpu); + gnet_stats_add_basic_cpu(bstats, cpu); return; } do { if (running) - seq = read_seqcount_begin(running); - bstats->bytes = b->bytes; - bstats->packets = b->packets; - } while (running && read_seqcount_retry(running, seq)); + start = u64_stats_fetch_begin_irq(&b->syncp); + bytes = u64_stats_read(&b->bytes); + packets = u64_stats_read(&b->packets); + } while (running && u64_stats_fetch_retry_irq(&b->syncp, start)); + + _bstats_update(bstats, bytes, packets); } -EXPORT_SYMBOL(__gnet_stats_copy_basic); +EXPORT_SYMBOL(gnet_stats_add_basic); static int -___gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b, - int type) +___gnet_stats_copy_basic(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, + int type, bool running) { - struct gnet_stats_basic_packed bstats = {0}; + struct gnet_stats_basic_sync bstats; + u64 bstats_bytes, bstats_packets; + + gnet_stats_basic_sync_init(&bstats); + gnet_stats_add_basic(&bstats, cpu, b, running); - __gnet_stats_copy_basic(running, &bstats, cpu, b); + bstats_bytes = u64_stats_read(&bstats.bytes); + bstats_packets = u64_stats_read(&bstats.packets); if (d->compat_tc_stats && type == TCA_STATS_BASIC) { - d->tc_stats.bytes = bstats.bytes; - d->tc_stats.packets = bstats.packets; + d->tc_stats.bytes = bstats_bytes; + d->tc_stats.packets = bstats_packets; } if (d->tail) { @@ -178,24 +196,28 @@ ___gnet_stats_copy_basic(const seqcount_t *running, int res; memset(&sb, 0, sizeof(sb)); - sb.bytes = bstats.bytes; - sb.packets = bstats.packets; + sb.bytes = bstats_bytes; + sb.packets = bstats_packets; res = gnet_stats_copy(d, type, &sb, sizeof(sb), TCA_STATS_PAD); - if (res < 0 || sb.packets == bstats.packets) + if (res < 0 || sb.packets == bstats_packets) return res; /* emit 64bit stats only if needed */ - return gnet_stats_copy(d, TCA_STATS_PKT64, &bstats.packets, - sizeof(bstats.packets), TCA_STATS_PAD); + return gnet_stats_copy(d, TCA_STATS_PKT64, &bstats_packets, + sizeof(bstats_packets), TCA_STATS_PAD); } return 0; } /** * gnet_stats_copy_basic - copy basic statistics into statistic TLV - * @running: seqcount_t pointer * @d: dumping handle * @cpu: copy statistic per cpu * @b: basic statistics + * @running: true if @b represents a running qdisc, thus @b's + * internal values might change during basic reads. + * Only used if @cpu is NULL + * + * Context: task; must not be run from IRQ or BH contexts * * Appends the basic statistics to the top level TLV created by * gnet_stats_start_copy(). @@ -204,22 +226,25 @@ ___gnet_stats_copy_basic(const seqcount_t *running, * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b) +gnet_stats_copy_basic(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, + bool running) { - return ___gnet_stats_copy_basic(running, d, cpu, b, - TCA_STATS_BASIC); + return ___gnet_stats_copy_basic(d, cpu, b, TCA_STATS_BASIC, running); } EXPORT_SYMBOL(gnet_stats_copy_basic); /** * gnet_stats_copy_basic_hw - copy basic hw statistics into statistic TLV - * @running: seqcount_t pointer * @d: dumping handle * @cpu: copy statistic per cpu * @b: basic statistics + * @running: true if @b represents a running qdisc, thus @b's + * internal values might change during basic reads. + * Only used if @cpu is NULL + * + * Context: task; must not be run from IRQ or BH contexts * * Appends the basic statistics to the top level TLV created by * gnet_stats_start_copy(). @@ -228,13 +253,12 @@ EXPORT_SYMBOL(gnet_stats_copy_basic); * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic_hw(const seqcount_t *running, - struct gnet_dump *d, - struct gnet_stats_basic_cpu __percpu *cpu, - struct gnet_stats_basic_packed *b) +gnet_stats_copy_basic_hw(struct gnet_dump *d, + struct gnet_stats_basic_sync __percpu *cpu, + struct gnet_stats_basic_sync *b, + bool running) { - return ___gnet_stats_copy_basic(running, d, cpu, b, - TCA_STATS_BASIC_HW); + return ___gnet_stats_copy_basic(d, cpu, b, TCA_STATS_BASIC_HW, running); } EXPORT_SYMBOL(gnet_stats_copy_basic_hw); @@ -282,16 +306,15 @@ gnet_stats_copy_rate_est(struct gnet_dump *d, } EXPORT_SYMBOL(gnet_stats_copy_rate_est); -static void -__gnet_stats_copy_queue_cpu(struct gnet_stats_queue *qstats, - const struct gnet_stats_queue __percpu *q) +static void gnet_stats_add_queue_cpu(struct gnet_stats_queue *qstats, + const struct gnet_stats_queue __percpu *q) { int i; for_each_possible_cpu(i) { const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i); - qstats->qlen = 0; + qstats->qlen += qcpu->backlog; qstats->backlog += qcpu->backlog; qstats->drops += qcpu->drops; qstats->requeues += qcpu->requeues; @@ -299,24 +322,21 @@ __gnet_stats_copy_queue_cpu(struct gnet_stats_queue *qstats, } } -void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats, - const struct gnet_stats_queue __percpu *cpu, - const struct gnet_stats_queue *q, - __u32 qlen) +void gnet_stats_add_queue(struct gnet_stats_queue *qstats, + const struct gnet_stats_queue __percpu *cpu, + const struct gnet_stats_queue *q) { if (cpu) { - __gnet_stats_copy_queue_cpu(qstats, cpu); + gnet_stats_add_queue_cpu(qstats, cpu); } else { - qstats->qlen = q->qlen; - qstats->backlog = q->backlog; - qstats->drops = q->drops; - qstats->requeues = q->requeues; - qstats->overlimits = q->overlimits; + qstats->qlen += q->qlen; + qstats->backlog += q->backlog; + qstats->drops += q->drops; + qstats->requeues += q->requeues; + qstats->overlimits += q->overlimits; } - - qstats->qlen = qlen; } -EXPORT_SYMBOL(__gnet_stats_copy_queue); +EXPORT_SYMBOL(gnet_stats_add_queue); /** * gnet_stats_copy_queue - copy queue statistics into statistics TLV @@ -339,7 +359,8 @@ gnet_stats_copy_queue(struct gnet_dump *d, { struct gnet_stats_queue qstats = {0}; - __gnet_stats_copy_queue(&qstats, cpu_q, q, qlen); + gnet_stats_add_queue(&qstats, cpu_q, q); + qstats.qlen = qlen; if (d->compat_tc_stats) { d->tc_stats.drops = qstats.drops; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2d5bc3a75fae..47931c8be04b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -122,6 +122,8 @@ static void neigh_mark_dead(struct neighbour *n) list_del_init(&n->gc_list); atomic_dec(&n->tbl->gc_entries); } + if (!list_empty(&n->managed_list)) + list_del_init(&n->managed_list); } static void neigh_update_gc_list(struct neighbour *n) @@ -130,7 +132,6 @@ static void neigh_update_gc_list(struct neighbour *n) write_lock_bh(&n->tbl->lock); write_lock(&n->lock); - if (n->dead) goto out; @@ -149,32 +150,59 @@ static void neigh_update_gc_list(struct neighbour *n) list_add_tail(&n->gc_list, &n->tbl->gc_list); atomic_inc(&n->tbl->gc_entries); } +out: + write_unlock(&n->lock); + write_unlock_bh(&n->tbl->lock); +} +static void neigh_update_managed_list(struct neighbour *n) +{ + bool on_managed_list, add_to_managed; + + write_lock_bh(&n->tbl->lock); + write_lock(&n->lock); + if (n->dead) + goto out; + + add_to_managed = n->flags & NTF_MANAGED; + on_managed_list = !list_empty(&n->managed_list); + + if (!add_to_managed && on_managed_list) + list_del_init(&n->managed_list); + else if (add_to_managed && !on_managed_list) + list_add_tail(&n->managed_list, &n->tbl->managed_list); out: write_unlock(&n->lock); write_unlock_bh(&n->tbl->lock); } -static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags, - int *notify) +static void neigh_update_flags(struct neighbour *neigh, u32 flags, int *notify, + bool *gc_update, bool *managed_update) { - bool rc = false; - u8 ndm_flags; + u32 ndm_flags, old_flags = neigh->flags; if (!(flags & NEIGH_UPDATE_F_ADMIN)) - return rc; + return; + + ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; + ndm_flags |= (flags & NEIGH_UPDATE_F_MANAGED) ? NTF_MANAGED : 0; - ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; - if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) { + if ((old_flags ^ ndm_flags) & NTF_EXT_LEARNED) { if (ndm_flags & NTF_EXT_LEARNED) neigh->flags |= NTF_EXT_LEARNED; else neigh->flags &= ~NTF_EXT_LEARNED; - rc = true; *notify = 1; + *gc_update = true; + } + if ((old_flags ^ ndm_flags) & NTF_MANAGED) { + if (ndm_flags & NTF_MANAGED) + neigh->flags |= NTF_MANAGED; + else + neigh->flags &= ~NTF_MANAGED; + *notify = 1; + *managed_update = true; } - - return rc; } static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np, @@ -379,7 +407,7 @@ EXPORT_SYMBOL(neigh_ifdown); static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev, - bool exempt_from_gc) + u32 flags, bool exempt_from_gc) { struct neighbour *n = NULL; unsigned long now = jiffies; @@ -412,6 +440,7 @@ do_alloc: n->updated = n->used = now; n->nud_state = NUD_NONE; n->output = neigh_blackhole; + n->flags = flags; seqlock_init(&n->hh.hh_lock); n->parms = neigh_parms_clone(&tbl->parms); timer_setup(&n->timer, neigh_timer_handler, 0); @@ -421,6 +450,7 @@ do_alloc: refcount_set(&n->refcnt, 1); n->dead = 1; INIT_LIST_HEAD(&n->gc_list); + INIT_LIST_HEAD(&n->managed_list); atomic_inc(&tbl->entries); out: @@ -575,19 +605,18 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, } EXPORT_SYMBOL(neigh_lookup_nodev); -static struct neighbour *___neigh_create(struct neigh_table *tbl, - const void *pkey, - struct net_device *dev, - bool exempt_from_gc, bool want_ref) +static struct neighbour * +___neigh_create(struct neigh_table *tbl, const void *pkey, + struct net_device *dev, u32 flags, + bool exempt_from_gc, bool want_ref) { - struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev, exempt_from_gc); - u32 hash_val; - unsigned int key_len = tbl->key_len; - int error; + u32 hash_val, key_len = tbl->key_len; + struct neighbour *n1, *rc, *n; struct neigh_hash_table *nht; + int error; + n = neigh_alloc(tbl, dev, flags, exempt_from_gc); trace_neigh_create(tbl, dev, pkey, n, exempt_from_gc); - if (!n) { rc = ERR_PTR(-ENOBUFS); goto out; @@ -650,7 +679,8 @@ static struct neighbour *___neigh_create(struct neigh_table *tbl, n->dead = 0; if (!exempt_from_gc) list_add_tail(&n->gc_list, &n->tbl->gc_list); - + if (n->flags & NTF_MANAGED) + list_add_tail(&n->managed_list, &n->tbl->managed_list); if (want_ref) neigh_hold(n); rcu_assign_pointer(n->next, @@ -674,7 +704,7 @@ out_neigh_release: struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref) { - return ___neigh_create(tbl, pkey, dev, false, want_ref); + return ___neigh_create(tbl, pkey, dev, 0, false, want_ref); } EXPORT_SYMBOL(__neigh_create); @@ -1205,8 +1235,6 @@ static void neigh_update_hhs(struct neighbour *neigh) } } - - /* Generic update routine. -- lladdr is new lladdr or NULL, if it is not supplied. -- new is new state. @@ -1217,7 +1245,8 @@ static void neigh_update_hhs(struct neighbour *neigh) lladdr instead of overriding it if it is different. NEIGH_UPDATE_F_ADMIN means that the change is administrative. - + NEIGH_UPDATE_F_USE means that the entry is user triggered. + NEIGH_UPDATE_F_MANAGED means that the entry will be auto-refreshed. NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing NTF_ROUTER flag. NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as @@ -1225,17 +1254,15 @@ static void neigh_update_hhs(struct neighbour *neigh) Caller MUST hold reference count on the entry. */ - static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid, struct netlink_ext_ack *extack) { - bool ext_learn_change = false; - u8 old; - int err; - int notify = 0; - struct net_device *dev; + bool gc_update = false, managed_update = false; int update_isrouter = 0; + struct net_device *dev; + int err, notify = 0; + u8 old; trace_neigh_update(neigh, lladdr, new, flags, nlmsg_pid); @@ -1254,7 +1281,13 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, (old & (NUD_NOARP | NUD_PERMANENT))) goto out; - ext_learn_change = neigh_update_ext_learned(neigh, flags, ¬ify); + neigh_update_flags(neigh, flags, ¬ify, &gc_update, &managed_update); + if (flags & (NEIGH_UPDATE_F_USE | NEIGH_UPDATE_F_MANAGED)) { + new = old & ~NUD_PERMANENT; + neigh->nud_state = new; + err = 0; + goto out; + } if (!(new & NUD_VALID)) { neigh_del_timer(neigh); @@ -1399,15 +1432,13 @@ out: if (update_isrouter) neigh_update_is_router(neigh, flags, ¬ify); write_unlock_bh(&neigh->lock); - - if (((new ^ old) & NUD_PERMANENT) || ext_learn_change) + if (((new ^ old) & NUD_PERMANENT) || gc_update) neigh_update_gc_list(neigh); - + if (managed_update) + neigh_update_managed_list(neigh); if (notify) neigh_update_notify(neigh, nlmsg_pid); - trace_neigh_update_done(neigh, err); - return err; } @@ -1533,6 +1564,20 @@ int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb) } EXPORT_SYMBOL(neigh_direct_output); +static void neigh_managed_work(struct work_struct *work) +{ + struct neigh_table *tbl = container_of(work, struct neigh_table, + managed_work.work); + struct neighbour *neigh; + + write_lock_bh(&tbl->lock); + list_for_each_entry(neigh, &tbl->managed_list, managed_list) + neigh_event_send(neigh, NULL); + queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, + NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME)); + write_unlock_bh(&tbl->lock); +} + static void neigh_proxy_process(struct timer_list *t) { struct neigh_table *tbl = from_timer(tbl, t, proxy_timer); @@ -1679,6 +1724,8 @@ void neigh_table_init(int index, struct neigh_table *tbl) INIT_LIST_HEAD(&tbl->parms_list); INIT_LIST_HEAD(&tbl->gc_list); + INIT_LIST_HEAD(&tbl->managed_list); + list_add(&tbl->parms.list, &tbl->parms_list); write_pnet(&tbl->parms.net, &init_net); refcount_set(&tbl->parms.refcnt, 1); @@ -1710,9 +1757,13 @@ void neigh_table_init(int index, struct neigh_table *tbl) WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); rwlock_init(&tbl->lock); + INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, tbl->parms.reachable_time); + INIT_DEFERRABLE_WORK(&tbl->managed_work, neigh_managed_work); + queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, 0); + timer_setup(&tbl->proxy_timer, neigh_proxy_process, 0); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); @@ -1783,6 +1834,7 @@ const struct nla_policy nda_policy[NDA_MAX+1] = { [NDA_MASTER] = { .type = NLA_U32 }, [NDA_PROTOCOL] = { .type = NLA_U8 }, [NDA_NH_ID] = { .type = NLA_U32 }, + [NDA_FLAGS_EXT] = NLA_POLICY_MASK(NLA_U32, NTF_EXT_MASK), [NDA_FDB_EXT_ATTRS] = { .type = NLA_NESTED }, }; @@ -1855,7 +1907,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE | - NEIGH_UPDATE_F_OVERRIDE_ISROUTER; + NEIGH_UPDATE_F_OVERRIDE_ISROUTER; struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; @@ -1864,6 +1916,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct neighbour *neigh; void *dst, *lladdr; u8 protocol = 0; + u32 ndm_flags; int err; ASSERT_RTNL(); @@ -1879,6 +1932,15 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, } ndm = nlmsg_data(nlh); + ndm_flags = ndm->ndm_flags; + if (tb[NDA_FLAGS_EXT]) { + u32 ext = nla_get_u32(tb[NDA_FLAGS_EXT]); + + BUILD_BUG_ON(sizeof(neigh->flags) * BITS_PER_BYTE < + (sizeof(ndm->ndm_flags) * BITS_PER_BYTE + + hweight32(NTF_EXT_MASK))); + ndm_flags |= (ext << NTF_EXT_SHIFT); + } if (ndm->ndm_ifindex) { dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { @@ -1906,14 +1968,18 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[NDA_PROTOCOL]) protocol = nla_get_u8(tb[NDA_PROTOCOL]); - - if (ndm->ndm_flags & NTF_PROXY) { + if (ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; + if (ndm_flags & NTF_MANAGED) { + NL_SET_ERR_MSG(extack, "Invalid NTF_* flag combination"); + goto out; + } + err = -ENOBUFS; pn = pneigh_lookup(tbl, net, dst, dev, 1); if (pn) { - pn->flags = ndm->ndm_flags; + pn->flags = ndm_flags; if (protocol) pn->protocol = protocol; err = 0; @@ -1933,16 +1999,24 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, neigh = neigh_lookup(tbl, dst, dev); if (neigh == NULL) { - bool exempt_from_gc; + bool ndm_permanent = ndm->ndm_state & NUD_PERMANENT; + bool exempt_from_gc = ndm_permanent || + ndm_flags & NTF_EXT_LEARNED; if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { err = -ENOENT; goto out; } + if (ndm_permanent && (ndm_flags & NTF_MANAGED)) { + NL_SET_ERR_MSG(extack, "Invalid NTF_* flag for permanent entry"); + err = -EINVAL; + goto out; + } - exempt_from_gc = ndm->ndm_state & NUD_PERMANENT || - ndm->ndm_flags & NTF_EXT_LEARNED; - neigh = ___neigh_create(tbl, dst, dev, exempt_from_gc, true); + neigh = ___neigh_create(tbl, dst, dev, + ndm_flags & + (NTF_EXT_LEARNED | NTF_MANAGED), + exempt_from_gc, true); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); goto out; @@ -1961,22 +2035,22 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (protocol) neigh->protocol = protocol; - - if (ndm->ndm_flags & NTF_EXT_LEARNED) + if (ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; - - if (ndm->ndm_flags & NTF_ROUTER) + if (ndm_flags & NTF_ROUTER) flags |= NEIGH_UPDATE_F_ISROUTER; + if (ndm_flags & NTF_MANAGED) + flags |= NEIGH_UPDATE_F_MANAGED; + if (ndm_flags & NTF_USE) + flags |= NEIGH_UPDATE_F_USE; - if (ndm->ndm_flags & NTF_USE) { + err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, + NETLINK_CB(skb).portid, extack); + if (!err && ndm_flags & (NTF_USE | NTF_MANAGED)) { neigh_event_send(neigh, NULL); err = 0; - } else - err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, - NETLINK_CB(skb).portid, extack); - + } neigh_release(neigh); - out: return err; } @@ -2427,6 +2501,7 @@ out: static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, u32 pid, u32 seq, int type, unsigned int flags) { + u32 neigh_flags, neigh_flags_ext; unsigned long now = jiffies; struct nda_cacheinfo ci; struct nlmsghdr *nlh; @@ -2436,11 +2511,14 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, if (nlh == NULL) return -EMSGSIZE; + neigh_flags_ext = neigh->flags >> NTF_EXT_SHIFT; + neigh_flags = neigh->flags & NTF_OLD_MASK; + ndm = nlmsg_data(nlh); ndm->ndm_family = neigh->ops->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = neigh->flags; + ndm->ndm_flags = neigh_flags; ndm->ndm_type = neigh->type; ndm->ndm_ifindex = neigh->dev->ifindex; @@ -2471,6 +2549,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, if (neigh->protocol && nla_put_u8(skb, NDA_PROTOCOL, neigh->protocol)) goto nla_put_failure; + if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext)) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -2484,6 +2564,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, u32 pid, u32 seq, int type, unsigned int flags, struct neigh_table *tbl) { + u32 neigh_flags, neigh_flags_ext; struct nlmsghdr *nlh; struct ndmsg *ndm; @@ -2491,11 +2572,14 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (nlh == NULL) return -EMSGSIZE; + neigh_flags_ext = pn->flags >> NTF_EXT_SHIFT; + neigh_flags = pn->flags & NTF_OLD_MASK; + ndm = nlmsg_data(nlh); ndm->ndm_family = tbl->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = pn->flags | NTF_PROXY; + ndm->ndm_flags = neigh_flags | NTF_PROXY; ndm->ndm_type = RTN_UNICAST; ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0; ndm->ndm_state = NUD_NONE; @@ -2505,6 +2589,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (pn->protocol && nla_put_u8(skb, NDA_PROTOCOL, pn->protocol)) goto nla_put_failure; + if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext)) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -2820,6 +2906,7 @@ static inline size_t neigh_nlmsg_size(void) + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(4) /* NDA_PROBES */ + + nla_total_size(4) /* NDA_FLAGS_EXT */ + nla_total_size(1); /* NDA_PROTOCOL */ } @@ -2848,6 +2935,7 @@ static inline size_t pneigh_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */ + + nla_total_size(4) /* NDA_FLAGS_EXT */ + nla_total_size(1); /* NDA_PROTOCOL */ } diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index eab5fc88a002..d8b9dbabd4a4 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -77,8 +77,8 @@ static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); - seq_printf(seq, "%9s: %16llu %12llu %4llu %6llu %4llu %5llu %10llu %9llu " - "%16llu %12llu %4llu %6llu %4llu %5llu %7llu %10llu\n", + seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " + "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, stats->rx_dropped + stats->rx_missed_errors, @@ -103,11 +103,11 @@ static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) static int dev_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) - seq_puts(seq, "Interface| Receive " - " | Transmit\n" - " | bytes packets errs drop fifo frame " - "compressed multicast| bytes packets errs " - " drop fifo colls carrier compressed\n"); + seq_puts(seq, "Inter-| Receive " + " | Transmit\n" + " face |bytes packets errs drop fifo frame " + "compressed multicast|bytes packets errs " + "drop fifo colls carrier compressed\n"); else dev_seq_printf_stats(seq, v); return 0; @@ -259,14 +259,14 @@ static int ptype_seq_show(struct seq_file *seq, void *v) struct packet_type *pt = v; if (v == SEQ_START_TOKEN) - seq_puts(seq, "Type Device Function\n"); + seq_puts(seq, "Type Device Function\n"); else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else seq_printf(seq, "%04x", ntohs(pt->type)); - seq_printf(seq, " %-9s %ps\n", + seq_printf(seq, " %-8s %ps\n", pt->dev ? pt->dev->name : "", pt->func); } @@ -327,14 +327,12 @@ static int dev_mc_seq_show(struct seq_file *seq, void *v) struct netdev_hw_addr *ha; struct net_device *dev = v; - if (v == SEQ_START_TOKEN) { - seq_puts(seq, "Ifindex Interface Refcount Global_use Address\n"); + if (v == SEQ_START_TOKEN) return 0; - } netif_addr_lock_bh(dev); netdev_for_each_mc_addr(ha, dev) { - seq_printf(seq, "%-7d %-9s %-8d %-10d %*phN\n", + seq_printf(seq, "%-4d %-15s %-5d %-5d %*phN\n", dev->ifindex, dev->name, ha->refcount, ha->global_use, (int)dev->addr_len, ha->addr); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index ae001c2ca2af..d6e4e0b43beb 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -175,6 +175,14 @@ static int change_carrier(struct net_device *dev, unsigned long new_carrier) static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { + struct net_device *netdev = to_net_dev(dev); + + /* The check is also done in change_carrier; this helps returning early + * without hitting the trylock/restart in netdev_store. + */ + if (!netdev->netdev_ops->ndo_change_carrier) + return -EOPNOTSUPP; + return netdev_store(dev, attr, buf, len, change_carrier); } @@ -196,6 +204,12 @@ static ssize_t speed_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; + /* The check is also done in __ethtool_get_link_ksettings; this helps + * returning early without hitting the trylock/restart below. + */ + if (!netdev->ethtool_ops->get_link_ksettings) + return ret; + if (!rtnl_trylock()) return restart_syscall(); @@ -216,6 +230,12 @@ static ssize_t duplex_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; + /* The check is also done in __ethtool_get_link_ksettings; this helps + * returning early without hitting the trylock/restart below. + */ + if (!netdev->ethtool_ops->get_link_ksettings) + return ret; + if (!rtnl_trylock()) return restart_syscall(); @@ -468,6 +488,14 @@ static ssize_t proto_down_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { + struct net_device *netdev = to_net_dev(dev); + + /* The check is also done in change_proto_down; this helps returning + * early without hitting the trylock/restart in netdev_store. + */ + if (!netdev->netdev_ops->ndo_change_proto_down) + return -EOPNOTSUPP; + return netdev_store(dev, attr, buf, len, change_proto_down); } NETDEVICE_SHOW_RW(proto_down, fmt_dec); @@ -478,6 +506,12 @@ static ssize_t phys_port_id_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; + /* The check is also done in dev_get_phys_port_id; this helps returning + * early without hitting the trylock/restart below. + */ + if (!netdev->netdev_ops->ndo_get_phys_port_id) + return -EOPNOTSUPP; + if (!rtnl_trylock()) return restart_syscall(); @@ -500,6 +534,13 @@ static ssize_t phys_port_name_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; + /* The checks are also done in dev_get_phys_port_name; this helps + * returning early without hitting the trylock/restart below. + */ + if (!netdev->netdev_ops->ndo_get_phys_port_name && + !netdev->netdev_ops->ndo_get_devlink_port) + return -EOPNOTSUPP; + if (!rtnl_trylock()) return restart_syscall(); @@ -522,6 +563,14 @@ static ssize_t phys_switch_id_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; + /* The checks are also done in dev_get_phys_port_name; this helps + * returning early without hitting the trylock/restart below. This works + * because recurse is false when calling dev_get_port_parent_id. + */ + if (!netdev->netdev_ops->ndo_get_port_parent_id && + !netdev->netdev_ops->ndo_get_devlink_port) + return -EOPNOTSUPP; + if (!rtnl_trylock()) return restart_syscall(); @@ -1226,6 +1275,12 @@ static ssize_t tx_maxrate_store(struct netdev_queue *queue, if (!capable(CAP_NET_ADMIN)) return -EPERM; + /* The check is also done later; this helps returning early without + * hitting the trylock/restart below. + */ + if (!dev->netdev_ops->ndo_set_tx_maxrate) + return -EOPNOTSUPP; + err = kstrtou32(buf, 10, &rate); if (err < 0) return err; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 1a6978427d6c..9b60e4301a44 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -49,6 +49,12 @@ static int page_pool_init(struct page_pool *pool, * which is the XDP_TX use-case. */ if (pool->p.flags & PP_FLAG_DMA_MAP) { + /* DMA-mapping is not supported on 32-bit systems with + * 64-bit DMA mapping. + */ + if (sizeof(dma_addr_t) > sizeof(unsigned long)) + return -EOPNOTSUPP; + if ((pool->p.dma_dir != DMA_FROM_DEVICE) && (pool->p.dma_dir != DMA_BIDIRECTIONAL)) return -EINVAL; @@ -69,10 +75,6 @@ static int page_pool_init(struct page_pool *pool, */ } - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT && - pool->p.flags & PP_FLAG_PAGE_FRAG) - return -EINVAL; - if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 327ca6bc6e6d..564d24c451af 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4384,7 +4384,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; if (br_dev != netdev_master_upper_dev_get(dev) && - !(dev->priv_flags & IFF_EBRIDGE)) + !netif_is_bridge_master(dev)) continue; cops = ops; } @@ -5262,7 +5262,7 @@ nla_put_failure: static size_t if_nlmsg_stats_size(const struct net_device *dev, u32 filter_mask) { - size_t size = 0; + size_t size = NLMSG_ALIGN(sizeof(struct if_stats_msg)); if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_64, 0)) size += nla_total_size_64bit(sizeof(struct rtnl_link_stats64)); diff --git a/net/core/sock.c b/net/core/sock.c index beda31764df9..9862eefce21e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -350,7 +350,7 @@ void sk_error_report(struct sock *sk) } EXPORT_SYMBOL(sk_error_report); -static int sock_get_timeout(long timeo, void *optval, bool old_timeval) +int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; @@ -379,12 +379,11 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval) *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } +EXPORT_SYMBOL(sock_get_timeout); -static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, - bool old_timeval) +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval) { - struct __kernel_sock_timeval tv; - if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; @@ -393,8 +392,8 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; - tv.tv_sec = tv32.tv_sec; - tv.tv_usec = tv32.tv_usec; + tv->tv_sec = tv32.tv_sec; + tv->tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; @@ -402,14 +401,28 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, return -EINVAL; if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; - tv.tv_sec = old_tv.tv_sec; - tv.tv_usec = old_tv.tv_usec; + tv->tv_sec = old_tv.tv_sec; + tv->tv_usec = old_tv.tv_usec; } else { - if (optlen < sizeof(tv)) + if (optlen < sizeof(*tv)) return -EINVAL; - if (copy_from_sockptr(&tv, optval, sizeof(tv))) + if (copy_from_sockptr(tv, optval, sizeof(*tv))) return -EFAULT; } + + return 0; +} +EXPORT_SYMBOL(sock_copy_user_timeval); + +static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, + bool old_timeval) +{ + struct __kernel_sock_timeval tv; + int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); + + if (err) + return err; + if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; diff --git a/net/core/stream.c b/net/core/stream.c index e09ffd410685..06b36c730ce8 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -195,9 +195,6 @@ void sk_stream_kill_queues(struct sock *sk) /* First the read buffer. */ __skb_queue_purge(&sk->sk_receive_queue); - /* Next, the error queue. */ - __skb_queue_purge(&sk->sk_error_queue); - /* Next, the write queue. */ WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index c5c1d2b8045e..5183e627468d 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -48,7 +48,7 @@ extern bool dccp_debug; extern struct inet_hashinfo dccp_hashinfo; -extern struct percpu_counter dccp_orphan_count; +DECLARE_PER_CPU(unsigned int, dccp_orphan_count); void dccp_time_wait(struct sock *sk, int state, int timeo); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index abb5c596a817..fc44dadc778b 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -42,8 +42,8 @@ DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly; EXPORT_SYMBOL_GPL(dccp_statistics); -struct percpu_counter dccp_orphan_count; -EXPORT_SYMBOL_GPL(dccp_orphan_count); +DEFINE_PER_CPU(unsigned int, dccp_orphan_count); +EXPORT_PER_CPU_SYMBOL_GPL(dccp_orphan_count); struct inet_hashinfo dccp_hashinfo; EXPORT_SYMBOL_GPL(dccp_hashinfo); @@ -1055,7 +1055,7 @@ adjudge_to_death: bh_lock_sock(sk); WARN_ON(sock_owned_by_user(sk)); - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(dccp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED) @@ -1115,13 +1115,10 @@ static int __init dccp_init(void) BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > sizeof_field(struct sk_buff, cb)); - rc = percpu_counter_init(&dccp_orphan_count, 0, GFP_KERNEL); - if (rc) - goto out_fail; inet_hashinfo_init(&dccp_hashinfo); rc = inet_hashinfo2_init_mod(&dccp_hashinfo); if (rc) - goto out_free_percpu; + goto out_fail; rc = -ENOBUFS; dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", @@ -1226,8 +1223,6 @@ out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); out_free_hashinfo2: inet_hashinfo2_free_mod(&dccp_hashinfo); -out_free_percpu: - percpu_counter_destroy(&dccp_orphan_count); out_fail: dccp_hashinfo.bhash = NULL; dccp_hashinfo.ehash = NULL; @@ -1250,7 +1245,6 @@ static void __exit dccp_fini(void) dccp_ackvec_exit(); dccp_sysctl_exit(); inet_hashinfo2_free_mod(&dccp_hashinfo); - percpu_counter_destroy(&dccp_orphan_count); } module_init(dccp_init); diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index bca1b5d66df2..8cb87b5067ee 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -92,17 +92,8 @@ config NET_DSA_TAG_KSZ Say Y if you want to enable support for tagging frames for the Microchip 8795/9477/9893 families of switches. -config NET_DSA_TAG_RTL4_A - tristate "Tag driver for Realtek 4 byte protocol A tags" - help - Say Y or M if you want to enable support for tagging frames for the - Realtek switches with 4 byte protocol A tags, sich as found in - the Realtek RTL8366RB. - config NET_DSA_TAG_OCELOT tristate "Tag driver for Ocelot family of switches, using NPI port" - depends on MSCC_OCELOT_SWITCH_LIB || \ - (MSCC_OCELOT_SWITCH_LIB=n && COMPILE_TEST) select PACKING help Say Y or M if you want to enable NPI tagging for the Ocelot switches @@ -114,8 +105,6 @@ config NET_DSA_TAG_OCELOT config NET_DSA_TAG_OCELOT_8021Q tristate "Tag driver for Ocelot family of switches, using VLAN" - depends on MSCC_OCELOT_SWITCH_LIB || \ - (MSCC_OCELOT_SWITCH_LIB=n && COMPILE_TEST) help Say Y or M if you want to enable support for tagging frames with a custom VLAN-based header. Frames that require timestamping, such as @@ -130,6 +119,19 @@ config NET_DSA_TAG_QCA Say Y or M if you want to enable support for tagging frames for the Qualcomm Atheros QCA8K switches. +config NET_DSA_TAG_RTL4_A + tristate "Tag driver for Realtek 4 byte protocol A tags" + help + Say Y or M if you want to enable support for tagging frames for the + Realtek switches with 4 byte protocol A tags, sich as found in + the Realtek RTL8366RB. + +config NET_DSA_TAG_RTL8_4 + tristate "Tag driver for Realtek 8 byte protocol 4 tags" + help + Say Y or M if you want to enable support for tagging frames for Realtek + switches with 8 byte protocol 4 tags, such as the Realtek RTL8365MB-VC. + config NET_DSA_TAG_LAN9303 tristate "Tag driver for SMSC/Microchip LAN9303 family of switches" help diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 67ea009f242c..9f75820e7c98 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -10,12 +10,13 @@ obj-$(CONFIG_NET_DSA_TAG_DSA_COMMON) += tag_dsa.o obj-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o obj-$(CONFIG_NET_DSA_TAG_HELLCREEK) += tag_hellcreek.o obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o -obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o obj-$(CONFIG_NET_DSA_TAG_OCELOT) += tag_ocelot.o obj-$(CONFIG_NET_DSA_TAG_OCELOT_8021Q) += tag_ocelot_8021q.o obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o +obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o +obj-$(CONFIG_NET_DSA_TAG_RTL8_4) += tag_rtl8_4.o obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o obj-$(CONFIG_NET_DSA_TAG_XRS700X) += tag_xrs700x.o diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 8ca6a1170c9d..691d27498b24 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -170,7 +170,7 @@ void dsa_bridge_num_put(const struct net_device *bridge_dev, int bridge_num) /* Check if the bridge is still in use, otherwise it is time * to clean it up so we can reuse this bridge_num later. */ - if (!dsa_bridge_num_find(bridge_dev)) + if (dsa_bridge_num_find(bridge_dev) < 0) clear_bit(bridge_num, &dsa_fwd_offloading_bridges); } @@ -811,7 +811,9 @@ static int dsa_switch_setup_tag_protocol(struct dsa_switch *ds) if (!dsa_is_cpu_port(ds, port)) continue; + rtnl_lock(); err = ds->ops->change_tag_protocol(ds, port, tag_ops->proto); + rtnl_unlock(); if (err) { dev_err(ds->dev, "Unable to use tag protocol \"%s\": %pe\n", tag_ops->name, ERR_PTR(err)); @@ -924,11 +926,11 @@ static void dsa_switch_teardown(struct dsa_switch *ds) ds->slave_mii_bus = NULL; } - dsa_switch_unregister_notifier(ds); - if (ds->ops->teardown) ds->ops->teardown(ds); + dsa_switch_unregister_notifier(ds); + if (ds->devlink) { list_for_each_entry(dp, &ds->dst->ports, list) if (dp->ds == ds) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 11ec9e689589..499f8d18c76d 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -789,6 +789,37 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) return -EOPNOTSUPP; } +static void dsa_slave_get_eth_phy_stats(struct net_device *dev, + struct ethtool_eth_phy_stats *phy_stats) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_eth_phy_stats) + ds->ops->get_eth_phy_stats(ds, dp->index, phy_stats); +} + +static void dsa_slave_get_eth_mac_stats(struct net_device *dev, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_eth_mac_stats) + ds->ops->get_eth_mac_stats(ds, dp->index, mac_stats); +} + +static void +dsa_slave_get_eth_ctrl_stats(struct net_device *dev, + struct ethtool_eth_ctrl_stats *ctrl_stats) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_eth_ctrl_stats) + ds->ops->get_eth_ctrl_stats(ds, dp->index, ctrl_stats); +} + static void dsa_slave_net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { @@ -1695,6 +1726,9 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_strings = dsa_slave_get_strings, .get_ethtool_stats = dsa_slave_get_ethtool_stats, .get_sset_count = dsa_slave_get_sset_count, + .get_eth_phy_stats = dsa_slave_get_eth_phy_stats, + .get_eth_mac_stats = dsa_slave_get_eth_mac_stats, + .get_eth_ctrl_stats = dsa_slave_get_eth_ctrl_stats, .set_wol = dsa_slave_set_wol, .get_wol = dsa_slave_get_wol, .set_eee = dsa_slave_set_eee, diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 1c797ec8e2c2..6466d0539af9 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -168,7 +168,7 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, if (extack._msg) dev_err(ds->dev, "port %d: %s\n", info->port, extack._msg); - if (err && err != EOPNOTSUPP) + if (err && err != -EOPNOTSUPP) return err; } diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 77d0ce89ab77..b3da4b2ea11c 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -45,6 +45,7 @@ * 6 6 2 2 4 2 N */ +#include <linux/dsa/mv88e6xxx.h> #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> @@ -129,12 +130,9 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, u8 tag_dev, tag_port; enum dsa_cmd cmd; u8 *dsa_header; - u16 pvid = 0; - int err; if (skb->offload_fwd_mark) { struct dsa_switch_tree *dst = dp->ds->dst; - struct net_device *br = dp->bridge_dev; cmd = DSA_CMD_FORWARD; @@ -144,19 +142,6 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, */ tag_dev = dst->last_switch + 1 + dp->bridge_num; tag_port = 0; - - /* If we are offloading forwarding for a VLAN-unaware bridge, - * inject packets to hardware using the bridge's pvid, since - * that's where the packets ingressed from. - */ - if (!br_vlan_enabled(br)) { - /* Safe because __dev_queue_xmit() runs under - * rcu_read_lock_bh() - */ - err = br_vlan_get_pvid_rcu(br, &pvid); - if (err) - return NULL; - } } else { cmd = DSA_CMD_FROM_CPU; tag_dev = dp->ds->index; @@ -180,16 +165,21 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, dsa_header[2] &= ~0x10; } } else { + struct net_device *br = dp->bridge_dev; + u16 vid; + + vid = br ? MV88E6XXX_VID_BRIDGED : MV88E6XXX_VID_STANDALONE; + skb_push(skb, DSA_HLEN + extra); dsa_alloc_etype_header(skb, DSA_HLEN + extra); - /* Construct untagged DSA tag. */ + /* Construct DSA header from untagged frame. */ dsa_header = dsa_etype_header_pos_tx(skb) + extra; dsa_header[0] = (cmd << 6) | tag_dev; dsa_header[1] = tag_port << 3; - dsa_header[2] = pvid >> 8; - dsa_header[3] = pvid & 0xff; + dsa_header[2] = vid >> 8; + dsa_header[3] = vid & 0xff; } return skb; @@ -210,7 +200,7 @@ static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, cmd = dsa_header[0] >> 6; switch (cmd) { case DSA_CMD_FORWARD: - trunk = !!(dsa_header[1] & 7); + trunk = !!(dsa_header[1] & 4); break; case DSA_CMD_TO_CPU: diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index d1d070523ea3..cd60b94fc175 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -2,7 +2,6 @@ /* Copyright 2019 NXP */ #include <linux/dsa/ocelot.h> -#include <soc/mscc/ocelot.h> #include "dsa_priv.h" /* If the port is under a VLAN-aware bridge, remove the VLAN header from the diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 59072930cb02..3412051981d7 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -9,10 +9,32 @@ * that on egress */ #include <linux/dsa/8021q.h> -#include <soc/mscc/ocelot.h> -#include <soc/mscc/ocelot_ptp.h> +#include <linux/dsa/ocelot.h> #include "dsa_priv.h" +static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, + struct sk_buff *skb) +{ + struct felix_deferred_xmit_work *xmit_work; + struct felix_port *felix_port = dp->priv; + + xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC); + if (!xmit_work) + return NULL; + + /* Calls felix_port_deferred_xmit in felix.c */ + kthread_init_work(&xmit_work->work, felix_port->xmit_work_fn); + /* Increase refcount so the kfree_skb in dsa_slave_xmit + * won't really free the packet. + */ + xmit_work->dp = dp; + xmit_work->skb = skb_get(skb); + + kthread_queue_work(felix_port->xmit_worker, &xmit_work->work); + + return NULL; +} + static struct sk_buff *ocelot_xmit(struct sk_buff *skb, struct net_device *netdev) { @@ -20,18 +42,10 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); - struct ocelot *ocelot = dp->ds->priv; - int port = dp->index; - u32 rew_op = 0; + struct ethhdr *hdr = eth_hdr(skb); - rew_op = ocelot_ptp_rew_op(skb); - if (rew_op) { - if (!ocelot_can_inject(ocelot, 0)) - return NULL; - - ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); - return NULL; - } + if (ocelot_ptp_rew_op(skb) || is_link_local_ether_addr(hdr->h_dest)) + return ocelot_defer_xmit(dp, skb); return dsa_8021q_xmit(skb, netdev, ETH_P_8021Q, ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); diff --git a/net/dsa/tag_rtl8_4.c b/net/dsa/tag_rtl8_4.c new file mode 100644 index 000000000000..02686ad4045d --- /dev/null +++ b/net/dsa/tag_rtl8_4.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Handler for Realtek 8 byte switch tags + * + * Copyright (C) 2021 Alvin Šipraga <alsi@bang-olufsen.dk> + * + * NOTE: Currently only supports protocol "4" found in the RTL8365MB, hence + * named tag_rtl8_4. + * + * This tag header has the following format: + * + * ------------------------------------------- + * | MAC DA | MAC SA | 8 byte tag | Type | ... + * ------------------------------------------- + * _______________/ \______________________________________ + * / \ + * 0 7|8 15 + * |-----------------------------------+-----------------------------------|--- + * | (16-bit) | ^ + * | Realtek EtherType [0x8899] | | + * |-----------------------------------+-----------------------------------| 8 + * | (8-bit) | (8-bit) | + * | Protocol [0x04] | REASON | b + * |-----------------------------------+-----------------------------------| y + * | (1) | (1) | (2) | (1) | (3) | (1) | (1) | (1) | (5) | t + * | FID_EN | X | FID | PRI_EN | PRI | KEEP | X | LEARN_DIS | X | e + * |-----------------------------------+-----------------------------------| s + * | (1) | (15-bit) | | + * | ALLOW | TX/RX | v + * |-----------------------------------+-----------------------------------|--- + * + * With the following field descriptions: + * + * field | description + * ------------+------------- + * Realtek | 0x8899: indicates that this is a proprietary Realtek tag; + * EtherType | note that Realtek uses the same EtherType for + * | other incompatible tag formats (e.g. tag_rtl4_a.c) + * Protocol | 0x04: indicates that this tag conforms to this format + * X | reserved + * ------------+------------- + * REASON | reason for forwarding packet to CPU + * | 0: packet was forwarded or flooded to CPU + * | 80: packet was trapped to CPU + * FID_EN | 1: packet has an FID + * | 0: no FID + * FID | FID of packet (if FID_EN=1) + * PRI_EN | 1: force priority of packet + * | 0: don't force priority + * PRI | priority of packet (if PRI_EN=1) + * KEEP | preserve packet VLAN tag format + * LEARN_DIS | don't learn the source MAC address of the packet + * ALLOW | 1: treat TX/RX field as an allowance port mask, meaning the + * | packet may only be forwarded to ports specified in the + * | mask + * | 0: no allowance port mask, TX/RX field is the forwarding + * | port mask + * TX/RX | TX (switch->CPU): port number the packet was received on + * | RX (CPU->switch): forwarding port mask (if ALLOW=0) + * | allowance port mask (if ALLOW=1) + */ + +#include <linux/bitfield.h> +#include <linux/bits.h> +#include <linux/etherdevice.h> + +#include "dsa_priv.h" + +/* Protocols supported: + * + * 0x04 = RTL8365MB DSA protocol + */ + +#define RTL8_4_TAG_LEN 8 + +#define RTL8_4_PROTOCOL GENMASK(15, 8) +#define RTL8_4_PROTOCOL_RTL8365MB 0x04 +#define RTL8_4_REASON GENMASK(7, 0) +#define RTL8_4_REASON_FORWARD 0 +#define RTL8_4_REASON_TRAP 80 + +#define RTL8_4_LEARN_DIS BIT(5) + +#define RTL8_4_TX GENMASK(3, 0) +#define RTL8_4_RX GENMASK(10, 0) + +static struct sk_buff *rtl8_4_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + __be16 *tag; + + skb_push(skb, RTL8_4_TAG_LEN); + + dsa_alloc_etype_header(skb, RTL8_4_TAG_LEN); + tag = dsa_etype_header_pos_tx(skb); + + /* Set Realtek EtherType */ + tag[0] = htons(ETH_P_REALTEK); + + /* Set Protocol; zero REASON */ + tag[1] = htons(FIELD_PREP(RTL8_4_PROTOCOL, RTL8_4_PROTOCOL_RTL8365MB)); + + /* Zero FID_EN, FID, PRI_EN, PRI, KEEP; set LEARN_DIS */ + tag[2] = htons(FIELD_PREP(RTL8_4_LEARN_DIS, 1)); + + /* Zero ALLOW; set RX (CPU->switch) forwarding port mask */ + tag[3] = htons(FIELD_PREP(RTL8_4_RX, BIT(dp->index))); + + return skb; +} + +static struct sk_buff *rtl8_4_tag_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + __be16 *tag; + u16 etype; + u8 reason; + u8 proto; + u8 port; + + if (unlikely(!pskb_may_pull(skb, RTL8_4_TAG_LEN))) + return NULL; + + tag = dsa_etype_header_pos_rx(skb); + + /* Parse Realtek EtherType */ + etype = ntohs(tag[0]); + if (unlikely(etype != ETH_P_REALTEK)) { + dev_warn_ratelimited(&dev->dev, + "non-realtek ethertype 0x%04x\n", etype); + return NULL; + } + + /* Parse Protocol */ + proto = FIELD_GET(RTL8_4_PROTOCOL, ntohs(tag[1])); + if (unlikely(proto != RTL8_4_PROTOCOL_RTL8365MB)) { + dev_warn_ratelimited(&dev->dev, + "unknown realtek protocol 0x%02x\n", + proto); + return NULL; + } + + /* Parse REASON */ + reason = FIELD_GET(RTL8_4_REASON, ntohs(tag[1])); + + /* Parse TX (switch->CPU) */ + port = FIELD_GET(RTL8_4_TX, ntohs(tag[3])); + skb->dev = dsa_master_find_slave(dev, 0, port); + if (!skb->dev) { + dev_warn_ratelimited(&dev->dev, + "could not find slave for port %d\n", + port); + return NULL; + } + + /* Remove tag and recalculate checksum */ + skb_pull_rcsum(skb, RTL8_4_TAG_LEN); + + dsa_strip_etype_header(skb, RTL8_4_TAG_LEN); + + if (reason != RTL8_4_REASON_TRAP) + dsa_default_offload_fwd_mark(skb); + + return skb; +} + +static const struct dsa_device_ops rtl8_4_netdev_ops = { + .name = "rtl8_4", + .proto = DSA_TAG_PROTO_RTL8_4, + .xmit = rtl8_4_tag_xmit, + .rcv = rtl8_4_tag_rcv, + .needed_headroom = RTL8_4_TAG_LEN, +}; +module_dsa_tag_driver(rtl8_4_netdev_ops); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL8_4); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index d7b8fa10fabb..c7d9e08107cb 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -524,6 +524,26 @@ int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr) EXPORT_SYMBOL(eth_platform_get_mac_address); /** + * platform_get_ethdev_address - Set netdev's MAC address from a given device + * @dev: Pointer to the device + * @netdev: Pointer to netdev to write the address to + * + * Wrapper around eth_platform_get_mac_address() which writes the address + * directly to netdev->dev_addr. + */ +int platform_get_ethdev_address(struct device *dev, struct net_device *netdev) +{ + u8 addr[ETH_ALEN] __aligned(2); + int ret; + + ret = eth_platform_get_mac_address(dev, addr); + if (!ret) + eth_hw_addr_set(netdev, addr); + return ret; +} +EXPORT_SYMBOL(platform_get_ethdev_address); + +/** * nvmem_get_mac_address - Obtain the MAC address from an nvmem cell named * 'mac-address' associated with given device. * @@ -558,7 +578,6 @@ int nvmem_get_mac_address(struct device *dev, void *addrbuf) return 0; } -EXPORT_SYMBOL(nvmem_get_mac_address); static int fwnode_get_mac_addr(struct fwnode_handle *fwnode, const char *name, char *addr) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 8b30cadff708..b7e277d8a84d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -1054,14 +1054,19 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) iio = skb_header_pointer(skb, sizeof(_ext_hdr), sizeof(iio->extobj_hdr), &_iio); if (!ext_hdr || !iio) goto send_mal_query; - if (ntohs(iio->extobj_hdr.length) <= sizeof(iio->extobj_hdr)) + if (ntohs(iio->extobj_hdr.length) <= sizeof(iio->extobj_hdr) || + ntohs(iio->extobj_hdr.length) > sizeof(_iio)) goto send_mal_query; ident_len = ntohs(iio->extobj_hdr.length) - sizeof(iio->extobj_hdr); + iio = skb_header_pointer(skb, sizeof(_ext_hdr), + sizeof(iio->extobj_hdr) + ident_len, &_iio); + if (!iio) + goto send_mal_query; + status = 0; dev = NULL; switch (iio->extobj_hdr.class_type) { case ICMP_EXT_ECHO_CTYPE_NAME: - iio = skb_header_pointer(skb, sizeof(_ext_hdr), sizeof(_iio), &_iio); if (ident_len >= IFNAMSIZ) goto send_mal_query; memset(buff, 0, sizeof(buff)); @@ -1069,30 +1074,24 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) dev = dev_get_by_name(net, buff); break; case ICMP_EXT_ECHO_CTYPE_INDEX: - iio = skb_header_pointer(skb, sizeof(_ext_hdr), sizeof(iio->extobj_hdr) + - sizeof(iio->ident.ifindex), &_iio); if (ident_len != sizeof(iio->ident.ifindex)) goto send_mal_query; dev = dev_get_by_index(net, ntohl(iio->ident.ifindex)); break; case ICMP_EXT_ECHO_CTYPE_ADDR: - if (ident_len != sizeof(iio->ident.addr.ctype3_hdr) + + if (ident_len < sizeof(iio->ident.addr.ctype3_hdr) || + ident_len != sizeof(iio->ident.addr.ctype3_hdr) + iio->ident.addr.ctype3_hdr.addrlen) goto send_mal_query; switch (ntohs(iio->ident.addr.ctype3_hdr.afi)) { case ICMP_AFI_IP: - iio = skb_header_pointer(skb, sizeof(_ext_hdr), sizeof(iio->extobj_hdr) + - sizeof(struct in_addr), &_iio); - if (ident_len != sizeof(iio->ident.addr.ctype3_hdr) + - sizeof(struct in_addr)) + if (iio->ident.addr.ctype3_hdr.addrlen != sizeof(struct in_addr)) goto send_mal_query; dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr); break; #if IS_ENABLED(CONFIG_IPV6) case ICMP_AFI_IP6: - iio = skb_header_pointer(skb, sizeof(_ext_hdr), sizeof(_iio), &_iio); - if (ident_len != sizeof(iio->ident.addr.ctype3_hdr) + - sizeof(struct in6_addr)) + if (iio->ident.addr.ctype3_hdr.addrlen != sizeof(struct in6_addr)) goto send_mal_query; dev = ipv6_stub->ipv6_dev_find(net, &iio->ident.addr.ip_addr.ipv6_addr, dev); dev_hold(dev); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f25d02ad4a8a..f7fea3a7c5e6 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1015,7 +1015,7 @@ void inet_csk_destroy_sock(struct sock *sk) sk_refcnt_debug_release(sk); - percpu_counter_dec(sk->sk_prot->orphan_count); + this_cpu_dec(*sk->sk_prot->orphan_count); sock_put(sk); } @@ -1074,7 +1074,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, sock_orphan(child); - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(*sk->sk_prot->orphan_count); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 80aeaf9e6e16..75737267746f 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -242,8 +242,10 @@ static inline int compute_score(struct sock *sk, struct net *net, if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) return -1; + score = sk->sk_bound_dev_if ? 2 : 1; - score = sk->sk_family == PF_INET ? 2 : 1; + if (sk->sk_family == PF_INET) + score++; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } @@ -596,7 +598,7 @@ bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ok) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); } else { - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(*sk->sk_prot->orphan_count); inet_sk_set_state(sk, TCP_CLOSE); sock_set_flag(sk, SOCK_DEAD); inet_csk_destroy_sock(sk); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0fe6c936dc54..2ac2b95c5694 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -986,7 +986,7 @@ static int ipgre_tunnel_init(struct net_device *dev) __gre_tunnel_init(dev); - memcpy(dev->dev_addr, &iph->saddr, 4); + __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index fe9101d3d69e..5a473319d3a5 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -834,7 +834,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; if (dev->type != ARPHRD_ETHER) { - memcpy(dev->dev_addr, &p->iph.saddr, 4); + __dev_addr_set(dev, &p->iph.saddr, 4); memcpy(dev->broadcast, &p->iph.daddr, 4); } ip_tunnel_add(itn, t); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index efe25a0172e6..8c2bd1d9ddce 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -425,7 +425,7 @@ static int vti_tunnel_init(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; - memcpy(dev->dev_addr, &iph->saddr, 4); + __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 3aa78ccbec3e..123ea63a04cb 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -380,7 +380,7 @@ static int ipip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); + __dev_addr_set(dev, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); tunnel->tun_hlen = 0; diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 613432a36f0a..e61ea428ea18 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -20,13 +20,8 @@ #endif #include <net/netfilter/nf_conntrack_zones.h> -static unsigned int defrag4_pernet_id __read_mostly; static DEFINE_MUTEX(defrag4_mutex); -struct defrag4_pernet { - unsigned int users; -}; - static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb, u_int32_t user) { @@ -111,19 +106,15 @@ static const struct nf_hook_ops ipv4_defrag_ops[] = { static void __net_exit defrag4_net_exit(struct net *net) { - struct defrag4_pernet *nf_defrag = net_generic(net, defrag4_pernet_id); - - if (nf_defrag->users) { + if (net->nf.defrag_ipv4_users) { nf_unregister_net_hooks(net, ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops)); - nf_defrag->users = 0; + net->nf.defrag_ipv4_users = 0; } } static struct pernet_operations defrag4_net_ops = { .exit = defrag4_net_exit, - .id = &defrag4_pernet_id, - .size = sizeof(struct defrag4_pernet), }; static int __init nf_defrag_init(void) @@ -138,24 +129,23 @@ static void __exit nf_defrag_fini(void) int nf_defrag_ipv4_enable(struct net *net) { - struct defrag4_pernet *nf_defrag = net_generic(net, defrag4_pernet_id); int err = 0; mutex_lock(&defrag4_mutex); - if (nf_defrag->users == UINT_MAX) { + if (net->nf.defrag_ipv4_users == UINT_MAX) { err = -EOVERFLOW; goto out_unlock; } - if (nf_defrag->users) { - nf_defrag->users++; + if (net->nf.defrag_ipv4_users) { + net->nf.defrag_ipv4_users++; goto out_unlock; } err = nf_register_net_hooks(net, ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops)); if (err == 0) - nf_defrag->users = 1; + net->nf.defrag_ipv4_users = 1; out_unlock: mutex_unlock(&defrag4_mutex); @@ -165,12 +155,10 @@ EXPORT_SYMBOL_GPL(nf_defrag_ipv4_enable); void nf_defrag_ipv4_disable(struct net *net) { - struct defrag4_pernet *nf_defrag = net_generic(net, defrag4_pernet_id); - mutex_lock(&defrag4_mutex); - if (nf_defrag->users) { - nf_defrag->users--; - if (nf_defrag->users == 0) + if (net->nf.defrag_ipv4_users) { + net->nf.defrag_ipv4_users--; + if (net->nf.defrag_ipv4_users == 0) nf_unregister_net_hooks(net, ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops)); } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index b0d3a09dc84e..f30273afb539 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -53,7 +53,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) struct net *net = seq->private; int orphans, sockets; - orphans = percpu_counter_sum_positive(&tcp_orphan_count); + orphans = tcp_orphan_count_sum(); sockets = proto_sockets_allocated_sum_positive(&tcp_prot); socket_seq_show(seq); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 414c179c28e0..c2d9830136d2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -287,8 +287,8 @@ enum { TCP_CMSG_TS = 2 }; -struct percpu_counter tcp_orphan_count; -EXPORT_SYMBOL_GPL(tcp_orphan_count); +DEFINE_PER_CPU(unsigned int, tcp_orphan_count); +EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); long sysctl_tcp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_tcp_mem); @@ -2673,11 +2673,36 @@ void tcp_shutdown(struct sock *sk, int how) } EXPORT_SYMBOL(tcp_shutdown); +int tcp_orphan_count_sum(void) +{ + int i, total = 0; + + for_each_possible_cpu(i) + total += per_cpu(tcp_orphan_count, i); + + return max(total, 0); +} + +static int tcp_orphan_cache; +static struct timer_list tcp_orphan_timer; +#define TCP_ORPHAN_TIMER_PERIOD msecs_to_jiffies(100) + +static void tcp_orphan_update(struct timer_list *unused) +{ + WRITE_ONCE(tcp_orphan_cache, tcp_orphan_count_sum()); + mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); +} + +static bool tcp_too_many_orphans(int shift) +{ + return READ_ONCE(tcp_orphan_cache) << shift > sysctl_tcp_max_orphans; +} + bool tcp_check_oom(struct sock *sk, int shift) { bool too_many_orphans, out_of_socket_memory; - too_many_orphans = tcp_too_many_orphans(sk, shift); + too_many_orphans = tcp_too_many_orphans(shift); out_of_socket_memory = tcp_out_of_memory(sk); if (too_many_orphans) @@ -2786,7 +2811,7 @@ adjudge_to_death: /* remove backlog if any, without releasing ownership. */ __release_sock(sk); - percpu_counter_inc(sk->sk_prot->orphan_count); + this_cpu_inc(tcp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) @@ -4479,7 +4504,10 @@ void __init tcp_init(void) sizeof_field(struct sk_buff, cb)); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); - percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); + + timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE); + mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); + inet_hashinfo_init(&tcp_hashinfo); inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash", thash_entries, 21, /* one slot per 2 MB*/ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 2a7825a5b842..8536b2a7210b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -390,7 +390,8 @@ static int compute_score(struct sock *sk, struct net *net, dif, sdif); if (!dev_match) return -1; - score += 4; + if (sk->sk_bound_dev_if) + score += 4; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c6a90b7bbb70..d4fae16deec4 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2237,12 +2237,12 @@ static int addrconf_ifid_6lowpan(u8 *eui, struct net_device *dev) static int addrconf_ifid_ieee1394(u8 *eui, struct net_device *dev) { - union fwnet_hwaddr *ha; + const union fwnet_hwaddr *ha; if (dev->addr_len != FWNET_ALEN) return -1; - ha = (union fwnet_hwaddr *)dev->dev_addr; + ha = (const union fwnet_hwaddr *)dev->dev_addr; memcpy(eui, &ha->uc.uniq_id, sizeof(ha->uc.uniq_id)); eui[0] ^= 2; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 55c290d55605..67c9114835c8 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -106,7 +106,7 @@ static inline int compute_score(struct sock *sk, struct net *net, if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) return -1; - score = 1; + score = sk->sk_bound_dev_if ? 2 : 1; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c index 4e5583dbadac..122a3d47424c 100644 --- a/net/ipv6/ioam6.c +++ b/net/ipv6/ioam6.c @@ -770,6 +770,66 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, data += sizeof(__be32); } + /* bit12 undefined: filled with empty value */ + if (trace->type.bit12) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* bit13 undefined: filled with empty value */ + if (trace->type.bit13) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* bit14 undefined: filled with empty value */ + if (trace->type.bit14) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* bit15 undefined: filled with empty value */ + if (trace->type.bit15) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* bit16 undefined: filled with empty value */ + if (trace->type.bit16) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* bit17 undefined: filled with empty value */ + if (trace->type.bit17) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* bit18 undefined: filled with empty value */ + if (trace->type.bit18) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* bit19 undefined: filled with empty value */ + if (trace->type.bit19) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* bit20 undefined: filled with empty value */ + if (trace->type.bit20) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + + /* bit21 undefined: filled with empty value */ + if (trace->type.bit21) { + *(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE); + data += sizeof(__be32); + } + /* opaque state snapshot */ if (trace->type.bit22) { if (!sc) { @@ -792,16 +852,10 @@ void ioam6_fill_trace_data(struct sk_buff *skb, struct ioam6_schema *sc; u8 sclen = 0; - /* Skip if Overflow flag is set OR - * if an unknown type (bit 12-21) is set + /* Skip if Overflow flag is set */ - if (trace->overflow || - trace->type.bit12 | trace->type.bit13 | trace->type.bit14 | - trace->type.bit15 | trace->type.bit16 | trace->type.bit17 | - trace->type.bit18 | trace->type.bit19 | trace->type.bit20 | - trace->type.bit21) { + if (trace->overflow) return; - } /* NodeLen does not include Opaque State Snapshot length. We need to * take it into account if the corresponding bit is set (bit 22) and diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index 392c183076ce..f90a87389fcc 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -67,7 +67,11 @@ static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace) u32 fields; if (!trace->type_be32 || !trace->remlen || - trace->remlen > IOAM6_TRACE_DATA_SIZE_MAX / 4) + trace->remlen > IOAM6_TRACE_DATA_SIZE_MAX / 4 || + trace->type.bit12 | trace->type.bit13 | trace->type.bit14 | + trace->type.bit15 | trace->type.bit16 | trace->type.bit17 | + trace->type.bit18 | trace->type.bit19 | trace->type.bit20 | + trace->type.bit21) return false; trace->nodelen = 0; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3ad201d372d8..d831d2439693 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1088,7 +1088,7 @@ static void ip6gre_tnl_link_config_common(struct ip6_tnl *t) struct flowi6 *fl6 = &t->fl.u.ip6; if (dev->type != ARPHRD_ETHER) { - memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); } @@ -1521,7 +1521,7 @@ static int ip6gre_tunnel_init(struct net_device *dev) if (tunnel->parms.collect_md) return 0; - memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr)); + __dev_addr_set(dev, &tunnel->parms.laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &tunnel->parms.raddr, sizeof(struct in6_addr)); if (ipv6_addr_any(&tunnel->parms.raddr)) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 20a67efda47f..484aca492cc0 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1449,7 +1449,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) unsigned int mtu; int t_hlen; - memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 1d8e3ffa225d..527e9ead7449 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -660,7 +660,7 @@ static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu) struct net_device *tdev = NULL; int mtu; - memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); + __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV | diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 4b098521a44c..184190b9ea25 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -142,7 +142,7 @@ struct neigh_table nd_tbl = { }; EXPORT_SYMBOL_GPL(nd_tbl); -void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, +void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, int data_len, int pad) { int space = __ndisc_opt_addr_space(data_len, pad); @@ -165,7 +165,7 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option); static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type, - void *data, u8 icmp6_type) + const void *data, u8 icmp6_type) { __ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len, ndisc_addr_option_pad(skb->dev->type)); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index a0108415275f..5c47be29b9ee 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -33,7 +33,7 @@ static const char nf_frags_cache_name[] = "nf-frags"; -unsigned int nf_frag_pernet_id __read_mostly; +static unsigned int nf_frag_pernet_id __read_mostly; static struct inet_frags nf_frags; static struct nft_ct_frag6_pernet *nf_frag_pernet(struct net *net) diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index e8a59d8bf2ad..cb4eb1d2c620 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -25,8 +25,6 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> -extern unsigned int nf_frag_pernet_id; - static DEFINE_MUTEX(defrag6_mutex); static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, @@ -91,12 +89,10 @@ static const struct nf_hook_ops ipv6_defrag_ops[] = { static void __net_exit defrag6_net_exit(struct net *net) { - struct nft_ct_frag6_pernet *nf_frag = net_generic(net, nf_frag_pernet_id); - - if (nf_frag->users) { + if (net->nf.defrag_ipv6_users) { nf_unregister_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); - nf_frag->users = 0; + net->nf.defrag_ipv6_users = 0; } } @@ -134,24 +130,23 @@ static void __exit nf_defrag_fini(void) int nf_defrag_ipv6_enable(struct net *net) { - struct nft_ct_frag6_pernet *nf_frag = net_generic(net, nf_frag_pernet_id); int err = 0; mutex_lock(&defrag6_mutex); - if (nf_frag->users == UINT_MAX) { + if (net->nf.defrag_ipv6_users == UINT_MAX) { err = -EOVERFLOW; goto out_unlock; } - if (nf_frag->users) { - nf_frag->users++; + if (net->nf.defrag_ipv6_users) { + net->nf.defrag_ipv6_users++; goto out_unlock; } err = nf_register_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); if (err == 0) - nf_frag->users = 1; + net->nf.defrag_ipv6_users = 1; out_unlock: mutex_unlock(&defrag6_mutex); @@ -161,12 +156,10 @@ EXPORT_SYMBOL_GPL(nf_defrag_ipv6_enable); void nf_defrag_ipv6_disable(struct net *net) { - struct nft_ct_frag6_pernet *nf_frag = net_generic(net, nf_frag_pernet_id); - mutex_lock(&defrag6_mutex); - if (nf_frag->users) { - nf_frag->users--; - if (nf_frag->users == 0) + if (net->nf.defrag_ipv6_users) { + net->nf.defrag_ipv6_users--; + if (net->nf.defrag_ipv6_users == 0) nf_unregister_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index ef0c7a7c18e2..1b57ee36d668 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -204,7 +204,7 @@ static int ipip6_tunnel_create(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); int err; - memcpy(dev->dev_addr, &t->parms.iph.saddr, 4); + __dev_addr_set(dev, &t->parms.iph.saddr, 4); memcpy(dev->broadcast, &t->parms.iph.daddr, 4); if ((__force u16)t->parms.i_flags & SIT_ISATAP) @@ -1149,7 +1149,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p, synchronize_net(); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; - memcpy(t->dev->dev_addr, &p->iph.saddr, 4); + __dev_addr_set(t->dev, &p->iph.saddr, 4); memcpy(t->dev->broadcast, &p->iph.daddr, 4); ipip6_tunnel_link(sitn, t); t->parms.iph.ttl = p->iph.ttl; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e505bb007e9f..8d785232b479 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -133,7 +133,8 @@ static int compute_score(struct sock *sk, struct net *net, dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif); if (!dev_match) return -1; - score++; + if (sk->sk_bound_dev_if) + score++; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 647c0554d04c..40ca3c1e42a2 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -781,7 +781,7 @@ int llc_conn_ac_send_sabme_cmd_p_set_x(struct sock *sk, struct sk_buff *skb) if (nskb) { struct llc_sap *sap = llc->sap; - u8 *dmac = llc->daddr.mac; + const u8 *dmac = llc->daddr.mac; if (llc->dev->flags & IFF_LOOPBACK) dmac = llc->dev->dev_addr; diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c index ad6547736c21..dde9bf08a593 100644 --- a/net/llc/llc_if.c +++ b/net/llc/llc_if.c @@ -80,7 +80,7 @@ out_free: * establishment will inform to upper layer via calling it's confirm * function and passing proper information. */ -int llc_establish_connection(struct sock *sk, u8 *lmac, u8 *dmac, u8 dsap) +int llc_establish_connection(struct sock *sk, const u8 *lmac, u8 *dmac, u8 dsap) { int rc = -EISCONN; struct llc_addr laddr, daddr; diff --git a/net/llc/llc_output.c b/net/llc/llc_output.c index b9ad087bcbd7..5a6466fc626a 100644 --- a/net/llc/llc_output.c +++ b/net/llc/llc_output.c @@ -56,7 +56,7 @@ int llc_mac_hdr_init(struct sk_buff *skb, * package primitive as an event and send to SAP event handler */ int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, - unsigned char *dmac, unsigned char dsap) + const unsigned char *dmac, unsigned char dsap) { int rc; llc_pdu_header_init(skb, LLC_PDU_TYPE_U, sap->laddr.lsap, diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c index a4eccb98220a..0ff490a73fae 100644 --- a/net/llc/llc_proc.c +++ b/net/llc/llc_proc.c @@ -26,7 +26,7 @@ #include <net/llc_c_st.h> #include <net/llc_conn.h> -static void llc_ui_format_mac(struct seq_file *seq, u8 *addr) +static void llc_ui_format_mac(struct seq_file *seq, const u8 *addr) { seq_printf(seq, "%pM", addr); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 2b5acb37587f..a39830418434 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -513,6 +513,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->cparams.target = MS2TIME(20); sta->cparams.interval = MS2TIME(100); sta->cparams.ecn = true; + sta->cparams.ce_threshold_ect1 = false; sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); diff --git a/net/mctp/route.c b/net/mctp/route.c index 04781459b2be..82fb5ae524f6 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -372,6 +372,7 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) trace_mctp_key_acquire(key); /* we don't need to release key->lock on exit */ + mctp_key_unref(key); key = NULL; } else { @@ -584,6 +585,9 @@ static int mctp_alloc_local_tag(struct mctp_sock *msk, trace_mctp_key_acquire(key); *tagp = key->tag; + /* done with the key in this scope */ + mctp_key_unref(key); + key = NULL; rc = 0; } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 050eea231528..7b96be1e9f14 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -654,9 +654,9 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) } } -int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, - struct mptcp_addr_info *addr, - u8 bkup) +static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, + struct mptcp_addr_info *addr, + u8 bkup) { struct mptcp_subflow_context *subflow; @@ -2052,6 +2052,9 @@ static int __net_init pm_nl_init_net(struct net *net) struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id); INIT_LIST_HEAD_RCU(&pernet->local_addr_list); + + /* Cit. 2 subflows ought to be enough for anybody. */ + pernet->subflows_max = 2; pernet->next_id = 1; pernet->stale_loss_cnt = 4; spin_lock_init(&pernet->lock); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index fda47011b19c..cd6b11c9b54d 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -528,7 +528,6 @@ static bool mptcp_check_data_fin(struct sock *sk) sk->sk_shutdown |= RCV_SHUTDOWN; smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ - set_bit(MPTCP_DATA_READY, &msk->flags); switch (sk->sk_state) { case TCP_ESTABLISHED: @@ -742,10 +741,9 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); - if (move_skbs_to_msk(msk, ssk)) { - set_bit(MPTCP_DATA_READY, &msk->flags); + if (move_skbs_to_msk(msk, ssk)) sk->sk_data_ready(sk); - } + mptcp_data_unlock(sk); } @@ -847,7 +845,6 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk) sk->sk_shutdown |= RCV_SHUTDOWN; smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ - set_bit(MPTCP_DATA_READY, &msk->flags); sk->sk_data_ready(sk); } @@ -1801,21 +1798,6 @@ out: return copied ? : ret; } -static void mptcp_wait_data(struct sock *sk, long *timeo) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - struct mptcp_sock *msk = mptcp_sk(sk); - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - - sk_wait_event(sk, timeo, - test_bit(MPTCP_DATA_READY, &msk->flags), &wait); - - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); -} - static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, struct msghdr *msg, size_t len, int flags, @@ -2119,19 +2101,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } pr_debug("block timeout %ld", timeo); - mptcp_wait_data(sk, &timeo); - } - - if (skb_queue_empty_lockless(&sk->sk_receive_queue) && - skb_queue_empty(&msk->receive_queue)) { - /* entire backlog drained, clear DATA_READY. */ - clear_bit(MPTCP_DATA_READY, &msk->flags); - - /* .. race-breaker: ssk might have gotten new data - * after last __mptcp_move_skbs() returned false. - */ - if (unlikely(__mptcp_move_skbs(msk))) - set_bit(MPTCP_DATA_READY, &msk->flags); + sk_wait_data(sk, &timeo, NULL); } out_err: @@ -2140,9 +2110,9 @@ out_err: tcp_recv_timestamp(msg, sk, &tss); } - pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d", - msk, test_bit(MPTCP_DATA_READY, &msk->flags), - skb_queue_empty_lockless(&sk->sk_receive_queue), copied); + pr_debug("msk=%p rx queue empty=%d:%d copied=%d", + msk, skb_queue_empty_lockless(&sk->sk_receive_queue), + skb_queue_empty(&msk->receive_queue), copied); if (!(flags & MSG_PEEK)) mptcp_rcv_space_adjust(msk, copied); @@ -2406,7 +2376,6 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) inet_sk_state_store(sk, TCP_CLOSE); sk->sk_shutdown = SHUTDOWN_MASK; smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ - set_bit(MPTCP_DATA_READY, &msk->flags); set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags); mptcp_close_wake_up(sk); @@ -3429,8 +3398,14 @@ unlock_fail: static __poll_t mptcp_check_readable(struct mptcp_sock *msk) { - return test_bit(MPTCP_DATA_READY, &msk->flags) ? EPOLLIN | EPOLLRDNORM : - 0; + /* Concurrent splices from sk_receive_queue into receive_queue will + * always show at least one non-empty queue when checked in this order. + */ + if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) && + skb_queue_empty_lockless(&msk->receive_queue)) + return 0; + + return EPOLLIN | EPOLLRDNORM; } static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) @@ -3465,7 +3440,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, state = inet_sk_state_load(sk); pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags); if (state == TCP_LISTEN) - return mptcp_check_readable(msk); + return test_bit(MPTCP_DATA_READY, &msk->flags) ? EPOLLIN | EPOLLRDNORM : 0; if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { mask |= mptcp_check_readable(msk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 7379ab580a7e..284fdcec067e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -736,9 +736,6 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk); void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup); -int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, - struct mptcp_addr_info *addr, - u8 bkup); void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq); void mptcp_pm_free_anno_list(struct mptcp_sock *msk); bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 8137cc3a4296..0f1e661c2032 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -861,6 +861,9 @@ static void mptcp_get_sub_addrs(const struct sock *sk, struct mptcp_subflow_addr } else if (sk->sk_family == AF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); + if (WARN_ON_ONCE(!np)) + return; + a->sin6_local.sin6_family = AF_INET6; a->sin6_local.sin6_port = inet->inet_sport; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index b9546defdc28..c0851fec11d4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -780,6 +780,7 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) { struct nftables_pernet *nft_net; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -790,8 +791,11 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_table_info(skb, ctx->net, ctx->portid, ctx->seq, - event, 0, ctx->family, ctx->table); + event, flags, ctx->family, ctx->table); if (err < 0) { kfree_skb(skb); goto err; @@ -1563,6 +1567,7 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) { struct nftables_pernet *nft_net; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -1573,8 +1578,11 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_chain_info(skb, ctx->net, ctx->portid, ctx->seq, - event, 0, ctx->family, ctx->table, + event, flags, ctx->family, ctx->table, ctx->chain); if (err < 0) { kfree_skb(skb); @@ -2866,8 +2874,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, - const struct nft_rule *rule, - const struct nft_rule *prule) + const struct nft_rule *rule, u64 handle) { struct nlmsghdr *nlh; const struct nft_expr *expr, *next; @@ -2887,9 +2894,8 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, NFTA_RULE_PAD)) goto nla_put_failure; - if (event != NFT_MSG_DELRULE && prule) { - if (nla_put_be64(skb, NFTA_RULE_POSITION, - cpu_to_be64(prule->handle), + if (event != NFT_MSG_DELRULE && handle) { + if (nla_put_be64(skb, NFTA_RULE_POSITION, cpu_to_be64(handle), NFTA_RULE_PAD)) goto nla_put_failure; } @@ -2925,7 +2931,10 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, const struct nft_rule *rule, int event) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); + const struct nft_rule *prule; struct sk_buff *skb; + u64 handle = 0; + u16 flags = 0; int err; if (!ctx->report && @@ -2936,9 +2945,20 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, if (skb == NULL) goto err; + if (event == NFT_MSG_NEWRULE && + !list_is_first(&rule->list, &ctx->chain->rules) && + !list_is_last(&rule->list, &ctx->chain->rules)) { + prule = list_prev_entry(rule, list); + handle = prule->handle; + } + if (ctx->flags & (NLM_F_APPEND | NLM_F_REPLACE)) + flags |= NLM_F_APPEND; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq, - event, 0, ctx->family, ctx->table, - ctx->chain, rule, NULL); + event, flags, ctx->family, ctx->table, + ctx->chain, rule, handle); if (err < 0) { kfree_skb(skb); goto err; @@ -2964,6 +2984,7 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, struct net *net = sock_net(skb->sk); const struct nft_rule *rule, *prule; unsigned int s_idx = cb->args[0]; + u64 handle; prule = NULL; list_for_each_entry_rcu(rule, &chain->rules, list) { @@ -2975,12 +2996,17 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); } + if (prule) + handle = prule->handle; + else + handle = 0; + if (nf_tables_fill_rule_info(skb, net, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, - table, chain, rule, prule) < 0) + table, chain, rule, handle) < 0) return 1; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -3143,7 +3169,7 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, - family, table, chain, rule, NULL); + family, table, chain, rule, 0); if (err < 0) goto err_fill_rule_info; @@ -3403,17 +3429,15 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, } if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { + err = nft_delrule(&ctx, old_rule); + if (err < 0) + goto err_destroy_flow_rule; + trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; goto err_destroy_flow_rule; } - err = nft_delrule(&ctx, old_rule); - if (err < 0) { - nft_trans_destroy(trans); - goto err_destroy_flow_rule; - } - list_add_tail_rcu(&rule->list, &old_rule->list); } else { trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); @@ -3943,8 +3967,9 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, gfp_t gfp_flags) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); - struct sk_buff *skb; u32 portid = ctx->portid; + struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -3955,7 +3980,10 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, if (skb == NULL) goto err; - err = nf_tables_fill_set(skb, ctx, set, event, 0); + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + + err = nf_tables_fill_set(skb, ctx, set, event, flags); if (err < 0) { kfree_skb(skb); goto err; @@ -5231,12 +5259,13 @@ static int nf_tables_getsetelem(struct sk_buff *skb, static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_set_elem *elem, - int event, u16 flags) + int event) { struct nftables_pernet *nft_net; struct net *net = ctx->net; u32 portid = ctx->portid; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) @@ -5246,6 +5275,9 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags, set, elem); if (err < 0) { @@ -6921,7 +6953,7 @@ static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, - int family, int report, gfp_t gfp) + u16 flags, int family, int report, gfp_t gfp) { struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *skb; @@ -6946,8 +6978,9 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, if (skb == NULL) goto err; - err = nf_tables_fill_obj_info(skb, net, portid, seq, event, 0, family, - table, obj, false); + err = nf_tables_fill_obj_info(skb, net, portid, seq, event, + flags & (NLM_F_CREATE | NLM_F_EXCL), + family, table, obj, false); if (err < 0) { kfree_skb(skb); goto err; @@ -6964,7 +6997,7 @@ static void nf_tables_obj_notify(const struct nft_ctx *ctx, struct nft_object *obj, int event) { nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event, - ctx->family, ctx->report, GFP_KERNEL); + ctx->flags, ctx->family, ctx->report, GFP_KERNEL); } /* @@ -7745,6 +7778,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -7755,8 +7789,11 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_flowtable_info(skb, ctx->net, ctx->portid, - ctx->seq, event, 0, + ctx->seq, event, flags, ctx->family, flowtable, hook_list); if (err < 0) { kfree_skb(skb); @@ -8634,7 +8671,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_setelem_activate(net, te->set, &te->elem); nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, - NFT_MSG_NEWSETELEM, 0); + NFT_MSG_NEWSETELEM); nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: @@ -8642,7 +8679,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, - NFT_MSG_DELSETELEM, 0); + NFT_MSG_DELSETELEM); nft_setelem_remove(net, te->set, &te->elem); if (!nft_setelem_is_catchall(te->set, &te->elem)) { atomic_dec(&te->set->nelems); diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 0363f533a42b..c4d1389f7185 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -60,7 +60,7 @@ static void nft_quota_obj_eval(struct nft_object *obj, if (overquota && !test_and_set_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags)) nft_obj_notify(nft_net(pkt), obj->key.table, obj, 0, 0, - NFT_MSG_NEWOBJ, nft_pf(pkt), 0, GFP_ATOMIC); + NFT_MSG_NEWOBJ, 0, nft_pf(pkt), 0, GFP_ATOMIC); } static int nft_quota_do_init(const struct nlattr * const tb[], diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 0d5c422f8745..8aec1b529364 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -94,11 +94,11 @@ static unsigned int xt_rateest_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_rateest_target_info *info = par->targinfo; - struct gnet_stats_basic_packed *stats = &info->est->bstats; + struct gnet_stats_basic_sync *stats = &info->est->bstats; spin_lock_bh(&info->est->lock); - stats->bytes += skb->len; - stats->packets++; + u64_stats_add(&stats->bytes, skb->len); + u64_stats_inc(&stats->packets); spin_unlock_bh(&info->est->lock); return XT_CONTINUE; @@ -143,6 +143,7 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) if (!est) goto err1; + gnet_stats_basic_sync_init(&est->bstats); strlcpy(est->name, info->name, sizeof(est->name)); spin_lock_init(&est->lock); est->refcnt = 1; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4f5f93fd6802..4c575324a985 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -594,7 +594,10 @@ static int netlink_insert(struct sock *sk, u32 portid) /* We need to ensure that the socket is hashed and visible. */ smp_wmb(); - nlk_sk(sk)->bound = portid; + /* Paired with lockless reads from netlink_bind(), + * netlink_connect() and netlink_sendmsg(). + */ + WRITE_ONCE(nlk_sk(sk)->bound, portid); err: release_sock(sk); @@ -1012,7 +1015,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nlk->ngroups < BITS_PER_LONG) groups &= (1UL << nlk->ngroups) - 1; - bound = nlk->bound; + /* Paired with WRITE_ONCE() in netlink_insert() */ + bound = READ_ONCE(nlk->bound); if (bound) { /* Ensure nlk->portid is up-to-date. */ smp_rmb(); @@ -1098,8 +1102,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, /* No need for barriers here as we return to user-space without * using any of the bound attributes. + * Paired with WRITE_ONCE() in netlink_insert(). */ - if (!nlk->bound) + if (!READ_ONCE(nlk->bound)) err = netlink_autobind(sock); if (err == 0) { @@ -1869,7 +1874,8 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) dst_group = nlk->dst_group; } - if (!nlk->bound) { + /* Paired with WRITE_ONCE() in netlink_insert() */ + if (!READ_ONCE(nlk->bound)) { err = netlink_autobind(sock); if (err) goto out; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 6d16e1ab1a8a..775064cdd0ee 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -633,7 +633,7 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); struct sockaddr_ax25 *addr = (struct sockaddr_ax25 *)uaddr; - ax25_address *source = NULL; + const ax25_address *source = NULL; ax25_uid_assoc *user; struct net_device *dev; int err = 0; @@ -673,7 +673,7 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr, err = -ENETUNREACH; goto out_release; } - source = (ax25_address *)dev->dev_addr; + source = (const ax25_address *)dev->dev_addr; user = ax25_findbyuid(current_euid()); if (user) { diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index 29e418c8c6c3..3aaac4a22b38 100644 --- a/net/netrom/nr_dev.c +++ b/net/netrom/nr_dev.c @@ -108,10 +108,10 @@ static int __must_check nr_set_mac_address(struct net_device *dev, void *addr) if (err) return err; - ax25_listen_release((ax25_address *)dev->dev_addr, NULL); + ax25_listen_release((const ax25_address *)dev->dev_addr, NULL); } - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -120,7 +120,7 @@ static int nr_open(struct net_device *dev) { int err; - err = ax25_listen_register((ax25_address *)dev->dev_addr, NULL); + err = ax25_listen_register((const ax25_address *)dev->dev_addr, NULL); if (err) return err; @@ -131,7 +131,7 @@ static int nr_open(struct net_device *dev) static int nr_close(struct net_device *dev) { - ax25_listen_release((ax25_address *)dev->dev_addr, NULL); + ax25_listen_release((const ax25_address *)dev->dev_addr, NULL); netif_stop_queue(dev); return 0; } diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index ddd5cbd455e3..baea3cbd76ca 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -598,7 +598,7 @@ struct net_device *nr_dev_get(ax25_address *addr) rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { if ((dev->flags & IFF_UP) && dev->type == ARPHRD_NETROM && - ax25cmp(addr, (ax25_address *)dev->dev_addr) == 0) { + ax25cmp(addr, (const ax25_address *)dev->dev_addr) == 0) { dev_hold(dev); goto out; } @@ -825,7 +825,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) ax25s = nr_neigh->ax25; nr_neigh->ax25 = ax25_send_frame(skb, 256, - (ax25_address *)dev->dev_addr, + (const ax25_address *)dev->dev_addr, &nr_neigh->callsign, nr_neigh->digipeat, nr_neigh->dev); if (ax25s) diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c index 6024fad905ff..dda323e0a473 100644 --- a/net/nfc/af_nfc.c +++ b/net/nfc/af_nfc.c @@ -60,6 +60,9 @@ int nfc_proto_register(const struct nfc_protocol *nfc_proto) proto_tab[nfc_proto->id] = nfc_proto; write_unlock(&proto_tab_lock); + if (rc) + proto_unregister(nfc_proto->proto); + return rc; } EXPORT_SYMBOL(nfc_proto_register); diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index fefc03674f4f..d63d2e5dc60c 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -277,6 +277,7 @@ int digital_tg_configure_hw(struct nfc_digital_dev *ddev, int type, int param) static int digital_tg_listen_mdaa(struct nfc_digital_dev *ddev, u8 rf_tech) { struct digital_tg_mdaa_params *params; + int rc; params = kzalloc(sizeof(*params), GFP_KERNEL); if (!params) @@ -291,8 +292,12 @@ static int digital_tg_listen_mdaa(struct nfc_digital_dev *ddev, u8 rf_tech) get_random_bytes(params->nfcid2 + 2, NFC_NFCID2_MAXSIZE - 2); params->sc = DIGITAL_SENSF_FELICA_SC; - return digital_send_cmd(ddev, DIGITAL_CMD_TG_LISTEN_MDAA, NULL, params, - 500, digital_tg_recv_atr_req, NULL); + rc = digital_send_cmd(ddev, DIGITAL_CMD_TG_LISTEN_MDAA, NULL, params, + 500, digital_tg_recv_atr_req, NULL); + if (rc) + kfree(params); + + return rc; } static int digital_tg_listen_md(struct nfc_digital_dev *ddev, u8 rf_tech) diff --git a/net/nfc/digital_technology.c b/net/nfc/digital_technology.c index 84d2345c75a3..3adf4589852a 100644 --- a/net/nfc/digital_technology.c +++ b/net/nfc/digital_technology.c @@ -465,8 +465,12 @@ static int digital_in_send_sdd_req(struct nfc_digital_dev *ddev, skb_put_u8(skb, sel_cmd); skb_put_u8(skb, DIGITAL_SDD_REQ_SEL_PAR); - return digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sdd_res, - target); + rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sdd_res, + target); + if (rc) + kfree_skb(skb); + + return rc; } static void digital_in_recv_sens_res(struct nfc_digital_dev *ddev, void *arg, diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c index 3a89bd9b89fc..af6bacb3ba98 100644 --- a/net/nfc/hci/command.c +++ b/net/nfc/hci/command.c @@ -114,8 +114,6 @@ int nfc_hci_send_cmd(struct nfc_hci_dev *hdev, u8 gate, u8 cmd, { u8 pipe; - pr_debug("\n"); - pipe = hdev->gate2pipe[gate]; if (pipe == NFC_HCI_INVALID_PIPE) return -EADDRNOTAVAIL; @@ -130,8 +128,6 @@ int nfc_hci_send_cmd_async(struct nfc_hci_dev *hdev, u8 gate, u8 cmd, { u8 pipe; - pr_debug("\n"); - pipe = hdev->gate2pipe[gate]; if (pipe == NFC_HCI_INVALID_PIPE) return -EADDRNOTAVAIL; @@ -205,8 +201,6 @@ static int nfc_hci_open_pipe(struct nfc_hci_dev *hdev, u8 pipe) static int nfc_hci_close_pipe(struct nfc_hci_dev *hdev, u8 pipe) { - pr_debug("\n"); - return nfc_hci_execute_cmd(hdev, pipe, NFC_HCI_ANY_CLOSE_PIPE, NULL, 0, NULL); } @@ -242,8 +236,6 @@ static u8 nfc_hci_create_pipe(struct nfc_hci_dev *hdev, u8 dest_host, static int nfc_hci_delete_pipe(struct nfc_hci_dev *hdev, u8 pipe) { - pr_debug("\n"); - return nfc_hci_execute_cmd(hdev, NFC_HCI_ADMIN_PIPE, NFC_HCI_ADM_DELETE_PIPE, &pipe, 1, NULL); } @@ -256,8 +248,6 @@ static int nfc_hci_clear_all_pipes(struct nfc_hci_dev *hdev) /* TODO: Find out what the identity reference data is * and fill param with it. HCI spec 6.1.3.5 */ - pr_debug("\n"); - if (test_bit(NFC_HCI_QUIRK_SHORT_CLEAR, &hdev->quirks)) param_len = 0; @@ -271,8 +261,6 @@ int nfc_hci_disconnect_gate(struct nfc_hci_dev *hdev, u8 gate) int r; u8 pipe = hdev->gate2pipe[gate]; - pr_debug("\n"); - if (pipe == NFC_HCI_INVALID_PIPE) return -EADDRNOTAVAIL; @@ -296,8 +284,6 @@ int nfc_hci_disconnect_all_gates(struct nfc_hci_dev *hdev) { int r; - pr_debug("\n"); - r = nfc_hci_clear_all_pipes(hdev); if (r < 0) return r; @@ -314,8 +300,6 @@ int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate, bool pipe_created = false; int r; - pr_debug("\n"); - if (pipe == NFC_HCI_DO_NOT_CREATE_PIPE) return 0; diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index 71e10347e6a9..e90f70385813 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -363,8 +363,6 @@ static int llc_shdlc_connect_initiate(const struct llc_shdlc *shdlc) { struct sk_buff *skb; - pr_debug("\n"); - skb = llc_shdlc_alloc_skb(shdlc, 2); if (skb == NULL) return -ENOMEM; @@ -379,8 +377,6 @@ static int llc_shdlc_connect_send_ua(const struct llc_shdlc *shdlc) { struct sk_buff *skb; - pr_debug("\n"); - skb = llc_shdlc_alloc_skb(shdlc, 0); if (skb == NULL) return -ENOMEM; @@ -570,8 +566,6 @@ static void llc_shdlc_connect_timeout(struct timer_list *t) { struct llc_shdlc *shdlc = from_timer(shdlc, t, connect_timer); - pr_debug("\n"); - schedule_work(&shdlc->sm_work); } @@ -598,8 +592,6 @@ static void llc_shdlc_sm_work(struct work_struct *work) struct llc_shdlc *shdlc = container_of(work, struct llc_shdlc, sm_work); int r; - pr_debug("\n"); - mutex_lock(&shdlc->state_mutex); switch (shdlc->state) { @@ -681,8 +673,6 @@ static int llc_shdlc_connect(struct llc_shdlc *shdlc) { DECLARE_WAIT_QUEUE_HEAD_ONSTACK(connect_wq); - pr_debug("\n"); - mutex_lock(&shdlc->state_mutex); shdlc->state = SHDLC_CONNECTING; @@ -701,8 +691,6 @@ static int llc_shdlc_connect(struct llc_shdlc *shdlc) static void llc_shdlc_disconnect(struct llc_shdlc *shdlc) { - pr_debug("\n"); - mutex_lock(&shdlc->state_mutex); shdlc->state = SHDLC_DISCONNECTED; diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 3c4172a5aeb5..41e3a20c8935 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -337,8 +337,6 @@ int nfc_llcp_send_disconnect(struct nfc_llcp_sock *sock) struct nfc_dev *dev; struct nfc_llcp_local *local; - pr_debug("Sending DISC\n"); - local = sock->local; if (local == NULL) return -ENODEV; @@ -362,8 +360,6 @@ int nfc_llcp_send_symm(struct nfc_dev *dev) struct nfc_llcp_local *local; u16 size = 0; - pr_debug("Sending SYMM\n"); - local = nfc_llcp_find_local(dev); if (local == NULL) return -ENODEV; @@ -399,8 +395,6 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) u16 size = 0; __be16 miux; - pr_debug("Sending CONNECT\n"); - local = sock->local; if (local == NULL) return -ENODEV; @@ -475,8 +469,6 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) u16 size = 0; __be16 miux; - pr_debug("Sending CC\n"); - local = sock->local; if (local == NULL) return -ENODEV; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index eaeb2b1cfa6a..5ad5157aa9c5 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -45,8 +45,6 @@ static void nfc_llcp_socket_purge(struct nfc_llcp_sock *sock) struct nfc_llcp_local *local = sock->local; struct sk_buff *s, *tmp; - pr_debug("%p\n", &sock->sk); - skb_queue_purge(&sock->tx_queue); skb_queue_purge(&sock->tx_pending_queue); @@ -1505,9 +1503,8 @@ void nfc_llcp_recv(void *data, struct sk_buff *skb, int err) { struct nfc_llcp_local *local = (struct nfc_llcp_local *) data; - pr_debug("Received an LLCP PDU\n"); if (err < 0) { - pr_err("err %d\n", err); + pr_err("LLCP PDU receive err %d\n", err); return; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 82ab39d80726..6fd873aa86be 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -930,8 +930,6 @@ static void nci_deactivate_target(struct nfc_dev *nfc_dev, struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); unsigned long nci_mode = NCI_DEACTIVATE_TYPE_IDLE_MODE; - pr_debug("entry\n"); - if (!ndev->target_active_prot) { pr_err("unable to deactivate target, no active target\n"); return; @@ -977,8 +975,6 @@ static int nci_dep_link_down(struct nfc_dev *nfc_dev) struct nci_dev *ndev = nfc_get_drvdata(nfc_dev); int rc; - pr_debug("entry\n"); - if (nfc_dev->rf_mode == NFC_RF_INITIATOR) { nci_deactivate_target(nfc_dev, NULL, NCI_DEACTIVATE_TYPE_IDLE_MODE); } else { diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index e199912ee1e5..19703a649b5a 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -432,8 +432,6 @@ void nci_hci_data_received_cb(void *context, struct sk_buff *frag_skb; int msg_len; - pr_debug("\n"); - if (err) { nci_req_complete(ndev, err); return; @@ -547,8 +545,6 @@ static u8 nci_hci_create_pipe(struct nci_dev *ndev, u8 dest_host, static int nci_hci_delete_pipe(struct nci_dev *ndev, u8 pipe) { - pr_debug("\n"); - return nci_hci_send_cmd(ndev, NCI_HCI_ADMIN_GATE, NCI_HCI_ADM_DELETE_PIPE, &pipe, 1, NULL); } diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index c5eacaac41ae..282c51051dcc 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -738,8 +738,6 @@ static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev, const struct nci_nfcee_discover_ntf *nfcee_ntf = (struct nci_nfcee_discover_ntf *)skb->data; - pr_debug("\n"); - /* NFCForum NCI 9.2.1 HCI Network Specific Handling * If the NFCC supports the HCI Network, it SHALL return one, * and only one, NFCEE_DISCOVER_NTF with a Protocol type of @@ -751,12 +749,6 @@ static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev, nci_req_complete(ndev, status); } -static void nci_nfcee_action_ntf_packet(struct nci_dev *ndev, - const struct sk_buff *skb) -{ - pr_debug("\n"); -} - void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) { __u16 ntf_opcode = nci_opcode(skb->data); @@ -813,7 +805,6 @@ void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) break; case NCI_OP_RF_NFCEE_ACTION_NTF: - nci_nfcee_action_ntf_packet(ndev, skb); break; default: diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c index a2e72c003805..b911ab78bed9 100644 --- a/net/nfc/nci/rsp.c +++ b/net/nfc/nci/rsp.c @@ -334,6 +334,8 @@ static void nci_core_conn_close_rsp_packet(struct nci_dev *ndev, ndev->cur_conn_id); if (conn_info) { list_del(&conn_info->list); + if (conn_info == ndev->rf_conn_info) + ndev->rf_conn_info = NULL; devm_kfree(&ndev->nfc_dev->dev, conn_info); } } diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index 502e7a3f8948..57500c262cc3 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -1,20 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2015, Marvell International Ltd. * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. - */ - -/* Inspired (hugely) by HCI LDISC implementation in Bluetooth. + * Inspired (hugely) by HCI LDISC implementation in Bluetooth. * * Copyright (C) 2000-2001 Qualcomm Incorporated * Copyright (C) 2002-2003 Maxim Krasnyansky <maxk@qualcomm.com> diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index cf7d974e0f61..30a1cf4c16c6 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -109,7 +109,7 @@ char *rose2asc(char *buf, const rose_address *addr) /* * Compare two ROSE addresses, 0 == equal. */ -int rosecmp(rose_address *addr1, rose_address *addr2) +int rosecmp(const rose_address *addr1, const rose_address *addr2) { int i; @@ -123,7 +123,8 @@ int rosecmp(rose_address *addr1, rose_address *addr2) /* * Compare two ROSE addresses for only mask digits, 0 == equal. */ -int rosecmpm(rose_address *addr1, rose_address *addr2, unsigned short mask) +int rosecmpm(const rose_address *addr1, const rose_address *addr2, + unsigned short mask) { unsigned int i, j; diff --git a/net/rose/rose_dev.c b/net/rose/rose_dev.c index 051804fbee17..f1a76a5820f1 100644 --- a/net/rose/rose_dev.c +++ b/net/rose/rose_dev.c @@ -66,10 +66,10 @@ static int rose_set_mac_address(struct net_device *dev, void *addr) if (err) return err; - rose_del_loopback_node((rose_address *)dev->dev_addr); + rose_del_loopback_node((const rose_address *)dev->dev_addr); } - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); + dev_addr_set(dev, sa->sa_data); return 0; } @@ -78,7 +78,7 @@ static int rose_open(struct net_device *dev) { int err; - err = rose_add_loopback_node((rose_address *)dev->dev_addr); + err = rose_add_loopback_node((const rose_address *)dev->dev_addr); if (err) return err; @@ -90,7 +90,7 @@ static int rose_open(struct net_device *dev) static int rose_close(struct net_device *dev) { netif_stop_queue(dev); - rose_del_loopback_node((rose_address *)dev->dev_addr); + rose_del_loopback_node((const rose_address *)dev->dev_addr); return 0; } diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index f6102e6f5161..8b96a56d3a49 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -94,11 +94,11 @@ static void rose_t0timer_expiry(struct timer_list *t) */ static int rose_send_frame(struct sk_buff *skb, struct rose_neigh *neigh) { - ax25_address *rose_call; + const ax25_address *rose_call; ax25_cb *ax25s; if (ax25cmp(&rose_callsign, &null_ax25_address) == 0) - rose_call = (ax25_address *)neigh->dev->dev_addr; + rose_call = (const ax25_address *)neigh->dev->dev_addr; else rose_call = &rose_callsign; @@ -117,11 +117,11 @@ static int rose_send_frame(struct sk_buff *skb, struct rose_neigh *neigh) */ static int rose_link_up(struct rose_neigh *neigh) { - ax25_address *rose_call; + const ax25_address *rose_call; ax25_cb *ax25s; if (ax25cmp(&rose_callsign, &null_ax25_address) == 0) - rose_call = (ax25_address *)neigh->dev->dev_addr; + rose_call = (const ax25_address *)neigh->dev->dev_addr; else rose_call = &rose_callsign; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index c0e04c261a15..e2e6b6b78578 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -401,7 +401,7 @@ void rose_add_loopback_neigh(void) /* * Add a loopback node. */ -int rose_add_loopback_node(rose_address *address) +int rose_add_loopback_node(const rose_address *address) { struct rose_node *rose_node; int err = 0; @@ -446,7 +446,7 @@ out: /* * Delete a loopback node. */ -void rose_del_loopback_node(rose_address *address) +void rose_del_loopback_node(const rose_address *address) { struct rose_node *rose_node; @@ -629,7 +629,8 @@ struct net_device *rose_dev_get(rose_address *addr) rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { - if ((dev->flags & IFF_UP) && dev->type == ARPHRD_ROSE && rosecmp(addr, (rose_address *)dev->dev_addr) == 0) { + if ((dev->flags & IFF_UP) && dev->type == ARPHRD_ROSE && + rosecmp(addr, (const rose_address *)dev->dev_addr) == 0) { dev_hold(dev); goto out; } @@ -646,7 +647,8 @@ static int rose_dev_exists(rose_address *addr) rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) { - if ((dev->flags & IFF_UP) && dev->type == ARPHRD_ROSE && rosecmp(addr, (rose_address *)dev->dev_addr) == 0) + if ((dev->flags & IFF_UP) && dev->type == ARPHRD_ROSE && + rosecmp(addr, (const rose_address *)dev->dev_addr) == 0) goto out; } dev = NULL; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 7dd3a2dc5fa4..3258da3d5bed 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -480,16 +480,18 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, atomic_set(&p->tcfa_bindcnt, 1); if (cpustats) { - p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); if (!p->cpu_bstats) goto err1; - p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + p->cpu_bstats_hw = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); if (!p->cpu_bstats_hw) goto err2; p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); if (!p->cpu_qstats) goto err3; } + gnet_stats_basic_sync_init(&p->tcfa_bstats); + gnet_stats_basic_sync_init(&p->tcfa_bstats_hw); spin_lock_init(&p->tcfa_lock); p->tcfa_index = index; p->tcfa_tm.install = jiffies; @@ -499,7 +501,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, if (est) { err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats, &p->tcfa_rate_est, - &p->tcfa_lock, NULL, est); + &p->tcfa_lock, false, est); if (err) goto err4; } @@ -1126,13 +1128,13 @@ void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets, u64 drops, bool hw) { if (a->cpu_bstats) { - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); + _bstats_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); this_cpu_ptr(a->cpu_qstats)->drops += drops; if (hw) - _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), - bytes, packets); + _bstats_update(this_cpu_ptr(a->cpu_bstats_hw), + bytes, packets); return; } @@ -1171,9 +1173,10 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p, if (err < 0) goto errout; - if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 || - gnet_stats_copy_basic_hw(NULL, &d, p->cpu_bstats_hw, - &p->tcfa_bstats_hw) < 0 || + if (gnet_stats_copy_basic(&d, p->cpu_bstats, + &p->tcfa_bstats, false) < 0 || + gnet_stats_copy_basic_hw(&d, p->cpu_bstats_hw, + &p->tcfa_bstats_hw, false) < 0 || gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 || gnet_stats_copy_queue(&d, p->cpu_qstats, &p->tcfa_qstats, diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 5c36013339e1..f2bf896331a5 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -41,7 +41,7 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, int action, filter_res; tcf_lastuse_update(&prog->tcf_tm); - bstats_cpu_update(this_cpu_ptr(prog->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(prog->common.cpu_bstats), skb); filter = rcu_dereference(prog->filter); if (at_ingress) { diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 7064a365a1a9..b757f90a2d58 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -718,7 +718,7 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u8 *tlv_data; u16 metalen; - bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); if (skb_at_tc_ingress(skb)) @@ -806,7 +806,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, exceed_mtu = true; } - bstats_cpu_update(this_cpu_ptr(ife->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); if (!metalen) { /* no metadata to send */ diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index e4529b428cf4..8faa4c58305e 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -59,7 +59,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, int ret, mac_len; tcf_lastuse_update(&m->tcf_tm); - bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(m->common.cpu_bstats), skb); /* Ensure 'data' points at mac_header prior calling mpls manipulating * functions. diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 832157a840fc..9e77ba8401e5 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -125,7 +125,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, police->common.cpu_bstats, &police->tcf_rate_est, &police->tcf_lock, - NULL, est); + false, est); if (err) goto failure; } else if (tb[TCA_POLICE_AVRATE] && @@ -248,7 +248,7 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, int ret; tcf_lastuse_update(&police->tcf_tm); - bstats_cpu_update(this_cpu_ptr(police->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(police->common.cpu_bstats), skb); ret = READ_ONCE(police->tcf_action); p = rcu_dereference_bh(police->params); diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 230501eb9e06..ce859b0e0deb 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -163,7 +163,7 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, int retval; tcf_lastuse_update(&s->tcf_tm); - bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(s->common.cpu_bstats), skb); retval = READ_ONCE(s->tcf_action); psample_group = rcu_dereference_bh(s->psample_group); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index cbbe1861d3a2..e617ab4505ca 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -36,7 +36,8 @@ static int tcf_simp_act(struct sk_buff *skb, const struct tc_action *a, * then it would look like "hello_3" (without quotes) */ pr_info("simple: %s_%llu\n", - (char *)d->tcfd_defdata, d->tcf_bstats.packets); + (char *)d->tcfd_defdata, + u64_stats_read(&d->tcf_bstats.packets)); spin_unlock(&d->tcf_lock); return d->tcf_action; } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 605418538347..d30ecbfc8f84 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -31,7 +31,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a, int action; tcf_lastuse_update(&d->tcf_tm); - bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb); params = rcu_dereference_bh(d->params); action = READ_ONCE(d->tcf_action); diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index ecb9ee666095..9b6b52c5e24e 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -31,7 +31,7 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, u64 flags; tcf_lastuse_update(&d->tcf_tm); - bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); + bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb); action = READ_ONCE(d->tcf_action); if (unlikely(action == TC_ACT_SHOT)) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 91820f67275c..efcd0b5e9a32 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -885,7 +885,7 @@ static void qdisc_offload_graft_root(struct net_device *dev, static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, u32 portid, u32 seq, u16 flags, int event) { - struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL; + struct gnet_stats_basic_sync __percpu *cpu_bstats = NULL; struct gnet_stats_queue __percpu *cpu_qstats = NULL; struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -943,8 +943,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, cpu_qstats = q->cpu_qstats; } - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(q), - &d, cpu_bstats, &q->bstats) < 0 || + if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats, true) < 0 || gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 || gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0) goto nla_put_failure; @@ -1265,26 +1264,17 @@ static struct Qdisc *qdisc_create(struct net_device *dev, rcu_assign_pointer(sch->stab, stab); } if (tca[TCA_RATE]) { - seqcount_t *running; - err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { NL_SET_ERR_MSG(extack, "Cannot attach rate estimator to a multi-queue root qdisc"); goto err_out4; } - if (sch->parent != TC_H_ROOT && - !(sch->flags & TCQ_F_INGRESS) && - (!p || !(p->flags & TCQ_F_MQROOT))) - running = qdisc_root_sleeping_running(sch); - else - running = &sch->running; - err = gen_new_estimator(&sch->bstats, sch->cpu_bstats, &sch->rate_est, NULL, - running, + true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to generate new estimator"); @@ -1360,7 +1350,7 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, sch->cpu_bstats, &sch->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); } out: diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 7d8518176b45..4c8e994cf0a5 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -52,7 +52,7 @@ struct atm_flow_data { struct atm_qdisc_data *parent; /* parent qdisc */ struct socket *sock; /* for closing */ int ref; /* reference count */ - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct list_head list; struct atm_flow_data *excess; /* flow for excess traffic; @@ -548,6 +548,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); INIT_LIST_HEAD(&p->flows); INIT_LIST_HEAD(&p->link.list); + gnet_stats_basic_sync_init(&p->link.bstats); list_add(&p->link.list, &p->flows); p->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, extack); @@ -652,8 +653,7 @@ atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, { struct atm_flow_data *flow = (struct atm_flow_data *)arg; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &flow->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &flow->bstats, true) < 0 || gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0) return -1; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index e0da15530f0e..02d9f0dfe356 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -116,7 +116,7 @@ struct cbq_class { long avgidle; long deficit; /* Saved deficit for WRR */ psched_time_t penalized; - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct tc_cbq_xstats xstats; @@ -565,8 +565,7 @@ cbq_update(struct cbq_sched_data *q) long avgidle = cl->avgidle; long idle; - cl->bstats.packets++; - cl->bstats.bytes += len; + _bstats_update(&cl->bstats, len, 1); /* * (now - last) is total time between packet right edges. @@ -1384,8 +1383,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (cl->undertime != PSCHED_PASTPERFECT) cl->xstats.undertime = cl->undertime - q->now; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; @@ -1519,7 +1517,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace specified rate estimator"); @@ -1611,6 +1609,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (cl == NULL) goto failure; + gnet_stats_basic_sync_init(&cl->bstats); err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); @@ -1619,9 +1618,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); + NULL, true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Couldn't create new estimator"); tcf_block_put(cl->block); diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 642cd179b7a7..18e4f7a0b291 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -19,7 +19,7 @@ struct drr_class { struct Qdisc_class_common common; unsigned int filter_cnt; - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct list_head alist; @@ -85,8 +85,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), + NULL, true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace estimator"); @@ -106,6 +105,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; + gnet_stats_basic_sync_init(&cl->bstats); cl->common.classid = classid; cl->quantum = quantum; cl->qdisc = qdisc_create_dflt(sch->dev_queue, @@ -118,9 +118,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); + NULL, true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace estimator"); qdisc_put(cl->qdisc); @@ -267,8 +265,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (qlen) xstats.deficit = cl->deficit; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, cl_q->cpu_qstats, &cl_q->qstats, qlen) < 0) return -1; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 1f857ffd1ac2..0eae9ff5edf6 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -41,7 +41,7 @@ struct ets_class { struct Qdisc *qdisc; u32 quantum; u32 deficit; - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; }; @@ -325,8 +325,7 @@ static int ets_class_dump_stats(struct Qdisc *sch, unsigned long arg, struct ets_class *cl = ets_class_from_arg(sch, arg); struct Qdisc *cl_q = cl->qdisc; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl_q->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats, true) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; @@ -661,7 +660,6 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->nbands = nbands; for (i = nstrict; i < q->nstrict; i++) { - INIT_LIST_HEAD(&q->classes[i].alist); if (q->classes[i].qdisc->q.qlen) { list_add_tail(&q->classes[i].alist, &q->active); q->classes[i].deficit = quanta[i]; @@ -687,7 +685,11 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, ets_offload_change(sch); for (i = q->nbands; i < oldbands; i++) { qdisc_put(q->classes[i].qdisc); - memset(&q->classes[i], 0, sizeof(q->classes[i])); + q->classes[i].qdisc = NULL; + q->classes[i].quantum = 0; + q->classes[i].deficit = 0; + gnet_stats_basic_sync_init(&q->classes[i].bstats); + memset(&q->classes[i].qstats, 0, sizeof(q->classes[i].qstats)); } return 0; } @@ -696,7 +698,7 @@ static int ets_qdisc_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct ets_sched *q = qdisc_priv(sch); - int err; + int err, i; if (!opt) return -EINVAL; @@ -706,6 +708,9 @@ static int ets_qdisc_init(struct Qdisc *sch, struct nlattr *opt, return err; INIT_LIST_HEAD(&q->active); + for (i = 0; i < TCQ_ETS_MAX_BANDS; i++) + INIT_LIST_HEAD(&q->classes[i].alist); + return ets_qdisc_change(sch, opt, extack); } diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index a579a4131d22..e1040421b797 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -233,6 +233,9 @@ int fifo_set_limit(struct Qdisc *q, unsigned int limit) if (strncmp(q->ops->id + 1, "fifo", 4) != 0) return 0; + if (!q->ops->change) + return 0; + nla = kmalloc(nla_attr_size(sizeof(struct tc_fifo_qopt)), GFP_KERNEL); if (nla) { nla->nla_type = RTM_NEWQDISC; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index bb0cd6d3d2c2..033d65d06eb1 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -362,6 +362,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { [TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CODEL_DROP_BATCH_SIZE] = { .type = NLA_U32 }, [TCA_FQ_CODEL_MEMORY_LIMIT] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_CE_THRESHOLD_ECT1] = { .type = NLA_U8 }, }; static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, @@ -408,6 +409,9 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; } + if (tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1]) + q->cparams.ce_threshold_ect1 = !!nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1]); + if (tb[TCA_FQ_CODEL_INTERVAL]) { u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]); @@ -544,10 +548,13 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) q->flows_cnt)) goto nla_put_failure; - if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD && - nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, - codel_time_to_us(q->cparams.ce_threshold))) - goto nla_put_failure; + if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD) { + if (nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, + codel_time_to_us(q->cparams.ce_threshold))) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_ECT1, q->cparams.ce_threshold_ect1)) + goto nla_put_failure; + } return nla_nest_end(skb, opts); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 8c64a552a64f..b0ff0dff2773 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -304,8 +304,8 @@ trace: /* * Transmit possibly several skbs, and handle the return status as - * required. Owning running seqcount bit guarantees that - * only one CPU can execute this function. + * required. Owning qdisc running bit guarantees that only one CPU + * can execute this function. * * Returns to the caller: * false - hardware queue frozen backoff @@ -606,7 +606,6 @@ struct Qdisc noop_qdisc = { .ops = &noop_qdisc_ops, .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, - .running = SEQCNT_ZERO(noop_qdisc.running), .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), .gso_skb = { .next = (struct sk_buff *)&noop_qdisc.gso_skb, @@ -867,7 +866,6 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { EXPORT_SYMBOL(pfifo_fast_ops); static struct lock_class_key qdisc_tx_busylock; -static struct lock_class_key qdisc_running_key; struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, @@ -892,11 +890,12 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, __skb_queue_head_init(&sch->gso_skb); __skb_queue_head_init(&sch->skb_bad_txq); qdisc_skb_head_init(&sch->q); + gnet_stats_basic_sync_init(&sch->bstats); spin_lock_init(&sch->q.lock); if (ops->static_flags & TCQ_F_CPUSTATS) { sch->cpu_bstats = - netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); if (!sch->cpu_bstats) goto errout1; @@ -916,10 +915,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, lockdep_set_class(&sch->seqlock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - seqcount_init(&sch->running); - lockdep_set_class(&sch->running, - dev->qdisc_running_key ?: &qdisc_running_key); - sch->ops = ops; sch->flags = ops->static_flags; sch->enqueue = ops->enqueue; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 621dc6afde8f..72de08ef8335 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -353,6 +353,7 @@ static int gred_offload_dump_stats(struct Qdisc *sch) { struct gred_sched *table = qdisc_priv(sch); struct tc_gred_qopt_offload *hw_stats; + u64 bytes = 0, packets = 0; unsigned int i; int ret; @@ -364,9 +365,11 @@ static int gred_offload_dump_stats(struct Qdisc *sch) hw_stats->handle = sch->handle; hw_stats->parent = sch->parent; - for (i = 0; i < MAX_DPs; i++) + for (i = 0; i < MAX_DPs; i++) { + gnet_stats_basic_sync_init(&hw_stats->stats.bstats[i]); if (table->tab[i]) hw_stats->stats.xstats[i] = &table->tab[i]->stats; + } ret = qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_GRED, hw_stats); /* Even if driver returns failure adjust the stats - in case offload @@ -375,19 +378,19 @@ static int gred_offload_dump_stats(struct Qdisc *sch) for (i = 0; i < MAX_DPs; i++) { if (!table->tab[i]) continue; - table->tab[i]->packetsin += hw_stats->stats.bstats[i].packets; - table->tab[i]->bytesin += hw_stats->stats.bstats[i].bytes; + table->tab[i]->packetsin += u64_stats_read(&hw_stats->stats.bstats[i].packets); + table->tab[i]->bytesin += u64_stats_read(&hw_stats->stats.bstats[i].bytes); table->tab[i]->backlog += hw_stats->stats.qstats[i].backlog; - _bstats_update(&sch->bstats, - hw_stats->stats.bstats[i].bytes, - hw_stats->stats.bstats[i].packets); + bytes += u64_stats_read(&hw_stats->stats.bstats[i].bytes); + packets += u64_stats_read(&hw_stats->stats.bstats[i].packets); sch->qstats.qlen += hw_stats->stats.qstats[i].qlen; sch->qstats.backlog += hw_stats->stats.qstats[i].backlog; sch->qstats.drops += hw_stats->stats.qstats[i].drops; sch->qstats.requeues += hw_stats->stats.qstats[i].requeues; sch->qstats.overlimits += hw_stats->stats.qstats[i].overlimits; } + _bstats_update(&sch->bstats, bytes, packets); kfree(hw_stats); return ret; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index b7ac30cca035..d3979a6000e7 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -111,7 +111,7 @@ enum hfsc_class_flags { struct hfsc_class { struct Qdisc_class_common cl_common; - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct tcf_proto __rcu *filter_list; /* filter list */ @@ -965,7 +965,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; @@ -1033,9 +1033,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); + NULL, true, tca[TCA_RATE]); if (err) { tcf_block_put(cl->block); kfree(cl); @@ -1328,7 +1326,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg, xstats.work = cl->cl_total; xstats.rtwork = cl->cl_cumul; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; @@ -1406,6 +1404,7 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt, if (err) return err; + gnet_stats_basic_sync_init(&q->root.bstats); q->root.cl_common.classid = sch->handle; q->root.sched = q; q->root.qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 5067a6e5d4fd..cf1d45db4e84 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -113,8 +113,8 @@ struct htb_class { /* * Written often fields */ - struct gnet_stats_basic_packed bstats; - struct gnet_stats_basic_packed bstats_bias; + struct gnet_stats_basic_sync bstats; + struct gnet_stats_basic_sync bstats_bias; struct tc_htb_xstats xstats; /* our special stats */ /* token bucket parameters */ @@ -1308,10 +1308,11 @@ nla_put_failure: static void htb_offload_aggregate_stats(struct htb_sched *q, struct htb_class *cl) { + u64 bytes = 0, packets = 0; struct htb_class *c; unsigned int i; - memset(&cl->bstats, 0, sizeof(cl->bstats)); + gnet_stats_basic_sync_init(&cl->bstats); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(c, &q->clhash.hash[i], common.hnode) { @@ -1323,14 +1324,15 @@ static void htb_offload_aggregate_stats(struct htb_sched *q, if (p != cl) continue; - cl->bstats.bytes += c->bstats_bias.bytes; - cl->bstats.packets += c->bstats_bias.packets; + bytes += u64_stats_read(&c->bstats_bias.bytes); + packets += u64_stats_read(&c->bstats_bias.packets); if (c->level == 0) { - cl->bstats.bytes += c->leaf.q->bstats.bytes; - cl->bstats.packets += c->leaf.q->bstats.packets; + bytes += u64_stats_read(&c->leaf.q->bstats.bytes); + packets += u64_stats_read(&c->leaf.q->bstats.packets); } } } + _bstats_update(&cl->bstats, bytes, packets); } static int @@ -1357,16 +1359,16 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) if (cl->leaf.q) cl->bstats = cl->leaf.q->bstats; else - memset(&cl->bstats, 0, sizeof(cl->bstats)); - cl->bstats.bytes += cl->bstats_bias.bytes; - cl->bstats.packets += cl->bstats_bias.packets; + gnet_stats_basic_sync_init(&cl->bstats); + _bstats_update(&cl->bstats, + u64_stats_read(&cl->bstats_bias.bytes), + u64_stats_read(&cl->bstats_bias.packets)); } else { htb_offload_aggregate_stats(q, cl); } } - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &qs, qlen) < 0) return -1; @@ -1578,8 +1580,9 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, WARN_ON(old != q); if (cl->parent) { - cl->parent->bstats_bias.bytes += q->bstats.bytes; - cl->parent->bstats_bias.packets += q->bstats.packets; + _bstats_update(&cl->parent->bstats_bias, + u64_stats_read(&q->bstats.bytes), + u64_stats_read(&q->bstats.packets)); } offload_opt = (struct tc_htb_qopt_offload) { @@ -1849,6 +1852,9 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) goto failure; + gnet_stats_basic_sync_init(&cl->bstats); + gnet_stats_basic_sync_init(&cl->bstats_bias); + err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); @@ -1858,7 +1864,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE] ? : &est.nla); if (err) goto err_block_put; @@ -1922,8 +1928,9 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, htb_graft_helper(dev_queue, old_q); goto err_kill_estimator; } - parent->bstats_bias.bytes += old_q->bstats.bytes; - parent->bstats_bias.packets += old_q->bstats.packets; + _bstats_update(&parent->bstats_bias, + u64_stats_read(&old_q->bstats.bytes), + u64_stats_read(&old_q->bstats.packets)); qdisc_put(old_q); } new_q = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, @@ -1983,7 +1990,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index e04f1a87642b..83d2e54bf303 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -130,10 +130,9 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) struct net_device *dev = qdisc_dev(sch); struct Qdisc *qdisc; unsigned int ntx; - __u32 qlen = 0; sch->q.qlen = 0; - memset(&sch->bstats, 0, sizeof(sch->bstats)); + gnet_stats_basic_sync_init(&sch->bstats); memset(&sch->qstats, 0, sizeof(sch->qstats)); /* MQ supports lockless qdiscs. However, statistics accounting needs @@ -145,25 +144,11 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; spin_lock_bh(qdisc_lock(qdisc)); - if (qdisc_is_percpu_stats(qdisc)) { - qlen = qdisc_qlen_sum(qdisc); - __gnet_stats_copy_basic(NULL, &sch->bstats, - qdisc->cpu_bstats, - &qdisc->bstats); - __gnet_stats_copy_queue(&sch->qstats, - qdisc->cpu_qstats, - &qdisc->qstats, qlen); - sch->q.qlen += qlen; - } else { - sch->q.qlen += qdisc->q.qlen; - sch->bstats.bytes += qdisc->bstats.bytes; - sch->bstats.packets += qdisc->bstats.packets; - sch->qstats.qlen += qdisc->qstats.qlen; - sch->qstats.backlog += qdisc->qstats.backlog; - sch->qstats.drops += qdisc->qstats.drops; - sch->qstats.requeues += qdisc->qstats.requeues; - sch->qstats.overlimits += qdisc->qstats.overlimits; - } + gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); + gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats, + &qdisc->qstats); + sch->q.qlen += qdisc_qlen(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); } @@ -246,8 +231,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = mq_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(&sch->running, d, sch->cpu_bstats, - &sch->bstats) < 0 || + if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 0bc10234e306..b29f3453c6ea 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -390,7 +390,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) unsigned int ntx, tc; sch->q.qlen = 0; - memset(&sch->bstats, 0, sizeof(sch->bstats)); + gnet_stats_basic_sync_init(&sch->bstats); memset(&sch->qstats, 0, sizeof(sch->qstats)); /* MQ supports lockless qdiscs. However, statistics accounting needs @@ -402,25 +402,11 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; spin_lock_bh(qdisc_lock(qdisc)); - if (qdisc_is_percpu_stats(qdisc)) { - __u32 qlen = qdisc_qlen_sum(qdisc); - - __gnet_stats_copy_basic(NULL, &sch->bstats, - qdisc->cpu_bstats, - &qdisc->bstats); - __gnet_stats_copy_queue(&sch->qstats, - qdisc->cpu_qstats, - &qdisc->qstats, qlen); - sch->q.qlen += qlen; - } else { - sch->q.qlen += qdisc->q.qlen; - sch->bstats.bytes += qdisc->bstats.bytes; - sch->bstats.packets += qdisc->bstats.packets; - sch->qstats.backlog += qdisc->qstats.backlog; - sch->qstats.drops += qdisc->qstats.drops; - sch->qstats.requeues += qdisc->qstats.requeues; - sch->qstats.overlimits += qdisc->qstats.overlimits; - } + gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); + gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats, + &qdisc->qstats); + sch->q.qlen += qdisc_qlen(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); } @@ -512,12 +498,13 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, { if (cl >= TC_H_MIN_PRIORITY) { int i; - __u32 qlen = 0; + __u32 qlen; struct gnet_stats_queue qstats = {0}; - struct gnet_stats_basic_packed bstats = {0}; + struct gnet_stats_basic_sync bstats; struct net_device *dev = qdisc_dev(sch); struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK]; + gnet_stats_basic_sync_init(&bstats); /* Drop lock here it will be reclaimed before touching * statistics this is required because the d->lock we * hold here is the look on dev_queue->qdisc_sleeping @@ -529,37 +516,31 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, for (i = tc.offset; i < tc.offset + tc.count; i++) { struct netdev_queue *q = netdev_get_tx_queue(dev, i); struct Qdisc *qdisc = rtnl_dereference(q->qdisc); - struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL; - struct gnet_stats_queue __percpu *cpu_qstats = NULL; spin_lock_bh(qdisc_lock(qdisc)); - if (qdisc_is_percpu_stats(qdisc)) { - cpu_bstats = qdisc->cpu_bstats; - cpu_qstats = qdisc->cpu_qstats; - } - qlen = qdisc_qlen_sum(qdisc); - __gnet_stats_copy_basic(NULL, &sch->bstats, - cpu_bstats, &qdisc->bstats); - __gnet_stats_copy_queue(&sch->qstats, - cpu_qstats, - &qdisc->qstats, - qlen); + gnet_stats_add_basic(&bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); + gnet_stats_add_queue(&qstats, qdisc->cpu_qstats, + &qdisc->qstats); + sch->q.qlen += qdisc_qlen(qdisc); + spin_unlock_bh(qdisc_lock(qdisc)); } + qlen = qdisc_qlen(sch) + qstats.qlen; /* Reclaim root sleeping lock before completing stats */ if (d->lock) spin_lock_bh(d->lock); - if (gnet_stats_copy_basic(NULL, d, NULL, &bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &bstats, false) < 0 || gnet_stats_copy_queue(d, NULL, &qstats, qlen) < 0) return -1; } else { struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, - sch->cpu_bstats, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(d, sch->cpu_bstats, + &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index e282e7382117..cd8ab90c4765 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -338,8 +338,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || + if (gnet_stats_copy_basic(d, cl_q->cpu_bstats, &cl_q->bstats, true) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 03fdf31ccb6a..3b8d7197c06b 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -361,8 +361,8 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || + if (gnet_stats_copy_basic(d, cl_q->cpu_bstats, + &cl_q->bstats, true) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 58a9d42b52b8..0b7f9ba28deb 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -131,7 +131,7 @@ struct qfq_class { unsigned int filter_cnt; - struct gnet_stats_basic_packed bstats; + struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct Qdisc *qdisc; @@ -451,7 +451,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; @@ -465,6 +465,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; + gnet_stats_basic_sync_init(&cl->bstats); cl->common.classid = classid; cl->deficit = lmax; @@ -477,7 +478,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) goto destroy_class; @@ -639,8 +640,7 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, xstats.weight = cl->agg->class_weight; xstats.lmax = cl->agg->lmax; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || qdisc_qstats_copy(d, cl->qdisc) < 0) return -1; @@ -1234,8 +1234,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } - cl->bstats.bytes += len; - cl->bstats.packets += gso_segs; + _bstats_update(&cl->bstats, len, gso_segs); sch->qstats.backlog += len; ++sch->q.qlen; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 1ab2fc933a21..9ab068fa2672 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1641,6 +1641,10 @@ static void taprio_destroy(struct Qdisc *sch) list_del(&q->taprio_list); spin_unlock(&taprio_list_lock); + /* Note that taprio_reset() might not be called if an error + * happens in qdisc_create(), after taprio_init() has been called. + */ + hrtimer_cancel(&q->advance_timer); taprio_disable_offload(dev, q, NULL); @@ -1973,7 +1977,7 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index b8fa8f1a7277..c7503fd64915 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3697,7 +3697,7 @@ struct sctp_chunk *sctp_make_strreset_req( outlen = (sizeof(outreq) + stream_len) * out; inlen = (sizeof(inreq) + stream_len) * in; - retval = sctp_make_reconf(asoc, outlen + inlen); + retval = sctp_make_reconf(asoc, SCTP_PAD4(outlen) + SCTP_PAD4(inlen)); if (!retval) return NULL; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index f69ef3f2019f..5e50e007a7da 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -439,6 +439,47 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc) return 0; } +static bool smc_isascii(char *hostname) +{ + int i; + + for (i = 0; i < SMC_MAX_HOSTNAME_LEN; i++) + if (!isascii(hostname[i])) + return false; + return true; +} + +static void smc_conn_save_peer_info_fce(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm *clc) +{ + struct smc_clc_msg_accept_confirm_v2 *clc_v2 = + (struct smc_clc_msg_accept_confirm_v2 *)clc; + struct smc_clc_first_contact_ext *fce; + int clc_v2_len; + + if (clc->hdr.version == SMC_V1 || + !(clc->hdr.typev2 & SMC_FIRST_CONTACT_MASK)) + return; + + if (smc->conn.lgr->is_smcd) { + memcpy(smc->conn.lgr->negotiated_eid, clc_v2->d1.eid, + SMC_MAX_EID_LEN); + clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm_v2, + d1); + } else { + memcpy(smc->conn.lgr->negotiated_eid, clc_v2->r1.eid, + SMC_MAX_EID_LEN); + clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm_v2, + r1); + } + fce = (struct smc_clc_first_contact_ext *)(((u8 *)clc_v2) + clc_v2_len); + smc->conn.lgr->peer_os = fce->os_type; + smc->conn.lgr->peer_smc_release = fce->release; + if (smc_isascii(fce->hostname)) + memcpy(smc->conn.lgr->peer_hostname, fce->hostname, + SMC_MAX_HOSTNAME_LEN); +} + static void smcr_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { @@ -451,16 +492,6 @@ static void smcr_conn_save_peer_info(struct smc_sock *smc, smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1); } -static bool smc_isascii(char *hostname) -{ - int i; - - for (i = 0; i < SMC_MAX_HOSTNAME_LEN; i++) - if (!isascii(hostname[i])) - return false; - return true; -} - static void smcd_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { @@ -472,22 +503,6 @@ static void smcd_conn_save_peer_info(struct smc_sock *smc, smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg); atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); smc->conn.tx_off = bufsize * smc->conn.peer_rmbe_idx; - if (clc->hdr.version > SMC_V1 && - (clc->hdr.typev2 & SMC_FIRST_CONTACT_MASK)) { - struct smc_clc_msg_accept_confirm_v2 *clc_v2 = - (struct smc_clc_msg_accept_confirm_v2 *)clc; - struct smc_clc_first_contact_ext *fce = - (struct smc_clc_first_contact_ext *) - (((u8 *)clc_v2) + sizeof(*clc_v2)); - - memcpy(smc->conn.lgr->negotiated_eid, clc_v2->eid, - SMC_MAX_EID_LEN); - smc->conn.lgr->peer_os = fce->os_type; - smc->conn.lgr->peer_smc_release = fce->release; - if (smc_isascii(fce->hostname)) - memcpy(smc->conn.lgr->peer_hostname, fce->hostname, - SMC_MAX_HOSTNAME_LEN); - } } static void smc_conn_save_peer_info(struct smc_sock *smc, @@ -497,14 +512,16 @@ static void smc_conn_save_peer_info(struct smc_sock *smc, smcd_conn_save_peer_info(smc, clc); else smcr_conn_save_peer_info(smc, clc); + smc_conn_save_peer_info_fce(smc, clc); } static void smc_link_save_peer_info(struct smc_link *link, - struct smc_clc_msg_accept_confirm *clc) + struct smc_clc_msg_accept_confirm *clc, + struct smc_init_info *ini) { link->peer_qpn = ntoh24(clc->r0.qpn); - memcpy(link->peer_gid, clc->r0.lcl.gid, SMC_GID_SIZE); - memcpy(link->peer_mac, clc->r0.lcl.mac, sizeof(link->peer_mac)); + memcpy(link->peer_gid, ini->peer_gid, SMC_GID_SIZE); + memcpy(link->peer_mac, ini->peer_mac, sizeof(link->peer_mac)); link->peer_psn = ntoh24(clc->r0.psn); link->peer_mtu = clc->r0.qp_mtu; } @@ -608,7 +625,9 @@ static int smc_find_rdma_device(struct smc_sock *smc, struct smc_init_info *ini) * used for the internal TCP socket */ smc_pnet_find_roce_resource(smc->clcsock->sk, ini); - if (!ini->ib_dev) + if (!ini->check_smcrv2 && !ini->ib_dev) + return SMC_CLC_DECL_NOSMCRDEV; + if (ini->check_smcrv2 && !ini->smcrv2.ib_dev_v2) return SMC_CLC_DECL_NOSMCRDEV; return 0; } @@ -692,27 +711,42 @@ static int smc_find_proposal_devices(struct smc_sock *smc, int rc = 0; /* check if there is an ism device available */ - if (ini->smcd_version & SMC_V1) { - if (smc_find_ism_device(smc, ini) || - smc_connect_ism_vlan_setup(smc, ini)) { - if (ini->smc_type_v1 == SMC_TYPE_B) - ini->smc_type_v1 = SMC_TYPE_R; - else - ini->smc_type_v1 = SMC_TYPE_N; - } /* else ISM V1 is supported for this connection */ - if (smc_find_rdma_device(smc, ini)) { - if (ini->smc_type_v1 == SMC_TYPE_B) - ini->smc_type_v1 = SMC_TYPE_D; - else - ini->smc_type_v1 = SMC_TYPE_N; - } /* else RDMA is supported for this connection */ - } - if (smc_ism_is_v2_capable() && smc_find_ism_v2_device_clnt(smc, ini)) - ini->smc_type_v2 = SMC_TYPE_N; + if (!(ini->smcd_version & SMC_V1) || + smc_find_ism_device(smc, ini) || + smc_connect_ism_vlan_setup(smc, ini)) + ini->smcd_version &= ~SMC_V1; + /* else ISM V1 is supported for this connection */ + + /* check if there is an rdma device available */ + if (!(ini->smcr_version & SMC_V1) || + smc_find_rdma_device(smc, ini)) + ini->smcr_version &= ~SMC_V1; + /* else RDMA is supported for this connection */ + + ini->smc_type_v1 = smc_indicated_type(ini->smcd_version & SMC_V1, + ini->smcr_version & SMC_V1); + + /* check if there is an ism v2 device available */ + if (!(ini->smcd_version & SMC_V2) || + !smc_ism_is_v2_capable() || + smc_find_ism_v2_device_clnt(smc, ini)) + ini->smcd_version &= ~SMC_V2; + + /* check if there is an rdma v2 device available */ + ini->check_smcrv2 = true; + ini->smcrv2.saddr = smc->clcsock->sk->sk_rcv_saddr; + if (!(ini->smcr_version & SMC_V2) || + smc->clcsock->sk->sk_family != AF_INET || + !smc_clc_ueid_count() || + smc_find_rdma_device(smc, ini)) + ini->smcr_version &= ~SMC_V2; + ini->check_smcrv2 = false; + + ini->smc_type_v2 = smc_indicated_type(ini->smcd_version & SMC_V2, + ini->smcr_version & SMC_V2); /* if neither ISM nor RDMA are supported, fallback */ - if (!smcr_indicated(ini->smc_type_v1) && - ini->smc_type_v1 == SMC_TYPE_N && ini->smc_type_v2 == SMC_TYPE_N) + if (ini->smc_type_v1 == SMC_TYPE_N && ini->smc_type_v2 == SMC_TYPE_N) rc = SMC_CLC_DECL_NOSMCDEV; return rc; @@ -752,6 +786,64 @@ static int smc_connect_clc(struct smc_sock *smc, SMC_CLC_ACCEPT, CLC_WAIT_TIME); } +void smc_fill_gid_list(struct smc_link_group *lgr, + struct smc_gidlist *gidlist, + struct smc_ib_device *known_dev, u8 *known_gid) +{ + struct smc_init_info *alt_ini = NULL; + + memset(gidlist, 0, sizeof(*gidlist)); + memcpy(gidlist->list[gidlist->len++], known_gid, SMC_GID_SIZE); + + alt_ini = kzalloc(sizeof(*alt_ini), GFP_KERNEL); + if (!alt_ini) + goto out; + + alt_ini->vlan_id = lgr->vlan_id; + alt_ini->check_smcrv2 = true; + alt_ini->smcrv2.saddr = lgr->saddr; + smc_pnet_find_alt_roce(lgr, alt_ini, known_dev); + + if (!alt_ini->smcrv2.ib_dev_v2) + goto out; + + memcpy(gidlist->list[gidlist->len++], alt_ini->smcrv2.ib_gid_v2, + SMC_GID_SIZE); + +out: + kfree(alt_ini); +} + +static int smc_connect_rdma_v2_prepare(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm *aclc, + struct smc_init_info *ini) +{ + struct smc_clc_msg_accept_confirm_v2 *clc_v2 = + (struct smc_clc_msg_accept_confirm_v2 *)aclc; + struct smc_clc_first_contact_ext *fce = + (struct smc_clc_first_contact_ext *) + (((u8 *)clc_v2) + sizeof(*clc_v2)); + + if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1) + return 0; + + if (fce->v2_direct) { + memcpy(ini->smcrv2.nexthop_mac, &aclc->r0.lcl.mac, ETH_ALEN); + ini->smcrv2.uses_gateway = false; + } else { + if (smc_ib_find_route(smc->clcsock->sk->sk_rcv_saddr, + smc_ib_gid_to_ipv4(aclc->r0.lcl.gid), + ini->smcrv2.nexthop_mac, + &ini->smcrv2.uses_gateway)) + return SMC_CLC_DECL_NOROUTE; + if (!ini->smcrv2.uses_gateway) { + /* mismatch: peer claims indirect, but its direct */ + return SMC_CLC_DECL_NOINDIRECT; + } + } + return 0; +} + /* setup for RDMA connection of client */ static int smc_connect_rdma(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *aclc, @@ -759,11 +851,18 @@ static int smc_connect_rdma(struct smc_sock *smc, { int i, reason_code = 0; struct smc_link *link; + u8 *eid = NULL; ini->is_smcd = false; - ini->ib_lcl = &aclc->r0.lcl; ini->ib_clcqpn = ntoh24(aclc->r0.qpn); ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK; + memcpy(ini->peer_systemid, aclc->r0.lcl.id_for_peer, SMC_SYSTEMID_LEN); + memcpy(ini->peer_gid, aclc->r0.lcl.gid, SMC_GID_SIZE); + memcpy(ini->peer_mac, aclc->r0.lcl.mac, ETH_ALEN); + + reason_code = smc_connect_rdma_v2_prepare(smc, aclc, ini); + if (reason_code) + return reason_code; mutex_lock(&smc_client_lgr_pending); reason_code = smc_conn_create(smc, ini); @@ -785,8 +884,9 @@ static int smc_connect_rdma(struct smc_sock *smc, if (l->peer_qpn == ntoh24(aclc->r0.qpn) && !memcmp(l->peer_gid, &aclc->r0.lcl.gid, SMC_GID_SIZE) && - !memcmp(l->peer_mac, &aclc->r0.lcl.mac, - sizeof(l->peer_mac))) { + (aclc->hdr.version > SMC_V1 || + !memcmp(l->peer_mac, &aclc->r0.lcl.mac, + sizeof(l->peer_mac)))) { link = l; break; } @@ -805,7 +905,7 @@ static int smc_connect_rdma(struct smc_sock *smc, } if (ini->first_contact_local) - smc_link_save_peer_info(link, aclc); + smc_link_save_peer_info(link, aclc, ini); if (smc_rmb_rtoken_handling(&smc->conn, link, aclc)) { reason_code = SMC_CLC_DECL_ERR_RTOK; @@ -828,8 +928,18 @@ static int smc_connect_rdma(struct smc_sock *smc, } smc_rmb_sync_sg_for_device(&smc->conn); + if (aclc->hdr.version > SMC_V1) { + struct smc_clc_msg_accept_confirm_v2 *clc_v2 = + (struct smc_clc_msg_accept_confirm_v2 *)aclc; + + eid = clc_v2->r1.eid; + if (ini->first_contact_local) + smc_fill_gid_list(link->lgr, &ini->smcrv2.gidlist, + link->smcibdev, link->gid); + } + reason_code = smc_clc_send_confirm(smc, ini->first_contact_local, - SMC_V1, NULL); + aclc->hdr.version, eid, ini); if (reason_code) goto connect_abort; @@ -869,7 +979,7 @@ smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm_v2 *aclc, int i; for (i = 0; i < ini->ism_offered_cnt + 1; i++) { - if (ini->ism_chid[i] == ntohs(aclc->chid)) { + if (ini->ism_chid[i] == ntohs(aclc->d1.chid)) { ini->ism_selected = i; return 0; } @@ -923,11 +1033,11 @@ static int smc_connect_ism(struct smc_sock *smc, struct smc_clc_msg_accept_confirm_v2 *clc_v2 = (struct smc_clc_msg_accept_confirm_v2 *)aclc; - eid = clc_v2->eid; + eid = clc_v2->d1.eid; } rc = smc_clc_send_confirm(smc, ini->first_contact_local, - aclc->hdr.version, eid); + aclc->hdr.version, eid, NULL); if (rc) goto connect_abort; mutex_unlock(&smc_server_lgr_pending); @@ -950,17 +1060,24 @@ connect_abort: static int smc_connect_check_aclc(struct smc_init_info *ini, struct smc_clc_msg_accept_confirm *aclc) { - if ((aclc->hdr.typev1 == SMC_TYPE_R && - !smcr_indicated(ini->smc_type_v1)) || - (aclc->hdr.typev1 == SMC_TYPE_D && - ((!smcd_indicated(ini->smc_type_v1) && - !smcd_indicated(ini->smc_type_v2)) || - (aclc->hdr.version == SMC_V1 && - !smcd_indicated(ini->smc_type_v1)) || - (aclc->hdr.version == SMC_V2 && - !smcd_indicated(ini->smc_type_v2))))) + if (aclc->hdr.typev1 != SMC_TYPE_R && + aclc->hdr.typev1 != SMC_TYPE_D) return SMC_CLC_DECL_MODEUNSUPP; + if (aclc->hdr.version >= SMC_V2) { + if ((aclc->hdr.typev1 == SMC_TYPE_R && + !smcr_indicated(ini->smc_type_v2)) || + (aclc->hdr.typev1 == SMC_TYPE_D && + !smcd_indicated(ini->smc_type_v2))) + return SMC_CLC_DECL_MODEUNSUPP; + } else { + if ((aclc->hdr.typev1 == SMC_TYPE_R && + !smcr_indicated(ini->smc_type_v1)) || + (aclc->hdr.typev1 == SMC_TYPE_D && + !smcd_indicated(ini->smc_type_v1))) + return SMC_CLC_DECL_MODEUNSUPP; + } + return 0; } @@ -991,14 +1108,15 @@ static int __smc_connect(struct smc_sock *smc) return smc_connect_decline_fallback(smc, SMC_CLC_DECL_MEM, version); - ini->smcd_version = SMC_V1; - ini->smcd_version |= smc_ism_is_v2_capable() ? SMC_V2 : 0; + ini->smcd_version = SMC_V1 | SMC_V2; + ini->smcr_version = SMC_V1 | SMC_V2; ini->smc_type_v1 = SMC_TYPE_B; - ini->smc_type_v2 = smc_ism_is_v2_capable() ? SMC_TYPE_D : SMC_TYPE_N; + ini->smc_type_v2 = SMC_TYPE_B; /* get vlan id from IP device */ if (smc_vlan_by_tcpsk(smc->clcsock, ini)) { ini->smcd_version &= ~SMC_V1; + ini->smcr_version = 0; ini->smc_type_v1 = SMC_TYPE_N; if (!ini->smcd_version) { rc = SMC_CLC_DECL_GETVLANERR; @@ -1026,15 +1144,17 @@ static int __smc_connect(struct smc_sock *smc) /* check if smc modes and versions of CLC proposal and accept match */ rc = smc_connect_check_aclc(ini, aclc); version = aclc->hdr.version == SMC_V1 ? SMC_V1 : SMC_V2; - ini->smcd_version = version; if (rc) goto vlan_cleanup; /* depending on previous steps, connect using rdma or ism */ - if (aclc->hdr.typev1 == SMC_TYPE_R) + if (aclc->hdr.typev1 == SMC_TYPE_R) { + ini->smcr_version = version; rc = smc_connect_rdma(smc, aclc, ini); - else if (aclc->hdr.typev1 == SMC_TYPE_D) + } else if (aclc->hdr.typev1 == SMC_TYPE_D) { + ini->smcd_version = version; rc = smc_connect_ism(smc, aclc, ini); + } if (rc) goto vlan_cleanup; @@ -1315,7 +1435,7 @@ static int smcr_serv_conf_first_link(struct smc_sock *smc) smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE); /* initial contact - try to establish second link */ - smc_llc_srv_add_link(link); + smc_llc_srv_add_link(link, NULL); return 0; } @@ -1395,33 +1515,48 @@ static int smc_listen_v2_check(struct smc_sock *new_smc, ini->smc_type_v1 = pclc->hdr.typev1; ini->smc_type_v2 = pclc->hdr.typev2; - ini->smcd_version = ini->smc_type_v1 != SMC_TYPE_N ? SMC_V1 : 0; - if (pclc->hdr.version > SMC_V1) - ini->smcd_version |= - ini->smc_type_v2 != SMC_TYPE_N ? SMC_V2 : 0; - if (!(ini->smcd_version & SMC_V2)) { + ini->smcd_version = smcd_indicated(ini->smc_type_v1) ? SMC_V1 : 0; + ini->smcr_version = smcr_indicated(ini->smc_type_v1) ? SMC_V1 : 0; + if (pclc->hdr.version > SMC_V1) { + if (smcd_indicated(ini->smc_type_v2)) + ini->smcd_version |= SMC_V2; + if (smcr_indicated(ini->smc_type_v2)) + ini->smcr_version |= SMC_V2; + } + if (!(ini->smcd_version & SMC_V2) && !(ini->smcr_version & SMC_V2)) { rc = SMC_CLC_DECL_PEERNOSMC; goto out; } - if (!smc_ism_is_v2_capable()) { - ini->smcd_version &= ~SMC_V2; - rc = SMC_CLC_DECL_NOISM2SUPP; - goto out; - } pclc_v2_ext = smc_get_clc_v2_ext(pclc); if (!pclc_v2_ext) { ini->smcd_version &= ~SMC_V2; + ini->smcr_version &= ~SMC_V2; rc = SMC_CLC_DECL_NOV2EXT; goto out; } pclc_smcd_v2_ext = smc_get_clc_smcd_v2_ext(pclc_v2_ext); - if (!pclc_smcd_v2_ext) { - ini->smcd_version &= ~SMC_V2; - rc = SMC_CLC_DECL_NOV2DEXT; + if (ini->smcd_version & SMC_V2) { + if (!smc_ism_is_v2_capable()) { + ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOISM2SUPP; + } else if (!pclc_smcd_v2_ext) { + ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOV2DEXT; + } else if (!pclc_v2_ext->hdr.eid_cnt && + !pclc_v2_ext->hdr.flag.seid) { + ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOUEID; + } + } + if (ini->smcr_version & SMC_V2) { + if (!pclc_v2_ext->hdr.eid_cnt) { + ini->smcr_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOUEID; + } } out: - if (!ini->smcd_version) + if (!ini->smcd_version && !ini->smcr_version) return rc; return 0; @@ -1541,10 +1676,6 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, pclc_smcd = smc_get_clc_msg_smcd(pclc); smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); - if (!smcd_v2_ext) { - smc_find_ism_store_rc(SMC_CLC_DECL_NOV2DEXT, ini); - goto not_found; - } mutex_lock(&smcd_dev_list.mutex); if (pclc_smcd->ism.chid) @@ -1562,8 +1693,10 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, } mutex_unlock(&smcd_dev_list.mutex); - if (!ini->ism_dev[0]) + if (!ini->ism_dev[0]) { + smc_find_ism_store_rc(SMC_CLC_DECL_NOSMCD2DEV, ini); goto not_found; + } smc_ism_get_system_eid(&eid); if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, @@ -1616,6 +1749,7 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, not_found: smc_find_ism_store_rc(rc, ini); + ini->smcd_version &= ~SMC_V1; ini->ism_dev[0] = NULL; ini->is_smcd = false; } @@ -1634,24 +1768,69 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, bool local_first) return 0; } +static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, + struct smc_clc_msg_proposal *pclc, + struct smc_init_info *ini) +{ + struct smc_clc_v2_extension *smc_v2_ext; + u8 smcr_version; + int rc; + + if (!(ini->smcr_version & SMC_V2) || !smcr_indicated(ini->smc_type_v2)) + goto not_found; + + smc_v2_ext = smc_get_clc_v2_ext(pclc); + if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) + goto not_found; + + /* prepare RDMA check */ + memcpy(ini->peer_systemid, pclc->lcl.id_for_peer, SMC_SYSTEMID_LEN); + memcpy(ini->peer_gid, smc_v2_ext->roce, SMC_GID_SIZE); + memcpy(ini->peer_mac, pclc->lcl.mac, ETH_ALEN); + ini->check_smcrv2 = true; + ini->smcrv2.clc_sk = new_smc->clcsock->sk; + ini->smcrv2.saddr = new_smc->clcsock->sk->sk_rcv_saddr; + ini->smcrv2.daddr = smc_ib_gid_to_ipv4(smc_v2_ext->roce); + rc = smc_find_rdma_device(new_smc, ini); + if (rc) { + smc_find_ism_store_rc(rc, ini); + goto not_found; + } + if (!ini->smcrv2.uses_gateway) + memcpy(ini->smcrv2.nexthop_mac, pclc->lcl.mac, ETH_ALEN); + + smcr_version = ini->smcr_version; + ini->smcr_version = SMC_V2; + rc = smc_listen_rdma_init(new_smc, ini); + if (!rc) + rc = smc_listen_rdma_reg(new_smc, ini->first_contact_local); + if (!rc) + return; + ini->smcr_version = smcr_version; + smc_find_ism_store_rc(rc, ini); + +not_found: + ini->smcr_version &= ~SMC_V2; + ini->check_smcrv2 = false; +} + static int smc_find_rdma_v1_device_serv(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { int rc; - if (!smcr_indicated(ini->smc_type_v1)) + if (!(ini->smcr_version & SMC_V1) || !smcr_indicated(ini->smc_type_v1)) return SMC_CLC_DECL_NOSMCDEV; /* prepare RDMA check */ - ini->ib_lcl = &pclc->lcl; + memcpy(ini->peer_systemid, pclc->lcl.id_for_peer, SMC_SYSTEMID_LEN); + memcpy(ini->peer_gid, pclc->lcl.gid, SMC_GID_SIZE); + memcpy(ini->peer_mac, pclc->lcl.mac, ETH_ALEN); rc = smc_find_rdma_device(new_smc, ini); if (rc) { /* no RDMA device found */ - if (ini->smc_type_v1 == SMC_TYPE_B) - /* neither ISM nor RDMA device found */ - rc = SMC_CLC_DECL_NOSMCDEV; - return rc; + return SMC_CLC_DECL_NOSMCDEV; } rc = smc_listen_rdma_init(new_smc, ini); if (rc) @@ -1664,51 +1843,60 @@ static int smc_listen_find_device(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) { - int rc; + int prfx_rc; /* check for ISM device matching V2 proposed device */ smc_find_ism_v2_device_serv(new_smc, pclc, ini); if (ini->ism_dev[0]) return 0; - if (!(ini->smcd_version & SMC_V1)) - return ini->rc ?: SMC_CLC_DECL_NOSMCD2DEV; - - /* check for matching IP prefix and subnet length */ - rc = smc_listen_prfx_check(new_smc, pclc); - if (rc) - return ini->rc ?: rc; + /* check for matching IP prefix and subnet length (V1) */ + prfx_rc = smc_listen_prfx_check(new_smc, pclc); + if (prfx_rc) + smc_find_ism_store_rc(prfx_rc, ini); /* get vlan id from IP device */ if (smc_vlan_by_tcpsk(new_smc->clcsock, ini)) return ini->rc ?: SMC_CLC_DECL_GETVLANERR; /* check for ISM device matching V1 proposed device */ - smc_find_ism_v1_device_serv(new_smc, pclc, ini); + if (!prfx_rc) + smc_find_ism_v1_device_serv(new_smc, pclc, ini); if (ini->ism_dev[0]) return 0; - if (pclc->hdr.typev1 == SMC_TYPE_D) + if (!smcr_indicated(pclc->hdr.typev1) && + !smcr_indicated(pclc->hdr.typev2)) /* skip RDMA and decline */ return ini->rc ?: SMC_CLC_DECL_NOSMCDDEV; - /* check if RDMA is available */ - rc = smc_find_rdma_v1_device_serv(new_smc, pclc, ini); - smc_find_ism_store_rc(rc, ini); + /* check if RDMA V2 is available */ + smc_find_rdma_v2_device_serv(new_smc, pclc, ini); + if (ini->smcrv2.ib_dev_v2) + return 0; - return (!rc) ? 0 : ini->rc; + /* check if RDMA V1 is available */ + if (!prfx_rc) { + int rc; + + rc = smc_find_rdma_v1_device_serv(new_smc, pclc, ini); + smc_find_ism_store_rc(rc, ini); + return (!rc) ? 0 : ini->rc; + } + return SMC_CLC_DECL_NOSMCDEV; } /* listen worker: finish RDMA setup */ static int smc_listen_rdma_finish(struct smc_sock *new_smc, struct smc_clc_msg_accept_confirm *cclc, - bool local_first) + bool local_first, + struct smc_init_info *ini) { struct smc_link *link = new_smc->conn.lnk; int reason_code = 0; if (local_first) - smc_link_save_peer_info(link, cclc); + smc_link_save_peer_info(link, cclc, ini); if (smc_rmb_rtoken_handling(&new_smc->conn, link, cclc)) return SMC_CLC_DECL_ERR_RTOK; @@ -1729,12 +1917,13 @@ static void smc_listen_work(struct work_struct *work) { struct smc_sock *new_smc = container_of(work, struct smc_sock, smc_listen_work); - u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1; struct socket *newclcsock = new_smc->clcsock; struct smc_clc_msg_accept_confirm *cclc; struct smc_clc_msg_proposal_area *buf; struct smc_clc_msg_proposal *pclc; struct smc_init_info *ini = NULL; + u8 proposal_version = SMC_V1; + u8 accept_version; int rc = 0; if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN) @@ -1765,7 +1954,9 @@ static void smc_listen_work(struct work_struct *work) SMC_CLC_PROPOSAL, CLC_WAIT_TIME); if (rc) goto out_decl; - version = pclc->hdr.version == SMC_V1 ? SMC_V1 : version; + + if (pclc->hdr.version > SMC_V1) + proposal_version = SMC_V2; /* IPSec connections opt out of SMC optimizations */ if (using_ipsec(new_smc)) { @@ -1795,9 +1986,9 @@ static void smc_listen_work(struct work_struct *work) goto out_unlock; /* send SMC Accept CLC message */ + accept_version = ini->is_smcd ? ini->smcd_version : ini->smcr_version; rc = smc_clc_send_accept(new_smc, ini->first_contact_local, - ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1, - ini->negotiated_eid); + accept_version, ini->negotiated_eid); if (rc) goto out_unlock; @@ -1819,7 +2010,7 @@ static void smc_listen_work(struct work_struct *work) /* finish worker */ if (!ini->is_smcd) { rc = smc_listen_rdma_finish(new_smc, cclc, - ini->first_contact_local); + ini->first_contact_local, ini); if (rc) goto out_unlock; mutex_unlock(&smc_server_lgr_pending); @@ -1833,7 +2024,7 @@ out_unlock: mutex_unlock(&smc_server_lgr_pending); out_decl: smc_listen_decline(new_smc, rc, ini ? ini->first_contact_local : 0, - version); + proposal_version); out_free: kfree(ini); kfree(buf); diff --git a/net/smc/smc.h b/net/smc/smc.h index 5e7def3ab730..f4286ca1f228 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -56,7 +56,20 @@ enum smc_state { /* possible states of an SMC socket */ struct smc_link_group; struct smc_wr_rx_hdr { /* common prefix part of LLC and CDC to demultiplex */ - u8 type; + union { + u8 type; +#if defined(__BIG_ENDIAN_BITFIELD) + struct { + u8 llc_version:4, + llc_type:4; + }; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + struct { + u8 llc_type:4, + llc_version:4; + }; +#endif + }; } __aligned(1); struct smc_cdc_conn_state_flags { @@ -286,7 +299,12 @@ static inline bool using_ipsec(struct smc_sock *smc) } #endif +struct smc_gidlist; + struct sock *smc_accept_dequeue(struct sock *parent, struct socket *new_sock); void smc_close_non_accepted(struct sock *sk); +void smc_fill_gid_list(struct smc_link_group *lgr, + struct smc_gidlist *gidlist, + struct smc_ib_device *known_dev, u8 *known_gid); #endif /* __SMC_H */ diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index f23f558054a7..99acd337ba90 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -150,9 +150,11 @@ static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn) again: link = conn->lnk; + if (!smc_wr_tx_link_hold(link)) + return -ENOLINK; rc = smc_cdc_get_free_slot(conn, link, &wr_buf, NULL, &pend); if (rc) - return rc; + goto put_out; spin_lock_bh(&conn->send_lock); if (link != conn->lnk) { @@ -160,6 +162,7 @@ again: spin_unlock_bh(&conn->send_lock); smc_wr_tx_put_slot(link, (struct smc_wr_tx_pend_priv *)pend); + smc_wr_tx_link_put(link); if (again) return -ENOLINK; again = true; @@ -167,6 +170,8 @@ again: } rc = smc_cdc_msg_send(conn, wr_buf, pend); spin_unlock_bh(&conn->send_lock); +put_out: + smc_wr_tx_link_put(link); return rc; } diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 1cc8a76b39f9..8409ab71a5e4 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -31,6 +31,7 @@ #define SMCR_CLC_ACCEPT_CONFIRM_LEN 68 #define SMCD_CLC_ACCEPT_CONFIRM_LEN 48 #define SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 78 +#define SMCR_CLC_ACCEPT_CONFIRM_LEN_V2 108 #define SMC_CLC_RECV_BUF_LEN 100 /* eye catcher "SMCR" EBCDIC for CLC messages */ @@ -114,6 +115,17 @@ err_out: return rc; } +int smc_clc_ueid_count(void) +{ + int count; + + read_lock(&smc_clc_eid_table.lock); + count = smc_clc_eid_table.ueid_cnt; + read_unlock(&smc_clc_eid_table.lock); + + return count; +} + int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info) { struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY]; @@ -298,7 +310,8 @@ bool smc_clc_match_eid(u8 *negotiated_eid, negotiated_eid[0] = 0; read_lock(&smc_clc_eid_table.lock); - if (smc_clc_eid_table.seid_enabled && + if (peer_eid && local_eid && + smc_clc_eid_table.seid_enabled && smc_v2_ext->hdr.flag.seid && !memcmp(peer_eid, local_eid, SMC_MAX_EID_LEN)) { memcpy(negotiated_eid, peer_eid, SMC_MAX_EID_LEN); @@ -380,6 +393,27 @@ smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm_v2 *clc_v2) (ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 + sizeof(struct smc_clc_first_contact_ext))) return false; + if (hdr->typev1 == SMC_TYPE_R && + ntohs(hdr->length) < SMCR_CLC_ACCEPT_CONFIRM_LEN_V2) + return false; + } + return true; +} + +/* check arriving CLC decline */ +static bool +smc_clc_msg_decl_valid(struct smc_clc_msg_decline *dclc) +{ + struct smc_clc_msg_hdr *hdr = &dclc->hdr; + + if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D) + return false; + if (hdr->version == SMC_V1) { + if (ntohs(hdr->length) != sizeof(struct smc_clc_msg_decline)) + return false; + } else { + if (ntohs(hdr->length) != sizeof(struct smc_clc_msg_decline_v2)) + return false; } return true; } @@ -425,9 +459,9 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl) break; case SMC_CLC_DECLINE: dclc = (struct smc_clc_msg_decline *)clcm; - if (ntohs(dclc->hdr.length) != sizeof(*dclc)) + if (!smc_clc_msg_decl_valid(dclc)) return false; - trl = &dclc->trl; + check_trl = false; break; default: return false; @@ -726,15 +760,16 @@ out: /* send CLC DECLINE message across internal TCP socket */ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version) { - struct smc_clc_msg_decline dclc; + struct smc_clc_msg_decline *dclc_v1; + struct smc_clc_msg_decline_v2 dclc; struct msghdr msg; + int len, send_len; struct kvec vec; - int len; + dclc_v1 = (struct smc_clc_msg_decline *)&dclc; memset(&dclc, 0, sizeof(dclc)); memcpy(dclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); dclc.hdr.type = SMC_CLC_DECLINE; - dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline)); dclc.hdr.version = version; dclc.os_type = version == SMC_V1 ? 0 : SMC_CLC_OS_LINUX; dclc.hdr.typev2 = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? @@ -744,14 +779,22 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version) memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid)); dclc.peer_diagnosis = htonl(peer_diag_info); - memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); + if (version == SMC_V1) { + memcpy(dclc_v1->trl.eyecatcher, SMC_EYECATCHER, + sizeof(SMC_EYECATCHER)); + send_len = sizeof(*dclc_v1); + } else { + memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, + sizeof(SMC_EYECATCHER)); + send_len = sizeof(dclc); + } + dclc.hdr.length = htons(send_len); memset(&msg, 0, sizeof(msg)); vec.iov_base = &dclc; - vec.iov_len = sizeof(struct smc_clc_msg_decline); - len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, - sizeof(struct smc_clc_msg_decline)); - if (len < 0 || len < sizeof(struct smc_clc_msg_decline)) + vec.iov_len = send_len; + len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, send_len); + if (len < 0 || len < send_len) len = -EPROTO; return len > 0 ? 0 : len; } @@ -833,8 +876,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) } else { struct smc_clc_eid_entry *ueident; u16 v2_ext_offset; - u8 *eid = NULL; + v2_ext->hdr.flag.release = SMC_RELEASE; v2_ext_offset = sizeof(*pclc_smcd) - offsetofend(struct smc_clc_msg_smcd, v2_ext_offset); if (ini->smc_type_v1 != SMC_TYPE_N) @@ -842,6 +885,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0]); pclc_smcd->v2_ext_offset = htons(v2_ext_offset); + plen += sizeof(*v2_ext); read_lock(&smc_clc_eid_table.lock); v2_ext->hdr.eid_cnt = smc_clc_eid_table.ueid_cnt; @@ -851,10 +895,13 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) memcpy(v2_ext->user_eids[i++], ueident->eid, sizeof(ueident->eid)); } - v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled; read_unlock(&smc_clc_eid_table.lock); + } + if (smcd_indicated(ini->smc_type_v2)) { + u8 *eid = NULL; + + v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled; v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt; - v2_ext->hdr.flag.release = SMC_RELEASE; v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) - offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset) + @@ -862,7 +909,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) smc_ism_get_system_eid(&eid); if (eid && v2_ext->hdr.flag.seid) memcpy(smcd_v2_ext->system_eid, eid, SMC_MAX_EID_LEN); - plen += sizeof(*v2_ext) + sizeof(*smcd_v2_ext); + plen += sizeof(*smcd_v2_ext); if (ini->ism_offered_cnt) { for (i = 1; i <= ini->ism_offered_cnt; i++) { gidchids[i - 1].gid = @@ -874,6 +921,9 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) sizeof(struct smc_clc_smcd_gid_chid); } } + if (smcr_indicated(ini->smc_type_v2)) + memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE); + pclc_base->hdr.length = htons(plen); memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); @@ -897,12 +947,14 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) vec[i].iov_base = v2_ext; vec[i++].iov_len = sizeof(*v2_ext) + (v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN); - vec[i].iov_base = smcd_v2_ext; - vec[i++].iov_len = sizeof(*smcd_v2_ext); - if (ini->ism_offered_cnt) { - vec[i].iov_base = gidchids; - vec[i++].iov_len = ini->ism_offered_cnt * + if (smcd_indicated(ini->smc_type_v2)) { + vec[i].iov_base = smcd_v2_ext; + vec[i++].iov_len = sizeof(*smcd_v2_ext); + if (ini->ism_offered_cnt) { + vec[i].iov_base = gidchids; + vec[i++].iov_len = ini->ism_offered_cnt * sizeof(struct smc_clc_smcd_gid_chid); + } } } vec[i].iov_base = trl; @@ -925,13 +977,14 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) static int smc_clc_send_confirm_accept(struct smc_sock *smc, struct smc_clc_msg_accept_confirm_v2 *clc_v2, int first_contact, u8 version, - u8 *eid) + u8 *eid, struct smc_init_info *ini) { struct smc_connection *conn = &smc->conn; struct smc_clc_msg_accept_confirm *clc; struct smc_clc_first_contact_ext fce; + struct smc_clc_fce_gid_ext gle; struct smc_clc_msg_trail trl; - struct kvec vec[3]; + struct kvec vec[5]; struct msghdr msg; int i, len; @@ -953,9 +1006,10 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, if (version == SMC_V1) { clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); } else { - clc_v2->chid = htons(smc_ism_get_chid(conn->lgr->smcd)); - if (eid[0]) - memcpy(clc_v2->eid, eid, SMC_MAX_EID_LEN); + clc_v2->d1.chid = + htons(smc_ism_get_chid(conn->lgr->smcd)); + if (eid && eid[0]) + memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN); len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; if (first_contact) smc_clc_fill_fce(&fce, &len); @@ -994,6 +1048,26 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->r0.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address (conn->rmb_desc->sgt[link->link_idx].sgl)); hton24(clc->r0.psn, link->psn_initial); + if (version == SMC_V1) { + clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN); + } else { + if (eid && eid[0]) + memcpy(clc_v2->r1.eid, eid, SMC_MAX_EID_LEN); + len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2; + if (first_contact) { + smc_clc_fill_fce(&fce, &len); + fce.v2_direct = !link->lgr->uses_gateway; + memset(&gle, 0, sizeof(gle)); + if (ini && clc->hdr.type == SMC_CLC_CONFIRM) { + gle.gid_cnt = ini->smcrv2.gidlist.len; + len += sizeof(gle); + len += gle.gid_cnt * sizeof(gle.gid[0]); + } else { + len += sizeof(gle.reserved); + } + } + clc_v2->hdr.length = htons(len); + } memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); } @@ -1001,7 +1075,10 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, i = 0; vec[i].iov_base = clc_v2; if (version > SMC_V1) - vec[i++].iov_len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 - sizeof(trl); + vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ? + SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 : + SMCR_CLC_ACCEPT_CONFIRM_LEN_V2) - + sizeof(trl); else vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ? SMCD_CLC_ACCEPT_CONFIRM_LEN : @@ -1010,6 +1087,18 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, if (version > SMC_V1 && first_contact) { vec[i].iov_base = &fce; vec[i++].iov_len = sizeof(fce); + if (!conn->lgr->is_smcd) { + if (clc->hdr.type == SMC_CLC_CONFIRM) { + vec[i].iov_base = &gle; + vec[i++].iov_len = sizeof(gle); + vec[i].iov_base = &ini->smcrv2.gidlist.list; + vec[i++].iov_len = gle.gid_cnt * + sizeof(gle.gid[0]); + } else { + vec[i].iov_base = &gle.reserved; + vec[i++].iov_len = sizeof(gle.reserved); + } + } } vec[i].iov_base = &trl; vec[i++].iov_len = sizeof(trl); @@ -1019,7 +1108,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, /* send CLC CONFIRM message across internal TCP socket */ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, - u8 version, u8 *eid) + u8 version, u8 *eid, struct smc_init_info *ini) { struct smc_clc_msg_accept_confirm_v2 cclc_v2; int reason_code = 0; @@ -1029,7 +1118,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, memset(&cclc_v2, 0, sizeof(cclc_v2)); cclc_v2.hdr.type = SMC_CLC_CONFIRM; len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact, - version, eid); + version, eid, ini); if (len < ntohs(cclc_v2.hdr.length)) { if (len >= 0) { reason_code = -ENETUNREACH; @@ -1052,7 +1141,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, memset(&aclc_v2, 0, sizeof(aclc_v2)); aclc_v2.hdr.type = SMC_CLC_ACCEPT; len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact, - version, negotiated_eid); + version, negotiated_eid, NULL); if (len < ntohs(aclc_v2.hdr.length)) len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 974d01d16bb5..83f02f131fc0 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -44,6 +44,7 @@ #define SMC_CLC_DECL_NOV2DEXT 0x03030005 /* peer sent no clc SMC-Dv2 ext. */ #define SMC_CLC_DECL_NOSEID 0x03030006 /* peer sent no SEID */ #define SMC_CLC_DECL_NOSMCD2DEV 0x03030007 /* no SMC-Dv2 device found */ +#define SMC_CLC_DECL_NOUEID 0x03030008 /* peer sent no UEID */ #define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/ #define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */ #define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */ @@ -54,6 +55,8 @@ #define SMC_CLC_DECL_NOSRVLINK 0x030b0000 /* SMC-R link from srv not found */ #define SMC_CLC_DECL_VERSMISMAT 0x030c0000 /* SMC version mismatch */ #define SMC_CLC_DECL_MAX_DMB 0x030d0000 /* SMC-D DMB limit exceeded */ +#define SMC_CLC_DECL_NOROUTE 0x030e0000 /* SMC-Rv2 conn. no route to peer */ +#define SMC_CLC_DECL_NOINDIRECT 0x030f0000 /* SMC-Rv2 conn. indirect mismatch*/ #define SMC_CLC_DECL_SYNCERR 0x04000000 /* synchronization error */ #define SMC_CLC_DECL_PEERDECL 0x05000000 /* peer declined during handshake */ #define SMC_CLC_DECL_INTERR 0x09990000 /* internal error */ @@ -213,11 +216,14 @@ struct smcd_clc_msg_accept_confirm_common { /* SMCD accept/confirm */ #define SMC_CLC_OS_AIX 3 struct smc_clc_first_contact_ext { - u8 reserved1; #if defined(__BIG_ENDIAN_BITFIELD) + u8 v2_direct : 1, + reserved : 7; u8 os_type : 4, release : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 reserved : 7, + v2_direct : 1; u8 release : 4, os_type : 4; #endif @@ -225,6 +231,13 @@ struct smc_clc_first_contact_ext { u8 hostname[SMC_MAX_HOSTNAME_LEN]; }; +struct smc_clc_fce_gid_ext { + u8 reserved[16]; + u8 gid_cnt; + u8 reserved2[3]; + u8 gid[][SMC_GID_SIZE]; +}; + struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */ struct smc_clc_msg_hdr hdr; union { @@ -239,13 +252,17 @@ struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */ struct smc_clc_msg_accept_confirm_v2 { /* clc accept / confirm message */ struct smc_clc_msg_hdr hdr; union { - struct smcr_clc_msg_accept_confirm r0; /* SMC-R */ + struct { /* SMC-R */ + struct smcr_clc_msg_accept_confirm r0; + u8 eid[SMC_MAX_EID_LEN]; + u8 reserved6[8]; + } r1; struct { /* SMC-D */ struct smcd_clc_msg_accept_confirm_common d0; __be16 chid; u8 eid[SMC_MAX_EID_LEN]; u8 reserved5[8]; - }; + } d1; }; }; @@ -264,6 +281,24 @@ struct smc_clc_msg_decline { /* clc decline message */ struct smc_clc_msg_trail trl; /* eye catcher "SMCD" or "SMCR" EBCDIC */ } __aligned(4); +#define SMC_DECL_DIAG_COUNT_V2 4 /* no. of additional peer diagnosis codes */ + +struct smc_clc_msg_decline_v2 { /* clc decline message */ + struct smc_clc_msg_hdr hdr; + u8 id_for_peer[SMC_SYSTEMID_LEN]; /* sender peer_id */ + __be32 peer_diagnosis; /* diagnosis information */ +#if defined(__BIG_ENDIAN_BITFIELD) + u8 os_type : 4, + reserved : 4; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 reserved : 4, + os_type : 4; +#endif + u8 reserved2[3]; + __be32 peer_diagnosis_v2[SMC_DECL_DIAG_COUNT_V2]; + struct smc_clc_msg_trail trl; /* eye catcher "SMCD" or "SMCR" EBCDIC */ +} __aligned(4); + /* determine start of the prefix area within the proposal message */ static inline struct smc_clc_msg_proposal_prefix * smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc) @@ -282,6 +317,17 @@ static inline bool smcd_indicated(int smc_type) return smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B; } +static inline u8 smc_indicated_type(int is_smcd, int is_smcr) +{ + if (is_smcd && is_smcr) + return SMC_TYPE_B; + if (is_smcd) + return SMC_TYPE_D; + if (is_smcr) + return SMC_TYPE_R; + return SMC_TYPE_N; +} + /* get SMC-D info from proposal message */ static inline struct smc_clc_msg_smcd * smc_get_clc_msg_smcd(struct smc_clc_msg_proposal *prop) @@ -334,7 +380,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version); int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini); int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, - u8 version, u8 *eid); + u8 version, u8 *eid, struct smc_init_info *ini); int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact, u8 version, u8 *negotiated_eid); void smc_clc_init(void) __init; @@ -343,6 +389,7 @@ void smc_clc_get_hostname(u8 **host); bool smc_clc_match_eid(u8 *negotiated_eid, struct smc_clc_v2_extension *smc_v2_ext, u8 *peer_eid, u8 *local_eid); +int smc_clc_ueid_count(void); int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb); int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info); int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f57449089a16..8e642f8f334f 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -244,6 +244,8 @@ int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_IS_ISM_V2, smc_ism_is_v2_capable())) goto errattr; + if (nla_put_u8(skb, SMC_NLA_SYS_IS_SMCR_V2, true)) + goto errattr; smc_clc_get_hostname(&host); if (host) { memcpy(hostname, host, SMC_MAX_HOSTNAME_LEN); @@ -271,12 +273,65 @@ errmsg: return skb->len; } +/* Fill SMC_NLA_LGR_D_V2_COMMON/SMC_NLA_LGR_R_V2_COMMON nested attributes */ +static int smc_nl_fill_lgr_v2_common(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb, + struct nlattr *v2_attrs) +{ + char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; + char smc_eid[SMC_MAX_EID_LEN + 1]; + + if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) + goto errv2attr; + memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN); + smc_host[SMC_MAX_HOSTNAME_LEN] = 0; + if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) + goto errv2attr; + memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN); + smc_eid[SMC_MAX_EID_LEN] = 0; + if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) + goto errv2attr; + + nla_nest_end(skb, v2_attrs); + return 0; + +errv2attr: + nla_nest_cancel(skb, v2_attrs); + return -EMSGSIZE; +} + +static int smc_nl_fill_smcr_lgr_v2(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nlattr *v2_attrs; + + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2); + if (!v2_attrs) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_DIRECT, !lgr->uses_gateway)) + goto errv2attr; + + nla_nest_end(skb, v2_attrs); + return 0; + +errv2attr: + nla_nest_cancel(skb, v2_attrs); +errattr: + return -EMSGSIZE; +} + static int smc_nl_fill_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { char smc_target[SMC_MAX_PNETID_LEN + 1]; - struct nlattr *attrs; + struct nlattr *attrs, *v2_attrs; attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCR); if (!attrs) @@ -296,6 +351,15 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr, smc_target[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) goto errattr; + if (lgr->smc_version > SMC_V1) { + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON); + if (!v2_attrs) + goto errattr; + if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) + goto errattr; + if (smc_nl_fill_smcr_lgr_v2(lgr, skb, cb)) + goto errattr; + } nla_nest_end(skb, attrs); return 0; @@ -428,10 +492,7 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { - char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; char smc_pnet[SMC_MAX_PNETID_LEN + 1]; - char smc_eid[SMC_MAX_EID_LEN + 1]; - struct nlattr *v2_attrs; struct nlattr *attrs; void *nlh; @@ -463,32 +524,19 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, smc_pnet[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) goto errattr; + if (lgr->smc_version > SMC_V1) { + struct nlattr *v2_attrs; - v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_V2); - if (!v2_attrs) - goto errattr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) - goto errv2attr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) - goto errv2attr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) - goto errv2attr; - memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN); - smc_host[SMC_MAX_HOSTNAME_LEN] = 0; - if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) - goto errv2attr; - memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN); - smc_eid[SMC_MAX_EID_LEN] = 0; - if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) - goto errv2attr; - - nla_nest_end(skb, v2_attrs); + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_D_V2_COMMON); + if (!v2_attrs) + goto errattr; + if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) + goto errattr; + } nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return 0; -errv2attr: - nla_nest_cancel(skb, v2_attrs); errattr: nla_nest_cancel(skb, attrs); errout: @@ -684,24 +732,30 @@ static void smcr_copy_dev_info_to_link(struct smc_link *link) int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini) { + struct smc_ib_device *smcibdev; u8 rndvec[3]; int rc; - get_device(&ini->ib_dev->ibdev->dev); - atomic_inc(&ini->ib_dev->lnk_cnt); + if (lgr->smc_version == SMC_V2) { + lnk->smcibdev = ini->smcrv2.ib_dev_v2; + lnk->ibport = ini->smcrv2.ib_port_v2; + } else { + lnk->smcibdev = ini->ib_dev; + lnk->ibport = ini->ib_port; + } + get_device(&lnk->smcibdev->ibdev->dev); + atomic_inc(&lnk->smcibdev->lnk_cnt); + lnk->path_mtu = lnk->smcibdev->pattr[lnk->ibport - 1].active_mtu; lnk->link_id = smcr_next_link_id(lgr); lnk->lgr = lgr; lnk->link_idx = link_idx; - lnk->smcibdev = ini->ib_dev; - lnk->ibport = ini->ib_port; smc_ibdev_cnt_inc(lnk); smcr_copy_dev_info_to_link(lnk); - lnk->path_mtu = ini->ib_dev->pattr[ini->ib_port - 1].active_mtu; atomic_set(&lnk->conn_cnt, 0); smc_llc_link_set_uid(lnk); INIT_WORK(&lnk->link_down_wrk, smc_link_down_work); - if (!ini->ib_dev->initialized) { - rc = (int)smc_ib_setup_per_ibdev(ini->ib_dev); + if (!lnk->smcibdev->initialized) { + rc = (int)smc_ib_setup_per_ibdev(lnk->smcibdev); if (rc) goto out; } @@ -709,7 +763,9 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16); rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport, - ini->vlan_id, lnk->gid, &lnk->sgid_index); + ini->vlan_id, lnk->gid, &lnk->sgid_index, + lgr->smc_version == SMC_V2 ? + &ini->smcrv2 : NULL); if (rc) goto out; rc = smc_llc_link_init(lnk); @@ -740,11 +796,12 @@ clear_llc_lnk: smc_llc_link_clear(lnk, false); out: smc_ibdev_cnt_dec(lnk); - put_device(&ini->ib_dev->ibdev->dev); + put_device(&lnk->smcibdev->ibdev->dev); + smcibdev = lnk->smcibdev; memset(lnk, 0, sizeof(struct smc_link)); lnk->state = SMC_LNK_UNUSED; - if (!atomic_dec_return(&ini->ib_dev->lnk_cnt)) - wake_up(&ini->ib_dev->lnks_deleted); + if (!atomic_dec_return(&smcibdev->lnk_cnt)) + wake_up(&smcibdev->lnks_deleted); return rc; } @@ -808,18 +865,37 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) atomic_inc(&ini->ism_dev[ini->ism_selected]->lgr_cnt); } else { /* SMC-R specific settings */ + struct smc_ib_device *ibdev; + int ibport; + lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; - memcpy(lgr->peer_systemid, ini->ib_lcl->id_for_peer, + lgr->smc_version = ini->smcr_version; + memcpy(lgr->peer_systemid, ini->peer_systemid, SMC_SYSTEMID_LEN); - memcpy(lgr->pnet_id, ini->ib_dev->pnetid[ini->ib_port - 1], + if (lgr->smc_version == SMC_V2) { + ibdev = ini->smcrv2.ib_dev_v2; + ibport = ini->smcrv2.ib_port_v2; + lgr->saddr = ini->smcrv2.saddr; + lgr->uses_gateway = ini->smcrv2.uses_gateway; + memcpy(lgr->nexthop_mac, ini->smcrv2.nexthop_mac, + ETH_ALEN); + } else { + ibdev = ini->ib_dev; + ibport = ini->ib_port; + } + memcpy(lgr->pnet_id, ibdev->pnetid[ibport - 1], SMC_MAX_PNETID_LEN); + if (smc_wr_alloc_lgr_mem(lgr)) + goto free_wq; smc_llc_lgr_init(lgr, smc); link_idx = SMC_SINGLE_LINK; lnk = &lgr->lnk[link_idx]; rc = smcr_link_init(lgr, lnk, link_idx, ini); - if (rc) + if (rc) { + smc_wr_free_lgr_mem(lgr); goto free_wq; + } lgr_list = &smc_lgr_list.list; lgr_lock = &smc_lgr_list.lock; atomic_inc(&lgr_cnt); @@ -943,7 +1019,7 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr, to_lnk = &lgr->lnk[i]; break; } - if (!to_lnk) { + if (!to_lnk || !smc_wr_tx_link_hold(to_lnk)) { smc_lgr_terminate_sched(lgr); return NULL; } @@ -975,24 +1051,26 @@ again: read_unlock_bh(&lgr->conns_lock); /* pre-fetch buffer outside of send_lock, might sleep */ rc = smc_cdc_get_free_slot(conn, to_lnk, &wr_buf, NULL, &pend); - if (rc) { - smcr_link_down_cond_sched(to_lnk); - return NULL; - } + if (rc) + goto err_out; /* avoid race with smcr_tx_sndbuf_nonempty() */ spin_lock_bh(&conn->send_lock); smc_switch_link_and_count(conn, to_lnk); rc = smc_switch_cursor(smc, pend, wr_buf); spin_unlock_bh(&conn->send_lock); sock_put(&smc->sk); - if (rc) { - smcr_link_down_cond_sched(to_lnk); - return NULL; - } + if (rc) + goto err_out; goto again; } read_unlock_bh(&lgr->conns_lock); + smc_wr_tx_link_put(to_lnk); return to_lnk; + +err_out: + smcr_link_down_cond_sched(to_lnk); + smc_wr_tx_link_put(to_lnk); + return NULL; } static void smcr_buf_unuse(struct smc_buf_desc *rmb_desc, @@ -1224,6 +1302,7 @@ static void smc_lgr_free(struct smc_link_group *lgr) if (!atomic_dec_return(&lgr->smcd->lgr_cnt)) wake_up(&lgr->smcd->lgrs_deleted); } else { + smc_wr_free_lgr_mem(lgr); if (!atomic_dec_return(&lgr_cnt)) wake_up(&lgrs_deleted); } @@ -1634,13 +1713,15 @@ out: return rc; } -static bool smcr_lgr_match(struct smc_link_group *lgr, - struct smc_clc_msg_local *lcl, +static bool smcr_lgr_match(struct smc_link_group *lgr, u8 smcr_version, + u8 peer_systemid[], + u8 peer_gid[], + u8 peer_mac_v1[], enum smc_lgr_role role, u32 clcqpn) { int i; - if (memcmp(lgr->peer_systemid, lcl->id_for_peer, SMC_SYSTEMID_LEN) || + if (memcmp(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN) || lgr->role != role) return false; @@ -1648,8 +1729,9 @@ static bool smcr_lgr_match(struct smc_link_group *lgr, if (!smc_link_active(&lgr->lnk[i])) continue; if ((lgr->role == SMC_SERV || lgr->lnk[i].peer_qpn == clcqpn) && - !memcmp(lgr->lnk[i].peer_gid, &lcl->gid, SMC_GID_SIZE) && - !memcmp(lgr->lnk[i].peer_mac, lcl->mac, sizeof(lcl->mac))) + !memcmp(lgr->lnk[i].peer_gid, peer_gid, SMC_GID_SIZE) && + (smcr_version == SMC_V2 || + !memcmp(lgr->lnk[i].peer_mac, peer_mac_v1, ETH_ALEN))) return true; } return false; @@ -1688,7 +1770,10 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) if ((ini->is_smcd ? smcd_lgr_match(lgr, ini->ism_dev[ini->ism_selected], ini->ism_peer_gid[ini->ism_selected]) : - smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) && + smcr_lgr_match(lgr, ini->smcr_version, + ini->peer_systemid, + ini->peer_gid, ini->peer_mac, role, + ini->ib_clcqpn)) && !lgr->sync_err && (ini->smcd_version == SMC_V2 || lgr->vlan_id == ini->vlan_id) && diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 83d30b06016f..59cef3b830d8 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -42,11 +42,16 @@ enum smc_link_state { /* possible states of a link */ }; #define SMC_WR_BUF_SIZE 48 /* size of work request buffer */ +#define SMC_WR_BUF_V2_SIZE 8192 /* size of v2 work request buffer */ struct smc_wr_buf { u8 raw[SMC_WR_BUF_SIZE]; }; +struct smc_wr_v2_buf { + u8 raw[SMC_WR_BUF_V2_SIZE]; +}; + #define SMC_WR_REG_MR_WAIT_TIME (5 * HZ)/* wait time for ib_wr_reg_mr result */ enum smc_wr_reg_state { @@ -92,7 +97,11 @@ struct smc_link { struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */ struct completion *wr_tx_compl; /* WR send CQE completion */ /* above four vectors have wr_tx_cnt elements and use the same index */ + struct ib_send_wr *wr_tx_v2_ib; /* WR send v2 meta data */ + struct ib_sge *wr_tx_v2_sge; /* WR send v2 gather meta data*/ + struct smc_wr_tx_pend *wr_tx_v2_pend; /* WR send v2 waiting for CQE */ dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */ + dma_addr_t wr_tx_v2_dma_addr; /* DMA address of v2 tx buf*/ atomic_long_t wr_tx_id; /* seq # of last sent WR */ unsigned long *wr_tx_mask; /* bit mask of used indexes */ u32 wr_tx_cnt; /* number of WR send buffers */ @@ -104,6 +113,7 @@ struct smc_link { struct ib_sge *wr_rx_sges; /* WR recv scatter meta data */ /* above three vectors have wr_rx_cnt elements and use the same index */ dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */ + dma_addr_t wr_rx_v2_dma_addr; /* DMA address of v2 rx buf*/ u64 wr_rx_id; /* seq # of last recv WR */ u32 wr_rx_cnt; /* number of WR recv buffers */ unsigned long wr_rx_tstamp; /* jiffies when last buf rx */ @@ -208,6 +218,7 @@ enum smc_llc_flowtype { SMC_LLC_FLOW_NONE = 0, SMC_LLC_FLOW_ADD_LINK = 2, SMC_LLC_FLOW_DEL_LINK = 4, + SMC_LLC_FLOW_REQ_ADD_LINK = 5, SMC_LLC_FLOW_RKEY = 6, }; @@ -250,6 +261,10 @@ struct smc_link_group { /* client or server */ struct smc_link lnk[SMC_LINKS_PER_LGR_MAX]; /* smc link */ + struct smc_wr_v2_buf *wr_rx_buf_v2; + /* WR v2 recv payload buffer */ + struct smc_wr_v2_buf *wr_tx_buf_v2; + /* WR v2 send payload buffer */ char peer_systemid[SMC_SYSTEMID_LEN]; /* unique system_id of peer */ struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX] @@ -288,6 +303,9 @@ struct smc_link_group { /* link keep alive time */ u32 llc_termination_rsn; /* rsn code for termination */ + u8 nexthop_mac[ETH_ALEN]; + u8 uses_gateway; + __be32 saddr; }; struct { /* SMC-D */ u64 peer_gid; @@ -302,6 +320,31 @@ struct smc_link_group { struct smc_clc_msg_local; +#define GID_LIST_SIZE 2 + +struct smc_gidlist { + u8 len; + u8 list[GID_LIST_SIZE][SMC_GID_SIZE]; +}; + +struct smc_init_info_smcrv2 { + /* Input fields */ + __be32 saddr; + struct sock *clc_sk; + __be32 daddr; + + /* Output fields when saddr is set */ + struct smc_ib_device *ib_dev_v2; + u8 ib_port_v2; + u8 ib_gid_v2[SMC_GID_SIZE]; + + /* Additional output fields when clc_sk and daddr is set as well */ + u8 uses_gateway; + u8 nexthop_mac[ETH_ALEN]; + + struct smc_gidlist gidlist; +}; + struct smc_init_info { u8 is_smcd; u8 smc_type_v1; @@ -312,11 +355,16 @@ struct smc_init_info { u32 rc; u8 negotiated_eid[SMC_MAX_EID_LEN]; /* SMC-R */ - struct smc_clc_msg_local *ib_lcl; + u8 smcr_version; + u8 check_smcrv2; + u8 peer_gid[SMC_GID_SIZE]; + u8 peer_mac[ETH_ALEN]; + u8 peer_systemid[SMC_SYSTEMID_LEN]; struct smc_ib_device *ib_dev; u8 ib_gid[SMC_GID_SIZE]; u8 ib_port; u32 ib_clcqpn; + struct smc_init_info_smcrv2 smcrv2; /* SMC-D */ u64 ism_peer_gid[SMC_MAX_ISM_DEVS + 1]; struct smcd_dev *ism_dev[SMC_MAX_ISM_DEVS + 1]; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index a8845343d183..d93055ec17ae 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -17,6 +17,7 @@ #include <linux/scatterlist.h> #include <linux/wait.h> #include <linux/mutex.h> +#include <linux/inetdevice.h> #include <rdma/ib_verbs.h> #include <rdma/ib_cache.h> @@ -62,16 +63,23 @@ static int smc_ib_modify_qp_rtr(struct smc_link *lnk) IB_QP_STATE | IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN | IB_QP_RQ_PSN | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_MIN_RNR_TIMER; struct ib_qp_attr qp_attr; + u8 hop_lim = 1; memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.qp_state = IB_QPS_RTR; qp_attr.path_mtu = min(lnk->path_mtu, lnk->peer_mtu); qp_attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE; rdma_ah_set_port_num(&qp_attr.ah_attr, lnk->ibport); - rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, 1, 0); + if (lnk->lgr->smc_version == SMC_V2 && lnk->lgr->uses_gateway) + hop_lim = IPV6_DEFAULT_HOPLIMIT; + rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, hop_lim, 0); rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid); - memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac, - sizeof(lnk->peer_mac)); + if (lnk->lgr->smc_version == SMC_V2 && lnk->lgr->uses_gateway) + memcpy(&qp_attr.ah_attr.roce.dmac, lnk->lgr->nexthop_mac, + sizeof(lnk->lgr->nexthop_mac)); + else + memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac, + sizeof(lnk->peer_mac)); qp_attr.dest_qp_num = lnk->peer_qpn; qp_attr.rq_psn = lnk->peer_psn; /* starting receive packet seq # */ qp_attr.max_dest_rd_atomic = 1; /* max # of resources for incoming @@ -183,9 +191,81 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport) return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE; } +int smc_ib_find_route(__be32 saddr, __be32 daddr, + u8 nexthop_mac[], u8 *uses_gateway) +{ + struct neighbour *neigh = NULL; + struct rtable *rt = NULL; + struct flowi4 fl4 = { + .saddr = saddr, + .daddr = daddr + }; + + if (daddr == cpu_to_be32(INADDR_NONE)) + goto out; + rt = ip_route_output_flow(&init_net, &fl4, NULL); + if (IS_ERR(rt)) + goto out; + if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET) + goto out; + neigh = rt->dst.ops->neigh_lookup(&rt->dst, NULL, &fl4.daddr); + if (neigh) { + memcpy(nexthop_mac, neigh->ha, ETH_ALEN); + *uses_gateway = rt->rt_uses_gateway; + return 0; + } +out: + return -ENOENT; +} + +static int smc_ib_determine_gid_rcu(const struct net_device *ndev, + const struct ib_gid_attr *attr, + u8 gid[], u8 *sgid_index, + struct smc_init_info_smcrv2 *smcrv2) +{ + if (!smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE) { + if (gid) + memcpy(gid, &attr->gid, SMC_GID_SIZE); + if (sgid_index) + *sgid_index = attr->index; + return 0; + } + if (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP && + smc_ib_gid_to_ipv4((u8 *)&attr->gid) != cpu_to_be32(INADDR_NONE)) { + struct in_device *in_dev = __in_dev_get_rcu(ndev); + const struct in_ifaddr *ifa; + bool subnet_match = false; + + if (!in_dev) + goto out; + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (!inet_ifa_match(smcrv2->saddr, ifa)) + continue; + subnet_match = true; + break; + } + if (!subnet_match) + goto out; + if (smcrv2->daddr && smc_ib_find_route(smcrv2->saddr, + smcrv2->daddr, + smcrv2->nexthop_mac, + &smcrv2->uses_gateway)) + goto out; + + if (gid) + memcpy(gid, &attr->gid, SMC_GID_SIZE); + if (sgid_index) + *sgid_index = attr->index; + return 0; + } +out: + return -ENODEV; +} + /* determine the gid for an ib-device port and vlan id */ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, - unsigned short vlan_id, u8 gid[], u8 *sgid_index) + unsigned short vlan_id, u8 gid[], u8 *sgid_index, + struct smc_init_info_smcrv2 *smcrv2) { const struct ib_gid_attr *attr; const struct net_device *ndev; @@ -201,15 +281,13 @@ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, if (!IS_ERR(ndev) && ((!vlan_id && !is_vlan_dev(ndev)) || (vlan_id && is_vlan_dev(ndev) && - vlan_dev_vlan_id(ndev) == vlan_id)) && - attr->gid_type == IB_GID_TYPE_ROCE) { - rcu_read_unlock(); - if (gid) - memcpy(gid, &attr->gid, SMC_GID_SIZE); - if (sgid_index) - *sgid_index = attr->index; - rdma_put_gid_attr(attr); - return 0; + vlan_dev_vlan_id(ndev) == vlan_id))) { + if (!smc_ib_determine_gid_rcu(ndev, attr, gid, + sgid_index, smcrv2)) { + rcu_read_unlock(); + rdma_put_gid_attr(attr); + return 0; + } } rcu_read_unlock(); rdma_put_gid_attr(attr); @@ -217,6 +295,58 @@ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, return -ENODEV; } +/* check if gid is still defined on smcibdev */ +static bool smc_ib_check_link_gid(u8 gid[SMC_GID_SIZE], bool smcrv2, + struct smc_ib_device *smcibdev, u8 ibport) +{ + const struct ib_gid_attr *attr; + bool rc = false; + int i; + + for (i = 0; !rc && i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) { + attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, i); + if (IS_ERR(attr)) + continue; + + rcu_read_lock(); + if ((!smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE) || + (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP && + !(ipv6_addr_type((const struct in6_addr *)&attr->gid) + & IPV6_ADDR_LINKLOCAL))) + if (!memcmp(gid, &attr->gid, SMC_GID_SIZE)) + rc = true; + rcu_read_unlock(); + rdma_put_gid_attr(attr); + } + return rc; +} + +/* check all links if the gid is still defined on smcibdev */ +static void smc_ib_gid_check(struct smc_ib_device *smcibdev, u8 ibport) +{ + struct smc_link_group *lgr; + int i; + + spin_lock_bh(&smc_lgr_list.lock); + list_for_each_entry(lgr, &smc_lgr_list.list, list) { + if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id, + SMC_MAX_PNETID_LEN)) + continue; /* lgr is not affected */ + if (list_empty(&lgr->list)) + continue; + for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { + if (lgr->lnk[i].state == SMC_LNK_UNUSED || + lgr->lnk[i].smcibdev != smcibdev) + continue; + if (!smc_ib_check_link_gid(lgr->lnk[i].gid, + lgr->smc_version == SMC_V2, + smcibdev, ibport)) + smcr_port_err(smcibdev, ibport); + } + } + spin_unlock_bh(&smc_lgr_list.lock); +} + static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) { int rc; @@ -255,6 +385,7 @@ static void smc_ib_port_event_work(struct work_struct *work) } else { clear_bit(port_idx, smcibdev->ports_going_away); smcr_port_add(smcibdev, port_idx + 1); + smc_ib_gid_check(smcibdev, port_idx + 1); } } } @@ -523,6 +654,7 @@ void smc_ib_destroy_queue_pair(struct smc_link *lnk) /* create a queue pair within the protection domain for a link */ int smc_ib_create_queue_pair(struct smc_link *lnk) { + int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1; struct ib_qp_init_attr qp_attr = { .event_handler = smc_ib_qp_event_handler, .qp_context = lnk, @@ -536,7 +668,7 @@ int smc_ib_create_queue_pair(struct smc_link *lnk) .max_send_wr = SMC_WR_BUF_CNT * 3, .max_recv_wr = SMC_WR_BUF_CNT * 3, .max_send_sge = SMC_IB_MAX_SEND_SGE, - .max_recv_sge = 1, + .max_recv_sge = sges_per_buf, }, .sq_sig_type = IB_SIGNAL_REQ_WR, .qp_type = IB_QPT_RC, diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 3085f5180da7..07585937370e 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -59,6 +59,17 @@ struct smc_ib_device { /* ib-device infos for smc */ int ndev_ifidx[SMC_MAX_PORTS]; /* ndev if indexes */ }; +static inline __be32 smc_ib_gid_to_ipv4(u8 gid[SMC_GID_SIZE]) +{ + struct in6_addr *addr6 = (struct in6_addr *)gid; + + if (ipv6_addr_v4mapped(addr6) || + !(addr6->s6_addr32[0] | addr6->s6_addr32[1] | addr6->s6_addr32[2])) + return addr6->s6_addr32[3]; + return cpu_to_be32(INADDR_NONE); +} + +struct smc_init_info_smcrv2; struct smc_buf_desc; struct smc_link; @@ -90,7 +101,10 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk, struct smc_buf_desc *buf_slot, enum dma_data_direction data_direction); int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, - unsigned short vlan_id, u8 gid[], u8 *sgid_index); + unsigned short vlan_id, u8 gid[], u8 *sgid_index, + struct smc_init_info_smcrv2 *smcrv2); +int smc_ib_find_route(__be32 saddr, __be32 daddr, + u8 nexthop_mac[], u8 *uses_gateway); bool smc_ib_is_valid_local_systemid(void); int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb); #endif diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 2e7560eba981..a9623c952007 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -23,16 +23,24 @@ struct smc_llc_hdr { struct smc_wr_rx_hdr common; - u8 length; /* 44 */ -#if defined(__BIG_ENDIAN_BITFIELD) - u8 reserved:4, - add_link_rej_rsn:4; + union { + struct { + u8 length; /* 44 */ + #if defined(__BIG_ENDIAN_BITFIELD) + u8 reserved:4, + add_link_rej_rsn:4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - u8 add_link_rej_rsn:4, - reserved:4; + u8 add_link_rej_rsn:4, + reserved:4; #endif + }; + u16 length_v2; /* 44 - 8192*/ + }; u8 flags; -}; +} __packed; /* format defined in + * IBM Shared Memory Communications Version 2 + * (https://www.ibm.com/support/pages/node/6326337) + */ #define SMC_LLC_FLAG_NO_RMBE_EYEC 0x03 @@ -76,6 +84,32 @@ struct smc_llc_msg_add_link_cont_rt { __be64 rmb_vaddr_new; }; +struct smc_llc_msg_add_link_v2_ext { +#if defined(__BIG_ENDIAN_BITFIELD) + u8 v2_direct : 1, + reserved : 7; +#elif defined(__LITTLE_ENDIAN_BITFIELD) + u8 reserved : 7, + v2_direct : 1; +#endif + u8 reserved2; + u8 client_target_gid[SMC_GID_SIZE]; + u8 reserved3[8]; + u16 num_rkeys; + struct smc_llc_msg_add_link_cont_rt rt[]; +} __packed; /* format defined in + * IBM Shared Memory Communications Version 2 + * (https://www.ibm.com/support/pages/node/6326337) + */ + +struct smc_llc_msg_req_add_link_v2 { + struct smc_llc_hdr hd; + u8 reserved[20]; + u8 gid_cnt; + u8 reserved2[3]; + u8 gid[][SMC_GID_SIZE]; +}; + #define SMC_LLC_RKEYS_PER_CONT_MSG 2 struct smc_llc_msg_add_link_cont { /* type 0x03 */ @@ -114,7 +148,8 @@ struct smc_rmb_rtoken { __be64 rmb_vaddr; } __packed; /* format defined in RFC7609 */ -#define SMC_LLC_RKEYS_PER_MSG 3 +#define SMC_LLC_RKEYS_PER_MSG 3 +#define SMC_LLC_RKEYS_PER_MSG_V2 255 struct smc_llc_msg_confirm_rkey { /* type 0x06 */ struct smc_llc_hdr hd; @@ -135,9 +170,18 @@ struct smc_llc_msg_delete_rkey { /* type 0x09 */ u8 reserved2[4]; }; +struct smc_llc_msg_delete_rkey_v2 { /* type 0x29 */ + struct smc_llc_hdr hd; + u8 num_rkeys; + u8 num_inval_rkeys; + u8 reserved[2]; + __be32 rkey[]; +}; + union smc_llc_msg { struct smc_llc_msg_confirm_link confirm_link; struct smc_llc_msg_add_link add_link; + struct smc_llc_msg_req_add_link_v2 req_add_link; struct smc_llc_msg_add_link_cont add_link_cont; struct smc_llc_msg_del_link delete_link; @@ -189,7 +233,7 @@ static inline void smc_llc_flow_qentry_set(struct smc_llc_flow *flow, static void smc_llc_flow_parallel(struct smc_link_group *lgr, u8 flow_type, struct smc_llc_qentry *qentry) { - u8 msg_type = qentry->msg.raw.hdr.common.type; + u8 msg_type = qentry->msg.raw.hdr.common.llc_type; if ((msg_type == SMC_LLC_ADD_LINK || msg_type == SMC_LLC_DELETE_LINK) && flow_type != msg_type && !lgr->delayed_event) { @@ -219,7 +263,7 @@ static bool smc_llc_flow_start(struct smc_llc_flow *flow, spin_unlock_bh(&lgr->llc_flow_lock); return false; } - switch (qentry->msg.raw.hdr.common.type) { + switch (qentry->msg.raw.hdr.common.llc_type) { case SMC_LLC_ADD_LINK: flow->type = SMC_LLC_FLOW_ADD_LINK; break; @@ -306,7 +350,7 @@ struct smc_llc_qentry *smc_llc_wait(struct smc_link_group *lgr, smc_llc_flow_qentry_del(flow); goto out; } - rcv_msg = flow->qentry->msg.raw.hdr.common.type; + rcv_msg = flow->qentry->msg.raw.hdr.common.llc_type; if (exp_msg && rcv_msg != exp_msg) { if (exp_msg == SMC_LLC_ADD_LINK && rcv_msg == SMC_LLC_DELETE_LINK) { @@ -374,6 +418,30 @@ static int smc_llc_add_pending_send(struct smc_link *link, return 0; } +static int smc_llc_add_pending_send_v2(struct smc_link *link, + struct smc_wr_v2_buf **wr_buf, + struct smc_wr_tx_pend_priv **pend) +{ + int rc; + + rc = smc_wr_tx_get_v2_slot(link, smc_llc_tx_handler, wr_buf, pend); + if (rc < 0) + return rc; + return 0; +} + +static void smc_llc_init_msg_hdr(struct smc_llc_hdr *hdr, + struct smc_link_group *lgr, size_t len) +{ + if (lgr->smc_version == SMC_V2) { + hdr->common.llc_version = SMC_V2; + hdr->length_v2 = len; + } else { + hdr->common.llc_version = 0; + hdr->length = len; + } +} + /* high-level API to send LLC confirm link */ int smc_llc_send_confirm_link(struct smc_link *link, enum smc_llc_reqresp reqresp) @@ -383,13 +451,15 @@ int smc_llc_send_confirm_link(struct smc_link *link, struct smc_wr_buf *wr_buf; int rc; + if (!smc_wr_tx_link_hold(link)) + return -ENOLINK; rc = smc_llc_add_pending_send(link, &wr_buf, &pend); if (rc) - return rc; + goto put_out; confllc = (struct smc_llc_msg_confirm_link *)wr_buf; memset(confllc, 0, sizeof(*confllc)); - confllc->hd.common.type = SMC_LLC_CONFIRM_LINK; - confllc->hd.length = sizeof(struct smc_llc_msg_confirm_link); + confllc->hd.common.llc_type = SMC_LLC_CONFIRM_LINK; + smc_llc_init_msg_hdr(&confllc->hd, link->lgr, sizeof(*confllc)); confllc->hd.flags |= SMC_LLC_FLAG_NO_RMBE_EYEC; if (reqresp == SMC_LLC_RESP) confllc->hd.flags |= SMC_LLC_FLAG_RESP; @@ -402,6 +472,8 @@ int smc_llc_send_confirm_link(struct smc_link *link, confllc->max_links = SMC_LLC_ADD_LNK_MAX_LINKS; /* send llc message */ rc = smc_wr_tx_send(link, pend); +put_out: + smc_wr_tx_link_put(link); return rc; } @@ -415,13 +487,15 @@ static int smc_llc_send_confirm_rkey(struct smc_link *send_link, struct smc_link *link; int i, rc, rtok_ix; + if (!smc_wr_tx_link_hold(send_link)) + return -ENOLINK; rc = smc_llc_add_pending_send(send_link, &wr_buf, &pend); if (rc) - return rc; + goto put_out; rkeyllc = (struct smc_llc_msg_confirm_rkey *)wr_buf; memset(rkeyllc, 0, sizeof(*rkeyllc)); - rkeyllc->hd.common.type = SMC_LLC_CONFIRM_RKEY; - rkeyllc->hd.length = sizeof(struct smc_llc_msg_confirm_rkey); + rkeyllc->hd.common.llc_type = SMC_LLC_CONFIRM_RKEY; + smc_llc_init_msg_hdr(&rkeyllc->hd, send_link->lgr, sizeof(*rkeyllc)); rtok_ix = 1; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { @@ -444,6 +518,8 @@ static int smc_llc_send_confirm_rkey(struct smc_link *send_link, (u64)sg_dma_address(rmb_desc->sgt[send_link->link_idx].sgl)); /* send llc message */ rc = smc_wr_tx_send(send_link, pend); +put_out: + smc_wr_tx_link_put(send_link); return rc; } @@ -456,38 +532,134 @@ static int smc_llc_send_delete_rkey(struct smc_link *link, struct smc_wr_buf *wr_buf; int rc; + if (!smc_wr_tx_link_hold(link)) + return -ENOLINK; rc = smc_llc_add_pending_send(link, &wr_buf, &pend); if (rc) - return rc; + goto put_out; rkeyllc = (struct smc_llc_msg_delete_rkey *)wr_buf; memset(rkeyllc, 0, sizeof(*rkeyllc)); - rkeyllc->hd.common.type = SMC_LLC_DELETE_RKEY; - rkeyllc->hd.length = sizeof(struct smc_llc_msg_delete_rkey); + rkeyllc->hd.common.llc_type = SMC_LLC_DELETE_RKEY; + smc_llc_init_msg_hdr(&rkeyllc->hd, link->lgr, sizeof(*rkeyllc)); rkeyllc->num_rkeys = 1; rkeyllc->rkey[0] = htonl(rmb_desc->mr_rx[link->link_idx]->rkey); /* send llc message */ rc = smc_wr_tx_send(link, pend); +put_out: + smc_wr_tx_link_put(link); return rc; } +/* return first buffer from any of the next buf lists */ +static struct smc_buf_desc *_smc_llc_get_next_rmb(struct smc_link_group *lgr, + int *buf_lst) +{ + struct smc_buf_desc *buf_pos; + + while (*buf_lst < SMC_RMBE_SIZES) { + buf_pos = list_first_entry_or_null(&lgr->rmbs[*buf_lst], + struct smc_buf_desc, list); + if (buf_pos) + return buf_pos; + (*buf_lst)++; + } + return NULL; +} + +/* return next rmb from buffer lists */ +static struct smc_buf_desc *smc_llc_get_next_rmb(struct smc_link_group *lgr, + int *buf_lst, + struct smc_buf_desc *buf_pos) +{ + struct smc_buf_desc *buf_next; + + if (!buf_pos || list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { + (*buf_lst)++; + return _smc_llc_get_next_rmb(lgr, buf_lst); + } + buf_next = list_next_entry(buf_pos, list); + return buf_next; +} + +static struct smc_buf_desc *smc_llc_get_first_rmb(struct smc_link_group *lgr, + int *buf_lst) +{ + *buf_lst = 0; + return smc_llc_get_next_rmb(lgr, buf_lst, NULL); +} + +static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, + struct smc_link *link, struct smc_link *link_new) +{ + struct smc_link_group *lgr = link->lgr; + struct smc_buf_desc *buf_pos; + int prim_lnk_idx, lnk_idx, i; + struct smc_buf_desc *rmb; + int len = sizeof(*ext); + int buf_lst; + + ext->v2_direct = !lgr->uses_gateway; + memcpy(ext->client_target_gid, link_new->gid, SMC_GID_SIZE); + + prim_lnk_idx = link->link_idx; + lnk_idx = link_new->link_idx; + mutex_lock(&lgr->rmbs_lock); + ext->num_rkeys = lgr->conns_num; + if (!ext->num_rkeys) + goto out; + buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); + for (i = 0; i < ext->num_rkeys; i++) { + if (!buf_pos) + break; + rmb = buf_pos; + ext->rt[i].rmb_key = htonl(rmb->mr_rx[prim_lnk_idx]->rkey); + ext->rt[i].rmb_key_new = htonl(rmb->mr_rx[lnk_idx]->rkey); + ext->rt[i].rmb_vaddr_new = + cpu_to_be64((u64)sg_dma_address(rmb->sgt[lnk_idx].sgl)); + buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); + while (buf_pos && !(buf_pos)->used) + buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); + } + len += i * sizeof(ext->rt[0]); +out: + mutex_unlock(&lgr->rmbs_lock); + return len; +} + /* send ADD LINK request or response */ int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[], struct smc_link *link_new, enum smc_llc_reqresp reqresp) { + struct smc_llc_msg_add_link_v2_ext *ext = NULL; struct smc_llc_msg_add_link *addllc; struct smc_wr_tx_pend_priv *pend; - struct smc_wr_buf *wr_buf; + int len = sizeof(*addllc); int rc; - rc = smc_llc_add_pending_send(link, &wr_buf, &pend); - if (rc) - return rc; - addllc = (struct smc_llc_msg_add_link *)wr_buf; + if (!smc_wr_tx_link_hold(link)) + return -ENOLINK; + if (link->lgr->smc_version == SMC_V2) { + struct smc_wr_v2_buf *wr_buf; + + rc = smc_llc_add_pending_send_v2(link, &wr_buf, &pend); + if (rc) + goto put_out; + addllc = (struct smc_llc_msg_add_link *)wr_buf; + ext = (struct smc_llc_msg_add_link_v2_ext *) + &wr_buf->raw[sizeof(*addllc)]; + memset(ext, 0, SMC_WR_TX_SIZE); + } else { + struct smc_wr_buf *wr_buf; + + rc = smc_llc_add_pending_send(link, &wr_buf, &pend); + if (rc) + goto put_out; + addllc = (struct smc_llc_msg_add_link *)wr_buf; + } memset(addllc, 0, sizeof(*addllc)); - addllc->hd.common.type = SMC_LLC_ADD_LINK; - addllc->hd.length = sizeof(struct smc_llc_msg_add_link); + addllc->hd.common.llc_type = SMC_LLC_ADD_LINK; if (reqresp == SMC_LLC_RESP) addllc->hd.flags |= SMC_LLC_FLAG_RESP; memcpy(addllc->sender_mac, mac, ETH_ALEN); @@ -502,8 +674,16 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[], addllc->qp_mtu = min(link_new->path_mtu, link_new->peer_mtu); } + if (ext && link_new) + len += smc_llc_fill_ext_v2(ext, link, link_new); + smc_llc_init_msg_hdr(&addllc->hd, link->lgr, len); /* send llc message */ - rc = smc_wr_tx_send(link, pend); + if (link->lgr->smc_version == SMC_V2) + rc = smc_wr_tx_v2_send(link, pend, len); + else + rc = smc_wr_tx_send(link, pend); +put_out: + smc_wr_tx_link_put(link); return rc; } @@ -517,14 +697,16 @@ int smc_llc_send_delete_link(struct smc_link *link, u8 link_del_id, struct smc_wr_buf *wr_buf; int rc; + if (!smc_wr_tx_link_hold(link)) + return -ENOLINK; rc = smc_llc_add_pending_send(link, &wr_buf, &pend); if (rc) - return rc; + goto put_out; delllc = (struct smc_llc_msg_del_link *)wr_buf; memset(delllc, 0, sizeof(*delllc)); - delllc->hd.common.type = SMC_LLC_DELETE_LINK; - delllc->hd.length = sizeof(struct smc_llc_msg_del_link); + delllc->hd.common.llc_type = SMC_LLC_DELETE_LINK; + smc_llc_init_msg_hdr(&delllc->hd, link->lgr, sizeof(*delllc)); if (reqresp == SMC_LLC_RESP) delllc->hd.flags |= SMC_LLC_FLAG_RESP; if (orderly) @@ -536,6 +718,8 @@ int smc_llc_send_delete_link(struct smc_link *link, u8 link_del_id, delllc->reason = htonl(reason); /* send llc message */ rc = smc_wr_tx_send(link, pend); +put_out: + smc_wr_tx_link_put(link); return rc; } @@ -547,16 +731,20 @@ static int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16]) struct smc_wr_buf *wr_buf; int rc; + if (!smc_wr_tx_link_hold(link)) + return -ENOLINK; rc = smc_llc_add_pending_send(link, &wr_buf, &pend); if (rc) - return rc; + goto put_out; testllc = (struct smc_llc_msg_test_link *)wr_buf; memset(testllc, 0, sizeof(*testllc)); - testllc->hd.common.type = SMC_LLC_TEST_LINK; - testllc->hd.length = sizeof(struct smc_llc_msg_test_link); + testllc->hd.common.llc_type = SMC_LLC_TEST_LINK; + smc_llc_init_msg_hdr(&testllc->hd, link->lgr, sizeof(*testllc)); memcpy(testllc->user_data, user_data, sizeof(testllc->user_data)); /* send llc message */ rc = smc_wr_tx_send(link, pend); +put_out: + smc_wr_tx_link_put(link); return rc; } @@ -567,13 +755,16 @@ static int smc_llc_send_message(struct smc_link *link, void *llcbuf) struct smc_wr_buf *wr_buf; int rc; - if (!smc_link_usable(link)) + if (!smc_wr_tx_link_hold(link)) return -ENOLINK; rc = smc_llc_add_pending_send(link, &wr_buf, &pend); if (rc) - return rc; + goto put_out; memcpy(wr_buf, llcbuf, sizeof(union smc_llc_msg)); - return smc_wr_tx_send(link, pend); + rc = smc_wr_tx_send(link, pend); +put_out: + smc_wr_tx_link_put(link); + return rc; } /* schedule an llc send on link, may wait for buffers, @@ -586,13 +777,16 @@ static int smc_llc_send_message_wait(struct smc_link *link, void *llcbuf) struct smc_wr_buf *wr_buf; int rc; - if (!smc_link_usable(link)) + if (!smc_wr_tx_link_hold(link)) return -ENOLINK; rc = smc_llc_add_pending_send(link, &wr_buf, &pend); if (rc) - return rc; + goto put_out; memcpy(wr_buf, llcbuf, sizeof(union smc_llc_msg)); - return smc_wr_tx_send_wait(link, pend, SMC_LLC_WAIT_TIME); + rc = smc_wr_tx_send_wait(link, pend, SMC_LLC_WAIT_TIME); +put_out: + smc_wr_tx_link_put(link); + return rc; } /********************************* receive ***********************************/ @@ -621,44 +815,6 @@ static int smc_llc_alloc_alt_link(struct smc_link_group *lgr, return -EMLINK; } -/* return first buffer from any of the next buf lists */ -static struct smc_buf_desc *_smc_llc_get_next_rmb(struct smc_link_group *lgr, - int *buf_lst) -{ - struct smc_buf_desc *buf_pos; - - while (*buf_lst < SMC_RMBE_SIZES) { - buf_pos = list_first_entry_or_null(&lgr->rmbs[*buf_lst], - struct smc_buf_desc, list); - if (buf_pos) - return buf_pos; - (*buf_lst)++; - } - return NULL; -} - -/* return next rmb from buffer lists */ -static struct smc_buf_desc *smc_llc_get_next_rmb(struct smc_link_group *lgr, - int *buf_lst, - struct smc_buf_desc *buf_pos) -{ - struct smc_buf_desc *buf_next; - - if (!buf_pos || list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { - (*buf_lst)++; - return _smc_llc_get_next_rmb(lgr, buf_lst); - } - buf_next = list_next_entry(buf_pos, list); - return buf_next; -} - -static struct smc_buf_desc *smc_llc_get_first_rmb(struct smc_link_group *lgr, - int *buf_lst) -{ - *buf_lst = 0; - return smc_llc_get_next_rmb(lgr, buf_lst, NULL); -} - /* send one add_link_continue msg */ static int smc_llc_add_link_cont(struct smc_link *link, struct smc_link *link_new, u8 *num_rkeys_todo, @@ -672,9 +828,11 @@ static int smc_llc_add_link_cont(struct smc_link *link, struct smc_buf_desc *rmb; u8 n; + if (!smc_wr_tx_link_hold(link)) + return -ENOLINK; rc = smc_llc_add_pending_send(link, &wr_buf, &pend); if (rc) - return rc; + goto put_out; addc_llc = (struct smc_llc_msg_add_link_cont *)wr_buf; memset(addc_llc, 0, sizeof(*addc_llc)); @@ -702,11 +860,14 @@ static int smc_llc_add_link_cont(struct smc_link *link, while (*buf_pos && !(*buf_pos)->used) *buf_pos = smc_llc_get_next_rmb(lgr, buf_lst, *buf_pos); } - addc_llc->hd.common.type = SMC_LLC_ADD_LINK_CONT; + addc_llc->hd.common.llc_type = SMC_LLC_ADD_LINK_CONT; addc_llc->hd.length = sizeof(struct smc_llc_msg_add_link_cont); if (lgr->role == SMC_CLNT) addc_llc->hd.flags |= SMC_LLC_FLAG_RESP; - return smc_wr_tx_send(link, pend); + rc = smc_wr_tx_send(link, pend); +put_out: + smc_wr_tx_link_put(link); + return rc; } static int smc_llc_cli_rkey_exchange(struct smc_link *link, @@ -758,6 +919,8 @@ static int smc_llc_cli_add_link_reject(struct smc_llc_qentry *qentry) qentry->msg.raw.hdr.flags |= SMC_LLC_FLAG_RESP; qentry->msg.raw.hdr.flags |= SMC_LLC_FLAG_ADD_LNK_REJ; qentry->msg.raw.hdr.add_link_rej_rsn = SMC_LLC_REJ_RSN_NO_ALT_PATH; + smc_llc_init_msg_hdr(&qentry->msg.raw.hdr, qentry->link->lgr, + sizeof(qentry->msg)); return smc_llc_send_message(qentry->link, &qentry->msg); } @@ -778,7 +941,7 @@ static int smc_llc_cli_conf_link(struct smc_link *link, SMC_LLC_DEL_LOST_PATH); return -ENOLINK; } - if (qentry->msg.raw.hdr.common.type != SMC_LLC_CONFIRM_LINK) { + if (qentry->msg.raw.hdr.common.llc_type != SMC_LLC_CONFIRM_LINK) { /* received DELETE_LINK instead */ qentry->msg.raw.hdr.flags |= SMC_LLC_FLAG_RESP; smc_llc_send_message(link, &qentry->msg); @@ -819,6 +982,26 @@ static int smc_llc_cli_conf_link(struct smc_link *link, return 0; } +static void smc_llc_save_add_link_rkeys(struct smc_link *link, + struct smc_link *link_new) +{ + struct smc_llc_msg_add_link_v2_ext *ext; + struct smc_link_group *lgr = link->lgr; + int max, i; + + ext = (struct smc_llc_msg_add_link_v2_ext *)((u8 *)lgr->wr_rx_buf_v2 + + SMC_WR_TX_SIZE); + max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); + mutex_lock(&lgr->rmbs_lock); + for (i = 0; i < max; i++) { + smc_rtoken_set(lgr, link->link_idx, link_new->link_idx, + ext->rt[i].rmb_key, + ext->rt[i].rmb_vaddr_new, + ext->rt[i].rmb_key_new); + } + mutex_unlock(&lgr->rmbs_lock); +} + static void smc_llc_save_add_link_info(struct smc_link *link, struct smc_llc_msg_add_link *add_llc) { @@ -835,31 +1018,47 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) struct smc_llc_msg_add_link *llc = &qentry->msg.add_link; enum smc_lgr_type lgr_new_t = SMC_LGR_SYMMETRIC; struct smc_link_group *lgr = smc_get_lgr(link); + struct smc_init_info *ini = NULL; struct smc_link *lnk_new = NULL; - struct smc_init_info ini; int lnk_idx, rc = 0; if (!llc->qp_mtu) goto out_reject; - ini.vlan_id = lgr->vlan_id; - smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev); + ini = kzalloc(sizeof(*ini), GFP_KERNEL); + if (!ini) { + rc = -ENOMEM; + goto out_reject; + } + + ini->vlan_id = lgr->vlan_id; + if (lgr->smc_version == SMC_V2) { + ini->check_smcrv2 = true; + ini->smcrv2.saddr = lgr->saddr; + ini->smcrv2.daddr = smc_ib_gid_to_ipv4(llc->sender_gid); + } + smc_pnet_find_alt_roce(lgr, ini, link->smcibdev); if (!memcmp(llc->sender_gid, link->peer_gid, SMC_GID_SIZE) && - !memcmp(llc->sender_mac, link->peer_mac, ETH_ALEN)) { - if (!ini.ib_dev) + (lgr->smc_version == SMC_V2 || + !memcmp(llc->sender_mac, link->peer_mac, ETH_ALEN))) { + if (!ini->ib_dev && !ini->smcrv2.ib_dev_v2) goto out_reject; lgr_new_t = SMC_LGR_ASYMMETRIC_PEER; } - if (!ini.ib_dev) { + if (lgr->smc_version == SMC_V2 && !ini->smcrv2.ib_dev_v2) { lgr_new_t = SMC_LGR_ASYMMETRIC_LOCAL; - ini.ib_dev = link->smcibdev; - ini.ib_port = link->ibport; + ini->smcrv2.ib_dev_v2 = link->smcibdev; + ini->smcrv2.ib_port_v2 = link->ibport; + } else if (lgr->smc_version < SMC_V2 && !ini->ib_dev) { + lgr_new_t = SMC_LGR_ASYMMETRIC_LOCAL; + ini->ib_dev = link->smcibdev; + ini->ib_port = link->ibport; } lnk_idx = smc_llc_alloc_alt_link(lgr, lgr_new_t); if (lnk_idx < 0) goto out_reject; lnk_new = &lgr->lnk[lnk_idx]; - rc = smcr_link_init(lgr, lnk_new, lnk_idx, &ini); + rc = smcr_link_init(lgr, lnk_new, lnk_idx, ini); if (rc) goto out_reject; smc_llc_save_add_link_info(lnk_new, llc); @@ -875,16 +1074,20 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry) goto out_clear_lnk; rc = smc_llc_send_add_link(link, - lnk_new->smcibdev->mac[ini.ib_port - 1], + lnk_new->smcibdev->mac[lnk_new->ibport - 1], lnk_new->gid, lnk_new, SMC_LLC_RESP); if (rc) goto out_clear_lnk; - rc = smc_llc_cli_rkey_exchange(link, lnk_new); - if (rc) { - rc = 0; - goto out_clear_lnk; + if (lgr->smc_version == SMC_V2) { + smc_llc_save_add_link_rkeys(link, lnk_new); + } else { + rc = smc_llc_cli_rkey_exchange(link, lnk_new); + if (rc) { + rc = 0; + goto out_clear_lnk; + } } - rc = smc_llc_cli_conf_link(link, &ini, lnk_new, lgr_new_t); + rc = smc_llc_cli_conf_link(link, ini, lnk_new, lgr_new_t); if (!rc) goto out; out_clear_lnk: @@ -893,29 +1096,78 @@ out_clear_lnk: out_reject: smc_llc_cli_add_link_reject(qentry); out: + kfree(ini); kfree(qentry); return rc; } +static void smc_llc_send_request_add_link(struct smc_link *link) +{ + struct smc_llc_msg_req_add_link_v2 *llc; + struct smc_wr_tx_pend_priv *pend; + struct smc_wr_v2_buf *wr_buf; + struct smc_gidlist gidlist; + int rc, len, i; + + if (!smc_wr_tx_link_hold(link)) + return; + if (link->lgr->type == SMC_LGR_SYMMETRIC || + link->lgr->type == SMC_LGR_ASYMMETRIC_PEER) + goto put_out; + + smc_fill_gid_list(link->lgr, &gidlist, link->smcibdev, link->gid); + if (gidlist.len <= 1) + goto put_out; + + rc = smc_llc_add_pending_send_v2(link, &wr_buf, &pend); + if (rc) + goto put_out; + llc = (struct smc_llc_msg_req_add_link_v2 *)wr_buf; + memset(llc, 0, SMC_WR_TX_SIZE); + + llc->hd.common.llc_type = SMC_LLC_REQ_ADD_LINK; + for (i = 0; i < gidlist.len; i++) + memcpy(llc->gid[i], gidlist.list[i], sizeof(gidlist.list[0])); + llc->gid_cnt = gidlist.len; + len = sizeof(*llc) + (gidlist.len * sizeof(gidlist.list[0])); + smc_llc_init_msg_hdr(&llc->hd, link->lgr, len); + rc = smc_wr_tx_v2_send(link, pend, len); + if (!rc) + /* set REQ_ADD_LINK flow and wait for response from peer */ + link->lgr->llc_flow_lcl.type = SMC_LLC_FLOW_REQ_ADD_LINK; +put_out: + smc_wr_tx_link_put(link); +} + /* as an SMC client, invite server to start the add_link processing */ static void smc_llc_cli_add_link_invite(struct smc_link *link, struct smc_llc_qentry *qentry) { struct smc_link_group *lgr = smc_get_lgr(link); - struct smc_init_info ini; + struct smc_init_info *ini = NULL; + + if (lgr->smc_version == SMC_V2) { + smc_llc_send_request_add_link(link); + goto out; + } if (lgr->type == SMC_LGR_SYMMETRIC || lgr->type == SMC_LGR_ASYMMETRIC_PEER) goto out; - ini.vlan_id = lgr->vlan_id; - smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev); - if (!ini.ib_dev) + ini = kzalloc(sizeof(*ini), GFP_KERNEL); + if (!ini) goto out; - smc_llc_send_add_link(link, ini.ib_dev->mac[ini.ib_port - 1], - ini.ib_gid, NULL, SMC_LLC_REQ); + ini->vlan_id = lgr->vlan_id; + smc_pnet_find_alt_roce(lgr, ini, link->smcibdev); + if (!ini->ib_dev) + goto out; + + smc_llc_send_add_link(link, ini->ib_dev->mac[ini->ib_port - 1], + ini->ib_gid, NULL, SMC_LLC_REQ); out: + kfree(ini); kfree(qentry); } @@ -931,7 +1183,7 @@ static bool smc_llc_is_empty_llc_message(union smc_llc_msg *llc) static bool smc_llc_is_local_add_link(union smc_llc_msg *llc) { - if (llc->raw.hdr.common.type == SMC_LLC_ADD_LINK && + if (llc->raw.hdr.common.llc_type == SMC_LLC_ADD_LINK && smc_llc_is_empty_llc_message(llc)) return true; return false; @@ -1098,7 +1350,7 @@ static int smc_llc_srv_conf_link(struct smc_link *link, /* receive CONFIRM LINK response over the RoCE fabric */ qentry = smc_llc_wait(lgr, link, SMC_LLC_WAIT_FIRST_TIME, 0); if (!qentry || - qentry->msg.raw.hdr.common.type != SMC_LLC_CONFIRM_LINK) { + qentry->msg.raw.hdr.common.llc_type != SMC_LLC_CONFIRM_LINK) { /* send DELETE LINK */ smc_llc_send_delete_link(link, link_new->link_id, SMC_LLC_REQ, false, SMC_LLC_DEL_LOST_PATH); @@ -1117,37 +1369,80 @@ static int smc_llc_srv_conf_link(struct smc_link *link, return 0; } -int smc_llc_srv_add_link(struct smc_link *link) +static void smc_llc_send_req_add_link_response(struct smc_llc_qentry *qentry) +{ + qentry->msg.raw.hdr.flags |= SMC_LLC_FLAG_RESP; + smc_llc_init_msg_hdr(&qentry->msg.raw.hdr, qentry->link->lgr, + sizeof(qentry->msg)); + memset(&qentry->msg.raw.data, 0, sizeof(qentry->msg.raw.data)); + smc_llc_send_message(qentry->link, &qentry->msg); +} + +int smc_llc_srv_add_link(struct smc_link *link, + struct smc_llc_qentry *req_qentry) { enum smc_lgr_type lgr_new_t = SMC_LGR_SYMMETRIC; struct smc_link_group *lgr = link->lgr; struct smc_llc_msg_add_link *add_llc; struct smc_llc_qentry *qentry = NULL; - struct smc_link *link_new; - struct smc_init_info ini; + bool send_req_add_link_resp = false; + struct smc_link *link_new = NULL; + struct smc_init_info *ini = NULL; int lnk_idx, rc = 0; + if (req_qentry && + req_qentry->msg.raw.hdr.common.llc_type == SMC_LLC_REQ_ADD_LINK) + send_req_add_link_resp = true; + + ini = kzalloc(sizeof(*ini), GFP_KERNEL); + if (!ini) { + rc = -ENOMEM; + goto out; + } + /* ignore client add link recommendation, start new flow */ - ini.vlan_id = lgr->vlan_id; - smc_pnet_find_alt_roce(lgr, &ini, link->smcibdev); - if (!ini.ib_dev) { + ini->vlan_id = lgr->vlan_id; + if (lgr->smc_version == SMC_V2) { + ini->check_smcrv2 = true; + ini->smcrv2.saddr = lgr->saddr; + if (send_req_add_link_resp) { + struct smc_llc_msg_req_add_link_v2 *req_add = + &req_qentry->msg.req_add_link; + + ini->smcrv2.daddr = smc_ib_gid_to_ipv4(req_add->gid[0]); + } + } + smc_pnet_find_alt_roce(lgr, ini, link->smcibdev); + if (lgr->smc_version == SMC_V2 && !ini->smcrv2.ib_dev_v2) { + lgr_new_t = SMC_LGR_ASYMMETRIC_LOCAL; + ini->smcrv2.ib_dev_v2 = link->smcibdev; + ini->smcrv2.ib_port_v2 = link->ibport; + } else if (lgr->smc_version < SMC_V2 && !ini->ib_dev) { lgr_new_t = SMC_LGR_ASYMMETRIC_LOCAL; - ini.ib_dev = link->smcibdev; - ini.ib_port = link->ibport; + ini->ib_dev = link->smcibdev; + ini->ib_port = link->ibport; } lnk_idx = smc_llc_alloc_alt_link(lgr, lgr_new_t); - if (lnk_idx < 0) - return 0; + if (lnk_idx < 0) { + rc = 0; + goto out; + } - rc = smcr_link_init(lgr, &lgr->lnk[lnk_idx], lnk_idx, &ini); + rc = smcr_link_init(lgr, &lgr->lnk[lnk_idx], lnk_idx, ini); if (rc) - return rc; + goto out; link_new = &lgr->lnk[lnk_idx]; + + rc = smcr_buf_map_lgr(link_new); + if (rc) + goto out_err; + rc = smc_llc_send_add_link(link, - link_new->smcibdev->mac[ini.ib_port - 1], + link_new->smcibdev->mac[link_new->ibport-1], link_new->gid, link_new, SMC_LLC_REQ); if (rc) goto out_err; + send_req_add_link_resp = false; /* receive ADD LINK response over the RoCE fabric */ qentry = smc_llc_wait(lgr, link, SMC_LLC_WAIT_TIME, SMC_LLC_ADD_LINK); if (!qentry) { @@ -1162,7 +1457,8 @@ int smc_llc_srv_add_link(struct smc_link *link) } if (lgr->type == SMC_LGR_SINGLE && (!memcmp(add_llc->sender_gid, link->peer_gid, SMC_GID_SIZE) && - !memcmp(add_llc->sender_mac, link->peer_mac, ETH_ALEN))) { + (lgr->smc_version == SMC_V2 || + !memcmp(add_llc->sender_mac, link->peer_mac, ETH_ALEN)))) { lgr_new_t = SMC_LGR_ASYMMETRIC_PEER; } smc_llc_save_add_link_info(link_new, add_llc); @@ -1171,39 +1467,49 @@ int smc_llc_srv_add_link(struct smc_link *link) rc = smc_ib_ready_link(link_new); if (rc) goto out_err; - rc = smcr_buf_map_lgr(link_new); - if (rc) - goto out_err; rc = smcr_buf_reg_lgr(link_new); if (rc) goto out_err; - rc = smc_llc_srv_rkey_exchange(link, link_new); - if (rc) - goto out_err; + if (lgr->smc_version == SMC_V2) { + smc_llc_save_add_link_rkeys(link, link_new); + } else { + rc = smc_llc_srv_rkey_exchange(link, link_new); + if (rc) + goto out_err; + } rc = smc_llc_srv_conf_link(link, link_new, lgr_new_t); if (rc) goto out_err; + kfree(ini); return 0; out_err: - link_new->state = SMC_LNK_INACTIVE; - smcr_link_clear(link_new, false); + if (link_new) { + link_new->state = SMC_LNK_INACTIVE; + smcr_link_clear(link_new, false); + } +out: + kfree(ini); + if (send_req_add_link_resp) + smc_llc_send_req_add_link_response(req_qentry); return rc; } static void smc_llc_process_srv_add_link(struct smc_link_group *lgr) { struct smc_link *link = lgr->llc_flow_lcl.qentry->link; + struct smc_llc_qentry *qentry; int rc; - smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); + qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); mutex_lock(&lgr->llc_conf_mutex); - rc = smc_llc_srv_add_link(link); + rc = smc_llc_srv_add_link(link, qentry); if (!rc && lgr->type == SMC_LGR_SYMMETRIC) { /* delete any asymmetric link */ smc_llc_delete_asym_link(lgr); } mutex_unlock(&lgr->llc_conf_mutex); + kfree(qentry); } /* enqueue a local add_link req to trigger a new add_link flow */ @@ -1211,8 +1517,8 @@ void smc_llc_add_link_local(struct smc_link *link) { struct smc_llc_msg_add_link add_llc = {}; - add_llc.hd.length = sizeof(add_llc); - add_llc.hd.common.type = SMC_LLC_ADD_LINK; + add_llc.hd.common.llc_type = SMC_LLC_ADD_LINK; + smc_llc_init_msg_hdr(&add_llc.hd, link->lgr, sizeof(add_llc)); /* no dev and port needed */ smc_llc_enqueue(link, (union smc_llc_msg *)&add_llc); } @@ -1234,7 +1540,8 @@ static void smc_llc_add_link_work(struct work_struct *work) else smc_llc_process_srv_add_link(lgr); out: - smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); + if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_REQ_ADD_LINK) + smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); } /* enqueue a local del_link msg to trigger a new del_link flow, @@ -1244,8 +1551,8 @@ void smc_llc_srv_delete_link_local(struct smc_link *link, u8 del_link_id) { struct smc_llc_msg_del_link del_llc = {}; - del_llc.hd.length = sizeof(del_llc); - del_llc.hd.common.type = SMC_LLC_DELETE_LINK; + del_llc.hd.common.llc_type = SMC_LLC_DELETE_LINK; + smc_llc_init_msg_hdr(&del_llc.hd, link->lgr, sizeof(del_llc)); del_llc.link_num = del_link_id; del_llc.reason = htonl(SMC_LLC_DEL_LOST_PATH); del_llc.hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY; @@ -1315,8 +1622,8 @@ void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn) struct smc_llc_msg_del_link delllc = {}; int i; - delllc.hd.common.type = SMC_LLC_DELETE_LINK; - delllc.hd.length = sizeof(delllc); + delllc.hd.common.llc_type = SMC_LLC_DELETE_LINK; + smc_llc_init_msg_hdr(&delllc.hd, lgr, sizeof(delllc)); if (ord) delllc.hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY; delllc.hd.flags |= SMC_LLC_FLAG_DEL_LINK_ALL; @@ -1432,6 +1739,8 @@ static void smc_llc_rmt_conf_rkey(struct smc_link_group *lgr) link = qentry->link; num_entries = llc->rtoken[0].num_rkeys; + if (num_entries > SMC_LLC_RKEYS_PER_MSG) + goto out_err; /* first rkey entry is for receiving link */ rk_idx = smc_rtoken_add(link, llc->rtoken[0].rmb_vaddr, @@ -1450,6 +1759,7 @@ out_err: llc->hd.flags |= SMC_LLC_FLAG_RKEY_RETRY; out: llc->hd.flags |= SMC_LLC_FLAG_RESP; + smc_llc_init_msg_hdr(&llc->hd, link->lgr, sizeof(*llc)); smc_llc_send_message(link, &qentry->msg); smc_llc_flow_qentry_del(&lgr->llc_flow_rmt); } @@ -1467,6 +1777,28 @@ static void smc_llc_rmt_delete_rkey(struct smc_link_group *lgr) llc = &qentry->msg.delete_rkey; link = qentry->link; + if (lgr->smc_version == SMC_V2) { + struct smc_llc_msg_delete_rkey_v2 *llcv2; + + memcpy(lgr->wr_rx_buf_v2, llc, sizeof(*llc)); + llcv2 = (struct smc_llc_msg_delete_rkey_v2 *)lgr->wr_rx_buf_v2; + llcv2->num_inval_rkeys = 0; + + max = min_t(u8, llcv2->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); + for (i = 0; i < max; i++) { + if (smc_rtoken_delete(link, llcv2->rkey[i])) + llcv2->num_inval_rkeys++; + } + memset(&llc->rkey[0], 0, sizeof(llc->rkey)); + memset(&llc->reserved2, 0, sizeof(llc->reserved2)); + smc_llc_init_msg_hdr(&llc->hd, link->lgr, sizeof(*llc)); + if (llcv2->num_inval_rkeys) { + llc->hd.flags |= SMC_LLC_FLAG_RKEY_NEG; + llc->err_mask = llcv2->num_inval_rkeys; + } + goto finish; + } + max = min_t(u8, llc->num_rkeys, SMC_LLC_DEL_RKEY_MAX); for (i = 0; i < max; i++) { if (smc_rtoken_delete(link, llc->rkey[i])) @@ -1476,6 +1808,7 @@ static void smc_llc_rmt_delete_rkey(struct smc_link_group *lgr) llc->hd.flags |= SMC_LLC_FLAG_RKEY_NEG; llc->err_mask = err_mask; } +finish: llc->hd.flags |= SMC_LLC_FLAG_RESP; smc_llc_send_message(link, &qentry->msg); smc_llc_flow_qentry_del(&lgr->llc_flow_rmt); @@ -1511,7 +1844,7 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) if (!smc_link_usable(link)) goto out; - switch (llc->raw.hdr.common.type) { + switch (llc->raw.hdr.common.llc_type) { case SMC_LLC_TEST_LINK: llc->test_link.hd.flags |= SMC_LLC_FLAG_RESP; smc_llc_send_message(link, llc); @@ -1536,8 +1869,18 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, qentry); wake_up(&lgr->llc_msg_waiter); - } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, - qentry)) { + return; + } + if (lgr->llc_flow_lcl.type == + SMC_LLC_FLOW_REQ_ADD_LINK) { + /* server started add_link processing */ + lgr->llc_flow_lcl.type = SMC_LLC_FLOW_ADD_LINK; + smc_llc_flow_qentry_set(&lgr->llc_flow_lcl, + qentry); + schedule_work(&lgr->llc_add_link_work); + return; + } + if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { schedule_work(&lgr->llc_add_link_work); } } else if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { @@ -1585,6 +1928,23 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry) smc_llc_flow_stop(lgr, &lgr->llc_flow_rmt); } return; + case SMC_LLC_REQ_ADD_LINK: + /* handle response here, smc_llc_flow_stop() cannot be called + * in tasklet context + */ + if (lgr->role == SMC_CLNT && + lgr->llc_flow_lcl.type == SMC_LLC_FLOW_REQ_ADD_LINK && + (llc->raw.hdr.flags & SMC_LLC_FLAG_RESP)) { + smc_llc_flow_stop(link->lgr, &lgr->llc_flow_lcl); + } else if (lgr->role == SMC_SERV) { + if (smc_llc_flow_start(&lgr->llc_flow_lcl, qentry)) { + /* as smc server, handle client suggestion */ + lgr->llc_flow_lcl.type = SMC_LLC_FLOW_ADD_LINK; + schedule_work(&lgr->llc_add_link_work); + } + return; + } + break; default: smc_llc_protocol_violation(lgr, llc->raw.hdr.common.type); break; @@ -1628,7 +1988,7 @@ static void smc_llc_rx_response(struct smc_link *link, { enum smc_llc_flowtype flowtype = link->lgr->llc_flow_lcl.type; struct smc_llc_flow *flow = &link->lgr->llc_flow_lcl; - u8 llc_type = qentry->msg.raw.hdr.common.type; + u8 llc_type = qentry->msg.raw.hdr.common.llc_type; switch (llc_type) { case SMC_LLC_TEST_LINK: @@ -1654,7 +2014,8 @@ static void smc_llc_rx_response(struct smc_link *link, /* not used because max links is 3 */ break; default: - smc_llc_protocol_violation(link->lgr, llc_type); + smc_llc_protocol_violation(link->lgr, + qentry->msg.raw.hdr.common.type); break; } kfree(qentry); @@ -1679,7 +2040,8 @@ static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc) memcpy(&qentry->msg, llc, sizeof(union smc_llc_msg)); /* process responses immediately */ - if (llc->raw.hdr.flags & SMC_LLC_FLAG_RESP) { + if ((llc->raw.hdr.flags & SMC_LLC_FLAG_RESP) && + llc->raw.hdr.common.llc_type != SMC_LLC_REQ_ADD_LINK) { smc_llc_rx_response(link, qentry); return; } @@ -1699,8 +2061,13 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf) if (wc->byte_len < sizeof(*llc)) return; /* short message */ - if (llc->raw.hdr.length != sizeof(*llc)) - return; /* invalid message */ + if (!llc->raw.hdr.common.llc_version) { + if (llc->raw.hdr.length != sizeof(*llc)) + return; /* invalid message */ + } else { + if (llc->raw.hdr.length_v2 < sizeof(*llc)) + return; /* invalid message */ + } smc_llc_enqueue(link, llc); } @@ -1919,6 +2286,35 @@ static struct smc_wr_rx_handler smc_llc_rx_handlers[] = { .handler = smc_llc_rx_handler, .type = SMC_LLC_DELETE_RKEY }, + /* V2 types */ + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_CONFIRM_LINK_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_TEST_LINK_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_ADD_LINK_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_DELETE_LINK_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_REQ_ADD_LINK_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_CONFIRM_RKEY_V2 + }, + { + .handler = smc_llc_rx_handler, + .type = SMC_LLC_DELETE_RKEY_V2 + }, { .handler = NULL, } diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h index cc00a2ec4e92..4404e52b3346 100644 --- a/net/smc/smc_llc.h +++ b/net/smc/smc_llc.h @@ -30,10 +30,19 @@ enum smc_llc_msg_type { SMC_LLC_ADD_LINK = 0x02, SMC_LLC_ADD_LINK_CONT = 0x03, SMC_LLC_DELETE_LINK = 0x04, + SMC_LLC_REQ_ADD_LINK = 0x05, SMC_LLC_CONFIRM_RKEY = 0x06, SMC_LLC_TEST_LINK = 0x07, SMC_LLC_CONFIRM_RKEY_CONT = 0x08, SMC_LLC_DELETE_RKEY = 0x09, + /* V2 types */ + SMC_LLC_CONFIRM_LINK_V2 = 0x21, + SMC_LLC_ADD_LINK_V2 = 0x22, + SMC_LLC_DELETE_LINK_V2 = 0x24, + SMC_LLC_REQ_ADD_LINK_V2 = 0x25, + SMC_LLC_CONFIRM_RKEY_V2 = 0x26, + SMC_LLC_TEST_LINK_V2 = 0x27, + SMC_LLC_DELETE_RKEY_V2 = 0x29, }; #define smc_link_downing(state) \ @@ -102,7 +111,8 @@ void smc_llc_flow_qentry_del(struct smc_llc_flow *flow); void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn); int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry); -int smc_llc_srv_add_link(struct smc_link *link); +int smc_llc_srv_add_link(struct smc_link *link, + struct smc_llc_qentry *req_qentry); void smc_llc_add_link_local(struct smc_link *link); int smc_llc_init(void) __init; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 4a964e9190b0..67e9d9fde085 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -953,6 +953,26 @@ static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev, return rc; } +static int smc_pnet_determine_gid(struct smc_ib_device *ibdev, int i, + struct smc_init_info *ini) +{ + if (!ini->check_smcrv2 && + !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->ib_gid, NULL, + NULL)) { + ini->ib_dev = ibdev; + ini->ib_port = i; + return 0; + } + if (ini->check_smcrv2 && + !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->smcrv2.ib_gid_v2, + NULL, &ini->smcrv2)) { + ini->smcrv2.ib_dev_v2 = ibdev; + ini->smcrv2.ib_port_v2 = i; + return 0; + } + return -ENODEV; +} + /* find a roce device for the given pnetid */ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, struct smc_init_info *ini, @@ -961,7 +981,6 @@ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, struct smc_ib_device *ibdev; int i; - ini->ib_dev = NULL; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (ibdev == known_dev) @@ -971,12 +990,9 @@ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, continue; if (smc_pnet_match(ibdev->pnetid[i - 1], pnet_id) && smc_ib_port_active(ibdev, i) && - !test_bit(i - 1, ibdev->ports_going_away) && - !smc_ib_determine_gid(ibdev, i, ini->vlan_id, - ini->ib_gid, NULL)) { - ini->ib_dev = ibdev; - ini->ib_port = i; - goto out; + !test_bit(i - 1, ibdev->ports_going_away)) { + if (!smc_pnet_determine_gid(ibdev, i, ini)) + goto out; } } } @@ -1016,12 +1032,9 @@ static void smc_pnet_find_rdma_dev(struct net_device *netdev, dev_put(ndev); if (netdev == ndev && smc_ib_port_active(ibdev, i) && - !test_bit(i - 1, ibdev->ports_going_away) && - !smc_ib_determine_gid(ibdev, i, ini->vlan_id, - ini->ib_gid, NULL)) { - ini->ib_dev = ibdev; - ini->ib_port = i; - break; + !test_bit(i - 1, ibdev->ports_going_away)) { + if (!smc_pnet_determine_gid(ibdev, i, ini)) + break; } } } @@ -1083,8 +1096,6 @@ void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); - ini->ib_dev = NULL; - ini->ib_port = 0; if (!dst) goto out; if (!dst->dev) diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index c79361dfcdfb..738a4a99c827 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -496,7 +496,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn, /* Wakeup sndbuf consumers from any context (IRQ or process) * since there is more data to transmit; usable snd_wnd as max transmit */ -static int _smcr_tx_sndbuf_nonempty(struct smc_connection *conn) +static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; struct smc_link *link = conn->lnk; @@ -505,8 +505,11 @@ static int _smcr_tx_sndbuf_nonempty(struct smc_connection *conn) struct smc_wr_buf *wr_buf; int rc; + if (!link || !smc_wr_tx_link_hold(link)) + return -ENOLINK; rc = smc_cdc_get_free_slot(conn, link, &wr_buf, &wr_rdma_buf, &pend); if (rc < 0) { + smc_wr_tx_link_put(link); if (rc == -EBUSY) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); @@ -547,22 +550,7 @@ static int _smcr_tx_sndbuf_nonempty(struct smc_connection *conn) out_unlock: spin_unlock_bh(&conn->send_lock); - return rc; -} - -static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) -{ - struct smc_link *link = conn->lnk; - int rc = -ENOLINK; - - if (!link) - return rc; - - atomic_inc(&link->wr_tx_refcnt); - if (smc_link_usable(link)) - rc = _smcr_tx_sndbuf_nonempty(conn); - if (atomic_dec_and_test(&link->wr_tx_refcnt)) - wake_up_all(&link->wr_tx_wait); + smc_wr_tx_link_put(link); return rc; } diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index a419e9af36b9..600ab5889227 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -101,19 +101,32 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc) } pnd_snd_idx = smc_wr_tx_find_pending_index(link, wc->wr_id); - if (pnd_snd_idx == link->wr_tx_cnt) - return; - link->wr_tx_pends[pnd_snd_idx].wc_status = wc->status; - if (link->wr_tx_pends[pnd_snd_idx].compl_requested) - complete(&link->wr_tx_compl[pnd_snd_idx]); - memcpy(&pnd_snd, &link->wr_tx_pends[pnd_snd_idx], sizeof(pnd_snd)); - /* clear the full struct smc_wr_tx_pend including .priv */ - memset(&link->wr_tx_pends[pnd_snd_idx], 0, - sizeof(link->wr_tx_pends[pnd_snd_idx])); - memset(&link->wr_tx_bufs[pnd_snd_idx], 0, - sizeof(link->wr_tx_bufs[pnd_snd_idx])); - if (!test_and_clear_bit(pnd_snd_idx, link->wr_tx_mask)) - return; + if (pnd_snd_idx == link->wr_tx_cnt) { + if (link->lgr->smc_version != SMC_V2 || + link->wr_tx_v2_pend->wr_id != wc->wr_id) + return; + link->wr_tx_v2_pend->wc_status = wc->status; + memcpy(&pnd_snd, link->wr_tx_v2_pend, sizeof(pnd_snd)); + /* clear the full struct smc_wr_tx_pend including .priv */ + memset(link->wr_tx_v2_pend, 0, + sizeof(*link->wr_tx_v2_pend)); + memset(link->lgr->wr_tx_buf_v2, 0, + sizeof(*link->lgr->wr_tx_buf_v2)); + } else { + link->wr_tx_pends[pnd_snd_idx].wc_status = wc->status; + if (link->wr_tx_pends[pnd_snd_idx].compl_requested) + complete(&link->wr_tx_compl[pnd_snd_idx]); + memcpy(&pnd_snd, &link->wr_tx_pends[pnd_snd_idx], + sizeof(pnd_snd)); + /* clear the full struct smc_wr_tx_pend including .priv */ + memset(&link->wr_tx_pends[pnd_snd_idx], 0, + sizeof(link->wr_tx_pends[pnd_snd_idx])); + memset(&link->wr_tx_bufs[pnd_snd_idx], 0, + sizeof(link->wr_tx_bufs[pnd_snd_idx])); + if (!test_and_clear_bit(pnd_snd_idx, link->wr_tx_mask)) + return; + } + if (wc->status) { for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) { /* clear full struct smc_wr_tx_pend including .priv */ @@ -123,6 +136,12 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc) sizeof(link->wr_tx_bufs[i])); clear_bit(i, link->wr_tx_mask); } + if (link->lgr->smc_version == SMC_V2) { + memset(link->wr_tx_v2_pend, 0, + sizeof(*link->wr_tx_v2_pend)); + memset(link->lgr->wr_tx_buf_v2, 0, + sizeof(*link->lgr->wr_tx_buf_v2)); + } /* terminate link */ smcr_link_down_cond_sched(link); } @@ -239,6 +258,33 @@ int smc_wr_tx_get_free_slot(struct smc_link *link, return 0; } +int smc_wr_tx_get_v2_slot(struct smc_link *link, + smc_wr_tx_handler handler, + struct smc_wr_v2_buf **wr_buf, + struct smc_wr_tx_pend_priv **wr_pend_priv) +{ + struct smc_wr_tx_pend *wr_pend; + struct ib_send_wr *wr_ib; + u64 wr_id; + + if (link->wr_tx_v2_pend->idx == link->wr_tx_cnt) + return -EBUSY; + + *wr_buf = NULL; + *wr_pend_priv = NULL; + wr_id = smc_wr_tx_get_next_wr_id(link); + wr_pend = link->wr_tx_v2_pend; + wr_pend->wr_id = wr_id; + wr_pend->handler = handler; + wr_pend->link = link; + wr_pend->idx = link->wr_tx_cnt; + wr_ib = link->wr_tx_v2_ib; + wr_ib->wr_id = wr_id; + *wr_buf = link->lgr->wr_tx_buf_v2; + *wr_pend_priv = &wr_pend->priv; + return 0; +} + int smc_wr_tx_put_slot(struct smc_link *link, struct smc_wr_tx_pend_priv *wr_pend_priv) { @@ -256,6 +302,14 @@ int smc_wr_tx_put_slot(struct smc_link *link, test_and_clear_bit(idx, link->wr_tx_mask); wake_up(&link->wr_tx_wait); return 1; + } else if (link->lgr->smc_version == SMC_V2 && + pend->idx == link->wr_tx_cnt) { + /* Large v2 buffer */ + memset(&link->wr_tx_v2_pend, 0, + sizeof(link->wr_tx_v2_pend)); + memset(&link->lgr->wr_tx_buf_v2, 0, + sizeof(link->lgr->wr_tx_buf_v2)); + return 1; } return 0; @@ -280,6 +334,22 @@ int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv) return rc; } +int smc_wr_tx_v2_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv, + int len) +{ + int rc; + + link->wr_tx_v2_ib->sg_list[0].length = len; + ib_req_notify_cq(link->smcibdev->roce_cq_send, + IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS); + rc = ib_post_send(link->roce_qp, link->wr_tx_v2_ib, NULL); + if (rc) { + smc_wr_tx_put_slot(link, priv); + smcr_link_down_cond_sched(link); + } + return rc; +} + /* Send prepared WR slot via ib_post_send and wait for send completion * notification. * @priv: pointer to smc_wr_tx_pend_priv identifying prepared message buffer @@ -517,6 +587,7 @@ void smc_wr_remember_qp_attr(struct smc_link *lnk) static void smc_wr_init_sge(struct smc_link *lnk) { + int sges_per_buf = (lnk->lgr->smc_version == SMC_V2) ? 2 : 1; u32 i; for (i = 0; i < lnk->wr_tx_cnt; i++) { @@ -545,14 +616,44 @@ static void smc_wr_init_sge(struct smc_link *lnk) lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.sg_list = lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge; } + + if (lnk->lgr->smc_version == SMC_V2) { + lnk->wr_tx_v2_sge->addr = lnk->wr_tx_v2_dma_addr; + lnk->wr_tx_v2_sge->length = SMC_WR_BUF_V2_SIZE; + lnk->wr_tx_v2_sge->lkey = lnk->roce_pd->local_dma_lkey; + + lnk->wr_tx_v2_ib->next = NULL; + lnk->wr_tx_v2_ib->sg_list = lnk->wr_tx_v2_sge; + lnk->wr_tx_v2_ib->num_sge = 1; + lnk->wr_tx_v2_ib->opcode = IB_WR_SEND; + lnk->wr_tx_v2_ib->send_flags = + IB_SEND_SIGNALED | IB_SEND_SOLICITED; + } + + /* With SMC-Rv2 there can be messages larger than SMC_WR_TX_SIZE. + * Each ib_recv_wr gets 2 sges, the second one is a spillover buffer + * and the same buffer for all sges. When a larger message arrived then + * the content of the first small sge is copied to the beginning of + * the larger spillover buffer, allowing easy data mapping. + */ for (i = 0; i < lnk->wr_rx_cnt; i++) { - lnk->wr_rx_sges[i].addr = + int x = i * sges_per_buf; + + lnk->wr_rx_sges[x].addr = lnk->wr_rx_dma_addr + i * SMC_WR_BUF_SIZE; - lnk->wr_rx_sges[i].length = SMC_WR_BUF_SIZE; - lnk->wr_rx_sges[i].lkey = lnk->roce_pd->local_dma_lkey; + lnk->wr_rx_sges[x].length = SMC_WR_TX_SIZE; + lnk->wr_rx_sges[x].lkey = lnk->roce_pd->local_dma_lkey; + if (lnk->lgr->smc_version == SMC_V2) { + lnk->wr_rx_sges[x + 1].addr = + lnk->wr_rx_v2_dma_addr + SMC_WR_TX_SIZE; + lnk->wr_rx_sges[x + 1].length = + SMC_WR_BUF_V2_SIZE - SMC_WR_TX_SIZE; + lnk->wr_rx_sges[x + 1].lkey = + lnk->roce_pd->local_dma_lkey; + } lnk->wr_rx_ibs[i].next = NULL; - lnk->wr_rx_ibs[i].sg_list = &lnk->wr_rx_sges[i]; - lnk->wr_rx_ibs[i].num_sge = 1; + lnk->wr_rx_ibs[i].sg_list = &lnk->wr_rx_sges[x]; + lnk->wr_rx_ibs[i].num_sge = sges_per_buf; } lnk->wr_reg.wr.next = NULL; lnk->wr_reg.wr.num_sge = 0; @@ -585,16 +686,45 @@ void smc_wr_free_link(struct smc_link *lnk) DMA_FROM_DEVICE); lnk->wr_rx_dma_addr = 0; } + if (lnk->wr_rx_v2_dma_addr) { + ib_dma_unmap_single(ibdev, lnk->wr_rx_v2_dma_addr, + SMC_WR_BUF_V2_SIZE, + DMA_FROM_DEVICE); + lnk->wr_rx_v2_dma_addr = 0; + } if (lnk->wr_tx_dma_addr) { ib_dma_unmap_single(ibdev, lnk->wr_tx_dma_addr, SMC_WR_BUF_SIZE * lnk->wr_tx_cnt, DMA_TO_DEVICE); lnk->wr_tx_dma_addr = 0; } + if (lnk->wr_tx_v2_dma_addr) { + ib_dma_unmap_single(ibdev, lnk->wr_tx_v2_dma_addr, + SMC_WR_BUF_V2_SIZE, + DMA_TO_DEVICE); + lnk->wr_tx_v2_dma_addr = 0; + } +} + +void smc_wr_free_lgr_mem(struct smc_link_group *lgr) +{ + if (lgr->smc_version < SMC_V2) + return; + + kfree(lgr->wr_rx_buf_v2); + lgr->wr_rx_buf_v2 = NULL; + kfree(lgr->wr_tx_buf_v2); + lgr->wr_tx_buf_v2 = NULL; } void smc_wr_free_link_mem(struct smc_link *lnk) { + kfree(lnk->wr_tx_v2_ib); + lnk->wr_tx_v2_ib = NULL; + kfree(lnk->wr_tx_v2_sge); + lnk->wr_tx_v2_sge = NULL; + kfree(lnk->wr_tx_v2_pend); + lnk->wr_tx_v2_pend = NULL; kfree(lnk->wr_tx_compl); lnk->wr_tx_compl = NULL; kfree(lnk->wr_tx_pends); @@ -619,8 +749,26 @@ void smc_wr_free_link_mem(struct smc_link *lnk) lnk->wr_rx_bufs = NULL; } +int smc_wr_alloc_lgr_mem(struct smc_link_group *lgr) +{ + if (lgr->smc_version < SMC_V2) + return 0; + + lgr->wr_rx_buf_v2 = kzalloc(SMC_WR_BUF_V2_SIZE, GFP_KERNEL); + if (!lgr->wr_rx_buf_v2) + return -ENOMEM; + lgr->wr_tx_buf_v2 = kzalloc(SMC_WR_BUF_V2_SIZE, GFP_KERNEL); + if (!lgr->wr_tx_buf_v2) { + kfree(lgr->wr_rx_buf_v2); + return -ENOMEM; + } + return 0; +} + int smc_wr_alloc_link_mem(struct smc_link *link) { + int sges_per_buf = link->lgr->smc_version == SMC_V2 ? 2 : 1; + /* allocate link related memory */ link->wr_tx_bufs = kcalloc(SMC_WR_BUF_CNT, SMC_WR_BUF_SIZE, GFP_KERNEL); if (!link->wr_tx_bufs) @@ -653,7 +801,7 @@ int smc_wr_alloc_link_mem(struct smc_link *link) if (!link->wr_tx_sges) goto no_mem_wr_tx_rdma_sges; link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3, - sizeof(link->wr_rx_sges[0]), + sizeof(link->wr_rx_sges[0]) * sges_per_buf, GFP_KERNEL); if (!link->wr_rx_sges) goto no_mem_wr_tx_sges; @@ -672,8 +820,29 @@ int smc_wr_alloc_link_mem(struct smc_link *link) GFP_KERNEL); if (!link->wr_tx_compl) goto no_mem_wr_tx_pends; + + if (link->lgr->smc_version == SMC_V2) { + link->wr_tx_v2_ib = kzalloc(sizeof(*link->wr_tx_v2_ib), + GFP_KERNEL); + if (!link->wr_tx_v2_ib) + goto no_mem_tx_compl; + link->wr_tx_v2_sge = kzalloc(sizeof(*link->wr_tx_v2_sge), + GFP_KERNEL); + if (!link->wr_tx_v2_sge) + goto no_mem_v2_ib; + link->wr_tx_v2_pend = kzalloc(sizeof(*link->wr_tx_v2_pend), + GFP_KERNEL); + if (!link->wr_tx_v2_pend) + goto no_mem_v2_sge; + } return 0; +no_mem_v2_sge: + kfree(link->wr_tx_v2_sge); +no_mem_v2_ib: + kfree(link->wr_tx_v2_ib); +no_mem_tx_compl: + kfree(link->wr_tx_compl); no_mem_wr_tx_pends: kfree(link->wr_tx_pends); no_mem_wr_tx_mask: @@ -725,6 +894,24 @@ int smc_wr_create_link(struct smc_link *lnk) rc = -EIO; goto out; } + if (lnk->lgr->smc_version == SMC_V2) { + lnk->wr_rx_v2_dma_addr = ib_dma_map_single(ibdev, + lnk->lgr->wr_rx_buf_v2, SMC_WR_BUF_V2_SIZE, + DMA_FROM_DEVICE); + if (ib_dma_mapping_error(ibdev, lnk->wr_rx_v2_dma_addr)) { + lnk->wr_rx_v2_dma_addr = 0; + rc = -EIO; + goto dma_unmap; + } + lnk->wr_tx_v2_dma_addr = ib_dma_map_single(ibdev, + lnk->lgr->wr_tx_buf_v2, SMC_WR_BUF_V2_SIZE, + DMA_TO_DEVICE); + if (ib_dma_mapping_error(ibdev, lnk->wr_tx_v2_dma_addr)) { + lnk->wr_tx_v2_dma_addr = 0; + rc = -EIO; + goto dma_unmap; + } + } lnk->wr_tx_dma_addr = ib_dma_map_single( ibdev, lnk->wr_tx_bufs, SMC_WR_BUF_SIZE * lnk->wr_tx_cnt, DMA_TO_DEVICE); @@ -742,6 +929,18 @@ int smc_wr_create_link(struct smc_link *lnk) return rc; dma_unmap: + if (lnk->wr_rx_v2_dma_addr) { + ib_dma_unmap_single(ibdev, lnk->wr_rx_v2_dma_addr, + SMC_WR_BUF_V2_SIZE, + DMA_FROM_DEVICE); + lnk->wr_rx_v2_dma_addr = 0; + } + if (lnk->wr_tx_v2_dma_addr) { + ib_dma_unmap_single(ibdev, lnk->wr_tx_v2_dma_addr, + SMC_WR_BUF_V2_SIZE, + DMA_TO_DEVICE); + lnk->wr_tx_v2_dma_addr = 0; + } ib_dma_unmap_single(ibdev, lnk->wr_rx_dma_addr, SMC_WR_BUF_SIZE * lnk->wr_rx_cnt, DMA_FROM_DEVICE); diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index 423b8709f1c9..f353311e6f84 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -60,6 +60,20 @@ static inline void smc_wr_tx_set_wr_id(atomic_long_t *wr_tx_id, long val) atomic_long_set(wr_tx_id, val); } +static inline bool smc_wr_tx_link_hold(struct smc_link *link) +{ + if (!smc_link_usable(link)) + return false; + atomic_inc(&link->wr_tx_refcnt); + return true; +} + +static inline void smc_wr_tx_link_put(struct smc_link *link) +{ + if (atomic_dec_and_test(&link->wr_tx_refcnt)) + wake_up_all(&link->wr_tx_wait); +} + static inline void smc_wr_wakeup_tx_wait(struct smc_link *lnk) { wake_up_all(&lnk->wr_tx_wait); @@ -87,8 +101,10 @@ static inline int smc_wr_rx_post(struct smc_link *link) int smc_wr_create_link(struct smc_link *lnk); int smc_wr_alloc_link_mem(struct smc_link *lnk); +int smc_wr_alloc_lgr_mem(struct smc_link_group *lgr); void smc_wr_free_link(struct smc_link *lnk); void smc_wr_free_link_mem(struct smc_link *lnk); +void smc_wr_free_lgr_mem(struct smc_link_group *lgr); void smc_wr_remember_qp_attr(struct smc_link *lnk); void smc_wr_remove_dev(struct smc_ib_device *smcibdev); void smc_wr_add_dev(struct smc_ib_device *smcibdev); @@ -97,10 +113,16 @@ int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, struct smc_rdma_wr **wrs, struct smc_wr_tx_pend_priv **wr_pend_priv); +int smc_wr_tx_get_v2_slot(struct smc_link *link, + smc_wr_tx_handler handler, + struct smc_wr_v2_buf **wr_buf, + struct smc_wr_tx_pend_priv **wr_pend_priv); int smc_wr_tx_put_slot(struct smc_link *link, struct smc_wr_tx_pend_priv *wr_pend_priv); int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *wr_pend_priv); +int smc_wr_tx_v2_send(struct smc_link *link, + struct smc_wr_tx_pend_priv *priv, int len); int smc_wr_tx_send_wait(struct smc_link *link, struct smc_wr_tx_pend_priv *priv, unsigned long timeout); void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context); diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 3e776e3dff91..1f2817195549 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -645,7 +645,7 @@ static bool gss_check_seq_num(const struct svc_rqst *rqstp, struct rsc *rsci, } __set_bit(seq_num % GSS_SEQ_WIN, sd->sd_win); goto ok; - } else if (seq_num <= sd->sd_max - GSS_SEQ_WIN) { + } else if (seq_num + GSS_SEQ_WIN <= sd->sd_max) { goto toolow; } if (__test_and_set_bit(seq_num % GSS_SEQ_WIN, sd->sd_win)) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 443f8e5b9477..60bc74b76adc 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -462,7 +462,7 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, b->bcast_addr.media_id = b->media->type_id; b->bcast_addr.broadcast = TIPC_BROADCAST_SUPPORT; b->mtu = dev->mtu; - b->media->raw2addr(b, &b->addr, (char *)dev->dev_addr); + b->media->raw2addr(b, &b->addr, (const char *)dev->dev_addr); rcu_assign_pointer(dev->tipc_ptr, b); return 0; } @@ -703,7 +703,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, break; case NETDEV_CHANGEADDR: b->media->raw2addr(b, &b->addr, - (char *)dev->dev_addr); + (const char *)dev->dev_addr); tipc_reset_bearer(net, b); break; case NETDEV_UNREGISTER: diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 57c6a1a719e2..490ad6e5f7a3 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -117,7 +117,7 @@ struct tipc_media { char *msg); int (*raw2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, - char *raw); + const char *raw); u32 priority; u32 tolerance; u32 min_win; diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c index c68019697cfe..cb0d185e06af 100644 --- a/net/tipc/eth_media.c +++ b/net/tipc/eth_media.c @@ -60,7 +60,7 @@ static int tipc_eth_addr2msg(char *msg, struct tipc_media_addr *addr) /* Convert raw mac address format to media addr format */ static int tipc_eth_raw2addr(struct tipc_bearer *b, struct tipc_media_addr *addr, - char *msg) + const char *msg) { memset(addr, 0, sizeof(*addr)); ether_addr_copy(addr->value, msg); diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c index 7aa9ff88458d..b9ad0434c3cd 100644 --- a/net/tipc/ib_media.c +++ b/net/tipc/ib_media.c @@ -67,7 +67,7 @@ static int tipc_ib_addr2msg(char *msg, struct tipc_media_addr *addr) /* Convert raw InfiniBand address format to media addr format */ static int tipc_ib_raw2addr(struct tipc_bearer *b, struct tipc_media_addr *addr, - char *msg) + const char *msg) { memset(addr, 0, sizeof(*addr)); memcpy(addr->value, msg, INFINIBAND_ALEN); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index efac5989edb5..89f9e85ae970 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -828,7 +828,7 @@ static void unix_unhash(struct sock *sk) } struct proto unix_dgram_proto = { - .name = "UNIX-DGRAM", + .name = "UNIX", .owner = THIS_MODULE, .obj_size = sizeof(struct unix_sock), .close = unix_close, @@ -2882,6 +2882,9 @@ static int unix_shutdown(struct socket *sock, int mode) unix_state_lock(sk); sk->sk_shutdown |= mode; + if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && + mode == SHUTDOWN_MASK) + sk->sk_state = TCP_CLOSE; other = unix_peer(sk); if (other) sock_hold(other); @@ -2904,12 +2907,10 @@ static int unix_shutdown(struct socket *sock, int mode) other->sk_shutdown |= peer_mode; unix_state_unlock(other); other->sk_state_change(other); - if (peer_mode == SHUTDOWN_MASK) { + if (peer_mode == SHUTDOWN_MASK) sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP); - other->sk_state = TCP_CLOSE; - } else if (peer_mode & RCV_SHUTDOWN) { + else if (peer_mode & RCV_SHUTDOWN) sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN); - } } if (other) sock_put(other); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index e2c0cfb334d2..7d851eb3a683 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1614,13 +1614,18 @@ static int vsock_connectible_setsockopt(struct socket *sock, vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; - case SO_VM_SOCKETS_CONNECT_TIMEOUT: { - struct __kernel_old_timeval tv; - COPY_IN(tv); + case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: + case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: { + struct __kernel_sock_timeval tv; + + err = sock_copy_user_timeval(&tv, optval, optlen, + optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); + if (err) + break; if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC && tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) { vsk->connect_timeout = tv.tv_sec * HZ + - DIV_ROUND_UP(tv.tv_usec, (1000000 / HZ)); + DIV_ROUND_UP((unsigned long)tv.tv_usec, (USEC_PER_SEC / HZ)); if (vsk->connect_timeout == 0) vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; @@ -1648,68 +1653,59 @@ static int vsock_connectible_getsockopt(struct socket *sock, char __user *optval, int __user *optlen) { - int err; + struct sock *sk = sock->sk; + struct vsock_sock *vsk = vsock_sk(sk); + + union { + u64 val64; + struct old_timeval32 tm32; + struct __kernel_old_timeval tm; + struct __kernel_sock_timeval stm; + } v; + + int lv = sizeof(v.val64); int len; - struct sock *sk; - struct vsock_sock *vsk; - u64 val; if (level != AF_VSOCK) return -ENOPROTOOPT; - err = get_user(len, optlen); - if (err != 0) - return err; - -#define COPY_OUT(_v) \ - do { \ - if (len < sizeof(_v)) \ - return -EINVAL; \ - \ - len = sizeof(_v); \ - if (copy_to_user(optval, &_v, len) != 0) \ - return -EFAULT; \ - \ - } while (0) + if (get_user(len, optlen)) + return -EFAULT; - err = 0; - sk = sock->sk; - vsk = vsock_sk(sk); + memset(&v, 0, sizeof(v)); switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: - val = vsk->buffer_size; - COPY_OUT(val); + v.val64 = vsk->buffer_size; break; case SO_VM_SOCKETS_BUFFER_MAX_SIZE: - val = vsk->buffer_max_size; - COPY_OUT(val); + v.val64 = vsk->buffer_max_size; break; case SO_VM_SOCKETS_BUFFER_MIN_SIZE: - val = vsk->buffer_min_size; - COPY_OUT(val); + v.val64 = vsk->buffer_min_size; break; - case SO_VM_SOCKETS_CONNECT_TIMEOUT: { - struct __kernel_old_timeval tv; - tv.tv_sec = vsk->connect_timeout / HZ; - tv.tv_usec = - (vsk->connect_timeout - - tv.tv_sec * HZ) * (1000000 / HZ); - COPY_OUT(tv); + case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: + case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: + lv = sock_get_timeout(vsk->connect_timeout, &v, + optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); break; - } + default: return -ENOPROTOOPT; } - err = put_user(len, optlen); - if (err != 0) + if (len < lv) + return -EINVAL; + if (len > lv) + len = lv; + if (copy_to_user(optval, &v, len)) return -EFAULT; -#undef COPY_OUT + if (put_user(len, optlen)) + return -EFAULT; return 0; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 03b66d154b2b..3a3cb09eec12 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1961,24 +1961,65 @@ static struct sk_buff *xfrm_policy_netlink(struct sk_buff *in_skb, return skb; } +static int xfrm_notify_userpolicy(struct net *net) +{ + struct xfrm_userpolicy_default *up; + int len = NLMSG_ALIGN(sizeof(*up)); + struct nlmsghdr *nlh; + struct sk_buff *skb; + int err; + + skb = nlmsg_new(len, GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + + nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_GETDEFAULT, sizeof(*up), 0); + if (nlh == NULL) { + kfree_skb(skb); + return -EMSGSIZE; + } + + up = nlmsg_data(nlh); + up->in = net->xfrm.policy_default & XFRM_POL_DEFAULT_IN ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; + up->fwd = net->xfrm.policy_default & XFRM_POL_DEFAULT_FWD ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; + up->out = net->xfrm.policy_default & XFRM_POL_DEFAULT_OUT ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; + + nlmsg_end(skb, nlh); + + rcu_read_lock(); + err = xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY); + rcu_read_unlock(); + + return err; +} + static int xfrm_set_default(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { struct net *net = sock_net(skb->sk); struct xfrm_userpolicy_default *up = nlmsg_data(nlh); - u8 dirmask; - u8 old_default = net->xfrm.policy_default; - if (up->dirmask >= XFRM_USERPOLICY_DIRMASK_MAX) - return -EINVAL; + if (up->in == XFRM_USERPOLICY_BLOCK) + net->xfrm.policy_default |= XFRM_POL_DEFAULT_IN; + else if (up->in == XFRM_USERPOLICY_ACCEPT) + net->xfrm.policy_default &= ~XFRM_POL_DEFAULT_IN; - dirmask = (1 << up->dirmask) & XFRM_POL_DEFAULT_MASK; + if (up->fwd == XFRM_USERPOLICY_BLOCK) + net->xfrm.policy_default |= XFRM_POL_DEFAULT_FWD; + else if (up->fwd == XFRM_USERPOLICY_ACCEPT) + net->xfrm.policy_default &= ~XFRM_POL_DEFAULT_FWD; - net->xfrm.policy_default = (old_default & (0xff ^ dirmask)) - | (up->action << up->dirmask); + if (up->out == XFRM_USERPOLICY_BLOCK) + net->xfrm.policy_default |= XFRM_POL_DEFAULT_OUT; + else if (up->out == XFRM_USERPOLICY_ACCEPT) + net->xfrm.policy_default &= ~XFRM_POL_DEFAULT_OUT; rt_genid_bump_all(net); + xfrm_notify_userpolicy(net); return 0; } @@ -1988,13 +2029,11 @@ static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh, struct sk_buff *r_skb; struct nlmsghdr *r_nlh; struct net *net = sock_net(skb->sk); - struct xfrm_userpolicy_default *r_up, *up; + struct xfrm_userpolicy_default *r_up; int len = NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_default)); u32 portid = NETLINK_CB(skb).portid; u32 seq = nlh->nlmsg_seq; - up = nlmsg_data(nlh); - r_skb = nlmsg_new(len, GFP_ATOMIC); if (!r_skb) return -ENOMEM; @@ -2007,8 +2046,12 @@ static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh, r_up = nlmsg_data(r_nlh); - r_up->action = ((net->xfrm.policy_default & (1 << up->dirmask)) >> up->dirmask); - r_up->dirmask = up->dirmask; + r_up->in = net->xfrm.policy_default & XFRM_POL_DEFAULT_IN ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; + r_up->fwd = net->xfrm.policy_default & XFRM_POL_DEFAULT_FWD ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; + r_up->out = net->xfrm.policy_default & XFRM_POL_DEFAULT_OUT ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; nlmsg_end(r_skb, r_nlh); return nlmsg_unicast(net->xfrm.nlsk, r_skb, portid); diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 4dc20be5fb96..5fd48a8d4f10 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -322,17 +322,11 @@ $(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.h -include $(BPF_SAMPLES_PATH)/Makefile.target -VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ - $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ - ../../../../vmlinux \ - /sys/kernel/btf/vmlinux \ - /boot/vmlinux-$(shell uname -r) +VMLINUX_BTF_PATHS ?= $(abspath $(if $(O),$(O)/vmlinux)) \ + $(abspath $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)) \ + $(abspath ./vmlinux) VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) -ifeq ($(VMLINUX_BTF),) -$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)") -endif - $(obj)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) ifeq ($(VMLINUX_H),) $(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@ @@ -340,6 +334,11 @@ else $(Q)cp "$(VMLINUX_H)" $@ endif +ifeq ($(VMLINUX_BTF),) + $(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)",\ + build the kernel or set VMLINUX_BTF variable) +endif + clean-files += vmlinux.h # Get Clang's default includes on this system, as opposed to those seen by diff --git a/samples/bpf/bpf_insn.h b/samples/bpf/bpf_insn.h index aee04534483a..29c3bb6ad1cd 100644 --- a/samples/bpf/bpf_insn.h +++ b/samples/bpf/bpf_insn.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ /* eBPF instruction mini library */ #ifndef __BPF_INSN_H #define __BPF_INSN_H diff --git a/samples/bpf/xdp_redirect_map_multi.bpf.c b/samples/bpf/xdp_redirect_map_multi.bpf.c index 8f59d430cb64..bb0a5a3bfcf0 100644 --- a/samples/bpf/xdp_redirect_map_multi.bpf.c +++ b/samples/bpf/xdp_redirect_map_multi.bpf.c @@ -5,11 +5,6 @@ #include "xdp_sample.bpf.h" #include "xdp_sample_shared.h" -enum { - BPF_F_BROADCAST = (1ULL << 3), - BPF_F_EXCLUDE_INGRESS = (1ULL << 4), -}; - struct { __uint(type, BPF_MAP_TYPE_DEVMAP_HASH); __uint(key_size, sizeof(int)); diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins index 952e46876329..4aad28480035 100644 --- a/scripts/Makefile.gcc-plugins +++ b/scripts/Makefile.gcc-plugins @@ -19,6 +19,10 @@ gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF) \ += -fplugin-arg-structleak_plugin-byref gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL) \ += -fplugin-arg-structleak_plugin-byref-all +ifdef CONFIG_GCC_PLUGIN_STRUCTLEAK + DISABLE_STRUCTLEAK_PLUGIN += -fplugin-arg-structleak_plugin-disable +endif +export DISABLE_STRUCTLEAK_PLUGIN gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK) \ += -DSTRUCTLEAK_PLUGIN diff --git a/scripts/checksyscalls.sh b/scripts/checksyscalls.sh index fd9777f63f14..9dbab13329fa 100755 --- a/scripts/checksyscalls.sh +++ b/scripts/checksyscalls.sh @@ -82,10 +82,8 @@ cat << EOF #define __IGNORE_truncate64 #define __IGNORE_stat64 #define __IGNORE_lstat64 -#define __IGNORE_fstat64 #define __IGNORE_fcntl64 #define __IGNORE_fadvise64_64 -#define __IGNORE_fstatat64 #define __IGNORE_fstatfs64 #define __IGNORE_statfs64 #define __IGNORE_llseek @@ -253,6 +251,10 @@ cat << EOF #define __IGNORE_getpmsg #define __IGNORE_putpmsg #define __IGNORE_vserver + +/* 64-bit ports never needed these, and new 32-bit ports can use statx */ +#define __IGNORE_fstat64 +#define __IGNORE_fstatat64 EOF } diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index d59276f48d4f..94ea2a8b2bb7 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -126,6 +126,8 @@ static const struct nlmsg_perm nlmsg_xfrm_perms[] = { XFRM_MSG_NEWSPDINFO, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_GETSPDINFO, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_MAPPING, NETLINK_XFRM_SOCKET__NLMSG_READ }, + { XFRM_MSG_SETDEFAULT, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, + { XFRM_MSG_GETDEFAULT, NETLINK_XFRM_SOCKET__NLMSG_READ }, }; static const struct nlmsg_perm nlmsg_audit_perms[] = @@ -189,7 +191,7 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) * structures at the top of this file with the new mappings * before updating the BUILD_BUG_ON() macro! */ - BUILD_BUG_ON(XFRM_MSG_MAX != XFRM_MSG_MAPPING); + BUILD_BUG_ON(XFRM_MSG_MAX != XFRM_MSG_GETDEFAULT); err = nlmsg_perm(nlmsg_type, perm, nlmsg_xfrm_perms, sizeof(nlmsg_xfrm_perms)); break; diff --git a/sound/core/pcm_compat.c b/sound/core/pcm_compat.c index a59de24695ec..dfe5a64e19d2 100644 --- a/sound/core/pcm_compat.c +++ b/sound/core/pcm_compat.c @@ -468,6 +468,76 @@ static int snd_pcm_ioctl_sync_ptr_x32(struct snd_pcm_substream *substream, } #endif /* CONFIG_X86_X32 */ +#ifdef __BIG_ENDIAN +typedef char __pad_before_u32[4]; +typedef char __pad_after_u32[0]; +#else +typedef char __pad_before_u32[0]; +typedef char __pad_after_u32[4]; +#endif + +/* PCM 2.0.15 API definition had a bug in mmap control; it puts the avail_min + * at the wrong offset due to a typo in padding type. + * The bug hits only 32bit. + * A workaround for incorrect read/write is needed only in 32bit compat mode. + */ +struct __snd_pcm_mmap_control64_buggy { + __pad_before_u32 __pad1; + __u32 appl_ptr; + __pad_before_u32 __pad2; /* SiC! here is the bug */ + __pad_before_u32 __pad3; + __u32 avail_min; + __pad_after_uframe __pad4; +}; + +static int snd_pcm_ioctl_sync_ptr_buggy(struct snd_pcm_substream *substream, + struct snd_pcm_sync_ptr __user *_sync_ptr) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + struct snd_pcm_sync_ptr sync_ptr; + struct __snd_pcm_mmap_control64_buggy *sync_cp; + volatile struct snd_pcm_mmap_status *status; + volatile struct snd_pcm_mmap_control *control; + int err; + + memset(&sync_ptr, 0, sizeof(sync_ptr)); + sync_cp = (struct __snd_pcm_mmap_control64_buggy *)&sync_ptr.c.control; + if (get_user(sync_ptr.flags, (unsigned __user *)&(_sync_ptr->flags))) + return -EFAULT; + if (copy_from_user(sync_cp, &(_sync_ptr->c.control), sizeof(*sync_cp))) + return -EFAULT; + status = runtime->status; + control = runtime->control; + if (sync_ptr.flags & SNDRV_PCM_SYNC_PTR_HWSYNC) { + err = snd_pcm_hwsync(substream); + if (err < 0) + return err; + } + snd_pcm_stream_lock_irq(substream); + if (!(sync_ptr.flags & SNDRV_PCM_SYNC_PTR_APPL)) { + err = pcm_lib_apply_appl_ptr(substream, sync_cp->appl_ptr); + if (err < 0) { + snd_pcm_stream_unlock_irq(substream); + return err; + } + } else { + sync_cp->appl_ptr = control->appl_ptr; + } + if (!(sync_ptr.flags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN)) + control->avail_min = sync_cp->avail_min; + else + sync_cp->avail_min = control->avail_min; + sync_ptr.s.status.state = status->state; + sync_ptr.s.status.hw_ptr = status->hw_ptr; + sync_ptr.s.status.tstamp = status->tstamp; + sync_ptr.s.status.suspended_state = status->suspended_state; + sync_ptr.s.status.audio_tstamp = status->audio_tstamp; + snd_pcm_stream_unlock_irq(substream); + if (copy_to_user(_sync_ptr, &sync_ptr, sizeof(sync_ptr))) + return -EFAULT; + return 0; +} + /* */ enum { @@ -537,7 +607,7 @@ static long snd_pcm_ioctl_compat(struct file *file, unsigned int cmd, unsigned l if (in_x32_syscall()) return snd_pcm_ioctl_sync_ptr_x32(substream, argp); #endif /* CONFIG_X86_X32 */ - return snd_pcm_common_ioctl(file, substream, cmd, argp); + return snd_pcm_ioctl_sync_ptr_buggy(substream, argp); case SNDRV_PCM_IOCTL_HW_REFINE32: return snd_pcm_ioctl_hw_params_compat(substream, 1, argp); case SNDRV_PCM_IOCTL_HW_PARAMS32: diff --git a/sound/core/seq_device.c b/sound/core/seq_device.c index 382275c5b193..7f3fd8eb016f 100644 --- a/sound/core/seq_device.c +++ b/sound/core/seq_device.c @@ -156,6 +156,8 @@ static int snd_seq_device_dev_free(struct snd_device *device) struct snd_seq_device *dev = device->device_data; cancel_autoload_drivers(); + if (dev->private_free) + dev->private_free(dev); put_device(&dev->dev); return 0; } @@ -183,11 +185,7 @@ static int snd_seq_device_dev_disconnect(struct snd_device *device) static void snd_seq_dev_release(struct device *dev) { - struct snd_seq_device *sdev = to_seq_dev(dev); - - if (sdev->private_free) - sdev->private_free(sdev); - kfree(sdev); + kfree(to_seq_dev(dev)); } /* diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c index 062da7a7a586..f7bd6e2db085 100644 --- a/sound/hda/hdac_controller.c +++ b/sound/hda/hdac_controller.c @@ -421,8 +421,9 @@ int snd_hdac_bus_reset_link(struct hdac_bus *bus, bool full_reset) if (!full_reset) goto skip_reset; - /* clear STATESTS */ - snd_hdac_chip_writew(bus, STATESTS, STATESTS_INT_MASK); + /* clear STATESTS if not in reset */ + if (snd_hdac_chip_readb(bus, GCTL) & AZX_GCTL_RESET) + snd_hdac_chip_writew(bus, STATESTS, STATESTS_INT_MASK); /* reset controller */ snd_hdac_bus_enter_link_reset(bus); diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c index 2523b23389e9..1c8bffc3eec6 100644 --- a/sound/pci/hda/hda_bind.c +++ b/sound/pci/hda/hda_bind.c @@ -298,29 +298,31 @@ int snd_hda_codec_configure(struct hda_codec *codec) { int err; + if (codec->configured) + return 0; + if (is_generic_config(codec)) codec->probe_id = HDA_CODEC_ID_GENERIC; else codec->probe_id = 0; - err = snd_hdac_device_register(&codec->core); - if (err < 0) - return err; + if (!device_is_registered(&codec->core.dev)) { + err = snd_hdac_device_register(&codec->core); + if (err < 0) + return err; + } if (!codec->preset) codec_bind_module(codec); if (!codec->preset) { err = codec_bind_generic(codec); if (err < 0) { - codec_err(codec, "Unable to bind the codec\n"); - goto error; + codec_dbg(codec, "Unable to bind the codec\n"); + return err; } } + codec->configured = 1; return 0; - - error: - snd_hdac_device_unregister(&codec->core); - return err; } EXPORT_SYMBOL_GPL(snd_hda_codec_configure); diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index a9ebefd60cf6..0c4a337c9fc0 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -791,6 +791,7 @@ void snd_hda_codec_cleanup_for_unbind(struct hda_codec *codec) snd_array_free(&codec->nids); remove_conn_list(codec); snd_hdac_regmap_exit(&codec->core); + codec->configured = 0; } EXPORT_SYMBOL_GPL(snd_hda_codec_cleanup_for_unbind); diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 7cd452831fd3..930ae4002a81 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -25,6 +25,7 @@ #include <sound/core.h> #include <sound/initval.h> #include "hda_controller.h" +#include "hda_local.h" #define CREATE_TRACE_POINTS #include "hda_controller_trace.h" @@ -1248,17 +1249,24 @@ EXPORT_SYMBOL_GPL(azx_probe_codecs); int azx_codec_configure(struct azx *chip) { struct hda_codec *codec, *next; + int success = 0; - /* use _safe version here since snd_hda_codec_configure() deregisters - * the device upon error and deletes itself from the bus list. - */ - list_for_each_codec_safe(codec, next, &chip->bus) { - snd_hda_codec_configure(codec); + list_for_each_codec(codec, &chip->bus) { + if (!snd_hda_codec_configure(codec)) + success++; } - if (!azx_bus(chip)->num_codecs) - return -ENODEV; - return 0; + if (success) { + /* unregister failed codecs if any codec has been probed */ + list_for_each_codec_safe(codec, next, &chip->bus) { + if (!codec->configured) { + codec_err(codec, "Unable to configure, disabling\n"); + snd_hdac_device_unregister(&codec->core); + } + } + } + + return success ? 0 : -ENODEV; } EXPORT_SYMBOL_GPL(azx_codec_configure); diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h index 3062f87380b1..f5bf295eb830 100644 --- a/sound/pci/hda/hda_controller.h +++ b/sound/pci/hda/hda_controller.h @@ -41,7 +41,7 @@ /* 24 unused */ #define AZX_DCAPS_COUNT_LPIB_DELAY (1 << 25) /* Take LPIB as delay */ #define AZX_DCAPS_PM_RUNTIME (1 << 26) /* runtime PM support */ -/* 27 unused */ +#define AZX_DCAPS_RETRY_PROBE (1 << 27) /* retry probe if no codec is configured */ #define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28) /* CORBRP clears itself after reset */ #define AZX_DCAPS_NO_MSI64 (1 << 29) /* Stick to 32-bit MSIs */ #define AZX_DCAPS_SEPARATE_STREAM_TAG (1 << 30) /* capture and playback use separate stream tag */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 47777439961c..4d22e7adeee8 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -307,7 +307,8 @@ enum { /* quirks for AMD SB */ #define AZX_DCAPS_PRESET_AMD_SB \ (AZX_DCAPS_NO_TCSEL | AZX_DCAPS_AMD_WORKAROUND |\ - AZX_DCAPS_SNOOP_TYPE(ATI) | AZX_DCAPS_PM_RUNTIME) + AZX_DCAPS_SNOOP_TYPE(ATI) | AZX_DCAPS_PM_RUNTIME |\ + AZX_DCAPS_RETRY_PROBE) /* quirks for Nvidia */ #define AZX_DCAPS_PRESET_NVIDIA \ @@ -1723,7 +1724,7 @@ static void azx_check_snoop_available(struct azx *chip) static void azx_probe_work(struct work_struct *work) { - struct hda_intel *hda = container_of(work, struct hda_intel, probe_work); + struct hda_intel *hda = container_of(work, struct hda_intel, probe_work.work); azx_probe_continue(&hda->chip); } @@ -1828,7 +1829,7 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci, } /* continue probing in work context as may trigger request module */ - INIT_WORK(&hda->probe_work, azx_probe_work); + INIT_DELAYED_WORK(&hda->probe_work, azx_probe_work); *rchip = chip; @@ -2142,7 +2143,7 @@ static int azx_probe(struct pci_dev *pci, #endif if (schedule_probe) - schedule_work(&hda->probe_work); + schedule_delayed_work(&hda->probe_work, 0); dev++; if (chip->disabled) @@ -2228,6 +2229,11 @@ static int azx_probe_continue(struct azx *chip) int dev = chip->dev_index; int err; + if (chip->disabled || hda->init_failed) + return -EIO; + if (hda->probe_retry) + goto probe_retry; + to_hda_bus(bus)->bus_probing = 1; hda->probe_continued = 1; @@ -2289,10 +2295,20 @@ static int azx_probe_continue(struct azx *chip) #endif } #endif + + probe_retry: if (bus->codec_mask && !(probe_only[dev] & 1)) { err = azx_codec_configure(chip); - if (err < 0) + if (err) { + if ((chip->driver_caps & AZX_DCAPS_RETRY_PROBE) && + ++hda->probe_retry < 60) { + schedule_delayed_work(&hda->probe_work, + msecs_to_jiffies(1000)); + return 0; /* keep things up */ + } + dev_err(chip->card->dev, "Cannot probe codecs, giving up\n"); goto out_free; + } } err = snd_card_register(chip->card); @@ -2322,6 +2338,7 @@ out_free: display_power(chip, false); complete_all(&hda->probe_wait); to_hda_bus(bus)->bus_probing = 0; + hda->probe_retry = 0; return 0; } @@ -2347,7 +2364,7 @@ static void azx_remove(struct pci_dev *pci) * device during cancel_work_sync() call. */ device_unlock(&pci->dev); - cancel_work_sync(&hda->probe_work); + cancel_delayed_work_sync(&hda->probe_work); device_lock(&pci->dev); snd_card_free(card); diff --git a/sound/pci/hda/hda_intel.h b/sound/pci/hda/hda_intel.h index 3fb119f09040..0f39418f9328 100644 --- a/sound/pci/hda/hda_intel.h +++ b/sound/pci/hda/hda_intel.h @@ -14,7 +14,7 @@ struct hda_intel { /* sync probing */ struct completion probe_wait; - struct work_struct probe_work; + struct delayed_work probe_work; /* card list (for power_save trigger) */ struct list_head list; @@ -30,6 +30,8 @@ struct hda_intel { unsigned int freed:1; /* resources already released */ bool need_i915_power:1; /* the hda controller needs i915 power */ + + int probe_retry; /* being probe-retry */ }; #endif diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4407f7da57c4..22d27b12c4e7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -526,6 +526,8 @@ static void alc_shutup_pins(struct hda_codec *codec) struct alc_spec *spec = codec->spec; switch (codec->core.vendor_id) { + case 0x10ec0236: + case 0x10ec0256: case 0x10ec0283: case 0x10ec0286: case 0x10ec0288: @@ -2537,7 +2539,8 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x67e5, "Clevo PC70D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK(0x1558, 0x70d1, "Clevo PC70[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS), - SND_PCI_QUIRK(0x1558, 0x7714, "Clevo X170", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x7714, "Clevo X170SM", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x7715, "Clevo X170KM-G", ALC1220_FIXUP_CLEVO_PB51ED), SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x9506, "Clevo P955HQ", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x950a, "Clevo P955H[PR]", ALC1220_FIXUP_CLEVO_P950), @@ -3528,7 +3531,8 @@ static void alc256_shutup(struct hda_codec *codec) /* If disable 3k pulldown control for alc257, the Mic detection will not work correctly * when booting with headset plugged. So skip setting it for the codec alc257 */ - if (codec->core.vendor_id != 0x10ec0257) + if (spec->codec_variant != ALC269_TYPE_ALC257 && + spec->codec_variant != ALC269_TYPE_ALC256) alc_update_coef_idx(codec, 0x46, 0, 3 << 12); if (!spec->no_shutup_pins) @@ -6449,6 +6453,24 @@ static void alc287_fixup_legion_15imhg05_speakers(struct hda_codec *codec, /* for alc285_fixup_ideapad_s740_coef() */ #include "ideapad_s740_helper.c" +static void alc256_fixup_tongfang_reset_persistent_settings(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + /* + * A certain other OS sets these coeffs to different values. On at least one TongFang + * barebone these settings might survive even a cold reboot. So to restore a clean slate the + * values are explicitly reset to default here. Without this, the external microphone is + * always in a plugged-in state, while the internal microphone is always in an unplugged + * state, breaking the ability to use the internal microphone. + */ + alc_write_coef_idx(codec, 0x24, 0x0000); + alc_write_coef_idx(codec, 0x26, 0x0000); + alc_write_coef_idx(codec, 0x29, 0x3000); + alc_write_coef_idx(codec, 0x37, 0xfe05); + alc_write_coef_idx(codec, 0x45, 0x5089); +} + enum { ALC269_FIXUP_GPIO2, ALC269_FIXUP_SONY_VAIO, @@ -6663,7 +6685,8 @@ enum { ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS, ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE, ALC287_FIXUP_YOGA7_14ITL_SPEAKERS, - ALC287_FIXUP_13S_GEN2_SPEAKERS + ALC287_FIXUP_13S_GEN2_SPEAKERS, + ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS, }; static const struct hda_fixup alc269_fixups[] = { @@ -8344,7 +8367,7 @@ static const struct hda_fixup alc269_fixups[] = { .v.verbs = (const struct hda_verb[]) { { 0x20, AC_VERB_SET_COEF_INDEX, 0x24 }, { 0x20, AC_VERB_SET_PROC_COEF, 0x41 }, - { 0x20, AC_VERB_SET_PROC_COEF, 0xb020 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x26 }, { 0x20, AC_VERB_SET_PROC_COEF, 0x2 }, { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, { 0x20, AC_VERB_SET_PROC_COEF, 0x0 }, @@ -8361,6 +8384,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE, }, + [ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc256_fixup_tongfang_reset_persistent_settings, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -8452,6 +8479,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0a30, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0a58, "Dell", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0a61, "Dell XPS 15 9510", ALC289_FIXUP_DUAL_SPK), + SND_PCI_QUIRK(0x1028, 0x0a62, "Dell Precision 5560", ALC289_FIXUP_DUAL_SPK), + SND_PCI_QUIRK(0x1028, 0x0a9d, "Dell Latitude 5430", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0a9e, "Dell Latitude 5430", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), @@ -8789,6 +8819,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */ SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802), SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X), + SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), @@ -10166,6 +10197,9 @@ enum { ALC671_FIXUP_HP_HEADSET_MIC2, ALC662_FIXUP_ACER_X2660G_HEADSET_MODE, ALC662_FIXUP_ACER_NITRO_HEADSET_MODE, + ALC668_FIXUP_ASUS_NO_HEADSET_MIC, + ALC668_FIXUP_HEADSET_MIC, + ALC668_FIXUP_MIC_DET_COEF, }; static const struct hda_fixup alc662_fixups[] = { @@ -10549,6 +10583,29 @@ static const struct hda_fixup alc662_fixups[] = { .chained = true, .chain_id = ALC662_FIXUP_USI_FUNC }, + [ALC668_FIXUP_ASUS_NO_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1b, 0x04a1112c }, + { } + }, + .chained = true, + .chain_id = ALC668_FIXUP_HEADSET_MIC + }, + [ALC668_FIXUP_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269_fixup_headset_mic, + .chained = true, + .chain_id = ALC668_FIXUP_MIC_DET_COEF + }, + [ALC668_FIXUP_MIC_DET_COEF] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x20, AC_VERB_SET_COEF_INDEX, 0x15 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0d60 }, + {} + }, + }, }; static const struct snd_pci_quirk alc662_fixup_tbl[] = { @@ -10584,6 +10641,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x15a7, "ASUS UX51VZH", ALC662_FIXUP_BASS_16), SND_PCI_QUIRK(0x1043, 0x177d, "ASUS N551", ALC668_FIXUP_ASUS_Nx51), SND_PCI_QUIRK(0x1043, 0x17bd, "ASUS N751", ALC668_FIXUP_ASUS_Nx51), + SND_PCI_QUIRK(0x1043, 0x185d, "ASUS G551JW", ALC668_FIXUP_ASUS_NO_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1963, "ASUS X71SL", ALC662_FIXUP_ASUS_MODE8), SND_PCI_QUIRK(0x1043, 0x1b73, "ASUS N55SF", ALC662_FIXUP_BASS_16), SND_PCI_QUIRK(0x1043, 0x1bf3, "ASUS N76VZ", ALC662_FIXUP_BASS_MODE4_CHMAP), diff --git a/sound/usb/mixer_scarlett_gen2.c b/sound/usb/mixer_scarlett_gen2.c index 3d5848d5481b..53ebabf42472 100644 --- a/sound/usb/mixer_scarlett_gen2.c +++ b/sound/usb/mixer_scarlett_gen2.c @@ -2450,6 +2450,8 @@ static int scarlett2_update_monitor_other(struct usb_mixer_interface *mixer) err = scarlett2_usb_get_config(mixer, SCARLETT2_CONFIG_TALKBACK_MAP, 1, &bitmap); + if (err < 0) + return err; for (i = 0; i < num_mixes; i++, bitmap >>= 1) private->talkback_map[i] = bitmap & 1; } diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index e03043f7dad3..de18fff69280 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -78,6 +78,48 @@ { USB_DEVICE_VENDOR_SPEC(0x041e, 0x3f19) }, /* + * Creative Technology, Ltd Live! Cam Sync HD [VF0770] + * The device advertises 8 formats, but only a rate of 48kHz is honored by the + * hardware and 24 bits give chopped audio, so only report the one working + * combination. + */ +{ + USB_DEVICE(0x041e, 0x4095), + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = &(const struct snd_usb_audio_quirk[]) { + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_MIXER, + }, + { + .ifnum = 3, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S16_LE, + .channels = 2, + .fmt_bits = 16, + .iface = 3, + .altsetting = 4, + .altset_idx = 4, + .endpoint = 0x82, + .ep_attr = 0x05, + .rates = SNDRV_PCM_RATE_48000, + .rate_min = 48000, + .rate_max = 48000, + .nr_rates = 1, + .rate_table = (unsigned int[]) { 48000 }, + }, + }, + { + .ifnum = -1 + }, + }, + }, +}, + +/* * HP Wireless Audio * When not ignored, causes instability issues for some users, forcing them to * skip the entire module. diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 6ee6d24c847f..889c855addfc 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1900,6 +1900,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY | QUIRK_FLAG_IFACE_DELAY), VENDOR_FLG(0x07fd, /* MOTU */ QUIRK_FLAG_VALIDATE_RATES), + VENDOR_FLG(0x1235, /* Focusrite Novation */ + QUIRK_FLAG_VALIDATE_RATES), VENDOR_FLG(0x152a, /* Thesycon devices */ QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x1de7, /* Phoenix Audio */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index 1d84ec9db93b..5859ca0a1439 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -784,6 +784,7 @@ struct snd_rawmidi_status { #define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int) #define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info) +#define SNDRV_RAWMIDI_IOCTL_USER_PVERSION _IOW('W', 0x02, int) #define SNDRV_RAWMIDI_IOCTL_PARAMS _IOWR('W', 0x10, struct snd_rawmidi_params) #define SNDRV_RAWMIDI_IOCTL_STATUS _IOWR('W', 0x20, struct snd_rawmidi_status) #define SNDRV_RAWMIDI_IOCTL_DROP _IOW('W', 0x30, int) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e23f1b6b9402..8892f2f1bbcc 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7024,7 +7024,8 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) if (obj->gen_loader) { /* reset FDs */ - btf__set_fd(obj->btf, -1); + if (obj->btf) + btf__set_fd(obj->btf, -1); for (i = 0; i < obj->nr_maps; i++) obj->maps[i].fd = -1; if (!err) diff --git a/tools/lib/bpf/strset.c b/tools/lib/bpf/strset.c index 1fb8b49de1d6..ea655318153f 100644 --- a/tools/lib/bpf/strset.c +++ b/tools/lib/bpf/strset.c @@ -88,6 +88,7 @@ void strset__free(struct strset *set) hashmap__free(set->strs_hash); free(set->strs_data); + free(set); } size_t strset__data_size(const struct strset *set) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index bc821056aba9..0893436cc09f 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -684,7 +684,7 @@ static int elf_add_alternative(struct elf *elf, sec = find_section_by_name(elf, ".altinstructions"); if (!sec) { sec = elf_create_section(elf, ".altinstructions", - SHF_ALLOC, size, 0); + SHF_ALLOC, 0, 0); if (!sec) { WARN_ELF("elf_create_section"); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index e5947fbb9e7a..06b5c164ae93 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -292,7 +292,7 @@ static int decode_instructions(struct objtool_file *file) !strcmp(sec->name, ".entry.text")) sec->noinstr = true; - for (offset = 0; offset < sec->len; offset += insn->len) { + for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) { insn = malloc(sizeof(*insn)); if (!insn) { WARN("malloc failed"); @@ -307,7 +307,7 @@ static int decode_instructions(struct objtool_file *file) insn->offset = offset; ret = arch_decode_instruction(file->elf, sec, offset, - sec->len - offset, + sec->sh.sh_size - offset, &insn->len, &insn->type, &insn->immediate, &insn->stack_ops); @@ -349,9 +349,9 @@ static struct instruction *find_last_insn(struct objtool_file *file, { struct instruction *insn = NULL; unsigned int offset; - unsigned int end = (sec->len > 10) ? sec->len - 10 : 0; + unsigned int end = (sec->sh.sh_size > 10) ? sec->sh.sh_size - 10 : 0; - for (offset = sec->len - 1; offset >= end && !insn; offset--) + for (offset = sec->sh.sh_size - 1; offset >= end && !insn; offset--) insn = find_insn(file, sec, offset); return insn; @@ -389,7 +389,7 @@ static int add_dead_ends(struct objtool_file *file) insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (reloc->addend == reloc->sym->sec->len) { + else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find unreachable insn at %s+0x%x", @@ -424,7 +424,7 @@ reachable: insn = find_insn(file, reloc->sym->sec, reloc->addend); if (insn) insn = list_prev_entry(insn, list); - else if (reloc->addend == reloc->sym->sec->len) { + else if (reloc->addend == reloc->sym->sec->sh.sh_size) { insn = find_last_insn(file, reloc->sym->sec); if (!insn) { WARN("can't find reachable insn at %s+0x%x", @@ -1561,14 +1561,14 @@ static int read_unwind_hints(struct objtool_file *file) return -1; } - if (sec->len % sizeof(struct unwind_hint)) { + if (sec->sh.sh_size % sizeof(struct unwind_hint)) { WARN("struct unwind_hint size mismatch"); return -1; } file->hints = true; - for (i = 0; i < sec->len / sizeof(struct unwind_hint); i++) { + for (i = 0; i < sec->sh.sh_size / sizeof(struct unwind_hint); i++) { hint = (struct unwind_hint *)sec->data->d_buf + i; reloc = find_reloc_by_dest(file->elf, sec, i * sizeof(*hint)); diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 8676c7598728..b18f0055b50b 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -286,10 +286,9 @@ static int read_sections(struct elf *elf) return -1; } } - sec->len = sec->sh.sh_size; if (sec->sh.sh_flags & SHF_EXECINSTR) - elf->text_size += sec->len; + elf->text_size += sec->sh.sh_size; list_add_tail(&sec->list, &elf->sections); elf_hash_add(section, &sec->hash, sec->idx); @@ -734,8 +733,8 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) data->d_size = strlen(str) + 1; data->d_align = 1; - len = strtab->len; - strtab->len += data->d_size; + len = strtab->sh.sh_size; + strtab->sh.sh_size += data->d_size; strtab->changed = true; return len; @@ -790,9 +789,9 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) data->d_align = 1; data->d_type = ELF_T_SYM; - sym->idx = symtab->len / sizeof(sym->sym); + sym->idx = symtab->sh.sh_size / sizeof(sym->sym); - symtab->len += data->d_size; + symtab->sh.sh_size += data->d_size; symtab->changed = true; symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); @@ -814,7 +813,7 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) data->d_align = 4; data->d_type = ELF_T_WORD; - symtab_shndx->len += 4; + symtab_shndx->sh.sh_size += 4; symtab_shndx->changed = true; } @@ -855,7 +854,6 @@ struct section *elf_create_section(struct elf *elf, const char *name, } sec->idx = elf_ndxscn(s); - sec->len = size; sec->changed = true; sec->data = elf_newdata(s); diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index e34395047530..075d8291b854 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -38,7 +38,6 @@ struct section { Elf_Data *data; char *name; int idx; - unsigned int len; bool changed, text, rodata, noinstr; }; diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index dc9b7dd314b0..b5865e2450cb 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -204,7 +204,7 @@ int orc_create(struct objtool_file *file) /* Add a section terminator */ if (!empty) { - orc_list_add(&orc_list, &null, sec, sec->len); + orc_list_add(&orc_list, &null, sec, sec->sh.sh_size); nr++; } } diff --git a/tools/objtool/special.c b/tools/objtool/special.c index bc925cf19e2d..06c3eacab3d5 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -58,6 +58,13 @@ void __weak arch_handle_alternative(unsigned short feature, struct special_alt * { } +static void reloc_to_sec_off(struct reloc *reloc, struct section **sec, + unsigned long *off) +{ + *sec = reloc->sym->sec; + *off = reloc->sym->offset + reloc->addend; +} + static int get_alt_entry(struct elf *elf, struct special_entry *entry, struct section *sec, int idx, struct special_alt *alt) @@ -91,14 +98,8 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); return -1; } - if (orig_reloc->sym->type != STT_SECTION) { - WARN_FUNC("don't know how to handle non-section reloc symbol %s", - sec, offset + entry->orig, orig_reloc->sym->name); - return -1; - } - alt->orig_sec = orig_reloc->sym->sec; - alt->orig_off = orig_reloc->addend; + reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off); if (!entry->group || alt->new_len) { new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); @@ -116,8 +117,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, if (arch_is_retpoline(new_reloc->sym)) return 1; - alt->new_sec = new_reloc->sym->sec; - alt->new_off = (unsigned int)new_reloc->addend; + reloc_to_sec_off(new_reloc, &alt->new_sec, &alt->new_off); /* _ASM_EXTABLE_EX hack */ if (alt->new_off >= 0x7ffffff0) @@ -159,13 +159,13 @@ int special_get_alts(struct elf *elf, struct list_head *alts) if (!sec) continue; - if (sec->len % entry->size != 0) { + if (sec->sh.sh_size % entry->size != 0) { WARN("%s size not a multiple of %d", sec->name, entry->size); return -1; } - nr_entries = sec->len / entry->size; + nr_entries = sec->sh.sh_size / entry->size; for (idx = 0; idx < nr_entries; idx++) { alt = malloc(sizeof(*alt)); diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 446180401e26..14e3e8d702a0 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -143,7 +143,7 @@ FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto ifdef CSINCLUDES LIBOPENCSD_CFLAGS := -I$(CSINCLUDES) endif -OPENCSDLIBS := -lopencsd_c_api -lopencsd +OPENCSDLIBS := -lopencsd_c_api -lopencsd -lstdc++ ifdef CSLIBS LIBOPENCSD_LDFLAGS := -L$(CSLIBS) endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index e04313c4d840..5cd702062a04 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -802,7 +802,7 @@ endif $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h) -LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(LDFLAGS)' +LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ) 'EXTRA_CFLAGS=$(EXTRA_CFLAGS)' 'LDFLAGS=$(filter-out -static,$(LDFLAGS))' $(LIBTRACEEVENT): FORCE $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index 6731b3cf0c2f..7c887d37b893 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -1285,6 +1285,7 @@ int main(int argc, char *argv[]) } free_arch_std_events(); + free_sys_event_tables(); free(mapfile); return 0; @@ -1306,6 +1307,7 @@ err_close_eventsfp: create_empty_mapping(output_file); err_out: free_arch_std_events(); + free_sys_event_tables(); free(mapfile); return ret; } diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index d9e99b3f77e6..d8ea6a88163f 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -68,3 +68,100 @@ fd=10 type=0 config=5 optional=1 + +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index 8b04a055d154..b656ab93c5bf 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 4fca9f1bfbf8..97625090a1c4 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 @@ -114,8 +211,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event15:base-stat] -fd=15 +[event24:base-stat] +fd=24 type=3 config=1 optional=1 @@ -124,8 +221,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event16:base-stat] -fd=16 +[event25:base-stat] +fd=25 type=3 config=65537 optional=1 @@ -134,8 +231,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event17:base-stat] -fd=17 +[event26:base-stat] +fd=26 type=3 config=3 optional=1 @@ -144,8 +241,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event18:base-stat] -fd=18 +[event27:base-stat] +fd=27 type=3 config=65539 optional=1 @@ -154,8 +251,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event19:base-stat] -fd=19 +[event28:base-stat] +fd=28 type=3 config=4 optional=1 @@ -164,8 +261,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event20:base-stat] -fd=20 +[event29:base-stat] +fd=29 type=3 config=65540 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index 4bb58e1c82a6..d555042e3fbf 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -70,12 +70,109 @@ type=0 config=5 optional=1 +# PERF_TYPE_RAW / slots (0x400) +[event11:base-stat] +fd=11 +group_fd=-1 +type=4 +config=1024 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-retiring (0x8000) +[event12:base-stat] +fd=12 +group_fd=11 +type=4 +config=32768 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +[event13:base-stat] +fd=13 +group_fd=11 +type=4 +config=33024 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +[event14:base-stat] +fd=14 +group_fd=11 +type=4 +config=33280 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-be-bound (0x8300) +[event15:base-stat] +fd=15 +group_fd=11 +type=4 +config=33536 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +[event16:base-stat] +fd=16 +group_fd=11 +type=4 +config=33792 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +[event17:base-stat] +fd=17 +group_fd=11 +type=4 +config=34048 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +[event18:base-stat] +fd=18 +group_fd=11 +type=4 +config=34304 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + +# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +[event19:base-stat] +fd=19 +group_fd=11 +type=4 +config=34560 +disabled=0 +enable_on_exec=0 +read_format=15 +optional=1 + # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event11:base-stat] -fd=11 +[event20:base-stat] +fd=20 type=3 config=0 optional=1 @@ -84,8 +181,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event12:base-stat] -fd=12 +[event21:base-stat] +fd=21 type=3 config=65536 optional=1 @@ -94,8 +191,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event13:base-stat] -fd=13 +[event22:base-stat] +fd=22 type=3 config=2 optional=1 @@ -104,8 +201,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event14:base-stat] -fd=14 +[event23:base-stat] +fd=23 type=3 config=65538 optional=1 @@ -114,8 +211,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event15:base-stat] -fd=15 +[event24:base-stat] +fd=24 type=3 config=1 optional=1 @@ -124,8 +221,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event16:base-stat] -fd=16 +[event25:base-stat] +fd=25 type=3 config=65537 optional=1 @@ -134,8 +231,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event17:base-stat] -fd=17 +[event26:base-stat] +fd=26 type=3 config=3 optional=1 @@ -144,8 +241,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event18:base-stat] -fd=18 +[event27:base-stat] +fd=27 type=3 config=65539 optional=1 @@ -154,8 +251,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event19:base-stat] -fd=19 +[event28:base-stat] +fd=28 type=3 config=4 optional=1 @@ -164,8 +261,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event20:base-stat] -fd=20 +[event29:base-stat] +fd=29 type=3 config=65540 optional=1 @@ -174,8 +271,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event21:base-stat] -fd=21 +[event30:base-stat] +fd=30 type=3 config=512 optional=1 @@ -184,8 +281,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event22:base-stat] -fd=22 +[event31:base-stat] +fd=31 type=3 config=66048 optional=1 diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 5a931456e718..ac35c61f65f5 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -16,7 +16,7 @@ assert sys.version_info >= (3, 7), "Python version is too old" from collections import namedtuple from enum import Enum, auto -from typing import Iterable +from typing import Iterable, Sequence import kunit_config import kunit_json @@ -186,6 +186,26 @@ def run_tests(linux: kunit_kernel.LinuxSourceTree, exec_result.elapsed_time)) return parse_result +# Problem: +# $ kunit.py run --json +# works as one would expect and prints the parsed test results as JSON. +# $ kunit.py run --json suite_name +# would *not* pass suite_name as the filter_glob and print as json. +# argparse will consider it to be another way of writing +# $ kunit.py run --json=suite_name +# i.e. it would run all tests, and dump the json to a `suite_name` file. +# So we hackily automatically rewrite --json => --json=stdout +pseudo_bool_flag_defaults = { + '--json': 'stdout', + '--raw_output': 'kunit', +} +def massage_argv(argv: Sequence[str]) -> Sequence[str]: + def massage_arg(arg: str) -> str: + if arg not in pseudo_bool_flag_defaults: + return arg + return f'{arg}={pseudo_bool_flag_defaults[arg]}' + return list(map(massage_arg, argv)) + def add_common_opts(parser) -> None: parser.add_argument('--build_dir', help='As in the make command, it specifies the build ' @@ -303,7 +323,7 @@ def main(argv, linux=None): help='Specifies the file to read results from.', type=str, nargs='?', metavar='input_file') - cli_args = parser.parse_args(argv) + cli_args = parser.parse_args(massage_argv(argv)) if get_kernel_root_path(): os.chdir(get_kernel_root_path()) diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 619c4554cbff..1edcc8373b4e 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -408,6 +408,14 @@ class KUnitMainTest(unittest.TestCase): self.assertNotEqual(call, mock.call(StrContains('Testing complete.'))) self.assertNotEqual(call, mock.call(StrContains(' 0 tests run'))) + def test_run_raw_output_does_not_take_positional_args(self): + # --raw_output is a string flag, but we don't want it to consume + # any positional arguments, only ones after an '=' + self.linux_source_mock.run_kernel = mock.Mock(return_value=[]) + kunit.main(['run', '--raw_output', 'filter_glob'], self.linux_source_mock) + self.linux_source_mock.run_kernel.assert_called_once_with( + args=None, build_dir='.kunit', filter_glob='filter_glob', timeout=300) + def test_exec_timeout(self): timeout = 3453 kunit.main(['exec', '--timeout', str(timeout)], self.linux_source_mock) diff --git a/tools/testing/selftests/drivers/dma-buf/udmabuf.c b/tools/testing/selftests/drivers/dma-buf/udmabuf.c index 4de902ea14d8..de1c4e6de0b2 100644 --- a/tools/testing/selftests/drivers/dma-buf/udmabuf.c +++ b/tools/testing/selftests/drivers/dma-buf/udmabuf.c @@ -1,10 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + #include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <string.h> #include <errno.h> -#include <linux/fcntl.h> +#include <fcntl.h> #include <malloc.h> #include <sys/ioctl.h> diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh index 8817851da7a9..e9a82cae8c9a 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh @@ -13,7 +13,7 @@ # | # +-------------------|-----+ # | SW1 | | -# | $swp1 + | +# | $swp1 + | # | 192.0.2.2/28 | # | | # | + g1a (gre) | @@ -27,8 +27,8 @@ # | # +--|----------------------+ # | | VRF2 | -# | + $rp2 | -# | 198.51.100.2/28 | +# | + $rp2 | +# | 198.51.100.2/28 | # +-------------------------+ lib_dir=$(dirname $0)/../../../net/forwarding @@ -116,12 +116,16 @@ cleanup() forwarding_restore } -ecn_payload_get() +ipip_payload_get() { + local flags=$1; shift + local key=$1; shift + p=$(: - )"0"$( : GRE flags + )"$flags"$( : GRE flags )"0:00:"$( : Reserved + version )"08:00:"$( : ETH protocol type + )"$key"$( : Key )"4"$( : IP version )"5:"$( : IHL )"00:"$( : IP TOS @@ -137,6 +141,11 @@ ecn_payload_get() echo $p } +ecn_payload_get() +{ + echo $(ipip_payload_get "0") +} + ecn_decap_test() { local trap_name="decap_error" @@ -171,31 +180,6 @@ ecn_decap_test() tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } -ipip_payload_get() -{ - local flags=$1; shift - local key=$1; shift - - p=$(: - )"$flags"$( : GRE flags - )"0:00:"$( : Reserved + version - )"08:00:"$( : ETH protocol type - )"$key"$( : Key - )"4"$( : IP version - )"5:"$( : IHL - )"00:"$( : IP TOS - )"00:14:"$( : IP total length - )"00:00:"$( : IP identification - )"20:00:"$( : IP flags + frag off - )"30:"$( : IP TTL - )"01:"$( : IP proto - )"E7:E6:"$( : IP header csum - )"C0:00:01:01:"$( : IP saddr : 192.0.1.1 - )"C0:00:02:01:"$( : IP daddr : 192.0.2.1 - ) - echo $p -} - no_matching_tunnel_test() { local trap_name="decap_error" @@ -239,7 +223,8 @@ decap_error_test() no_matching_tunnel_test "Decap error: Source IP check failed" \ 192.0.2.68 "0" no_matching_tunnel_test \ - "Decap error: Key exists but was not expected" $sip "2" ":E9:" + "Decap error: Key exists but was not expected" $sip "2" \ + "00:00:00:E9:" # Destroy the tunnel and create new one with key __addr_add_del g1 del 192.0.2.65/32 @@ -251,7 +236,8 @@ decap_error_test() no_matching_tunnel_test \ "Decap error: Key does not exist but was expected" $sip "0" no_matching_tunnel_test \ - "Decap error: Packet has a wrong key field" $sip "2" "E8:" + "Decap error: Packet has a wrong key field" $sip "2" \ + "00:00:00:E8:" } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh index 33ddd01689be..dd90cd87d4f9 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -331,6 +331,14 @@ get_nmarked() ethtool_stats_get $swp3 ecn_marked } +get_qdisc_nmarked() +{ + local vlan=$1; shift + + busywait_for_counter 1100 +1 \ + qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .marked +} + get_qdisc_npackets() { local vlan=$1; shift @@ -384,14 +392,15 @@ build_backlog() check_marking() { + local get_nmarked=$1; shift local vlan=$1; shift local cond=$1; shift local npackets_0=$(get_qdisc_npackets $vlan) - local nmarked_0=$(get_nmarked $vlan) + local nmarked_0=$($get_nmarked $vlan) sleep 5 local npackets_1=$(get_qdisc_npackets $vlan) - local nmarked_1=$(get_nmarked $vlan) + local nmarked_1=$($get_nmarked $vlan) local nmarked_d=$((nmarked_1 - nmarked_0)) local npackets_d=$((npackets_1 - npackets_0)) @@ -404,6 +413,7 @@ check_marking() ecn_test_common() { local name=$1; shift + local get_nmarked=$1; shift local vlan=$1; shift local limit=$1; shift local backlog @@ -416,7 +426,7 @@ ecn_test_common() RET=0 backlog=$(build_backlog $vlan $((2 * limit / 3)) udp) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking "$get_nmarked" $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." log_test "TC $((vlan - 10)): $name backlog < limit" @@ -426,22 +436,23 @@ ecn_test_common() RET=0 backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan ">= 95") + pct=$(check_marking "$get_nmarked" $vlan ">= 95") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95." log_test "TC $((vlan - 10)): $name backlog > limit" } -do_ecn_test() +__do_ecn_test() { + local get_nmarked=$1; shift local vlan=$1; shift local limit=$1; shift - local name=ECN + local name=${1-ECN}; shift start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ $h3_mac tos=0x01 sleep 1 - ecn_test_common "$name" $vlan $limit + ecn_test_common "$name" "$get_nmarked" $vlan $limit # Up there we saw that UDP gets accepted when backlog is below the # limit. Now that it is above, it should all get dropped, and backlog @@ -455,6 +466,26 @@ do_ecn_test() sleep 1 } +do_ecn_test() +{ + local vlan=$1; shift + local limit=$1; shift + + __do_ecn_test get_nmarked "$vlan" "$limit" +} + +do_ecn_test_perband() +{ + local vlan=$1; shift + local limit=$1; shift + + # Per-band ECN counters are not supported on Spectrum-1 and Spectrum-2. + [[ "$DEVLINK_VIDDID" == "15b3:cb84" || + "$DEVLINK_VIDDID" == "15b3:cf6c" ]] && return + + __do_ecn_test get_qdisc_nmarked "$vlan" "$limit" "per-band ECN" +} + do_ecn_nodrop_test() { local vlan=$1; shift @@ -465,7 +496,7 @@ do_ecn_nodrop_test() $h3_mac tos=0x01 sleep 1 - ecn_test_common "$name" $vlan $limit + ecn_test_common "$name" get_nmarked $vlan $limit # Up there we saw that UDP gets accepted when backlog is below the # limit. Now that it is above, in nodrop mode, make sure it goes to @@ -495,7 +526,7 @@ do_red_test() RET=0 backlog=$(build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking get_nmarked $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." log_test "TC $((vlan - 10)): RED backlog < limit" @@ -503,7 +534,7 @@ do_red_test() RET=0 backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) check_fail $? "Traffic went into backlog instead of being early-dropped" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking get_nmarked $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." local diff=$((limit - backlog)) pct=$((100 * diff / limit)) @@ -544,6 +575,53 @@ do_mc_backlog_test() log_test "TC $((vlan - 10)): Qdisc reports MC backlog" } +do_mark_test() +{ + local vlan=$1; shift + local limit=$1; shift + local subtest=$1; shift + local fetch_counter=$1; shift + local should_fail=$1; shift + local base + + RET=0 + + start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ + $h3_mac tos=0x01 + + # Create a bit of a backlog and observe no mirroring due to marks. + qevent_rule_install_$subtest + + build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01 >/dev/null + + base=$($fetch_counter) + count=$(busywait 1100 until_counter_is ">= $((base + 1))" \ + $fetch_counter) + check_fail $? "Spurious packets ($base -> $count) observed without buffer pressure" + + # Above limit, everything should be mirrored, we should see lots of + # packets. + build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01 >/dev/null + busywait_for_counter 1100 +10000 \ + $fetch_counter > /dev/null + check_err_fail "$should_fail" $? "ECN-marked packets $subtest'd" + + # When the rule is uninstalled, there should be no mirroring. + qevent_rule_uninstall_$subtest + busywait_for_counter 1100 +10 \ + $fetch_counter > /dev/null + check_fail $? "Spurious packets observed after uninstall" + + if ((should_fail)); then + log_test "TC $((vlan - 10)): marked packets not $subtest'd" + else + log_test "TC $((vlan - 10)): marked packets $subtest'd" + fi + + stop_traffic + sleep 1 +} + do_drop_test() { local vlan=$1; shift @@ -551,10 +629,8 @@ do_drop_test() local trigger=$1; shift local subtest=$1; shift local fetch_counter=$1; shift - local backlog local base local now - local pct RET=0 @@ -628,6 +704,22 @@ do_drop_mirror_test() tc filter del dev $h2 ingress pref 1 handle 101 flower } +do_mark_mirror_test() +{ + local vlan=$1; shift + local limit=$1; shift + + tc filter add dev $h2 ingress pref 1 handle 101 prot ip \ + flower skip_sw ip_proto tcp \ + action drop + + do_mark_test "$vlan" "$limit" mirror \ + qevent_counter_fetch_mirror \ + $(: should_fail=)0 + + tc filter del dev $h2 ingress pref 1 handle 101 flower +} + qevent_rule_install_trap() { tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ @@ -655,3 +747,14 @@ do_drop_trap_test() do_drop_test "$vlan" "$limit" "$trap_name" trap \ "qevent_counter_fetch_trap $trap_name" } + +qevent_rule_install_trap_fwd() +{ + tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ + action trap_fwd hw_stats disabled +} + +qevent_rule_uninstall_trap_fwd() +{ + tc filter del block 10 pref 1234 handle 102 matchall +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh index f3ef3274f9b3..1e5ad3209436 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -4,11 +4,13 @@ ALL_TESTS=" ping_ipv4 ecn_test + ecn_test_perband ecn_nodrop_test red_test mc_backlog_test red_mirror_test red_trap_test + ecn_mirror_test " : ${QDISC:=ets} source sch_red_core.sh @@ -21,28 +23,60 @@ source sch_red_core.sh BACKLOG1=200000 BACKLOG2=500000 -install_qdisc() +install_root_qdisc() { - local -a args=("$@") - tc qdisc add dev $swp3 root handle 10: $QDISC \ bands 8 priomap 7 6 5 4 3 2 1 0 +} + +install_qdisc_tc0() +{ + local -a args=("$@") + tc qdisc add dev $swp3 parent 10:8 handle 108: red \ limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \ probability 1.0 avpkt 8000 burst 38 "${args[@]}" +} + +install_qdisc_tc1() +{ + local -a args=("$@") + tc qdisc add dev $swp3 parent 10:7 handle 107: red \ limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \ probability 1.0 avpkt 8000 burst 63 "${args[@]}" +} + +install_qdisc() +{ + install_root_qdisc + install_qdisc_tc0 "$@" + install_qdisc_tc1 "$@" sleep 1 } -uninstall_qdisc() +uninstall_qdisc_tc0() { - tc qdisc del dev $swp3 parent 10:7 tc qdisc del dev $swp3 parent 10:8 +} + +uninstall_qdisc_tc1() +{ + tc qdisc del dev $swp3 parent 10:7 +} + +uninstall_root_qdisc() +{ tc qdisc del dev $swp3 root } +uninstall_qdisc() +{ + uninstall_qdisc_tc0 + uninstall_qdisc_tc1 + uninstall_root_qdisc +} + ecn_test() { install_qdisc ecn @@ -53,6 +87,16 @@ ecn_test() uninstall_qdisc } +ecn_test_perband() +{ + install_qdisc ecn + + do_ecn_test_perband 10 $BACKLOG1 + do_ecn_test_perband 11 $BACKLOG2 + + uninstall_qdisc +} + ecn_nodrop_test() { install_qdisc ecn nodrop @@ -112,6 +156,16 @@ red_trap_test() uninstall_qdisc } +ecn_mirror_test() +{ + install_qdisc ecn qevent mark block 10 + + do_mark_mirror_test 10 $BACKLOG1 + do_mark_mirror_test 11 $BACKLOG2 + + uninstall_qdisc +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh index ede9c38d3eff..d79a82f317d2 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh @@ -4,6 +4,7 @@ ALL_TESTS=" ping_ipv4 ecn_test + ecn_test_perband ecn_nodrop_test red_test mc_backlog_test @@ -35,6 +36,13 @@ ecn_test() uninstall_qdisc } +ecn_test_perband() +{ + install_qdisc ecn + do_ecn_test_perband 10 $BACKLOG + uninstall_qdisc +} + ecn_nodrop_test() { install_qdisc ecn nodrop diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh new file mode 100755 index 000000000000..f62ce479c266 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh @@ -0,0 +1,250 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap tunnel exceptions functionality over mlxsw. +# Check all exception traps to make sure they are triggered under the right +# conditions. + +# +-------------------------+ +# | H1 | +# | $h1 + | +# | 2001:db8:1::1/64 | | +# +-------------------|-----+ +# | +# +-------------------|-----+ +# | SW1 | | +# | $swp1 + | +# | 2001:db8:1::2/64 | +# | | +# | + g1 (ip6gre) | +# | loc=2001:db8:3::1 | +# | rem=2001:db8:3::2 | +# | tos=inherit | +# | | +# | + $rp1 | +# | | 2001:db8:10::1/64 | +# +--|----------------------+ +# | +# +--|----------------------+ +# | | VRF2 | +# | + $rp2 | +# | 2001:db8:10::2/64 | +# +-------------------------+ + +lib_dir=$(dirname $0)/../../../../net/forwarding + +ALL_TESTS=" + decap_error_test +" + +NUM_NETIFS=4 +source $lib_dir/lib.sh +source $lib_dir/tc_common.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 2001:db8:1::1/64 +} + +vrf2_create() +{ + simple_if_init $rp2 2001:db8:10::2/64 +} + +vrf2_destroy() +{ + simple_if_fini $rp2 2001:db8:10::2/64 +} + +switch_create() +{ + ip link set dev $swp1 up + __addr_add_del $swp1 add 2001:db8:1::2/64 + tc qdisc add dev $swp1 clsact + + tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit + ip link set dev g1 up + __addr_add_del g1 add 2001:db8:3::1/128 + + ip link set dev $rp1 up + __addr_add_del $rp1 add 2001:db8:10::1/64 +} + +switch_destroy() +{ + __addr_add_del $rp1 del 2001:db8:10::1/64 + ip link set dev $rp1 down + + __addr_add_del g1 del 2001:db8:3::1/128 + ip link set dev g1 down + tunnel_destroy g1 + + tc qdisc del dev $swp1 clsact + __addr_add_del $swp1 del 2001:db8:1::2/64 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + forwarding_enable + vrf_prepare + h1_create + switch_create + vrf2_create +} + +cleanup() +{ + pre_cleanup + + vrf2_destroy + switch_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +ipip_payload_get() +{ + local saddr="20:01:0d:b8:00:02:00:00:00:00:00:00:00:00:00:01" + local daddr="20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01" + local flags=$1; shift + local key=$1; shift + + p=$(: + )"$flags"$( : GRE flags + )"0:00:"$( : Reserved + version + )"86:dd:"$( : ETH protocol type + )"$key"$( : Key + )"6"$( : IP version + )"0:0"$( : Traffic class + )"0:00:00:"$( : Flow label + )"00:00:"$( : Payload length + )"3a:"$( : Next header + )"04:"$( : Hop limit + )"$saddr:"$( : IP saddr + )"$daddr:"$( : IP daddr + ) + echo $p +} + +ecn_payload_get() +{ + echo $(ipip_payload_get "0") +} + +ecn_decap_test() +{ + local trap_name="decap_error" + local desc=$1; shift + local ecn_desc=$1; shift + local outer_tos=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ipv6 pref 1 handle 101 \ + flower src_ip 2001:db8:2::1 dst_ip 2001:db8:1::1 skip_sw \ + action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ecn_payload_get) + + ip vrf exec v$rp2 $MZ -6 $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A 2001:db8:3::2 -B 2001:db8:3::1 -t ip \ + tos=$outer_tos,next=47,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower +} + +no_matching_tunnel_test() +{ + local trap_name="decap_error" + local desc=$1; shift + local sip=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ipv6 pref 1 handle 101 \ + flower src_ip 2001:db8:2::1 dst_ip 2001:db8:1::1 action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ipip_payload_get "$@") + + ip vrf exec v$rp2 $MZ -6 $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A $sip -B 2001:db8:3::1 -t ip next=47,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower +} + +decap_error_test() +{ + # Correct source IP - the remote address + local sip=2001:db8:3::2 + + ecn_decap_test "Decap error" "ECT(1)" 01 + ecn_decap_test "Decap error" "ECT(0)" 02 + ecn_decap_test "Decap error" "CE" 03 + + no_matching_tunnel_test "Decap error: Source IP check failed" \ + 2001:db8:4::2 "0" + no_matching_tunnel_test \ + "Decap error: Key exists but was not expected" $sip "2" \ + "00:00:00:E9:" + + # Destroy the tunnel and create new one with key + __addr_add_del g1 del 2001:db8:3::1/128 + tunnel_destroy g1 + + tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit key 233 + __addr_add_del g1 add 2001:db8:3::1/128 + + no_matching_tunnel_test \ + "Decap error: Key does not exist but was expected" $sip "0" + no_matching_tunnel_test \ + "Decap error: Packet has a wrong key field" $sip "2" \ + "00:00:00:E8:" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index eba8bd08293e..05e65ca1c30c 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -315,7 +315,7 @@ static inline void set_xmm(int n, unsigned long val) #define GET_XMM(__xmm) \ ({ \ unsigned long __val; \ - asm volatile("movq %%"#__xmm", %0" : "=r"(__val) : : #__xmm); \ + asm volatile("movq %%"#__xmm", %0" : "=r"(__val)); \ __val; \ }) diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index c5e0dd664a7b..4158da0da2bb 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -10,6 +10,7 @@ #include <signal.h> #include <syscall.h> #include <sys/ioctl.h> +#include <sys/sysinfo.h> #include <asm/barrier.h> #include <linux/atomic.h> #include <linux/rseq.h> @@ -39,6 +40,7 @@ static __thread volatile struct rseq __rseq = { static pthread_t migration_thread; static cpu_set_t possible_mask; +static int min_cpu, max_cpu; static bool done; static atomic_t seq_cnt; @@ -57,20 +59,37 @@ static void sys_rseq(int flags) TEST_ASSERT(!r, "rseq failed, errno = %d (%s)", errno, strerror(errno)); } +static int next_cpu(int cpu) +{ + /* + * Advance to the next CPU, skipping those that weren't in the original + * affinity set. Sadly, there is no CPU_SET_FOR_EACH, and cpu_set_t's + * data storage is considered as opaque. Note, if this task is pinned + * to a small set of discontigous CPUs, e.g. 2 and 1023, this loop will + * burn a lot cycles and the test will take longer than normal to + * complete. + */ + do { + cpu++; + if (cpu > max_cpu) { + cpu = min_cpu; + TEST_ASSERT(CPU_ISSET(cpu, &possible_mask), + "Min CPU = %d must always be usable", cpu); + break; + } + } while (!CPU_ISSET(cpu, &possible_mask)); + + return cpu; +} + static void *migration_worker(void *ign) { cpu_set_t allowed_mask; - int r, i, nr_cpus, cpu; + int r, i, cpu; CPU_ZERO(&allowed_mask); - nr_cpus = CPU_COUNT(&possible_mask); - - for (i = 0; i < NR_TASK_MIGRATIONS; i++) { - cpu = i % nr_cpus; - if (!CPU_ISSET(cpu, &possible_mask)) - continue; - + for (i = 0, cpu = min_cpu; i < NR_TASK_MIGRATIONS; i++, cpu = next_cpu(cpu)) { CPU_SET(cpu, &allowed_mask); /* @@ -154,6 +173,36 @@ static void *migration_worker(void *ign) return NULL; } +static int calc_min_max_cpu(void) +{ + int i, cnt, nproc; + + if (CPU_COUNT(&possible_mask) < 2) + return -EINVAL; + + /* + * CPU_SET doesn't provide a FOR_EACH helper, get the min/max CPU that + * this task is affined to in order to reduce the time spent querying + * unusable CPUs, e.g. if this task is pinned to a small percentage of + * total CPUs. + */ + nproc = get_nprocs_conf(); + min_cpu = -1; + max_cpu = -1; + cnt = 0; + + for (i = 0; i < nproc; i++) { + if (!CPU_ISSET(i, &possible_mask)) + continue; + if (min_cpu == -1) + min_cpu = i; + max_cpu = i; + cnt++; + } + + return (cnt < 2) ? -EINVAL : 0; +} + int main(int argc, char *argv[]) { int r, i, snapshot; @@ -167,8 +216,8 @@ int main(int argc, char *argv[]) TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno, strerror(errno)); - if (CPU_COUNT(&possible_mask) < 2) { - print_skip("Only one CPU, task migration not possible\n"); + if (calc_min_max_cpu()) { + print_skip("Only one usable CPU, task migration not possible"); exit(KSFT_SKIP); } diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index b802c14d2950..10ce3720aa6f 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -39,3 +39,6 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# Flag for tc match, supposed to be skip_sw/skip_hw which means do not process +# filter by software/hardware +TC_FLAG=skip_hw diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh new file mode 100755 index 000000000000..96c97064f2d3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel without key. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 + sw2_flat_create $ol2 $ul2 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6" +} + +gre_mtu_change() +{ + test_mtu_change +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh new file mode 100755 index 000000000000..ff9fb0db9bd1 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel with key. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 key 233 + sw2_flat_create $ol2 $ul2 key 233 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key" +} + +gre_mtu_change() +{ + test_mtu_change +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh new file mode 100755 index 000000000000..12c138785242 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel with keys. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 ikey 111 okey 222 + sw2_flat_create $ol2 $ul2 ikey 222 okey 111 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh new file mode 100755 index 000000000000..83b55c30a5c3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 + sw2_hierarchical_create $ol2 $ul2 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh new file mode 100755 index 000000000000..256607916d92 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 key 22 + sw2_hierarchical_create $ol2 $ul2 key 22 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh new file mode 100755 index 000000000000..ad1bcd6334a8 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 ikey 111 okey 222 + sw2_hierarchical_create $ol2 $ul2 ikey 222 okey 111 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh new file mode 100644 index 000000000000..58a3597037b1 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh @@ -0,0 +1,438 @@ +# SPDX-License-Identifier: GPL-2.0 +#!/bin/bash + +# Handles creation and destruction of IP-in-IP or GRE tunnels over the given +# topology. Supports both flat and hierarchical models. +# +# Flat Model: +# Overlay and underlay share the same VRF. +# SW1 uses default VRF so tunnel has no bound dev. +# SW2 uses non-default VRF tunnel has a bound dev. +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.1/24 | | +# | 2001:db8:1::1/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------+ +# | SW1 | | +# | $ol1 + | +# | 198.51.100.2/24 | +# | 2001:db8:1::2/64 | +# | | +# | + g1a (ip6gre) | +# | loc=2001:db8:3::1 | +# | rem=2001:db8:3::2 --. | +# | tos=inherit | | +# | . | +# | .--------------------- | +# | | | +# | v | +# | + $ul1.111 (vlan) | +# | | 2001:db8:10::1/64 | +# | \ | +# | \____________ | +# | | | +# | VRF default + $ul1 | +# +---------------------|-----------------------+ +# | +# +---------------------|-----------------------+ +# | SW2 | | +# | $ul2 + | +# | ___________| | +# | / | +# | / | +# | + $ul2.111 (vlan) | +# | ^ 2001:db8:10::2/64 | +# | | | +# | | | +# | '----------------------. | +# | + g2a (ip6gre) | | +# | loc=2001:db8:3::2 | | +# | rem=2001:db8:3::1 --' | +# | tos=inherit | +# | | +# | + $ol2 | +# | | 203.0.113.2/24 | +# | VRF v$ol2 | 2001:db8:2::2/64 | +# +---------------------|-----------------------+ +# +---------------------|----------+ +# | H2 | | +# | $h2 + | +# | 203.0.113.1/24 | +# | 2001:db8:2::1/64 | +# +--------------------------------+ +# +# Hierarchical model: +# The tunnel is bound to a device in a different VRF +# +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.1/24 | | +# | 2001:db8:1::1/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------+ +# | SW1 | | +# | +-----------------------|-----------------+ | +# | | $ol1 + | | +# | | 198.51.100.2/24 | | +# | | 2001:db8:1::2/64 | | +# | | | | +# | | + g1a (ip6gre) | | +# | | loc=2001:db8:3::1 | | +# | | rem=2001:db8:3::2 | | +# | | tos=inherit | | +# | | ^ | | +# | | VRF v$ol1 | | | +# | +--------------------|--------------------+ | +# | | | +# | +--------------------|--------------------+ | +# | | VRF v$ul1 | | | +# | | | | | +# | | v | | +# | | dummy1 + | | +# | | 2001:db8:3::1/64 | | +# | | .-----------' | | +# | | | | | +# | | v | | +# | | + $ul1.111 (vlan) | | +# | | | 2001:db8:10::1/64 | | +# | | \ | | +# | | \__________ | | +# | | | | | +# | | + $ul1 | | +# | +---------------------|-------------------+ | +# +-----------------------|---------------------+ +# | +# +-----------------------|---------------------+ +# | SW2 | | +# | +---------------------|-------------------+ | +# | | + $ul2 | | +# | | _____| | | +# | | / | | +# | | / | | +# | | | $ul2.111 (vlan) | | +# | | + 2001:db8:10::2/64 | | +# | | ^ | | +# | | | | | +# | | '------. | | +# | | dummy2 + | | +# | | 2001:db8:3::2/64 | | +# | | ^ | | +# | | | | | +# | | | | | +# | | VRF v$ul2 | | | +# | +---------------------|-------------------+ | +# | | | +# | +---------------------|-------------------+ | +# | | VRF v$ol2 | | | +# | | | | | +# | | v | | +# | | g2a (ip6gre) + | | +# | | loc=2001:db8:3::2 | | +# | | rem=2001:db8:3::1 | | +# | | tos=inherit | | +# | | | | +# | | $ol2 + | | +# | | 203.0.113.2/24 | | | +# | | 2001:db8:2::2/64 | | | +# | +---------------------|-------------------+ | +# +-----------------------|---------------------+ +# | +# +-----------------------|--------+ +# | H2 | | +# | $h2 + | +# | 203.0.113.1/24 | +# | 2001:db8:2::1/64 | +# +--------------------------------+ + +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 198.51.100.1/24 2001:db8:1::1/64 + ip route add vrf v$h1 203.0.113.0/24 via 198.51.100.2 + ip -6 route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 + ip route del vrf v$h1 203.0.113.0/24 via 198.51.100.2 + simple_if_fini $h1 198.51.100.1/24 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 203.0.113.1/24 2001:db8:2::1/64 + ip route add vrf v$h2 198.51.100.0/24 via 203.0.113.2 + ip -6 route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::2 +} + +h2_destroy() +{ + ip -6 route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::2 + ip route del vrf v$h2 198.51.100.0/24 via 203.0.113.2 + simple_if_fini $h2 203.0.113.1/24 2001:db8:2::1/64 +} + +sw1_flat_create() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip link set dev $ol1 up + __addr_add_del $ol1 add 198.51.100.2/24 2001:db8:1::2/64 + + ip link set dev $ul1 up + vlan_create $ul1 111 "" 2001:db8:10::1/64 + + tunnel_create g1a ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit "$@" + ip link set dev g1a up + __addr_add_del g1a add "2001:db8:3::1/128" + + ip -6 route add 2001:db8:3::2/128 via 2001:db8:10::2 + ip route add 203.0.113.0/24 dev g1a + ip -6 route add 2001:db8:2::/64 dev g1a +} + +sw1_flat_destroy() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip -6 route del 2001:db8:2::/64 + ip route del 203.0.113.0/24 + ip -6 route del 2001:db8:3::2/128 via 2001:db8:10::2 + + __simple_if_fini g1a 2001:db8:3::1/128 + tunnel_destroy g1a + + vlan_destroy $ul1 111 + __simple_if_fini $ul1 + __simple_if_fini $ol1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw2_flat_create() +{ + local ol2=$1; shift + local ul2=$1; shift + + simple_if_init $ol2 203.0.113.2/24 2001:db8:2::2/64 + __simple_if_init $ul2 v$ol2 + vlan_create $ul2 111 v$ol2 2001:db8:10::2/64 + + tunnel_create g2a ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \ + ttl inherit dev v$ol2 "$@" + __simple_if_init g2a v$ol2 2001:db8:3::2/128 + + # Replace neighbor to avoid 1 dropped packet due to "unresolved neigh" + ip neigh replace dev $ol2 203.0.113.1 lladdr $(mac_get $h2) + ip -6 neigh replace dev $ol2 2001:db8:2::1 lladdr $(mac_get $h2) + + ip -6 route add vrf v$ol2 2001:db8:3::1/128 via 2001:db8:10::1 + ip route add vrf v$ol2 198.51.100.0/24 dev g2a + ip -6 route add vrf v$ol2 2001:db8:1::/64 dev g2a +} + +sw2_flat_destroy() +{ + local ol2=$1; shift + local ul2=$1; shift + + ip -6 route del vrf v$ol2 2001:db8:2::/64 + ip route del vrf v$ol2 198.51.100.0/24 + ip -6 route del vrf v$ol2 2001:db8:3::1/128 via 2001:db8:10::1 + + __simple_if_fini g2a 2001:db8:3::2/128 + tunnel_destroy g2a + + vlan_destroy $ul2 111 + __simple_if_fini $ul2 + simple_if_fini $ol2 203.0.113.2/24 2001:db8:2::2/64 +} + +sw1_hierarchical_create() +{ + local ol1=$1; shift + local ul1=$1; shift + + simple_if_init $ol1 198.51.100.2/24 2001:db8:1::2/64 + simple_if_init $ul1 + ip link add name dummy1 type dummy + __simple_if_init dummy1 v$ul1 2001:db8:3::1/64 + + vlan_create $ul1 111 v$ul1 2001:db8:10::1/64 + tunnel_create g1a ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit dev dummy1 "$@" + ip link set dev g1a master v$ol1 + + ip -6 route add vrf v$ul1 2001:db8:3::2/128 via 2001:db8:10::2 + ip route add vrf v$ol1 203.0.113.0/24 dev g1a + ip -6 route add vrf v$ol1 2001:db8:2::/64 dev g1a +} + +sw1_hierarchical_destroy() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip -6 route del vrf v$ol1 2001:db8:2::/64 + ip route del vrf v$ol1 203.0.113.0/24 + ip -6 route del vrf v$ul1 2001:db8:3::2/128 + + tunnel_destroy g1a + vlan_destroy $ul1 111 + + __simple_if_fini dummy1 2001:db8:3::1/64 + ip link del dev dummy1 + + simple_if_fini $ul1 + simple_if_fini $ol1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw2_hierarchical_create() +{ + local ol2=$1; shift + local ul2=$1; shift + + simple_if_init $ol2 203.0.113.2/24 2001:db8:2::2/64 + simple_if_init $ul2 + + ip link add name dummy2 type dummy + __simple_if_init dummy2 v$ul2 2001:db8:3::2/64 + + vlan_create $ul2 111 v$ul2 2001:db8:10::2/64 + tunnel_create g2a ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \ + ttl inherit dev dummy2 "$@" + ip link set dev g2a master v$ol2 + + # Replace neighbor to avoid 1 dropped packet due to "unresolved neigh" + ip neigh replace dev $ol2 203.0.113.1 lladdr $(mac_get $h2) + ip -6 neigh replace dev $ol2 2001:db8:2::1 lladdr $(mac_get $h2) + + ip -6 route add vrf v$ul2 2001:db8:3::1/128 via 2001:db8:10::1 + ip route add vrf v$ol2 198.51.100.0/24 dev g2a + ip -6 route add vrf v$ol2 2001:db8:1::/64 dev g2a +} + +sw2_hierarchical_destroy() +{ + local ol2=$1; shift + local ul2=$1; shift + + ip -6 route del vrf v$ol2 2001:db8:2::/64 + ip route del vrf v$ol2 198.51.100.0/24 + ip -6 route del vrf v$ul2 2001:db8:3::1/128 + + tunnel_destroy g2a + vlan_destroy $ul2 111 + + __simple_if_fini dummy2 2001:db8:3::2/64 + ip link del dev dummy2 + + simple_if_fini $ul2 + simple_if_fini $ol2 203.0.113.2/24 2001:db8:2::2/64 +} + +test_traffic_ip4ip6() +{ + RET=0 + + h1mac=$(mac_get $h1) + ol1mac=$(mac_get $ol1) + + tc qdisc add dev $ul1 clsact + tc filter add dev $ul1 egress proto all pref 1 handle 101 \ + flower $TC_FLAG action pass + + tc qdisc add dev $ol2 clsact + tc filter add dev $ol2 egress protocol ipv4 pref 1 handle 101 \ + flower $TC_FLAG dst_ip 203.0.113.1 action pass + + $MZ $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 198.51.100.1 \ + -B 203.0.113.1 -t ip -q -d 1msec + + # Check ports after encap and after decap. + tc_check_at_least_x_packets "dev $ul1 egress" 101 1000 + check_err $? "Packets did not go through $ul1, tc_flag = $TC_FLAG" + + tc_check_at_least_x_packets "dev $ol2 egress" 101 1000 + check_err $? "Packets did not go through $ol2, tc_flag = $TC_FLAG" + + log_test "$@" + + tc filter del dev $ol2 egress protocol ipv4 pref 1 handle 101 flower + tc qdisc del dev $ol2 clsact + tc filter del dev $ul1 egress proto all pref 1 handle 101 flower + tc qdisc del dev $ul1 clsact +} + +test_traffic_ip6ip6() +{ + RET=0 + + h1mac=$(mac_get $h1) + ol1mac=$(mac_get $ol1) + + tc qdisc add dev $ul1 clsact + tc filter add dev $ul1 egress proto all pref 1 handle 101 \ + flower $TC_FLAG action pass + + tc qdisc add dev $ol2 clsact + tc filter add dev $ol2 egress protocol ipv6 pref 1 handle 101 \ + flower $TC_FLAG dst_ip 2001:db8:2::1 action pass + + $MZ -6 $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 2001:db8:1::1 \ + -B 2001:db8:2::1 -t ip -q -d 1msec + + # Check ports after encap and after decap. + tc_check_at_least_x_packets "dev $ul1 egress" 101 1000 + check_err $? "Packets did not go through $ul1, tc_flag = $TC_FLAG" + + tc_check_at_least_x_packets "dev $ol2 egress" 101 1000 + check_err $? "Packets did not go through $ol2, tc_flag = $TC_FLAG" + + log_test "$@" + + tc filter del dev $ol2 egress protocol ipv6 pref 1 handle 101 flower + tc qdisc del dev $ol2 clsact + tc filter del dev $ul1 egress proto all pref 1 handle 101 flower + tc qdisc del dev $ul1 clsact +} + +topo_mtu_change() +{ + local mtu=$1 + + ip link set mtu $mtu dev $h1 + ip link set mtu $mtu dev $ol1 + ip link set mtu $mtu dev g1a + ip link set mtu $mtu dev $ul1 + ip link set mtu $mtu dev $ul1.111 + ip link set mtu $mtu dev $h2 + ip link set mtu $mtu dev $ol2 + ip link set mtu $mtu dev g2a + ip link set mtu $mtu dev $ul2 + ip link set mtu $mtu dev $ul2.111 +} + +test_mtu_change() +{ + RET=0 + + ping6_do $h1 2001:db8:2::1 "-s 1800 -w 3" + check_fail $? "ping GRE IPv6 should not pass with packet size 1800" + + RET=0 + + topo_mtu_change 2000 + ping6_do $h1 2001:db8:2::1 "-s 1800 -w 3" + check_err $? + log_test "ping GRE IPv6, packet size 1800 after MTU change" +} diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh index 0e18e8be6e2a..bce8bb8d2b6f 100644 --- a/tools/testing/selftests/net/forwarding/tc_common.sh +++ b/tools/testing/selftests/net/forwarding/tc_common.sh @@ -16,6 +16,16 @@ tc_check_packets() tc_rule_handle_stats_get "$id" "$handle" > /dev/null } +tc_check_at_least_x_packets() +{ + local id=$1 + local handle=$2 + local count=$3 + + busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $count" \ + tc_rule_handle_stats_get "$id" "$handle" > /dev/null +} + tc_check_packets_hitting() { local id=$1 diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index 90700303d8a9..a2b9fad5a9a6 100755 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -536,10 +536,25 @@ out_bits() do ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ - dev veth0 + dev veth0 &>/dev/null + + local cmd_res=$? + local descr="${desc/<n>/$i}" - run_test "out_bit$i" "${desc/<n>/$i} ($1 mode)" ioam-node-alpha \ + if [[ $i -ge 12 && $i -le 21 ]] + then + if [ $cmd_res != 0 ] + then + npassed=$((npassed+1)) + log_test_passed "$descr" + else + nfailed=$((nfailed+1)) + log_test_failed "$descr" + fi + else + run_test "out_bit$i" "$descr ($1 mode)" ioam-node-alpha \ ioam-node-beta db01::2 db01::1 veth0 ${bit2type[$i]} 123 + fi done [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down @@ -632,7 +647,7 @@ in_bits() [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - for i in {0..22} + for i in {0..11} {22..22} do ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c index d376cb2c383c..8f6997d35816 100644 --- a/tools/testing/selftests/net/ioam6_parser.c +++ b/tools/testing/selftests/net/ioam6_parser.c @@ -94,16 +94,6 @@ enum { TEST_OUT_BIT9, TEST_OUT_BIT10, TEST_OUT_BIT11, - TEST_OUT_BIT12, - TEST_OUT_BIT13, - TEST_OUT_BIT14, - TEST_OUT_BIT15, - TEST_OUT_BIT16, - TEST_OUT_BIT17, - TEST_OUT_BIT18, - TEST_OUT_BIT19, - TEST_OUT_BIT20, - TEST_OUT_BIT21, TEST_OUT_BIT22, TEST_OUT_FULL_SUPP_TRACE, @@ -125,16 +115,6 @@ enum { TEST_IN_BIT9, TEST_IN_BIT10, TEST_IN_BIT11, - TEST_IN_BIT12, - TEST_IN_BIT13, - TEST_IN_BIT14, - TEST_IN_BIT15, - TEST_IN_BIT16, - TEST_IN_BIT17, - TEST_IN_BIT18, - TEST_IN_BIT19, - TEST_IN_BIT20, - TEST_IN_BIT21, TEST_IN_BIT22, TEST_IN_FULL_SUPP_TRACE, @@ -199,30 +179,6 @@ static int check_ioam_header(int tid, struct ioam6_trace_hdr *ioam6h, ioam6h->nodelen != 2 || ioam6h->remlen; - case TEST_OUT_BIT12: - case TEST_IN_BIT12: - case TEST_OUT_BIT13: - case TEST_IN_BIT13: - case TEST_OUT_BIT14: - case TEST_IN_BIT14: - case TEST_OUT_BIT15: - case TEST_IN_BIT15: - case TEST_OUT_BIT16: - case TEST_IN_BIT16: - case TEST_OUT_BIT17: - case TEST_IN_BIT17: - case TEST_OUT_BIT18: - case TEST_IN_BIT18: - case TEST_OUT_BIT19: - case TEST_IN_BIT19: - case TEST_OUT_BIT20: - case TEST_IN_BIT20: - case TEST_OUT_BIT21: - case TEST_IN_BIT21: - return ioam6h->overflow || - ioam6h->nodelen || - ioam6h->remlen != 1; - case TEST_OUT_BIT22: case TEST_IN_BIT22: return ioam6h->overflow || @@ -326,6 +282,66 @@ static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h, *p += sizeof(__u32); } + if (ioam6h->type.bit12) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit13) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit14) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit15) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit16) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit17) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit18) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit19) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit20) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + + if (ioam6h->type.bit21) { + if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) + return 1; + *p += sizeof(__u32); + } + if (ioam6h->type.bit22) { len = cnf.sc_data ? strlen(cnf.sc_data) : 0; aligned = cnf.sc_data ? __ALIGN_KERNEL(len, 4) : 0; @@ -455,26 +471,6 @@ static int str2id(const char *tname) return TEST_OUT_BIT10; if (!strcmp("out_bit11", tname)) return TEST_OUT_BIT11; - if (!strcmp("out_bit12", tname)) - return TEST_OUT_BIT12; - if (!strcmp("out_bit13", tname)) - return TEST_OUT_BIT13; - if (!strcmp("out_bit14", tname)) - return TEST_OUT_BIT14; - if (!strcmp("out_bit15", tname)) - return TEST_OUT_BIT15; - if (!strcmp("out_bit16", tname)) - return TEST_OUT_BIT16; - if (!strcmp("out_bit17", tname)) - return TEST_OUT_BIT17; - if (!strcmp("out_bit18", tname)) - return TEST_OUT_BIT18; - if (!strcmp("out_bit19", tname)) - return TEST_OUT_BIT19; - if (!strcmp("out_bit20", tname)) - return TEST_OUT_BIT20; - if (!strcmp("out_bit21", tname)) - return TEST_OUT_BIT21; if (!strcmp("out_bit22", tname)) return TEST_OUT_BIT22; if (!strcmp("out_full_supp_trace", tname)) @@ -509,26 +505,6 @@ static int str2id(const char *tname) return TEST_IN_BIT10; if (!strcmp("in_bit11", tname)) return TEST_IN_BIT11; - if (!strcmp("in_bit12", tname)) - return TEST_IN_BIT12; - if (!strcmp("in_bit13", tname)) - return TEST_IN_BIT13; - if (!strcmp("in_bit14", tname)) - return TEST_IN_BIT14; - if (!strcmp("in_bit15", tname)) - return TEST_IN_BIT15; - if (!strcmp("in_bit16", tname)) - return TEST_IN_BIT16; - if (!strcmp("in_bit17", tname)) - return TEST_IN_BIT17; - if (!strcmp("in_bit18", tname)) - return TEST_IN_BIT18; - if (!strcmp("in_bit19", tname)) - return TEST_IN_BIT19; - if (!strcmp("in_bit20", tname)) - return TEST_IN_BIT20; - if (!strcmp("in_bit21", tname)) - return TEST_IN_BIT21; if (!strcmp("in_bit22", tname)) return TEST_IN_BIT22; if (!strcmp("in_full_supp_trace", tname)) @@ -606,16 +582,6 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { [TEST_OUT_BIT9] = check_ioam_header_and_data, [TEST_OUT_BIT10] = check_ioam_header_and_data, [TEST_OUT_BIT11] = check_ioam_header_and_data, - [TEST_OUT_BIT12] = check_ioam_header, - [TEST_OUT_BIT13] = check_ioam_header, - [TEST_OUT_BIT14] = check_ioam_header, - [TEST_OUT_BIT15] = check_ioam_header, - [TEST_OUT_BIT16] = check_ioam_header, - [TEST_OUT_BIT17] = check_ioam_header, - [TEST_OUT_BIT18] = check_ioam_header, - [TEST_OUT_BIT19] = check_ioam_header, - [TEST_OUT_BIT20] = check_ioam_header, - [TEST_OUT_BIT21] = check_ioam_header, [TEST_OUT_BIT22] = check_ioam_header_and_data, [TEST_OUT_FULL_SUPP_TRACE] = check_ioam_header_and_data, [TEST_IN_UNDEF_NS] = check_ioam_header, @@ -633,16 +599,6 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { [TEST_IN_BIT9] = check_ioam_header_and_data, [TEST_IN_BIT10] = check_ioam_header_and_data, [TEST_IN_BIT11] = check_ioam_header_and_data, - [TEST_IN_BIT12] = check_ioam_header, - [TEST_IN_BIT13] = check_ioam_header, - [TEST_IN_BIT14] = check_ioam_header, - [TEST_IN_BIT15] = check_ioam_header, - [TEST_IN_BIT16] = check_ioam_header, - [TEST_IN_BIT17] = check_ioam_header, - [TEST_IN_BIT18] = check_ioam_header, - [TEST_IN_BIT19] = check_ioam_header, - [TEST_IN_BIT20] = check_ioam_header, - [TEST_IN_BIT21] = check_ioam_header, [TEST_IN_BIT22] = check_ioam_header_and_data, [TEST_IN_FULL_SUPP_TRACE] = check_ioam_header_and_data, [TEST_FWD_FULL_SUPP_TRACE] = check_ioam_header_and_data, diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 255793c5ac4f..293d349e21fe 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -945,12 +945,15 @@ subflows_tests() # subflow limited by client reset + ip netns exec $ns1 ./pm_nl_ctl limits 0 0 + ip netns exec $ns2 ./pm_nl_ctl limits 0 0 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow, limited by client" 0 0 0 # subflow limited by server reset + ip netns exec $ns1 ./pm_nl_ctl limits 0 0 ip netns exec $ns2 ./pm_nl_ctl limits 0 1 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 @@ -973,7 +976,7 @@ subflows_tests() run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows" 2 2 2 - # multiple subflows limited by serverf + # multiple subflows limited by server reset ip netns exec $ns1 ./pm_nl_ctl limits 0 1 ip netns exec $ns2 ./pm_nl_ctl limits 0 2 diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 3c741abe034e..cbacf9f6538b 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -70,7 +70,7 @@ check() check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list" check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "defaults limits" +subflows 2" "defaults limits" ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo @@ -118,11 +118,11 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs" ip netns exec $ns1 ./pm_nl_ctl limits 9 1 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "rcv addrs above hard limit" +subflows 2" "rcv addrs above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 1 9 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "subflows above hard limit" +subflows 2" "subflows above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 8 8 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8 diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 97fceb9be9ed..d3047e251fe9 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -29,6 +29,8 @@ struct tls_crypto_info_keys { union { struct tls12_crypto_info_aes_gcm_128 aes128; struct tls12_crypto_info_chacha20_poly1305 chacha20; + struct tls12_crypto_info_sm4_gcm sm4gcm; + struct tls12_crypto_info_sm4_ccm sm4ccm; }; size_t len; }; @@ -49,6 +51,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, tls12->aes128.info.version = tls_version; tls12->aes128.info.cipher_type = cipher_type; break; + case TLS_CIPHER_SM4_GCM: + tls12->len = sizeof(struct tls12_crypto_info_sm4_gcm); + tls12->sm4gcm.info.version = tls_version; + tls12->sm4gcm.info.cipher_type = cipher_type; + break; + case TLS_CIPHER_SM4_CCM: + tls12->len = sizeof(struct tls12_crypto_info_sm4_ccm); + tls12->sm4ccm.info.version = tls_version; + tls12->sm4ccm.info.cipher_type = cipher_type; + break; default: break; } @@ -148,13 +160,13 @@ FIXTURE_VARIANT(tls) uint16_t cipher_type; }; -FIXTURE_VARIANT_ADD(tls, 12_gcm) +FIXTURE_VARIANT_ADD(tls, 12_aes_gcm) { .tls_version = TLS_1_2_VERSION, .cipher_type = TLS_CIPHER_AES_GCM_128, }; -FIXTURE_VARIANT_ADD(tls, 13_gcm) +FIXTURE_VARIANT_ADD(tls, 13_aes_gcm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_AES_GCM_128, @@ -172,6 +184,18 @@ FIXTURE_VARIANT_ADD(tls, 13_chacha) .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, }; +FIXTURE_VARIANT_ADD(tls, 13_sm4_gcm) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_SM4_GCM, +}; + +FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_SM4_CCM, +}; + FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12; |