diff options
421 files changed, 5613 insertions, 3611 deletions
diff --git a/Documentation/devicetree/bindings/dma/moxa,moxart-dma.txt b/Documentation/devicetree/bindings/dma/moxa,moxart-dma.txt index 8a9f3559335b..7e14e26676ec 100644 --- a/Documentation/devicetree/bindings/dma/moxa,moxart-dma.txt +++ b/Documentation/devicetree/bindings/dma/moxa,moxart-dma.txt @@ -34,8 +34,8 @@ Example: Use specific request line passing from dma For example, MMC request line is 5 - sdhci: sdhci@98e00000 { - compatible = "moxa,moxart-sdhci"; + mmc: mmc@98e00000 { + compatible = "moxa,moxart-mmc"; reg = <0x98e00000 0x5C>; interrupts = <5 0>; clocks = <&clk_apb>; diff --git a/Documentation/devicetree/bindings/memory-controllers/fsl/imx8m-ddrc.yaml b/Documentation/devicetree/bindings/memory-controllers/fsl/imx8m-ddrc.yaml index 445e46feda69..2b39fce5f650 100644 --- a/Documentation/devicetree/bindings/memory-controllers/fsl/imx8m-ddrc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/fsl/imx8m-ddrc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: i.MX8M DDR Controller maintainers: - - Leonard Crestez <[email protected]> + - Peng Fan <[email protected]> description: The DDRC block is integrated in i.MX8M for interfacing with DDR based diff --git a/Documentation/devicetree/bindings/opp/opp-v2-kryo-cpu.yaml b/Documentation/devicetree/bindings/opp/opp-v2-kryo-cpu.yaml index 59663e897dae..a202b6c6561d 100644 --- a/Documentation/devicetree/bindings/opp/opp-v2-kryo-cpu.yaml +++ b/Documentation/devicetree/bindings/opp/opp-v2-kryo-cpu.yaml @@ -40,6 +40,7 @@ properties: patternProperties: '^opp-?[0-9]+$': type: object + additionalProperties: false properties: opp-hz: true diff --git a/Documentation/devicetree/bindings/opp/opp-v2-qcom-level.yaml b/Documentation/devicetree/bindings/opp/opp-v2-qcom-level.yaml index 14a7a689ad6d..df8442fb11f0 100644 --- a/Documentation/devicetree/bindings/opp/opp-v2-qcom-level.yaml +++ b/Documentation/devicetree/bindings/opp/opp-v2-qcom-level.yaml @@ -19,6 +19,7 @@ properties: patternProperties: '^opp-?[0-9]+$': type: object + additionalProperties: false properties: opp-level: true diff --git a/Documentation/i2c/dev-interface.rst b/Documentation/i2c/dev-interface.rst index 73ad34849f99..c277a8e1202b 100644 --- a/Documentation/i2c/dev-interface.rst +++ b/Documentation/i2c/dev-interface.rst @@ -148,7 +148,7 @@ You can do plain I2C transactions by using read(2) and write(2) calls. You do not need to pass the address byte; instead, set it through ioctl I2C_SLAVE before you try to access the device. -You can do SMBus level transactions (see documentation file smbus-protocol +You can do SMBus level transactions (see documentation file smbus-protocol.rst for details) through the following functions:: __s32 i2c_smbus_write_quick(int file, __u8 value); diff --git a/Documentation/i2c/slave-interface.rst b/Documentation/i2c/slave-interface.rst index 82ea3e1d6fe4..58fb143baee4 100644 --- a/Documentation/i2c/slave-interface.rst +++ b/Documentation/i2c/slave-interface.rst @@ -32,9 +32,9 @@ User manual =========== I2C slave backends behave like standard I2C clients. So, you can instantiate -them as described in the document 'instantiating-devices'. The only difference -is that i2c slave backends have their own address space. So, you have to add -0x1000 to the address you would originally request. An example for +them as described in the document instantiating-devices.rst. The only +difference is that i2c slave backends have their own address space. So, you +have to add 0x1000 to the address you would originally request. An example for instantiating the slave-eeprom driver from userspace at the 7 bit address 0x64 on bus 1:: diff --git a/Documentation/i2c/writing-clients.rst b/Documentation/i2c/writing-clients.rst index e3b126cf4a3b..47f7cbf4ed1a 100644 --- a/Documentation/i2c/writing-clients.rst +++ b/Documentation/i2c/writing-clients.rst @@ -364,7 +364,7 @@ stop condition is issued between transaction. The i2c_msg structure contains for each message the client address, the number of bytes of the message and the message data itself. -You can read the file ``i2c-protocol`` for more information about the +You can read the file i2c-protocol.rst for more information about the actual I2C protocol. @@ -414,7 +414,7 @@ transactions return 0 on success; the 'read' transactions return the read value, except for block transactions, which return the number of values read. The block buffers need not be longer than 32 bytes. -You can read the file ``smbus-protocol`` for more information about the +You can read the file smbus-protocol.rst for more information about the actual SMBus protocol. diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst index e263dfcc4b40..213510698014 100644 --- a/Documentation/networking/mptcp-sysctl.rst +++ b/Documentation/networking/mptcp-sysctl.rst @@ -47,7 +47,6 @@ allow_join_initial_addr_port - BOOLEAN Default: 1 pm_type - INTEGER - Set the default path manager type to use for each new MPTCP socket. In-kernel path management will control subflow connections and address advertisements according to diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst index 834945ebc4cd..1120d71f28d7 100644 --- a/Documentation/networking/nf_conntrack-sysctl.rst +++ b/Documentation/networking/nf_conntrack-sysctl.rst @@ -70,15 +70,6 @@ nf_conntrack_generic_timeout - INTEGER (seconds) Default for generic timeout. This refers to layer 4 unknown/unsupported protocols. -nf_conntrack_helper - BOOLEAN - - 0 - disabled (default) - - not 0 - enabled - - Enable automatic conntrack helper assignment. - If disabled it is required to set up iptables rules to assign - helpers to connections. See the CT target description in the - iptables-extensions(8) man page for further information. - nf_conntrack_icmp_timeout - INTEGER (seconds) default 30 diff --git a/MAINTAINERS b/MAINTAINERS index 9ae989b32ebb..c6c1eef614ef 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -671,7 +671,8 @@ F: fs/afs/ F: include/trace/events/afs.h AGPGART DRIVER -M: David Airlie <[email protected]> +M: David Airlie <[email protected]> S: Maintained T: git git://anongit.freedesktop.org/drm/drm F: drivers/char/agp/ @@ -1010,7 +1011,6 @@ F: drivers/spi/spi-amd.c AMD MP2 I2C DRIVER M: Elie Morisse <[email protected]> -M: Nehal Shah <[email protected]> M: Shyam Sundar S K <[email protected]> S: Maintained @@ -5245,6 +5245,7 @@ F: block/blk-throttle.c F: include/linux/blk-cgroup.h CONTROL GROUP - CPUSET +M: Waiman Long <[email protected]> M: Zefan Li <[email protected]> S: Maintained @@ -6753,7 +6754,7 @@ F: Documentation/devicetree/bindings/display/panel/samsung,lms380kf01.yaml F: drivers/gpu/drm/panel/panel-widechips-ws2401.c DRM DRIVERS -M: David Airlie <[email protected]> +M: David Airlie <[email protected]> M: Daniel Vetter <[email protected]> S: Maintained @@ -8652,8 +8653,8 @@ F: drivers/input/touchscreen/goodix* GOOGLE ETHERNET DRIVERS M: Jeroen de Borst <[email protected]> -R: Catherine Sullivan <[email protected]> -R: David Awogbemila <[email protected]> +M: Catherine Sullivan <[email protected]> +R: Shailend Chand <[email protected]> S: Supported F: Documentation/networking/device_drivers/ethernet/google/gve.rst @@ -14546,6 +14547,15 @@ F: drivers/nvme/common/ F: include/linux/nvme* F: include/uapi/linux/nvme_ioctl.h +NVM EXPRESS FABRICS AUTHENTICATION +M: Hannes Reinecke <[email protected]> +S: Supported +F: drivers/nvme/host/auth.c +F: drivers/nvme/target/auth.c +F: drivers/nvme/target/fabrics-cmd-auth.c +F: include/linux/nvme-auth.h + NVM EXPRESS FC TRANSPORT DRIVERS M: James Smart <[email protected]> @@ -16857,6 +16867,7 @@ F: drivers/net/ethernet/qualcomm/emac/ QUALCOMM ETHQOS ETHERNET DRIVER M: Vinod Koul <[email protected]> +R: Bhupesh Sharma <[email protected]> S: Maintained F: Documentation/devicetree/bindings/net/qcom,ethqos.txt @@ -19959,6 +19970,7 @@ S: Supported F: drivers/net/team/ F: include/linux/if_team.h F: include/uapi/linux/if_team.h +F: tools/testing/selftests/net/team/ TECHNOLOGIC SYSTEMS TS-5500 PLATFORM SUPPORT M: "Savoir-faire Linux Inc." <[email protected]> @@ -21565,7 +21577,7 @@ F: drivers/gpio/gpio-virtio.c F: include/uapi/linux/virtio_gpio.h VIRTIO GPU DRIVER -M: David Airlie <[email protected]> +M: David Airlie <[email protected]> M: Gerd Hoffmann <[email protected]> R: Gurchetan Singh <[email protected]> R: Chia-I Wu <[email protected]> @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/lan966x.dtsi b/arch/arm/boot/dts/lan966x.dtsi index 894bf9da19a4..0bf818713422 100644 --- a/arch/arm/boot/dts/lan966x.dtsi +++ b/arch/arm/boot/dts/lan966x.dtsi @@ -541,13 +541,13 @@ phy0: ethernet-phy@1 { reg = <1>; - interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; phy1: ethernet-phy@2 { reg = <2>; - interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/moxart-uc7112lx.dts b/arch/arm/boot/dts/moxart-uc7112lx.dts index eb5291b0ee3a..e07b807b4cec 100644 --- a/arch/arm/boot/dts/moxart-uc7112lx.dts +++ b/arch/arm/boot/dts/moxart-uc7112lx.dts @@ -79,7 +79,7 @@ clocks = <&ref12>; }; -&sdhci { +&mmc { status = "okay"; }; diff --git a/arch/arm/boot/dts/moxart.dtsi b/arch/arm/boot/dts/moxart.dtsi index f5f070a87482..764832ddfa78 100644 --- a/arch/arm/boot/dts/moxart.dtsi +++ b/arch/arm/boot/dts/moxart.dtsi @@ -93,8 +93,8 @@ clock-names = "PCLK"; }; - sdhci: sdhci@98e00000 { - compatible = "moxa,moxart-sdhci"; + mmc: mmc@98e00000 { + compatible = "moxa,moxart-mmc"; reg = <0x98e00000 0x5C>; interrupts = <5 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk_apb>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts index c97f4e06ae5f..32f6f2f50c10 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts @@ -152,11 +152,11 @@ * CPLD_reset is RESET_SOFT in schematic */ gpio-line-names = - "CPLD_D[1]", "CPLD_int", "CPLD_reset", "", - "", "CPLD_D[0]", "", "", - "", "", "", "CPLD_D[2]", - "CPLD_D[3]", "CPLD_D[4]", "CPLD_D[5]", "CPLD_D[6]", - "CPLD_D[7]", "", "", "", + "CPLD_D[6]", "CPLD_int", "CPLD_reset", "", + "", "CPLD_D[7]", "", "", + "", "", "", "CPLD_D[5]", + "CPLD_D[4]", "CPLD_D[3]", "CPLD_D[2]", "CPLD_D[1]", + "CPLD_D[0]", "", "", "", "", "", "", "", "", "", "", "KBD_intK", "", "", "", ""; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts index 286d2df01cfa..7e0aeb2db305 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml-mba8mx.dts @@ -5,7 +5,6 @@ /dts-v1/; -#include <dt-bindings/phy/phy-imx8-pcie.h> #include "imx8mm-tqma8mqml.dtsi" #include "mba8mx.dtsi" diff --git a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi index 16ee9b5179e6..f649dfacb4b6 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-tqma8mqml.dtsi @@ -3,6 +3,7 @@ * Copyright 2020-2021 TQ-Systems GmbH */ +#include <dt-bindings/phy/phy-imx8-pcie.h> #include "imx8mm.dtsi" / { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index b379c461aa13..3ec0c9ac3170 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -367,8 +367,8 @@ nxp,dvs-standby-voltage = <850000>; regulator-always-on; regulator-boot-on; - regulator-max-microvolt = <950000>; - regulator-min-microvolt = <850000>; + regulator-max-microvolt = <1050000>; + regulator-min-microvolt = <805000>; regulator-name = "On-module +VDD_ARM (BUCK2)"; regulator-ramp-delay = <3125>; }; @@ -376,8 +376,8 @@ reg_vdd_dram: BUCK3 { regulator-always-on; regulator-boot-on; - regulator-max-microvolt = <950000>; - regulator-min-microvolt = <850000>; + regulator-max-microvolt = <1000000>; + regulator-min-microvolt = <805000>; regulator-name = "On-module +VDD_GPU_VPU_DDR (BUCK3)"; }; @@ -416,7 +416,7 @@ reg_vdd_snvs: LDO2 { regulator-always-on; regulator-boot-on; - regulator-max-microvolt = <900000>; + regulator-max-microvolt = <800000>; regulator-min-microvolt = <800000>; regulator-name = "On-module +V0.8_SNVS (LDO2)"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 0c71b740a316..cb2836bfbd95 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -672,7 +672,6 @@ <&clk IMX8MN_CLK_GPU_SHADER>, <&clk IMX8MN_CLK_GPU_BUS_ROOT>, <&clk IMX8MN_CLK_GPU_AHB>; - resets = <&src IMX8MQ_RESET_GPU_RESET>; }; pgc_dispmix: power-domain@3 { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts index d8ca52976170..0e237b2f9541 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts @@ -57,13 +57,13 @@ switch-1 { label = "S12"; linux,code = <BTN_0>; - gpios = <&gpio5 26 GPIO_ACTIVE_LOW>; + gpios = <&gpio5 27 GPIO_ACTIVE_LOW>; }; switch-2 { label = "S13"; linux,code = <BTN_1>; - gpios = <&gpio5 27 GPIO_ACTIVE_LOW>; + gpios = <&gpio5 26 GPIO_ACTIVE_LOW>; }; }; @@ -394,6 +394,8 @@ &pcf85063 { /* RTC_EVENT# is connected on MBa8MPxL */ + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_pcf85063>; interrupt-parent = <&gpio4>; interrupts = <28 IRQ_TYPE_EDGE_FALLING>; }; @@ -630,6 +632,10 @@ fsl,pins = <MX8MP_IOMUXC_SAI5_RXC__GPIO3_IO20 0x10>; /* Power enable */ }; + pinctrl_pcf85063: pcf85063grp { + fsl,pins = <MX8MP_IOMUXC_SAI3_RXFS__GPIO4_IO28 0x80>; + }; + /* LVDS Backlight */ pinctrl_pwm2: pwm2grp { fsl,pins = <MX8MP_IOMUXC_SAI5_RXD0__PWM2_OUT 0x14>; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts index 6630ec561dc2..211e6a1b296e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts @@ -123,8 +123,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_reg_can>; regulator-name = "can2_stby"; - gpio = <&gpio3 19 GPIO_ACTIVE_HIGH>; - enable-active-high; + gpio = <&gpio3 19 GPIO_ACTIVE_LOW>; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; }; @@ -484,35 +483,40 @@ lan1: port@0 { reg = <0>; label = "lan1"; + phy-mode = "internal"; local-mac-address = [00 00 00 00 00 00]; }; lan2: port@1 { reg = <1>; label = "lan2"; + phy-mode = "internal"; local-mac-address = [00 00 00 00 00 00]; }; lan3: port@2 { reg = <2>; label = "lan3"; + phy-mode = "internal"; local-mac-address = [00 00 00 00 00 00]; }; lan4: port@3 { reg = <3>; label = "lan4"; + phy-mode = "internal"; local-mac-address = [00 00 00 00 00 00]; }; lan5: port@4 { reg = <4>; label = "lan5"; + phy-mode = "internal"; local-mac-address = [00 00 00 00 00 00]; }; - port@6 { - reg = <6>; + port@5 { + reg = <5>; label = "cpu"; ethernet = <&fec>; phy-mode = "rgmii-id"; diff --git a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi index 60c1b018bf03..bb56390b8f54 100644 --- a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi @@ -172,6 +172,7 @@ compatible = "fsl,imx8ulp-pcc3"; reg = <0x292d0000 0x10000>; #clock-cells = <1>; + #reset-cells = <1>; }; tpm5: tpm@29340000 { @@ -270,6 +271,7 @@ compatible = "fsl,imx8ulp-pcc4"; reg = <0x29800000 0x10000>; #clock-cells = <1>; + #reset-cells = <1>; }; lpi2c6: i2c@29840000 { @@ -414,6 +416,7 @@ compatible = "fsl,imx8ulp-pcc5"; reg = <0x2da70000 0x10000>; #clock-cells = <1>; + #reset-cells = <1>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core.dtsi b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core.dtsi index 7249871530ab..5eecbefa8a33 100644 --- a/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-engicam-px30-core.dtsi @@ -2,8 +2,8 @@ /* * Copyright (c) 2020 Fuzhou Rockchip Electronics Co., Ltd * Copyright (c) 2020 Engicam srl - * Copyright (c) 2020 Amarula Solutons - * Copyright (c) 2020 Amarula Solutons(India) + * Copyright (c) 2020 Amarula Solutions + * Copyright (c) 2020 Amarula Solutions(India) */ #include <dt-bindings/gpio/gpio.h> diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts index 31ebb4e5fd33..0f9cc042d9bf 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts @@ -88,3 +88,8 @@ }; }; }; + +&wlan_host_wake_l { + /* Kevin has an external pull up, but Bob does not. */ + rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi index cd074641884b..ee6095baba4d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi @@ -244,6 +244,14 @@ &edp { status = "okay"; + /* + * eDP PHY/clk don't sync reliably at anything other than 24 MHz. Only + * set this here, because rk3399-gru.dtsi ensures we can generate this + * off GPLL=600MHz, whereas some other RK3399 boards may not. + */ + assigned-clocks = <&cru PCLK_EDP>; + assigned-clock-rates = <24000000>; + ports { edp_out: port@1 { reg = <1>; @@ -578,6 +586,7 @@ ap_i2c_tp: &i2c5 { }; wlan_host_wake_l: wlan-host-wake-l { + /* Kevin has an external pull up, but Bob does not */ rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index b1ac3a89f259..aa3e21bd6c8f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -62,7 +62,6 @@ vcc5v0_host: vcc5v0-host-regulator { compatible = "regulator-fixed"; gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_LOW>; - enable-active-low; pinctrl-names = "default"; pinctrl-0 = <&vcc5v0_host_en>; regulator-name = "vcc5v0_host"; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts index d943559b157c..a05460b92415 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts @@ -189,7 +189,6 @@ vcc3v3_sd: vcc3v3_sd { compatible = "regulator-fixed"; - enable-active-low; gpio = <&gpio0 RK_PA5 GPIO_ACTIVE_LOW>; pinctrl-names = "default"; pinctrl-0 = <&vcc_sd_h>; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts index 02d5f5a8ca03..528bb4e8ac77 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-b.dts @@ -506,7 +506,7 @@ disable-wp; pinctrl-names = "default"; pinctrl-0 = <&sdmmc0_bus4 &sdmmc0_clk &sdmmc0_cmd &sdmmc0_det>; - sd-uhs-sdr104; + sd-uhs-sdr50; vmmc-supply = <&vcc3v3_sd>; vqmmc-supply = <&vccio_sd>; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts index 5e34bd0b214d..93d383b8be87 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts @@ -678,7 +678,7 @@ }; &usb_host0_xhci { - extcon = <&usb2phy0>; + dr_mode = "host"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts index 6ff89ff95ad1..674792567fa6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts @@ -656,7 +656,7 @@ }; &usb2phy0_otg { - vbus-supply = <&vcc5v0_usb_otg>; + phy-supply = <&vcc5v0_usb_otg>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts index 6b5093a1a6cf..b2e040dffb59 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts @@ -581,7 +581,7 @@ }; &usb2phy0_otg { - vbus-supply = <&vcc5v0_usb_otg>; + phy-supply = <&vcc5v0_usb_otg>; status = "okay"; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index d5b2d2dd4904..5b167649097e 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -48,6 +48,7 @@ CONFIG_ARCH_KEEMBAY=y CONFIG_ARCH_MEDIATEK=y CONFIG_ARCH_MESON=y CONFIG_ARCH_MVEBU=y +CONFIG_ARCH_NXP=y CONFIG_ARCH_MXC=y CONFIG_ARCH_NPCM=y CONFIG_ARCH_QCOM=y diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index ad2bfc794257..44ebf5b2fc4b 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -237,7 +237,7 @@ static void amu_fie_setup(const struct cpumask *cpus) for_each_cpu(cpu, cpus) { if (!freq_counters_valid(cpu) || freq_inv_set_max_ratio(cpu, - cpufreq_get_hw_max_freq(cpu) * 1000, + cpufreq_get_hw_max_freq(cpu) * 1000ULL, arch_timer_get_rate())) return; } diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 2ff0ef62abad..917086be5c6b 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2114,7 +2114,7 @@ static int finalize_hyp_mode(void) * at, which would end badly once inaccessible. */ kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start); - kmemleak_free_part(__va(hyp_mem_base), hyp_mem_size); + kmemleak_free_part_phys(hyp_mem_base, hyp_mem_size); return pkvm_drop_host_privileges(); } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index e7ad44585f40..eb489302c28a 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -331,12 +331,6 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end, } BUG_ON(p4d_bad(p4d)); - /* - * No need for locking during early boot. And it doesn't work as - * expected with KASLR enabled. - */ - if (system_state != SYSTEM_BOOTING) - mutex_lock(&fixmap_lock); pudp = pud_set_fixmap_offset(p4dp, addr); do { pud_t old_pud = READ_ONCE(*pudp); @@ -368,15 +362,13 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end, } while (pudp++, addr = next, addr != end); pud_clear_fixmap(); - if (system_state != SYSTEM_BOOTING) - mutex_unlock(&fixmap_lock); } -static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, - unsigned long virt, phys_addr_t size, - pgprot_t prot, - phys_addr_t (*pgtable_alloc)(int), - int flags) +static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(int), + int flags) { unsigned long addr, end, next; pgd_t *pgdp = pgd_offset_pgd(pgdir, virt); @@ -400,8 +392,20 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, } while (pgdp++, addr = next, addr != end); } +static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(int), + int flags) +{ + mutex_lock(&fixmap_lock); + __create_pgd_mapping_locked(pgdir, phys, virt, size, prot, + pgtable_alloc, flags); + mutex_unlock(&fixmap_lock); +} + #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -extern __alias(__create_pgd_mapping) +extern __alias(__create_pgd_mapping_locked) void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags); diff --git a/arch/mips/lantiq/clk.c b/arch/mips/lantiq/clk.c index 7a623684d9b5..2d5a0bcb0cec 100644 --- a/arch/mips/lantiq/clk.c +++ b/arch/mips/lantiq/clk.c @@ -50,6 +50,7 @@ struct clk *clk_get_io(void) { return &cpu_clk_generic[2]; } +EXPORT_SYMBOL_GPL(clk_get_io); struct clk *clk_get_ppe(void) { diff --git a/arch/mips/loongson32/common/platform.c b/arch/mips/loongson32/common/platform.c index 794c96c2a4cd..311dc1580bbd 100644 --- a/arch/mips/loongson32/common/platform.c +++ b/arch/mips/loongson32/common/platform.c @@ -98,7 +98,7 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv) if (plat_dat->bus_id) { __raw_writel(__raw_readl(LS1X_MUX_CTRL0) | GMAC1_USE_UART1 | GMAC1_USE_UART0, LS1X_MUX_CTRL0); - switch (plat_dat->interface) { + switch (plat_dat->phy_interface) { case PHY_INTERFACE_MODE_RGMII: val &= ~(GMAC1_USE_TXCLK | GMAC1_USE_PWM23); break; @@ -107,12 +107,12 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv) break; default: pr_err("unsupported mii mode %d\n", - plat_dat->interface); + plat_dat->phy_interface); return -ENOTSUPP; } val &= ~GMAC1_SHUT; } else { - switch (plat_dat->interface) { + switch (plat_dat->phy_interface) { case PHY_INTERFACE_MODE_RGMII: val &= ~(GMAC0_USE_TXCLK | GMAC0_USE_PWM01); break; @@ -121,7 +121,7 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv) break; default: pr_err("unsupported mii mode %d\n", - plat_dat->interface); + plat_dat->phy_interface); return -ENOTSUPP; } val &= ~GMAC0_SHUT; @@ -131,7 +131,7 @@ int ls1x_eth_mux_init(struct platform_device *pdev, void *priv) plat_dat = dev_get_platdata(&pdev->dev); val &= ~PHY_INTF_SELI; - if (plat_dat->interface == PHY_INTERFACE_MODE_RMII) + if (plat_dat->phy_interface == PHY_INTERFACE_MODE_RMII) val |= 0x4 << PHY_INTF_SELI_SHIFT; __raw_writel(val, LS1X_MUX_CTRL1); @@ -146,9 +146,9 @@ static struct plat_stmmacenet_data ls1x_eth0_pdata = { .bus_id = 0, .phy_addr = -1, #if defined(CONFIG_LOONGSON1_LS1B) - .interface = PHY_INTERFACE_MODE_MII, + .phy_interface = PHY_INTERFACE_MODE_MII, #elif defined(CONFIG_LOONGSON1_LS1C) - .interface = PHY_INTERFACE_MODE_RMII, + .phy_interface = PHY_INTERFACE_MODE_RMII, #endif .mdio_bus_data = &ls1x_mdio_bus_data, .dma_cfg = &ls1x_eth_dma_cfg, @@ -186,7 +186,7 @@ struct platform_device ls1x_eth0_pdev = { static struct plat_stmmacenet_data ls1x_eth1_pdata = { .bus_id = 1, .phy_addr = -1, - .interface = PHY_INTERFACE_MODE_MII, + .phy_interface = PHY_INTERFACE_MODE_MII, .mdio_bus_data = &ls1x_mdio_bus_data, .dma_cfg = &ls1x_eth_dma_cfg, .has_gmac = 1, diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index ed66c31e4655..59d18881f35b 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -386,6 +386,7 @@ config RISCV_ISA_C config RISCV_ISA_SVPBMT bool "SVPBMT extension support" depends on 64BIT && MMU + depends on !XIP_KERNEL select RISCV_ALTERNATIVE default y help diff --git a/arch/riscv/Kconfig.erratas b/arch/riscv/Kconfig.erratas index 6850e9389930..f3623df23b5f 100644 --- a/arch/riscv/Kconfig.erratas +++ b/arch/riscv/Kconfig.erratas @@ -46,7 +46,7 @@ config ERRATA_THEAD config ERRATA_THEAD_PBMT bool "Apply T-Head memory type errata" - depends on ERRATA_THEAD && 64BIT + depends on ERRATA_THEAD && 64BIT && MMU select RISCV_ALTERNATIVE_EARLY default y help @@ -57,7 +57,7 @@ config ERRATA_THEAD_PBMT config ERRATA_THEAD_CMO bool "Apply T-Head cache management errata" - depends on ERRATA_THEAD + depends on ERRATA_THEAD && MMU select RISCV_DMA_NONCOHERENT default y help diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index 202c83f677b2..96648c176f37 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -37,6 +37,7 @@ static bool errata_probe_cmo(unsigned int stage, if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) return false; + riscv_cbom_block_size = L1_CACHE_BYTES; riscv_noncoherent_supported(); return true; #else diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index a60acaecfeda..273ece6b622f 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -42,6 +42,11 @@ void flush_icache_mm(struct mm_struct *mm, bool local); #endif /* CONFIG_SMP */ +/* + * The T-Head CMO errata internally probe the CBOM block size, but otherwise + * don't depend on Zicbom. + */ +extern unsigned int riscv_cbom_block_size; #ifdef CONFIG_RISCV_ISA_ZICBOM void riscv_init_cbom_blocksize(void); #else diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 95ef6e2bf45c..2dfc463b86bb 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -296,8 +296,8 @@ void __init setup_arch(char **cmdline_p) setup_smp(); #endif - riscv_fill_hwcap(); riscv_init_cbom_blocksize(); + riscv_fill_hwcap(); apply_boot_alternatives(); } diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 5a2de6b6f882..5c591123c440 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -124,6 +124,8 @@ SYSCALL_DEFINE0(rt_sigreturn) if (restore_altstack(&frame->uc.uc_stack)) goto badframe; + regs->cause = -1UL; + return regs->a0; badframe: diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c index cd2225304c82..e3f9bdf47c5f 100644 --- a/arch/riscv/mm/dma-noncoherent.c +++ b/arch/riscv/mm/dma-noncoherent.c @@ -12,7 +12,7 @@ #include <linux/of_device.h> #include <asm/cacheflush.h> -static unsigned int riscv_cbom_block_size = L1_CACHE_BYTES; +unsigned int riscv_cbom_block_size; static bool noncoherent_supported; void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, @@ -79,38 +79,41 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, void riscv_init_cbom_blocksize(void) { struct device_node *node; + unsigned long cbom_hartid; + u32 val, probed_block_size; int ret; - u32 val; + probed_block_size = 0; for_each_of_cpu_node(node) { unsigned long hartid; - int cbom_hartid; ret = riscv_of_processor_hartid(node, &hartid); if (ret) continue; - if (hartid < 0) - continue; - /* set block-size for cbom extension if available */ ret = of_property_read_u32(node, "riscv,cbom-block-size", &val); if (ret) continue; - if (!riscv_cbom_block_size) { - riscv_cbom_block_size = val; + if (!probed_block_size) { + probed_block_size = val; cbom_hartid = hartid; } else { - if (riscv_cbom_block_size != val) - pr_warn("cbom-block-size mismatched between harts %d and %lu\n", + if (probed_block_size != val) + pr_warn("cbom-block-size mismatched between harts %lu and %lu\n", cbom_hartid, hartid); } } + + if (probed_block_size) + riscv_cbom_block_size = probed_block_size; } #endif void riscv_noncoherent_supported(void) { + WARN(!riscv_cbom_block_size, + "Non-coherent DMA support enabled without a block size\n"); noncoherent_supported = true; } diff --git a/arch/s390/include/asm/scsw.h b/arch/s390/include/asm/scsw.h index 7ce584aff5bb..322bdcd4b616 100644 --- a/arch/s390/include/asm/scsw.h +++ b/arch/s390/include/asm/scsw.h @@ -215,6 +215,11 @@ union scsw { #define SNS2_ENV_DATA_PRESENT 0x10 #define SNS2_INPRECISE_END 0x04 +/* + * architectured values for PPRC errors + */ +#define SNS7_INVALID_ON_SEC 0x0e + /** * scsw_is_tm - check for transport mode scsw * @scsw: pointer to scsw diff --git a/arch/s390/include/uapi/asm/dasd.h b/arch/s390/include/uapi/asm/dasd.h index 9ec86fae9980..93d1ccd3304c 100644 --- a/arch/s390/include/uapi/asm/dasd.h +++ b/arch/s390/include/uapi/asm/dasd.h @@ -183,6 +183,18 @@ typedef struct format_data_t { } format_data_t; /* + * struct dasd_copypair_swap_data_t + * represents all data necessary to issue a swap of the copy pair relation + */ +struct dasd_copypair_swap_data_t { + char primary[20]; /* BUSID of primary */ + char secondary[20]; /* BUSID of secondary */ + + /* Reserved for future updates. */ + __u8 reserved[64]; +}; + +/* * values to be used for format_data_t.intensity * 0/8: normal format * 1/9: also write record zero @@ -326,6 +338,8 @@ struct dasd_snid_ioctl_data { #define BIODASDSATTR _IOW(DASD_IOCTL_LETTER,2,attrib_data_t) /* Release Allocated Space */ #define BIODASDRAS _IOW(DASD_IOCTL_LETTER, 3, format_data_t) +/* Swap copy pair relation */ +#define BIODASDCOPYPAIRSWAP _IOW(DASD_IOCTL_LETTER, 4, struct dasd_copypair_swap_data_t) /* Get Sense Path Group ID (SNID) data */ #define BIODASDSNID _IOWR(DASD_IOCTL_LETTER, 1, struct dasd_snid_ioctl_data) diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 082ec5f2c3a5..0243b6e38d36 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -489,6 +489,8 @@ enum prot_type { PROT_TYPE_ALC = 2, PROT_TYPE_DAT = 3, PROT_TYPE_IEP = 4, + /* Dummy value for passing an initialized value when code != PGM_PROTECTION */ + PROT_NONE, }; static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva, u8 ar, @@ -504,6 +506,10 @@ static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva, switch (code) { case PGM_PROTECTION: switch (prot) { + case PROT_NONE: + /* We should never get here, acts like termination */ + WARN_ON_ONCE(1); + break; case PROT_TYPE_IEP: tec->b61 = 1; fallthrough; @@ -968,8 +974,10 @@ static int guest_range_to_gpas(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, return rc; } else { gpa = kvm_s390_real_to_abs(vcpu, ga); - if (kvm_is_error_gpa(vcpu->kvm, gpa)) + if (kvm_is_error_gpa(vcpu->kvm, gpa)) { rc = PGM_ADDRESSING; + prot = PROT_NONE; + } } if (rc) return trans_exc(vcpu, rc, ga, ar, mode, prot); @@ -1112,8 +1120,6 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, if (rc == PGM_PROTECTION && try_storage_prot_override) rc = access_guest_page_with_key(vcpu->kvm, mode, gpas[idx], data, fragment_len, PAGE_SPO_ACC); - if (rc == PGM_PROTECTION) - prot = PROT_TYPE_KEYC; if (rc) break; len -= fragment_len; @@ -1123,6 +1129,10 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, if (rc > 0) { bool terminate = (mode == GACC_STORE) && (idx > 0); + if (rc == PGM_PROTECTION) + prot = PROT_TYPE_KEYC; + else + prot = PROT_NONE; rc = trans_exc_ending(vcpu, rc, ga, ar, mode, prot, terminate); } out_unlock: diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index b9c944b262c7..ab569faf0df2 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -3324,7 +3324,7 @@ static void aen_host_forward(unsigned long si) if (gaite->count == 0) return; if (gaite->aisb != 0) - set_bit_inv(gaite->aisbo, (unsigned long *)gaite->aisb); + set_bit_inv(gaite->aisbo, phys_to_virt(gaite->aisb)); kvm = kvm_s390_pci_si_to_kvm(aift, si); if (!kvm) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index edfd4bbd0cba..b7ef0b71014d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -505,7 +505,7 @@ int kvm_arch_init(void *opaque) goto out; } - if (kvm_s390_pci_interp_allowed()) { + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) { rc = kvm_s390_pci_init(); if (rc) { pr_err("Unable to allocate AIFT for PCI\n"); @@ -527,7 +527,7 @@ out: void kvm_arch_exit(void) { kvm_s390_gib_destroy(); - if (kvm_s390_pci_interp_allowed()) + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) kvm_s390_pci_exit(); debug_unregister(kvm_s390_dbf); debug_unregister(kvm_s390_dbf_uv); diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index bb8c335d17b9..c50c1645c0ae 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -58,7 +58,7 @@ static int zpci_setup_aipb(u8 nisc) if (!zpci_aipb) return -ENOMEM; - aift->sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC, 0); + aift->sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC, NULL); if (!aift->sbv) { rc = -ENOMEM; goto free_aipb; @@ -71,7 +71,7 @@ static int zpci_setup_aipb(u8 nisc) rc = -ENOMEM; goto free_sbv; } - aift->gait = (struct zpci_gaite *)page_to_phys(page); + aift->gait = (struct zpci_gaite *)page_to_virt(page); zpci_aipb->aipb.faisb = virt_to_phys(aift->sbv->vector); zpci_aipb->aipb.gait = virt_to_phys(aift->gait); @@ -373,7 +373,7 @@ static int kvm_s390_pci_aif_disable(struct zpci_dev *zdev, bool force) gaite->gisc = 0; gaite->aisbo = 0; gaite->gisa = 0; - aift->kzdev[zdev->aisb] = 0; + aift->kzdev[zdev->aisb] = NULL; /* Clear zdev info */ airq_iv_free_bit(aift->sbv, zdev->aisb); airq_iv_release(zdev->aibv); @@ -672,23 +672,31 @@ out: int kvm_s390_pci_init(void) { + zpci_kvm_hook.kvm_register = kvm_s390_pci_register_kvm; + zpci_kvm_hook.kvm_unregister = kvm_s390_pci_unregister_kvm; + + if (!kvm_s390_pci_interp_allowed()) + return 0; + aift = kzalloc(sizeof(struct zpci_aift), GFP_KERNEL); if (!aift) return -ENOMEM; spin_lock_init(&aift->gait_lock); mutex_init(&aift->aift_lock); - zpci_kvm_hook.kvm_register = kvm_s390_pci_register_kvm; - zpci_kvm_hook.kvm_unregister = kvm_s390_pci_unregister_kvm; return 0; } void kvm_s390_pci_exit(void) { - mutex_destroy(&aift->aift_lock); zpci_kvm_hook.kvm_register = NULL; zpci_kvm_hook.kvm_unregister = NULL; + if (!kvm_s390_pci_interp_allowed()) + return; + + mutex_destroy(&aift->aift_lock); + kfree(aift); } diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index 3a3606c3a0fe..486d06ef563f 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -46,9 +46,9 @@ extern struct zpci_aift *aift; static inline struct kvm *kvm_s390_pci_si_to_kvm(struct zpci_aift *aift, unsigned long si) { - if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM) || aift->kzdev == 0 || - aift->kzdev[si] == 0) - return 0; + if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM) || !aift->kzdev || + !aift->kzdev[si]) + return NULL; return aift->kzdev[si]->kvm; }; diff --git a/arch/um/Makefile b/arch/um/Makefile index f2fe63bfd819..f1d4d67157be 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -132,10 +132,18 @@ export LDS_ELF_FORMAT := $(ELF_FORMAT) # The wrappers will select whether using "malloc" or the kernel allocator. LINK_WRAPS = -Wl,--wrap,malloc -Wl,--wrap,free -Wl,--wrap,calloc +# Avoid binutils 2.39+ warnings by marking the stack non-executable and +# ignorning warnings for the kallsyms sections. +LDFLAGS_EXECSTACK = -z noexecstack +ifeq ($(CONFIG_LD_IS_BFD),y) +LDFLAGS_EXECSTACK += $(call ld-option,--no-warn-rwx-segments) +endif + LD_FLAGS_CMDLINE = $(foreach opt,$(KBUILD_LDFLAGS),-Wl,$(opt)) # Used by link-vmlinux.sh which has special support for um link export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE) +export LDFLAGS_vmlinux := $(LDFLAGS_EXECSTACK) # When cleaning we don't include .config, so we don't include # TT or skas makefiles and don't clean skas_ptregs.h. diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c index 7452f70d50d0..746715379f12 100644 --- a/arch/um/kernel/sysrq.c +++ b/arch/um/kernel/sysrq.c @@ -48,7 +48,8 @@ void show_stack(struct task_struct *task, unsigned long *stack, break; if (i && ((i % STACKSLOTS_PER_LINE) == 0)) pr_cont("\n"); - pr_cont(" %08lx", *stack++); + pr_cont(" %08lx", READ_ONCE_NOCHECK(*stack)); + stack++; } printk("%sCall Trace:\n", loglvl); diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index e0de60e503b9..d9e023c78f56 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -33,7 +33,7 @@ #include "um_arch.h" #define DEFAULT_COMMAND_LINE_ROOT "root=98:0" -#define DEFAULT_COMMAND_LINE_CONSOLE "console=tty" +#define DEFAULT_COMMAND_LINE_CONSOLE "console=tty0" /* Changed in add_arg and setup_arch, which run before SMP is started */ static char __initdata command_line[COMMAND_LINE_SIZE] = { 0 }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 2c96c43c313a..aa381ab69a19 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -729,6 +729,7 @@ struct kvm_vcpu_arch { struct fpu_guest guest_fpu; u64 xcr0; + u64 guest_supported_xcr0; struct kvm_pio_request pio; void *pio_data; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 75dcf7a72605..4c1c2c06e96b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -315,7 +315,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; - u64 guest_supported_xcr0; best = kvm_find_cpuid_entry(vcpu, 1); if (best && apic) { @@ -327,10 +326,16 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_apic_set_version(vcpu); } - guest_supported_xcr0 = + vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); - vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0; + /* + * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if + * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't + * supported by the host. + */ + vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 | + XFEATURE_MASK_FPSSE; kvm_update_pv_runtime(vcpu); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index d5ec3a2ed5a4..aacb28c83e43 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4132,6 +4132,9 @@ static int em_xsetbv(struct x86_emulate_ctxt *ctxt) { u32 eax, ecx, edx; + if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSXSAVE)) + return emulate_ud(ctxt); + eax = reg_read(ctxt, VCPU_REGS_RAX); edx = reg_read(ctxt, VCPU_REGS_RDX); ecx = reg_read(ctxt, VCPU_REGS_RCX); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index e418ef3ecfcb..3552e6af3684 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1596,6 +1596,8 @@ static void __rmap_add(struct kvm *kvm, rmap_head = gfn_to_rmap(gfn, sp->role.level, slot); rmap_count = pte_list_add(cache, spte, rmap_head); + if (rmap_count > kvm->stat.max_mmu_rmap_size) + kvm->stat.max_mmu_rmap_size = rmap_count; if (rmap_count > RMAP_RECYCLE_THRESHOLD) { kvm_zap_all_rmap_sptes(kvm, rmap_head); kvm_flush_remote_tlbs_with_address( diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 43a6a7efc6ec..b0c47b41c264 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1011,15 +1011,10 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); -static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.guest_fpu.fpstate->user_xfeatures; -} - #ifdef CONFIG_X86_64 static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) { - return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC; + return vcpu->arch.guest_supported_xcr0 & XFEATURE_MASK_USER_DYNAMIC; } #endif @@ -1042,7 +1037,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ - valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP; + valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; @@ -1070,6 +1065,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) { + /* Note, #UD due to CR4.OSXSAVE=0 has priority over the intercept. */ if (static_call(kvm_x86_get_cpl)(vcpu) != 0 || __kvm_set_xcr(vcpu, kvm_rcx_read(vcpu), kvm_read_edx_eax(vcpu))) { kvm_inject_gp(vcpu, 0); diff --git a/arch/x86/um/shared/sysdep/syscalls_32.h b/arch/x86/um/shared/sysdep/syscalls_32.h index 68fd2cf526fd..f6e9f84397e7 100644 --- a/arch/x86/um/shared/sysdep/syscalls_32.h +++ b/arch/x86/um/shared/sysdep/syscalls_32.h @@ -6,10 +6,9 @@ #include <asm/unistd.h> #include <sysdep/ptrace.h> -typedef long syscall_handler_t(struct pt_regs); +typedef long syscall_handler_t(struct syscall_args); extern syscall_handler_t *sys_call_table[]; #define EXECUTE_SYSCALL(syscall, regs) \ - ((long (*)(struct syscall_args)) \ - (*sys_call_table[syscall]))(SYSCALL_ARGS(®s->regs)) + ((*sys_call_table[syscall]))(SYSCALL_ARGS(®s->regs)) diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c index ac8eee093f9c..66162eafd8e8 100644 --- a/arch/x86/um/tls_32.c +++ b/arch/x86/um/tls_32.c @@ -65,9 +65,6 @@ static int get_free_idx(struct task_struct* task) struct thread_struct *t = &task->thread; int idx; - if (!t->arch.tls_array) - return GDT_ENTRY_TLS_MIN; - for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++) if (!t->arch.tls_array[idx].present) return idx + GDT_ENTRY_TLS_MIN; @@ -240,9 +237,6 @@ static int get_tls_entry(struct task_struct *task, struct user_desc *info, { struct thread_struct *t = &task->thread; - if (!t->arch.tls_array) - goto clear; - if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) return -EINVAL; diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 8c0396fd0e6f..6fbe97c52c99 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -65,7 +65,7 @@ quiet_cmd_vdso = VDSO $@ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' -VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv +VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack GCOV_PROFILE := n # diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 30b15a9a47c4..144bca006463 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -254,17 +254,12 @@ void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns, #else /* CONFIG_BFQ_CGROUP_DEBUG */ -void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq, - blk_opf_t opf) { } void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf) { } void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf) { } void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns, u64 io_start_time_ns, blk_opf_t opf) { } void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { } -void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { } -void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { } void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { } -void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { } #endif /* CONFIG_BFQ_CGROUP_DEBUG */ diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index c740b41fe0a4..7ea427817f7f 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -1925,7 +1925,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, bfqq->service_from_backlogged = 0; bfq_clear_bfqq_softrt_update(bfqq); - bfq_add_bfqq_busy(bfqd, bfqq); + bfq_add_bfqq_busy(bfqq); /* * Expire in-service queue if preemption may be needed for @@ -2419,7 +2419,7 @@ static void bfq_remove_request(struct request_queue *q, bfqq->next_rq = NULL; if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) { - bfq_del_bfqq_busy(bfqd, bfqq, false); + bfq_del_bfqq_busy(bfqq, false); /* * bfqq emptied. In normal operation, when * bfqq is empty, bfqq->entity.service and @@ -3098,7 +3098,7 @@ void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq) */ if (bfq_bfqq_busy(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list) && bfqq != bfqd->in_service_queue) - bfq_del_bfqq_busy(bfqd, bfqq, false); + bfq_del_bfqq_busy(bfqq, false); bfq_reassign_last_bfqq(bfqq, NULL); @@ -3908,7 +3908,7 @@ static bool __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq, */ bfqq->budget_timeout = jiffies; - bfq_del_bfqq_busy(bfqd, bfqq, true); + bfq_del_bfqq_busy(bfqq, true); } else { bfq_requeue_bfqq(bfqd, bfqq, true); /* @@ -5255,9 +5255,7 @@ void bfq_put_queue(struct bfq_queue *bfqq) struct hlist_node *n; struct bfq_group *bfqg = bfqq_group(bfqq); - if (bfqq->bfqd) - bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d", - bfqq, bfqq->ref); + bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d", bfqq, bfqq->ref); bfqq->ref--; if (bfqq->ref) @@ -5321,7 +5319,7 @@ void bfq_put_queue(struct bfq_queue *bfqq) hlist_del_init(&item->woken_list_node); } - if (bfqq->bfqd && bfqq->bfqd->last_completed_rq_bfqq == bfqq) + if (bfqq->bfqd->last_completed_rq_bfqq == bfqq) bfqq->bfqd->last_completed_rq_bfqq = NULL; kmem_cache_free(bfq_pool, bfqq); diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index ad8e513d7e87..64ee618064ba 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -993,20 +993,23 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg); /* ---------------- cgroups-support interface ---------------- */ void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq); -void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq, - blk_opf_t opf); void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf); void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf); void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns, u64 io_start_time_ns, blk_opf_t opf); void bfqg_stats_update_dequeue(struct bfq_group *bfqg); -void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg); -void bfqg_stats_update_idle_time(struct bfq_group *bfqg); void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg); -void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg); void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct bfq_group *bfqg); +#ifdef CONFIG_BFQ_CGROUP_DEBUG +void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq, + blk_opf_t opf); +void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg); +void bfqg_stats_update_idle_time(struct bfq_group *bfqg); +void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg); +#endif + void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg); void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio); void bfq_end_wr_async(struct bfq_data *bfqd); @@ -1077,9 +1080,8 @@ void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq); void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, bool expiration); -void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq, - bool expiration); -void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq); +void bfq_del_bfqq_busy(struct bfq_queue *bfqq, bool expiration); +void bfq_add_bfqq_busy(struct bfq_queue *bfqq); /* --------------- end of interface of B-WF2Q+ ---------------- */ diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index 983413cdefad..8fc3da4c23bb 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -1651,9 +1651,10 @@ void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, * the service tree. As a special case, it can be invoked during an * expiration. */ -void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq, - bool expiration) +void bfq_del_bfqq_busy(struct bfq_queue *bfqq, bool expiration) { + struct bfq_data *bfqd = bfqq->bfqd; + bfq_log_bfqq(bfqd, bfqq, "del from busy"); bfq_clear_bfqq_busy(bfqq); @@ -1674,8 +1675,10 @@ void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq, /* * Called when an inactive queue receives a new request. */ -void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq) +void bfq_add_bfqq_busy(struct bfq_queue *bfqq) { + struct bfq_data *bfqd = bfqq->bfqd; + bfq_log_bfqq(bfqd, bfqq, "add to busy"); bfq_activate_bfqq(bfqd, bfqq); diff --git a/block/bio.c b/block/bio.c index 3d3a2678fea2..7cb7d2ff139b 100644 --- a/block/bio.c +++ b/block/bio.c @@ -760,8 +760,6 @@ EXPORT_SYMBOL(bio_put); static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp) { bio_set_flag(bio, BIO_CLONED); - if (bio_flagged(bio_src, BIO_THROTTLED)) - bio_set_flag(bio, BIO_THROTTLED); bio->bi_ioprio = bio_src->bi_ioprio; bio->bi_iter = bio_src->bi_iter; @@ -1065,9 +1063,6 @@ void __bio_add_page(struct bio *bio, struct page *page, bio->bi_iter.bi_size += len; bio->bi_vcnt++; - - if (!bio_flagged(bio, BIO_WORKINGSET) && unlikely(PageWorkingset(page))) - bio_set_flag(bio, BIO_WORKINGSET); } EXPORT_SYMBOL_GPL(__bio_add_page); @@ -1276,9 +1271,6 @@ out: * fit into the bio, or are requested in @iter, whatever is smaller. If * MM encounters an error pinning the requested pages, it stops. Error * is returned only if 0 pages could be pinned. - * - * It's intended for direct IO, so doesn't do PSI tracking, the caller is - * responsible for setting BIO_WORKINGSET if necessary. */ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { @@ -1294,8 +1286,6 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) ret = __bio_iov_iter_get_pages(bio, iter); } while (!ret && iov_iter_count(iter) && !bio_full(bio, 0)); - /* don't account direct I/O as memory stall */ - bio_clear_flag(bio, BIO_WORKINGSET); return bio->bi_vcnt ? 0 : ret; } EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); @@ -1754,7 +1744,8 @@ static int __init init_bio(void) cpuhp_setup_state_multi(CPUHP_BIO_DEAD, "block/bio:dead", NULL, bio_cpu_dead); - if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS)) + if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, + BIOSET_NEED_BVECS | BIOSET_PERCPU_CACHE)) panic("bio: can't allocate bios\n"); if (bioset_integrity_create(&fs_bio_set, BIO_POOL_SIZE)) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 869af9d72bcf..6a5c849ee061 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -202,19 +202,19 @@ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with - * @q: request_queue the new blkg is associated with + * @disk: gendisk the new blkg is associated with * @gfp_mask: allocation mask to use * * Allocate a new blkg assocating @blkcg and @q. */ -static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, +static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk, gfp_t gfp_mask) { struct blkcg_gq *blkg; int i, cpu; /* alloc and init base part */ - blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node); + blkg = kzalloc_node(sizeof(*blkg), gfp_mask, disk->queue->node); if (!blkg) return NULL; @@ -225,10 +225,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, if (!blkg->iostat_cpu) goto err_free; - if (!blk_get_queue(q)) + if (!blk_get_queue(disk->queue)) goto err_free; - blkg->q = q; + blkg->q = disk->queue; INIT_LIST_HEAD(&blkg->q_node); spin_lock_init(&blkg->async_bio_lock); bio_list_init(&blkg->async_bios); @@ -243,11 +243,11 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; - if (!blkcg_policy_enabled(q, pol)) + if (!blkcg_policy_enabled(disk->queue, pol)) continue; /* alloc per-policy data and attach it to blkg */ - pd = pol->pd_alloc_fn(gfp_mask, q, blkcg); + pd = pol->pd_alloc_fn(gfp_mask, disk->queue, blkcg); if (!pd) goto err_free; @@ -263,45 +263,20 @@ err_free: return NULL; } -struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, - struct request_queue *q, bool update_hint) -{ - struct blkcg_gq *blkg; - - /* - * Hint didn't match. Look up from the radix tree. Note that the - * hint can only be updated under queue_lock as otherwise @blkg - * could have already been removed from blkg_tree. The caller is - * responsible for grabbing queue_lock if @update_hint. - */ - blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id); - if (blkg && blkg->q == q) { - if (update_hint) { - lockdep_assert_held(&q->queue_lock); - rcu_assign_pointer(blkcg->blkg_hint, blkg); - } - return blkg; - } - - return NULL; -} -EXPORT_SYMBOL_GPL(blkg_lookup_slowpath); - /* * If @new_blkg is %NULL, this function tries to allocate a new one as * necessary using %GFP_NOWAIT. @new_blkg is always consumed on return. */ -static struct blkcg_gq *blkg_create(struct blkcg *blkcg, - struct request_queue *q, +static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, struct blkcg_gq *new_blkg) { struct blkcg_gq *blkg; int i, ret; - lockdep_assert_held(&q->queue_lock); + lockdep_assert_held(&disk->queue->queue_lock); /* request_queue is dying, do not create/recreate a blkg */ - if (blk_queue_dying(q)) { + if (blk_queue_dying(disk->queue)) { ret = -ENODEV; goto err_free_blkg; } @@ -314,7 +289,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, /* allocate */ if (!new_blkg) { - new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN); + new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto err_put_css; @@ -324,7 +299,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, /* link parent */ if (blkcg_parent(blkcg)) { - blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false); + blkg->parent = blkg_lookup(blkcg_parent(blkcg), disk->queue); if (WARN_ON_ONCE(!blkg->parent)) { ret = -ENODEV; goto err_put_css; @@ -342,10 +317,10 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, /* insert */ spin_lock(&blkcg->lock); - ret = radix_tree_insert(&blkcg->blkg_tree, q->id, blkg); + ret = radix_tree_insert(&blkcg->blkg_tree, disk->queue->id, blkg); if (likely(!ret)) { hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list); - list_add(&blkg->q_node, &q->blkg_list); + list_add(&blkg->q_node, &disk->queue->blkg_list); for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -374,19 +349,20 @@ err_free_blkg: /** * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest - * @q: request_queue of interest + * @disk: gendisk of interest * - * Lookup blkg for the @blkcg - @q pair. If it doesn't exist, try to + * Lookup blkg for the @blkcg - @disk pair. If it doesn't exist, try to * create one. blkg creation is performed recursively from blkcg_root such * that all non-root blkg's have access to the parent blkg. This function - * should be called under RCU read lock and takes @q->queue_lock. + * should be called under RCU read lock and takes @disk->queue->queue_lock. * * Returns the blkg or the closest blkg if blkg_create() fails as it walks * down from root. */ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q) + struct gendisk *disk) { + struct request_queue *q = disk->queue; struct blkcg_gq *blkg; unsigned long flags; @@ -397,9 +373,13 @@ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, return blkg; spin_lock_irqsave(&q->queue_lock, flags); - blkg = __blkg_lookup(blkcg, q, true); - if (blkg) + blkg = blkg_lookup(blkcg, q); + if (blkg) { + if (blkcg != &blkcg_root && + blkg != rcu_dereference(blkcg->blkg_hint)) + rcu_assign_pointer(blkcg->blkg_hint, blkg); goto found; + } /* * Create blkgs walking down from blkcg_root to @blkcg, so that all @@ -412,7 +392,7 @@ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct blkcg_gq *ret_blkg = q->root_blkg; while (parent) { - blkg = __blkg_lookup(parent, q, false); + blkg = blkg_lookup(parent, q); if (blkg) { /* remember closest blkg */ ret_blkg = blkg; @@ -422,7 +402,7 @@ static struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, parent = blkcg_parent(parent); } - blkg = blkg_create(pos, q, NULL); + blkg = blkg_create(pos, disk, NULL); if (IS_ERR(blkg)) { blkg = ret_blkg; break; @@ -476,14 +456,9 @@ static void blkg_destroy(struct blkcg_gq *blkg) percpu_ref_kill(&blkg->refcnt); } -/** - * blkg_destroy_all - destroy all blkgs associated with a request_queue - * @q: request_queue of interest - * - * Destroy all blkgs associated with @q. - */ -static void blkg_destroy_all(struct request_queue *q) +static void blkg_destroy_all(struct gendisk *disk) { + struct request_queue *q = disk->queue; struct blkcg_gq *blkg, *n; int count = BLKG_DESTROY_BATCH_SIZE; @@ -616,19 +591,6 @@ u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v) } EXPORT_SYMBOL_GPL(__blkg_prfill_u64); -/* Performs queue bypass and policy enabled checks then looks up blkg. */ -static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg, - const struct blkcg_policy *pol, - struct request_queue *q) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - lockdep_assert_held(&q->queue_lock); - - if (!blkcg_policy_enabled(q, pol)) - return ERR_PTR(-EOPNOTSUPP); - return __blkg_lookup(blkcg, q, true /* update_hint */); -} - /** * blkcg_conf_open_bdev - parse and open bdev for per-blkg config update * @inputp: input string pointer @@ -684,6 +646,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, __acquires(rcu) __acquires(&bdev->bd_queue->queue_lock) { struct block_device *bdev; + struct gendisk *disk; struct request_queue *q; struct blkcg_gq *blkg; int ret; @@ -691,8 +654,8 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, bdev = blkcg_conf_open_bdev(&input); if (IS_ERR(bdev)) return PTR_ERR(bdev); - - q = bdev_get_queue(bdev); + disk = bdev->bd_disk; + q = disk->queue; /* * blkcg_deactivate_policy() requires queue to be frozen, we can grab @@ -705,12 +668,12 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, rcu_read_lock(); spin_lock_irq(&q->queue_lock); - blkg = blkg_lookup_check(blkcg, pol, q); - if (IS_ERR(blkg)) { - ret = PTR_ERR(blkg); + if (!blkcg_policy_enabled(q, pol)) { + ret = -EOPNOTSUPP; goto fail_unlock; } + blkg = blkg_lookup(blkcg, q); if (blkg) goto success; @@ -724,7 +687,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, struct blkcg_gq *new_blkg; parent = blkcg_parent(blkcg); - while (parent && !__blkg_lookup(parent, q, false)) { + while (parent && !blkg_lookup(parent, q)) { pos = parent; parent = blkcg_parent(parent); } @@ -733,7 +696,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); - new_blkg = blkg_alloc(pos, q, GFP_KERNEL); + new_blkg = blkg_alloc(pos, disk, GFP_KERNEL); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto fail_exit_queue; @@ -748,17 +711,17 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, rcu_read_lock(); spin_lock_irq(&q->queue_lock); - blkg = blkg_lookup_check(pos, pol, q); - if (IS_ERR(blkg)) { - ret = PTR_ERR(blkg); + if (!blkcg_policy_enabled(q, pol)) { blkg_free(new_blkg); + ret = -EOPNOTSUPP; goto fail_preloaded; } + blkg = blkg_lookup(pos, q); if (blkg) { blkg_free(new_blkg); } else { - blkg = blkg_create(pos, q, new_blkg); + blkg = blkg_create(pos, disk, new_blkg); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); goto fail_preloaded; @@ -915,8 +878,7 @@ static void blkcg_fill_root_iostats(void) class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct block_device *bdev = dev_to_bdev(dev); - struct blkcg_gq *blkg = - blk_queue_root_blkg(bdev_get_queue(bdev)); + struct blkcg_gq *blkg = bdev->bd_disk->queue->root_blkg; struct blkg_iostat tmp; int cpu; unsigned long flags; @@ -1255,25 +1217,16 @@ static int blkcg_css_online(struct cgroup_subsys_state *css) return 0; } -/** - * blkcg_init_queue - initialize blkcg part of request queue - * @q: request_queue to initialize - * - * Called from blk_alloc_queue(). Responsible for initializing blkcg - * part of new request_queue @q. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int blkcg_init_queue(struct request_queue *q) +int blkcg_init_disk(struct gendisk *disk) { + struct request_queue *q = disk->queue; struct blkcg_gq *new_blkg, *blkg; bool preloaded; int ret; INIT_LIST_HEAD(&q->blkg_list); - new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL); + new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL); if (!new_blkg) return -ENOMEM; @@ -1282,7 +1235,7 @@ int blkcg_init_queue(struct request_queue *q) /* Make sure the root blkg exists. */ /* spin_lock_irq can serve as RCU read-side critical section. */ spin_lock_irq(&q->queue_lock); - blkg = blkg_create(&blkcg_root, q, new_blkg); + blkg = blkg_create(&blkcg_root, disk, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; @@ -1291,25 +1244,26 @@ int blkcg_init_queue(struct request_queue *q) if (preloaded) radix_tree_preload_end(); - ret = blk_ioprio_init(q); + ret = blk_ioprio_init(disk); if (ret) goto err_destroy_all; - ret = blk_throtl_init(q); + ret = blk_throtl_init(disk); if (ret) - goto err_destroy_all; + goto err_ioprio_exit; - ret = blk_iolatency_init(q); - if (ret) { - blk_throtl_exit(q); - blk_ioprio_exit(q); - goto err_destroy_all; - } + ret = blk_iolatency_init(disk); + if (ret) + goto err_throtl_exit; return 0; +err_throtl_exit: + blk_throtl_exit(disk); +err_ioprio_exit: + blk_ioprio_exit(disk); err_destroy_all: - blkg_destroy_all(q); + blkg_destroy_all(disk); return ret; err_unlock: spin_unlock_irq(&q->queue_lock); @@ -1318,16 +1272,10 @@ err_unlock: return PTR_ERR(blkg); } -/** - * blkcg_exit_queue - exit and release blkcg part of request_queue - * @q: request_queue being released - * - * Called from blk_exit_queue(). Responsible for exiting blkcg part. - */ -void blkcg_exit_queue(struct request_queue *q) +void blkcg_exit_disk(struct gendisk *disk) { - blkg_destroy_all(q); - blk_throtl_exit(q); + blkg_destroy_all(disk); + blk_throtl_exit(disk); } static void blkcg_bind(struct cgroup_subsys_state *root_css) @@ -1836,13 +1784,13 @@ out: /** * blkcg_schedule_throttle - this task needs to check for throttling - * @q: the request queue IO was submitted on + * @gendisk: disk to throttle * @use_memdelay: do we charge this to memory delay for PSI * * This is called by the IO controller when we know there's delay accumulated * for the blkg for this task. We do not pass the blkg because there are places * we call this that may not have that information, the swapping code for - * instance will only have a request_queue at that point. This set's the + * instance will only have a block_device at that point. This set's the * notify_resume for the task to check and see if it requires throttling before * returning to user space. * @@ -1851,8 +1799,10 @@ out: * throttle once. If the task needs to be throttled again it'll need to be * re-set at the next time we see the task. */ -void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) +void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay) { + struct request_queue *q = disk->queue; + if (unlikely(current->flags & PF_KTHREAD)) return; @@ -1902,8 +1852,7 @@ static inline struct blkcg_gq *blkg_tryget_closest(struct bio *bio, struct blkcg_gq *blkg, *ret_blkg = NULL; rcu_read_lock(); - blkg = blkg_lookup_create(css_to_blkcg(css), - bdev_get_queue(bio->bi_bdev)); + blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_bdev->bd_disk); while (blkg) { if (blkg_tryget(blkg)) { ret_blkg = blkg; diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index d2724d1dd7c9..aa2b286bc825 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -178,10 +178,8 @@ struct blkcg_policy { extern struct blkcg blkcg_root; extern bool blkcg_debug_stats; -struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, - struct request_queue *q, bool update_hint); -int blkcg_init_queue(struct request_queue *q); -void blkcg_exit_queue(struct request_queue *q); +int blkcg_init_disk(struct gendisk *disk); +void blkcg_exit_disk(struct gendisk *disk); /* Blkio controller policy registration */ int blkcg_policy_register(struct blkcg_policy *pol); @@ -227,22 +225,21 @@ static inline bool bio_issue_as_root_blkg(struct bio *bio) } /** - * __blkg_lookup - internal version of blkg_lookup() + * blkg_lookup - lookup blkg for the specified blkcg - q pair * @blkcg: blkcg of interest * @q: request_queue of interest - * @update_hint: whether to update lookup hint with the result or not * - * This is internal version and shouldn't be used by policy - * implementations. Looks up blkgs for the @blkcg - @q pair regardless of - * @q's bypass state. If @update_hint is %true, the caller should be - * holding @q->queue_lock and lookup hint is updated on success. + * Lookup blkg for the @blkcg - @q pair. + + * Must be called in a RCU critical section. */ -static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, - struct request_queue *q, - bool update_hint) +static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, + struct request_queue *q) { struct blkcg_gq *blkg; + WARN_ON_ONCE(!rcu_read_lock_held()); + if (blkcg == &blkcg_root) return q->root_blkg; @@ -250,33 +247,10 @@ static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, if (blkg && blkg->q == q) return blkg; - return blkg_lookup_slowpath(blkcg, q, update_hint); -} - -/** - * blkg_lookup - lookup blkg for the specified blkcg - q pair - * @blkcg: blkcg of interest - * @q: request_queue of interest - * - * Lookup blkg for the @blkcg - @q pair. This function should be called - * under RCU read lock. - */ -static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, - struct request_queue *q) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return __blkg_lookup(blkcg, q, false); -} - -/** - * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair - * @q: request_queue of interest - * - * Lookup blkg for @q at the root level. See also blkg_lookup(). - */ -static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) -{ - return q->root_blkg; + blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id); + if (blkg && blkg->q != q) + blkg = NULL; + return blkg; } /** @@ -373,8 +347,8 @@ static inline void blkg_put(struct blkcg_gq *blkg) */ #define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ - if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ - (p_blkg)->q, false))) + if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css), \ + (p_blkg)->q))) /** * blkg_for_each_descendant_post - post-order walk of a blkg's descendants @@ -388,8 +362,8 @@ static inline void blkg_put(struct blkcg_gq *blkg) */ #define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ - if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ - (p_blkg)->q, false))) + if (((d_blkg) = blkg_lookup(css_to_blkcg(pos_css), \ + (p_blkg)->q))) bool __blkcg_punt_bio_submit(struct bio *bio); @@ -507,10 +481,8 @@ struct blkcg { }; static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } -static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) -{ return NULL; } -static inline int blkcg_init_queue(struct request_queue *q) { return 0; } -static inline void blkcg_exit_queue(struct request_queue *q) { } +static inline int blkcg_init_disk(struct gendisk *disk) { return 0; } +static inline void blkcg_exit_disk(struct gendisk *disk) { } static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } static inline int blkcg_activate_policy(struct request_queue *q, diff --git a/block/blk-core.c b/block/blk-core.c index 651057c4146b..17667159482e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -37,7 +37,6 @@ #include <linux/t10-pi.h> #include <linux/debugfs.h> #include <linux/bpf.h> -#include <linux/psi.h> #include <linux/part_stat.h> #include <linux/sched/sysctl.h> #include <linux/blk-crypto.h> @@ -487,18 +486,15 @@ static int __init fail_make_request_debugfs(void) late_initcall(fail_make_request_debugfs); #endif /* CONFIG_FAIL_MAKE_REQUEST */ -static inline bool bio_check_ro(struct bio *bio) +static inline void bio_check_ro(struct bio *bio) { if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) { if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) - return false; + return; pr_warn("Trying to write to read-only block-device %pg\n", bio->bi_bdev); /* Older lvm-tools actually trigger this */ - return false; } - - return false; } static noinline int should_fail_bio(struct bio *bio) @@ -717,13 +713,12 @@ void submit_bio_noacct(struct bio *bio) * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue does not support NOWAIT. */ - if ((bio->bi_opf & REQ_NOWAIT) && !blk_queue_nowait(q)) + if ((bio->bi_opf & REQ_NOWAIT) && !bdev_nowait(bdev)) goto not_supported; if (should_fail_bio(bio)) goto end_io; - if (unlikely(bio_check_ro(bio))) - goto end_io; + bio_check_ro(bio); if (!bio_flagged(bio, BIO_REMAPPED)) { if (unlikely(bio_check_eod(bio))) goto end_io; @@ -814,7 +809,7 @@ EXPORT_SYMBOL(submit_bio_noacct); * * The success/failure status of the request, along with notification of * completion, is delivered asynchronously through the ->bi_end_io() callback - * in @bio. The bio must NOT be touched by thecaller until ->bi_end_io() has + * in @bio. The bio must NOT be touched by the caller until ->bi_end_io() has * been called. */ void submit_bio(struct bio *bio) @@ -829,22 +824,6 @@ void submit_bio(struct bio *bio) count_vm_events(PGPGOUT, bio_sectors(bio)); } - /* - * If we're reading data that is part of the userspace workingset, count - * submission time as memory stall. When the device is congested, or - * the submitting cgroup IO-throttled, submission can be a significant - * part of overall IO time. - */ - if (unlikely(bio_op(bio) == REQ_OP_READ && - bio_flagged(bio, BIO_WORKINGSET))) { - unsigned long pflags; - - psi_memstall_enter(&pflags); - submit_bio_noacct(bio); - psi_memstall_leave(&pflags); - return; - } - submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); @@ -871,6 +850,12 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) !test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) return 0; + /* + * As the requests that require a zone lock are not plugged in the + * first place, directly accessing the plug instead of using + * blk_mq_plug() should not have any consequences during flushing for + * zoned devices. + */ blk_flush_plug(current->plug, false); if (bio_queue_enter(bio)) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 7936e5f5821c..495396425bad 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -664,17 +664,13 @@ static struct ioc *q_to_ioc(struct request_queue *q) return rqos_to_ioc(rq_qos_id(q, RQ_QOS_COST)); } -static const char *q_name(struct request_queue *q) -{ - if (blk_queue_registered(q)) - return kobject_name(q->kobj.parent); - else - return "<unknown>"; -} - static const char __maybe_unused *ioc_name(struct ioc *ioc) { - return q_name(ioc->rqos.q); + struct gendisk *disk = ioc->rqos.q->disk; + + if (!disk) + return "<unknown>"; + return disk->disk_name; } static struct ioc_gq *pd_to_iocg(struct blkg_policy_data *pd) @@ -1430,7 +1426,7 @@ static int iocg_wake_fn(struct wait_queue_entry *wq_entry, unsigned mode, int flags, void *key) { struct iocg_wait *wait = container_of(wq_entry, struct iocg_wait, wait); - struct iocg_wake_ctx *ctx = (struct iocg_wake_ctx *)key; + struct iocg_wake_ctx *ctx = key; u64 cost = abs_cost_to_cost(wait->abs_cost, ctx->hw_inuse); ctx->vbudget -= cost; @@ -2640,7 +2636,7 @@ retry_lock: if (use_debt) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) - blkcg_schedule_throttle(rqos->q, + blkcg_schedule_throttle(rqos->q->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); iocg_unlock(iocg, ioc_locked, &flags); return; @@ -2741,7 +2737,7 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, if (likely(!list_empty(&iocg->active_list))) { iocg_incur_debt(iocg, abs_cost, &now); if (iocg_kick_delay(iocg, &now)) - blkcg_schedule_throttle(rqos->q, + blkcg_schedule_throttle(rqos->q->disk, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); } else { iocg_commit_bio(iocg, bio, abs_cost, cost); @@ -2832,8 +2828,9 @@ static struct rq_qos_ops ioc_rqos_ops = { .exit = ioc_rqos_exit, }; -static int blk_iocost_init(struct request_queue *q) +static int blk_iocost_init(struct gendisk *disk) { + struct request_queue *q = disk->queue; struct ioc *ioc; struct rq_qos *rqos; int i, cpu, ret; @@ -3170,6 +3167,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, size_t nbytes, loff_t off) { struct block_device *bdev; + struct gendisk *disk; struct ioc *ioc; u32 qos[NR_QOS_PARAMS]; bool enable, user; @@ -3180,12 +3178,13 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, if (IS_ERR(bdev)) return PTR_ERR(bdev); - ioc = q_to_ioc(bdev_get_queue(bdev)); + disk = bdev->bd_disk; + ioc = q_to_ioc(disk->queue); if (!ioc) { - ret = blk_iocost_init(bdev_get_queue(bdev)); + ret = blk_iocost_init(disk); if (ret) goto err; - ioc = q_to_ioc(bdev_get_queue(bdev)); + ioc = q_to_ioc(disk->queue); } spin_lock_irq(&ioc->lock); @@ -3262,11 +3261,11 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, spin_lock_irq(&ioc->lock); if (enable) { - blk_stat_enable_accounting(ioc->rqos.q); - blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, ioc->rqos.q); + blk_stat_enable_accounting(disk->queue); + blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = true; } else { - blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, ioc->rqos.q); + blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); ioc->enabled = false; } @@ -3349,7 +3348,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, ioc = q_to_ioc(bdev_get_queue(bdev)); if (!ioc) { - ret = blk_iocost_init(bdev_get_queue(bdev)); + ret = blk_iocost_init(bdev->bd_disk); if (ret) goto err; ioc = q_to_ioc(bdev_get_queue(bdev)); diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index e285152345a2..571fa95aafe9 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -292,7 +292,7 @@ static void __blkcg_iolatency_throttle(struct rq_qos *rqos, unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay); if (use_delay) - blkcg_schedule_throttle(rqos->q, use_memdelay); + blkcg_schedule_throttle(rqos->q->disk, use_memdelay); /* * To avoid priority inversions we want to just take a slot if we are @@ -756,8 +756,9 @@ static void blkiolatency_enable_work_fn(struct work_struct *work) } } -int blk_iolatency_init(struct request_queue *q) +int blk_iolatency_init(struct gendisk *disk) { + struct request_queue *q = disk->queue; struct blk_iolatency *blkiolat; struct rq_qos *rqos; int ret; diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c index c00060a02c6e..8bb6b8eba4ce 100644 --- a/block/blk-ioprio.c +++ b/block/blk-ioprio.c @@ -202,14 +202,14 @@ void blkcg_set_ioprio(struct bio *bio) bio->bi_ioprio = prio; } -void blk_ioprio_exit(struct request_queue *q) +void blk_ioprio_exit(struct gendisk *disk) { - blkcg_deactivate_policy(q, &ioprio_policy); + blkcg_deactivate_policy(disk->queue, &ioprio_policy); } -int blk_ioprio_init(struct request_queue *q) +int blk_ioprio_init(struct gendisk *disk) { - return blkcg_activate_policy(q, &ioprio_policy); + return blkcg_activate_policy(disk->queue, &ioprio_policy); } static int __init ioprio_init(void) diff --git a/block/blk-ioprio.h b/block/blk-ioprio.h index 5a1eb550e178..b6afb8e80de0 100644 --- a/block/blk-ioprio.h +++ b/block/blk-ioprio.h @@ -9,15 +9,15 @@ struct request_queue; struct bio; #ifdef CONFIG_BLK_CGROUP_IOPRIO -int blk_ioprio_init(struct request_queue *q); -void blk_ioprio_exit(struct request_queue *q); +int blk_ioprio_init(struct gendisk *disk); +void blk_ioprio_exit(struct gendisk *disk); void blkcg_set_ioprio(struct bio *bio); #else -static inline int blk_ioprio_init(struct request_queue *q) +static inline int blk_ioprio_init(struct gendisk *disk) { return 0; } -static inline void blk_ioprio_exit(struct request_queue *q) +static inline void blk_ioprio_exit(struct gendisk *disk) { } static inline void blkcg_set_ioprio(struct bio *bio) diff --git a/block/blk-map.c b/block/blk-map.c index 7196a6b64c80..7693f8e3c454 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -158,7 +158,7 @@ static int bio_copy_user_iov(struct request *rq, struct rq_map_data *map_data, bio_init(bio, NULL, bio->bi_inline_vecs, nr_pages, req_op(rq)); if (map_data) { - nr_pages = 1 << map_data->page_order; + nr_pages = 1U << map_data->page_order; i = map_data->offset / PAGE_SIZE; } while (len) { @@ -231,6 +231,16 @@ out_bmd: return ret; } +static void bio_map_put(struct bio *bio) +{ + if (bio->bi_opf & REQ_ALLOC_CACHE) { + bio_put(bio); + } else { + bio_uninit(bio); + kfree(bio); + } +} + static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, gfp_t gfp_mask) { @@ -243,18 +253,34 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, if (!iov_iter_count(iter)) return -EINVAL; - bio = bio_kmalloc(nr_vecs, gfp_mask); - if (!bio) - return -ENOMEM; - bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, req_op(rq)); + if (rq->cmd_flags & REQ_POLLED) { + blk_opf_t opf = rq->cmd_flags | REQ_ALLOC_CACHE; + + bio = bio_alloc_bioset(NULL, nr_vecs, opf, gfp_mask, + &fs_bio_set); + if (!bio) + return -ENOMEM; + } else { + bio = bio_kmalloc(nr_vecs, gfp_mask); + if (!bio) + return -ENOMEM; + bio_init(bio, NULL, bio->bi_inline_vecs, nr_vecs, req_op(rq)); + } while (iov_iter_count(iter)) { - struct page **pages; + struct page **pages, *stack_pages[UIO_FASTIOV]; ssize_t bytes; - size_t offs, added = 0; + size_t offs; int npages; - bytes = iov_iter_get_pages_alloc2(iter, &pages, LONG_MAX, &offs); + if (nr_vecs <= ARRAY_SIZE(stack_pages)) { + pages = stack_pages; + bytes = iov_iter_get_pages2(iter, pages, LONG_MAX, + nr_vecs, &offs); + } else { + bytes = iov_iter_get_pages_alloc2(iter, &pages, + LONG_MAX, &offs); + } if (unlikely(bytes <= 0)) { ret = bytes ? bytes : -EFAULT; goto out_unmap; @@ -280,7 +306,6 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, break; } - added += n; bytes -= n; offs = 0; } @@ -290,7 +315,8 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, */ while (j < npages) put_page(pages[j++]); - kvfree(pages); + if (pages != stack_pages) + kvfree(pages); /* couldn't stuff something into bio? */ if (bytes) { iov_iter_revert(iter, bytes); @@ -305,8 +331,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, out_unmap: bio_release_pages(bio, false); - bio_uninit(bio); - kfree(bio); + bio_map_put(bio); return ret; } @@ -611,8 +636,7 @@ int blk_rq_unmap_user(struct bio *bio) next_bio = bio; bio = bio->bi_next; - bio_uninit(next_bio); - kfree(next_bio); + bio_map_put(next_bio); } return ret; diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index 3db84d3197f1..9c2fce1a7b50 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -32,7 +32,7 @@ static int get_first_sibling(unsigned int cpu) return cpu; } -int blk_mq_map_queues(struct blk_mq_queue_map *qmap) +void blk_mq_map_queues(struct blk_mq_queue_map *qmap) { unsigned int *map = qmap->mq_map; unsigned int nr_queues = qmap->nr_queues; @@ -70,8 +70,6 @@ int blk_mq_map_queues(struct blk_mq_queue_map *qmap) map[cpu] = map[first_sibling]; } } - - return 0; } EXPORT_SYMBOL_GPL(blk_mq_map_queues); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index dee789f2f98f..bd942341b638 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -807,8 +807,6 @@ static const char *rq_qos_id_to_name(enum rq_qos_id id) return "latency"; case RQ_QOS_COST: return "cost"; - case RQ_QOS_IOPRIO: - return "ioprio"; } return "unknown"; } diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c index b595a94c4d16..a90b88fd1332 100644 --- a/block/blk-mq-pci.c +++ b/block/blk-mq-pci.c @@ -23,8 +23,8 @@ * that maps a queue to the CPUs that have irq affinity for the corresponding * vector. */ -int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, - int offset) +void blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, + int offset) { const struct cpumask *mask; unsigned int queue, cpu; @@ -38,11 +38,10 @@ int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, qmap->mq_map[cpu] = qmap->queue_offset + queue; } - return 0; + return; fallback: WARN_ON_ONCE(qmap->nr_queues > 1); blk_mq_clear_mq_map(qmap); - return 0; } EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues); diff --git a/block/blk-mq-rdma.c b/block/blk-mq-rdma.c index 14f968e58b8f..29c1f4d6eb04 100644 --- a/block/blk-mq-rdma.c +++ b/block/blk-mq-rdma.c @@ -21,7 +21,7 @@ * @set->nr_hw_queues, or @dev does not provide an affinity mask for a * vector, we fallback to the naive mapping. */ -int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, +void blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, struct ib_device *dev, int first_vec) { const struct cpumask *mask; @@ -36,9 +36,9 @@ int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, map->mq_map[cpu] = map->queue_offset + queue; } - return 0; + return; fallback: - return blk_mq_map_queues(map); + blk_mq_map_queues(map); } EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 8e3b36d1cb57..9eb968e14d31 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -196,7 +196,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) * other allocations on previous queue won't be starved. */ if (bt != bt_prev) - sbitmap_queue_wake_up(bt_prev); + sbitmap_queue_wake_up(bt_prev, 1); ws = bt_wait_ptr(bt, data->hctx); } while (1); diff --git a/block/blk-mq-virtio.c b/block/blk-mq-virtio.c index 7b8a42c35102..6589f076a096 100644 --- a/block/blk-mq-virtio.c +++ b/block/blk-mq-virtio.c @@ -21,7 +21,7 @@ * that maps a queue to the CPUs that have irq affinity for the corresponding * vector. */ -int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, +void blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, struct virtio_device *vdev, int first_vec) { const struct cpumask *mask; @@ -39,8 +39,9 @@ int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, qmap->mq_map[cpu] = qmap->queue_offset + queue; } - return 0; + return; + fallback: - return blk_mq_map_queues(qmap); + blk_mq_map_queues(qmap); } EXPORT_SYMBOL_GPL(blk_mq_virtio_map_queues); diff --git a/block/blk-mq.c b/block/blk-mq.c index 0df20184cc3e..83492d942348 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1093,10 +1093,12 @@ bool blk_mq_complete_request_remote(struct request *rq) WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); /* - * For a polled request, always complete locally, it's pointless - * to redirect the completion. + * For request which hctx has only one ctx mapping, + * or a polled request, always complete locally, + * it's pointless to redirect the completion. */ - if (rq->cmd_flags & REQ_POLLED) + if (rq->mq_hctx->nr_ctx == 1 || + rq->cmd_flags & REQ_POLLED) return false; if (blk_mq_complete_need_ipi(rq)) { @@ -1213,6 +1215,12 @@ void blk_execute_rq_nowait(struct request *rq, bool at_head) WARN_ON(!blk_rq_is_passthrough(rq)); blk_account_io_start(rq); + + /* + * As plugging can be enabled for passthrough requests on a zoned + * device, directly accessing the plug instead of using blk_mq_plug() + * should not have any consequences. + */ if (current->plug) blk_add_rq_to_plug(current->plug, rq); else @@ -1993,7 +2001,7 @@ out: if (!needs_restart || (no_tag && list_empty_careful(&hctx->dispatch_wait.entry))) blk_mq_run_hw_queue(hctx, true); - else if (needs_restart && needs_resource) + else if (needs_resource) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY); blk_mq_update_dispatch_busy(hctx, true); @@ -4192,7 +4200,7 @@ static int blk_mq_alloc_set_map_and_rqs(struct blk_mq_tag_set *set) return 0; } -static int blk_mq_update_queue_map(struct blk_mq_tag_set *set) +static void blk_mq_update_queue_map(struct blk_mq_tag_set *set) { /* * blk_mq_map_queues() and multiple .map_queues() implementations @@ -4222,10 +4230,10 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set) for (i = 0; i < set->nr_maps; i++) blk_mq_clear_mq_map(&set->map[i]); - return set->ops->map_queues(set); + set->ops->map_queues(set); } else { BUG_ON(set->nr_maps > 1); - return blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); + blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); } } @@ -4324,9 +4332,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) set->map[i].nr_queues = is_kdump_kernel() ? 1 : set->nr_hw_queues; } - ret = blk_mq_update_queue_map(set); - if (ret) - goto out_free_mq_map; + blk_mq_update_queue_map(set); ret = blk_mq_alloc_set_map_and_rqs(set); if (ret) @@ -4474,14 +4480,14 @@ static bool blk_mq_elv_switch_none(struct list_head *head, list_add(&qe->node, head); /* - * After elevator_switch_mq, the previous elevator_queue will be + * After elevator_switch, the previous elevator_queue will be * released by elevator_release. The reference of the io scheduler * module get by elevator_get will also be put. So we need to get * a reference of the io scheduler module here to prevent it to be * removed. */ __module_get(qe->type->elevator_owner); - elevator_switch_mq(q, NULL); + elevator_switch(q, NULL); mutex_unlock(&q->sysfs_lock); return true; @@ -4513,7 +4519,7 @@ static void blk_mq_elv_switch_back(struct list_head *head, kfree(qe); mutex_lock(&q->sysfs_lock); - elevator_switch_mq(q, t); + elevator_switch(q, t); mutex_unlock(&q->sysfs_lock); } diff --git a/block/blk-mq.h b/block/blk-mq.h index 8ca453ac243d..0b2870839cdd 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -312,7 +312,8 @@ static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) static inline struct blk_plug *blk_mq_plug( struct bio *bio) { /* Zoned block device write operation case: do not plug the BIO */ - if (bdev_is_zoned(bio->bi_bdev) && op_is_write(bio_op(bio))) + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + bdev_op_is_zoned_write(bio->bi_bdev, bio_op(bio))) return NULL; /* diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 08b856570ad1..1ef1f7d4bc3c 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -17,7 +17,6 @@ enum rq_qos_id { RQ_QOS_WBT, RQ_QOS_LATENCY, RQ_QOS_COST, - RQ_QOS_IOPRIO, }; struct rq_wait { diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index e1f009aba6fd..e71b3b43927c 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -844,7 +844,7 @@ int blk_register_queue(struct gendisk *disk) blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); wbt_enable_default(q); - blk_throtl_register_queue(q); + blk_throtl_register(disk); /* Now everything is ready and send out KOBJ_ADD uevent */ kobject_uevent(&q->kobj, KOBJ_ADD); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 9f5fe62afff9..847721dc2b2b 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -329,8 +329,8 @@ static struct bio *throtl_pop_queued(struct list_head *queued, /* init a service_queue, assumes the caller zeroed it */ static void throtl_service_queue_init(struct throtl_service_queue *sq) { - INIT_LIST_HEAD(&sq->queued[0]); - INIT_LIST_HEAD(&sq->queued[1]); + INIT_LIST_HEAD(&sq->queued[READ]); + INIT_LIST_HEAD(&sq->queued[WRITE]); sq->pending_tree = RB_ROOT_CACHED; timer_setup(&sq->pending_timer, throtl_pending_timer_fn, 0); } @@ -420,24 +420,17 @@ static void tg_update_has_rules(struct throtl_grp *tg) struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq); struct throtl_data *td = tg->td; int rw; - int has_iops_limit = 0; for (rw = READ; rw <= WRITE; rw++) { - unsigned int iops_limit = tg_iops_limit(tg, rw); - - tg->has_rules[rw] = (parent_tg && parent_tg->has_rules[rw]) || + tg->has_rules_iops[rw] = + (parent_tg && parent_tg->has_rules_iops[rw]) || (td->limit_valid[td->limit_index] && - (tg_bps_limit(tg, rw) != U64_MAX || - iops_limit != UINT_MAX)); - - if (iops_limit != UINT_MAX) - has_iops_limit = 1; + tg_iops_limit(tg, rw) != UINT_MAX); + tg->has_rules_bps[rw] = + (parent_tg && parent_tg->has_rules_bps[rw]) || + (td->limit_valid[td->limit_index] && + (tg_bps_limit(tg, rw) != U64_MAX)); } - - if (has_iops_limit) - tg->flags |= THROTL_TG_HAS_IOPS_LIMIT; - else - tg->flags &= ~THROTL_TG_HAS_IOPS_LIMIT; } static void throtl_pd_online(struct blkg_policy_data *pd) @@ -520,7 +513,6 @@ static void throtl_rb_erase(struct rb_node *n, { rb_erase_cached(n, &parent_sq->pending_tree); RB_CLEAR_NODE(n); - --parent_sq->nr_pending; } static void update_min_dispatch_time(struct throtl_service_queue *parent_sq) @@ -572,7 +564,11 @@ static void throtl_enqueue_tg(struct throtl_grp *tg) static void throtl_dequeue_tg(struct throtl_grp *tg) { if (tg->flags & THROTL_TG_PENDING) { - throtl_rb_erase(&tg->rb_node, tg->service_queue.parent_sq); + struct throtl_service_queue *parent_sq = + tg->service_queue.parent_sq; + + throtl_rb_erase(&tg->rb_node, parent_sq); + --parent_sq->nr_pending; tg->flags &= ~THROTL_TG_PENDING; } } @@ -639,6 +635,8 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg, { tg->bytes_disp[rw] = 0; tg->io_disp[rw] = 0; + tg->carryover_bytes[rw] = 0; + tg->carryover_ios[rw] = 0; /* * Previous slice has expired. We must have trimmed it after last @@ -656,12 +654,17 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg, tg->slice_end[rw], jiffies); } -static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw) +static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw, + bool clear_carryover) { tg->bytes_disp[rw] = 0; tg->io_disp[rw] = 0; tg->slice_start[rw] = jiffies; tg->slice_end[rw] = jiffies + tg->td->throtl_slice; + if (clear_carryover) { + tg->carryover_bytes[rw] = 0; + tg->carryover_ios[rw] = 0; + } throtl_log(&tg->service_queue, "[%c] new slice start=%lu end=%lu jiffies=%lu", @@ -754,33 +757,20 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) tg->slice_start[rw], tg->slice_end[rw], jiffies); } -static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio, - u32 iops_limit, unsigned long *wait) +static unsigned int calculate_io_allowed(u32 iops_limit, + unsigned long jiffy_elapsed) { - bool rw = bio_data_dir(bio); unsigned int io_allowed; - unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; u64 tmp; - if (iops_limit == UINT_MAX) { - if (wait) - *wait = 0; - return true; - } - - jiffy_elapsed = jiffies - tg->slice_start[rw]; - - /* Round up to the next throttle slice, wait time must be nonzero */ - jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice); - /* - * jiffy_elapsed_rnd should not be a big value as minimum iops can be + * jiffy_elapsed should not be a big value as minimum iops can be * 1 then at max jiffy elapsed should be equivalent of 1 second as we * will allow dispatch after 1 second and after that slice should * have been trimmed. */ - tmp = (u64)iops_limit * jiffy_elapsed_rnd; + tmp = (u64)iops_limit * jiffy_elapsed; do_div(tmp, HZ); if (tmp > UINT_MAX) @@ -788,6 +778,68 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio, else io_allowed = tmp; + return io_allowed; +} + +static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed) +{ + return mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed, (u64)HZ); +} + +static void __tg_update_carryover(struct throtl_grp *tg, bool rw) +{ + unsigned long jiffy_elapsed = jiffies - tg->slice_start[rw]; + u64 bps_limit = tg_bps_limit(tg, rw); + u32 iops_limit = tg_iops_limit(tg, rw); + + /* + * If config is updated while bios are still throttled, calculate and + * accumulate how many bytes/ios are waited across changes. And + * carryover_bytes/ios will be used to calculate new wait time under new + * configuration. + */ + if (bps_limit != U64_MAX) + tg->carryover_bytes[rw] += + calculate_bytes_allowed(bps_limit, jiffy_elapsed) - + tg->bytes_disp[rw]; + if (iops_limit != UINT_MAX) + tg->carryover_ios[rw] += + calculate_io_allowed(iops_limit, jiffy_elapsed) - + tg->io_disp[rw]; +} + +static void tg_update_carryover(struct throtl_grp *tg) +{ + if (tg->service_queue.nr_queued[READ]) + __tg_update_carryover(tg, READ); + if (tg->service_queue.nr_queued[WRITE]) + __tg_update_carryover(tg, WRITE); + + /* see comments in struct throtl_grp for meaning of these fields. */ + throtl_log(&tg->service_queue, "%s: %llu %llu %u %u\n", __func__, + tg->carryover_bytes[READ], tg->carryover_bytes[WRITE], + tg->carryover_ios[READ], tg->carryover_ios[WRITE]); +} + +static bool tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio, + u32 iops_limit, unsigned long *wait) +{ + bool rw = bio_data_dir(bio); + unsigned int io_allowed; + unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; + + if (iops_limit == UINT_MAX) { + if (wait) + *wait = 0; + return true; + } + + jiffy_elapsed = jiffies - tg->slice_start[rw]; + + /* Round up to the next throttle slice, wait time must be nonzero */ + jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice); + io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed_rnd) + + tg->carryover_ios[rw]; if (tg->io_disp[rw] + 1 <= io_allowed) { if (wait) *wait = 0; @@ -802,16 +854,16 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio, return false; } -static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio, - u64 bps_limit, unsigned long *wait) +static bool tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio, + u64 bps_limit, unsigned long *wait) { bool rw = bio_data_dir(bio); - u64 bytes_allowed, extra_bytes, tmp; + u64 bytes_allowed, extra_bytes; unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; unsigned int bio_size = throtl_bio_data_size(bio); /* no need to throttle if this bio's bytes have been accounted */ - if (bps_limit == U64_MAX || bio_flagged(bio, BIO_THROTTLED)) { + if (bps_limit == U64_MAX || bio_flagged(bio, BIO_BPS_THROTTLED)) { if (wait) *wait = 0; return true; @@ -824,11 +876,8 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio, jiffy_elapsed_rnd = tg->td->throtl_slice; jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice); - - tmp = bps_limit * jiffy_elapsed_rnd; - do_div(tmp, HZ); - bytes_allowed = tmp; - + bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed_rnd) + + tg->carryover_bytes[rw]; if (tg->bytes_disp[rw] + bio_size <= bytes_allowed) { if (wait) *wait = 0; @@ -889,7 +938,7 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, * slice and it should be extended instead. */ if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw])) - throtl_start_new_slice(tg, rw); + throtl_start_new_slice(tg, rw, true); else { if (time_before(tg->slice_end[rw], jiffies + tg->td->throtl_slice)) @@ -897,8 +946,8 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, jiffies + tg->td->throtl_slice); } - if (tg_with_in_bps_limit(tg, bio, bps_limit, &bps_wait) && - tg_with_in_iops_limit(tg, bio, iops_limit, &iops_wait)) { + if (tg_within_bps_limit(tg, bio, bps_limit, &bps_wait) && + tg_within_iops_limit(tg, bio, iops_limit, &iops_wait)) { if (wait) *wait = 0; return true; @@ -921,22 +970,13 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) unsigned int bio_size = throtl_bio_data_size(bio); /* Charge the bio to the group */ - if (!bio_flagged(bio, BIO_THROTTLED)) { + if (!bio_flagged(bio, BIO_BPS_THROTTLED)) { tg->bytes_disp[rw] += bio_size; tg->last_bytes_disp[rw] += bio_size; } tg->io_disp[rw]++; tg->last_io_disp[rw]++; - - /* - * BIO_THROTTLED is used to prevent the same bio to be throttled - * more than once as a throttled bio will go through blk-throtl the - * second time when it eventually gets issued. Set it when a bio - * is being charged to a tg. - */ - if (!bio_flagged(bio, BIO_THROTTLED)) - bio_set_flag(bio, BIO_THROTTLED); } /** @@ -990,9 +1030,9 @@ static void tg_update_disptime(struct throtl_grp *tg) disptime = jiffies + min_wait; /* Update dispatch time */ - throtl_dequeue_tg(tg); + throtl_rb_erase(&tg->rb_node, tg->service_queue.parent_sq); tg->disptime = disptime; - throtl_enqueue_tg(tg); + tg_service_queue_add(tg); /* see throtl_add_bio_tg() */ tg->flags &= ~THROTL_TG_WAS_EMPTY; @@ -1026,6 +1066,7 @@ static void tg_dispatch_one_bio(struct throtl_grp *tg, bool rw) sq->nr_queued[rw]--; throtl_charge_bio(tg, bio); + bio_set_flag(bio, BIO_BPS_THROTTLED); /* * If our parent is another tg, we just need to transfer @bio to @@ -1101,13 +1142,13 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq) if (time_before(jiffies, tg->disptime)) break; - throtl_dequeue_tg(tg); - nr_disp += throtl_dispatch_tg(tg); sq = &tg->service_queue; - if (sq->nr_queued[0] || sq->nr_queued[1]) + if (sq->nr_queued[READ] || sq->nr_queued[WRITE]) tg_update_disptime(tg); + else + throtl_dequeue_tg(tg); if (nr_disp >= THROTL_QUANTUM) break; @@ -1321,8 +1362,8 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global) * that a group's limit are dropped suddenly and we don't want to * account recently dispatched IO with new low rate. */ - throtl_start_new_slice(tg, READ); - throtl_start_new_slice(tg, WRITE); + throtl_start_new_slice(tg, READ, false); + throtl_start_new_slice(tg, WRITE, false); if (tg->flags & THROTL_TG_PENDING) { tg_update_disptime(tg); @@ -1350,6 +1391,7 @@ static ssize_t tg_set_conf(struct kernfs_open_file *of, v = U64_MAX; tg = blkg_to_tg(ctx.blkg); + tg_update_carryover(tg); if (is_u64) *(u64 *)((void *)tg + of_cft(of)->private) = v; @@ -1536,6 +1578,7 @@ static ssize_t tg_set_limit(struct kernfs_open_file *of, return ret; tg = blkg_to_tg(ctx.blkg); + tg_update_carryover(tg); v[0] = tg->bps_conf[READ][index]; v[1] = tg->bps_conf[WRITE][index]; @@ -1673,6 +1716,41 @@ struct blkcg_policy blkcg_policy_throtl = { .pd_free_fn = throtl_pd_free, }; +void blk_throtl_cancel_bios(struct gendisk *disk) +{ + struct request_queue *q = disk->queue; + struct cgroup_subsys_state *pos_css; + struct blkcg_gq *blkg; + + spin_lock_irq(&q->queue_lock); + /* + * queue_lock is held, rcu lock is not needed here technically. + * However, rcu lock is still held to emphasize that following + * path need RCU protection and to prevent warning from lockdep. + */ + rcu_read_lock(); + blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) { + struct throtl_grp *tg = blkg_to_tg(blkg); + struct throtl_service_queue *sq = &tg->service_queue; + + /* + * Set the flag to make sure throtl_pending_timer_fn() won't + * stop until all throttled bios are dispatched. + */ + blkg_to_tg(blkg)->flags |= THROTL_TG_CANCELING; + /* + * Update disptime after setting the above flag to make sure + * throtl_select_dispatch() won't exit without dispatching. + */ + tg_update_disptime(tg); + + throtl_schedule_pending_timer(sq, jiffies + 1); + } + rcu_read_unlock(); + spin_unlock_irq(&q->queue_lock); +} + +#ifdef CONFIG_BLK_DEV_THROTTLING_LOW static unsigned long __tg_last_low_overflow_time(struct throtl_grp *tg) { unsigned long rtime = jiffies, wtime = jiffies; @@ -1777,39 +1855,6 @@ static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg) return false; } -void blk_throtl_cancel_bios(struct request_queue *q) -{ - struct cgroup_subsys_state *pos_css; - struct blkcg_gq *blkg; - - spin_lock_irq(&q->queue_lock); - /* - * queue_lock is held, rcu lock is not needed here technically. - * However, rcu lock is still held to emphasize that following - * path need RCU protection and to prevent warning from lockdep. - */ - rcu_read_lock(); - blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) { - struct throtl_grp *tg = blkg_to_tg(blkg); - struct throtl_service_queue *sq = &tg->service_queue; - - /* - * Set the flag to make sure throtl_pending_timer_fn() won't - * stop until all throttled bios are dispatched. - */ - blkg_to_tg(blkg)->flags |= THROTL_TG_CANCELING; - /* - * Update disptime after setting the above flag to make sure - * throtl_select_dispatch() won't exit without dispatching. - */ - tg_update_disptime(tg); - - throtl_schedule_pending_timer(sq, jiffies + 1); - } - rcu_read_unlock(); - spin_unlock_irq(&q->queue_lock); -} - static bool throtl_can_upgrade(struct throtl_data *td, struct throtl_grp *this_tg) { @@ -2005,7 +2050,6 @@ static void blk_throtl_update_idletime(struct throtl_grp *tg) tg->checked_last_finish_time = last_finish_time; } -#ifdef CONFIG_BLK_DEV_THROTTLING_LOW static void throtl_update_latency_buckets(struct throtl_data *td) { struct avg_latency_bucket avg_latency[2][LATENCY_BUCKET_SIZE]; @@ -2086,6 +2130,28 @@ static void throtl_update_latency_buckets(struct throtl_data *td) static inline void throtl_update_latency_buckets(struct throtl_data *td) { } + +static void blk_throtl_update_idletime(struct throtl_grp *tg) +{ +} + +static void throtl_downgrade_check(struct throtl_grp *tg) +{ +} + +static void throtl_upgrade_check(struct throtl_grp *tg) +{ +} + +static bool throtl_can_upgrade(struct throtl_data *td, + struct throtl_grp *this_tg) +{ + return false; +} + +static void throtl_upgrade_state(struct throtl_data *td) +{ +} #endif bool __blk_throtl_bio(struct bio *bio) @@ -2159,8 +2225,10 @@ again: qn = &tg->qnode_on_parent[rw]; sq = sq->parent_sq; tg = sq_to_tg(sq); - if (!tg) + if (!tg) { + bio_set_flag(bio, BIO_BPS_THROTTLED); goto out_unlock; + } } /* out-of-limit, queue to @tg */ @@ -2189,8 +2257,6 @@ again: } out_unlock: - bio_set_flag(bio, BIO_THROTTLED); - #ifdef CONFIG_BLK_DEV_THROTTLING_LOW if (throttled || !td->track_bio_latency) bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY; @@ -2286,8 +2352,9 @@ void blk_throtl_bio_endio(struct bio *bio) } #endif -int blk_throtl_init(struct request_queue *q) +int blk_throtl_init(struct gendisk *disk) { + struct request_queue *q = disk->queue; struct throtl_data *td; int ret; @@ -2329,8 +2396,10 @@ int blk_throtl_init(struct request_queue *q) return ret; } -void blk_throtl_exit(struct request_queue *q) +void blk_throtl_exit(struct gendisk *disk) { + struct request_queue *q = disk->queue; + BUG_ON(!q->td); del_timer_sync(&q->td->service_queue.pending_timer); throtl_shutdown_wq(q); @@ -2340,8 +2409,9 @@ void blk_throtl_exit(struct request_queue *q) kfree(q->td); } -void blk_throtl_register_queue(struct request_queue *q) +void blk_throtl_register(struct gendisk *disk) { + struct request_queue *q = disk->queue; struct throtl_data *td; int i; diff --git a/block/blk-throttle.h b/block/blk-throttle.h index c1b602996127..ef4b7a4de987 100644 --- a/block/blk-throttle.h +++ b/block/blk-throttle.h @@ -55,8 +55,7 @@ struct throtl_service_queue { enum tg_state_flags { THROTL_TG_PENDING = 1 << 0, /* on parent's pending tree */ THROTL_TG_WAS_EMPTY = 1 << 1, /* bio_lists[] became non-empty */ - THROTL_TG_HAS_IOPS_LIMIT = 1 << 2, /* tg has iops limit */ - THROTL_TG_CANCELING = 1 << 3, /* starts to cancel bio */ + THROTL_TG_CANCELING = 1 << 2, /* starts to cancel bio */ }; enum { @@ -99,7 +98,8 @@ struct throtl_grp { unsigned int flags; /* are there any throtl rules between this group and td? */ - bool has_rules[2]; + bool has_rules_bps[2]; + bool has_rules_iops[2]; /* internally used bytes per second rate limits */ uint64_t bps[2][LIMIT_CNT]; @@ -121,6 +121,15 @@ struct throtl_grp { uint64_t last_bytes_disp[2]; unsigned int last_io_disp[2]; + /* + * The following two fields are updated when new configuration is + * submitted while some bios are still throttled, they record how many + * bytes/ios are waited already in previous configuration, and they will + * be used to calculate wait time under new configuration. + */ + uint64_t carryover_bytes[2]; + unsigned int carryover_ios[2]; + unsigned long last_check_time; unsigned long latency_target; /* us */ @@ -159,27 +168,37 @@ static inline struct throtl_grp *blkg_to_tg(struct blkcg_gq *blkg) * Internal throttling interface */ #ifndef CONFIG_BLK_DEV_THROTTLING -static inline int blk_throtl_init(struct request_queue *q) { return 0; } -static inline void blk_throtl_exit(struct request_queue *q) { } -static inline void blk_throtl_register_queue(struct request_queue *q) { } +static inline int blk_throtl_init(struct gendisk *disk) { return 0; } +static inline void blk_throtl_exit(struct gendisk *disk) { } +static inline void blk_throtl_register(struct gendisk *disk) { } static inline bool blk_throtl_bio(struct bio *bio) { return false; } -static inline void blk_throtl_cancel_bios(struct request_queue *q) { } +static inline void blk_throtl_cancel_bios(struct gendisk *disk) { } #else /* CONFIG_BLK_DEV_THROTTLING */ -int blk_throtl_init(struct request_queue *q); -void blk_throtl_exit(struct request_queue *q); -void blk_throtl_register_queue(struct request_queue *q); +int blk_throtl_init(struct gendisk *disk); +void blk_throtl_exit(struct gendisk *disk); +void blk_throtl_register(struct gendisk *disk); bool __blk_throtl_bio(struct bio *bio); -void blk_throtl_cancel_bios(struct request_queue *q); -static inline bool blk_throtl_bio(struct bio *bio) +void blk_throtl_cancel_bios(struct gendisk *disk); + +static inline bool blk_should_throtl(struct bio *bio) { struct throtl_grp *tg = blkg_to_tg(bio->bi_blkg); + int rw = bio_data_dir(bio); - /* no need to throttle bps any more if the bio has been throttled */ - if (bio_flagged(bio, BIO_THROTTLED) && - !(tg->flags & THROTL_TG_HAS_IOPS_LIMIT)) - return false; + /* iops limit is always counted */ + if (tg->has_rules_iops[rw]) + return true; + + if (tg->has_rules_bps[rw] && !bio_flagged(bio, BIO_BPS_THROTTLED)) + return true; + + return false; +} + +static inline bool blk_throtl_bio(struct bio *bio) +{ - if (!tg->has_rules[bio_data_dir(bio)]) + if (!blk_should_throtl(bio)) return false; return __blk_throtl_bio(bio); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index a9982000b667..246467926253 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -843,6 +843,10 @@ int wbt_init(struct request_queue *q) rwb->enable_state = WBT_STATE_ON_DEFAULT; rwb->wc = 1; rwb->rq_depth.default_depth = RWB_DEF_DEPTH; + rwb->min_lat_nsec = wbt_default_latency_nsec(q); + + wbt_queue_depth_changed(&rwb->rqos); + wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); /* * Assign rwb and add the stats callback. @@ -853,11 +857,6 @@ int wbt_init(struct request_queue *q) blk_stat_add_callback(q, rwb->cb); - rwb->min_lat_nsec = wbt_default_latency_nsec(q); - - wbt_queue_depth_changed(&rwb->rqos); - wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); - return 0; err_free: diff --git a/block/blk-zoned.c b/block/blk-zoned.c index a264621d4905..db829401d8d0 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -63,13 +63,10 @@ bool blk_req_needs_zone_write_lock(struct request *rq) if (!rq->q->disk->seq_zones_wlock) return false; - switch (req_op(rq)) { - case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE: + if (bdev_op_is_zoned_write(rq->q->disk->part0, req_op(rq))) return blk_rq_zone_is_seq(rq); - default: - return false; - } + + return false; } EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock); diff --git a/block/blk.h b/block/blk.h index d7142c4d2fef..5350bf363035 100644 --- a/block/blk.h +++ b/block/blk.h @@ -270,8 +270,7 @@ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, void blk_insert_flush(struct request *rq); -int elevator_switch_mq(struct request_queue *q, - struct elevator_type *new_e); +int elevator_switch(struct request_queue *q, struct elevator_type *new_e); void elevator_exit(struct request_queue *q); int elv_register_queue(struct request_queue *q, bool uevent); void elv_unregister_queue(struct request_queue *q); @@ -389,9 +388,9 @@ static inline struct bio *blk_queue_bounce(struct bio *bio, } #ifdef CONFIG_BLK_CGROUP_IOLATENCY -extern int blk_iolatency_init(struct request_queue *q); +int blk_iolatency_init(struct gendisk *disk); #else -static inline int blk_iolatency_init(struct request_queue *q) { return 0; } +static inline int blk_iolatency_init(struct gendisk *disk) { return 0; }; #endif #ifdef CONFIG_BLK_DEV_ZONED diff --git a/block/elevator.c b/block/elevator.c index c319765892bb..bd71f0fc4e4b 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -588,7 +588,7 @@ void elv_unregister(struct elevator_type *e) } EXPORT_SYMBOL_GPL(elv_unregister); -int elevator_switch_mq(struct request_queue *q, +static int elevator_switch_mq(struct request_queue *q, struct elevator_type *new_e) { int ret; @@ -723,7 +723,7 @@ void elevator_init_mq(struct request_queue *q) * need for the new one. this way we have a chance of going back to the old * one, if the new one fails init for some reason. */ -static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) +int elevator_switch(struct request_queue *q, struct elevator_type *new_e) { int err; diff --git a/block/genhd.c b/block/genhd.c index d36fabf0abc1..514395361d7c 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -602,7 +602,6 @@ void del_gendisk(struct gendisk *disk) * Prevent new I/O from crossing bio_queue_enter(). */ blk_queue_start_drain(q); - blk_mq_freeze_queue_wait(q); if (!(disk->flags & GENHD_FL_HIDDEN)) { sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); @@ -626,7 +625,9 @@ void del_gendisk(struct gendisk *disk) pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); device_del(disk_to_dev(disk)); - blk_throtl_cancel_bios(disk->queue); + blk_mq_freeze_queue_wait(q); + + blk_throtl_cancel_bios(disk); blk_sync_queue(q); blk_flush_integrity(); @@ -1150,7 +1151,8 @@ static void disk_release(struct device *dev) !test_bit(GD_ADDED, &disk->state)) blk_mq_exit_queue(disk->queue); - blkcg_exit_queue(disk->queue); + blkcg_exit_disk(disk); + bioset_exit(&disk->bio_split); disk_release_events(disk); @@ -1363,7 +1365,7 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL)) goto out_destroy_part_tbl; - if (blkcg_init_queue(q)) + if (blkcg_init_disk(disk)) goto out_erase_part0; rand_initialize_disk(disk); diff --git a/block/opal_proto.h b/block/opal_proto.h index b486b3ec7dc4..7152aa1f1a49 100644 --- a/block/opal_proto.h +++ b/block/opal_proto.h @@ -39,7 +39,12 @@ enum opal_response_token { #define FIRST_TPER_SESSION_NUM 4096 #define TPER_SYNC_SUPPORTED 0x01 +/* FC_LOCKING features */ +#define LOCKING_SUPPORTED_MASK 0x01 +#define LOCKING_ENABLED_MASK 0x02 +#define LOCKED_MASK 0x04 #define MBR_ENABLED_MASK 0x10 +#define MBR_DONE_MASK 0x20 #define TINY_ATOM_DATA_MASK 0x3F #define TINY_ATOM_SIGNED 0x40 diff --git a/block/sed-opal.c b/block/sed-opal.c index 9700197000f2..2c5327a0543a 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -74,8 +74,7 @@ struct parsed_resp { }; struct opal_dev { - bool supported; - bool mbr_enabled; + u32 flags; void *data; sec_send_recv *send_recv; @@ -280,6 +279,30 @@ static bool check_tper(const void *data) return true; } +static bool check_lcksuppt(const void *data) +{ + const struct d0_locking_features *lfeat = data; + u8 sup_feat = lfeat->supported_features; + + return !!(sup_feat & LOCKING_SUPPORTED_MASK); +} + +static bool check_lckenabled(const void *data) +{ + const struct d0_locking_features *lfeat = data; + u8 sup_feat = lfeat->supported_features; + + return !!(sup_feat & LOCKING_ENABLED_MASK); +} + +static bool check_locked(const void *data) +{ + const struct d0_locking_features *lfeat = data; + u8 sup_feat = lfeat->supported_features; + + return !!(sup_feat & LOCKED_MASK); +} + static bool check_mbrenabled(const void *data) { const struct d0_locking_features *lfeat = data; @@ -288,6 +311,14 @@ static bool check_mbrenabled(const void *data) return !!(sup_feat & MBR_ENABLED_MASK); } +static bool check_mbrdone(const void *data) +{ + const struct d0_locking_features *lfeat = data; + u8 sup_feat = lfeat->supported_features; + + return !!(sup_feat & MBR_DONE_MASK); +} + static bool check_sum(const void *data) { const struct d0_single_user_mode *sum = data; @@ -435,7 +466,7 @@ static int opal_discovery0_end(struct opal_dev *dev) u32 hlen = be32_to_cpu(hdr->length); print_buffer(dev->resp, hlen); - dev->mbr_enabled = false; + dev->flags &= OPAL_FL_SUPPORTED; if (hlen > IO_BUFFER_LENGTH - sizeof(*hdr)) { pr_debug("Discovery length overflows buffer (%zu+%u)/%u\n", @@ -461,7 +492,16 @@ static int opal_discovery0_end(struct opal_dev *dev) check_geometry(dev, body); break; case FC_LOCKING: - dev->mbr_enabled = check_mbrenabled(body->features); + if (check_lcksuppt(body->features)) + dev->flags |= OPAL_FL_LOCKING_SUPPORTED; + if (check_lckenabled(body->features)) + dev->flags |= OPAL_FL_LOCKING_ENABLED; + if (check_locked(body->features)) + dev->flags |= OPAL_FL_LOCKED; + if (check_mbrenabled(body->features)) + dev->flags |= OPAL_FL_MBR_ENABLED; + if (check_mbrdone(body->features)) + dev->flags |= OPAL_FL_MBR_DONE; break; case FC_ENTERPRISE: case FC_DATASTORE: @@ -2109,7 +2149,8 @@ static int check_opal_support(struct opal_dev *dev) mutex_lock(&dev->dev_lock); setup_opal_dev(dev); ret = opal_discovery0_step(dev); - dev->supported = !ret; + if (!ret) + dev->flags |= OPAL_FL_SUPPORTED; mutex_unlock(&dev->dev_lock); return ret; @@ -2148,6 +2189,7 @@ struct opal_dev *init_opal_dev(void *data, sec_send_recv *send_recv) INIT_LIST_HEAD(&dev->unlk_lst); mutex_init(&dev->dev_lock); + dev->flags = 0; dev->data = data; dev->send_recv = send_recv; if (check_opal_support(dev) != 0) { @@ -2528,7 +2570,7 @@ bool opal_unlock_from_suspend(struct opal_dev *dev) if (!dev) return false; - if (!dev->supported) + if (!(dev->flags & OPAL_FL_SUPPORTED)) return false; mutex_lock(&dev->dev_lock); @@ -2546,7 +2588,7 @@ bool opal_unlock_from_suspend(struct opal_dev *dev) was_failure = true; } - if (dev->mbr_enabled) { + if (dev->flags & OPAL_FL_MBR_ENABLED) { ret = __opal_set_mbr_done(dev, &suspend->unlk.session.opal_key); if (ret) pr_debug("Failed to set MBR Done in S3 resume\n"); @@ -2620,6 +2662,23 @@ static int opal_generic_read_write_table(struct opal_dev *dev, return ret; } +static int opal_get_status(struct opal_dev *dev, void __user *data) +{ + struct opal_status sts = {0}; + + /* + * check_opal_support() error is not fatal, + * !dev->supported is a valid condition + */ + if (!check_opal_support(dev)) + sts.flags = dev->flags; + if (copy_to_user(data, &sts, sizeof(sts))) { + pr_debug("Error copying status to userspace\n"); + return -EFAULT; + } + return 0; +} + int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg) { void *p; @@ -2629,12 +2688,14 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg) return -EACCES; if (!dev) return -ENOTSUPP; - if (!dev->supported) + if (!(dev->flags & OPAL_FL_SUPPORTED)) return -ENOTSUPP; - p = memdup_user(arg, _IOC_SIZE(cmd)); - if (IS_ERR(p)) - return PTR_ERR(p); + if (cmd & IOC_IN) { + p = memdup_user(arg, _IOC_SIZE(cmd)); + if (IS_ERR(p)) + return PTR_ERR(p); + } switch (cmd) { case IOC_OPAL_SAVE: @@ -2685,11 +2746,15 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg) case IOC_OPAL_GENERIC_TABLE_RW: ret = opal_generic_read_write_table(dev, p); break; + case IOC_OPAL_GET_STATUS: + ret = opal_get_status(dev, arg); + break; default: break; } - kfree(p); + if (cmd & IOC_IN) + kfree(p); return ret; } EXPORT_SYMBOL_GPL(sed_ioctl); diff --git a/certs/Kconfig b/certs/Kconfig index bf9b511573d7..1f109b070877 100644 --- a/certs/Kconfig +++ b/certs/Kconfig @@ -43,7 +43,7 @@ config SYSTEM_TRUSTED_KEYRING bool "Provide system-wide ring of trusted keys" depends on KEYS depends on ASYMMETRIC_KEY_TYPE - depends on X509_CERTIFICATE_PARSER + depends on X509_CERTIFICATE_PARSER = y help Provide a system keyring to which trusted keys can be added. Keys in the keyring are considered to be trusted. Keys may be added at will diff --git a/drivers/base/core.c b/drivers/base/core.c index 753e7cca0f40..5fb4bc51dd8b 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1625,7 +1625,7 @@ static int __init fw_devlink_setup(char *arg) } early_param("fw_devlink", fw_devlink_setup); -static bool fw_devlink_strict = true; +static bool fw_devlink_strict; static int __init fw_devlink_strict_setup(char *arg) { return strtobool(arg, &fw_devlink_strict); diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 12b3ca8f6f4a..128722cf6c3c 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -108,7 +108,7 @@ static ssize_t aoedisk_show_payload(struct device *dev, return sysfs_emit(page, "%lu\n", d->maxbcnt); } -static int aoedisk_debugfs_show(struct seq_file *s, void *ignored) +static int aoe_debugfs_show(struct seq_file *s, void *ignored) { struct aoedev *d; struct aoetgt **t, **te; @@ -151,11 +151,7 @@ static int aoedisk_debugfs_show(struct seq_file *s, void *ignored) return 0; } - -static int aoe_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, aoedisk_debugfs_show, inode->i_private); -} +DEFINE_SHOW_ATTRIBUTE(aoe_debugfs); static DEVICE_ATTR(state, 0444, aoedisk_show_state, NULL); static DEVICE_ATTR(mac, 0444, aoedisk_show_mac, NULL); @@ -184,13 +180,6 @@ static const struct attribute_group *aoe_attr_groups[] = { NULL, }; -static const struct file_operations aoe_debugfs_fops = { - .open = aoe_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static void aoedisk_add_debugfs(struct aoedev *d) { diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 859499cd1ff8..20acc4a1fd6d 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -397,7 +397,7 @@ static int brd_alloc(int i) disk->minors = max_part; disk->fops = &brd_fops; disk->private_data = brd; - strlcpy(disk->disk_name, buf, DISK_NAME_LEN); + strscpy(disk->disk_name, buf, DISK_NAME_LEN); set_capacity(disk, rd_size * 2); /* diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index f15f2f041596..4d661282ff41 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1529,7 +1529,6 @@ extern int w_send_read_req(struct drbd_work *, int); extern int w_e_reissue(struct drbd_work *, int); extern int w_restart_disk_io(struct drbd_work *, int); extern int w_send_out_of_sync(struct drbd_work *, int); -extern int w_start_resync(struct drbd_work *, int); extern void resync_timer_fn(struct timer_list *t); extern void start_resync_timer_fn(struct timer_list *t); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 013d355a2033..864c98e74875 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -4752,7 +4752,7 @@ void notify_helper(enum drbd_notification_type type, struct drbd_genlmsghdr *dh; int err; - strlcpy(helper_info.helper_name, name, sizeof(helper_info.helper_name)); + strscpy(helper_info.helper_name, name, sizeof(helper_info.helper_name)); helper_info.helper_name_len = min(strlen(name), sizeof(helper_info.helper_name)); helper_info.helper_status = status; diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index af4c7d65490b..c897c4572036 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -2113,9 +2113,6 @@ static int receive_DataReply(struct drbd_connection *connection, struct packet_i if (unlikely(!req)) return -EIO; - /* hlist_del(&req->collision) is done in _req_may_be_done, to avoid - * special casing it there for the various failure cases. - * still no race with drbd_fail_pending_reads */ err = recv_dless_read(peer_device, req, sector, pi->size); if (!err) req_mod(req, DATA_RECEIVED); diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h index 511f39a08de4..6237fa1dcb0e 100644 --- a/drivers/block/drbd/drbd_req.h +++ b/drivers/block/drbd/drbd_req.h @@ -266,8 +266,6 @@ struct bio_and_error { extern void start_new_tl_epoch(struct drbd_connection *connection); extern void drbd_req_destroy(struct kref *kref); -extern void _req_may_be_done(struct drbd_request *req, - struct bio_and_error *m); extern int __req_mod(struct drbd_request *req, enum drbd_req_event what, struct bio_and_error *m); extern void complete_master_bio(struct drbd_device *device, diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 562725d222a7..815d77ba6381 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -1397,15 +1397,15 @@ static void mtip_dump_identify(struct mtip_port *port) if (!port->identify_valid) return; - strlcpy(cbuf, (char *)(port->identify+10), 21); + strscpy(cbuf, (char *)(port->identify + 10), 21); dev_info(&port->dd->pdev->dev, "Serial No.: %s\n", cbuf); - strlcpy(cbuf, (char *)(port->identify+23), 9); + strscpy(cbuf, (char *)(port->identify + 23), 9); dev_info(&port->dd->pdev->dev, "Firmware Ver.: %s\n", cbuf); - strlcpy(cbuf, (char *)(port->identify+27), 41); + strscpy(cbuf, (char *)(port->identify + 27), 41); dev_info(&port->dd->pdev->dev, "Model: %s\n", cbuf); dev_info(&port->dd->pdev->dev, "Security: %04x %s\n", @@ -1421,13 +1421,13 @@ static void mtip_dump_identify(struct mtip_port *port) pci_read_config_word(port->dd->pdev, PCI_REVISION_ID, &revid); switch (revid & 0xFF) { case 0x1: - strlcpy(cbuf, "A0", 3); + strscpy(cbuf, "A0", 3); break; case 0x3: - strlcpy(cbuf, "A2", 3); + strscpy(cbuf, "A2", 3); break; default: - strlcpy(cbuf, "?", 2); + strscpy(cbuf, "?", 2); break; } dev_info(&port->dd->pdev->dev, diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 2a709daefbc4..2a2a1d996a57 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1413,10 +1413,12 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd) mutex_unlock(&nbd->config_lock); ret = wait_event_interruptible(config->recv_wq, atomic_read(&config->recv_threads) == 0); - if (ret) + if (ret) { sock_shutdown(nbd); - flush_workqueue(nbd->recv_workq); + nbd_clear_que(nbd); + } + flush_workqueue(nbd->recv_workq); mutex_lock(&nbd->config_lock); nbd_bdev_reset(nbd); /* user requested, ignore socket errors */ diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index c451c477978f..1f154f92f4c2 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1528,7 +1528,7 @@ static bool should_requeue_request(struct request *rq) return false; } -static int null_map_queues(struct blk_mq_tag_set *set) +static void null_map_queues(struct blk_mq_tag_set *set) { struct nullb *nullb = set->driver_data; int i, qoff; @@ -1555,7 +1555,9 @@ static int null_map_queues(struct blk_mq_tag_set *set) } else { pr_warn("tag set has unexpected nr_hw_queues: %d\n", set->nr_hw_queues); - return -EINVAL; + WARN_ON_ONCE(true); + submit_queues = 1; + poll_queues = 0; } } @@ -1577,8 +1579,6 @@ static int null_map_queues(struct blk_mq_tag_set *set) qoff += map->nr_queues; blk_mq_map_queues(map); } - - return 0; } static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index e1d080f680ed..c76e0148eada 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -745,7 +745,7 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) gendisk->flags |= GENHD_FL_NO_PART; gendisk->fops = &ps3vram_fops; gendisk->private_data = dev; - strlcpy(gendisk->disk_name, DEVICE_NAME, sizeof(gendisk->disk_name)); + strscpy(gendisk->disk_name, DEVICE_NAME, sizeof(gendisk->disk_name)); set_capacity(gendisk, priv->size >> 9); blk_queue_max_segments(gendisk->queue, BLK_MAX_SEGMENTS); blk_queue_max_segment_size(gendisk->queue, BLK_MAX_SEGMENT_SIZE); diff --git a/drivers/block/rnbd/Makefile b/drivers/block/rnbd/Makefile index 5bb1a7ad1ada..40b31630822c 100644 --- a/drivers/block/rnbd/Makefile +++ b/drivers/block/rnbd/Makefile @@ -6,10 +6,12 @@ rnbd-client-y := rnbd-clt.o \ rnbd-clt-sysfs.o \ rnbd-common.o +CFLAGS_rnbd-srv-trace.o = -I$(src) + rnbd-server-y := rnbd-common.o \ rnbd-srv.o \ - rnbd-srv-dev.o \ - rnbd-srv-sysfs.o + rnbd-srv-sysfs.o \ + rnbd-srv-trace.o obj-$(CONFIG_BLK_DEV_RNBD_CLIENT) += rnbd-client.o obj-$(CONFIG_BLK_DEV_RNBD_SERVER) += rnbd-server.o diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 04da33a22ef4..78334da74d8b 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1159,13 +1159,11 @@ static int rnbd_rdma_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) { struct rnbd_queue *q = hctx->driver_data; struct rnbd_clt_dev *dev = q->dev; - int cnt; - cnt = rtrs_clt_rdma_cq_direct(dev->sess->rtrs, hctx->queue_num); - return cnt; + return rtrs_clt_rdma_cq_direct(dev->sess->rtrs, hctx->queue_num); } -static int rnbd_rdma_map_queues(struct blk_mq_tag_set *set) +static void rnbd_rdma_map_queues(struct blk_mq_tag_set *set) { struct rnbd_clt_session *sess = set->driver_data; @@ -1194,8 +1192,6 @@ static int rnbd_rdma_map_queues(struct blk_mq_tag_set *set) set->map[HCTX_TYPE_DEFAULT].nr_queues, set->map[HCTX_TYPE_READ].nr_queues); } - - return 0; } static struct blk_mq_ops rnbd_mq_ops = { diff --git a/drivers/block/rnbd/rnbd-srv-dev.c b/drivers/block/rnbd/rnbd-srv-dev.c deleted file mode 100644 index c63017f6e421..000000000000 --- a/drivers/block/rnbd/rnbd-srv-dev.c +++ /dev/null @@ -1,43 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RDMA Network Block Driver - * - * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. - * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. - * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. - */ -#undef pr_fmt -#define pr_fmt(fmt) KBUILD_MODNAME " L" __stringify(__LINE__) ": " fmt - -#include "rnbd-srv-dev.h" -#include "rnbd-log.h" - -struct rnbd_dev *rnbd_dev_open(const char *path, fmode_t flags) -{ - struct rnbd_dev *dev; - int ret; - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) - return ERR_PTR(-ENOMEM); - - dev->blk_open_flags = flags; - dev->bdev = blkdev_get_by_path(path, flags, THIS_MODULE); - ret = PTR_ERR_OR_ZERO(dev->bdev); - if (ret) - goto err; - - dev->blk_open_flags = flags; - - return dev; - -err: - kfree(dev); - return ERR_PTR(ret); -} - -void rnbd_dev_close(struct rnbd_dev *dev) -{ - blkdev_put(dev->bdev, dev->blk_open_flags); - kfree(dev); -} diff --git a/drivers/block/rnbd/rnbd-srv-dev.h b/drivers/block/rnbd/rnbd-srv-dev.h deleted file mode 100644 index 8407d12f70af..000000000000 --- a/drivers/block/rnbd/rnbd-srv-dev.h +++ /dev/null @@ -1,64 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * RDMA Network Block Driver - * - * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved. - * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved. - * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved. - */ -#ifndef RNBD_SRV_DEV_H -#define RNBD_SRV_DEV_H - -#include <linux/fs.h> -#include "rnbd-proto.h" - -struct rnbd_dev { - struct block_device *bdev; - fmode_t blk_open_flags; -}; - -/** - * rnbd_dev_open() - Open a device - * @path: path to open - * @flags: open flags - */ -struct rnbd_dev *rnbd_dev_open(const char *path, fmode_t flags); - -/** - * rnbd_dev_close() - Close a device - */ -void rnbd_dev_close(struct rnbd_dev *dev); - -void rnbd_endio(void *priv, int error); - -static inline int rnbd_dev_get_max_segs(const struct rnbd_dev *dev) -{ - return queue_max_segments(bdev_get_queue(dev->bdev)); -} - -static inline int rnbd_dev_get_max_hw_sects(const struct rnbd_dev *dev) -{ - return queue_max_hw_sectors(bdev_get_queue(dev->bdev)); -} - -static inline int rnbd_dev_get_secure_discard(const struct rnbd_dev *dev) -{ - return bdev_max_secure_erase_sectors(dev->bdev); -} - -static inline int rnbd_dev_get_max_discard_sects(const struct rnbd_dev *dev) -{ - return bdev_max_discard_sectors(dev->bdev); -} - -static inline int rnbd_dev_get_discard_granularity(const struct rnbd_dev *dev) -{ - return bdev_get_queue(dev->bdev)->limits.discard_granularity; -} - -static inline int rnbd_dev_get_discard_alignment(const struct rnbd_dev *dev) -{ - return bdev_discard_alignment(dev->bdev); -} - -#endif /* RNBD_SRV_DEV_H */ diff --git a/drivers/block/rnbd/rnbd-srv-trace.c b/drivers/block/rnbd/rnbd-srv-trace.c new file mode 100644 index 000000000000..30f0895c18f5 --- /dev/null +++ b/drivers/block/rnbd/rnbd-srv-trace.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * RDMA Network Block Driver + * + * Copyright (c) 2022 1&1 IONOS SE. All rights reserved. + */ +#include "rtrs.h" +#include "rtrs-srv.h" +#include "rnbd-srv.h" +#include "rnbd-proto.h" + +/* + * We include this last to have the helpers above available for the trace + * event implementations. + */ +#define CREATE_TRACE_POINTS +#include "rnbd-srv-trace.h" diff --git a/drivers/block/rnbd/rnbd-srv-trace.h b/drivers/block/rnbd/rnbd-srv-trace.h new file mode 100644 index 000000000000..8dedf73bdd28 --- /dev/null +++ b/drivers/block/rnbd/rnbd-srv-trace.h @@ -0,0 +1,207 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * RDMA Network Block Driver + * + * Copyright (c) 2022 1&1 IONOS SE. All rights reserved. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM rnbd_srv + +#if !defined(_TRACE_RNBD_SRV_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_RNBD_SRV_H + +#include <linux/tracepoint.h> + +struct rnbd_srv_session; +struct rtrs_srv_op; + +DECLARE_EVENT_CLASS(rnbd_srv_link_class, + TP_PROTO(struct rnbd_srv_session *srv), + + TP_ARGS(srv), + + TP_STRUCT__entry( + __field(int, qdepth) + __string(sessname, srv->sessname) + ), + + TP_fast_assign( + __entry->qdepth = srv->queue_depth; + __assign_str(sessname, srv->sessname); + ), + + TP_printk("sessname: %s qdepth: %d", + __get_str(sessname), + __entry->qdepth + ) +); + +#define DEFINE_LINK_EVENT(name) \ +DEFINE_EVENT(rnbd_srv_link_class, name, \ + TP_PROTO(struct rnbd_srv_session *srv), \ + TP_ARGS(srv)) + +DEFINE_LINK_EVENT(create_sess); +DEFINE_LINK_EVENT(destroy_sess); + +TRACE_DEFINE_ENUM(RNBD_OP_READ); +TRACE_DEFINE_ENUM(RNBD_OP_WRITE); +TRACE_DEFINE_ENUM(RNBD_OP_FLUSH); +TRACE_DEFINE_ENUM(RNBD_OP_DISCARD); +TRACE_DEFINE_ENUM(RNBD_OP_SECURE_ERASE); +TRACE_DEFINE_ENUM(RNBD_F_SYNC); +TRACE_DEFINE_ENUM(RNBD_F_FUA); + +#define show_rnbd_rw_flags(x) \ + __print_flags(x, "|", \ + { RNBD_OP_READ, "READ" }, \ + { RNBD_OP_WRITE, "WRITE" }, \ + { RNBD_OP_FLUSH, "FLUSH" }, \ + { RNBD_OP_DISCARD, "DISCARD" }, \ + { RNBD_OP_SECURE_ERASE, "SECURE_ERASE" }, \ + { RNBD_F_SYNC, "SYNC" }, \ + { RNBD_F_FUA, "FUA" }) + +TRACE_EVENT(process_rdma, + TP_PROTO(struct rnbd_srv_session *srv, + const struct rnbd_msg_io *msg, + struct rtrs_srv_op *id, + u32 datalen, + size_t usrlen), + + TP_ARGS(srv, msg, id, datalen, usrlen), + + TP_STRUCT__entry( + __string(sessname, srv->sessname) + __field(u8, dir) + __field(u8, ver) + __field(u32, device_id) + __field(u64, sector) + __field(u32, flags) + __field(u32, bi_size) + __field(u16, ioprio) + __field(u32, datalen) + __field(size_t, usrlen) + ), + + TP_fast_assign( + __assign_str(sessname, srv->sessname); + __entry->dir = id->dir; + __entry->ver = srv->ver; + __entry->device_id = le32_to_cpu(msg->device_id); + __entry->sector = le64_to_cpu(msg->sector); + __entry->bi_size = le32_to_cpu(msg->bi_size); + __entry->flags = le32_to_cpu(msg->rw); + __entry->ioprio = le16_to_cpu(msg->prio); + __entry->datalen = datalen; + __entry->usrlen = usrlen; + ), + + TP_printk("I/O req: sess: %s, type: %s, ver: %d, devid: %u, sector: %llu, bsize: %u, flags: %s, ioprio: %d, datalen: %u, usrlen: %zu", + __get_str(sessname), + __print_symbolic(__entry->dir, + { READ, "READ" }, + { WRITE, "WRITE" }), + __entry->ver, + __entry->device_id, + __entry->sector, + __entry->bi_size, + show_rnbd_rw_flags(__entry->flags), + __entry->ioprio, + __entry->datalen, + __entry->usrlen + ) +); + +TRACE_EVENT(process_msg_sess_info, + TP_PROTO(struct rnbd_srv_session *srv, + const struct rnbd_msg_sess_info *msg), + + TP_ARGS(srv, msg), + + TP_STRUCT__entry( + __field(u8, proto_ver) + __field(u8, clt_ver) + __field(u8, srv_ver) + __string(sessname, srv->sessname) + ), + + TP_fast_assign( + __entry->proto_ver = srv->ver; + __entry->clt_ver = msg->ver; + __entry->srv_ver = RNBD_PROTO_VER_MAJOR; + __assign_str(sessname, srv->sessname); + ), + + TP_printk("Session %s using proto-ver %d (clt-ver: %d, srv-ver: %d)", + __get_str(sessname), + __entry->proto_ver, + __entry->clt_ver, + __entry->srv_ver + ) +); + +TRACE_DEFINE_ENUM(RNBD_ACCESS_RO); +TRACE_DEFINE_ENUM(RNBD_ACCESS_RW); +TRACE_DEFINE_ENUM(RNBD_ACCESS_MIGRATION); + +#define show_rnbd_access_mode(x) \ + __print_symbolic(x, \ + { RNBD_ACCESS_RO, "RO" }, \ + { RNBD_ACCESS_RW, "RW" }, \ + { RNBD_ACCESS_MIGRATION, "MIGRATION" }) + +TRACE_EVENT(process_msg_open, + TP_PROTO(struct rnbd_srv_session *srv, + const struct rnbd_msg_open *msg), + + TP_ARGS(srv, msg), + + TP_STRUCT__entry( + __field(u8, access_mode) + __string(sessname, srv->sessname) + __string(dev_name, msg->dev_name) + ), + + TP_fast_assign( + __entry->access_mode = msg->access_mode; + __assign_str(sessname, srv->sessname); + __assign_str(dev_name, msg->dev_name); + ), + + TP_printk("Open message received: session='%s' path='%s' access_mode=%s", + __get_str(sessname), + __get_str(dev_name), + show_rnbd_access_mode(__entry->access_mode) + ) +); + +TRACE_EVENT(process_msg_close, + TP_PROTO(struct rnbd_srv_session *srv, + const struct rnbd_msg_close *msg), + + TP_ARGS(srv, msg), + + TP_STRUCT__entry( + __field(u32, device_id) + __string(sessname, srv->sessname) + ), + + TP_fast_assign( + __entry->device_id = le32_to_cpu(msg->device_id); + __assign_str(sessname, srv->sessname); + ), + + TP_printk("Close message received: session='%s' device id='%d'", + __get_str(sessname), + __entry->device_id + ) +); + +#endif /* _TRACE_RNBD_SRV_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE rnbd-srv-trace +#include <trace/define_trace.h> + diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c index 5e08da277ddf..08b041159cd3 100644 --- a/drivers/block/rnbd/rnbd-srv.c +++ b/drivers/block/rnbd/rnbd-srv.c @@ -13,7 +13,7 @@ #include <linux/blkdev.h> #include "rnbd-srv.h" -#include "rnbd-srv-dev.h" +#include "rnbd-srv-trace.h" MODULE_DESCRIPTION("RDMA Network Block Device Server"); MODULE_LICENSE("GPL"); @@ -84,18 +84,6 @@ static inline void rnbd_put_sess_dev(struct rnbd_srv_sess_dev *sess_dev) kref_put(&sess_dev->kref, rnbd_sess_dev_release); } -void rnbd_endio(void *priv, int error) -{ - struct rnbd_io_private *rnbd_priv = priv; - struct rnbd_srv_sess_dev *sess_dev = rnbd_priv->sess_dev; - - rnbd_put_sess_dev(sess_dev); - - rtrs_srv_resp_rdma(rnbd_priv->id, error); - - kfree(priv); -} - static struct rnbd_srv_sess_dev * rnbd_get_sess_dev(int dev_id, struct rnbd_srv_session *srv_sess) { @@ -116,7 +104,13 @@ rnbd_get_sess_dev(int dev_id, struct rnbd_srv_session *srv_sess) static void rnbd_dev_bi_end_io(struct bio *bio) { - rnbd_endio(bio->bi_private, blk_status_to_errno(bio->bi_status)); + struct rnbd_io_private *rnbd_priv = bio->bi_private; + struct rnbd_srv_sess_dev *sess_dev = rnbd_priv->sess_dev; + + rnbd_put_sess_dev(sess_dev); + rtrs_srv_resp_rdma(rnbd_priv->id, blk_status_to_errno(bio->bi_status)); + + kfree(rnbd_priv); bio_put(bio); } @@ -132,6 +126,8 @@ static int process_rdma(struct rnbd_srv_session *srv_sess, struct bio *bio; short prio; + trace_process_rdma(srv_sess, msg, id, datalen, usrlen); + priv = kmalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; @@ -149,7 +145,7 @@ static int process_rdma(struct rnbd_srv_session *srv_sess, priv->sess_dev = sess_dev; priv->id = id; - bio = bio_alloc(sess_dev->rnbd_dev->bdev, 1, + bio = bio_alloc(sess_dev->bdev, 1, rnbd_to_bio_flags(le32_to_cpu(msg->rw)), GFP_KERNEL); if (bio_add_page(bio, virt_to_page(data), datalen, offset_in_page(data)) != datalen) { @@ -223,7 +219,7 @@ void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id) rnbd_put_sess_dev(sess_dev); wait_for_completion(&dc); /* wait for inflights to drop to zero */ - rnbd_dev_close(sess_dev->rnbd_dev); + blkdev_put(sess_dev->bdev, sess_dev->open_flags); mutex_lock(&sess_dev->dev->lock); list_del(&sess_dev->dev_list); if (sess_dev->open_flags & FMODE_WRITE) @@ -244,6 +240,8 @@ static void destroy_sess(struct rnbd_srv_session *srv_sess) if (xa_empty(&srv_sess->index_idr)) goto out; + trace_destroy_sess(srv_sess); + mutex_lock(&srv_sess->lock); xa_for_each(&srv_sess->index_idr, index, sess_dev) rnbd_srv_destroy_dev_session_sysfs(sess_dev); @@ -290,6 +288,8 @@ static int create_sess(struct rtrs_srv_sess *rtrs) rtrs_srv_set_sess_priv(rtrs, srv_sess); + trace_create_sess(srv_sess); + return 0; } @@ -332,23 +332,24 @@ void rnbd_srv_sess_dev_force_close(struct rnbd_srv_sess_dev *sess_dev, mutex_unlock(&sess->lock); } -static int process_msg_close(struct rnbd_srv_session *srv_sess, +static void process_msg_close(struct rnbd_srv_session *srv_sess, void *data, size_t datalen, const void *usr, size_t usrlen) { const struct rnbd_msg_close *close_msg = usr; struct rnbd_srv_sess_dev *sess_dev; + trace_process_msg_close(srv_sess, close_msg); + sess_dev = rnbd_get_sess_dev(le32_to_cpu(close_msg->device_id), srv_sess); if (IS_ERR(sess_dev)) - return 0; + return; rnbd_put_sess_dev(sess_dev); mutex_lock(&srv_sess->lock); rnbd_srv_destroy_dev_session_sysfs(sess_dev); mutex_unlock(&srv_sess->lock); - return 0; } static int process_msg_open(struct rnbd_srv_session *srv_sess, @@ -378,7 +379,7 @@ static int rnbd_srv_rdma_ev(void *priv, case RNBD_MSG_IO: return process_rdma(srv_sess, id, data, datalen, usr, usrlen); case RNBD_MSG_CLOSE: - ret = process_msg_close(srv_sess, data, datalen, usr, usrlen); + process_msg_close(srv_sess, data, datalen, usr, usrlen); break; case RNBD_MSG_OPEN: ret = process_msg_open(srv_sess, usr, usrlen, data, datalen); @@ -393,6 +394,11 @@ static int rnbd_srv_rdma_ev(void *priv, return -EINVAL; } + /* + * Since ret is passed to rtrs to handle the failure case, we + * just return 0 at the end otherwise callers in rtrs would call + * send_io_resp_imm again to print redundant err message. + */ rtrs_srv_resp_rdma(id, ret); return 0; } @@ -504,14 +510,14 @@ static int rnbd_srv_check_update_open_perm(struct rnbd_srv_dev *srv_dev, } static struct rnbd_srv_dev * -rnbd_srv_get_or_create_srv_dev(struct rnbd_dev *rnbd_dev, +rnbd_srv_get_or_create_srv_dev(struct block_device *bdev, struct rnbd_srv_session *srv_sess, enum rnbd_access_mode access_mode) { int ret; struct rnbd_srv_dev *new_dev, *dev; - new_dev = rnbd_srv_init_srv_dev(rnbd_dev->bdev); + new_dev = rnbd_srv_init_srv_dev(bdev); if (IS_ERR(new_dev)) return new_dev; @@ -531,41 +537,32 @@ rnbd_srv_get_or_create_srv_dev(struct rnbd_dev *rnbd_dev, static void rnbd_srv_fill_msg_open_rsp(struct rnbd_msg_open_rsp *rsp, struct rnbd_srv_sess_dev *sess_dev) { - struct rnbd_dev *rnbd_dev = sess_dev->rnbd_dev; + struct block_device *bdev = sess_dev->bdev; rsp->hdr.type = cpu_to_le16(RNBD_MSG_OPEN_RSP); - rsp->device_id = - cpu_to_le32(sess_dev->device_id); - rsp->nsectors = - cpu_to_le64(get_capacity(rnbd_dev->bdev->bd_disk)); - rsp->logical_block_size = - cpu_to_le16(bdev_logical_block_size(rnbd_dev->bdev)); - rsp->physical_block_size = - cpu_to_le16(bdev_physical_block_size(rnbd_dev->bdev)); - rsp->max_segments = - cpu_to_le16(rnbd_dev_get_max_segs(rnbd_dev)); + rsp->device_id = cpu_to_le32(sess_dev->device_id); + rsp->nsectors = cpu_to_le64(bdev_nr_sectors(bdev)); + rsp->logical_block_size = cpu_to_le16(bdev_logical_block_size(bdev)); + rsp->physical_block_size = cpu_to_le16(bdev_physical_block_size(bdev)); + rsp->max_segments = cpu_to_le16(bdev_max_segments(bdev)); rsp->max_hw_sectors = - cpu_to_le32(rnbd_dev_get_max_hw_sects(rnbd_dev)); + cpu_to_le32(queue_max_hw_sectors(bdev_get_queue(bdev))); rsp->max_write_same_sectors = 0; - rsp->max_discard_sectors = - cpu_to_le32(rnbd_dev_get_max_discard_sects(rnbd_dev)); - rsp->discard_granularity = - cpu_to_le32(rnbd_dev_get_discard_granularity(rnbd_dev)); - rsp->discard_alignment = - cpu_to_le32(rnbd_dev_get_discard_alignment(rnbd_dev)); - rsp->secure_discard = - cpu_to_le16(rnbd_dev_get_secure_discard(rnbd_dev)); + rsp->max_discard_sectors = cpu_to_le32(bdev_max_discard_sectors(bdev)); + rsp->discard_granularity = cpu_to_le32(bdev_discard_granularity(bdev)); + rsp->discard_alignment = cpu_to_le32(bdev_discard_alignment(bdev)); + rsp->secure_discard = cpu_to_le16(bdev_max_secure_erase_sectors(bdev)); rsp->cache_policy = 0; - if (bdev_write_cache(rnbd_dev->bdev)) + if (bdev_write_cache(bdev)) rsp->cache_policy |= RNBD_WRITEBACK; - if (bdev_fua(rnbd_dev->bdev)) + if (bdev_fua(bdev)) rsp->cache_policy |= RNBD_FUA; } static struct rnbd_srv_sess_dev * rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess, const struct rnbd_msg_open *open_msg, - struct rnbd_dev *rnbd_dev, fmode_t open_flags, + struct block_device *bdev, fmode_t open_flags, struct rnbd_srv_dev *srv_dev) { struct rnbd_srv_sess_dev *sdev = rnbd_sess_dev_alloc(srv_sess); @@ -577,7 +574,7 @@ rnbd_srv_create_set_sess_dev(struct rnbd_srv_session *srv_sess, strscpy(sdev->pathname, open_msg->dev_name, sizeof(sdev->pathname)); - sdev->rnbd_dev = rnbd_dev; + sdev->bdev = bdev; sdev->sess = srv_sess; sdev->dev = srv_dev; sdev->open_flags = open_flags; @@ -643,9 +640,8 @@ static int process_msg_sess_info(struct rnbd_srv_session *srv_sess, struct rnbd_msg_sess_info_rsp *rsp = data; srv_sess->ver = min_t(u8, sess_info_msg->ver, RNBD_PROTO_VER_MAJOR); - pr_debug("Session %s using protocol version %d (client version: %d, server version: %d)\n", - srv_sess->sessname, srv_sess->ver, - sess_info_msg->ver, RNBD_PROTO_VER_MAJOR); + + trace_process_msg_sess_info(srv_sess, sess_info_msg); rsp->hdr.type = cpu_to_le16(RNBD_MSG_SESS_INFO_RSP); rsp->ver = srv_sess->ver; @@ -685,14 +681,13 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, struct rnbd_srv_dev *srv_dev; struct rnbd_srv_sess_dev *srv_sess_dev; const struct rnbd_msg_open *open_msg = msg; + struct block_device *bdev; fmode_t open_flags; char *full_path; - struct rnbd_dev *rnbd_dev; struct rnbd_msg_open_rsp *rsp = data; - pr_debug("Open message received: session='%s' path='%s' access_mode=%d\n", - srv_sess->sessname, open_msg->dev_name, - open_msg->access_mode); + trace_process_msg_open(srv_sess, open_msg); + open_flags = FMODE_READ; if (open_msg->access_mode != RNBD_ACCESS_RO) open_flags |= FMODE_WRITE; @@ -725,25 +720,25 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, goto reject; } - rnbd_dev = rnbd_dev_open(full_path, open_flags); - if (IS_ERR(rnbd_dev)) { - pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %ld\n", - full_path, srv_sess->sessname, PTR_ERR(rnbd_dev)); - ret = PTR_ERR(rnbd_dev); + bdev = blkdev_get_by_path(full_path, open_flags, THIS_MODULE); + if (IS_ERR(bdev)) { + ret = PTR_ERR(bdev); + pr_err("Opening device '%s' on session %s failed, failed to open the block device, err: %d\n", + full_path, srv_sess->sessname, ret); goto free_path; } - srv_dev = rnbd_srv_get_or_create_srv_dev(rnbd_dev, srv_sess, + srv_dev = rnbd_srv_get_or_create_srv_dev(bdev, srv_sess, open_msg->access_mode); if (IS_ERR(srv_dev)) { pr_err("Opening device '%s' on session %s failed, creating srv_dev failed, err: %ld\n", full_path, srv_sess->sessname, PTR_ERR(srv_dev)); ret = PTR_ERR(srv_dev); - goto rnbd_dev_close; + goto blkdev_put; } srv_sess_dev = rnbd_srv_create_set_sess_dev(srv_sess, open_msg, - rnbd_dev, open_flags, + bdev, open_flags, srv_dev); if (IS_ERR(srv_sess_dev)) { pr_err("Opening device '%s' on session %s failed, creating sess_dev failed, err: %ld\n", @@ -758,7 +753,7 @@ static int process_msg_open(struct rnbd_srv_session *srv_sess, */ mutex_lock(&srv_dev->lock); if (!srv_dev->dev_kobj.state_in_sysfs) { - ret = rnbd_srv_create_dev_sysfs(srv_dev, rnbd_dev->bdev); + ret = rnbd_srv_create_dev_sysfs(srv_dev, bdev); if (ret) { mutex_unlock(&srv_dev->lock); rnbd_srv_err(srv_sess_dev, @@ -800,8 +795,8 @@ srv_dev_put: mutex_unlock(&srv_dev->lock); } rnbd_put_srv_dev(srv_dev); -rnbd_dev_close: - rnbd_dev_close(rnbd_dev); +blkdev_put: + blkdev_put(bdev, open_flags); free_path: kfree(full_path); reject: diff --git a/drivers/block/rnbd/rnbd-srv.h b/drivers/block/rnbd/rnbd-srv.h index 081bceaf4ae9..f5962fd31d62 100644 --- a/drivers/block/rnbd/rnbd-srv.h +++ b/drivers/block/rnbd/rnbd-srv.h @@ -46,7 +46,7 @@ struct rnbd_srv_dev { struct rnbd_srv_sess_dev { /* Entry inside rnbd_srv_dev struct */ struct list_head dev_list; - struct rnbd_dev *rnbd_dev; + struct block_device *bdev; struct rnbd_srv_session *sess; struct rnbd_srv_dev *dev; struct kobject kobj; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 6a4a94b4cdf4..2651bf41dde3 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -49,7 +49,9 @@ /* All UBLK_F_* have to be included into UBLK_F_ALL */ #define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY \ | UBLK_F_URING_CMD_COMP_IN_TASK \ - | UBLK_F_NEED_GET_DATA) + | UBLK_F_NEED_GET_DATA \ + | UBLK_F_USER_RECOVERY \ + | UBLK_F_USER_RECOVERY_REISSUE) /* All UBLK_PARAM_TYPE_* should be included here */ #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD) @@ -119,7 +121,7 @@ struct ublk_queue { unsigned long io_addr; /* mapped vm address */ unsigned int max_io_sz; - bool abort_work_pending; + bool force_abort; unsigned short nr_io_ready; /* how many ios setup */ struct ublk_device *dev; struct ublk_io ios[0]; @@ -161,6 +163,7 @@ struct ublk_device { * monitor each queue's daemon periodically */ struct delayed_work monitor_work; + struct work_struct quiesce_work; struct work_struct stop_work; }; @@ -323,6 +326,30 @@ static inline int ublk_queue_cmd_buf_size(struct ublk_device *ub, int q_id) PAGE_SIZE); } +static inline bool ublk_queue_can_use_recovery_reissue( + struct ublk_queue *ubq) +{ + if ((ubq->flags & UBLK_F_USER_RECOVERY) && + (ubq->flags & UBLK_F_USER_RECOVERY_REISSUE)) + return true; + return false; +} + +static inline bool ublk_queue_can_use_recovery( + struct ublk_queue *ubq) +{ + if (ubq->flags & UBLK_F_USER_RECOVERY) + return true; + return false; +} + +static inline bool ublk_can_use_recovery(struct ublk_device *ub) +{ + if (ub->dev_info.flags & UBLK_F_USER_RECOVERY) + return true; + return false; +} + static void ublk_free_disk(struct gendisk *disk) { struct ublk_device *ub = disk->private_data; @@ -612,13 +639,17 @@ static void ublk_complete_rq(struct request *req) * Also aborting may not be started yet, keep in mind that one failed * request may be issued by block layer again. */ -static void __ublk_fail_req(struct ublk_io *io, struct request *req) +static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io, + struct request *req) { WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE); if (!(io->flags & UBLK_IO_FLAG_ABORTED)) { io->flags |= UBLK_IO_FLAG_ABORTED; - blk_mq_end_request(req, BLK_STS_IOERR); + if (ublk_queue_can_use_recovery_reissue(ubq)) + blk_mq_requeue_request(req, false); + else + blk_mq_end_request(req, BLK_STS_IOERR); } } @@ -639,22 +670,40 @@ static void ubq_complete_io_cmd(struct ublk_io *io, int res) #define UBLK_REQUEUE_DELAY_MS 3 +static inline void __ublk_abort_rq(struct ublk_queue *ubq, + struct request *rq) +{ + /* We cannot process this rq so just requeue it. */ + if (ublk_queue_can_use_recovery(ubq)) + blk_mq_requeue_request(rq, false); + else + blk_mq_end_request(rq, BLK_STS_IOERR); + + mod_delayed_work(system_wq, &ubq->dev->monitor_work, 0); +} + static inline void __ublk_rq_task_work(struct request *req) { struct ublk_queue *ubq = req->mq_hctx->driver_data; - struct ublk_device *ub = ubq->dev; int tag = req->tag; struct ublk_io *io = &ubq->ios[tag]; - bool task_exiting = current != ubq->ubq_daemon || ubq_daemon_is_dying(ubq); unsigned int mapped_bytes; pr_devel("%s: complete: op %d, qid %d tag %d io_flags %x addr %llx\n", __func__, io->cmd->cmd_op, ubq->q_id, req->tag, io->flags, ublk_get_iod(ubq, req->tag)->addr); - if (unlikely(task_exiting)) { - blk_mq_end_request(req, BLK_STS_IOERR); - mod_delayed_work(system_wq, &ub->monitor_work, 0); + /* + * Task is exiting if either: + * + * (1) current != ubq_daemon. + * io_uring_cmd_complete_in_task() tries to run task_work + * in a workqueue if ubq_daemon(cmd's task) is PF_EXITING. + * + * (2) current->flags & PF_EXITING. + */ + if (unlikely(current != ubq->ubq_daemon || current->flags & PF_EXITING)) { + __ublk_abort_rq(ubq, req); return; } @@ -739,13 +788,24 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, res = ublk_setup_iod(ubq, rq); if (unlikely(res != BLK_STS_OK)) return BLK_STS_IOERR; + /* With recovery feature enabled, force_abort is set in + * ublk_stop_dev() before calling del_gendisk(). We have to + * abort all requeued and new rqs here to let del_gendisk() + * move on. Besides, we cannot not call io_uring_cmd_complete_in_task() + * to avoid UAF on io_uring ctx. + * + * Note: force_abort is guaranteed to be seen because it is set + * before request queue is unqiuesced. + */ + if (ublk_queue_can_use_recovery(ubq) && unlikely(ubq->force_abort)) + return BLK_STS_IOERR; blk_mq_start_request(bd->rq); if (unlikely(ubq_daemon_is_dying(ubq))) { fail: - mod_delayed_work(system_wq, &ubq->dev->monitor_work, 0); - return BLK_STS_IOERR; + __ublk_abort_rq(ubq, rq); + return BLK_STS_OK; } if (ublk_can_use_task_work(ubq)) { @@ -916,7 +976,7 @@ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq) */ rq = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], i); if (rq) - __ublk_fail_req(io, rq); + __ublk_fail_req(ubq, io, rq); } } ublk_put_device(ub); @@ -932,7 +992,10 @@ static void ublk_daemon_monitor_work(struct work_struct *work) struct ublk_queue *ubq = ublk_get_queue(ub, i); if (ubq_daemon_is_dying(ubq)) { - schedule_work(&ub->stop_work); + if (ublk_queue_can_use_recovery(ubq)) + schedule_work(&ub->quiesce_work); + else + schedule_work(&ub->stop_work); /* abort queue is for making forward progress */ ublk_abort_queue(ub, ubq); @@ -940,12 +1003,13 @@ static void ublk_daemon_monitor_work(struct work_struct *work) } /* - * We can't schedule monitor work after ublk_remove() is started. + * We can't schedule monitor work after ub's state is not UBLK_S_DEV_LIVE. + * after ublk_remove() or __ublk_quiesce_dev() is started. * * No need ub->mutex, monitor work are canceled after state is marked - * as DEAD, so DEAD state is observed reliably. + * as not LIVE, so new state is observed reliably. */ - if (ub->dev_info.state != UBLK_S_DEV_DEAD) + if (ub->dev_info.state == UBLK_S_DEV_LIVE) schedule_delayed_work(&ub->monitor_work, UBLK_DAEMON_MONITOR_PERIOD); } @@ -982,12 +1046,97 @@ static void ublk_cancel_dev(struct ublk_device *ub) ublk_cancel_queue(ublk_get_queue(ub, i)); } -static void ublk_stop_dev(struct ublk_device *ub) +static bool ublk_check_inflight_rq(struct request *rq, void *data) +{ + bool *idle = data; + + if (blk_mq_request_started(rq)) { + *idle = false; + return false; + } + return true; +} + +static void ublk_wait_tagset_rqs_idle(struct ublk_device *ub) { + bool idle; + + WARN_ON_ONCE(!blk_queue_quiesced(ub->ub_disk->queue)); + while (true) { + idle = true; + blk_mq_tagset_busy_iter(&ub->tag_set, + ublk_check_inflight_rq, &idle); + if (idle) + break; + msleep(UBLK_REQUEUE_DELAY_MS); + } +} + +static void __ublk_quiesce_dev(struct ublk_device *ub) +{ + pr_devel("%s: quiesce ub: dev_id %d state %s\n", + __func__, ub->dev_info.dev_id, + ub->dev_info.state == UBLK_S_DEV_LIVE ? + "LIVE" : "QUIESCED"); + blk_mq_quiesce_queue(ub->ub_disk->queue); + ublk_wait_tagset_rqs_idle(ub); + ub->dev_info.state = UBLK_S_DEV_QUIESCED; + ublk_cancel_dev(ub); + /* we are going to release task_struct of ubq_daemon and resets + * ->ubq_daemon to NULL. So in monitor_work, check on ubq_daemon causes UAF. + * Besides, monitor_work is not necessary in QUIESCED state since we have + * already scheduled quiesce_work and quiesced all ubqs. + * + * Do not let monitor_work schedule itself if state it QUIESCED. And we cancel + * it here and re-schedule it in END_USER_RECOVERY to avoid UAF. + */ + cancel_delayed_work_sync(&ub->monitor_work); +} + +static void ublk_quiesce_work_fn(struct work_struct *work) +{ + struct ublk_device *ub = + container_of(work, struct ublk_device, quiesce_work); + mutex_lock(&ub->mutex); if (ub->dev_info.state != UBLK_S_DEV_LIVE) goto unlock; + __ublk_quiesce_dev(ub); + unlock: + mutex_unlock(&ub->mutex); +} + +static void ublk_unquiesce_dev(struct ublk_device *ub) +{ + int i; + + pr_devel("%s: unquiesce ub: dev_id %d state %s\n", + __func__, ub->dev_info.dev_id, + ub->dev_info.state == UBLK_S_DEV_LIVE ? + "LIVE" : "QUIESCED"); + /* quiesce_work has run. We let requeued rqs be aborted + * before running fallback_wq. "force_abort" must be seen + * after request queue is unqiuesced. Then del_gendisk() + * can move on. + */ + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) + ublk_get_queue(ub, i)->force_abort = true; + + blk_mq_unquiesce_queue(ub->ub_disk->queue); + /* We may have requeued some rqs in ublk_quiesce_queue() */ + blk_mq_kick_requeue_list(ub->ub_disk->queue); +} +static void ublk_stop_dev(struct ublk_device *ub) +{ + mutex_lock(&ub->mutex); + if (ub->dev_info.state == UBLK_S_DEV_DEAD) + goto unlock; + if (ublk_can_use_recovery(ub)) { + if (ub->dev_info.state == UBLK_S_DEV_LIVE) + __ublk_quiesce_dev(ub); + ublk_unquiesce_dev(ub); + } del_gendisk(ub->ub_disk); ub->dev_info.state = UBLK_S_DEV_DEAD; ub->dev_info.ublksrv_pid = -1; @@ -1311,6 +1460,7 @@ static void ublk_remove(struct ublk_device *ub) { ublk_stop_dev(ub); cancel_work_sync(&ub->stop_work); + cancel_work_sync(&ub->quiesce_work); cdev_device_del(&ub->cdev, &ub->cdev_dev); put_device(&ub->cdev_dev); } @@ -1487,6 +1637,7 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) goto out_unlock; mutex_init(&ub->mutex); spin_lock_init(&ub->mm_lock); + INIT_WORK(&ub->quiesce_work, ublk_quiesce_work_fn); INIT_WORK(&ub->stop_work, ublk_stop_work_fn); INIT_DELAYED_WORK(&ub->monitor_work, ublk_daemon_monitor_work); @@ -1607,6 +1758,7 @@ static int ublk_ctrl_stop_dev(struct io_uring_cmd *cmd) ublk_stop_dev(ub); cancel_work_sync(&ub->stop_work); + cancel_work_sync(&ub->quiesce_work); ublk_put_device(ub); return 0; @@ -1709,6 +1861,116 @@ static int ublk_ctrl_set_params(struct io_uring_cmd *cmd) return ret; } +static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) +{ + int i; + + WARN_ON_ONCE(!(ubq->ubq_daemon && ubq_daemon_is_dying(ubq))); + /* All old ioucmds have to be completed */ + WARN_ON_ONCE(ubq->nr_io_ready); + /* old daemon is PF_EXITING, put it now */ + put_task_struct(ubq->ubq_daemon); + /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */ + ubq->ubq_daemon = NULL; + + for (i = 0; i < ubq->q_depth; i++) { + struct ublk_io *io = &ubq->ios[i]; + + /* forget everything now and be ready for new FETCH_REQ */ + io->flags = 0; + io->cmd = NULL; + io->addr = 0; + } +} + +static int ublk_ctrl_start_recovery(struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + struct ublk_device *ub; + int ret = -EINVAL; + int i; + + ub = ublk_get_device_from_id(header->dev_id); + if (!ub) + return ret; + + mutex_lock(&ub->mutex); + if (!ublk_can_use_recovery(ub)) + goto out_unlock; + /* + * START_RECOVERY is only allowd after: + * + * (1) UB_STATE_OPEN is not set, which means the dying process is exited + * and related io_uring ctx is freed so file struct of /dev/ublkcX is + * released. + * + * (2) UBLK_S_DEV_QUIESCED is set, which means the quiesce_work: + * (a)has quiesced request queue + * (b)has requeued every inflight rqs whose io_flags is ACTIVE + * (c)has requeued/aborted every inflight rqs whose io_flags is NOT ACTIVE + * (d)has completed/camceled all ioucmds owned by ther dying process + */ + if (test_bit(UB_STATE_OPEN, &ub->state) || + ub->dev_info.state != UBLK_S_DEV_QUIESCED) { + ret = -EBUSY; + goto out_unlock; + } + pr_devel("%s: start recovery for dev id %d.\n", __func__, header->dev_id); + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) + ublk_queue_reinit(ub, ublk_get_queue(ub, i)); + /* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */ + ub->mm = NULL; + ub->nr_queues_ready = 0; + init_completion(&ub->completion); + ret = 0; + out_unlock: + mutex_unlock(&ub->mutex); + ublk_put_device(ub); + return ret; +} + +static int ublk_ctrl_end_recovery(struct io_uring_cmd *cmd) +{ + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + int ublksrv_pid = (int)header->data[0]; + struct ublk_device *ub; + int ret = -EINVAL; + + ub = ublk_get_device_from_id(header->dev_id); + if (!ub) + return ret; + + pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n", + __func__, ub->dev_info.nr_hw_queues, header->dev_id); + /* wait until new ubq_daemon sending all FETCH_REQ */ + wait_for_completion_interruptible(&ub->completion); + pr_devel("%s: All new ubq_daemons(nr: %d) are ready, dev id %d\n", + __func__, ub->dev_info.nr_hw_queues, header->dev_id); + + mutex_lock(&ub->mutex); + if (!ublk_can_use_recovery(ub)) + goto out_unlock; + + if (ub->dev_info.state != UBLK_S_DEV_QUIESCED) { + ret = -EBUSY; + goto out_unlock; + } + ub->dev_info.ublksrv_pid = ublksrv_pid; + pr_devel("%s: new ublksrv_pid %d, dev id %d\n", + __func__, ublksrv_pid, header->dev_id); + blk_mq_unquiesce_queue(ub->ub_disk->queue); + pr_devel("%s: queue unquiesced, dev id %d.\n", + __func__, header->dev_id); + blk_mq_kick_requeue_list(ub->ub_disk->queue); + ub->dev_info.state = UBLK_S_DEV_LIVE; + schedule_delayed_work(&ub->monitor_work, UBLK_DAEMON_MONITOR_PERIOD); + ret = 0; + out_unlock: + mutex_unlock(&ub->mutex); + ublk_put_device(ub); + return ret; +} + static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { @@ -1750,6 +2012,12 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, case UBLK_CMD_SET_PARAMS: ret = ublk_ctrl_set_params(cmd); break; + case UBLK_CMD_START_USER_RECOVERY: + ret = ublk_ctrl_start_recovery(cmd); + break; + case UBLK_CMD_END_USER_RECOVERY: + ret = ublk_ctrl_end_recovery(cmd); + break; default: break; } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 30255fcaf181..23c5a1239520 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -802,7 +802,7 @@ static const struct attribute_group *virtblk_attr_groups[] = { NULL, }; -static int virtblk_map_queues(struct blk_mq_tag_set *set) +static void virtblk_map_queues(struct blk_mq_tag_set *set) { struct virtio_blk *vblk = set->driver_data; int i, qoff; @@ -827,8 +827,6 @@ static int virtblk_map_queues(struct blk_mq_tag_set *set) else blk_mq_virtio_map_queues(&set->map[i], vblk->vdev, 0); } - - return 0; } static void virtblk_complete_batch(struct io_comp_batch *iob) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 226ea76cc819..e551433cd107 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -499,7 +499,7 @@ static ssize_t backing_dev_store(struct device *dev, goto out; } - strlcpy(file_name, buf, PATH_MAX); + strscpy(file_name, buf, PATH_MAX); /* ignore trailing newline */ sz = strlen(file_name); if (sz > 0 && file_name[sz - 1] == '\n') @@ -1031,7 +1031,7 @@ static ssize_t comp_algorithm_store(struct device *dev, char compressor[ARRAY_SIZE(zram->compressor)]; size_t sz; - strlcpy(compressor, buf, sizeof(compressor)); + strscpy(compressor, buf, sizeof(compressor)); /* ignore trailing newline */ sz = strlen(compressor); if (sz > 0 && compressor[sz - 1] == '\n') @@ -1974,7 +1974,7 @@ static int zram_add(void) if (ret) goto out_cleanup_disk; - strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor)); + strscpy(zram->compressor, default_compressor, sizeof(zram->compressor)); zram_debugfs_register(zram); pr_info("Added device: %s\n", zram->disk->disk_name); diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index 62c2b7ac4339..4407203e0c9b 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -449,6 +449,9 @@ static int quad8_events_configure(struct counter_device *counter) return -EINVAL; } + /* Enable IRQ line */ + irq_enabled |= BIT(event_node->channel); + /* Skip configuration if it is the same as previously set */ if (priv->irq_trigger[event_node->channel] == next_irq_trigger) continue; @@ -462,9 +465,6 @@ static int quad8_events_configure(struct counter_device *counter) priv->irq_trigger[event_node->channel] << 3; iowrite8(QUAD8_CTR_IOR | ior_cfg, &priv->reg->channel[event_node->channel].control); - - /* Enable IRQ line */ - irq_enabled |= BIT(event_node->channel); } iowrite8(irq_enabled, &priv->reg->index_interrupt); diff --git a/drivers/dax/hmem/device.c b/drivers/dax/hmem/device.c index cb6401c9e9a4..acf31cc1dbcc 100644 --- a/drivers/dax/hmem/device.c +++ b/drivers/dax/hmem/device.c @@ -15,6 +15,7 @@ void hmem_register_device(int target_nid, struct resource *r) .start = r->start, .end = r->end, .flags = IORESOURCE_MEM, + .desc = IORES_DESC_SOFT_RESERVED, }; struct platform_device *pdev; struct memregion_info info; diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c index d4f1e4e9603a..85e00701473c 100644 --- a/drivers/dma/ti/k3-udma-private.c +++ b/drivers/dma/ti/k3-udma-private.c @@ -31,14 +31,14 @@ struct udma_dev *of_xudma_dev_get(struct device_node *np, const char *property) } pdev = of_find_device_by_node(udma_node); + if (np != udma_node) + of_node_put(udma_node); + if (!pdev) { pr_debug("UDMA device not found\n"); return ERR_PTR(-EPROBE_DEFER); } - if (np != udma_node) - of_node_put(udma_node); - ud = platform_get_drvdata(pdev); if (!ud) { pr_debug("UDMA has not been probed\n"); diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index 6276934d4d2b..8cd4e69dc7b4 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -3040,9 +3040,10 @@ static int xilinx_dma_probe(struct platform_device *pdev) /* Request and map I/O memory */ xdev->regs = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(xdev->regs)) - return PTR_ERR(xdev->regs); - + if (IS_ERR(xdev->regs)) { + err = PTR_ERR(xdev->regs); + goto disable_clks; + } /* Retrieve the DMA engine properties from the device tree */ xdev->max_buffer_len = GENMASK(XILINX_DMA_MAX_TRANS_LEN_MAX - 1, 0); xdev->s2mm_chan_id = xdev->dma_config->max_channels / 2; @@ -3070,7 +3071,7 @@ static int xilinx_dma_probe(struct platform_device *pdev) if (err < 0) { dev_err(xdev->dev, "missing xlnx,num-fstores property\n"); - return err; + goto disable_clks; } err = of_property_read_u32(node, "xlnx,flush-fsync", @@ -3090,7 +3091,11 @@ static int xilinx_dma_probe(struct platform_device *pdev) xdev->ext_addr = false; /* Set the dma mask bits */ - dma_set_mask_and_coherent(xdev->dev, DMA_BIT_MASK(addr_width)); + err = dma_set_mask_and_coherent(xdev->dev, DMA_BIT_MASK(addr_width)); + if (err < 0) { + dev_err(xdev->dev, "DMA mask error %d\n", err); + goto disable_clks; + } /* Initialize the DMA engine */ xdev->common.dev = &pdev->dev; @@ -3137,7 +3142,7 @@ static int xilinx_dma_probe(struct platform_device *pdev) for_each_child_of_node(node, child) { err = xilinx_dma_child_probe(xdev, child); if (err < 0) - goto disable_clks; + goto error; } if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) { @@ -3172,12 +3177,12 @@ static int xilinx_dma_probe(struct platform_device *pdev) return 0; -disable_clks: - xdma_disable_allclks(xdev); error: for (i = 0; i < xdev->dma_config->max_channels; i++) if (xdev->chan[i]) xilinx_dma_chan_remove(xdev->chan[i]); +disable_clks: + xdma_disable_allclks(xdev); return err; } diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c index dc299ab36818..3f4ee3954384 100644 --- a/drivers/dma/xilinx/zynqmp_dma.c +++ b/drivers/dma/xilinx/zynqmp_dma.c @@ -849,7 +849,7 @@ static struct dma_async_tx_descriptor *zynqmp_dma_prep_memcpy( zynqmp_dma_desc_config_eod(chan, desc); async_tx_ack(&first->async_tx); - first->async_tx.flags = flags; + first->async_tx.flags = (enum dma_ctrl_flags)flags; return &first->async_tx; } diff --git a/drivers/firmware/arm_scmi/clock.c b/drivers/firmware/arm_scmi/clock.c index 3ed7ae0d6781..96060bf90a24 100644 --- a/drivers/firmware/arm_scmi/clock.c +++ b/drivers/firmware/arm_scmi/clock.c @@ -450,9 +450,13 @@ static int scmi_clock_count_get(const struct scmi_protocol_handle *ph) static const struct scmi_clock_info * scmi_clock_info_get(const struct scmi_protocol_handle *ph, u32 clk_id) { + struct scmi_clock_info *clk; struct clock_info *ci = ph->get_priv(ph); - struct scmi_clock_info *clk = ci->clk + clk_id; + if (clk_id >= ci->num_clocks) + return NULL; + + clk = ci->clk + clk_id; if (!clk->name[0]) return NULL; diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c index 8abace56b958..f42dad997ac9 100644 --- a/drivers/firmware/arm_scmi/optee.c +++ b/drivers/firmware/arm_scmi/optee.c @@ -106,6 +106,7 @@ enum scmi_optee_pta_cmd { * @channel_id: OP-TEE channel ID used for this transport * @tee_session: TEE session identifier * @caps: OP-TEE SCMI channel capabilities + * @rx_len: Response size * @mu: Mutex protection on channel access * @cinfo: SCMI channel information * @shmem: Virtual base address of the shared memory diff --git a/drivers/firmware/arm_scmi/reset.c b/drivers/firmware/arm_scmi/reset.c index 673f3eb498f4..e9afa8cab730 100644 --- a/drivers/firmware/arm_scmi/reset.c +++ b/drivers/firmware/arm_scmi/reset.c @@ -166,9 +166,13 @@ static int scmi_domain_reset(const struct scmi_protocol_handle *ph, u32 domain, struct scmi_xfer *t; struct scmi_msg_reset_domain_reset *dom; struct scmi_reset_info *pi = ph->get_priv(ph); - struct reset_dom_info *rdom = pi->dom_info + domain; + struct reset_dom_info *rdom; - if (rdom->async_reset) + if (domain >= pi->num_domains) + return -EINVAL; + + rdom = pi->dom_info + domain; + if (rdom->async_reset && flags & AUTONOMOUS_RESET) flags |= ASYNCHRONOUS_RESET; ret = ph->xops->xfer_get_init(ph, RESET, sizeof(*dom), 0, &t); @@ -180,7 +184,7 @@ static int scmi_domain_reset(const struct scmi_protocol_handle *ph, u32 domain, dom->flags = cpu_to_le32(flags); dom->reset_state = cpu_to_le32(state); - if (rdom->async_reset) + if (flags & ASYNCHRONOUS_RESET) ret = ph->xops->do_xfer_with_response(ph, t); else ret = ph->xops->do_xfer(ph, t); diff --git a/drivers/firmware/arm_scmi/scmi_pm_domain.c b/drivers/firmware/arm_scmi/scmi_pm_domain.c index 581d34c95769..4e27c3d66a83 100644 --- a/drivers/firmware/arm_scmi/scmi_pm_domain.c +++ b/drivers/firmware/arm_scmi/scmi_pm_domain.c @@ -138,9 +138,28 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev) scmi_pd_data->domains = domains; scmi_pd_data->num_domains = num_domains; + dev_set_drvdata(dev, scmi_pd_data); + return of_genpd_add_provider_onecell(np, scmi_pd_data); } +static void scmi_pm_domain_remove(struct scmi_device *sdev) +{ + int i; + struct genpd_onecell_data *scmi_pd_data; + struct device *dev = &sdev->dev; + struct device_node *np = dev->of_node; + + of_genpd_del_provider(np); + + scmi_pd_data = dev_get_drvdata(dev); + for (i = 0; i < scmi_pd_data->num_domains; i++) { + if (!scmi_pd_data->domains[i]) + continue; + pm_genpd_remove(scmi_pd_data->domains[i]); + } +} + static const struct scmi_device_id scmi_id_table[] = { { SCMI_PROTOCOL_POWER, "genpd" }, { }, @@ -150,6 +169,7 @@ MODULE_DEVICE_TABLE(scmi, scmi_id_table); static struct scmi_driver scmi_power_domain_driver = { .name = "scmi-power-domain", .probe = scmi_pm_domain_probe, + .remove = scmi_pm_domain_remove, .id_table = scmi_id_table, }; module_scmi_driver(scmi_power_domain_driver); diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c index 7288c6117838..0b5853fa9d87 100644 --- a/drivers/firmware/arm_scmi/sensors.c +++ b/drivers/firmware/arm_scmi/sensors.c @@ -762,6 +762,10 @@ static int scmi_sensor_config_get(const struct scmi_protocol_handle *ph, { int ret; struct scmi_xfer *t; + struct sensors_info *si = ph->get_priv(ph); + + if (sensor_id >= si->num_sensors) + return -EINVAL; ret = ph->xops->xfer_get_init(ph, SENSOR_CONFIG_GET, sizeof(__le32), sizeof(__le32), &t); @@ -771,7 +775,6 @@ static int scmi_sensor_config_get(const struct scmi_protocol_handle *ph, put_unaligned_le32(sensor_id, t->tx.buf); ret = ph->xops->do_xfer(ph, t); if (!ret) { - struct sensors_info *si = ph->get_priv(ph); struct scmi_sensor_info *s = si->sensors + sensor_id; *sensor_config = get_unaligned_le64(t->rx.buf); @@ -788,6 +791,10 @@ static int scmi_sensor_config_set(const struct scmi_protocol_handle *ph, int ret; struct scmi_xfer *t; struct scmi_msg_sensor_config_set *msg; + struct sensors_info *si = ph->get_priv(ph); + + if (sensor_id >= si->num_sensors) + return -EINVAL; ret = ph->xops->xfer_get_init(ph, SENSOR_CONFIG_SET, sizeof(*msg), 0, &t); @@ -800,7 +807,6 @@ static int scmi_sensor_config_set(const struct scmi_protocol_handle *ph, ret = ph->xops->do_xfer(ph, t); if (!ret) { - struct sensors_info *si = ph->get_priv(ph); struct scmi_sensor_info *s = si->sensors + sensor_id; s->sensor_config = sensor_config; @@ -831,8 +837,11 @@ static int scmi_sensor_reading_get(const struct scmi_protocol_handle *ph, int ret; struct scmi_xfer *t; struct scmi_msg_sensor_reading_get *sensor; + struct scmi_sensor_info *s; struct sensors_info *si = ph->get_priv(ph); - struct scmi_sensor_info *s = si->sensors + sensor_id; + + if (sensor_id >= si->num_sensors) + return -EINVAL; ret = ph->xops->xfer_get_init(ph, SENSOR_READING_GET, sizeof(*sensor), 0, &t); @@ -841,6 +850,7 @@ static int scmi_sensor_reading_get(const struct scmi_protocol_handle *ph, sensor = t->tx.buf; sensor->id = cpu_to_le32(sensor_id); + s = si->sensors + sensor_id; if (s->async) { sensor->flags = cpu_to_le32(SENSOR_READ_ASYNC); ret = ph->xops->do_xfer_with_response(ph, t); @@ -895,9 +905,13 @@ scmi_sensor_reading_get_timestamped(const struct scmi_protocol_handle *ph, int ret; struct scmi_xfer *t; struct scmi_msg_sensor_reading_get *sensor; + struct scmi_sensor_info *s; struct sensors_info *si = ph->get_priv(ph); - struct scmi_sensor_info *s = si->sensors + sensor_id; + if (sensor_id >= si->num_sensors) + return -EINVAL; + + s = si->sensors + sensor_id; if (!count || !readings || (!s->num_axis && count > 1) || (s->num_axis && count > s->num_axis)) return -EINVAL; @@ -948,6 +962,9 @@ scmi_sensor_info_get(const struct scmi_protocol_handle *ph, u32 sensor_id) { struct sensors_info *si = ph->get_priv(ph); + if (sensor_id >= si->num_sensors) + return NULL; + return si->sensors + sensor_id; } diff --git a/drivers/firmware/efi/efibc.c b/drivers/firmware/efi/efibc.c index 8ced7af8e56d..4f9fb086eab7 100644 --- a/drivers/firmware/efi/efibc.c +++ b/drivers/firmware/efi/efibc.c @@ -48,6 +48,9 @@ static int efibc_reboot_notifier_call(struct notifier_block *notifier, return NOTIFY_DONE; wdata = kmalloc(MAX_DATA_LEN * sizeof(efi_char16_t), GFP_KERNEL); + if (!wdata) + return NOTIFY_DONE; + for (l = 0; l < MAX_DATA_LEN - 1 && str[l] != '\0'; l++) wdata[l] = str[l]; wdata[l] = L'\0'; diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c index 8a18930f3eb6..516f4f0069bd 100644 --- a/drivers/firmware/efi/libstub/secureboot.c +++ b/drivers/firmware/efi/libstub/secureboot.c @@ -14,7 +14,7 @@ /* SHIM variables */ static const efi_guid_t shim_guid = EFI_SHIM_LOCK_GUID; -static const efi_char16_t shim_MokSBState_name[] = L"MokSBState"; +static const efi_char16_t shim_MokSBState_name[] = L"MokSBStateRT"; static efi_status_t get_var(efi_char16_t *name, efi_guid_t *vendor, u32 *attr, unsigned long *data_size, void *data) @@ -43,8 +43,8 @@ enum efi_secureboot_mode efi_get_secureboot(void) /* * See if a user has put the shim into insecure mode. If so, and if the - * variable doesn't have the runtime attribute set, we might as well - * honor that. + * variable doesn't have the non-volatile attribute set, we might as + * well honor that. */ size = sizeof(moksbstate); status = get_efi_var(shim_MokSBState_name, &shim_guid, @@ -53,7 +53,7 @@ enum efi_secureboot_mode efi_get_secureboot(void) /* If it fails, we don't care why. Default to secure */ if (status != EFI_SUCCESS) goto secure_boot_enabled; - if (!(attr & EFI_VARIABLE_RUNTIME_ACCESS) && moksbstate == 1) + if (!(attr & EFI_VARIABLE_NON_VOLATILE) && moksbstate == 1) return efi_secureboot_mode_disabled; secure_boot_enabled: diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 43ca665af610..7a7abc8959d2 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -516,6 +516,13 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, hdr->ramdisk_image = 0; hdr->ramdisk_size = 0; + /* + * Disregard any setup data that was provided by the bootloader: + * setup_data could be pointing anywhere, and we have no way of + * authenticating or validating the payload. + */ + hdr->setup_data = 0; + efi_stub_entry(handle, sys_table_arg, boot_params); /* not reached */ diff --git a/drivers/fpga/intel-m10-bmc-sec-update.c b/drivers/fpga/intel-m10-bmc-sec-update.c index 72c677c910de..133e511355c9 100644 --- a/drivers/fpga/intel-m10-bmc-sec-update.c +++ b/drivers/fpga/intel-m10-bmc-sec-update.c @@ -148,10 +148,6 @@ static ssize_t flash_count_show(struct device *dev, stride = regmap_get_reg_stride(sec->m10bmc->regmap); num_bits = FLASH_COUNT_SIZE * 8; - flash_buf = kmalloc(FLASH_COUNT_SIZE, GFP_KERNEL); - if (!flash_buf) - return -ENOMEM; - if (FLASH_COUNT_SIZE % stride) { dev_err(sec->dev, "FLASH_COUNT_SIZE (0x%x) not aligned to stride (0x%x)\n", @@ -160,6 +156,10 @@ static ssize_t flash_count_show(struct device *dev, return -EINVAL; } + flash_buf = kmalloc(FLASH_COUNT_SIZE, GFP_KERNEL); + if (!flash_buf) + return -ENOMEM; + ret = regmap_bulk_read(sec->m10bmc->regmap, STAGING_FLASH_COUNT, flash_buf, FLASH_COUNT_SIZE / stride); if (ret) { diff --git a/drivers/gpio/gpio-ftgpio010.c b/drivers/gpio/gpio-ftgpio010.c index f422c3e129a0..f77a965f5780 100644 --- a/drivers/gpio/gpio-ftgpio010.c +++ b/drivers/gpio/gpio-ftgpio010.c @@ -41,14 +41,12 @@ * struct ftgpio_gpio - Gemini GPIO state container * @dev: containing device for this instance * @gc: gpiochip for this instance - * @irq: irqchip for this instance * @base: remapped I/O-memory base * @clk: silicon clock */ struct ftgpio_gpio { struct device *dev; struct gpio_chip gc; - struct irq_chip irq; void __iomem *base; struct clk *clk; }; @@ -70,6 +68,7 @@ static void ftgpio_gpio_mask_irq(struct irq_data *d) val = readl(g->base + GPIO_INT_EN); val &= ~BIT(irqd_to_hwirq(d)); writel(val, g->base + GPIO_INT_EN); + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); } static void ftgpio_gpio_unmask_irq(struct irq_data *d) @@ -78,6 +77,7 @@ static void ftgpio_gpio_unmask_irq(struct irq_data *d) struct ftgpio_gpio *g = gpiochip_get_data(gc); u32 val; + gpiochip_enable_irq(gc, irqd_to_hwirq(d)); val = readl(g->base + GPIO_INT_EN); val |= BIT(irqd_to_hwirq(d)); writel(val, g->base + GPIO_INT_EN); @@ -221,6 +221,16 @@ static int ftgpio_gpio_set_config(struct gpio_chip *gc, unsigned int offset, return 0; } +static const struct irq_chip ftgpio_irq_chip = { + .name = "FTGPIO010", + .irq_ack = ftgpio_gpio_ack_irq, + .irq_mask = ftgpio_gpio_mask_irq, + .irq_unmask = ftgpio_gpio_unmask_irq, + .irq_set_type = ftgpio_gpio_set_irq_type, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int ftgpio_gpio_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -277,14 +287,8 @@ static int ftgpio_gpio_probe(struct platform_device *pdev) if (!IS_ERR(g->clk)) g->gc.set_config = ftgpio_gpio_set_config; - g->irq.name = "FTGPIO010"; - g->irq.irq_ack = ftgpio_gpio_ack_irq; - g->irq.irq_mask = ftgpio_gpio_mask_irq; - g->irq.irq_unmask = ftgpio_gpio_unmask_irq; - g->irq.irq_set_type = ftgpio_gpio_set_irq_type; - girq = &g->gc.irq; - girq->chip = &g->irq; + gpio_irq_chip_set_chip(girq, &ftgpio_irq_chip); girq->parent_handler = ftgpio_gpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(dev, 1, sizeof(*girq->parents), diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index a2e505a7545c..523dfd17dd92 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -533,8 +533,10 @@ static int __init gpio_mockup_register_chip(int idx) } fwnode = fwnode_create_software_node(properties, NULL); - if (IS_ERR(fwnode)) + if (IS_ERR(fwnode)) { + kfree_strarray(line_names, ngpio); return PTR_ERR(fwnode); + } pdevinfo.name = "gpio-mockup"; pdevinfo.id = idx; @@ -597,9 +599,9 @@ static int __init gpio_mockup_init(void) static void __exit gpio_mockup_exit(void) { + gpio_mockup_unregister_pdevs(); debugfs_remove_recursive(gpio_mockup_dbg_dir); platform_driver_unregister(&gpio_mockup_driver); - gpio_mockup_unregister_pdevs(); } module_init(gpio_mockup_init); diff --git a/drivers/gpio/gpio-tqmx86.c b/drivers/gpio/gpio-tqmx86.c index fa4bc7481f9a..e739dcea61b2 100644 --- a/drivers/gpio/gpio-tqmx86.c +++ b/drivers/gpio/gpio-tqmx86.c @@ -307,6 +307,8 @@ static int tqmx86_gpio_probe(struct platform_device *pdev) girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_simple_irq; girq->init_valid_mask = tqmx86_init_irq_valid_mask; + + irq_domain_set_pm_device(girq->domain, dev); } ret = devm_gpiochip_add_data(dev, chip, gpio); @@ -315,8 +317,6 @@ static int tqmx86_gpio_probe(struct platform_device *pdev) goto out_pm_dis; } - irq_domain_set_pm_device(girq->domain, dev); - dev_info(dev, "GPIO functionality initialized with %d pins\n", chip->ngpio); diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index f8041d4898d1..92f185575e94 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -1986,7 +1986,6 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) ret = -ENODEV; goto out_free_le; } - le->irq = irq; if (eflags & GPIOEVENT_REQUEST_RISING_EDGE) irqflags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ? @@ -2000,7 +1999,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) init_waitqueue_head(&le->wait); /* Request a thread to read the events */ - ret = request_threaded_irq(le->irq, + ret = request_threaded_irq(irq, lineevent_irq_handler, lineevent_irq_thread, irqflags, @@ -2009,6 +2008,8 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) if (ret) goto out_free_le; + le->irq = irq; + fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC); if (fd < 0) { ret = fd; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 5b09c8f4fe95..23998f727c7f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -39,6 +39,7 @@ #include <linux/pm_runtime.h> #include <drm/drm_crtc_helper.h> #include <drm/drm_damage_helper.h> +#include <drm/drm_drv.h> #include <drm/drm_edid.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_fb_helper.h> @@ -497,6 +498,11 @@ bool amdgpu_display_ddc_probe(struct amdgpu_connector *amdgpu_connector, static const struct drm_framebuffer_funcs amdgpu_fb_funcs = { .destroy = drm_gem_fb_destroy, .create_handle = drm_gem_fb_create_handle, +}; + +static const struct drm_framebuffer_funcs amdgpu_fb_funcs_atomic = { + .destroy = drm_gem_fb_destroy, + .create_handle = drm_gem_fb_create_handle, .dirty = drm_atomic_helper_dirtyfb, }; @@ -1102,7 +1108,10 @@ static int amdgpu_display_gem_fb_verify_and_init(struct drm_device *dev, if (ret) goto err; - ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); + if (drm_drv_uses_atomic_modeset(dev)) + ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs_atomic); + else + ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); if (ret) goto err; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index fe82b8b19a4e..0c546245793b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -181,6 +181,9 @@ int amdgpu_mes_init(struct amdgpu_device *adev) for (i = 0; i < AMDGPU_MES_MAX_SDMA_PIPES; i++) { if (adev->ip_versions[SDMA0_HWIP][0] < IP_VERSION(6, 0, 0)) adev->mes.sdma_hqd_mask[i] = i ? 0 : 0x3fc; + /* zero sdma_hqd_mask for non-existent engine */ + else if (adev->sdma.num_instances == 1) + adev->mes.sdma_hqd_mask[i] = i ? 0 : 0xfc; else adev->mes.sdma_hqd_mask[i] = 0xfc; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 59cac347baa3..690fd4f639f1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2484,8 +2484,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, /* Intentionally setting invalid PTE flag * combination to force a no-retry-fault */ - flags = AMDGPU_PTE_EXECUTABLE | AMDGPU_PDE_PTE | - AMDGPU_PTE_TF; + flags = AMDGPU_PTE_SNOOPED | AMDGPU_PTE_PRT; value = 0; } else if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) { /* Redirect the access to the dummy page */ diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 4603653916f5..67ca16a8027c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1103,10 +1103,13 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level, *flags |= AMDGPU_PDE_BFS(0x9); } else if (level == AMDGPU_VM_PDB0) { - if (*flags & AMDGPU_PDE_PTE) + if (*flags & AMDGPU_PDE_PTE) { *flags &= ~AMDGPU_PDE_PTE; - else + if (!(*flags & AMDGPU_PTE_VALID)) + *addr |= 1 << PAGE_SHIFT; + } else { *flags |= AMDGPU_PTE_TF; + } } } 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 5140d9c2bf3b..1efe7fa5bc58 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4759,7 +4759,7 @@ fill_dc_plane_info_and_addr(struct amdgpu_device *adev, plane_info->visible = true; plane_info->stereo_format = PLANE_STEREO_FORMAT_NONE; - plane_info->layer_index = 0; + plane_info->layer_index = plane_state->normalized_zpos; ret = fill_plane_color_attributes(plane_state, plane_info->format, &plane_info->color_space); @@ -4827,7 +4827,7 @@ static int fill_dc_plane_attributes(struct amdgpu_device *adev, dc_plane_state->global_alpha = plane_info.global_alpha; dc_plane_state->global_alpha_value = plane_info.global_alpha_value; dc_plane_state->dcc = plane_info.dcc; - dc_plane_state->layer_index = plane_info.layer_index; // Always returns 0 + dc_plane_state->layer_index = plane_info.layer_index; dc_plane_state->flip_int_enabled = true; /* @@ -9485,6 +9485,14 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, } } + /* + * DC consults the zpos (layer_index in DC terminology) to determine the + * hw plane on which to enable the hw cursor (see + * `dcn10_can_pipe_disable_cursor`). By now, all modified planes are in + * atomic state, so call drm helper to normalize zpos. + */ + drm_atomic_normalize_zpos(dev, state); + /* Remove exiting planes if they are modified */ for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) { ret = dm_update_plane_state(dc, state, plane, diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index c09be3f15fe6..23a299c929a1 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -99,7 +99,7 @@ static int dcn31_get_active_display_cnt_wa( return display_count; } -static void dcn31_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) +static void dcn31_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; @@ -110,9 +110,10 @@ static void dcn31_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) if (pipe->top_pipe || pipe->prev_odm_pipe) continue; if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) { - if (disable) + if (disable) { pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); - else + reset_sync_context_for_pipe(dc, context, i); + } else pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); } } @@ -211,11 +212,11 @@ void dcn31_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn31_disable_otg_wa(clk_mgr_base, true); + dcn31_disable_otg_wa(clk_mgr_base, context, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn31_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn31_disable_otg_wa(clk_mgr_base, false); + dcn31_disable_otg_wa(clk_mgr_base, context, false); update_dispclk = true; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index 9781a8dbc238..8559dcd80af0 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -119,7 +119,7 @@ static int dcn314_get_active_display_cnt_wa( return display_count; } -static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) +static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; @@ -129,11 +129,11 @@ static void dcn314_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) if (pipe->top_pipe || pipe->prev_odm_pipe) continue; - if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL || - dc_is_virtual_signal(pipe->stream->signal))) { - if (disable) + if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) { + if (disable) { pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); - else + reset_sync_context_for_pipe(dc, context, i); + } else pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); } } @@ -233,11 +233,11 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn314_disable_otg_wa(clk_mgr_base, true); + dcn314_disable_otg_wa(clk_mgr_base, context, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn314_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn314_disable_otg_wa(clk_mgr_base, false); + dcn314_disable_otg_wa(clk_mgr_base, context, false); update_dispclk = true; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index cc076621f5e6..98ad8e0fd2d8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -46,6 +46,9 @@ #define TO_CLK_MGR_DCN315(clk_mgr)\ container_of(clk_mgr, struct clk_mgr_dcn315, base) +#define UNSUPPORTED_DCFCLK 10000000 +#define MIN_DPP_DISP_CLK 100000 + static int dcn315_get_active_display_cnt_wa( struct dc *dc, struct dc_state *context) @@ -79,7 +82,7 @@ static int dcn315_get_active_display_cnt_wa( return display_count; } -static void dcn315_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) +static void dcn315_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; @@ -91,9 +94,10 @@ static void dcn315_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) continue; if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL || dc_is_virtual_signal(pipe->stream->signal))) { - if (disable) + if (disable) { pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); - else + reset_sync_context_for_pipe(dc, context, i); + } else pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); } } @@ -146,6 +150,9 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, } } + /* Lock pstate by requesting unsupported dcfclk if change is unsupported */ + if (!new_clocks->p_state_change_support) + new_clocks->dcfclk_khz = UNSUPPORTED_DCFCLK; if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, clk_mgr_base->clks.dcfclk_khz)) { clk_mgr_base->clks.dcfclk_khz = new_clocks->dcfclk_khz; dcn315_smu_set_hard_min_dcfclk(clk_mgr, clk_mgr_base->clks.dcfclk_khz); @@ -159,10 +166,10 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, // workaround: Limit dppclk to 100Mhz to avoid lower eDP panel switch to plus 4K monitor underflow. if (!IS_DIAG_DC(dc->ctx->dce_environment)) { - if (new_clocks->dppclk_khz < 100000) - new_clocks->dppclk_khz = 100000; - if (new_clocks->dispclk_khz < 100000) - new_clocks->dispclk_khz = 100000; + if (new_clocks->dppclk_khz < MIN_DPP_DISP_CLK) + new_clocks->dppclk_khz = MIN_DPP_DISP_CLK; + if (new_clocks->dispclk_khz < MIN_DPP_DISP_CLK) + new_clocks->dispclk_khz = MIN_DPP_DISP_CLK; } if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) { @@ -175,12 +182,12 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { /* No need to apply the w/a if we haven't taken over from bios yet */ if (clk_mgr_base->clks.dispclk_khz) - dcn315_disable_otg_wa(clk_mgr_base, true); + dcn315_disable_otg_wa(clk_mgr_base, context, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn315_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); if (clk_mgr_base->clks.dispclk_khz) - dcn315_disable_otg_wa(clk_mgr_base, false); + dcn315_disable_otg_wa(clk_mgr_base, context, false); update_dispclk = true; } @@ -275,7 +282,7 @@ static struct wm_table ddr5_wm_table = { { .wm_inst = WM_A, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 64.0, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -283,7 +290,7 @@ static struct wm_table ddr5_wm_table = { { .wm_inst = WM_B, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 64.0, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -291,7 +298,7 @@ static struct wm_table ddr5_wm_table = { { .wm_inst = WM_C, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 64.0, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -299,7 +306,7 @@ static struct wm_table ddr5_wm_table = { { .wm_inst = WM_D, .wm_type = WM_TYPE_PSTATE_CHG, - .pstate_latency_us = 64.0, + .pstate_latency_us = 129.0, .sr_exit_time_us = 11.5, .sr_enter_plus_exit_time_us = 14.5, .valid = true, @@ -556,8 +563,7 @@ static void dcn315_clk_mgr_helper_populate_bw_params( ASSERT(bw_params->clk_table.entries[i-1].dcfclk_mhz); bw_params->vram_type = bios_info->memory_type; bw_params->num_channels = bios_info->ma_channel_number; - if (!bw_params->num_channels) - bw_params->num_channels = 2; + bw_params->dram_channel_width_bytes = bios_info->memory_type == 0x22 ? 8 : 4; for (i = 0; i < WM_SET_COUNT; i++) { bw_params->wm_table.entries[i].wm_inst = i; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 0cd3d2eb7ac7..187f5b27fdc8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -112,7 +112,7 @@ static int dcn316_get_active_display_cnt_wa( return display_count; } -static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) +static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, struct dc_state *context, bool disable) { struct dc *dc = clk_mgr_base->ctx->dc; int i; @@ -124,9 +124,10 @@ static void dcn316_disable_otg_wa(struct clk_mgr *clk_mgr_base, bool disable) continue; if (pipe->stream && (pipe->stream->dpms_off || pipe->plane_state == NULL || dc_is_virtual_signal(pipe->stream->signal))) { - if (disable) + if (disable) { pipe->stream_res.tg->funcs->immediate_disable_crtc(pipe->stream_res.tg); - else + reset_sync_context_for_pipe(dc, context, i); + } else pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg); } } @@ -221,11 +222,11 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base, } if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) { - dcn316_disable_otg_wa(clk_mgr_base, true); + dcn316_disable_otg_wa(clk_mgr_base, context, true); clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz; dcn316_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz); - dcn316_disable_otg_wa(clk_mgr_base, false); + dcn316_disable_otg_wa(clk_mgr_base, context, false); update_dispclk = true; } 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 48dad093ae8b..780f7f4c28b6 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 @@ -2758,8 +2758,14 @@ bool perform_link_training_with_retries( skip_video_pattern); /* Transmit idle pattern once training successful. */ - if (status == LINK_TRAINING_SUCCESS && !is_link_bw_low) + if (status == LINK_TRAINING_SUCCESS && !is_link_bw_low) { dp_set_hw_test_pattern(link, &pipe_ctx->link_res, DP_TEST_PATTERN_VIDEO_MODE, NULL, 0); + /* Update verified link settings to current one + * Because DPIA LT might fallback to lower link setting. + */ + link->verified_link_cap.link_rate = link->cur_link_settings.link_rate; + link->verified_link_cap.lane_count = link->cur_link_settings.lane_count; + } } else { status = dc_link_dp_perform_link_training(link, &pipe_ctx->link_res, @@ -5121,6 +5127,14 @@ bool dp_retrieve_lttpr_cap(struct dc_link *link) lttpr_dpcd_data[DP_PHY_REPEATER_128B132B_RATES - DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV]; + /* If this chip cap is set, at least one retimer must exist in the chain + * Override count to 1 if we receive a known bad count (0 or an invalid value) */ + if (link->chip_caps & EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN && + (dp_convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) == 0)) { + ASSERT(0); + link->dpcd_caps.lttpr_caps.phy_repeater_cnt = 0x80; + } + /* Attempt to train in LTTPR transparent mode if repeater count exceeds 8. */ is_lttpr_present = (link->dpcd_caps.lttpr_caps.max_lane_count > 0 && link->dpcd_caps.lttpr_caps.max_lane_count <= 4 && diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 7dbab15bfa68..ccf7bd3d90fe 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -3584,6 +3584,23 @@ void check_syncd_pipes_for_disabled_master_pipe(struct dc *dc, } } +void reset_sync_context_for_pipe(const struct dc *dc, + struct dc_state *context, + uint8_t pipe_idx) +{ + int i; + struct pipe_ctx *pipe_ctx_reset; + + /* reset the otg sync context for the pipe and its slave pipes if any */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe_ctx_reset = &context->res_ctx.pipe_ctx[i]; + + if (((GET_PIPE_SYNCD_FROM_PIPE(pipe_ctx_reset) == pipe_idx) && + IS_PIPE_SYNCD_VALID(pipe_ctx_reset)) || (i == pipe_idx)) + SET_PIPE_SYNCD_TO_PIPE(pipe_ctx_reset, i); + } +} + uint8_t resource_transmitter_to_phy_idx(const struct dc *dc, enum transmitter transmitter) { /* TODO - get transmitter to phy idx mapping from DMUB */ diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 38a67051d470..aea49334021c 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -2164,7 +2164,8 @@ static void dce110_setup_audio_dto( continue; if (pipe_ctx->stream->signal != SIGNAL_TYPE_HDMI_TYPE_A) continue; - if (pipe_ctx->stream_res.audio != NULL) { + if (pipe_ctx->stream_res.audio != NULL && + pipe_ctx->stream_res.audio->enabled == false) { struct audio_output audio_output; build_audio_output(context, pipe_ctx, &audio_output); @@ -2204,7 +2205,8 @@ static void dce110_setup_audio_dto( if (!dc_is_dp_signal(pipe_ctx->stream->signal)) continue; - if (pipe_ctx->stream_res.audio != NULL) { + if (pipe_ctx->stream_res.audio != NULL && + pipe_ctx->stream_res.audio->enabled == false) { struct audio_output audio_output; build_audio_output(context, pipe_ctx, &audio_output); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h index cd2671161ef1..7ce64a3c1b02 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h @@ -445,226 +445,6 @@ type DSCRM_DSC_FORWARD_EN; \ type DSCRM_DSC_OPP_PIPE_SOURCE -#define DSC_REG_LIST_DCN314(id) \ - SRI(DSC_TOP_CONTROL, DSC_TOP, id),\ - SRI(DSC_DEBUG_CONTROL, DSC_TOP, id),\ - SRI(DSCC_CONFIG0, DSCC, id),\ - SRI(DSCC_CONFIG1, DSCC, id),\ - SRI(DSCC_STATUS, DSCC, id),\ - SRI(DSCC_INTERRUPT_CONTROL_STATUS, DSCC, id),\ - SRI(DSCC_PPS_CONFIG0, DSCC, id),\ - SRI(DSCC_PPS_CONFIG1, DSCC, id),\ - SRI(DSCC_PPS_CONFIG2, DSCC, id),\ - SRI(DSCC_PPS_CONFIG3, DSCC, id),\ - SRI(DSCC_PPS_CONFIG4, DSCC, id),\ - SRI(DSCC_PPS_CONFIG5, DSCC, id),\ - SRI(DSCC_PPS_CONFIG6, DSCC, id),\ - SRI(DSCC_PPS_CONFIG7, DSCC, id),\ - SRI(DSCC_PPS_CONFIG8, DSCC, id),\ - SRI(DSCC_PPS_CONFIG9, DSCC, id),\ - SRI(DSCC_PPS_CONFIG10, DSCC, id),\ - SRI(DSCC_PPS_CONFIG11, DSCC, id),\ - SRI(DSCC_PPS_CONFIG12, DSCC, id),\ - SRI(DSCC_PPS_CONFIG13, DSCC, id),\ - SRI(DSCC_PPS_CONFIG14, DSCC, id),\ - SRI(DSCC_PPS_CONFIG15, DSCC, id),\ - SRI(DSCC_PPS_CONFIG16, DSCC, id),\ - SRI(DSCC_PPS_CONFIG17, DSCC, id),\ - SRI(DSCC_PPS_CONFIG18, DSCC, id),\ - SRI(DSCC_PPS_CONFIG19, DSCC, id),\ - SRI(DSCC_PPS_CONFIG20, DSCC, id),\ - SRI(DSCC_PPS_CONFIG21, DSCC, id),\ - SRI(DSCC_PPS_CONFIG22, DSCC, id),\ - SRI(DSCC_MEM_POWER_CONTROL, DSCC, id),\ - SRI(DSCC_R_Y_SQUARED_ERROR_LOWER, DSCC, id),\ - SRI(DSCC_R_Y_SQUARED_ERROR_UPPER, DSCC, id),\ - SRI(DSCC_G_CB_SQUARED_ERROR_LOWER, DSCC, id),\ - SRI(DSCC_G_CB_SQUARED_ERROR_UPPER, DSCC, id),\ - SRI(DSCC_B_CR_SQUARED_ERROR_LOWER, DSCC, id),\ - SRI(DSCC_B_CR_SQUARED_ERROR_UPPER, DSCC, id),\ - SRI(DSCC_MAX_ABS_ERROR0, DSCC, id),\ - SRI(DSCC_MAX_ABS_ERROR1, DSCC, id),\ - SRI(DSCC_RATE_BUFFER0_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_BUFFER1_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_BUFFER2_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_BUFFER3_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_CONTROL_BUFFER0_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_CONTROL_BUFFER1_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_CONTROL_BUFFER2_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCC_RATE_CONTROL_BUFFER3_MAX_FULLNESS_LEVEL, DSCC, id),\ - SRI(DSCCIF_CONFIG0, DSCCIF, id),\ - SRI(DSCCIF_CONFIG1, DSCCIF, id),\ - SRI(DSCRM_DSC_FORWARD_CONFIG, DSCRM, id) - -#define DSC_REG_LIST_SH_MASK_DCN314(mask_sh)\ - DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_CLOCK_EN, mask_sh), \ - DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_DISPCLK_R_GATE_DIS, mask_sh), \ - DSC_SF(DSC_TOP0_DSC_TOP_CONTROL, DSC_DSCCLK_R_GATE_DIS, mask_sh), \ - DSC_SF(DSC_TOP0_DSC_DEBUG_CONTROL, DSC_DBG_EN, mask_sh), \ - DSC_SF(DSC_TOP0_DSC_DEBUG_CONTROL, DSC_TEST_CLOCK_MUX_SEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_CONFIG0, NUMBER_OF_SLICES_PER_LINE, mask_sh), \ - DSC_SF(DSCC0_DSCC_CONFIG0, ALTERNATE_ICH_ENCODING_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_CONFIG0, NUMBER_OF_SLICES_IN_VERTICAL_DIRECTION, mask_sh), \ - DSC_SF(DSCC0_DSCC_CONFIG1, DSCC_RATE_CONTROL_BUFFER_MODEL_SIZE, mask_sh), \ - /*DSC_SF(DSCC0_DSCC_CONFIG1, DSCC_DISABLE_ICH, mask_sh),*/ \ - DSC_SF(DSCC0_DSCC_STATUS, DSCC_DOUBLE_BUFFER_REG_UPDATE_PENDING, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_UNDERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_UNDERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_UNDERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_UNDERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL0_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL1_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL2_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL3_OVERFLOW_OCCURRED, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER0_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER1_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER2_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_BUFFER3_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL0_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL1_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL2_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_INTERRUPT_CONTROL_STATUS, DSCC_RATE_CONTROL_BUFFER_MODEL3_OVERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG0, DSC_VERSION_MINOR, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG0, DSC_VERSION_MAJOR, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG0, PPS_IDENTIFIER, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG0, LINEBUF_DEPTH, mask_sh), \ - DSC2_SF(DSCC0, DSCC_PPS_CONFIG0__BITS_PER_COMPONENT, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, BITS_PER_PIXEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, VBR_ENABLE, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, SIMPLE_422, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, CONVERT_RGB, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, BLOCK_PRED_ENABLE, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, NATIVE_422, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, NATIVE_420, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG1, CHUNK_SIZE, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG2, PIC_WIDTH, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG2, PIC_HEIGHT, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG3, SLICE_WIDTH, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG3, SLICE_HEIGHT, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG4, INITIAL_XMIT_DELAY, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG4, INITIAL_DEC_DELAY, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG5, INITIAL_SCALE_VALUE, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG5, SCALE_INCREMENT_INTERVAL, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG6, SCALE_DECREMENT_INTERVAL, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG6, FIRST_LINE_BPG_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG6, SECOND_LINE_BPG_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG7, NFL_BPG_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG7, SLICE_BPG_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG8, NSL_BPG_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG8, SECOND_LINE_OFFSET_ADJ, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG9, INITIAL_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG9, FINAL_OFFSET, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG10, FLATNESS_MIN_QP, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG10, FLATNESS_MAX_QP, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG10, RC_MODEL_SIZE, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_EDGE_FACTOR, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_QUANT_INCR_LIMIT0, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_QUANT_INCR_LIMIT1, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_TGT_OFFSET_LO, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG11, RC_TGT_OFFSET_HI, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH0, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH1, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH2, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG12, RC_BUF_THRESH3, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH4, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH5, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH6, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG13, RC_BUF_THRESH7, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH8, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH9, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH10, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG14, RC_BUF_THRESH11, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RC_BUF_THRESH12, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RC_BUF_THRESH13, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RANGE_MIN_QP0, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RANGE_MAX_QP0, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG15, RANGE_BPG_OFFSET0, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MIN_QP1, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MAX_QP1, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_BPG_OFFSET1, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MIN_QP2, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_MAX_QP2, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG16, RANGE_BPG_OFFSET2, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MIN_QP3, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MAX_QP3, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_BPG_OFFSET3, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MIN_QP4, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_MAX_QP4, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG17, RANGE_BPG_OFFSET4, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MIN_QP5, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MAX_QP5, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_BPG_OFFSET5, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MIN_QP6, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_MAX_QP6, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG18, RANGE_BPG_OFFSET6, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MIN_QP7, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MAX_QP7, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_BPG_OFFSET7, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MIN_QP8, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_MAX_QP8, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG19, RANGE_BPG_OFFSET8, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MIN_QP9, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MAX_QP9, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_BPG_OFFSET9, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MIN_QP10, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_MAX_QP10, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG20, RANGE_BPG_OFFSET10, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MIN_QP11, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MAX_QP11, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_BPG_OFFSET11, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MIN_QP12, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_MAX_QP12, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG21, RANGE_BPG_OFFSET12, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MIN_QP13, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MAX_QP13, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_BPG_OFFSET13, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MIN_QP14, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_MAX_QP14, mask_sh), \ - DSC_SF(DSCC0_DSCC_PPS_CONFIG22, RANGE_BPG_OFFSET14, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_DEFAULT_MEM_LOW_POWER_STATE, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_MEM_PWR_FORCE, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_MEM_PWR_DIS, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_MEM_PWR_STATE, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_NATIVE_422_MEM_PWR_FORCE, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_NATIVE_422_MEM_PWR_DIS, mask_sh), \ - DSC_SF(DSCC0_DSCC_MEM_POWER_CONTROL, DSCC_NATIVE_422_MEM_PWR_STATE, mask_sh), \ - DSC_SF(DSCC0_DSCC_R_Y_SQUARED_ERROR_LOWER, DSCC_R_Y_SQUARED_ERROR_LOWER, mask_sh), \ - DSC_SF(DSCC0_DSCC_R_Y_SQUARED_ERROR_UPPER, DSCC_R_Y_SQUARED_ERROR_UPPER, mask_sh), \ - DSC_SF(DSCC0_DSCC_G_CB_SQUARED_ERROR_LOWER, DSCC_G_CB_SQUARED_ERROR_LOWER, mask_sh), \ - DSC_SF(DSCC0_DSCC_G_CB_SQUARED_ERROR_UPPER, DSCC_G_CB_SQUARED_ERROR_UPPER, mask_sh), \ - DSC_SF(DSCC0_DSCC_B_CR_SQUARED_ERROR_LOWER, DSCC_B_CR_SQUARED_ERROR_LOWER, mask_sh), \ - DSC_SF(DSCC0_DSCC_B_CR_SQUARED_ERROR_UPPER, DSCC_B_CR_SQUARED_ERROR_UPPER, mask_sh), \ - DSC_SF(DSCC0_DSCC_MAX_ABS_ERROR0, DSCC_R_Y_MAX_ABS_ERROR, mask_sh), \ - DSC_SF(DSCC0_DSCC_MAX_ABS_ERROR0, DSCC_G_CB_MAX_ABS_ERROR, mask_sh), \ - DSC_SF(DSCC0_DSCC_MAX_ABS_ERROR1, DSCC_B_CR_MAX_ABS_ERROR, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_BUFFER0_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER0_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_BUFFER1_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER1_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_BUFFER2_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER2_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_BUFFER3_MAX_FULLNESS_LEVEL, DSCC_RATE_BUFFER3_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER0_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER0_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER1_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER1_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER2_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER2_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCC0_DSCC_RATE_CONTROL_BUFFER3_MAX_FULLNESS_LEVEL, DSCC_RATE_CONTROL_BUFFER3_MAX_FULLNESS_LEVEL, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_INTERFACE_UNDERFLOW_RECOVERY_EN, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_INTERFACE_UNDERFLOW_OCCURRED_INT_EN, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_INTERFACE_UNDERFLOW_OCCURRED_STATUS, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG0, INPUT_PIXEL_FORMAT, mask_sh), \ - DSC2_SF(DSCCIF0, DSCCIF_CONFIG0__BITS_PER_COMPONENT, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG0, DOUBLE_BUFFER_REG_UPDATE_PENDING, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG1, PIC_WIDTH, mask_sh), \ - DSC_SF(DSCCIF0_DSCCIF_CONFIG1, PIC_HEIGHT, mask_sh), \ - DSC_SF(DSCRM0_DSCRM_DSC_FORWARD_CONFIG, DSCRM_DSC_FORWARD_EN, mask_sh), \ - DSC_SF(DSCRM0_DSCRM_DSC_FORWARD_CONFIG, DSCRM_DSC_OPP_PIPE_SOURCE, mask_sh) - - struct dcn20_dsc_registers { uint32_t DSC_TOP_CONTROL; uint32_t DSC_DEBUG_CONTROL; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 884fa060f375..598ce872a8d7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1565,6 +1565,7 @@ static void dcn20_update_dchubp_dpp( /* Any updates are handled in dc interface, just need * to apply existing for plane enable / opp change */ if (pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed + || pipe_ctx->update_flags.bits.plane_changed || pipe_ctx->stream->update_flags.bits.gamut_remap || pipe_ctx->stream->update_flags.bits.out_csc) { /* dpp/cm gamut remap*/ diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c index 39931d48f385..f4d1b83979fe 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c @@ -343,7 +343,6 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig { struct dc_stream_state *stream = pipe_ctx->stream; unsigned int odm_combine_factor = 0; - struct dc *dc = pipe_ctx->stream->ctx->dc; bool two_pix_per_container = false; two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing); @@ -364,7 +363,7 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig } else { *k1_div = PIXEL_RATE_DIV_BY_1; *k2_div = PIXEL_RATE_DIV_BY_4; - if ((odm_combine_factor == 2) || dc->debug.enable_dp_dig_pixel_rate_div_policy) + if (odm_combine_factor == 2) *k2_div = PIXEL_RATE_DIV_BY_2; } } @@ -384,21 +383,10 @@ void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx) return; odm_combine_factor = get_odm_config(pipe_ctx, NULL); - if (optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing) || odm_combine_factor > 1 - || dcn314_is_dp_dig_pixel_rate_div_policy(pipe_ctx)) + if (optc2_is_two_pixels_per_containter(&pipe_ctx->stream->timing) || odm_combine_factor > 1) pix_per_cycle = 2; if (pipe_ctx->stream_res.stream_enc->funcs->set_input_mode) pipe_ctx->stream_res.stream_enc->funcs->set_input_mode(pipe_ctx->stream_res.stream_enc, pix_per_cycle); } - -bool dcn314_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx) -{ - struct dc *dc = pipe_ctx->stream->ctx->dc; - - if (dc_is_dp_signal(pipe_ctx->stream->signal) && !is_dp_128b_132b_signal(pipe_ctx) && - dc->debug.enable_dp_dig_pixel_rate_div_policy) - return true; - return false; -} diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h index d014580592ac..244280298212 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h @@ -41,6 +41,4 @@ unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsig void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx); -bool dcn314_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx); - #endif /* __DC_HWSS_DCN314_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c index fcf67eb3478f..72a563a4c3e8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c @@ -146,7 +146,6 @@ static const struct hwseq_private_funcs dcn314_private_funcs = { .setup_hpo_hw_control = dcn31_setup_hpo_hw_control, .calculate_dccg_k1_k2_values = dcn314_calculate_dccg_k1_k2_values, .set_pixels_per_cycle = dcn314_set_pixels_per_cycle, - .is_dp_dig_pixel_rate_div_policy = dcn314_is_dp_dig_pixel_rate_div_policy, }; void dcn314_hw_sequencer_construct(struct dc *dc) diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index 2a2a4a9cc117..44ac1c2aabf5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -87,6 +87,9 @@ #define DCHUBBUB_DEBUG_CTRL_0__DET_DEPTH__SHIFT 0x10 #define DCHUBBUB_DEBUG_CTRL_0__DET_DEPTH_MASK 0x01FF0000L +#define DSCC0_DSCC_CONFIG0__ICH_RESET_AT_END_OF_LINE__SHIFT 0x0 +#define DSCC0_DSCC_CONFIG0__ICH_RESET_AT_END_OF_LINE_MASK 0x0000000FL + #include "reg_helper.h" #include "dce/dmub_abm.h" #include "dce/dmub_psr.h" @@ -579,7 +582,7 @@ static const struct dcn30_mmhubbub_mask mcif_wb30_mask = { #define dsc_regsDCN314(id)\ [id] = {\ - DSC_REG_LIST_DCN314(id)\ + DSC_REG_LIST_DCN20(id)\ } static const struct dcn20_dsc_registers dsc_regs[] = { @@ -590,11 +593,11 @@ static const struct dcn20_dsc_registers dsc_regs[] = { }; static const struct dcn20_dsc_shift dsc_shift = { - DSC_REG_LIST_SH_MASK_DCN314(__SHIFT) + DSC_REG_LIST_SH_MASK_DCN20(__SHIFT) }; static const struct dcn20_dsc_mask dsc_mask = { - DSC_REG_LIST_SH_MASK_DCN314(_MASK) + DSC_REG_LIST_SH_MASK_DCN20(_MASK) }; static const struct dcn30_mpc_registers mpc_regs = { @@ -844,7 +847,7 @@ static const struct resource_caps res_cap_dcn314 = { .num_ddc = 5, .num_vmid = 16, .num_mpc_3dlut = 2, - .num_dsc = 4, + .num_dsc = 3, }; static const struct dc_plane_cap plane_cap = { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c index 149a1b17cdf3..fa7b0291ce4d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c @@ -291,6 +291,7 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_15_soc = { .do_urgent_latency_adjustment = false, .urgent_latency_adjustment_fabric_clock_component_us = 0, .urgent_latency_adjustment_fabric_clock_reference_mhz = 0, + .num_chans = 4, }; struct _vcs_dpi_ip_params_st dcn3_16_ip = { @@ -680,7 +681,11 @@ void dcn315_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param dcn3_15_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator; dcn3_15_ip.max_num_dpp = dc->res_pool->pipe_count; - dcn3_15_soc.num_chans = bw_params->num_channels; + + if (bw_params->num_channels > 0) + dcn3_15_soc.num_chans = bw_params->num_channels; + if (bw_params->dram_channel_width_bytes > 0) + dcn3_15_soc.dram_channel_width_bytes = bw_params->dram_channel_width_bytes; ASSERT(clk_table->num_entries); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c index 01f3fad172f3..ee821c4fb5dd 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c @@ -265,33 +265,13 @@ static void CalculateRowBandwidth( static void CalculateFlipSchedule( struct display_mode_lib *mode_lib, + unsigned int k, double HostVMInefficiencyFactor, double UrgentExtraLatency, double UrgentLatency, - unsigned int GPUVMMaxPageTableLevels, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - bool GPUVMEnable, - double HostVMMinPageSize, double PDEAndMetaPTEBytesPerFrame, double MetaRowBytes, - double DPTEBytesPerRow, - double BandwidthAvailableForImmediateFlip, - unsigned int TotImmediateFlipBytes, - enum source_format_class SourcePixelFormat, - double LineTime, - double VRatio, - double VRatioChroma, - double Tno_bw, - bool DCCEnable, - unsigned int dpte_row_height, - unsigned int meta_row_height, - unsigned int dpte_row_height_chroma, - unsigned int meta_row_height_chroma, - double *DestinationLinesToRequestVMInImmediateFlip, - double *DestinationLinesToRequestRowInImmediateFlip, - double *final_flip_bw, - bool *ImmediateFlipSupportedForPipe); + double DPTEBytesPerRow); static double CalculateWriteBackDelay( enum source_format_class WritebackPixelFormat, double WritebackHRatio, @@ -325,64 +305,28 @@ static void CalculateVupdateAndDynamicMetadataParameters( static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizedVBlank, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, - double SRExitZ8Time, - double SREnterPlusExitZ8Time, double DCFCLKDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerPlane[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, unsigned int CompressedBufferSizeInkByte, enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, double *StutterExitWatermark, double *StutterEnterPlusExitWatermark, double *Z8StutterExitWatermark, - double *Z8StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported); + double *Z8StutterEnterPlusExitWatermark); static void CalculateDCFCLKDeepSleep( struct display_mode_lib *mode_lib, @@ -2928,33 +2872,13 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman for (k = 0; k < v->NumberOfActivePlanes; ++k) { CalculateFlipSchedule( mode_lib, + k, HostVMInefficiencyFactor, v->UrgentExtraLatency, v->UrgentLatency, - v->GPUVMMaxPageTableLevels, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->GPUVMEnable, - v->HostVMMinPageSize, v->PDEAndMetaPTEBytesFrame[k], v->MetaRowByte[k], - v->PixelPTEBytesPerRow[k], - v->BandwidthAvailableForImmediateFlip, - v->TotImmediateFlipBytes, - v->SourcePixelFormat[k], - v->HTotal[k] / v->PixelClock[k], - v->VRatio[k], - v->VRatioChroma[k], - v->Tno_bw[k], - v->DCCEnable[k], - v->dpte_row_height[k], - v->meta_row_height[k], - v->dpte_row_height_chroma[k], - v->meta_row_height_chroma[k], - &v->DestinationLinesToRequestVMInImmediateFlip[k], - &v->DestinationLinesToRequestRowInImmediateFlip[k], - &v->final_flip_bw[k], - &v->ImmediateFlipSupportedForPipe[k]); + v->PixelPTEBytesPerRow[k]); } v->total_dcn_read_bw_with_flip = 0.0; @@ -3041,64 +2965,28 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, PrefetchMode, - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->WritebackInterfaceBufferSize, v->DCFCLK, v->ReturnBW, - v->SynchronizedVBlank, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgentLatency, v->UrgentExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLK, - v->DRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, - v->SRExitZ8Time, - v->SREnterPlusExitZ8Time, v->DCFCLKDeepSleep, v->DETBufferSizeY, v->DETBufferSizeC, v->SwathHeightY, v->SwathHeightC, - v->LBBitPerPixel, v->SwathWidthY, v->SwathWidthC, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->DPPPerPlane, v->BytePerPixelDETY, v->BytePerPixelDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, v->UnboundedRequestEnabled, v->CompressedBufferSizeInkByte, &DRAMClockChangeSupport, - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, &v->StutterExitWatermark, &v->StutterEnterPlusExitWatermark, &v->Z8StutterExitWatermark, - &v->Z8StutterEnterPlusExitWatermark, - &v->MinActiveDRAMClockChangeLatencySupported); + &v->Z8StutterEnterPlusExitWatermark); for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->WritebackEnable[k] == true) { @@ -3710,61 +3598,43 @@ static void CalculateRowBandwidth( static void CalculateFlipSchedule( struct display_mode_lib *mode_lib, + unsigned int k, double HostVMInefficiencyFactor, double UrgentExtraLatency, double UrgentLatency, - unsigned int GPUVMMaxPageTableLevels, - bool HostVMEnable, - unsigned int HostVMMaxNonCachedPageTableLevels, - bool GPUVMEnable, - double HostVMMinPageSize, double PDEAndMetaPTEBytesPerFrame, double MetaRowBytes, - double DPTEBytesPerRow, - double BandwidthAvailableForImmediateFlip, - unsigned int TotImmediateFlipBytes, - enum source_format_class SourcePixelFormat, - double LineTime, - double VRatio, - double VRatioChroma, - double Tno_bw, - bool DCCEnable, - unsigned int dpte_row_height, - unsigned int meta_row_height, - unsigned int dpte_row_height_chroma, - unsigned int meta_row_height_chroma, - double *DestinationLinesToRequestVMInImmediateFlip, - double *DestinationLinesToRequestRowInImmediateFlip, - double *final_flip_bw, - bool *ImmediateFlipSupportedForPipe) + double DPTEBytesPerRow) { + struct vba_vars_st *v = &mode_lib->vba; double min_row_time = 0.0; unsigned int HostVMDynamicLevelsTrips; double TimeForFetchingMetaPTEImmediateFlip; double TimeForFetchingRowInVBlankImmediateFlip; double ImmediateFlipBW; + double LineTime = v->HTotal[k] / v->PixelClock[k]; - if (GPUVMEnable == true && HostVMEnable == true) { - HostVMDynamicLevelsTrips = HostVMMaxNonCachedPageTableLevels; + if (v->GPUVMEnable == true && v->HostVMEnable == true) { + HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; } else { HostVMDynamicLevelsTrips = 0; } - if (GPUVMEnable == true || DCCEnable == true) { - ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * BandwidthAvailableForImmediateFlip / TotImmediateFlipBytes; + if (v->GPUVMEnable == true || v->DCCEnable[k] == true) { + ImmediateFlipBW = (PDEAndMetaPTEBytesPerFrame + MetaRowBytes + DPTEBytesPerRow) * v->BandwidthAvailableForImmediateFlip / v->TotImmediateFlipBytes; } - if (GPUVMEnable == true) { + if (v->GPUVMEnable == true) { TimeForFetchingMetaPTEImmediateFlip = dml_max3( - Tno_bw + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW, - UrgentExtraLatency + UrgentLatency * (GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1), + v->Tno_bw[k] + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / ImmediateFlipBW, + UrgentExtraLatency + UrgentLatency * (v->GPUVMMaxPageTableLevels * (HostVMDynamicLevelsTrips + 1) - 1), LineTime / 4.0); } else { TimeForFetchingMetaPTEImmediateFlip = 0; } - *DestinationLinesToRequestVMInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0; - if ((GPUVMEnable == true || DCCEnable == true)) { + v->DestinationLinesToRequestVMInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingMetaPTEImmediateFlip / LineTime), 1) / 4.0; + if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) { TimeForFetchingRowInVBlankImmediateFlip = dml_max3( (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / ImmediateFlipBW, UrgentLatency * (HostVMDynamicLevelsTrips + 1), @@ -3773,54 +3643,54 @@ static void CalculateFlipSchedule( TimeForFetchingRowInVBlankImmediateFlip = 0; } - *DestinationLinesToRequestRowInImmediateFlip = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0; + v->DestinationLinesToRequestRowInImmediateFlip[k] = dml_ceil(4.0 * (TimeForFetchingRowInVBlankImmediateFlip / LineTime), 1) / 4.0; - if (GPUVMEnable == true) { - *final_flip_bw = dml_max( - PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (*DestinationLinesToRequestVMInImmediateFlip * LineTime), - (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime)); - } else if ((GPUVMEnable == true || DCCEnable == true)) { - *final_flip_bw = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (*DestinationLinesToRequestRowInImmediateFlip * LineTime); + if (v->GPUVMEnable == true) { + v->final_flip_bw[k] = dml_max( + PDEAndMetaPTEBytesPerFrame * HostVMInefficiencyFactor / (v->DestinationLinesToRequestVMInImmediateFlip[k] * LineTime), + (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime)); + } else if ((v->GPUVMEnable == true || v->DCCEnable[k] == true)) { + v->final_flip_bw[k] = (MetaRowBytes + DPTEBytesPerRow * HostVMInefficiencyFactor) / (v->DestinationLinesToRequestRowInImmediateFlip[k] * LineTime); } else { - *final_flip_bw = 0; + v->final_flip_bw[k] = 0; } - if (SourcePixelFormat == dm_420_8 || SourcePixelFormat == dm_420_10 || SourcePixelFormat == dm_rgbe_alpha) { - if (GPUVMEnable == true && DCCEnable != true) { - min_row_time = dml_min(dpte_row_height * LineTime / VRatio, dpte_row_height_chroma * LineTime / VRatioChroma); - } else if (GPUVMEnable != true && DCCEnable == true) { - min_row_time = dml_min(meta_row_height * LineTime / VRatio, meta_row_height_chroma * LineTime / VRatioChroma); + if (v->SourcePixelFormat[k] == dm_420_8 || v->SourcePixelFormat[k] == dm_420_10 || v->SourcePixelFormat[k] == dm_rgbe_alpha) { + if (v->GPUVMEnable == true && v->DCCEnable[k] != true) { + min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); + } else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) { + min_row_time = dml_min(v->meta_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); } else { min_row_time = dml_min4( - dpte_row_height * LineTime / VRatio, - meta_row_height * LineTime / VRatio, - dpte_row_height_chroma * LineTime / VRatioChroma, - meta_row_height_chroma * LineTime / VRatioChroma); + v->dpte_row_height[k] * LineTime / v->VRatio[k], + v->meta_row_height[k] * LineTime / v->VRatio[k], + v->dpte_row_height_chroma[k] * LineTime / v->VRatioChroma[k], + v->meta_row_height_chroma[k] * LineTime / v->VRatioChroma[k]); } } else { - if (GPUVMEnable == true && DCCEnable != true) { - min_row_time = dpte_row_height * LineTime / VRatio; - } else if (GPUVMEnable != true && DCCEnable == true) { - min_row_time = meta_row_height * LineTime / VRatio; + if (v->GPUVMEnable == true && v->DCCEnable[k] != true) { + min_row_time = v->dpte_row_height[k] * LineTime / v->VRatio[k]; + } else if (v->GPUVMEnable != true && v->DCCEnable[k] == true) { + min_row_time = v->meta_row_height[k] * LineTime / v->VRatio[k]; } else { - min_row_time = dml_min(dpte_row_height * LineTime / VRatio, meta_row_height * LineTime / VRatio); + min_row_time = dml_min(v->dpte_row_height[k] * LineTime / v->VRatio[k], v->meta_row_height[k] * LineTime / v->VRatio[k]); } } - if (*DestinationLinesToRequestVMInImmediateFlip >= 32 || *DestinationLinesToRequestRowInImmediateFlip >= 16 + if (v->DestinationLinesToRequestVMInImmediateFlip[k] >= 32 || v->DestinationLinesToRequestRowInImmediateFlip[k] >= 16 || TimeForFetchingMetaPTEImmediateFlip + 2 * TimeForFetchingRowInVBlankImmediateFlip > min_row_time) { - *ImmediateFlipSupportedForPipe = false; + v->ImmediateFlipSupportedForPipe[k] = false; } else { - *ImmediateFlipSupportedForPipe = true; + v->ImmediateFlipSupportedForPipe[k] = true; } #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestVMInImmediateFlip); - dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, *DestinationLinesToRequestRowInImmediateFlip); + dml_print("DML::%s: DestinationLinesToRequestVMInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestVMInImmediateFlip[k]); + dml_print("DML::%s: DestinationLinesToRequestRowInImmediateFlip = %f\n", __func__, v->DestinationLinesToRequestRowInImmediateFlip[k]); dml_print("DML::%s: TimeForFetchingMetaPTEImmediateFlip = %f\n", __func__, TimeForFetchingMetaPTEImmediateFlip); dml_print("DML::%s: TimeForFetchingRowInVBlankImmediateFlip = %f\n", __func__, TimeForFetchingRowInVBlankImmediateFlip); dml_print("DML::%s: min_row_time = %f\n", __func__, min_row_time); - dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, *ImmediateFlipSupportedForPipe); + dml_print("DML::%s: ImmediateFlipSupportedForPipe = %d\n", __func__, v->ImmediateFlipSupportedForPipe[k]); #endif } @@ -5412,33 +5282,13 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_ for (k = 0; k < v->NumberOfActivePlanes; k++) { CalculateFlipSchedule( mode_lib, + k, HostVMInefficiencyFactor, v->ExtraLatency, v->UrgLatency[i], - v->GPUVMMaxPageTableLevels, - v->HostVMEnable, - v->HostVMMaxNonCachedPageTableLevels, - v->GPUVMEnable, - v->HostVMMinPageSize, v->PDEAndMetaPTEBytesPerFrame[i][j][k], v->MetaRowBytes[i][j][k], - v->DPTEBytesPerRow[i][j][k], - v->BandwidthAvailableForImmediateFlip, - v->TotImmediateFlipBytes, - v->SourcePixelFormat[k], - v->HTotal[k] / v->PixelClock[k], - v->VRatio[k], - v->VRatioChroma[k], - v->Tno_bw[k], - v->DCCEnable[k], - v->dpte_row_height[k], - v->meta_row_height[k], - v->dpte_row_height_chroma[k], - v->meta_row_height_chroma[k], - &v->DestinationLinesToRequestVMInImmediateFlip[k], - &v->DestinationLinesToRequestRowInImmediateFlip[k], - &v->final_flip_bw[k], - &v->ImmediateFlipSupportedForPipe[k]); + v->DPTEBytesPerRow[i][j][k]); } v->total_dcn_read_bw_with_flip = 0.0; for (k = 0; k < v->NumberOfActivePlanes; k++) { @@ -5496,64 +5346,28 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_ CalculateWatermarksAndDRAMSpeedChangeSupport( mode_lib, v->PrefetchModePerState[i][j], - v->NumberOfActivePlanes, - v->MaxLineBufferLines, - v->LineBufferSize, - v->WritebackInterfaceBufferSize, v->DCFCLKState[i][j], v->ReturnBWPerState[i][j], - v->SynchronizedVBlank, - v->dpte_group_bytes, - v->MetaChunkSize, v->UrgLatency[i], v->ExtraLatency, - v->WritebackLatency, - v->WritebackChunkSize, v->SOCCLKPerState[i], - v->DRAMClockChangeLatency, - v->SRExitTime, - v->SREnterPlusExitTime, - v->SRExitZ8Time, - v->SREnterPlusExitZ8Time, v->ProjectedDCFCLKDeepSleep[i][j], v->DETBufferSizeYThisState, v->DETBufferSizeCThisState, v->SwathHeightYThisState, v->SwathHeightCThisState, - v->LBBitPerPixel, v->SwathWidthYThisState, v->SwathWidthCThisState, - v->HRatio, - v->HRatioChroma, - v->vtaps, - v->VTAPsChroma, - v->VRatio, - v->VRatioChroma, - v->HTotal, - v->PixelClock, - v->BlendingAndTiming, v->NoOfDPPThisState, v->BytePerPixelInDETY, v->BytePerPixelInDETC, - v->DSTXAfterScaler, - v->DSTYAfterScaler, - v->WritebackEnable, - v->WritebackPixelFormat, - v->WritebackDestinationWidth, - v->WritebackDestinationHeight, - v->WritebackSourceHeight, UnboundedRequestEnabledThisState, CompressedBufferSizeInkByteThisState, &v->DRAMClockChangeSupport[i][j], - &v->UrgentWatermark, - &v->WritebackUrgentWatermark, - &v->DRAMClockChangeWatermark, - &v->WritebackDRAMClockChangeWatermark, - &dummy, &dummy, &dummy, &dummy, - &v->MinActiveDRAMClockChangeLatencySupported); + &dummy); } } @@ -5679,64 +5493,28 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_ static void CalculateWatermarksAndDRAMSpeedChangeSupport( struct display_mode_lib *mode_lib, unsigned int PrefetchMode, - unsigned int NumberOfActivePlanes, - unsigned int MaxLineBufferLines, - unsigned int LineBufferSize, - unsigned int WritebackInterfaceBufferSize, double DCFCLK, double ReturnBW, - bool SynchronizedVBlank, - unsigned int dpte_group_bytes[], - unsigned int MetaChunkSize, double UrgentLatency, double ExtraLatency, - double WritebackLatency, - double WritebackChunkSize, double SOCCLK, - double DRAMClockChangeLatency, - double SRExitTime, - double SREnterPlusExitTime, - double SRExitZ8Time, - double SREnterPlusExitZ8Time, double DCFCLKDeepSleep, unsigned int DETBufferSizeY[], unsigned int DETBufferSizeC[], unsigned int SwathHeightY[], unsigned int SwathHeightC[], - unsigned int LBBitPerPixel[], double SwathWidthY[], double SwathWidthC[], - double HRatio[], - double HRatioChroma[], - unsigned int vtaps[], - unsigned int VTAPsChroma[], - double VRatio[], - double VRatioChroma[], - unsigned int HTotal[], - double PixelClock[], - unsigned int BlendingAndTiming[], unsigned int DPPPerPlane[], double BytePerPixelDETY[], double BytePerPixelDETC[], - double DSTXAfterScaler[], - double DSTYAfterScaler[], - bool WritebackEnable[], - enum source_format_class WritebackPixelFormat[], - double WritebackDestinationWidth[], - double WritebackDestinationHeight[], - double WritebackSourceHeight[], bool UnboundedRequestEnabled, unsigned int CompressedBufferSizeInkByte, enum clock_change_support *DRAMClockChangeSupport, - double *UrgentWatermark, - double *WritebackUrgentWatermark, - double *DRAMClockChangeWatermark, - double *WritebackDRAMClockChangeWatermark, double *StutterExitWatermark, double *StutterEnterPlusExitWatermark, double *Z8StutterExitWatermark, - double *Z8StutterEnterPlusExitWatermark, - double *MinActiveDRAMClockChangeLatencySupported) + double *Z8StutterEnterPlusExitWatermark) { struct vba_vars_st *v = &mode_lib->vba; double EffectiveLBLatencyHidingY; @@ -5756,103 +5534,103 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( double TotalPixelBW = 0.0; int k, j; - *UrgentWatermark = UrgentLatency + ExtraLatency; + v->UrgentWatermark = UrgentLatency + ExtraLatency; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: UrgentLatency = %f\n", __func__, UrgentLatency); dml_print("DML::%s: ExtraLatency = %f\n", __func__, ExtraLatency); - dml_print("DML::%s: UrgentWatermark = %f\n", __func__, *UrgentWatermark); + dml_print("DML::%s: UrgentWatermark = %f\n", __func__, v->UrgentWatermark); #endif - *DRAMClockChangeWatermark = DRAMClockChangeLatency + *UrgentWatermark; + v->DRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->UrgentWatermark; #ifdef __DML_VBA_DEBUG__ - dml_print("DML::%s: DRAMClockChangeLatency = %f\n", __func__, DRAMClockChangeLatency); - dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, *DRAMClockChangeWatermark); + dml_print("DML::%s: v->DRAMClockChangeLatency = %f\n", __func__, v->DRAMClockChangeLatency); + dml_print("DML::%s: DRAMClockChangeWatermark = %f\n", __func__, v->DRAMClockChangeWatermark); #endif v->TotalActiveWriteback = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (WritebackEnable[k] == true) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->WritebackEnable[k] == true) { v->TotalActiveWriteback = v->TotalActiveWriteback + 1; } } if (v->TotalActiveWriteback <= 1) { - *WritebackUrgentWatermark = WritebackLatency; + v->WritebackUrgentWatermark = v->WritebackLatency; } else { - *WritebackUrgentWatermark = WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackUrgentWatermark = v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } if (v->TotalActiveWriteback <= 1) { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency; + v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency; } else { - *WritebackDRAMClockChangeWatermark = DRAMClockChangeLatency + WritebackLatency + WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; + v->WritebackDRAMClockChangeWatermark = v->DRAMClockChangeLatency + v->WritebackLatency + v->WritebackChunkSize * 1024.0 / 32.0 / SOCCLK; } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { TotalPixelBW = TotalPixelBW - + DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * VRatioChroma[k]) - / (HTotal[k] / PixelClock[k]); + + DPPPerPlane[k] * (SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] + SwathWidthC[k] * BytePerPixelDETC[k] * v->VRatioChroma[k]) + / (v->HTotal[k] / v->PixelClock[k]); } - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { double EffectiveDETBufferSizeY = DETBufferSizeY[k]; v->LBLatencyHidingSourceLinesY = dml_min( - (double) MaxLineBufferLines, - dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(HRatio[k], 1.0)), 1)) - (vtaps[k] - 1); + (double) v->MaxLineBufferLines, + dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthY[k] / dml_max(v->HRatio[k], 1.0)), 1)) - (v->vtaps[k] - 1); v->LBLatencyHidingSourceLinesC = dml_min( - (double) MaxLineBufferLines, - dml_floor(LineBufferSize / LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(HRatioChroma[k], 1.0)), 1)) - (VTAPsChroma[k] - 1); + (double) v->MaxLineBufferLines, + dml_floor(v->LineBufferSize / v->LBBitPerPixel[k] / (SwathWidthC[k] / dml_max(v->HRatioChroma[k], 1.0)), 1)) - (v->VTAPsChroma[k] - 1); - EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / VRatio[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingY = v->LBLatencyHidingSourceLinesY / v->VRatio[k] * (v->HTotal[k] / v->PixelClock[k]); - EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / VRatioChroma[k] * (HTotal[k] / PixelClock[k]); + EffectiveLBLatencyHidingC = v->LBLatencyHidingSourceLinesC / v->VRatioChroma[k] * (v->HTotal[k] / v->PixelClock[k]); if (UnboundedRequestEnabled) { EffectiveDETBufferSizeY = EffectiveDETBufferSizeY - + CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * VRatio[k] / (HTotal[k] / PixelClock[k]) / TotalPixelBW; + + CompressedBufferSizeInkByte * 1024 * SwathWidthY[k] * BytePerPixelDETY[k] * v->VRatio[k] / (v->HTotal[k] / v->PixelClock[k]) / TotalPixelBW; } LinesInDETY[k] = (double) EffectiveDETBufferSizeY / BytePerPixelDETY[k] / SwathWidthY[k]; LinesInDETYRoundedDownToSwath[k] = dml_floor(LinesInDETY[k], SwathHeightY[k]); - FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (HTotal[k] / PixelClock[k]) / VRatio[k]; + FullDETBufferingTimeY = LinesInDETYRoundedDownToSwath[k] * (v->HTotal[k] / v->PixelClock[k]) / v->VRatio[k]; if (BytePerPixelDETC[k] > 0) { LinesInDETC = v->DETBufferSizeC[k] / BytePerPixelDETC[k] / SwathWidthC[k]; LinesInDETCRoundedDownToSwath = dml_floor(LinesInDETC, SwathHeightC[k]); - FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (HTotal[k] / PixelClock[k]) / VRatioChroma[k]; + FullDETBufferingTimeC = LinesInDETCRoundedDownToSwath * (v->HTotal[k] / v->PixelClock[k]) / v->VRatioChroma[k]; } else { LinesInDETC = 0; FullDETBufferingTimeC = 999999; } ActiveDRAMClockChangeLatencyMarginY = EffectiveLBLatencyHidingY + FullDETBufferingTimeY - - ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark; + - ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { + if (v->NumberOfActivePlanes > 1) { ActiveDRAMClockChangeLatencyMarginY = ActiveDRAMClockChangeLatencyMarginY - - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightY[k] * HTotal[k] / PixelClock[k] / VRatio[k]; + - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k]; } if (BytePerPixelDETC[k] > 0) { ActiveDRAMClockChangeLatencyMarginC = EffectiveLBLatencyHidingC + FullDETBufferingTimeC - - ((double) DSTXAfterScaler[k] / HTotal[k] + DSTYAfterScaler[k]) * HTotal[k] / PixelClock[k] - *UrgentWatermark - *DRAMClockChangeWatermark; + - ((double) v->DSTXAfterScaler[k] / v->HTotal[k] + v->DSTYAfterScaler[k]) * v->HTotal[k] / v->PixelClock[k] - v->UrgentWatermark - v->DRAMClockChangeWatermark; - if (NumberOfActivePlanes > 1) { + if (v->NumberOfActivePlanes > 1) { ActiveDRAMClockChangeLatencyMarginC = ActiveDRAMClockChangeLatencyMarginC - - (1 - 1.0 / NumberOfActivePlanes) * SwathHeightC[k] * HTotal[k] / PixelClock[k] / VRatioChroma[k]; + - (1 - 1.0 / v->NumberOfActivePlanes) * SwathHeightC[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatioChroma[k]; } v->ActiveDRAMClockChangeLatencyMargin[k] = dml_min(ActiveDRAMClockChangeLatencyMarginY, ActiveDRAMClockChangeLatencyMarginC); } else { v->ActiveDRAMClockChangeLatencyMargin[k] = ActiveDRAMClockChangeLatencyMarginY; } - if (WritebackEnable[k] == true) { - WritebackDRAMClockChangeLatencyHiding = WritebackInterfaceBufferSize * 1024 - / (WritebackDestinationWidth[k] * WritebackDestinationHeight[k] / (WritebackSourceHeight[k] * HTotal[k] / PixelClock[k]) * 4); - if (WritebackPixelFormat[k] == dm_444_64) { + if (v->WritebackEnable[k] == true) { + WritebackDRAMClockChangeLatencyHiding = v->WritebackInterfaceBufferSize * 1024 + / (v->WritebackDestinationWidth[k] * v->WritebackDestinationHeight[k] / (v->WritebackSourceHeight[k] * v->HTotal[k] / v->PixelClock[k]) * 4); + if (v->WritebackPixelFormat[k] == dm_444_64) { WritebackDRAMClockChangeLatencyHiding = WritebackDRAMClockChangeLatencyHiding / 2; } WritebackDRAMClockChangeLatencyMargin = WritebackDRAMClockChangeLatencyHiding - v->WritebackDRAMClockChangeWatermark; @@ -5862,14 +5640,14 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( v->MinActiveDRAMClockChangeMargin = 999999; PlaneWithMinActiveDRAMClockChangeMargin = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { if (v->ActiveDRAMClockChangeLatencyMargin[k] < v->MinActiveDRAMClockChangeMargin) { v->MinActiveDRAMClockChangeMargin = v->ActiveDRAMClockChangeLatencyMargin[k]; - if (BlendingAndTiming[k] == k) { + if (v->BlendingAndTiming[k] == k) { PlaneWithMinActiveDRAMClockChangeMargin = k; } else { - for (j = 0; j < NumberOfActivePlanes; ++j) { - if (BlendingAndTiming[k] == j) { + for (j = 0; j < v->NumberOfActivePlanes; ++j) { + if (v->BlendingAndTiming[k] == j) { PlaneWithMinActiveDRAMClockChangeMargin = j; } } @@ -5877,11 +5655,11 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( } } - *MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + DRAMClockChangeLatency; + v->MinActiveDRAMClockChangeLatencySupported = v->MinActiveDRAMClockChangeMargin + v->DRAMClockChangeLatency ; SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = 999999; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (BlendingAndTiming[k] == k)) && !(BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (!((k == PlaneWithMinActiveDRAMClockChangeMargin) && (v->BlendingAndTiming[k] == k)) && !(v->BlendingAndTiming[k] == PlaneWithMinActiveDRAMClockChangeMargin) && v->ActiveDRAMClockChangeLatencyMargin[k] < SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank) { SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank = v->ActiveDRAMClockChangeLatencyMargin[k]; } @@ -5889,25 +5667,25 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport( v->TotalNumberOfActiveOTG = 0; - for (k = 0; k < NumberOfActivePlanes; ++k) { - if (BlendingAndTiming[k] == k) { + for (k = 0; k < v->NumberOfActivePlanes; ++k) { + if (v->BlendingAndTiming[k] == k) { v->TotalNumberOfActiveOTG = v->TotalNumberOfActiveOTG + 1; } } if (v->MinActiveDRAMClockChangeMargin > 0 && PrefetchMode == 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vactive; - } else if ((SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 + } else if ((v->SynchronizedVBlank == true || v->TotalNumberOfActiveOTG == 1 || SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank > 0) && PrefetchMode == 0) { *DRAMClockChangeSupport = dm_dram_clock_change_vblank; } else { *DRAMClockChangeSupport = dm_dram_clock_change_unsupported; } - *StutterExitWatermark = SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; - *StutterEnterPlusExitWatermark = (SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep); - *Z8StutterExitWatermark = SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; - *Z8StutterEnterPlusExitWatermark = SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; + *StutterExitWatermark = v->SRExitTime + ExtraLatency + 10 / DCFCLKDeepSleep; + *StutterEnterPlusExitWatermark = (v->SREnterPlusExitTime + ExtraLatency + 10 / DCFCLKDeepSleep); + *Z8StutterExitWatermark = v->SRExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; + *Z8StutterEnterPlusExitWatermark = v->SREnterPlusExitZ8Time + ExtraLatency + 10 / DCFCLKDeepSleep; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: StutterExitWatermark = %f\n", __func__, *StutterExitWatermark); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 8e4c9d0887ce..f43686997917 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -244,6 +244,50 @@ void dcn32_build_wm_range_table_fpu(struct clk_mgr_internal *clk_mgr) } /** + * Finds dummy_latency_index when MCLK switching using firmware based + * vblank stretch is enabled. This function will iterate through the + * table of dummy pstate latencies until the lowest value that allows + * dm_allow_self_refresh_and_mclk_switch to happen is found + */ +int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel) +{ + const int max_latency_table_entries = 4; + const struct vba_vars_st *vba = &context->bw_ctx.dml.vba; + int dummy_latency_index = 0; + + dc_assert_fp_enabled(); + + while (dummy_latency_index < max_latency_table_entries) { + context->bw_ctx.dml.soc.dram_clock_change_latency_us = + dc->clk_mgr->bw_params->dummy_pstate_table[dummy_latency_index].dummy_pstate_latency_us; + dcn32_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, false); + + if (vlevel < context->bw_ctx.dml.vba.soc.num_states && + vba->DRAMClockChangeSupport[vlevel][vba->maxMpcComb] != dm_dram_clock_change_unsupported) + break; + + dummy_latency_index++; + } + + if (dummy_latency_index == max_latency_table_entries) { + ASSERT(dummy_latency_index != max_latency_table_entries); + /* If the execution gets here, it means dummy p_states are + * not possible. This should never happen and would mean + * something is severely wrong. + * Here we reset dummy_latency_index to 3, because it is + * better to have underflows than system crashes. + */ + dummy_latency_index = max_latency_table_entries - 1; + } + + return dummy_latency_index; +} + +/** * dcn32_helper_populate_phantom_dlg_params - Get DLG params for phantom pipes * and populate pipe_ctx with those params. * @@ -1646,7 +1690,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, dcn30_can_support_mclk_switch_using_fw_based_vblank_stretch(dc, context); if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { - dummy_latency_index = dcn30_find_dummy_latency_index_for_fw_based_mclk_switch(dc, + dummy_latency_index = dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(dc, context, pipes, pipe_cnt, vlevel); /* After calling dcn30_find_dummy_latency_index_for_fw_based_mclk_switch diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h index 3ed06ab855be..6ce221098979 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h @@ -71,4 +71,10 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_params); +int dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 9a60f27eceaa..6980f698eb23 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -1992,6 +1992,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l dml32_CalculateODMMode( mode_lib->vba.MaximumPixelsPerLinePerDSCUnit, mode_lib->vba.HActive[k], + mode_lib->vba.OutputFormat[k], mode_lib->vba.Output[k], mode_lib->vba.ODMUse[k], mode_lib->vba.MaxDispclk[i], @@ -2013,6 +2014,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l dml32_CalculateODMMode( mode_lib->vba.MaximumPixelsPerLinePerDSCUnit, mode_lib->vba.HActive[k], + mode_lib->vba.OutputFormat[k], mode_lib->vba.Output[k], mode_lib->vba.ODMUse[k], mode_lib->vba.MaxDispclk[i], diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index 59c2547d01b1..365d290bba99 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -27,6 +27,8 @@ #include "display_mode_vba_32.h" #include "../display_mode_lib.h" +#define DCN32_MAX_FMT_420_BUFFER_WIDTH 4096 + unsigned int dml32_dscceComputeDelay( unsigned int bpc, double BPP, @@ -1182,6 +1184,7 @@ void dml32_CalculateDETBufferSize( void dml32_CalculateODMMode( unsigned int MaximumPixelsPerLinePerDSCUnit, unsigned int HActive, + enum output_format_class OutFormat, enum output_encoder_class Output, enum odm_combine_policy ODMUse, double StateDispclk, @@ -1253,6 +1256,29 @@ void dml32_CalculateODMMode( else *TotalAvailablePipesSupport = false; } + if (OutFormat == dm_420 && HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH && + ODMUse != dm_odm_combine_policy_4to1) { + if (HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH * 4) { + *ODMMode = dm_odm_combine_mode_disabled; + *NumberOfDPP = 0; + *TotalAvailablePipesSupport = false; + } else if (HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH * 2 || + *ODMMode == dm_odm_combine_mode_4to1) { + *ODMMode = dm_odm_combine_mode_4to1; + *RequiredDISPCLKPerSurface = SurfaceRequiredDISPCLKWithODMCombineFourToOne; + *NumberOfDPP = 4; + } else { + *ODMMode = dm_odm_combine_mode_2to1; + *RequiredDISPCLKPerSurface = SurfaceRequiredDISPCLKWithODMCombineTwoToOne; + *NumberOfDPP = 2; + } + } + if (Output == dm_hdmi && OutFormat == dm_420 && + HActive > DCN32_MAX_FMT_420_BUFFER_WIDTH) { + *ODMMode = dm_odm_combine_mode_disabled; + *NumberOfDPP = 0; + *TotalAvailablePipesSupport = false; + } } double dml32_CalculateRequiredDispclk( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h index 924e361ad243..0b427d89b3c5 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h @@ -216,6 +216,7 @@ void dml32_CalculateDETBufferSize( void dml32_CalculateODMMode( unsigned int MaximumPixelsPerLinePerDSCUnit, unsigned int HActive, + enum output_format_class OutFormat, enum output_encoder_class Output, enum odm_combine_policy ODMUse, double StateDispclk, diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index 58158764adc0..7614125c92c7 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -219,6 +219,10 @@ void check_syncd_pipes_for_disabled_master_pipe(struct dc *dc, struct dc_state *context, uint8_t disabled_master_pipe_idx); +void reset_sync_context_for_pipe(const struct dc *dc, + struct dc_state *context, + uint8_t pipe_idx); + uint8_t resource_transmitter_to_phy_idx(const struct dc *dc, enum transmitter transmitter); const struct link_hwss *get_link_hwss(const struct dc_link *link, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 24488f4cb78c..93f9b8377539 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -209,7 +209,8 @@ int smu_v13_0_init_pptable_microcode(struct smu_context *smu) if (!adev->scpm_enabled) return 0; - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 7)) + if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 7)) || + (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0))) return 0; /* override pptable_id from driver parameter */ @@ -218,27 +219,6 @@ int smu_v13_0_init_pptable_microcode(struct smu_context *smu) dev_info(adev->dev, "override pptable id %d\n", pptable_id); } else { pptable_id = smu->smu_table.boot_values.pp_table_id; - - /* - * Temporary solution for SMU V13.0.0 with SCPM enabled: - * - use vbios carried pptable when pptable_id is 3664, 3715 or 3795 - * - use 36831 soft pptable when pptable_id is 3683 - */ - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) { - switch (pptable_id) { - case 3664: - case 3715: - case 3795: - pptable_id = 0; - break; - case 3683: - pptable_id = 36831; - break; - default: - dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id); - return -EINVAL; - } - } } /* "pptable_id == 0" means vbios carries the pptable. */ @@ -471,26 +451,6 @@ int smu_v13_0_setup_pptable(struct smu_context *smu) } else { pptable_id = smu->smu_table.boot_values.pp_table_id; - /* - * Temporary solution for SMU V13.0.0 with SCPM disabled: - * - use 3664, 3683 or 3715 on request - * - use 3664 when pptable_id is 0 - * TODO: drop these when the pptable carried in vbios is ready. - */ - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) { - switch (pptable_id) { - case 0: - pptable_id = 3664; - break; - case 3664: - case 3683: - case 3715: - break; - default: - dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id); - return -EINVAL; - } - } } /* force using vbios pptable in sriov mode */ diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 7db2fd9ea74a..096327513dd0 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -410,58 +410,11 @@ static int smu_v13_0_0_setup_pptable(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; struct amdgpu_device *adev = smu->adev; - uint32_t pptable_id; int ret = 0; - /* - * With SCPM enabled, the pptable used will be signed. It cannot - * be used directly by driver. To get the raw pptable, we need to - * rely on the combo pptable(and its revelant SMU message). - */ - if (adev->scpm_enabled) { - ret = smu_v13_0_0_get_pptable_from_pmfw(smu, - &smu_table->power_play_table, - &smu_table->power_play_table_size); - } else { - /* override pptable_id from driver parameter */ - if (amdgpu_smu_pptable_id >= 0) { - pptable_id = amdgpu_smu_pptable_id; - dev_info(adev->dev, "override pptable id %d\n", pptable_id); - } else { - pptable_id = smu_table->boot_values.pp_table_id; - } - - /* - * Temporary solution for SMU V13.0.0 with SCPM disabled: - * - use vbios carried pptable when pptable_id is 3664, 3715 or 3795 - * - use soft pptable when pptable_id is 3683 - */ - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 0)) { - switch (pptable_id) { - case 3664: - case 3715: - case 3795: - pptable_id = 0; - break; - case 3683: - break; - default: - dev_err(adev->dev, "Unsupported pptable id %d\n", pptable_id); - return -EINVAL; - } - } - - /* force using vbios pptable in sriov mode */ - if ((amdgpu_sriov_vf(adev) || !pptable_id) && (amdgpu_emu_mode != 1)) - ret = smu_v13_0_0_get_pptable_from_pmfw(smu, - &smu_table->power_play_table, - &smu_table->power_play_table_size); - else - ret = smu_v13_0_get_pptable_from_firmware(smu, - &smu_table->power_play_table, - &smu_table->power_play_table_size, - pptable_id); - } + ret = smu_v13_0_0_get_pptable_from_pmfw(smu, + &smu_table->power_play_table, + &smu_table->power_play_table_size); if (ret) return ret; diff --git a/drivers/gpu/drm/hisilicon/hibmc/Kconfig b/drivers/gpu/drm/hisilicon/hibmc/Kconfig index 073adfe438dd..4e41c144a290 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/Kconfig +++ b/drivers/gpu/drm/hisilicon/hibmc/Kconfig @@ -2,6 +2,7 @@ config DRM_HISI_HIBMC tristate "DRM Support for Hisilicon Hibmc" depends on DRM && PCI && (ARM64 || COMPILE_TEST) + depends on MMU select DRM_KMS_HELPER select DRM_VRAM_HELPER select DRM_TTM diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index dabdfe09f5e5..0bcde53c50c6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -1269,6 +1269,10 @@ static void i915_gem_context_release_work(struct work_struct *work) trace_i915_context_free(ctx); GEM_BUG_ON(!i915_gem_context_is_closed(ctx)); + spin_lock(&ctx->i915->gem.contexts.lock); + list_del(&ctx->link); + spin_unlock(&ctx->i915->gem.contexts.lock); + if (ctx->syncobj) drm_syncobj_put(ctx->syncobj); @@ -1521,10 +1525,6 @@ static void context_close(struct i915_gem_context *ctx) ctx->file_priv = ERR_PTR(-EBADF); - spin_lock(&ctx->i915->gem.contexts.lock); - list_del(&ctx->link); - spin_unlock(&ctx->i915->gem.contexts.lock); - client = ctx->client; if (client) { spin_lock(&client->ctx_lock); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 702e5b89be22..b605d0ceaefa 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1191,7 +1191,8 @@ void i915_gem_driver_release(struct drm_i915_private *dev_priv) intel_uc_cleanup_firmwares(&to_gt(dev_priv)->uc); - i915_gem_drain_freed_objects(dev_priv); + /* Flush any outstanding work, including i915_gem_context.release_work. */ + i915_gem_drain_workqueue(dev_priv); drm_WARN_ON(&dev_priv->drm, !list_empty(&dev_priv->gem.contexts.list)); } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c index 2d72cc5ddaba..6b6d5335c834 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c @@ -157,7 +157,7 @@ static void mtk_dither_config(struct device *dev, unsigned int w, { struct mtk_ddp_comp_dev *priv = dev_get_drvdata(dev); - mtk_ddp_write(cmdq_pkt, h << 16 | w, &priv->cmdq_reg, priv->regs, DISP_REG_DITHER_SIZE); + mtk_ddp_write(cmdq_pkt, w << 16 | h, &priv->cmdq_reg, priv->regs, DISP_REG_DITHER_SIZE); mtk_ddp_write(cmdq_pkt, DITHER_RELAY_MODE, &priv->cmdq_reg, priv->regs, DISP_REG_DITHER_CFG); mtk_dither_set_common(priv->regs, &priv->cmdq_reg, bpc, DISP_REG_DITHER_CFG, diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 9cc406e1eee1..3b7d13028fb6 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -685,6 +685,16 @@ static void mtk_dsi_poweroff(struct mtk_dsi *dsi) if (--dsi->refcount != 0) return; + /* + * mtk_dsi_stop() and mtk_dsi_start() is asymmetric, since + * mtk_dsi_stop() should be called after mtk_drm_crtc_atomic_disable(), + * which needs irq for vblank, and mtk_dsi_stop() will disable irq. + * mtk_dsi_start() needs to be called in mtk_output_dsi_enable(), + * after dsi is fully set. + */ + mtk_dsi_stop(dsi); + + mtk_dsi_switch_to_cmd_mode(dsi, VM_DONE_INT_FLAG, 500); mtk_dsi_reset_engine(dsi); mtk_dsi_lane0_ulp_mode_enter(dsi); mtk_dsi_clk_ulp_mode_enter(dsi); @@ -735,17 +745,6 @@ static void mtk_output_dsi_disable(struct mtk_dsi *dsi) if (!dsi->enabled) return; - /* - * mtk_dsi_stop() and mtk_dsi_start() is asymmetric, since - * mtk_dsi_stop() should be called after mtk_drm_crtc_atomic_disable(), - * which needs irq for vblank, and mtk_dsi_stop() will disable irq. - * mtk_dsi_start() needs to be called in mtk_output_dsi_enable(), - * after dsi is fully set. - */ - mtk_dsi_stop(dsi); - - mtk_dsi_switch_to_cmd_mode(dsi, VM_DONE_INT_FLAG, 500); - dsi->enabled = false; } @@ -808,10 +807,13 @@ static void mtk_dsi_bridge_atomic_post_disable(struct drm_bridge *bridge, static const struct drm_bridge_funcs mtk_dsi_bridge_funcs = { .attach = mtk_dsi_bridge_attach, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, .atomic_disable = mtk_dsi_bridge_atomic_disable, + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_enable = mtk_dsi_bridge_atomic_enable, .atomic_pre_enable = mtk_dsi_bridge_atomic_pre_enable, .atomic_post_disable = mtk_dsi_bridge_atomic_post_disable, + .atomic_reset = drm_atomic_helper_bridge_reset, .mode_set = mtk_dsi_bridge_mode_set, }; diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c index 251a1bb648cc..a222bf76804f 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.c +++ b/drivers/gpu/drm/mgag200/mgag200_drv.c @@ -262,7 +262,11 @@ mgag200_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) return ret; - drm_fbdev_generic_setup(dev, 0); + /* + * FIXME: A 24-bit color depth does not work with 24 bpp on + * G200ER. Force 32 bpp. + */ + drm_fbdev_generic_setup(dev, 32); return 0; } diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index ff5e1a44c43a..1e716c23019a 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2257,7 +2257,7 @@ static const struct panel_desc innolux_g121i1_l01 = { .enable = 200, .disable = 20, }, - .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, + .bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG, .connector_type = DRM_MODE_CONNECTOR_LVDS, }; diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index e47fa3465671..3082183bd66a 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1583,7 +1583,7 @@ static int i2c_imx_remove(struct platform_device *pdev) if (i2c_imx->dma) i2c_imx_dma_free(i2c_imx); - if (ret == 0) { + if (ret >= 0) { /* setup chip registers to defaults */ imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IADR); imx_i2c_write_reg(0, i2c_imx, IMX_I2C_IFDR); diff --git a/drivers/i2c/busses/i2c-mlxbf.c b/drivers/i2c/busses/i2c-mlxbf.c index 8716032f030a..ad5efd7497d1 100644 --- a/drivers/i2c/busses/i2c-mlxbf.c +++ b/drivers/i2c/busses/i2c-mlxbf.c @@ -6,6 +6,7 @@ */ #include <linux/acpi.h> +#include <linux/bitfield.h> #include <linux/delay.h> #include <linux/err.h> #include <linux/interrupt.h> @@ -63,13 +64,14 @@ */ #define MLXBF_I2C_TYU_PLL_OUT_FREQ (400 * 1000 * 1000) /* Reference clock for Bluefield - 156 MHz. */ -#define MLXBF_I2C_PLL_IN_FREQ (156 * 1000 * 1000) +#define MLXBF_I2C_PLL_IN_FREQ 156250000ULL /* Constant used to determine the PLL frequency. */ -#define MLNXBF_I2C_COREPLL_CONST 16384 +#define MLNXBF_I2C_COREPLL_CONST 16384ULL + +#define MLXBF_I2C_FREQUENCY_1GHZ 1000000000ULL /* PLL registers. */ -#define MLXBF_I2C_CORE_PLL_REG0 0x0 #define MLXBF_I2C_CORE_PLL_REG1 0x4 #define MLXBF_I2C_CORE_PLL_REG2 0x8 @@ -181,22 +183,15 @@ #define MLXBF_I2C_COREPLL_FREQ MLXBF_I2C_TYU_PLL_OUT_FREQ /* Core PLL TYU configuration. */ -#define MLXBF_I2C_COREPLL_CORE_F_TYU_MASK GENMASK(12, 0) -#define MLXBF_I2C_COREPLL_CORE_OD_TYU_MASK GENMASK(3, 0) -#define MLXBF_I2C_COREPLL_CORE_R_TYU_MASK GENMASK(5, 0) - -#define MLXBF_I2C_COREPLL_CORE_F_TYU_SHIFT 3 -#define MLXBF_I2C_COREPLL_CORE_OD_TYU_SHIFT 16 -#define MLXBF_I2C_COREPLL_CORE_R_TYU_SHIFT 20 +#define MLXBF_I2C_COREPLL_CORE_F_TYU_MASK GENMASK(15, 3) +#define MLXBF_I2C_COREPLL_CORE_OD_TYU_MASK GENMASK(19, 16) +#define MLXBF_I2C_COREPLL_CORE_R_TYU_MASK GENMASK(25, 20) /* Core PLL YU configuration. */ #define MLXBF_I2C_COREPLL_CORE_F_YU_MASK GENMASK(25, 0) #define MLXBF_I2C_COREPLL_CORE_OD_YU_MASK GENMASK(3, 0) -#define MLXBF_I2C_COREPLL_CORE_R_YU_MASK GENMASK(5, 0) +#define MLXBF_I2C_COREPLL_CORE_R_YU_MASK GENMASK(31, 26) -#define MLXBF_I2C_COREPLL_CORE_F_YU_SHIFT 0 -#define MLXBF_I2C_COREPLL_CORE_OD_YU_SHIFT 1 -#define MLXBF_I2C_COREPLL_CORE_R_YU_SHIFT 26 /* Core PLL frequency. */ static u64 mlxbf_i2c_corepll_frequency; @@ -479,8 +474,6 @@ static struct mutex mlxbf_i2c_bus_lock; #define MLXBF_I2C_MASK_8 GENMASK(7, 0) #define MLXBF_I2C_MASK_16 GENMASK(15, 0) -#define MLXBF_I2C_FREQUENCY_1GHZ 1000000000 - /* * Function to poll a set of bits at a specific address; it checks whether * the bits are equal to zero when eq_zero is set to 'true', and not equal @@ -669,7 +662,7 @@ static int mlxbf_i2c_smbus_enable(struct mlxbf_i2c_priv *priv, u8 slave, /* Clear status bits. */ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_STATUS); /* Set the cause data. */ - writel(~0x0, priv->smbus->io + MLXBF_I2C_CAUSE_OR_CLEAR); + writel(~0x0, priv->mst_cause->io + MLXBF_I2C_CAUSE_OR_CLEAR); /* Zero PEC byte. */ writel(0x0, priv->smbus->io + MLXBF_I2C_SMBUS_MASTER_PEC); /* Zero byte count. */ @@ -738,6 +731,9 @@ mlxbf_i2c_smbus_start_transaction(struct mlxbf_i2c_priv *priv, if (flags & MLXBF_I2C_F_WRITE) { write_en = 1; write_len += operation->length; + if (data_idx + operation->length > + MLXBF_I2C_MASTER_DATA_DESC_SIZE) + return -ENOBUFS; memcpy(data_desc + data_idx, operation->buffer, operation->length); data_idx += operation->length; @@ -1407,24 +1403,19 @@ static int mlxbf_i2c_init_master(struct platform_device *pdev, return 0; } -static u64 mlxbf_calculate_freq_from_tyu(struct mlxbf_i2c_resource *corepll_res) +static u64 mlxbf_i2c_calculate_freq_from_tyu(struct mlxbf_i2c_resource *corepll_res) { - u64 core_frequency, pad_frequency; + u64 core_frequency; u8 core_od, core_r; u32 corepll_val; u16 core_f; - pad_frequency = MLXBF_I2C_PLL_IN_FREQ; - corepll_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1); /* Get Core PLL configuration bits. */ - core_f = rol32(corepll_val, MLXBF_I2C_COREPLL_CORE_F_TYU_SHIFT) & - MLXBF_I2C_COREPLL_CORE_F_TYU_MASK; - core_od = rol32(corepll_val, MLXBF_I2C_COREPLL_CORE_OD_TYU_SHIFT) & - MLXBF_I2C_COREPLL_CORE_OD_TYU_MASK; - core_r = rol32(corepll_val, MLXBF_I2C_COREPLL_CORE_R_TYU_SHIFT) & - MLXBF_I2C_COREPLL_CORE_R_TYU_MASK; + core_f = FIELD_GET(MLXBF_I2C_COREPLL_CORE_F_TYU_MASK, corepll_val); + core_od = FIELD_GET(MLXBF_I2C_COREPLL_CORE_OD_TYU_MASK, corepll_val); + core_r = FIELD_GET(MLXBF_I2C_COREPLL_CORE_R_TYU_MASK, corepll_val); /* * Compute PLL output frequency as follow: @@ -1436,31 +1427,26 @@ static u64 mlxbf_calculate_freq_from_tyu(struct mlxbf_i2c_resource *corepll_res) * Where PLL_OUT_FREQ and PLL_IN_FREQ refer to CoreFrequency * and PadFrequency, respectively. */ - core_frequency = pad_frequency * (++core_f); + core_frequency = MLXBF_I2C_PLL_IN_FREQ * (++core_f); core_frequency /= (++core_r) * (++core_od); return core_frequency; } -static u64 mlxbf_calculate_freq_from_yu(struct mlxbf_i2c_resource *corepll_res) +static u64 mlxbf_i2c_calculate_freq_from_yu(struct mlxbf_i2c_resource *corepll_res) { u32 corepll_reg1_val, corepll_reg2_val; - u64 corepll_frequency, pad_frequency; + u64 corepll_frequency; u8 core_od, core_r; u32 core_f; - pad_frequency = MLXBF_I2C_PLL_IN_FREQ; - corepll_reg1_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG1); corepll_reg2_val = readl(corepll_res->io + MLXBF_I2C_CORE_PLL_REG2); /* Get Core PLL configuration bits */ - core_f = rol32(corepll_reg1_val, MLXBF_I2C_COREPLL_CORE_F_YU_SHIFT) & - MLXBF_I2C_COREPLL_CORE_F_YU_MASK; - core_r = rol32(corepll_reg1_val, MLXBF_I2C_COREPLL_CORE_R_YU_SHIFT) & - MLXBF_I2C_COREPLL_CORE_R_YU_MASK; - core_od = rol32(corepll_reg2_val, MLXBF_I2C_COREPLL_CORE_OD_YU_SHIFT) & - MLXBF_I2C_COREPLL_CORE_OD_YU_MASK; + core_f = FIELD_GET(MLXBF_I2C_COREPLL_CORE_F_YU_MASK, corepll_reg1_val); + core_r = FIELD_GET(MLXBF_I2C_COREPLL_CORE_R_YU_MASK, corepll_reg1_val); + core_od = FIELD_GET(MLXBF_I2C_COREPLL_CORE_OD_YU_MASK, corepll_reg2_val); /* * Compute PLL output frequency as follow: @@ -1472,7 +1458,7 @@ static u64 mlxbf_calculate_freq_from_yu(struct mlxbf_i2c_resource *corepll_res) * Where PLL_OUT_FREQ and PLL_IN_FREQ refer to CoreFrequency * and PadFrequency, respectively. */ - corepll_frequency = (pad_frequency * core_f) / MLNXBF_I2C_COREPLL_CONST; + corepll_frequency = (MLXBF_I2C_PLL_IN_FREQ * core_f) / MLNXBF_I2C_COREPLL_CONST; corepll_frequency /= (++core_r) * (++core_od); return corepll_frequency; @@ -2180,14 +2166,14 @@ static struct mlxbf_i2c_chip_info mlxbf_i2c_chip[] = { [1] = &mlxbf_i2c_corepll_res[MLXBF_I2C_CHIP_TYPE_1], [2] = &mlxbf_i2c_gpio_res[MLXBF_I2C_CHIP_TYPE_1] }, - .calculate_freq = mlxbf_calculate_freq_from_tyu + .calculate_freq = mlxbf_i2c_calculate_freq_from_tyu }, [MLXBF_I2C_CHIP_TYPE_2] = { .type = MLXBF_I2C_CHIP_TYPE_2, .shared_res = { [0] = &mlxbf_i2c_corepll_res[MLXBF_I2C_CHIP_TYPE_2] }, - .calculate_freq = mlxbf_calculate_freq_from_yu + .calculate_freq = mlxbf_i2c_calculate_freq_from_yu } }; diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c index 774507b54b57..313904be5f3b 100644 --- a/drivers/i2c/i2c-mux.c +++ b/drivers/i2c/i2c-mux.c @@ -243,9 +243,10 @@ struct i2c_mux_core *i2c_mux_alloc(struct i2c_adapter *parent, int (*deselect)(struct i2c_mux_core *, u32)) { struct i2c_mux_core *muxc; + size_t mux_size; - muxc = devm_kzalloc(dev, struct_size(muxc, adapter, max_adapters) - + sizeof_priv, GFP_KERNEL); + mux_size = struct_size(muxc, adapter, max_adapters); + muxc = devm_kzalloc(dev, size_add(mux_size, sizeof_priv), GFP_KERNEL); if (!muxc) return NULL; if (sizeof_priv) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 497c912ad9e1..5a8f780e7ffd 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -2349,13 +2349,6 @@ static int dmar_device_hotplug(acpi_handle handle, bool insert) if (!dmar_in_use()) return 0; - /* - * It's unlikely that any I/O board is hot added before the IOMMU - * subsystem is initialized. - */ - if (IS_ENABLED(CONFIG_INTEL_IOMMU) && !intel_iommu_enabled) - return -EOPNOTSUPP; - if (dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD)) { tmp = handle; } else { diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 1f2cd43cf9bc..31bc50e538a3 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -399,7 +399,7 @@ static unsigned long __iommu_calculate_sagaw(struct intel_iommu *iommu) { unsigned long fl_sagaw, sl_sagaw; - fl_sagaw = BIT(2) | (cap_fl1gp_support(iommu->cap) ? BIT(3) : 0); + fl_sagaw = BIT(2) | (cap_5lp_support(iommu->cap) ? BIT(3) : 0); sl_sagaw = cap_sagaw(iommu->cap); /* Second level only. */ @@ -3019,7 +3019,13 @@ static int __init init_dmars(void) #ifdef CONFIG_INTEL_IOMMU_SVM if (pasid_supported(iommu) && ecap_prs(iommu->ecap)) { + /* + * Call dmar_alloc_hwirq() with dmar_global_lock held, + * could cause possible lock race condition. + */ + up_write(&dmar_global_lock); ret = intel_svm_enable_prq(iommu); + down_write(&dmar_global_lock); if (ret) goto free_iommu; } @@ -3932,6 +3938,7 @@ int __init intel_iommu_init(void) force_on = (!intel_iommu_tboot_noforce && tboot_force_iommu()) || platform_optin_force_iommu(); + down_write(&dmar_global_lock); if (dmar_table_init()) { if (force_on) panic("tboot: Failed to initialize DMAR table\n"); @@ -3944,6 +3951,16 @@ int __init intel_iommu_init(void) goto out_free_dmar; } + up_write(&dmar_global_lock); + + /* + * The bus notifier takes the dmar_global_lock, so lockdep will + * complain later when we register it under the lock. + */ + dmar_register_bus_notifier(); + + down_write(&dmar_global_lock); + if (!no_iommu) intel_iommu_debugfs_init(); @@ -3988,9 +4005,11 @@ int __init intel_iommu_init(void) pr_err("Initialization failed\n"); goto out_free_dmar; } + up_write(&dmar_global_lock); init_iommu_pm_ops(); + down_read(&dmar_global_lock); for_each_active_iommu(iommu, drhd) { /* * The flush queue implementation does not perform @@ -4008,11 +4027,13 @@ int __init intel_iommu_init(void) "%s", iommu->name); iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL); } + up_read(&dmar_global_lock); bus_set_iommu(&pci_bus_type, &intel_iommu_ops); if (si_domain && !hw_pass_through) register_memory_notifier(&intel_iommu_memory_nb); + down_read(&dmar_global_lock); if (probe_acpi_namespace_devices()) pr_warn("ACPI name space devices didn't probe correctly\n"); @@ -4023,15 +4044,17 @@ int __init intel_iommu_init(void) iommu_disable_protect_mem_regions(iommu); } + up_read(&dmar_global_lock); - intel_iommu_enabled = 1; - dmar_register_bus_notifier(); pr_info("Intel(R) Virtualization Technology for Directed I/O\n"); + intel_iommu_enabled = 1; + return 0; out_free_dmar: intel_iommu_free_dmars(); + up_write(&dmar_global_lock); return ret; } diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 2acda9cea0f9..aebb7ef10e63 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -107,7 +107,7 @@ * * BTREE NODES: * - * Our unit of allocation is a bucket, and we we can't arbitrarily allocate and + * Our unit of allocation is a bucket, and we can't arbitrarily allocate and * free smaller than a bucket - so, that's how big our btree nodes are. * * (If buckets are really big we'll only use part of the bucket for a btree node diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 94d38e8a59b3..2bba4d6aaaa2 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -1264,7 +1264,7 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter, * * Don't worry event 'out' is allocated from mempool, it can * still be swapped here. Because state->pool is a page mempool - * creaated by by mempool_init_page_pool(), which allocates + * created by mempool_init_page_pool(), which allocates * pages by alloc_pages() indeed. */ diff --git a/drivers/md/bcache/stats.h b/drivers/md/bcache/stats.h index ca4f435f7216..bd3afc856d53 100644 --- a/drivers/md/bcache/stats.h +++ b/drivers/md/bcache/stats.h @@ -54,7 +54,6 @@ void bch_cache_accounting_destroy(struct cache_accounting *acc); void bch_mark_cache_accounting(struct cache_set *c, struct bcache_device *d, bool hit, bool bypass); -void bch_mark_cache_readahead(struct cache_set *c, struct bcache_device *d); void bch_mark_cache_miss_collision(struct cache_set *c, struct bcache_device *d); void bch_mark_sectors_bypassed(struct cache_set *c, diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 3f0ff3aab6f2..0285b676e983 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -157,6 +157,53 @@ static void __update_writeback_rate(struct cached_dev *dc) dc->writeback_rate_target = target; } +static bool idle_counter_exceeded(struct cache_set *c) +{ + int counter, dev_nr; + + /* + * If c->idle_counter is overflow (idel for really long time), + * reset as 0 and not set maximum rate this time for code + * simplicity. + */ + counter = atomic_inc_return(&c->idle_counter); + if (counter <= 0) { + atomic_set(&c->idle_counter, 0); + return false; + } + + dev_nr = atomic_read(&c->attached_dev_nr); + if (dev_nr == 0) + return false; + + /* + * c->idle_counter is increased by writeback thread of all + * attached backing devices, in order to represent a rough + * time period, counter should be divided by dev_nr. + * Otherwise the idle time cannot be larger with more backing + * device attached. + * The following calculation equals to checking + * (counter / dev_nr) < (dev_nr * 6) + */ + if (counter < (dev_nr * dev_nr * 6)) + return false; + + return true; +} + +/* + * Idle_counter is increased every time when update_writeback_rate() is + * called. If all backing devices attached to the same cache set have + * identical dc->writeback_rate_update_seconds values, it is about 6 + * rounds of update_writeback_rate() on each backing device before + * c->at_max_writeback_rate is set to 1, and then max wrteback rate set + * to each dc->writeback_rate.rate. + * In order to avoid extra locking cost for counting exact dirty cached + * devices number, c->attached_dev_nr is used to calculate the idle + * throushold. It might be bigger if not all cached device are in write- + * back mode, but it still works well with limited extra rounds of + * update_writeback_rate(). + */ static bool set_at_max_writeback_rate(struct cache_set *c, struct cached_dev *dc) { @@ -167,21 +214,8 @@ static bool set_at_max_writeback_rate(struct cache_set *c, /* Don't set max writeback rate if gc is running */ if (!c->gc_mark_valid) return false; - /* - * Idle_counter is increased everytime when update_writeback_rate() is - * called. If all backing devices attached to the same cache set have - * identical dc->writeback_rate_update_seconds values, it is about 6 - * rounds of update_writeback_rate() on each backing device before - * c->at_max_writeback_rate is set to 1, and then max wrteback rate set - * to each dc->writeback_rate.rate. - * In order to avoid extra locking cost for counting exact dirty cached - * devices number, c->attached_dev_nr is used to calculate the idle - * throushold. It might be bigger if not all cached device are in write- - * back mode, but it still works well with limited extra rounds of - * update_writeback_rate(). - */ - if (atomic_inc_return(&c->idle_counter) < - atomic_read(&c->attached_dev_nr) * 6) + + if (!idle_counter_exceeded(c)) return false; if (atomic_read(&c->at_max_writeback_rate) != 1) @@ -195,13 +229,10 @@ static bool set_at_max_writeback_rate(struct cache_set *c, dc->writeback_rate_change = 0; /* - * Check c->idle_counter and c->at_max_writeback_rate agagain in case - * new I/O arrives during before set_at_max_writeback_rate() returns. - * Then the writeback rate is set to 1, and its new value should be - * decided via __update_writeback_rate(). + * In case new I/O arrives during before + * set_at_max_writeback_rate() returns. */ - if ((atomic_read(&c->idle_counter) < - atomic_read(&c->attached_dev_nr) * 6) || + if (!idle_counter_exceeded(c) || !atomic_read(&c->at_max_writeback_rate)) return false; @@ -801,10 +832,9 @@ static int bch_writeback_thread(void *arg) } } - if (dc->writeback_write_wq) { - flush_workqueue(dc->writeback_write_wq); + if (dc->writeback_write_wq) destroy_workqueue(dc->writeback_write_wq); - } + cached_dev_put(dc); wait_for_kthread_stop(); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 332f96b58252..d8034ff0cb24 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1856,9 +1856,7 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t) static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return !blk_queue_nowait(q); + return !bdev_nowait(dev->bdev); } static bool dm_table_supports_nowait(struct dm_table *t) diff --git a/drivers/md/md.c b/drivers/md/md.c index 729be2c5296c..a467b492d4ad 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5845,7 +5845,7 @@ int md_run(struct mddev *mddev) } } sysfs_notify_dirent_safe(rdev->sysfs_state); - nowait = nowait && blk_queue_nowait(bdev_get_queue(rdev->bdev)); + nowait = nowait && bdev_nowait(rdev->bdev); } if (!bioset_initialized(&mddev->bio_set)) { @@ -6982,7 +6982,7 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) * If the new disk does not support REQ_NOWAIT, * disable on the whole MD. */ - if (!blk_queue_nowait(bdev_get_queue(rdev->bdev))) { + if (!bdev_nowait(rdev->bdev)) { pr_info("%s: Disabling nowait because %pg does not support nowait\n", mdname(mddev), rdev->bdev); blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, mddev->queue); @@ -8156,7 +8156,6 @@ static void *md_seq_start(struct seq_file *seq, loff_t *pos) list_for_each(tmp,&all_mddevs) if (!l--) { mddev = list_entry(tmp, struct mddev, all_mddevs); - mddev_get(mddev); if (!mddev_get(mddev)) continue; spin_unlock(&all_mddevs_lock); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 78addfe4a0c9..857c49399c28 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -47,7 +47,7 @@ static void dump_zones(struct mddev *mddev) int len = 0; for (k = 0; k < conf->strip_zone[j].nb_dev; k++) - len += snprintf(line+len, 200-len, "%s%pg", k?"/":"", + len += scnprintf(line+len, 200-len, "%s%pg", k?"/":"", conf->devlist[j * raid_disks + k]->bdev); pr_debug("md: zone%d=[%s]\n", j, line); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 64d6e4cd8a3a..3aa8b6e11d58 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -79,6 +79,21 @@ static void end_reshape(struct r10conf *conf); #include "raid1-10.c" +#define NULL_CMD +#define cmd_before(conf, cmd) \ + do { \ + write_sequnlock_irq(&(conf)->resync_lock); \ + cmd; \ + } while (0) +#define cmd_after(conf) write_seqlock_irq(&(conf)->resync_lock) + +#define wait_event_barrier_cmd(conf, cond, cmd) \ + wait_event_cmd((conf)->wait_barrier, cond, cmd_before(conf, cmd), \ + cmd_after(conf)) + +#define wait_event_barrier(conf, cond) \ + wait_event_barrier_cmd(conf, cond, NULL_CMD) + /* * for resync bio, r10bio pointer can be retrieved from the per-bio * 'struct resync_pages'. @@ -274,6 +289,12 @@ static void put_buf(struct r10bio *r10_bio) lower_barrier(conf); } +static void wake_up_barrier(struct r10conf *conf) +{ + if (wq_has_sleeper(&conf->wait_barrier)) + wake_up(&conf->wait_barrier); +} + static void reschedule_retry(struct r10bio *r10_bio) { unsigned long flags; @@ -930,78 +951,101 @@ static void flush_pending_writes(struct r10conf *conf) static void raise_barrier(struct r10conf *conf, int force) { + write_seqlock_irq(&conf->resync_lock); BUG_ON(force && !conf->barrier); - spin_lock_irq(&conf->resync_lock); /* Wait until no block IO is waiting (unless 'force') */ - wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting, - conf->resync_lock); + wait_event_barrier(conf, force || !conf->nr_waiting); /* block any new IO from starting */ - conf->barrier++; + WRITE_ONCE(conf->barrier, conf->barrier + 1); /* Now wait for all pending IO to complete */ - wait_event_lock_irq(conf->wait_barrier, - !atomic_read(&conf->nr_pending) && conf->barrier < RESYNC_DEPTH, - conf->resync_lock); + wait_event_barrier(conf, !atomic_read(&conf->nr_pending) && + conf->barrier < RESYNC_DEPTH); - spin_unlock_irq(&conf->resync_lock); + write_sequnlock_irq(&conf->resync_lock); } static void lower_barrier(struct r10conf *conf) { unsigned long flags; - spin_lock_irqsave(&conf->resync_lock, flags); - conf->barrier--; - spin_unlock_irqrestore(&conf->resync_lock, flags); + + write_seqlock_irqsave(&conf->resync_lock, flags); + WRITE_ONCE(conf->barrier, conf->barrier - 1); + write_sequnlock_irqrestore(&conf->resync_lock, flags); wake_up(&conf->wait_barrier); } +static bool stop_waiting_barrier(struct r10conf *conf) +{ + struct bio_list *bio_list = current->bio_list; + + /* barrier is dropped */ + if (!conf->barrier) + return true; + + /* + * If there are already pending requests (preventing the barrier from + * rising completely), and the pre-process bio queue isn't empty, then + * don't wait, as we need to empty that queue to get the nr_pending + * count down. + */ + if (atomic_read(&conf->nr_pending) && bio_list && + (!bio_list_empty(&bio_list[0]) || !bio_list_empty(&bio_list[1]))) + return true; + + /* move on if recovery thread is blocked by us */ + if (conf->mddev->thread->tsk == current && + test_bit(MD_RECOVERY_RUNNING, &conf->mddev->recovery) && + conf->nr_queued > 0) + return true; + + return false; +} + +static bool wait_barrier_nolock(struct r10conf *conf) +{ + unsigned int seq = read_seqbegin(&conf->resync_lock); + + if (READ_ONCE(conf->barrier)) + return false; + + atomic_inc(&conf->nr_pending); + if (!read_seqretry(&conf->resync_lock, seq)) + return true; + + if (atomic_dec_and_test(&conf->nr_pending)) + wake_up_barrier(conf); + + return false; +} + static bool wait_barrier(struct r10conf *conf, bool nowait) { bool ret = true; - spin_lock_irq(&conf->resync_lock); + if (wait_barrier_nolock(conf)) + return true; + + write_seqlock_irq(&conf->resync_lock); if (conf->barrier) { - struct bio_list *bio_list = current->bio_list; - conf->nr_waiting++; - /* Wait for the barrier to drop. - * However if there are already pending - * requests (preventing the barrier from - * rising completely), and the - * pre-process bio queue isn't empty, - * then don't wait, as we need to empty - * that queue to get the nr_pending - * count down. - */ /* Return false when nowait flag is set */ if (nowait) { ret = false; } else { + conf->nr_waiting++; raid10_log(conf->mddev, "wait barrier"); - wait_event_lock_irq(conf->wait_barrier, - !conf->barrier || - (atomic_read(&conf->nr_pending) && - bio_list && - (!bio_list_empty(&bio_list[0]) || - !bio_list_empty(&bio_list[1]))) || - /* move on if recovery thread is - * blocked by us - */ - (conf->mddev->thread->tsk == current && - test_bit(MD_RECOVERY_RUNNING, - &conf->mddev->recovery) && - conf->nr_queued > 0), - conf->resync_lock); + wait_event_barrier(conf, stop_waiting_barrier(conf)); + conf->nr_waiting--; } - conf->nr_waiting--; if (!conf->nr_waiting) wake_up(&conf->wait_barrier); } /* Only increment nr_pending when we wait */ if (ret) atomic_inc(&conf->nr_pending); - spin_unlock_irq(&conf->resync_lock); + write_sequnlock_irq(&conf->resync_lock); return ret; } @@ -1009,7 +1053,7 @@ static void allow_barrier(struct r10conf *conf) { if ((atomic_dec_and_test(&conf->nr_pending)) || (conf->array_freeze_pending)) - wake_up(&conf->wait_barrier); + wake_up_barrier(conf); } static void freeze_array(struct r10conf *conf, int extra) @@ -1026,27 +1070,24 @@ static void freeze_array(struct r10conf *conf, int extra) * must match the number of pending IOs (nr_pending) before * we continue. */ - spin_lock_irq(&conf->resync_lock); + write_seqlock_irq(&conf->resync_lock); conf->array_freeze_pending++; - conf->barrier++; + WRITE_ONCE(conf->barrier, conf->barrier + 1); conf->nr_waiting++; - wait_event_lock_irq_cmd(conf->wait_barrier, - atomic_read(&conf->nr_pending) == conf->nr_queued+extra, - conf->resync_lock, - flush_pending_writes(conf)); - + wait_event_barrier_cmd(conf, atomic_read(&conf->nr_pending) == + conf->nr_queued + extra, flush_pending_writes(conf)); conf->array_freeze_pending--; - spin_unlock_irq(&conf->resync_lock); + write_sequnlock_irq(&conf->resync_lock); } static void unfreeze_array(struct r10conf *conf) { /* reverse the effect of the freeze */ - spin_lock_irq(&conf->resync_lock); - conf->barrier--; + write_seqlock_irq(&conf->resync_lock); + WRITE_ONCE(conf->barrier, conf->barrier - 1); conf->nr_waiting--; wake_up(&conf->wait_barrier); - spin_unlock_irq(&conf->resync_lock); + write_sequnlock_irq(&conf->resync_lock); } static sector_t choose_data_offset(struct r10bio *r10_bio, @@ -1885,7 +1926,7 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio) __make_request(mddev, bio, sectors); /* In case raid10d snuck in to freeze_array */ - wake_up(&conf->wait_barrier); + wake_up_barrier(conf); return true; } @@ -1980,7 +2021,7 @@ static int enough(struct r10conf *conf, int ignore) * Otherwise, it must be degraded: * - recovery is interrupted. * - &mddev->degraded is bumped. - + * * @rdev is marked as &Faulty excluding case when array is failed and * &mddev->fail_last_dev is off. */ @@ -4032,7 +4073,7 @@ static struct r10conf *setup_conf(struct mddev *mddev) INIT_LIST_HEAD(&conf->retry_list); INIT_LIST_HEAD(&conf->bio_end_io_list); - spin_lock_init(&conf->resync_lock); + seqlock_init(&conf->resync_lock); init_waitqueue_head(&conf->wait_barrier); atomic_set(&conf->nr_pending, 0); @@ -4351,7 +4392,7 @@ static void *raid10_takeover_raid0(struct mddev *mddev, sector_t size, int devs) rdev->new_raid_disk = rdev->raid_disk * 2; rdev->sectors = size; } - conf->barrier = 1; + WRITE_ONCE(conf->barrier, 1); } return conf; diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 5c0804d8bb1f..8c072ce0bc54 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -76,7 +76,7 @@ struct r10conf { /* queue pending writes and submit them on unplug */ struct bio_list pending_bio_list; - spinlock_t resync_lock; + seqlock_t resync_lock; atomic_t nr_pending; int nr_waiting; int nr_queued; diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index f4e1cc1ece43..79c73330020b 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -125,7 +125,7 @@ struct r5l_log { * reclaimed. if it's 0, reclaim spaces * used by io_units which are in * IO_UNIT_STRIPE_END state (eg, reclaim - * dones't wait for specific io_unit + * doesn't wait for specific io_unit * switching to IO_UNIT_STRIPE_END * state) */ wait_queue_head_t iounit_wait; @@ -1327,9 +1327,9 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log, * superblock is updated to new log tail. Updating superblock (either * directly call md_update_sb() or depend on md thread) must hold * reconfig mutex. On the other hand, raid5_quiesce is called with - * reconfig_mutex hold. The first step of raid5_quiesce() is waitting - * for all IO finish, hence waitting for reclaim thread, while reclaim - * thread is calling this function and waitting for reconfig mutex. So + * reconfig_mutex hold. The first step of raid5_quiesce() is waiting + * for all IO finish, hence waiting for reclaim thread, while reclaim + * thread is calling this function and waiting for reconfig mutex. So * there is a deadlock. We workaround this issue with a trylock. * FIXME: we could miss discard if we can't take reconfig mutex */ @@ -1923,7 +1923,8 @@ r5c_recovery_alloc_stripe( { struct stripe_head *sh; - sh = raid5_get_active_stripe(conf, stripe_sect, 0, noblock, 0); + sh = raid5_get_active_stripe(conf, NULL, stripe_sect, + noblock ? R5_GAS_NOBLOCK : 0); if (!sh) return NULL; /* no more stripe available */ diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 31a0cbf63384..7b820b81d8c2 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -36,6 +36,7 @@ */ #include <linux/blkdev.h> +#include <linux/delay.h> #include <linux/kthread.h> #include <linux/raid/pq.h> #include <linux/async_tx.h> @@ -789,87 +790,80 @@ struct stripe_request_ctx { */ static bool is_inactive_blocked(struct r5conf *conf, int hash) { - int active = atomic_read(&conf->active_stripes); - if (list_empty(conf->inactive_list + hash)) return false; if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) return true; - return active < (conf->max_nr_stripes * 3 / 4); + return (atomic_read(&conf->active_stripes) < + (conf->max_nr_stripes * 3 / 4)); } -static struct stripe_head *__raid5_get_active_stripe(struct r5conf *conf, +struct stripe_head *raid5_get_active_stripe(struct r5conf *conf, struct stripe_request_ctx *ctx, sector_t sector, - bool previous, bool noblock, bool noquiesce) + unsigned int flags) { struct stripe_head *sh; int hash = stripe_hash_locks_hash(conf, sector); + int previous = !!(flags & R5_GAS_PREVIOUS); pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector); spin_lock_irq(conf->hash_locks + hash); -retry: - if (!noquiesce && conf->quiesce) { - /* - * Must release the reference to batch_last before waiting, - * on quiesce, otherwise the batch_last will hold a reference - * to a stripe and raid5_quiesce() will deadlock waiting for - * active_stripes to go to zero. - */ - if (ctx && ctx->batch_last) { - raid5_release_stripe(ctx->batch_last); - ctx->batch_last = NULL; - } - - wait_event_lock_irq(conf->wait_for_quiescent, !conf->quiesce, - *(conf->hash_locks + hash)); - } + for (;;) { + if (!(flags & R5_GAS_NOQUIESCE) && conf->quiesce) { + /* + * Must release the reference to batch_last before + * waiting, on quiesce, otherwise the batch_last will + * hold a reference to a stripe and raid5_quiesce() + * will deadlock waiting for active_stripes to go to + * zero. + */ + if (ctx && ctx->batch_last) { + raid5_release_stripe(ctx->batch_last); + ctx->batch_last = NULL; + } - sh = find_get_stripe(conf, sector, conf->generation - previous, hash); - if (sh) - goto out; + wait_event_lock_irq(conf->wait_for_quiescent, + !conf->quiesce, + *(conf->hash_locks + hash)); + } - if (test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) - goto wait_for_stripe; + sh = find_get_stripe(conf, sector, conf->generation - previous, + hash); + if (sh) + break; - sh = get_free_stripe(conf, hash); - if (sh) { - r5c_check_stripe_cache_usage(conf); - init_stripe(sh, sector, previous); - atomic_inc(&sh->count); - goto out; - } + if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) { + sh = get_free_stripe(conf, hash); + if (sh) { + r5c_check_stripe_cache_usage(conf); + init_stripe(sh, sector, previous); + atomic_inc(&sh->count); + break; + } - if (!test_bit(R5_DID_ALLOC, &conf->cache_state)) - set_bit(R5_ALLOC_MORE, &conf->cache_state); + if (!test_bit(R5_DID_ALLOC, &conf->cache_state)) + set_bit(R5_ALLOC_MORE, &conf->cache_state); + } -wait_for_stripe: - if (noblock) - goto out; + if (flags & R5_GAS_NOBLOCK) + break; - set_bit(R5_INACTIVE_BLOCKED, &conf->cache_state); - r5l_wake_reclaim(conf->log, 0); - wait_event_lock_irq(conf->wait_for_stripe, - is_inactive_blocked(conf, hash), - *(conf->hash_locks + hash)); - clear_bit(R5_INACTIVE_BLOCKED, &conf->cache_state); - goto retry; + set_bit(R5_INACTIVE_BLOCKED, &conf->cache_state); + r5l_wake_reclaim(conf->log, 0); + wait_event_lock_irq(conf->wait_for_stripe, + is_inactive_blocked(conf, hash), + *(conf->hash_locks + hash)); + clear_bit(R5_INACTIVE_BLOCKED, &conf->cache_state); + } -out: spin_unlock_irq(conf->hash_locks + hash); return sh; } -struct stripe_head *raid5_get_active_stripe(struct r5conf *conf, - sector_t sector, bool previous, bool noblock, bool noquiesce) -{ - return __raid5_get_active_stripe(conf, NULL, sector, previous, noblock, - noquiesce); -} - static bool is_full_stripe_write(struct stripe_head *sh) { BUG_ON(sh->overwrite_disks > (sh->disks - sh->raid_conf->max_degraded)); @@ -4047,7 +4041,7 @@ static void handle_stripe_fill(struct stripe_head *sh, * back cache (prexor with orig_page, and then xor with * page) in the read path */ - if (s->injournal && s->failed) { + if (s->to_read && s->injournal && s->failed) { if (test_bit(STRIPE_R5C_CACHING, &sh->state)) r5c_make_stripe_write_out(sh); goto out; @@ -4636,7 +4630,8 @@ static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh) sector_t bn = raid5_compute_blocknr(sh, i, 1); sector_t s = raid5_compute_sector(conf, bn, 0, &dd_idx, NULL); - sh2 = raid5_get_active_stripe(conf, s, 0, 1, 1); + sh2 = raid5_get_active_stripe(conf, NULL, s, + R5_GAS_NOBLOCK | R5_GAS_NOQUIESCE); if (sh2 == NULL) /* so far only the early blocks of this stripe * have been requested. When later blocks @@ -5273,7 +5268,9 @@ static void handle_stripe(struct stripe_head *sh) /* Finish reconstruct operations initiated by the expansion process */ if (sh->reconstruct_state == reconstruct_state_result) { struct stripe_head *sh_src - = raid5_get_active_stripe(conf, sh->sector, 1, 1, 1); + = raid5_get_active_stripe(conf, NULL, sh->sector, + R5_GAS_PREVIOUS | R5_GAS_NOBLOCK | + R5_GAS_NOQUIESCE); if (sh_src && test_bit(STRIPE_EXPAND_SOURCE, &sh_src->state)) { /* sh cannot be written until sh_src has been read. * so arrange for sh to be delayed a little @@ -5542,7 +5539,6 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad, &bad_sectors)) { - bio_put(raid_bio); rdev_dec_pending(rdev, mddev); return 0; } @@ -5823,7 +5819,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) DEFINE_WAIT(w); int d; again: - sh = raid5_get_active_stripe(conf, logical_sector, 0, 0, 0); + sh = raid5_get_active_stripe(conf, NULL, logical_sector, 0); prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); set_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags); @@ -5978,7 +5974,7 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, enum stripe_result ret; struct stripe_head *sh; sector_t new_sector; - int previous = 0; + int previous = 0, flags = 0; int seq, dd_idx; seq = read_seqcount_begin(&conf->gen_lock); @@ -6012,8 +6008,11 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, pr_debug("raid456: %s, sector %llu logical %llu\n", __func__, new_sector, logical_sector); - sh = __raid5_get_active_stripe(conf, ctx, new_sector, previous, - (bi->bi_opf & REQ_RAHEAD), 0); + if (previous) + flags |= R5_GAS_PREVIOUS; + if (bi->bi_opf & REQ_RAHEAD) + flags |= R5_GAS_NOBLOCK; + sh = raid5_get_active_stripe(conf, ctx, new_sector, flags); if (unlikely(!sh)) { /* cannot get stripe, just give-up */ bi->bi_status = BLK_STS_IOERR; @@ -6362,7 +6361,8 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk for (i = 0; i < reshape_sectors; i += RAID5_STRIPE_SECTORS(conf)) { int j; int skipped_disk = 0; - sh = raid5_get_active_stripe(conf, stripe_addr+i, 0, 0, 1); + sh = raid5_get_active_stripe(conf, NULL, stripe_addr+i, + R5_GAS_NOQUIESCE); set_bit(STRIPE_EXPANDING, &sh->state); atomic_inc(&conf->reshape_stripes); /* If any of this stripe is beyond the end of the old @@ -6411,7 +6411,8 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk if (last_sector >= mddev->dev_sectors) last_sector = mddev->dev_sectors - 1; while (first_sector <= last_sector) { - sh = raid5_get_active_stripe(conf, first_sector, 1, 0, 1); + sh = raid5_get_active_stripe(conf, NULL, first_sector, + R5_GAS_PREVIOUS | R5_GAS_NOQUIESCE); set_bit(STRIPE_EXPAND_SOURCE, &sh->state); set_bit(STRIPE_HANDLE, &sh->state); raid5_release_stripe(sh); @@ -6531,9 +6532,10 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n md_bitmap_cond_end_sync(mddev->bitmap, sector_nr, false); - sh = raid5_get_active_stripe(conf, sector_nr, 0, 1, 0); + sh = raid5_get_active_stripe(conf, NULL, sector_nr, + R5_GAS_NOBLOCK); if (sh == NULL) { - sh = raid5_get_active_stripe(conf, sector_nr, 0, 0, 0); + sh = raid5_get_active_stripe(conf, NULL, sector_nr, 0); /* make sure we don't swamp the stripe cache if someone else * is trying to get access */ @@ -6596,8 +6598,8 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio, /* already done this stripe */ continue; - sh = raid5_get_active_stripe(conf, sector, 0, 1, 1); - + sh = raid5_get_active_stripe(conf, NULL, sector, + R5_GAS_NOBLOCK | R5_GAS_NOQUIESCE); if (!sh) { /* failed to get a stripe - must wait */ conf->retry_read_aligned = raid_bio; @@ -6781,7 +6783,18 @@ static void raid5d(struct md_thread *thread) spin_unlock_irq(&conf->device_lock); md_check_recovery(mddev); spin_lock_irq(&conf->device_lock); + + /* + * Waiting on MD_SB_CHANGE_PENDING below may deadlock + * seeing md_check_recovery() is needed to clear + * the flag when using mdmon. + */ + continue; } + + wait_event_lock_irq(mddev->sb_wait, + !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags), + conf->device_lock); } pr_debug("%d stripes handled\n", handled); diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index a5082bed83c8..e873938a6125 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -803,16 +803,24 @@ raid5_get_dev_page(struct stripe_head *sh, int disk_idx) } #endif -extern void md_raid5_kick_device(struct r5conf *conf); -extern int raid5_set_cache_size(struct mddev *mddev, int size); -extern sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous); -extern void raid5_release_stripe(struct stripe_head *sh); -extern sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector, - int previous, int *dd_idx, - struct stripe_head *sh); -extern struct stripe_head * -raid5_get_active_stripe(struct r5conf *conf, sector_t sector, - bool previous, bool noblock, bool noquiesce); -extern int raid5_calc_degraded(struct r5conf *conf); -extern int r5c_journal_mode_set(struct mddev *mddev, int journal_mode); +void md_raid5_kick_device(struct r5conf *conf); +int raid5_set_cache_size(struct mddev *mddev, int size); +sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous); +void raid5_release_stripe(struct stripe_head *sh); +sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector, + int previous, int *dd_idx, struct stripe_head *sh); + +struct stripe_request_ctx; +/* get stripe from previous generation (when reshaping) */ +#define R5_GAS_PREVIOUS (1 << 0) +/* do not block waiting for a free stripe */ +#define R5_GAS_NOBLOCK (1 << 1) +/* do not block waiting for quiesce to be released */ +#define R5_GAS_NOQUIESCE (1 << 2) +struct stripe_head *raid5_get_active_stripe(struct r5conf *conf, + struct stripe_request_ctx *ctx, sector_t sector, + unsigned int flags); + +int raid5_calc_degraded(struct r5conf *conf); +int r5c_journal_mode_set(struct mddev *mddev, int journal_mode); #endif diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c index 7835bb0f32fc..e012b21c4fd7 100644 --- a/drivers/media/usb/b2c2/flexcop-usb.c +++ b/drivers/media/usb/b2c2/flexcop-usb.c @@ -511,7 +511,7 @@ static int flexcop_usb_init(struct flexcop_usb *fc_usb) if (fc_usb->uintf->cur_altsetting->desc.bNumEndpoints < 1) return -ENODEV; - if (!usb_endpoint_is_isoc_in(&fc_usb->uintf->cur_altsetting->endpoint[1].desc)) + if (!usb_endpoint_is_isoc_in(&fc_usb->uintf->cur_altsetting->endpoint[0].desc)) return -ENODEV; switch (fc_usb->udev->speed) { diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 184608bd8999..e58a1e0cadd2 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -88,8 +88,9 @@ static const u8 null_mac_addr[ETH_ALEN + 2] __long_aligned = { static const u16 ad_ticks_per_sec = 1000 / AD_TIMER_INTERVAL; static const int ad_delta_in_ticks = (AD_TIMER_INTERVAL * HZ) / 1000; -static const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned = - MULTICAST_LACPDU_ADDR; +const u8 lacpdu_mcast_addr[ETH_ALEN + 2] __long_aligned = { + 0x01, 0x80, 0xC2, 0x00, 0x00, 0x02 +}; /* ================= main 802.3ad protocol functions ================== */ static int ad_lacpdu_send(struct port *port); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5c2febe94428..86d42306aa5e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -865,12 +865,8 @@ static void bond_hw_addr_flush(struct net_device *bond_dev, dev_uc_unsync(slave_dev, bond_dev); dev_mc_unsync(slave_dev, bond_dev); - if (BOND_MODE(bond) == BOND_MODE_8023AD) { - /* del lacpdu mc addr from mc list */ - u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; - - dev_mc_del(slave_dev, lacpdu_multicast); - } + if (BOND_MODE(bond) == BOND_MODE_8023AD) + dev_mc_del(slave_dev, lacpdu_mcast_addr); } /*--------------------------- Active slave change ---------------------------*/ @@ -890,7 +886,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(old_active->dev, -1); - bond_hw_addr_flush(bond->dev, old_active->dev); + if (bond->dev->flags & IFF_UP) + bond_hw_addr_flush(bond->dev, old_active->dev); } if (new_active) { @@ -901,10 +898,12 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(new_active->dev, 1); - netif_addr_lock_bh(bond->dev); - dev_uc_sync(new_active->dev, bond->dev); - dev_mc_sync(new_active->dev, bond->dev); - netif_addr_unlock_bh(bond->dev); + if (bond->dev->flags & IFF_UP) { + netif_addr_lock_bh(bond->dev); + dev_uc_sync(new_active->dev, bond->dev); + dev_mc_sync(new_active->dev, bond->dev); + netif_addr_unlock_bh(bond->dev); + } } } @@ -2166,16 +2165,14 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, } } - netif_addr_lock_bh(bond_dev); - dev_mc_sync_multiple(slave_dev, bond_dev); - dev_uc_sync_multiple(slave_dev, bond_dev); - netif_addr_unlock_bh(bond_dev); - - if (BOND_MODE(bond) == BOND_MODE_8023AD) { - /* add lacpdu mc addr to mc list */ - u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; + if (bond_dev->flags & IFF_UP) { + netif_addr_lock_bh(bond_dev); + dev_mc_sync_multiple(slave_dev, bond_dev); + dev_uc_sync_multiple(slave_dev, bond_dev); + netif_addr_unlock_bh(bond_dev); - dev_mc_add(slave_dev, lacpdu_multicast); + if (BOND_MODE(bond) == BOND_MODE_8023AD) + dev_mc_add(slave_dev, lacpdu_mcast_addr); } } @@ -2447,7 +2444,8 @@ static int __bond_release_one(struct net_device *bond_dev, if (old_flags & IFF_ALLMULTI) dev_set_allmulti(slave_dev, -1); - bond_hw_addr_flush(bond_dev, slave_dev); + if (old_flags & IFF_UP) + bond_hw_addr_flush(bond_dev, slave_dev); } slave_disable_netpoll(slave); @@ -4184,6 +4182,12 @@ static int bond_open(struct net_device *bond_dev) struct list_head *iter; struct slave *slave; + if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN && !bond->rr_tx_counter) { + bond->rr_tx_counter = alloc_percpu(u32); + if (!bond->rr_tx_counter) + return -ENOMEM; + } + /* reset slave->backup and slave->inactive */ if (bond_has_slaves(bond)) { bond_for_each_slave(bond, slave, iter) { @@ -4221,6 +4225,9 @@ static int bond_open(struct net_device *bond_dev) /* register to receive LACPDUs */ bond->recv_probe = bond_3ad_lacpdu_recv; bond_3ad_initiate_agg_selection(bond, 1); + + bond_for_each_slave(bond, slave, iter) + dev_mc_add(slave->dev, lacpdu_mcast_addr); } if (bond_mode_can_use_xmit_hash(bond)) @@ -4232,6 +4239,7 @@ static int bond_open(struct net_device *bond_dev) static int bond_close(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; bond_work_cancel_all(bond); bond->send_peer_notif = 0; @@ -4239,6 +4247,19 @@ static int bond_close(struct net_device *bond_dev) bond_alb_deinitialize(bond); bond->recv_probe = NULL; + if (bond_uses_primary(bond)) { + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + bond_hw_addr_flush(bond_dev, slave->dev); + rcu_read_unlock(); + } else { + struct list_head *iter; + + bond_for_each_slave(bond, slave, iter) + bond_hw_addr_flush(bond_dev, slave->dev); + } + return 0; } @@ -6228,15 +6249,6 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; - if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN) { - bond->rr_tx_counter = alloc_percpu(u32); - if (!bond->rr_tx_counter) { - destroy_workqueue(bond->wq); - bond->wq = NULL; - return -ENOMEM; - } - } - spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev); diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index f857968efed7..ccb438eca517 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -941,11 +941,6 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload, u32 reg_ctrl, reg_id, reg_iflag1; int i; - if (unlikely(drop)) { - skb = ERR_PTR(-ENOBUFS); - goto mark_as_read; - } - mb = flexcan_get_mb(priv, n); if (priv->devtype_data.quirks & FLEXCAN_QUIRK_USE_RX_MAILBOX) { @@ -974,6 +969,11 @@ static struct sk_buff *flexcan_mailbox_read(struct can_rx_offload *offload, reg_ctrl = priv->read(&mb->can_ctrl); } + if (unlikely(drop)) { + skb = ERR_PTR(-ENOBUFS); + goto mark_as_read; + } + if (reg_ctrl & FLEXCAN_MB_CNT_EDL) skb = alloc_canfd_skb(offload->dev, &cfd); else diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index baf749c8cda3..c1ff3c046d62 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -824,6 +824,7 @@ static int gs_can_open(struct net_device *netdev) flags |= GS_CAN_MODE_TRIPLE_SAMPLE; /* finally start device */ + dev->can.state = CAN_STATE_ERROR_ACTIVE; dm->mode = cpu_to_le32(GS_CAN_MODE_START); dm->flags = cpu_to_le32(flags); rc = usb_control_msg(interface_to_usbdev(dev->iface), @@ -835,13 +836,12 @@ static int gs_can_open(struct net_device *netdev) if (rc < 0) { netdev_err(netdev, "Couldn't start device (err=%d)\n", rc); kfree(dm); + dev->can.state = CAN_STATE_STOPPED; return rc; } kfree(dm); - dev->can.state = CAN_STATE_ERROR_ACTIVE; - parent->active_channels++; if (!(dev->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)) netif_start_queue(netdev); @@ -925,17 +925,21 @@ static int gs_usb_set_identify(struct net_device *netdev, bool do_identify) } /* blink LED's for finding the this interface */ -static int gs_usb_set_phys_id(struct net_device *dev, +static int gs_usb_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) { + const struct gs_can *dev = netdev_priv(netdev); int rc = 0; + if (!(dev->feature & GS_CAN_FEATURE_IDENTIFY)) + return -EOPNOTSUPP; + switch (state) { case ETHTOOL_ID_ACTIVE: - rc = gs_usb_set_identify(dev, GS_CAN_IDENTIFY_ON); + rc = gs_usb_set_identify(netdev, GS_CAN_IDENTIFY_ON); break; case ETHTOOL_ID_INACTIVE: - rc = gs_usb_set_identify(dev, GS_CAN_IDENTIFY_OFF); + rc = gs_usb_set_identify(netdev, GS_CAN_IDENTIFY_OFF); break; default: break; @@ -1072,9 +1076,10 @@ static struct gs_can *gs_make_candev(unsigned int channel, dev->feature |= GS_CAN_FEATURE_REQ_USB_QUIRK_LPC546XX | GS_CAN_FEATURE_QUIRK_BREQ_CANTACT_PRO; - if (le32_to_cpu(dconf->sw_version) > 1) - if (feature & GS_CAN_FEATURE_IDENTIFY) - netdev->ethtool_ops = &gs_usb_ethtool_ops; + /* GS_CAN_FEATURE_IDENTIFY is only supported for sw_version > 1 */ + if (!(le32_to_cpu(dconf->sw_version) > 1 && + feature & GS_CAN_FEATURE_IDENTIFY)) + dev->feature &= ~GS_CAN_FEATURE_IDENTIFY; kfree(bt_const); diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c index daedd2bf20c1..5579644e8fde 100644 --- a/drivers/net/dsa/microchip/lan937x_main.c +++ b/drivers/net/dsa/microchip/lan937x_main.c @@ -244,10 +244,6 @@ void lan937x_port_setup(struct ksz_device *dev, int port, bool cpu_port) lan937x_port_cfg(dev, port, REG_PORT_CTRL_0, PORT_TAIL_TAG_ENABLE, true); - /* disable frame check length field */ - lan937x_port_cfg(dev, port, REG_PORT_MAC_CTRL_0, PORT_CHECK_LENGTH, - false); - /* set back pressure for half duplex */ lan937x_port_cfg(dev, port, REG_PORT_MAC_CTRL_1, PORT_BACK_PRESSURE, true); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index 88595863d8bc..8a0af371e7dc 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -94,11 +94,8 @@ static int aq_ndev_close(struct net_device *ndev) int err = 0; err = aq_nic_stop(aq_nic); - if (err < 0) - goto err_exit; aq_nic_deinit(aq_nic, true); -err_exit: return err; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f46eefb5a029..96da0ba3d507 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -659,7 +659,6 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) for (i = 0; i < nr_pkts; i++) { struct bnxt_sw_tx_bd *tx_buf; - bool compl_deferred = false; struct sk_buff *skb; int j, last; @@ -668,6 +667,8 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) skb = tx_buf->skb; tx_buf->skb = NULL; + tx_bytes += skb->len; + if (tx_buf->is_push) { tx_buf->is_push = 0; goto next_tx_int; @@ -688,8 +689,9 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) } if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) { if (bp->flags & BNXT_FLAG_CHIP_P5) { + /* PTP worker takes ownership of the skb */ if (!bnxt_get_tx_ts_p5(bp, skb)) - compl_deferred = true; + skb = NULL; else atomic_inc(&bp->ptp_cfg->tx_avail); } @@ -698,9 +700,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) next_tx_int: cons = NEXT_TX(cons); - tx_bytes += skb->len; - if (!compl_deferred) - dev_kfree_skb_any(skb); + dev_kfree_skb_any(skb); } netdev_tx_completed_queue(txq, nr_pkts, tx_bytes); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 7f3c0875b6f5..8e316367f6ce 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -317,9 +317,9 @@ void bnxt_ptp_cfg_tstamp_filters(struct bnxt *bp) if (!(bp->fw_cap & BNXT_FW_CAP_RX_ALL_PKT_TS) && (ptp->tstamp_filters & (PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE | - PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE))) { + PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_DISABLE))) { ptp->tstamp_filters &= ~(PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE | - PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE); + PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_DISABLE); netdev_warn(bp->dev, "Unsupported FW for all RX pkts timestamp filter\n"); } diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile index a139f2e9d59f..e0e8dfd13793 100644 --- a/drivers/net/ethernet/freescale/enetc/Makefile +++ b/drivers/net/ethernet/freescale/enetc/Makefile @@ -9,7 +9,6 @@ fsl-enetc-$(CONFIG_FSL_ENETC_QOS) += enetc_qos.o obj-$(CONFIG_FSL_ENETC_VF) += fsl-enetc-vf.o fsl-enetc-vf-y := enetc_vf.o $(common-objs) -fsl-enetc-vf-$(CONFIG_FSL_ENETC_QOS) += enetc_qos.o obj-$(CONFIG_FSL_ENETC_IERB) += fsl-enetc-ierb.o fsl-enetc-ierb-y := enetc_ierb.o diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 4470a4a3e4c3..9f5b921039bd 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2432,7 +2432,7 @@ int enetc_close(struct net_device *ndev) return 0; } -static int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) +int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct tc_mqprio_qopt *mqprio = type_data; @@ -2486,25 +2486,6 @@ static int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) return 0; } -int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type, - void *type_data) -{ - switch (type) { - case TC_SETUP_QDISC_MQPRIO: - return enetc_setup_tc_mqprio(ndev, type_data); - case TC_SETUP_QDISC_TAPRIO: - return enetc_setup_tc_taprio(ndev, type_data); - case TC_SETUP_QDISC_CBS: - return enetc_setup_tc_cbs(ndev, type_data); - case TC_SETUP_QDISC_ETF: - return enetc_setup_tc_txtime(ndev, type_data); - case TC_SETUP_BLOCK: - return enetc_setup_tc_psfp(ndev, type_data); - default: - return -EOPNOTSUPP; - } -} - static int enetc_setup_xdp_prog(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { @@ -2600,29 +2581,6 @@ static int enetc_set_rss(struct net_device *ndev, int en) return 0; } -static int enetc_set_psfp(struct net_device *ndev, int en) -{ - struct enetc_ndev_priv *priv = netdev_priv(ndev); - int err; - - if (en) { - err = enetc_psfp_enable(priv); - if (err) - return err; - - priv->active_offloads |= ENETC_F_QCI; - return 0; - } - - err = enetc_psfp_disable(priv); - if (err) - return err; - - priv->active_offloads &= ~ENETC_F_QCI; - - return 0; -} - static void enetc_enable_rxvlan(struct net_device *ndev, bool en) { struct enetc_ndev_priv *priv = netdev_priv(ndev); @@ -2641,11 +2599,9 @@ static void enetc_enable_txvlan(struct net_device *ndev, bool en) enetc_bdr_enable_txvlan(&priv->si->hw, i, en); } -int enetc_set_features(struct net_device *ndev, - netdev_features_t features) +void enetc_set_features(struct net_device *ndev, netdev_features_t features) { netdev_features_t changed = ndev->features ^ features; - int err = 0; if (changed & NETIF_F_RXHASH) enetc_set_rss(ndev, !!(features & NETIF_F_RXHASH)); @@ -2657,11 +2613,6 @@ int enetc_set_features(struct net_device *ndev, if (changed & NETIF_F_HW_VLAN_CTAG_TX) enetc_enable_txvlan(ndev, !!(features & NETIF_F_HW_VLAN_CTAG_TX)); - - if (changed & NETIF_F_HW_TC) - err = enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC)); - - return err; } #ifdef CONFIG_FSL_ENETC_PTP_CLOCK diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 29922c20531f..2cfe6944ebd3 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -393,11 +393,9 @@ void enetc_start(struct net_device *ndev); void enetc_stop(struct net_device *ndev); netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev); struct net_device_stats *enetc_get_stats(struct net_device *ndev); -int enetc_set_features(struct net_device *ndev, - netdev_features_t features); +void enetc_set_features(struct net_device *ndev, netdev_features_t features); int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd); -int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type, - void *type_data); +int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data); int enetc_setup_bpf(struct net_device *dev, struct netdev_bpf *xdp); int enetc_xdp_xmit(struct net_device *ndev, int num_frames, struct xdp_frame **frames, u32 flags); @@ -465,6 +463,7 @@ int enetc_setup_tc_block_cb(enum tc_setup_type type, void *type_data, int enetc_setup_tc_psfp(struct net_device *ndev, void *type_data); int enetc_psfp_init(struct enetc_ndev_priv *priv); int enetc_psfp_clean(struct enetc_ndev_priv *priv); +int enetc_set_psfp(struct net_device *ndev, bool en); static inline void enetc_get_max_cap(struct enetc_ndev_priv *priv) { @@ -540,4 +539,9 @@ static inline int enetc_psfp_disable(struct enetc_ndev_priv *priv) { return 0; } + +static inline int enetc_set_psfp(struct net_device *ndev, bool en) +{ + return 0; +} #endif diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index c4a0e836d4f0..bb7750222691 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -709,6 +709,13 @@ static int enetc_pf_set_features(struct net_device *ndev, { netdev_features_t changed = ndev->features ^ features; struct enetc_ndev_priv *priv = netdev_priv(ndev); + int err; + + if (changed & NETIF_F_HW_TC) { + err = enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC)); + if (err) + return err; + } if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) { struct enetc_pf *pf = enetc_si_priv(priv->si); @@ -722,7 +729,28 @@ static int enetc_pf_set_features(struct net_device *ndev, if (changed & NETIF_F_LOOPBACK) enetc_set_loopback(ndev, !!(features & NETIF_F_LOOPBACK)); - return enetc_set_features(ndev, features); + enetc_set_features(ndev, features); + + return 0; +} + +static int enetc_pf_setup_tc(struct net_device *ndev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_QDISC_MQPRIO: + return enetc_setup_tc_mqprio(ndev, type_data); + case TC_SETUP_QDISC_TAPRIO: + return enetc_setup_tc_taprio(ndev, type_data); + case TC_SETUP_QDISC_CBS: + return enetc_setup_tc_cbs(ndev, type_data); + case TC_SETUP_QDISC_ETF: + return enetc_setup_tc_txtime(ndev, type_data); + case TC_SETUP_BLOCK: + return enetc_setup_tc_psfp(ndev, type_data); + default: + return -EOPNOTSUPP; + } } static const struct net_device_ops enetc_ndev_ops = { @@ -739,7 +767,7 @@ static const struct net_device_ops enetc_ndev_ops = { .ndo_set_vf_spoofchk = enetc_pf_set_vf_spoofchk, .ndo_set_features = enetc_pf_set_features, .ndo_eth_ioctl = enetc_ioctl, - .ndo_setup_tc = enetc_setup_tc, + .ndo_setup_tc = enetc_pf_setup_tc, .ndo_bpf = enetc_setup_bpf, .ndo_xdp_xmit = enetc_xdp_xmit, }; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 582a663ed0ba..f8a2f02ce22d 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -1517,6 +1517,29 @@ int enetc_setup_tc_block_cb(enum tc_setup_type type, void *type_data, } } +int enetc_set_psfp(struct net_device *ndev, bool en) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + int err; + + if (en) { + err = enetc_psfp_enable(priv); + if (err) + return err; + + priv->active_offloads |= ENETC_F_QCI; + return 0; + } + + err = enetc_psfp_disable(priv); + if (err) + return err; + + priv->active_offloads &= ~ENETC_F_QCI; + + return 0; +} + int enetc_psfp_init(struct enetc_ndev_priv *priv) { if (epsfp.psfp_sfi_bitmap) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c index 17924305afa2..dfcaac302e24 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c @@ -88,7 +88,20 @@ static int enetc_vf_set_mac_addr(struct net_device *ndev, void *addr) static int enetc_vf_set_features(struct net_device *ndev, netdev_features_t features) { - return enetc_set_features(ndev, features); + enetc_set_features(ndev, features); + + return 0; +} + +static int enetc_vf_setup_tc(struct net_device *ndev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_QDISC_MQPRIO: + return enetc_setup_tc_mqprio(ndev, type_data); + default: + return -EOPNOTSUPP; + } } /* Probing/ Init */ @@ -100,7 +113,7 @@ static const struct net_device_ops enetc_ndev_ops = { .ndo_set_mac_address = enetc_vf_set_mac_addr, .ndo_set_features = enetc_vf_set_features, .ndo_eth_ioctl = enetc_ioctl, - .ndo_setup_tc = enetc_setup_tc, + .ndo_setup_tc = enetc_vf_setup_tc, }; static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev, diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index d77ee8936c6a..a5fed00cb971 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -561,6 +561,7 @@ struct fec_enet_private { struct clk *clk_2x_txclk; bool ptp_clk_on; + struct mutex ptp_clk_mutex; unsigned int num_tx_queues; unsigned int num_rx_queues; @@ -638,13 +639,6 @@ struct fec_enet_private { int pps_enable; unsigned int next_counter; - struct { - struct timespec64 ts_phc; - u64 ns_sys; - u32 at_corr; - u8 at_inc_corr; - } ptp_saved_state; - u64 ethtool_stats[]; }; @@ -655,8 +649,5 @@ void fec_ptp_disable_hwts(struct net_device *ndev); int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr); int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr); -void fec_ptp_save_state(struct fec_enet_private *fep); -int fec_ptp_restore_state(struct fec_enet_private *fep); - /****************************************************************************/ #endif /* FEC_H */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 6152f6dbf1bc..92c55e1a5507 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -286,11 +286,8 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address"); #define FEC_MMFR_TA (2 << 16) #define FEC_MMFR_DATA(v) (v & 0xffff) /* FEC ECR bits definition */ -#define FEC_ECR_RESET BIT(0) -#define FEC_ECR_ETHEREN BIT(1) -#define FEC_ECR_MAGICEN BIT(2) -#define FEC_ECR_SLEEP BIT(3) -#define FEC_ECR_EN1588 BIT(4) +#define FEC_ECR_MAGICEN (1 << 2) +#define FEC_ECR_SLEEP (1 << 3) #define FEC_MII_TIMEOUT 30000 /* us */ @@ -986,9 +983,6 @@ fec_restart(struct net_device *ndev) u32 temp_mac[2]; u32 rcntl = OPT_FRAME_SIZE | 0x04; u32 ecntl = 0x2; /* ETHEREN */ - struct ptp_clock_request ptp_rq = { .type = PTP_CLK_REQ_PPS }; - - fec_ptp_save_state(fep); /* Whack a reset. We should wait for this. * For i.MX6SX SOC, enet use AXI bus, we use disable MAC @@ -1142,7 +1136,7 @@ fec_restart(struct net_device *ndev) } if (fep->bufdesc_ex) - ecntl |= FEC_ECR_EN1588; + ecntl |= (1 << 4); if (fep->quirks & FEC_QUIRK_DELAYED_CLKS_SUPPORT && fep->rgmii_txc_dly) @@ -1163,14 +1157,6 @@ fec_restart(struct net_device *ndev) if (fep->bufdesc_ex) fec_ptp_start_cyclecounter(ndev); - /* Restart PPS if needed */ - if (fep->pps_enable) { - /* Clear flag so fec_ptp_enable_pps() doesn't return immediately */ - fep->pps_enable = 0; - fec_ptp_restore_state(fep); - fep->ptp_caps.enable(&fep->ptp_caps, &ptp_rq, 1); - } - /* Enable interrupts we wish to service */ if (fep->link) writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); @@ -1221,8 +1207,6 @@ fec_stop(struct net_device *ndev) struct fec_enet_private *fep = netdev_priv(ndev); u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8); u32 val; - struct ptp_clock_request ptp_rq = { .type = PTP_CLK_REQ_PPS }; - u32 ecntl = 0; /* We cannot expect a graceful transmit stop without link !!! */ if (fep->link) { @@ -1232,8 +1216,6 @@ fec_stop(struct net_device *ndev) netdev_err(ndev, "Graceful transmit stop did not complete!\n"); } - fec_ptp_save_state(fep); - /* Whack a reset. We should wait for this. * For i.MX6SX SOC, enet use AXI bus, we use disable MAC * instead of reset MAC itself. @@ -1253,28 +1235,12 @@ fec_stop(struct net_device *ndev) writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); - if (fep->bufdesc_ex) - ecntl |= FEC_ECR_EN1588; - /* We have to keep ENET enabled to have MII interrupt stay working */ if (fep->quirks & FEC_QUIRK_ENET_MAC && !(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) { - ecntl |= FEC_ECR_ETHEREN; + writel(2, fep->hwp + FEC_ECNTRL); writel(rmii_mode, fep->hwp + FEC_R_CNTRL); } - - writel(ecntl, fep->hwp + FEC_ECNTRL); - - if (fep->bufdesc_ex) - fec_ptp_start_cyclecounter(ndev); - - /* Restart PPS if needed */ - if (fep->pps_enable) { - /* Clear flag so fec_ptp_enable_pps() doesn't return immediately */ - fep->pps_enable = 0; - fec_ptp_restore_state(fep); - fep->ptp_caps.enable(&fep->ptp_caps, &ptp_rq, 1); - } } @@ -2029,7 +1995,6 @@ static void fec_enet_phy_reset_after_clk_enable(struct net_device *ndev) static int fec_enet_clk_enable(struct net_device *ndev, bool enable) { struct fec_enet_private *fep = netdev_priv(ndev); - unsigned long flags; int ret; if (enable) { @@ -2038,15 +2003,15 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) return ret; if (fep->clk_ptp) { - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&fep->ptp_clk_mutex); ret = clk_prepare_enable(fep->clk_ptp); if (ret) { - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); goto failed_clk_ptp; } else { fep->ptp_clk_on = true; } - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); } ret = clk_prepare_enable(fep->clk_ref); @@ -2061,10 +2026,10 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) } else { clk_disable_unprepare(fep->clk_enet_out); if (fep->clk_ptp) { - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&fep->ptp_clk_mutex); clk_disable_unprepare(fep->clk_ptp); fep->ptp_clk_on = false; - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); } clk_disable_unprepare(fep->clk_ref); clk_disable_unprepare(fep->clk_2x_txclk); @@ -2077,10 +2042,10 @@ failed_clk_2x_txclk: clk_disable_unprepare(fep->clk_ref); failed_clk_ref: if (fep->clk_ptp) { - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&fep->ptp_clk_mutex); clk_disable_unprepare(fep->clk_ptp); fep->ptp_clk_on = false; - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); } failed_clk_ptp: clk_disable_unprepare(fep->clk_enet_out); @@ -3915,7 +3880,7 @@ fec_probe(struct platform_device *pdev) } fep->ptp_clk_on = false; - spin_lock_init(&fep->tmreg_lock); + mutex_init(&fep->ptp_clk_mutex); /* clk_ref is optional, depends on board */ fep->clk_ref = devm_clk_get_optional(&pdev->dev, "enet_clk_ref"); diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 8dd5a2615a89..3dc3c0b626c2 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -365,19 +365,21 @@ static int fec_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) */ static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { - struct fec_enet_private *fep = + struct fec_enet_private *adapter = container_of(ptp, struct fec_enet_private, ptp_caps); u64 ns; unsigned long flags; - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&adapter->ptp_clk_mutex); /* Check the ptp clock */ - if (!fep->ptp_clk_on) { - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + if (!adapter->ptp_clk_on) { + mutex_unlock(&adapter->ptp_clk_mutex); return -EINVAL; } - ns = timecounter_read(&fep->tc); - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_read(&adapter->tc); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + mutex_unlock(&adapter->ptp_clk_mutex); *ts = ns_to_timespec64(ns); @@ -402,10 +404,10 @@ static int fec_ptp_settime(struct ptp_clock_info *ptp, unsigned long flags; u32 counter; - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&fep->ptp_clk_mutex); /* Check the ptp clock */ if (!fep->ptp_clk_on) { - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); return -EINVAL; } @@ -415,9 +417,11 @@ static int fec_ptp_settime(struct ptp_clock_info *ptp, */ counter = ns & fep->cc.mask; + spin_lock_irqsave(&fep->tmreg_lock, flags); writel(counter, fep->hwp + FEC_ATIME); timecounter_init(&fep->tc, &fep->cc, ns); spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); return 0; } @@ -514,11 +518,13 @@ static void fec_time_keep(struct work_struct *work) struct fec_enet_private *fep = container_of(dwork, struct fec_enet_private, time_keep); unsigned long flags; - spin_lock_irqsave(&fep->tmreg_lock, flags); + mutex_lock(&fep->ptp_clk_mutex); if (fep->ptp_clk_on) { + spin_lock_irqsave(&fep->tmreg_lock, flags); timecounter_read(&fep->tc); + spin_unlock_irqrestore(&fep->tmreg_lock, flags); } - spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); schedule_delayed_work(&fep->time_keep, HZ); } @@ -593,6 +599,8 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx) } fep->ptp_inc = NSEC_PER_SEC / fep->cycle_speed; + spin_lock_init(&fep->tmreg_lock); + fec_ptp_start_cyclecounter(ndev); INIT_DELAYED_WORK(&fep->time_keep, fec_time_keep); @@ -625,36 +633,7 @@ void fec_ptp_stop(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); - if (fep->pps_enable) - fec_ptp_enable_pps(fep, 0); - cancel_delayed_work_sync(&fep->time_keep); if (fep->ptp_clock) ptp_clock_unregister(fep->ptp_clock); } - -void fec_ptp_save_state(struct fec_enet_private *fep) -{ - u32 atime_inc_corr; - - fec_ptp_gettime(&fep->ptp_caps, &fep->ptp_saved_state.ts_phc); - fep->ptp_saved_state.ns_sys = ktime_get_ns(); - - fep->ptp_saved_state.at_corr = readl(fep->hwp + FEC_ATIME_CORR); - atime_inc_corr = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_CORR_MASK; - fep->ptp_saved_state.at_inc_corr = (u8)(atime_inc_corr >> FEC_T_INC_CORR_OFFSET); -} - -int fec_ptp_restore_state(struct fec_enet_private *fep) -{ - u32 atime_inc = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_MASK; - u64 ns_sys; - - writel(fep->ptp_saved_state.at_corr, fep->hwp + FEC_ATIME_CORR); - atime_inc |= ((u32)fep->ptp_saved_state.at_inc_corr) << FEC_T_INC_CORR_OFFSET; - writel(atime_inc, fep->hwp + FEC_ATIME_INC); - - ns_sys = ktime_get_ns() - fep->ptp_saved_state.ns_sys; - timespec64_add_ns(&fep->ptp_saved_state.ts_phc, ns_sys); - return fec_ptp_settime(&fep->ptp_caps, &fep->ptp_saved_state.ts_phc); -} diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 8c939628e2d8..2e6461b0ea8b 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -157,7 +157,7 @@ static int gve_alloc_page_dqo(struct gve_priv *priv, int err; err = gve_alloc_page(priv, &priv->pdev->dev, &buf_state->page_info.page, - &buf_state->addr, DMA_FROM_DEVICE, GFP_KERNEL); + &buf_state->addr, DMA_FROM_DEVICE, GFP_ATOMIC); if (err) return err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 10c1e1ea83a1..e3d9804aeb25 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5909,6 +5909,26 @@ static int i40e_get_link_speed(struct i40e_vsi *vsi) } /** + * i40e_bw_bytes_to_mbits - Convert max_tx_rate from bytes to mbits + * @vsi: Pointer to vsi structure + * @max_tx_rate: max TX rate in bytes to be converted into Mbits + * + * Helper function to convert units before send to set BW limit + **/ +static u64 i40e_bw_bytes_to_mbits(struct i40e_vsi *vsi, u64 max_tx_rate) +{ + if (max_tx_rate < I40E_BW_MBPS_DIVISOR) { + dev_warn(&vsi->back->pdev->dev, + "Setting max tx rate to minimum usable value of 50Mbps.\n"); + max_tx_rate = I40E_BW_CREDIT_DIVISOR; + } else { + do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); + } + + return max_tx_rate; +} + +/** * i40e_set_bw_limit - setup BW limit for Tx traffic based on max_tx_rate * @vsi: VSI to be configured * @seid: seid of the channel/VSI @@ -5930,10 +5950,10 @@ int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate) max_tx_rate, seid); return -EINVAL; } - if (max_tx_rate && max_tx_rate < 50) { + if (max_tx_rate && max_tx_rate < I40E_BW_CREDIT_DIVISOR) { dev_warn(&pf->pdev->dev, "Setting max tx rate to minimum usable value of 50Mbps.\n"); - max_tx_rate = 50; + max_tx_rate = I40E_BW_CREDIT_DIVISOR; } /* Tx rate credits are in values of 50Mbps, 0 is disabled */ @@ -8224,9 +8244,9 @@ config_tc: if (i40e_is_tc_mqprio_enabled(pf)) { if (vsi->mqprio_qopt.max_rate[0]) { - u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; + u64 max_tx_rate = i40e_bw_bytes_to_mbits(vsi, + vsi->mqprio_qopt.max_rate[0]); - do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); if (!ret) { u64 credits = max_tx_rate; @@ -10971,10 +10991,10 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } if (vsi->mqprio_qopt.max_rate[0]) { - u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; + u64 max_tx_rate = i40e_bw_bytes_to_mbits(vsi, + vsi->mqprio_qopt.max_rate[0]); u64 credits = 0; - do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR); ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate); if (ret) goto end_unlock; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 4f184c50f6e8..7e9f6a69eb10 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2039,6 +2039,25 @@ static void i40e_del_qch(struct i40e_vf *vf) } /** + * i40e_vc_get_max_frame_size + * @vf: pointer to the VF + * + * Max frame size is determined based on the current port's max frame size and + * whether a port VLAN is configured on this VF. The VF is not aware whether + * it's in a port VLAN so the PF needs to account for this in max frame size + * checks and sending the max frame size to the VF. + **/ +static u16 i40e_vc_get_max_frame_size(struct i40e_vf *vf) +{ + u16 max_frame_size = vf->pf->hw.phy.link_info.max_frame_size; + + if (vf->port_vlan_id) + max_frame_size -= VLAN_HLEN; + + return max_frame_size; +} + +/** * i40e_vc_get_vf_resources_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2139,6 +2158,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf; vfres->rss_key_size = I40E_HKEY_ARRAY_SIZE; vfres->rss_lut_size = I40E_VF_HLUT_ARRAY_SIZE; + vfres->max_mtu = i40e_vc_get_max_frame_size(vf); if (vf->lan_vsi_idx) { vfres->vsi_res[0].vsi_id = vf->lan_vsi_id; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 10aa99dfdcdb..0c89f16bf1e2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1077,7 +1077,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p) { struct iavf_adapter *adapter = netdev_priv(netdev); struct sockaddr *addr = p; - bool handle_mac = iavf_is_mac_set_handled(netdev, addr->sa_data); int ret; if (!is_valid_ether_addr(addr->sa_data)) @@ -1094,10 +1093,9 @@ static int iavf_set_mac(struct net_device *netdev, void *p) return 0; } - if (handle_mac) - goto done; - - ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, false, msecs_to_jiffies(2500)); + ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, + iavf_is_mac_set_handled(netdev, addr->sa_data), + msecs_to_jiffies(2500)); /* If ret < 0 then it means wait was interrupted. * If ret == 0 then it means we got a timeout. @@ -1111,7 +1109,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p) if (!ret) return -EAGAIN; -done: if (!ether_addr_equal(netdev->dev_addr, addr->sa_data)) return -EACCES; diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 06d18797d25a..18b6a702a1d6 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -114,8 +114,11 @@ u32 iavf_get_tx_pending(struct iavf_ring *ring, bool in_sw) { u32 head, tail; + /* underlying hardware might not allow access and/or always return + * 0 for the head/tail registers so just use the cached values + */ head = ring->next_to_clean; - tail = readl(ring->tail); + tail = ring->next_to_use; if (head != tail) return (head < tail) ? @@ -1390,7 +1393,7 @@ static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring, #endif struct sk_buff *skb; - if (!rx_buffer) + if (!rx_buffer || !size) return NULL; /* prefetch first cache line of first page */ va = page_address(rx_buffer->page) + rx_buffer->page_offset; @@ -1548,7 +1551,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) /* exit if we failed to retrieve a buffer */ if (!skb) { rx_ring->rx_stats.alloc_buff_failed++; - if (rx_buffer) + if (rx_buffer && size) rx_buffer->pagecnt_bias++; break; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 15ee85dc33bd..5a9e6563923e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -269,11 +269,14 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter) void iavf_configure_queues(struct iavf_adapter *adapter) { struct virtchnl_vsi_queue_config_info *vqci; - struct virtchnl_queue_pair_info *vqpi; + int i, max_frame = adapter->vf_res->max_mtu; int pairs = adapter->num_active_queues; - int i, max_frame = IAVF_MAX_RXBUFFER; + struct virtchnl_queue_pair_info *vqpi; size_t len; + if (max_frame > IAVF_MAX_RXBUFFER || !max_frame) + max_frame = IAVF_MAX_RXBUFFER; + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ dev_err(&adapter->pdev->dev, "Cannot configure queues, command %d pending\n", diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 0c4ec9264071..58d483e2f539 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -914,7 +914,7 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) */ static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) { - u16 offset = 0, qmap = 0, tx_count = 0, pow = 0; + u16 offset = 0, qmap = 0, tx_count = 0, rx_count = 0, pow = 0; u16 num_txq_per_tc, num_rxq_per_tc; u16 qcount_tx = vsi->alloc_txq; u16 qcount_rx = vsi->alloc_rxq; @@ -981,23 +981,25 @@ static int ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) * at least 1) */ if (offset) - vsi->num_rxq = offset; + rx_count = offset; else - vsi->num_rxq = num_rxq_per_tc; + rx_count = num_rxq_per_tc; - if (vsi->num_rxq > vsi->alloc_rxq) { + if (rx_count > vsi->alloc_rxq) { dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n", - vsi->num_rxq, vsi->alloc_rxq); + rx_count, vsi->alloc_rxq); return -EINVAL; } - vsi->num_txq = tx_count; - if (vsi->num_txq > vsi->alloc_txq) { + if (tx_count > vsi->alloc_txq) { dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n", - vsi->num_txq, vsi->alloc_txq); + tx_count, vsi->alloc_txq); return -EINVAL; } + vsi->num_txq = tx_count; + vsi->num_rxq = rx_count; + if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) { dev_dbg(ice_pf_to_dev(vsi->back), "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n"); /* since there is a chance that num_rxq could have been changed @@ -3490,6 +3492,7 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt, u16 pow, offset = 0, qcount_tx = 0, qcount_rx = 0, qmap; u16 tc0_offset = vsi->mqprio_qopt.qopt.offset[0]; int tc0_qcount = vsi->mqprio_qopt.qopt.count[0]; + u16 new_txq, new_rxq; u8 netdev_tc = 0; int i; @@ -3530,21 +3533,24 @@ ice_vsi_setup_q_map_mqprio(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt, } } - /* Set actual Tx/Rx queue pairs */ - vsi->num_txq = offset + qcount_tx; - if (vsi->num_txq > vsi->alloc_txq) { + new_txq = offset + qcount_tx; + if (new_txq > vsi->alloc_txq) { dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Tx queues (%u), than were allocated (%u)!\n", - vsi->num_txq, vsi->alloc_txq); + new_txq, vsi->alloc_txq); return -EINVAL; } - vsi->num_rxq = offset + qcount_rx; - if (vsi->num_rxq > vsi->alloc_rxq) { + new_rxq = offset + qcount_rx; + if (new_rxq > vsi->alloc_rxq) { dev_err(ice_pf_to_dev(vsi->back), "Trying to use more Rx queues (%u), than were allocated (%u)!\n", - vsi->num_rxq, vsi->alloc_rxq); + new_rxq, vsi->alloc_rxq); return -EINVAL; } + /* Set actual Tx/Rx queue pairs */ + vsi->num_txq = new_txq; + vsi->num_rxq = new_rxq; + /* Setup queue TC[0].qmap for given VSI context */ ctxt->info.tc_mapping[0] = cpu_to_le16(qmap); ctxt->info.q_mapping[0] = cpu_to_le16(vsi->rxq_map[0]); @@ -3576,6 +3582,7 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_pf *pf = vsi->back; + struct ice_tc_cfg old_tc_cfg; struct ice_vsi_ctx *ctx; struct device *dev; int i, ret = 0; @@ -3600,6 +3607,7 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) max_txqs[i] = vsi->num_txq; } + memcpy(&old_tc_cfg, &vsi->tc_cfg, sizeof(old_tc_cfg)); vsi->tc_cfg.ena_tc = ena_tc; vsi->tc_cfg.numtc = num_tc; @@ -3616,8 +3624,10 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) else ret = ice_vsi_setup_q_map(vsi, ctx); - if (ret) + if (ret) { + memcpy(&vsi->tc_cfg, &old_tc_cfg, sizeof(vsi->tc_cfg)); goto out; + } /* must to indicate which section of VSI context are being modified */ ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 8c30eea61b6d..e109cb93886b 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2399,8 +2399,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset) return -EBUSY; } - ice_unplug_aux_dev(pf); - switch (reset) { case ICE_RESET_PFR: set_bit(ICE_PFR_REQ, pf->state); @@ -6651,7 +6649,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) */ int ice_down(struct ice_vsi *vsi) { - int i, tx_err, rx_err, link_err = 0, vlan_err = 0; + int i, tx_err, rx_err, vlan_err = 0; WARN_ON(!test_bit(ICE_VSI_DOWN, vsi->state)); @@ -6685,20 +6683,13 @@ int ice_down(struct ice_vsi *vsi) ice_napi_disable_all(vsi); - if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) { - link_err = ice_force_phys_link_state(vsi, false); - if (link_err) - netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", - vsi->vsi_num, link_err); - } - ice_for_each_txq(vsi, i) ice_clean_tx_ring(vsi->tx_rings[i]); ice_for_each_rxq(vsi, i) ice_clean_rx_ring(vsi->rx_rings[i]); - if (tx_err || rx_err || link_err || vlan_err) { + if (tx_err || rx_err || vlan_err) { netdev_err(vsi->netdev, "Failed to close VSI 0x%04X on switch 0x%04X\n", vsi->vsi_num, vsi->vsw->sw_id); return -EIO; @@ -6860,6 +6851,8 @@ int ice_vsi_open(struct ice_vsi *vsi) if (err) goto err_setup_rx; + ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); + 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); @@ -8892,6 +8885,16 @@ int ice_stop(struct net_device *netdev) return -EBUSY; } + if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) { + int link_err = ice_force_phys_link_state(vsi, false); + + if (link_err) { + netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", + vsi->vsi_num, link_err); + return -EIO; + } + } + ice_vsi_close(vsi); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 836dce840712..97453d1dfafe 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -610,7 +610,7 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, if (test_bit(ICE_VSI_DOWN, vsi->state)) return -ENETDOWN; - if (!ice_is_xdp_ena_vsi(vsi) || queue_index >= vsi->num_xdp_txq) + if (!ice_is_xdp_ena_vsi(vsi)) return -ENXIO; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) @@ -621,6 +621,9 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, xdp_ring = vsi->xdp_rings[queue_index]; spin_lock(&xdp_ring->tx_lock); } else { + /* Generally, should not happen */ + if (unlikely(queue_index >= vsi->num_xdp_txq)) + return -ENXIO; xdp_ring = vsi->xdp_rings[queue_index]; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index ede3e53b9790..a895862b4821 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -368,6 +368,7 @@ static int prestera_port_sfp_bind(struct prestera_port *port) if (!sw->np) return 0; + of_node_get(sw->np); ports = of_find_node_by_name(sw->np, "ports"); for_each_child_of_node(ports, node) { @@ -417,6 +418,7 @@ static int prestera_port_sfp_bind(struct prestera_port *port) } out: + of_node_put(node); of_node_put(ports); return err; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index f538a749ebd4..59470d99f522 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -872,6 +872,7 @@ static void prestera_pci_remove(struct pci_dev *pdev) static const struct pci_device_id prestera_pci_devices[] = { { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xC804) }, { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xC80C) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xCC1E) }, { } }; MODULE_DEVICE_TABLE(pci, prestera_pci_devices); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 5ace4609de47..b344632beadd 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1458,7 +1458,7 @@ static void mtk_update_rx_cpu_idx(struct mtk_eth *eth) static bool mtk_page_pool_enabled(struct mtk_eth *eth) { - return !eth->hwlro; + return MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2); } static struct page_pool *mtk_create_page_pool(struct mtk_eth *eth, diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c index 85155cd9405c..4aeb927c3715 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c @@ -179,6 +179,9 @@ static int mlxbf_gige_mdio_read(struct mii_bus *bus, int phy_add, int phy_reg) /* Only return ad bits of the gw register */ ret &= MLXBF_GIGE_MDIO_GW_AD_MASK; + /* The MDIO lock is set on read. To release it, clear gw register */ + writel(0, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + return ret; } @@ -203,6 +206,9 @@ static int mlxbf_gige_mdio_write(struct mii_bus *bus, int phy_add, temp, !(temp & MLXBF_GIGE_MDIO_GW_BUSY_MASK), 5, 1000000); + /* The MDIO lock is set on read. To release it, clear gw register */ + writel(0, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + return ret; } diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 00d8198072ae..a6f99b4344d9 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -397,6 +397,11 @@ static void mana_gd_process_eq_events(void *arg) break; } + /* Per GDMA spec, rmb is necessary after checking owner_bits, before + * reading eqe. + */ + rmb(); + mana_gd_process_eqe(eq); eq->head++; @@ -1134,6 +1139,11 @@ static int mana_gd_read_cqe(struct gdma_queue *cq, struct gdma_comp *comp) if (WARN_ON_ONCE(owner_bits != new_bits)) return -1; + /* Per GDMA spec, rmb is necessary after checking owner_bits, before + * reading completion info + */ + rmb(); + comp->wq_num = cqe->cqe_info.wq_num; comp->is_sq = cqe->cqe_info.is_sq; memcpy(comp->cqe_data, cqe->cqe_data, GDMA_COMP_DATA_SIZE); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index b357ac4c56c5..7e32b04eb0c7 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1449,6 +1449,8 @@ static int ravb_phy_init(struct net_device *ndev) phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); } + /* Indicate that the MAC is responsible for managing PHY PM */ + phydev->mac_managed_pm = true; phy_attached_info(phydev); return 0; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 67ade78fb767..7fd8828d3a84 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2029,6 +2029,8 @@ static int sh_eth_phy_init(struct net_device *ndev) if (mdp->cd->register_type != SH_ETH_REG_GIGABIT) phy_set_max_speed(phydev, SPEED_100); + /* Indicate that the MAC is responsible for managing PHY PM */ + phydev->mac_managed_pm = true; phy_attached_info(phydev); return 0; diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index 032b8c0bd788..5b4d661ab986 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -319,7 +319,7 @@ int efx_probe_interrupts(struct efx_nic *efx) efx->n_channels = 1 + (efx_separate_tx_channels ? 1 : 0); efx->n_rx_channels = 1; efx->n_tx_channels = 1; - efx->tx_channel_offset = 1; + efx->tx_channel_offset = efx_separate_tx_channels ? 1 : 0; efx->n_xdp_channels = 0; efx->xdp_channel_offset = efx->n_channels; efx->legacy_irq = efx->pci_dev->irq; diff --git a/drivers/net/ethernet/sfc/siena/efx_channels.c b/drivers/net/ethernet/sfc/siena/efx_channels.c index 017212a40df3..f54ebd007286 100644 --- a/drivers/net/ethernet/sfc/siena/efx_channels.c +++ b/drivers/net/ethernet/sfc/siena/efx_channels.c @@ -320,7 +320,7 @@ int efx_siena_probe_interrupts(struct efx_nic *efx) efx->n_channels = 1 + (efx_siena_separate_tx_channels ? 1 : 0); efx->n_rx_channels = 1; efx->n_tx_channels = 1; - efx->tx_channel_offset = 1; + efx->tx_channel_offset = efx_siena_separate_tx_channels ? 1 : 0; efx->n_xdp_channels = 0; efx->xdp_channel_offset = efx->n_channels; efx->legacy_irq = efx->pci_dev->irq; diff --git a/drivers/net/ethernet/sfc/siena/tx.c b/drivers/net/ethernet/sfc/siena/tx.c index e166dcb9b99c..91e87594ed1e 100644 --- a/drivers/net/ethernet/sfc/siena/tx.c +++ b/drivers/net/ethernet/sfc/siena/tx.c @@ -336,7 +336,7 @@ netdev_tx_t efx_siena_hard_start_xmit(struct sk_buff *skb, * previous packets out. */ if (!netdev_xmit_more()) - efx_tx_send_pending(tx_queue->channel); + efx_tx_send_pending(efx_get_tx_channel(efx, index)); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index d12474042c84..c5f88f7a7a04 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -549,7 +549,7 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, * previous packets out. */ if (!netdev_xmit_more()) - efx_tx_send_pending(tx_queue->channel); + efx_tx_send_pending(efx_get_tx_channel(efx, index)); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 8594ee839628..88aa0d310aee 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -2020,9 +2020,9 @@ static void happy_meal_rx(struct happy_meal *hp, struct net_device *dev) skb_reserve(copy_skb, 2); skb_put(copy_skb, len); - dma_sync_single_for_cpu(hp->dma_dev, dma_addr, len, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(hp->dma_dev, dma_addr, len + 2, DMA_FROM_DEVICE); skb_copy_from_linear_data(skb, copy_skb->data, len); - dma_sync_single_for_device(hp->dma_dev, dma_addr, len, DMA_FROM_DEVICE); + dma_sync_single_for_device(hp->dma_dev, dma_addr, len + 2, DMA_FROM_DEVICE); /* Reuse original ring buffer. */ hme_write_rxd(hp, this, (RXFLAG_OWN|((RX_BUF_ALLOC_SIZE-RX_OFFSET)<<16)), diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c index ec010cf2e816..6f874f99b910 100644 --- a/drivers/net/ipa/ipa_qmi.c +++ b/drivers/net/ipa/ipa_qmi.c @@ -308,12 +308,12 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) mem = ipa_mem_find(ipa, IPA_MEM_V4_ROUTE); req.v4_route_tbl_info_valid = 1; req.v4_route_tbl_info.start = ipa->mem_offset + mem->offset; - req.v4_route_tbl_info.count = mem->size / sizeof(__le64); + req.v4_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1; mem = ipa_mem_find(ipa, IPA_MEM_V6_ROUTE); req.v6_route_tbl_info_valid = 1; req.v6_route_tbl_info.start = ipa->mem_offset + mem->offset; - req.v6_route_tbl_info.count = mem->size / sizeof(__le64); + req.v6_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1; mem = ipa_mem_find(ipa, IPA_MEM_V4_FILTER); req.v4_filter_tbl_start_valid = 1; @@ -352,7 +352,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) req.v4_hash_route_tbl_info_valid = 1; req.v4_hash_route_tbl_info.start = ipa->mem_offset + mem->offset; - req.v4_hash_route_tbl_info.count = mem->size / sizeof(__le64); + req.v4_hash_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1; } mem = ipa_mem_find(ipa, IPA_MEM_V6_ROUTE_HASHED); @@ -360,7 +360,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) req.v6_hash_route_tbl_info_valid = 1; req.v6_hash_route_tbl_info.start = ipa->mem_offset + mem->offset; - req.v6_hash_route_tbl_info.count = mem->size / sizeof(__le64); + req.v6_hash_route_tbl_info.end = IPA_ROUTE_MODEM_COUNT - 1; } mem = ipa_mem_find(ipa, IPA_MEM_V4_FILTER_HASHED); diff --git a/drivers/net/ipa/ipa_qmi_msg.c b/drivers/net/ipa/ipa_qmi_msg.c index 6838e8065072..75d3fc0092e9 100644 --- a/drivers/net/ipa/ipa_qmi_msg.c +++ b/drivers/net/ipa/ipa_qmi_msg.c @@ -311,7 +311,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = { .tlv_type = 0x12, .offset = offsetof(struct ipa_init_modem_driver_req, v4_route_tbl_info), - .ei_array = ipa_mem_array_ei, + .ei_array = ipa_mem_bounds_ei, }, { .data_type = QMI_OPT_FLAG, @@ -332,7 +332,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = { .tlv_type = 0x13, .offset = offsetof(struct ipa_init_modem_driver_req, v6_route_tbl_info), - .ei_array = ipa_mem_array_ei, + .ei_array = ipa_mem_bounds_ei, }, { .data_type = QMI_OPT_FLAG, @@ -496,7 +496,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = { .tlv_type = 0x1b, .offset = offsetof(struct ipa_init_modem_driver_req, v4_hash_route_tbl_info), - .ei_array = ipa_mem_array_ei, + .ei_array = ipa_mem_bounds_ei, }, { .data_type = QMI_OPT_FLAG, @@ -517,7 +517,7 @@ struct qmi_elem_info ipa_init_modem_driver_req_ei[] = { .tlv_type = 0x1c, .offset = offsetof(struct ipa_init_modem_driver_req, v6_hash_route_tbl_info), - .ei_array = ipa_mem_array_ei, + .ei_array = ipa_mem_bounds_ei, }, { .data_type = QMI_OPT_FLAG, diff --git a/drivers/net/ipa/ipa_qmi_msg.h b/drivers/net/ipa/ipa_qmi_msg.h index 495e85abe50b..9651aa59b596 100644 --- a/drivers/net/ipa/ipa_qmi_msg.h +++ b/drivers/net/ipa/ipa_qmi_msg.h @@ -86,9 +86,11 @@ enum ipa_platform_type { IPA_QMI_PLATFORM_TYPE_MSM_QNX_V01 = 0x5, /* QNX MSM */ }; -/* This defines the start and end offset of a range of memory. Both - * fields are offsets relative to the start of IPA shared memory. - * The end value is the last addressable byte *within* the range. +/* This defines the start and end offset of a range of memory. The start + * value is a byte offset relative to the start of IPA shared memory. The + * end value is the last addressable unit *within* the range. Typically + * the end value is in units of bytes, however it can also be a maximum + * array index value. */ struct ipa_mem_bounds { u32 start; @@ -129,18 +131,19 @@ struct ipa_init_modem_driver_req { u8 hdr_tbl_info_valid; struct ipa_mem_bounds hdr_tbl_info; - /* Routing table information. These define the location and size of - * non-hashable IPv4 and IPv6 filter tables. The start values are - * offsets relative to the start of IPA shared memory. + /* Routing table information. These define the location and maximum + * *index* (not byte) for the modem portion of non-hashable IPv4 and + * IPv6 routing tables. The start values are byte offsets relative + * to the start of IPA shared memory. */ u8 v4_route_tbl_info_valid; - struct ipa_mem_array v4_route_tbl_info; + struct ipa_mem_bounds v4_route_tbl_info; u8 v6_route_tbl_info_valid; - struct ipa_mem_array v6_route_tbl_info; + struct ipa_mem_bounds v6_route_tbl_info; /* Filter table information. These define the location of the * non-hashable IPv4 and IPv6 filter tables. The start values are - * offsets relative to the start of IPA shared memory. + * byte offsets relative to the start of IPA shared memory. */ u8 v4_filter_tbl_start_valid; u32 v4_filter_tbl_start; @@ -181,18 +184,20 @@ struct ipa_init_modem_driver_req { u8 zip_tbl_info_valid; struct ipa_mem_bounds zip_tbl_info; - /* Routing table information. These define the location and size - * of hashable IPv4 and IPv6 filter tables. The start values are - * offsets relative to the start of IPA shared memory. + /* Routing table information. These define the location and maximum + * *index* (not byte) for the modem portion of hashable IPv4 and IPv6 + * routing tables (if supported by hardware). The start values are + * byte offsets relative to the start of IPA shared memory. */ u8 v4_hash_route_tbl_info_valid; - struct ipa_mem_array v4_hash_route_tbl_info; + struct ipa_mem_bounds v4_hash_route_tbl_info; u8 v6_hash_route_tbl_info_valid; - struct ipa_mem_array v6_hash_route_tbl_info; + struct ipa_mem_bounds v6_hash_route_tbl_info; /* Filter table information. These define the location and size - * of hashable IPv4 and IPv6 filter tables. The start values are - * offsets relative to the start of IPA shared memory. + * of hashable IPv4 and IPv6 filter tables (if supported by hardware). + * The start values are byte offsets relative to the start of IPA + * shared memory. */ u8 v4_hash_filter_tbl_start_valid; u32 v4_hash_filter_tbl_start; diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index 2f5a58bfc529..69efe672ca52 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -108,8 +108,6 @@ /* Assignment of route table entries to the modem and AP */ #define IPA_ROUTE_MODEM_MIN 0 -#define IPA_ROUTE_MODEM_COUNT 8 - #define IPA_ROUTE_AP_MIN IPA_ROUTE_MODEM_COUNT #define IPA_ROUTE_AP_COUNT \ (IPA_ROUTE_COUNT_MAX - IPA_ROUTE_MODEM_COUNT) diff --git a/drivers/net/ipa/ipa_table.h b/drivers/net/ipa/ipa_table.h index b6a9a0d79d68..1538e2e1732f 100644 --- a/drivers/net/ipa/ipa_table.h +++ b/drivers/net/ipa/ipa_table.h @@ -13,6 +13,9 @@ struct ipa; /* The maximum number of filter table entries (IPv4, IPv6; hashed or not) */ #define IPA_FILTER_COUNT_MAX 14 +/* The number of route table entries allotted to the modem */ +#define IPA_ROUTE_MODEM_COUNT 8 + /* The maximum number of route table entries (IPv4, IPv6; hashed or not) */ #define IPA_ROUTE_COUNT_MAX 15 diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index dfeb5b392e64..bb1c298c1e78 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -495,7 +495,6 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) static int ipvlan_process_outbound(struct sk_buff *skb) { - struct ethhdr *ethh = eth_hdr(skb); int ret = NET_XMIT_DROP; /* The ipvlan is a pseudo-L2 device, so the packets that we receive @@ -505,6 +504,8 @@ static int ipvlan_process_outbound(struct sk_buff *skb) if (skb_mac_header_was_set(skb)) { /* In this mode we dont care about * multicast and broadcast traffic */ + struct ethhdr *ethh = eth_hdr(skb); + if (is_multicast_ether_addr(ethh->h_dest)) { pr_debug_ratelimited( "Dropped {multi|broad}cast of type=[%x]\n", @@ -589,7 +590,7 @@ out: static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); - struct ethhdr *eth = eth_hdr(skb); + struct ethhdr *eth = skb_eth_hdr(skb); struct ipvl_addr *addr; void *lyr3h; int addr_type; @@ -619,6 +620,7 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) return dev_forward_skb(ipvlan->phy_dev, skb); } else if (is_multicast_ether_addr(eth->h_dest)) { + skb_reset_mac_header(skb); ipvlan_skb_crossing_ns(skb, NULL); ipvlan_multicast_enqueue(ipvlan->port, skb, true); return NET_XMIT_SUCCESS; diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 9e3c815a070f..796e9c7857d0 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -231,6 +231,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) return 0; unregister: + of_node_put(child); mdiobus_unregister(mdio); return rc; } diff --git a/drivers/net/netdevsim/hwstats.c b/drivers/net/netdevsim/hwstats.c index 605a38e16db0..0e58aa7f0374 100644 --- a/drivers/net/netdevsim/hwstats.c +++ b/drivers/net/netdevsim/hwstats.c @@ -433,11 +433,11 @@ int nsim_dev_hwstats_init(struct nsim_dev *nsim_dev) goto err_remove_hwstats_recursive; } - debugfs_create_file("enable_ifindex", 0600, hwstats->l3_ddir, hwstats, + debugfs_create_file("enable_ifindex", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_enable_fops.fops); - debugfs_create_file("disable_ifindex", 0600, hwstats->l3_ddir, hwstats, + debugfs_create_file("disable_ifindex", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_disable_fops.fops); - debugfs_create_file("fail_next_enable", 0600, hwstats->l3_ddir, hwstats, + debugfs_create_file("fail_next_enable", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_fail_fops.fops); INIT_DELAYED_WORK(&hwstats->traffic_dw, diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c index 8b7a46db30e0..7111e2e958e9 100644 --- a/drivers/net/phy/aquantia_main.c +++ b/drivers/net/phy/aquantia_main.c @@ -91,6 +91,9 @@ #define VEND1_GLOBAL_FW_ID_MAJOR GENMASK(15, 8) #define VEND1_GLOBAL_FW_ID_MINOR GENMASK(7, 0) +#define VEND1_GLOBAL_GEN_STAT2 0xc831 +#define VEND1_GLOBAL_GEN_STAT2_OP_IN_PROG BIT(15) + #define VEND1_GLOBAL_RSVD_STAT1 0xc885 #define VEND1_GLOBAL_RSVD_STAT1_FW_BUILD_ID GENMASK(7, 4) #define VEND1_GLOBAL_RSVD_STAT1_PROV_ID GENMASK(3, 0) @@ -125,6 +128,12 @@ #define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL2 BIT(1) #define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3 BIT(0) +/* Sleep and timeout for checking if the Processor-Intensive + * MDIO operation is finished + */ +#define AQR107_OP_IN_PROG_SLEEP 1000 +#define AQR107_OP_IN_PROG_TIMEOUT 100000 + struct aqr107_hw_stat { const char *name; int reg; @@ -597,16 +606,52 @@ static void aqr107_link_change_notify(struct phy_device *phydev) phydev_info(phydev, "Aquantia 1000Base-T2 mode active\n"); } +static int aqr107_wait_processor_intensive_op(struct phy_device *phydev) +{ + int val, err; + + /* The datasheet notes to wait at least 1ms after issuing a + * processor intensive operation before checking. + * We cannot use the 'sleep_before_read' parameter of read_poll_timeout + * because that just determines the maximum time slept, not the minimum. + */ + usleep_range(1000, 5000); + + err = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, + VEND1_GLOBAL_GEN_STAT2, val, + !(val & VEND1_GLOBAL_GEN_STAT2_OP_IN_PROG), + AQR107_OP_IN_PROG_SLEEP, + AQR107_OP_IN_PROG_TIMEOUT, false); + if (err) { + phydev_err(phydev, "timeout: processor-intensive MDIO operation\n"); + return err; + } + + return 0; +} + static int aqr107_suspend(struct phy_device *phydev) { - return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1, - MDIO_CTRL1_LPOWER); + int err; + + err = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1, + MDIO_CTRL1_LPOWER); + if (err) + return err; + + return aqr107_wait_processor_intensive_op(phydev); } static int aqr107_resume(struct phy_device *phydev) { - return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1, - MDIO_CTRL1_LPOWER); + int err; + + err = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MDIO_CTRL1, + MDIO_CTRL1_LPOWER); + if (err) + return err; + + return aqr107_wait_processor_intensive_op(phydev); } static int aqr107_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 6f52b4fb6888..38234d7e14c5 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2679,16 +2679,19 @@ static int lan8804_config_init(struct phy_device *phydev) static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev) { int irq_status, tsu_irq_status; + int ret = IRQ_NONE; irq_status = phy_read(phydev, LAN8814_INTS); - if (irq_status > 0 && (irq_status & LAN8814_INT_LINK)) - phy_trigger_machine(phydev); - if (irq_status < 0) { phy_error(phydev); return IRQ_NONE; } + if (irq_status & LAN8814_INT_LINK) { + phy_trigger_machine(phydev); + ret = IRQ_HANDLED; + } + while (1) { tsu_irq_status = lanphy_read_page_reg(phydev, 4, LAN8814_INTR_STS_REG); @@ -2697,12 +2700,15 @@ static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev) (tsu_irq_status & (LAN8814_INTR_STS_REG_1588_TSU0_ | LAN8814_INTR_STS_REG_1588_TSU1_ | LAN8814_INTR_STS_REG_1588_TSU2_ | - LAN8814_INTR_STS_REG_1588_TSU3_))) + LAN8814_INTR_STS_REG_1588_TSU3_))) { lan8814_handle_ptp_interrupt(phydev); - else + ret = IRQ_HANDLED; + } else { break; + } } - return IRQ_HANDLED; + + return ret; } static int lan8814_ack_interrupt(struct phy_device *phydev) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index aac133a1e27a..154a3c0a6dfd 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1275,10 +1275,12 @@ static int team_port_add(struct team *team, struct net_device *port_dev, } } - netif_addr_lock_bh(dev); - dev_uc_sync_multiple(port_dev, dev); - dev_mc_sync_multiple(port_dev, dev); - netif_addr_unlock_bh(dev); + if (dev->flags & IFF_UP) { + netif_addr_lock_bh(dev); + dev_uc_sync_multiple(port_dev, dev); + dev_mc_sync_multiple(port_dev, dev); + netif_addr_unlock_bh(dev); + } port->index = -1; list_add_tail_rcu(&port->list, &team->port_list); @@ -1349,8 +1351,10 @@ static int team_port_del(struct team *team, struct net_device *port_dev) netdev_rx_handler_unregister(port_dev); team_port_disable_netpoll(port); vlan_vids_del_by_dev(port_dev, dev); - dev_uc_unsync(port_dev, dev); - dev_mc_unsync(port_dev, dev); + if (dev->flags & IFF_UP) { + dev_uc_unsync(port_dev, dev); + dev_mc_unsync(port_dev, dev); + } dev_close(port_dev); team_port_leave(team, port); @@ -1700,6 +1704,14 @@ static int team_open(struct net_device *dev) static int team_close(struct net_device *dev) { + struct team *team = netdev_priv(dev); + struct team_port *port; + + list_for_each_entry(port, &team->port_list, list) { + dev_uc_unsync(port->dev, dev); + dev_mc_unsync(port->dev, dev); + } + return 0; } diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index d0f3b6d7f408..5c804bcabfe6 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -436,14 +436,13 @@ static int set_peer(struct wg_device *wg, struct nlattr **attrs) if (attrs[WGPEER_A_ENDPOINT]) { struct sockaddr *addr = nla_data(attrs[WGPEER_A_ENDPOINT]); size_t len = nla_len(attrs[WGPEER_A_ENDPOINT]); + struct endpoint endpoint = { { { 0 } } }; - if ((len == sizeof(struct sockaddr_in) && - addr->sa_family == AF_INET) || - (len == sizeof(struct sockaddr_in6) && - addr->sa_family == AF_INET6)) { - struct endpoint endpoint = { { { 0 } } }; - - memcpy(&endpoint.addr, addr, len); + if (len == sizeof(struct sockaddr_in) && addr->sa_family == AF_INET) { + endpoint.addr4 = *(struct sockaddr_in *)addr; + wg_socket_set_peer_endpoint(peer, &endpoint); + } else if (len == sizeof(struct sockaddr_in6) && addr->sa_family == AF_INET6) { + endpoint.addr6 = *(struct sockaddr_in6 *)addr; wg_socket_set_peer_endpoint(peer, &endpoint); } } diff --git a/drivers/net/wireguard/selftest/ratelimiter.c b/drivers/net/wireguard/selftest/ratelimiter.c index ba87d294604f..d4bb40a695ab 100644 --- a/drivers/net/wireguard/selftest/ratelimiter.c +++ b/drivers/net/wireguard/selftest/ratelimiter.c @@ -6,29 +6,28 @@ #ifdef DEBUG #include <linux/jiffies.h> -#include <linux/hrtimer.h> static const struct { bool result; - u64 nsec_to_sleep_before; + unsigned int msec_to_sleep_before; } expected_results[] __initconst = { [0 ... PACKETS_BURSTABLE - 1] = { true, 0 }, [PACKETS_BURSTABLE] = { false, 0 }, - [PACKETS_BURSTABLE + 1] = { true, NSEC_PER_SEC / PACKETS_PER_SECOND }, + [PACKETS_BURSTABLE + 1] = { true, MSEC_PER_SEC / PACKETS_PER_SECOND }, [PACKETS_BURSTABLE + 2] = { false, 0 }, - [PACKETS_BURSTABLE + 3] = { true, (NSEC_PER_SEC / PACKETS_PER_SECOND) * 2 }, + [PACKETS_BURSTABLE + 3] = { true, (MSEC_PER_SEC / PACKETS_PER_SECOND) * 2 }, [PACKETS_BURSTABLE + 4] = { true, 0 }, [PACKETS_BURSTABLE + 5] = { false, 0 } }; static __init unsigned int maximum_jiffies_at_index(int index) { - u64 total_nsecs = 2 * NSEC_PER_SEC / PACKETS_PER_SECOND / 3; + unsigned int total_msecs = 2 * MSEC_PER_SEC / PACKETS_PER_SECOND / 3; int i; for (i = 0; i <= index; ++i) - total_nsecs += expected_results[i].nsec_to_sleep_before; - return nsecs_to_jiffies(total_nsecs); + total_msecs += expected_results[i].msec_to_sleep_before; + return msecs_to_jiffies(total_msecs); } static __init int timings_test(struct sk_buff *skb4, struct iphdr *hdr4, @@ -43,12 +42,8 @@ static __init int timings_test(struct sk_buff *skb4, struct iphdr *hdr4, loop_start_time = jiffies; for (i = 0; i < ARRAY_SIZE(expected_results); ++i) { - if (expected_results[i].nsec_to_sleep_before) { - ktime_t timeout = ktime_add(ktime_add_ns(ktime_get_coarse_boottime(), TICK_NSEC * 4 / 3), - ns_to_ktime(expected_results[i].nsec_to_sleep_before)); - set_current_state(TASK_UNINTERRUPTIBLE); - schedule_hrtimeout_range_clock(&timeout, 0, HRTIMER_MODE_ABS, CLOCK_BOOTTIME); - } + if (expected_results[i].msec_to_sleep_before) + msleep(expected_results[i].msec_to_sleep_before); if (time_is_before_jiffies(loop_start_time + maximum_jiffies_at_index(i))) @@ -132,7 +127,7 @@ bool __init wg_ratelimiter_selftest(void) if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN)) return true; - BUILD_BUG_ON(NSEC_PER_SEC % PACKETS_PER_SECOND != 0); + BUILD_BUG_ON(MSEC_PER_SEC % PACKETS_PER_SECOND != 0); if (wg_ratelimiter_init()) goto out; @@ -172,7 +167,7 @@ bool __init wg_ratelimiter_selftest(void) ++test; #endif - for (trials = TRIALS_BEFORE_GIVING_UP;;) { + for (trials = TRIALS_BEFORE_GIVING_UP; IS_ENABLED(DEBUG_RATELIMITER_TIMINGS);) { int test_count = 0, ret; ret = timings_test(skb4, hdr4, skb6, hdr6, &test_count); diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig index a647a406b87b..b20409f8c13a 100644 --- a/drivers/net/wireless/intel/iwlwifi/Kconfig +++ b/drivers/net/wireless/intel/iwlwifi/Kconfig @@ -140,6 +140,7 @@ config IWLMEI depends on INTEL_MEI depends on PM depends on CFG80211 + depends on BROKEN help Enables the iwlmei kernel module. diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 5eb28f8ee87e..11536f115198 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1833,8 +1833,8 @@ static void iwl_mvm_parse_ppe(struct iwl_mvm *mvm, * If nss < MAX: we can set zeros in other streams */ if (nss > MAX_HE_SUPP_NSS) { - IWL_INFO(mvm, "Got NSS = %d - trimming to %d\n", nss, - MAX_HE_SUPP_NSS); + IWL_DEBUG_INFO(mvm, "Got NSS = %d - trimming to %d\n", nss, + MAX_HE_SUPP_NSS); nss = MAX_HE_SUPP_NSS; } diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 253cbc1956d1..6de13d641438 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -267,7 +267,8 @@ static void mt76_init_stream_cap(struct mt76_phy *phy, } vht_cap->vht_mcs.rx_mcs_map = cpu_to_le16(mcs_map); vht_cap->vht_mcs.tx_mcs_map = cpu_to_le16(mcs_map); - vht_cap->vht_mcs.tx_highest |= + if (ieee80211_hw_check(phy->hw, SUPPORTS_VHT_EXT_NSS_BW)) + vht_cap->vht_mcs.tx_highest |= cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index ad6c7d632eed..d6aae60c440d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -1088,7 +1088,7 @@ u32 mt7615_mac_get_sta_tid_sn(struct mt7615_dev *dev, int wcid, u8 tid) offset %= 32; val = mt76_rr(dev, addr); - val >>= (tid % 32); + val >>= offset; if (offset > 20) { addr += 4; diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index bf4f5c09d9b1..bbe5099c836d 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -1712,8 +1712,6 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, res->flags = IORESOURCE_MEM; for (i = 0; i < nd_region->ndr_mappings; i++) { - uuid_t uuid; - nsl_get_uuid(ndd, nd_label, &uuid); if (has_uuid_at_pos(nd_region, &uuid, cookie, i)) continue; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 7e88cd242380..96e6e9a5f235 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -45,7 +45,7 @@ static struct nd_region *to_region(struct pmem_device *pmem) return to_nd_region(to_dev(pmem)->parent); } -static phys_addr_t to_phys(struct pmem_device *pmem, phys_addr_t offset) +static phys_addr_t pmem_to_phys(struct pmem_device *pmem, phys_addr_t offset) { return pmem->phys_addr + offset; } @@ -63,7 +63,7 @@ static phys_addr_t to_offset(struct pmem_device *pmem, sector_t sector) static void pmem_mkpage_present(struct pmem_device *pmem, phys_addr_t offset, unsigned int len) { - phys_addr_t phys = to_phys(pmem, offset); + phys_addr_t phys = pmem_to_phys(pmem, offset); unsigned long pfn_start, pfn_end, pfn; /* only pmem in the linear map supports HWPoison */ @@ -97,7 +97,7 @@ static void pmem_clear_bb(struct pmem_device *pmem, sector_t sector, long blks) static long __pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset, unsigned int len) { - phys_addr_t phys = to_phys(pmem, offset); + phys_addr_t phys = pmem_to_phys(pmem, offset); long cleared = nvdimm_clear_poison(to_dev(pmem), phys, len); if (cleared > 0) { diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 0038283702a1..0f05b61a30fe 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1111,8 +1111,8 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return effects; } -static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, - struct nvme_command *cmd, int status) +void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, + struct nvme_command *cmd, int status) { if (effects & NVME_CMD_EFFECTS_CSE_MASK) { nvme_unfreeze(ctrl); @@ -1148,21 +1148,16 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, break; } } +EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, NVME_TARGET_PASSTHRU); -int nvme_execute_passthru_rq(struct request *rq) +int nvme_execute_passthru_rq(struct request *rq, u32 *effects) { struct nvme_command *cmd = nvme_req(rq)->cmd; struct nvme_ctrl *ctrl = nvme_req(rq)->ctrl; struct nvme_ns *ns = rq->q->queuedata; - u32 effects; - int ret; - effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode); - ret = nvme_execute_rq(rq, false); - if (effects) /* nothing to be done for zero cmd effects */ - nvme_passthru_end(ctrl, effects, cmd, ret); - - return ret; + *effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode); + return nvme_execute_rq(rq, false); } EXPORT_SYMBOL_NS_GPL(nvme_execute_passthru_rq, NVME_TARGET_PASSTHRU); @@ -2696,7 +2691,7 @@ static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ct if(!(ctrl->quirks & NVME_QUIRK_IGNORE_DEV_SUBNQN)) { nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE); if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) { - strlcpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE); + strscpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE); return; } @@ -2704,7 +2699,11 @@ static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ct dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n"); } - /* Generate a "fake" NQN per Figure 254 in NVMe 1.3 + ECN 001 */ + /* + * Generate a "fake" NQN similar to the one in Section 4.5 of the NVMe + * Base Specification 2.0. It is slightly different from the format + * specified there due to historic reasons, and we can't change it now. + */ off = snprintf(subsys->subnqn, NVMF_NQN_SIZE, "nqn.2014.08.org.nvmexpress:%04x%04x", le16_to_cpu(id->vid), le16_to_cpu(id->ssvid)); @@ -2894,7 +2893,6 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) nvme_init_subnqn(subsys, ctrl, id); memcpy(subsys->serial, id->sn, sizeof(subsys->serial)); memcpy(subsys->model, id->mn, sizeof(subsys->model)); - memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev)); subsys->vendor_id = le16_to_cpu(id->vid); subsys->cmic = id->cmic; @@ -3113,6 +3111,8 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->quirks |= core_quirks[i].quirks; } } + memcpy(ctrl->subsys->firmware_rev, id->fr, + sizeof(ctrl->subsys->firmware_rev)); if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) { dev_warn(ctrl->device, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n"); @@ -4805,6 +4805,108 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, } EXPORT_SYMBOL_GPL(nvme_complete_async_event); +int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int flags, + unsigned int cmd_size) +{ + int ret; + + memset(set, 0, sizeof(*set)); + set->ops = ops; + set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; + if (ctrl->ops->flags & NVME_F_FABRICS) + set->reserved_tags = NVMF_RESERVED_TAGS; + set->numa_node = ctrl->numa_node; + set->flags = flags; + set->cmd_size = cmd_size; + set->driver_data = ctrl; + set->nr_hw_queues = 1; + set->timeout = NVME_ADMIN_TIMEOUT; + ret = blk_mq_alloc_tag_set(set); + if (ret) + return ret; + + ctrl->admin_q = blk_mq_init_queue(set); + if (IS_ERR(ctrl->admin_q)) { + ret = PTR_ERR(ctrl->admin_q); + goto out_free_tagset; + } + + if (ctrl->ops->flags & NVME_F_FABRICS) { + ctrl->fabrics_q = blk_mq_init_queue(set); + if (IS_ERR(ctrl->fabrics_q)) { + ret = PTR_ERR(ctrl->fabrics_q); + goto out_cleanup_admin_q; + } + } + + ctrl->admin_tagset = set; + return 0; + +out_cleanup_admin_q: + blk_mq_destroy_queue(ctrl->fabrics_q); +out_free_tagset: + blk_mq_free_tag_set(ctrl->admin_tagset); + return ret; +} +EXPORT_SYMBOL_GPL(nvme_alloc_admin_tag_set); + +void nvme_remove_admin_tag_set(struct nvme_ctrl *ctrl) +{ + blk_mq_destroy_queue(ctrl->admin_q); + if (ctrl->ops->flags & NVME_F_FABRICS) + blk_mq_destroy_queue(ctrl->fabrics_q); + blk_mq_free_tag_set(ctrl->admin_tagset); +} +EXPORT_SYMBOL_GPL(nvme_remove_admin_tag_set); + +int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int flags, + unsigned int cmd_size) +{ + int ret; + + memset(set, 0, sizeof(*set)); + set->ops = ops; + set->queue_depth = ctrl->sqsize + 1; + set->reserved_tags = NVMF_RESERVED_TAGS; + set->numa_node = ctrl->numa_node; + set->flags = flags; + set->cmd_size = cmd_size, + set->driver_data = ctrl; + set->nr_hw_queues = ctrl->queue_count - 1; + set->timeout = NVME_IO_TIMEOUT; + if (ops->map_queues) + set->nr_maps = ctrl->opts->nr_poll_queues ? HCTX_MAX_TYPES : 2; + ret = blk_mq_alloc_tag_set(set); + if (ret) + return ret; + + if (ctrl->ops->flags & NVME_F_FABRICS) { + ctrl->connect_q = blk_mq_init_queue(set); + if (IS_ERR(ctrl->connect_q)) { + ret = PTR_ERR(ctrl->connect_q); + goto out_free_tag_set; + } + } + + ctrl->tagset = set; + return 0; + +out_free_tag_set: + blk_mq_free_tag_set(set); + return ret; +} +EXPORT_SYMBOL_GPL(nvme_alloc_io_tag_set); + +void nvme_remove_io_tag_set(struct nvme_ctrl *ctrl) +{ + if (ctrl->ops->flags & NVME_F_FABRICS) + blk_mq_destroy_queue(ctrl->connect_q); + blk_mq_free_tag_set(ctrl->tagset); +} +EXPORT_SYMBOL_GPL(nvme_remove_io_tag_set); + void nvme_stop_ctrl(struct nvme_ctrl *ctrl) { nvme_mpath_stop(ctrl); @@ -4824,6 +4926,16 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) nvme_enable_aen(ctrl); + /* + * persistent discovery controllers need to send indication to userspace + * to re-read the discovery log page to learn about possible changes + * that were missed. We identify persistent discovery controllers by + * checking that they started once before, hence are reconnecting back. + */ + if (test_and_set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && + nvme_discovery_ctrl(ctrl)) + nvme_change_uevent(ctrl, "NVME_EVENT=rediscover"); + if (ctrl->queue_count > 1) { nvme_queue_scan(ctrl); nvme_start_queues(ctrl); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 10cc4a814602..ce27276f552d 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -49,7 +49,7 @@ static struct nvmf_host *nvmf_host_add(const char *hostnqn) goto out_unlock; kref_init(&host->ref); - strlcpy(host->nqn, hostnqn, NVMF_NQN_SIZE); + strscpy(host->nqn, hostnqn, NVMF_NQN_SIZE); list_add_tail(&host->list, &nvmf_hosts); out_unlock: @@ -971,13 +971,17 @@ bool nvmf_ip_options_match(struct nvme_ctrl *ctrl, return false; /* - * Checking the local address is rough. In most cases, none is specified - * and the host port is selected by the stack. + * Checking the local address or host interfaces is rough. + * + * In most cases, none is specified and the host port or + * host interface is selected by the stack. * * Assume no match if: - * - local address is specified and address is not the same - * - local address is not specified but remote is, or vice versa - * (admin using specific host_traddr when it matters). + * - local address or host interface is specified and address + * or host interface is not the same + * - local address or host interface is not specified but + * remote is, or vice versa (admin using specific + * host_traddr/host_iface when it matters). */ if ((opts->mask & NVMF_OPT_HOST_TRADDR) && (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR)) { @@ -988,6 +992,15 @@ bool nvmf_ip_options_match(struct nvme_ctrl *ctrl, return false; } + if ((opts->mask & NVMF_OPT_HOST_IFACE) && + (ctrl->opts->mask & NVMF_OPT_HOST_IFACE)) { + if (strcmp(opts->host_iface, ctrl->opts->host_iface)) + return false; + } else if ((opts->mask & NVMF_OPT_HOST_IFACE) || + (ctrl->opts->mask & NVMF_OPT_HOST_IFACE)) { + return false; + } + return true; } EXPORT_SYMBOL_GPL(nvmf_ip_options_match); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 127abaf9ba5d..5d57a042dbca 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1829,7 +1829,7 @@ nvme_fc_exit_request(struct blk_mq_tag_set *set, struct request *rq, { struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq); - return __nvme_fc_exit_request(set->driver_data, op); + return __nvme_fc_exit_request(to_fc_ctrl(set->driver_data), op); } static int @@ -2135,7 +2135,7 @@ static int nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, unsigned int numa_node) { - struct nvme_fc_ctrl *ctrl = set->driver_data; + struct nvme_fc_ctrl *ctrl = to_fc_ctrl(set->driver_data); struct nvme_fcp_op_w_sgl *op = blk_mq_rq_to_pdu(rq); int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0; struct nvme_fc_queue *queue = &ctrl->queues[queue_idx]; @@ -2206,36 +2206,28 @@ nvme_fc_term_aen_ops(struct nvme_fc_ctrl *ctrl) } } -static inline void -__nvme_fc_init_hctx(struct blk_mq_hw_ctx *hctx, struct nvme_fc_ctrl *ctrl, - unsigned int qidx) +static inline int +__nvme_fc_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int qidx) { + struct nvme_fc_ctrl *ctrl = to_fc_ctrl(data); struct nvme_fc_queue *queue = &ctrl->queues[qidx]; hctx->driver_data = queue; queue->hctx = hctx; + return 0; } static int -nvme_fc_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, - unsigned int hctx_idx) +nvme_fc_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { - struct nvme_fc_ctrl *ctrl = data; - - __nvme_fc_init_hctx(hctx, ctrl, hctx_idx + 1); - - return 0; + return __nvme_fc_init_hctx(hctx, data, hctx_idx + 1); } static int nvme_fc_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { - struct nvme_fc_ctrl *ctrl = data; - - __nvme_fc_init_hctx(hctx, ctrl, hctx_idx); - - return 0; + return __nvme_fc_init_hctx(hctx, data, hctx_idx); } static void @@ -2391,10 +2383,8 @@ nvme_fc_ctrl_free(struct kref *ref) container_of(ref, struct nvme_fc_ctrl, ref); unsigned long flags; - if (ctrl->ctrl.tagset) { - blk_mq_destroy_queue(ctrl->ctrl.connect_q); - blk_mq_free_tag_set(&ctrl->tag_set); - } + if (ctrl->ctrl.tagset) + nvme_remove_io_tag_set(&ctrl->ctrl); /* remove from rport list */ spin_lock_irqsave(&ctrl->rport->lock, flags); @@ -2402,9 +2392,7 @@ nvme_fc_ctrl_free(struct kref *ref) spin_unlock_irqrestore(&ctrl->rport->lock, flags); nvme_start_admin_queue(&ctrl->ctrl); - blk_mq_destroy_queue(ctrl->ctrl.admin_q); - blk_mq_destroy_queue(ctrl->ctrl.fabrics_q); - blk_mq_free_tag_set(&ctrl->admin_tag_set); + nvme_remove_admin_tag_set(&ctrl->ctrl); kfree(ctrl->queues); @@ -2860,9 +2848,9 @@ nvme_fc_complete_rq(struct request *rq) nvme_fc_ctrl_put(ctrl); } -static int nvme_fc_map_queues(struct blk_mq_tag_set *set) +static void nvme_fc_map_queues(struct blk_mq_tag_set *set) { - struct nvme_fc_ctrl *ctrl = set->driver_data; + struct nvme_fc_ctrl *ctrl = to_fc_ctrl(set->driver_data); int i; for (i = 0; i < set->nr_maps; i++) { @@ -2880,7 +2868,6 @@ static int nvme_fc_map_queues(struct blk_mq_tag_set *set) else blk_mq_map_queues(map); } - return 0; } static const struct blk_mq_ops nvme_fc_mq_ops = { @@ -2915,32 +2902,16 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl) nvme_fc_init_io_queues(ctrl); - memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set)); - ctrl->tag_set.ops = &nvme_fc_mq_ops; - ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; - ctrl->tag_set.reserved_tags = NVMF_RESERVED_TAGS; - ctrl->tag_set.numa_node = ctrl->ctrl.numa_node; - ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; - ctrl->tag_set.cmd_size = - struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv, - ctrl->lport->ops->fcprqst_priv_sz); - ctrl->tag_set.driver_data = ctrl; - ctrl->tag_set.nr_hw_queues = ctrl->ctrl.queue_count - 1; - ctrl->tag_set.timeout = NVME_IO_TIMEOUT; - - ret = blk_mq_alloc_tag_set(&ctrl->tag_set); + ret = nvme_alloc_io_tag_set(&ctrl->ctrl, &ctrl->tag_set, + &nvme_fc_mq_ops, BLK_MQ_F_SHOULD_MERGE, + struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv, + ctrl->lport->ops->fcprqst_priv_sz)); if (ret) return ret; - ctrl->ctrl.tagset = &ctrl->tag_set; - - ret = nvme_ctrl_init_connect_q(&(ctrl->ctrl)); - if (ret) - goto out_free_tag_set; - ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) - goto out_cleanup_blk_queue; + goto out_cleanup_tagset; ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.sqsize + 1); if (ret) @@ -2952,10 +2923,8 @@ nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl) out_delete_hw_queues: nvme_fc_delete_hw_io_queues(ctrl); -out_cleanup_blk_queue: - blk_mq_destroy_queue(ctrl->ctrl.connect_q); -out_free_tag_set: - blk_mq_free_tag_set(&ctrl->tag_set); +out_cleanup_tagset: + nvme_remove_io_tag_set(&ctrl->ctrl); nvme_fc_free_io_queues(ctrl); /* force put free routine to ignore io queues */ @@ -3166,15 +3135,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) "to maxcmd\n", opts->queue_size, ctrl->ctrl.maxcmd); opts->queue_size = ctrl->ctrl.maxcmd; - } - - if (opts->queue_size > ctrl->ctrl.sqsize + 1) { - /* warn if sqsize is lower than queue_size */ - dev_warn(ctrl->ctrl.device, - "queue_size %zu > ctrl sqsize %u, reducing " - "to sqsize\n", - opts->queue_size, ctrl->ctrl.sqsize + 1); - opts->queue_size = ctrl->ctrl.sqsize + 1; + ctrl->ctrl.sqsize = opts->queue_size - 1; } ret = nvme_fc_init_aen_ops(ctrl); @@ -3547,35 +3508,12 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, nvme_fc_init_queue(ctrl, 0); - memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set)); - ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops; - ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH; - ctrl->admin_tag_set.reserved_tags = NVMF_RESERVED_TAGS; - ctrl->admin_tag_set.numa_node = ctrl->ctrl.numa_node; - ctrl->admin_tag_set.cmd_size = - struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv, - ctrl->lport->ops->fcprqst_priv_sz); - ctrl->admin_tag_set.driver_data = ctrl; - ctrl->admin_tag_set.nr_hw_queues = 1; - ctrl->admin_tag_set.timeout = NVME_ADMIN_TIMEOUT; - ctrl->admin_tag_set.flags = BLK_MQ_F_NO_SCHED; - - ret = blk_mq_alloc_tag_set(&ctrl->admin_tag_set); + ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set, + &nvme_fc_admin_mq_ops, BLK_MQ_F_NO_SCHED, + struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv, + ctrl->lport->ops->fcprqst_priv_sz)); if (ret) goto out_free_queues; - ctrl->ctrl.admin_tagset = &ctrl->admin_tag_set; - - ctrl->ctrl.fabrics_q = blk_mq_init_queue(&ctrl->admin_tag_set); - if (IS_ERR(ctrl->ctrl.fabrics_q)) { - ret = PTR_ERR(ctrl->ctrl.fabrics_q); - goto out_free_admin_tag_set; - } - - ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set); - if (IS_ERR(ctrl->ctrl.admin_q)) { - ret = PTR_ERR(ctrl->ctrl.admin_q); - goto out_cleanup_fabrics_q; - } /* * Would have been nice to init io queues tag set as well. @@ -3586,7 +3524,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0); if (ret) - goto out_cleanup_admin_q; + goto out_cleanup_tagset; /* at this point, teardown path changes to ref counting on nvme ctrl */ @@ -3641,12 +3579,8 @@ fail_ctrl: return ERR_PTR(-EIO); -out_cleanup_admin_q: - blk_mq_destroy_queue(ctrl->ctrl.admin_q); -out_cleanup_fabrics_q: - blk_mq_destroy_queue(ctrl->ctrl.fabrics_q); -out_free_admin_tag_set: - blk_mq_free_tag_set(&ctrl->admin_tag_set); +out_cleanup_tagset: + nvme_remove_admin_tag_set(&ctrl->ctrl); out_free_queues: kfree(ctrl->queues); out_free_ida: diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 548aca8b5b9f..357791ff0623 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -136,9 +136,11 @@ static int nvme_submit_user_cmd(struct request_queue *q, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, u32 meta_seed, u64 *result, unsigned timeout, bool vec) { + struct nvme_ctrl *ctrl; struct request *req; void *meta = NULL; struct bio *bio; + u32 effects; int ret; req = nvme_alloc_user_request(q, cmd, ubuffer, bufflen, meta_buffer, @@ -147,8 +149,9 @@ static int nvme_submit_user_cmd(struct request_queue *q, return PTR_ERR(req); bio = req->bio; + ctrl = nvme_req(req)->ctrl; - ret = nvme_execute_passthru_rq(req); + ret = nvme_execute_passthru_rq(req, &effects); if (result) *result = le64_to_cpu(nvme_req(req)->result.u64); @@ -158,6 +161,10 @@ static int nvme_submit_user_cmd(struct request_queue *q, if (bio) blk_rq_unmap_user(bio); blk_mq_free_request(req); + + if (effects) + nvme_passthru_end(ctrl, effects, cmd, ret); + return ret; } @@ -824,11 +831,17 @@ long nvme_dev_ioctl(struct file *file, unsigned int cmd, case NVME_IOCTL_IO_CMD: return nvme_dev_user_cmd(ctrl, argp); case NVME_IOCTL_RESET: + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; dev_warn(ctrl->device, "resetting controller\n"); return nvme_reset_ctrl_sync(ctrl); case NVME_IOCTL_SUBSYS_RESET: + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; return nvme_reset_subsystem(ctrl); case NVME_IOCTL_RESCAN: + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; nvme_queue_scan(ctrl); return 0; default: diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 216acbe953b3..a29877217ee6 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -233,6 +233,12 @@ struct nvme_fault_inject { #endif }; +enum nvme_ctrl_flags { + NVME_CTRL_FAILFAST_EXPIRED = 0, + NVME_CTRL_ADMIN_Q_STOPPED = 1, + NVME_CTRL_STARTED_ONCE = 2, +}; + struct nvme_ctrl { bool comp_seen; enum nvme_ctrl_state state; @@ -354,8 +360,6 @@ struct nvme_ctrl { u16 maxcmd; int nr_reconnects; unsigned long flags; -#define NVME_CTRL_FAILFAST_EXPIRED 0 -#define NVME_CTRL_ADMIN_Q_STOPPED 1 struct nvmf_ctrl_options *opts; struct page *discard_page; @@ -602,11 +606,23 @@ static inline void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inj) static inline void nvme_should_fail(struct request *req) {} #endif +bool nvme_wait_reset(struct nvme_ctrl *ctrl); +int nvme_try_sched_reset(struct nvme_ctrl *ctrl); + static inline int nvme_reset_subsystem(struct nvme_ctrl *ctrl) { + int ret; + if (!ctrl->subsystem) return -ENOTTY; - return ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65); + if (!nvme_wait_reset(ctrl)) + return -EBUSY; + + ret = ctrl->ops->reg_write32(ctrl, NVME_REG_NSSR, 0x4E564D65); + if (ret) + return ret; + + return nvme_try_sched_reset(ctrl); } /* @@ -712,7 +728,6 @@ void nvme_cancel_tagset(struct nvme_ctrl *ctrl); void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state); -bool nvme_wait_reset(struct nvme_ctrl *ctrl); int nvme_disable_ctrl(struct nvme_ctrl *ctrl); int nvme_enable_ctrl(struct nvme_ctrl *ctrl); int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl); @@ -722,6 +737,14 @@ void nvme_uninit_ctrl(struct nvme_ctrl *ctrl); void nvme_start_ctrl(struct nvme_ctrl *ctrl); void nvme_stop_ctrl(struct nvme_ctrl *ctrl); int nvme_init_ctrl_finish(struct nvme_ctrl *ctrl); +int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int flags, + unsigned int cmd_size); +void nvme_remove_admin_tag_set(struct nvme_ctrl *ctrl); +int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int flags, + unsigned int cmd_size); +void nvme_remove_io_tag_set(struct nvme_ctrl *ctrl); void nvme_remove_namespaces(struct nvme_ctrl *ctrl); @@ -802,7 +825,6 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count); void nvme_stop_keep_alive(struct nvme_ctrl *ctrl); int nvme_reset_ctrl(struct nvme_ctrl *ctrl); int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl); -int nvme_try_sched_reset(struct nvme_ctrl *ctrl); int nvme_delete_ctrl(struct nvme_ctrl *ctrl); void nvme_queue_scan(struct nvme_ctrl *ctrl); int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, @@ -972,14 +994,6 @@ static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf) } #endif -static inline int nvme_ctrl_init_connect_q(struct nvme_ctrl *ctrl) -{ - ctrl->connect_q = blk_mq_init_queue(ctrl->tagset); - if (IS_ERR(ctrl->connect_q)) - return PTR_ERR(ctrl->connect_q); - return 0; -} - static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) { return dev_to_disk(dev)->private_data; @@ -1027,7 +1041,9 @@ static inline void nvme_auth_free(struct nvme_ctrl *ctrl) {}; u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); -int nvme_execute_passthru_rq(struct request *rq); +int nvme_execute_passthru_rq(struct request *rq, u32 *effects); +void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, + struct nvme_command *cmd, int status); struct nvme_ctrl *nvme_ctrl_from_file(struct file *file); struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid); void nvme_put_ns(struct nvme_ns *ns); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 98864b853eef..f9af99b7e672 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -226,12 +226,12 @@ struct nvme_queue { struct nvme_iod { struct nvme_request req; struct nvme_command cmd; - struct nvme_queue *nvmeq; bool use_sgl; - int aborted; - int npages; /* In the PRP list. 0 means small pool in use */ - dma_addr_t first_dma; + bool aborted; + s8 nr_allocations; /* PRP list pool allocations. 0 means small + pool in use */ unsigned int dma_len; /* length of single DMA segment mapping */ + dma_addr_t first_dma; dma_addr_t meta_dma; struct sg_table sgt; }; @@ -430,11 +430,6 @@ static int nvme_pci_init_request(struct blk_mq_tag_set *set, { struct nvme_dev *dev = set->driver_data; struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - int queue_idx = (set == &dev->tagset) ? hctx_idx + 1 : 0; - struct nvme_queue *nvmeq = &dev->queues[queue_idx]; - - BUG_ON(!nvmeq); - iod->nvmeq = nvmeq; nvme_req(req)->ctrl = &dev->ctrl; nvme_req(req)->cmd = &iod->cmd; @@ -450,7 +445,7 @@ static int queue_irq_offset(struct nvme_dev *dev) return 0; } -static int nvme_pci_map_queues(struct blk_mq_tag_set *set) +static void nvme_pci_map_queues(struct blk_mq_tag_set *set) { struct nvme_dev *dev = set->driver_data; int i, qoff, offset; @@ -477,8 +472,6 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set) qoff += map->nr_queues; offset += map->nr_queues; } - - return 0; } /* @@ -528,7 +521,7 @@ static void **nvme_pci_iod_list(struct request *req) static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req) { - struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + struct nvme_queue *nvmeq = req->mq_hctx->driver_data; int nseg = blk_rq_nr_phys_segments(req); unsigned int avg_seg_size; @@ -536,7 +529,7 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req) if (!nvme_ctrl_sgl_supported(&dev->ctrl)) return false; - if (!iod->nvmeq->qid) + if (!nvmeq->qid) return false; if (!sgl_threshold || avg_seg_size < sgl_threshold) return false; @@ -550,7 +543,7 @@ static void nvme_free_prps(struct nvme_dev *dev, struct request *req) dma_addr_t dma_addr = iod->first_dma; int i; - for (i = 0; i < iod->npages; i++) { + for (i = 0; i < iod->nr_allocations; i++) { __le64 *prp_list = nvme_pci_iod_list(req)[i]; dma_addr_t next_dma_addr = le64_to_cpu(prp_list[last_prp]); @@ -566,7 +559,7 @@ static void nvme_free_sgls(struct nvme_dev *dev, struct request *req) dma_addr_t dma_addr = iod->first_dma; int i; - for (i = 0; i < iod->npages; i++) { + for (i = 0; i < iod->nr_allocations; i++) { struct nvme_sgl_desc *sg_list = nvme_pci_iod_list(req)[i]; dma_addr_t next_dma_addr = le64_to_cpu((sg_list[last_sg]).addr); @@ -589,7 +582,7 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0); - if (iod->npages == 0) + if (iod->nr_allocations == 0) dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0], iod->first_dma); else if (iod->use_sgl) @@ -651,15 +644,15 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, nprps = DIV_ROUND_UP(length, NVME_CTRL_PAGE_SIZE); if (nprps <= (256 / 8)) { pool = dev->prp_small_pool; - iod->npages = 0; + iod->nr_allocations = 0; } else { pool = dev->prp_page_pool; - iod->npages = 1; + iod->nr_allocations = 1; } prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); if (!prp_list) { - iod->npages = -1; + iod->nr_allocations = -1; return BLK_STS_RESOURCE; } list[0] = prp_list; @@ -671,7 +664,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev *dev, prp_list = dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); if (!prp_list) goto free_prps; - list[iod->npages++] = prp_list; + list[iod->nr_allocations++] = prp_list; prp_list[0] = old_prp_list[i - 1]; old_prp_list[i - 1] = cpu_to_le64(prp_dma); i = 1; @@ -746,15 +739,15 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, if (entries <= (256 / sizeof(struct nvme_sgl_desc))) { pool = dev->prp_small_pool; - iod->npages = 0; + iod->nr_allocations = 0; } else { pool = dev->prp_page_pool; - iod->npages = 1; + iod->nr_allocations = 1; } sg_list = dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); if (!sg_list) { - iod->npages = -1; + iod->nr_allocations = -1; return BLK_STS_RESOURCE; } @@ -773,7 +766,7 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, goto free_sgls; i = 0; - nvme_pci_iod_list(req)[iod->npages++] = sg_list; + nvme_pci_iod_list(req)[iod->nr_allocations++] = sg_list; sg_list[i++] = *link; nvme_pci_sgl_set_seg(link, sgl_dma, entries); } @@ -833,6 +826,7 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, int rc; if (blk_rq_nr_phys_segments(req) == 1) { + struct nvme_queue *nvmeq = req->mq_hctx->driver_data; struct bio_vec bv = req_bvec(req); if (!is_pci_p2pdma_page(bv.bv_page)) { @@ -840,7 +834,7 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, return nvme_setup_prp_simple(dev, req, &cmnd->rw, &bv); - if (iod->nvmeq->qid && sgl_threshold && + if (nvmeq->qid && sgl_threshold && nvme_ctrl_sgl_supported(&dev->ctrl)) return nvme_setup_sgl_simple(dev, req, &cmnd->rw, &bv); @@ -898,8 +892,8 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req) struct nvme_iod *iod = blk_mq_rq_to_pdu(req); blk_status_t ret; - iod->aborted = 0; - iod->npages = -1; + iod->aborted = false; + iod->nr_allocations = -1; iod->sgt.nents = 0; ret = nvme_setup_cmd(req->q->queuedata, req); @@ -1019,12 +1013,16 @@ static void nvme_queue_rqs(struct request **rqlist) static __always_inline void nvme_pci_unmap_rq(struct request *req) { - struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - struct nvme_dev *dev = iod->nvmeq->dev; + struct nvme_queue *nvmeq = req->mq_hctx->driver_data; + struct nvme_dev *dev = nvmeq->dev; + + if (blk_integrity_rq(req)) { + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - if (blk_integrity_rq(req)) dma_unmap_page(dev->dev, iod->meta_dma, rq_integrity_vec(req)->bv_len, rq_data_dir(req)); + } + if (blk_rq_nr_phys_segments(req)) nvme_unmap_data(dev, req); } @@ -1272,8 +1270,7 @@ static int adapter_delete_sq(struct nvme_dev *dev, u16 sqid) static void abort_endio(struct request *req, blk_status_t error) { - struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - struct nvme_queue *nvmeq = iod->nvmeq; + struct nvme_queue *nvmeq = req->mq_hctx->driver_data; dev_warn(nvmeq->dev->ctrl.device, "Abort status: 0x%x", nvme_req(req)->status); @@ -1335,7 +1332,7 @@ static void nvme_warn_reset(struct nvme_dev *dev, u32 csts) static enum blk_eh_timer_return nvme_timeout(struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - struct nvme_queue *nvmeq = iod->nvmeq; + struct nvme_queue *nvmeq = req->mq_hctx->driver_data; struct nvme_dev *dev = nvmeq->dev; struct request *abort_req; struct nvme_command cmd = { }; @@ -1416,7 +1413,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) atomic_inc(&dev->ctrl.abort_limit); return BLK_EH_RESET_TIMER; } - iod->aborted = 1; + iod->aborted = true; cmd.abort.opcode = nvme_admin_abort_cmd; cmd.abort.cid = nvme_cid(req); @@ -2529,9 +2526,11 @@ static void nvme_pci_alloc_tag_set(struct nvme_dev *dev) set->ops = &nvme_mq_ops; set->nr_hw_queues = dev->online_queues - 1; - set->nr_maps = 2; /* default + read */ + set->nr_maps = 1; + if (dev->io_queues[HCTX_TYPE_READ]) + set->nr_maps = 2; if (dev->io_queues[HCTX_TYPE_POLL]) - set->nr_maps++; + set->nr_maps = 3; set->timeout = NVME_IO_TIMEOUT; set->numa_node = dev->ctrl.numa_node; set->queue_depth = min_t(unsigned, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1; @@ -2834,6 +2833,8 @@ static void nvme_reset_work(struct work_struct *work) nvme_start_admin_queue(&dev->ctrl); } + dma_set_min_align_mask(dev->dev, NVME_CTRL_PAGE_SIZE - 1); + /* * Limit the max command size to prevent iod->sg allocations going * over a single page. @@ -2846,7 +2847,6 @@ static void nvme_reset_work(struct work_struct *work) * Don't limit the IOMMU merged segment size. */ dma_set_max_seg_size(dev->dev, 0xffffffff); - dma_set_min_align_mask(dev->dev, NVME_CTRL_PAGE_SIZE - 1); mutex_unlock(&dev->shutdown_lock); @@ -3565,6 +3565,8 @@ static int __init nvme_init(void) BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64); BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64); BUILD_BUG_ON(IRQ_AFFINITY_MAX_SETS < 2); + BUILD_BUG_ON(DIV_ROUND_UP(nvme_pci_npages_prp(), NVME_CTRL_PAGE_SIZE) > + S8_MAX); return pci_register_driver(&nvme_driver); } diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 3100643be299..5ad0ab2853a4 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -295,7 +295,7 @@ static int nvme_rdma_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, unsigned int numa_node) { - struct nvme_rdma_ctrl *ctrl = set->driver_data; + struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(set->driver_data); struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0; struct nvme_rdma_queue *queue = &ctrl->queues[queue_idx]; @@ -320,7 +320,7 @@ static int nvme_rdma_init_request(struct blk_mq_tag_set *set, static int nvme_rdma_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { - struct nvme_rdma_ctrl *ctrl = data; + struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(data); struct nvme_rdma_queue *queue = &ctrl->queues[hctx_idx + 1]; BUG_ON(hctx_idx >= ctrl->ctrl.queue_count); @@ -332,7 +332,7 @@ static int nvme_rdma_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, static int nvme_rdma_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { - struct nvme_rdma_ctrl *ctrl = data; + struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(data); struct nvme_rdma_queue *queue = &ctrl->queues[0]; BUG_ON(hctx_idx != 0); @@ -696,11 +696,12 @@ static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx) return ret; } -static int nvme_rdma_start_io_queues(struct nvme_rdma_ctrl *ctrl) +static int nvme_rdma_start_io_queues(struct nvme_rdma_ctrl *ctrl, + int first, int last) { int i, ret = 0; - for (i = 1; i < ctrl->ctrl.queue_count; i++) { + for (i = first; i < last; i++) { ret = nvme_rdma_start_queue(ctrl, i); if (ret) goto out_stop_queues; @@ -709,7 +710,7 @@ static int nvme_rdma_start_io_queues(struct nvme_rdma_ctrl *ctrl) return 0; out_stop_queues: - for (i--; i >= 1; i--) + for (i--; i >= first; i--) nvme_rdma_stop_queue(&ctrl->queues[i]); return ret; } @@ -787,64 +788,21 @@ out_free_queues: return ret; } -static int nvme_rdma_alloc_admin_tag_set(struct nvme_ctrl *nctrl) +static int nvme_rdma_alloc_tag_set(struct nvme_ctrl *ctrl) { - struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); - struct blk_mq_tag_set *set = &ctrl->admin_tag_set; - int ret; + unsigned int cmd_size = sizeof(struct nvme_rdma_request) + + NVME_RDMA_DATA_SGL_SIZE; - memset(set, 0, sizeof(*set)); - set->ops = &nvme_rdma_admin_mq_ops; - set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; - set->reserved_tags = NVMF_RESERVED_TAGS; - set->numa_node = nctrl->numa_node; - set->cmd_size = sizeof(struct nvme_rdma_request) + - NVME_RDMA_DATA_SGL_SIZE; - set->driver_data = ctrl; - set->nr_hw_queues = 1; - set->timeout = NVME_ADMIN_TIMEOUT; - set->flags = BLK_MQ_F_NO_SCHED; - ret = blk_mq_alloc_tag_set(set); - if (!ret) - ctrl->ctrl.admin_tagset = set; - return ret; -} - -static int nvme_rdma_alloc_tag_set(struct nvme_ctrl *nctrl) -{ - struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); - struct blk_mq_tag_set *set = &ctrl->tag_set; - int ret; + if (ctrl->max_integrity_segments) + cmd_size += sizeof(struct nvme_rdma_sgl) + + NVME_RDMA_METADATA_SGL_SIZE; - memset(set, 0, sizeof(*set)); - set->ops = &nvme_rdma_mq_ops; - set->queue_depth = nctrl->sqsize + 1; - set->reserved_tags = NVMF_RESERVED_TAGS; - set->numa_node = nctrl->numa_node; - set->flags = BLK_MQ_F_SHOULD_MERGE; - set->cmd_size = sizeof(struct nvme_rdma_request) + - NVME_RDMA_DATA_SGL_SIZE; - if (nctrl->max_integrity_segments) - set->cmd_size += sizeof(struct nvme_rdma_sgl) + - NVME_RDMA_METADATA_SGL_SIZE; - set->driver_data = ctrl; - set->nr_hw_queues = nctrl->queue_count - 1; - set->timeout = NVME_IO_TIMEOUT; - set->nr_maps = nctrl->opts->nr_poll_queues ? HCTX_MAX_TYPES : 2; - ret = blk_mq_alloc_tag_set(set); - if (!ret) - ctrl->ctrl.tagset = set; - return ret; + return nvme_alloc_io_tag_set(ctrl, &to_rdma_ctrl(ctrl)->tag_set, + &nvme_rdma_mq_ops, BLK_MQ_F_SHOULD_MERGE, cmd_size); } -static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl, - bool remove) +static void nvme_rdma_destroy_admin_queue(struct nvme_rdma_ctrl *ctrl) { - if (remove) { - blk_mq_destroy_queue(ctrl->ctrl.admin_q); - blk_mq_destroy_queue(ctrl->ctrl.fabrics_q); - blk_mq_free_tag_set(ctrl->ctrl.admin_tagset); - } if (ctrl->async_event_sqe.data) { cancel_work_sync(&ctrl->ctrl.async_event_work); nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe, @@ -886,26 +844,19 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, goto out_free_queue; if (new) { - error = nvme_rdma_alloc_admin_tag_set(&ctrl->ctrl); + error = nvme_alloc_admin_tag_set(&ctrl->ctrl, + &ctrl->admin_tag_set, &nvme_rdma_admin_mq_ops, + BLK_MQ_F_NO_SCHED, + sizeof(struct nvme_rdma_request) + + NVME_RDMA_DATA_SGL_SIZE); if (error) goto out_free_async_qe; - ctrl->ctrl.fabrics_q = blk_mq_init_queue(&ctrl->admin_tag_set); - if (IS_ERR(ctrl->ctrl.fabrics_q)) { - error = PTR_ERR(ctrl->ctrl.fabrics_q); - goto out_free_tagset; - } - - ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set); - if (IS_ERR(ctrl->ctrl.admin_q)) { - error = PTR_ERR(ctrl->ctrl.admin_q); - goto out_cleanup_fabrics_q; - } } error = nvme_rdma_start_queue(ctrl, 0); if (error) - goto out_cleanup_queue; + goto out_remove_admin_tag_set; error = nvme_enable_ctrl(&ctrl->ctrl); if (error) @@ -932,15 +883,9 @@ out_quiesce_queue: out_stop_queue: nvme_rdma_stop_queue(&ctrl->queues[0]); nvme_cancel_admin_tagset(&ctrl->ctrl); -out_cleanup_queue: - if (new) - blk_mq_destroy_queue(ctrl->ctrl.admin_q); -out_cleanup_fabrics_q: +out_remove_admin_tag_set: if (new) - blk_mq_destroy_queue(ctrl->ctrl.fabrics_q); -out_free_tagset: - if (new) - blk_mq_free_tag_set(ctrl->ctrl.admin_tagset); + nvme_remove_admin_tag_set(&ctrl->ctrl); out_free_async_qe: if (ctrl->async_event_sqe.data) { nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe, @@ -952,19 +897,9 @@ out_free_queue: return error; } -static void nvme_rdma_destroy_io_queues(struct nvme_rdma_ctrl *ctrl, - bool remove) -{ - if (remove) { - blk_mq_destroy_queue(ctrl->ctrl.connect_q); - blk_mq_free_tag_set(ctrl->ctrl.tagset); - } - nvme_rdma_free_io_queues(ctrl); -} - static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) { - int ret; + int ret, nr_queues; ret = nvme_rdma_alloc_io_queues(ctrl); if (ret) @@ -974,15 +909,17 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) ret = nvme_rdma_alloc_tag_set(&ctrl->ctrl); if (ret) goto out_free_io_queues; - - ret = nvme_ctrl_init_connect_q(&(ctrl->ctrl)); - if (ret) - goto out_free_tag_set; } - ret = nvme_rdma_start_io_queues(ctrl); + /* + * Only start IO queues for which we have allocated the tagset + * and limitted it to the available queues. On reconnects, the + * queue number might have changed. + */ + nr_queues = min(ctrl->tag_set.nr_hw_queues + 1, ctrl->ctrl.queue_count); + ret = nvme_rdma_start_io_queues(ctrl, 1, nr_queues); if (ret) - goto out_cleanup_connect_q; + goto out_cleanup_tagset; if (!new) { nvme_start_queues(&ctrl->ctrl); @@ -1000,19 +937,25 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) nvme_unfreeze(&ctrl->ctrl); } + /* + * If the number of queues has increased (reconnect case) + * start all new queues now. + */ + ret = nvme_rdma_start_io_queues(ctrl, nr_queues, + ctrl->tag_set.nr_hw_queues + 1); + if (ret) + goto out_wait_freeze_timed_out; + return 0; out_wait_freeze_timed_out: nvme_stop_queues(&ctrl->ctrl); nvme_sync_io_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); -out_cleanup_connect_q: +out_cleanup_tagset: nvme_cancel_tagset(&ctrl->ctrl); if (new) - blk_mq_destroy_queue(ctrl->ctrl.connect_q); -out_free_tag_set: - if (new) - blk_mq_free_tag_set(ctrl->ctrl.tagset); + nvme_remove_io_tag_set(&ctrl->ctrl); out_free_io_queues: nvme_rdma_free_io_queues(ctrl); return ret; @@ -1025,9 +968,11 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl, blk_sync_queue(ctrl->ctrl.admin_q); nvme_rdma_stop_queue(&ctrl->queues[0]); nvme_cancel_admin_tagset(&ctrl->ctrl); - if (remove) + if (remove) { nvme_start_admin_queue(&ctrl->ctrl); - nvme_rdma_destroy_admin_queue(ctrl, remove); + nvme_remove_admin_tag_set(&ctrl->ctrl); + } + nvme_rdma_destroy_admin_queue(ctrl); } static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, @@ -1039,9 +984,11 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, nvme_sync_io_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); nvme_cancel_tagset(&ctrl->ctrl); - if (remove) + if (remove) { nvme_start_queues(&ctrl->ctrl); - nvme_rdma_destroy_io_queues(ctrl, remove); + nvme_remove_io_tag_set(&ctrl->ctrl); + } + nvme_rdma_free_io_queues(ctrl); } } @@ -1163,14 +1110,18 @@ destroy_io: nvme_sync_io_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); nvme_cancel_tagset(&ctrl->ctrl); - nvme_rdma_destroy_io_queues(ctrl, new); + if (new) + nvme_remove_io_tag_set(&ctrl->ctrl); + nvme_rdma_free_io_queues(ctrl); } destroy_admin: nvme_stop_admin_queue(&ctrl->ctrl); blk_sync_queue(ctrl->ctrl.admin_q); nvme_rdma_stop_queue(&ctrl->queues[0]); nvme_cancel_admin_tagset(&ctrl->ctrl); - nvme_rdma_destroy_admin_queue(ctrl, new); + if (new) + nvme_remove_admin_tag_set(&ctrl->ctrl); + nvme_rdma_destroy_admin_queue(ctrl); return ret; } @@ -2188,9 +2139,9 @@ static void nvme_rdma_complete_rq(struct request *rq) nvme_complete_rq(rq); } -static int nvme_rdma_map_queues(struct blk_mq_tag_set *set) +static void nvme_rdma_map_queues(struct blk_mq_tag_set *set) { - struct nvme_rdma_ctrl *ctrl = set->driver_data; + struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(set->driver_data); struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) { @@ -2231,8 +2182,6 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set) ctrl->io_queues[HCTX_TYPE_DEFAULT], ctrl->io_queues[HCTX_TYPE_READ], ctrl->io_queues[HCTX_TYPE_POLL]); - - return 0; } static const struct blk_mq_ops nvme_rdma_mq_ops = { diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index d5871fd6f769..93e2e313fa70 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -133,7 +133,6 @@ struct nvme_tcp_queue { /* send state */ struct nvme_tcp_request *request; - int queue_size; u32 maxh2cdata; size_t cmnd_capsule_len; struct nvme_tcp_ctrl *ctrl; @@ -463,7 +462,7 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, unsigned int numa_node) { - struct nvme_tcp_ctrl *ctrl = set->driver_data; + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(set->driver_data); struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); struct nvme_tcp_cmd_pdu *pdu; int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0; @@ -487,7 +486,7 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set, static int nvme_tcp_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { - struct nvme_tcp_ctrl *ctrl = data; + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(data); struct nvme_tcp_queue *queue = &ctrl->queues[hctx_idx + 1]; hctx->driver_data = queue; @@ -497,7 +496,7 @@ static int nvme_tcp_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, static int nvme_tcp_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { - struct nvme_tcp_ctrl *ctrl = data; + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(data); struct nvme_tcp_queue *queue = &ctrl->queues[0]; hctx->driver_data = queue; @@ -1476,8 +1475,7 @@ static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue) queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false); } -static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, - int qid, size_t queue_size) +static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; @@ -1489,7 +1487,6 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, INIT_LIST_HEAD(&queue->send_list); mutex_init(&queue->send_mutex); INIT_WORK(&queue->io_work, nvme_tcp_io_work); - queue->queue_size = queue_size; if (qid > 0) queue->cmnd_capsule_len = nctrl->ioccsz * 16; @@ -1687,51 +1684,6 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx) return ret; } -static int nvme_tcp_alloc_admin_tag_set(struct nvme_ctrl *nctrl) -{ - struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); - struct blk_mq_tag_set *set = &ctrl->admin_tag_set; - int ret; - - memset(set, 0, sizeof(*set)); - set->ops = &nvme_tcp_admin_mq_ops; - set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; - set->reserved_tags = NVMF_RESERVED_TAGS; - set->numa_node = nctrl->numa_node; - set->flags = BLK_MQ_F_BLOCKING; - set->cmd_size = sizeof(struct nvme_tcp_request); - set->driver_data = ctrl; - set->nr_hw_queues = 1; - set->timeout = NVME_ADMIN_TIMEOUT; - ret = blk_mq_alloc_tag_set(set); - if (!ret) - nctrl->admin_tagset = set; - return ret; -} - -static int nvme_tcp_alloc_tag_set(struct nvme_ctrl *nctrl) -{ - struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); - struct blk_mq_tag_set *set = &ctrl->tag_set; - int ret; - - memset(set, 0, sizeof(*set)); - set->ops = &nvme_tcp_mq_ops; - set->queue_depth = nctrl->sqsize + 1; - set->reserved_tags = NVMF_RESERVED_TAGS; - set->numa_node = nctrl->numa_node; - set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING; - set->cmd_size = sizeof(struct nvme_tcp_request); - set->driver_data = ctrl; - set->nr_hw_queues = nctrl->queue_count - 1; - set->timeout = NVME_IO_TIMEOUT; - set->nr_maps = nctrl->opts->nr_poll_queues ? HCTX_MAX_TYPES : 2; - ret = blk_mq_alloc_tag_set(set); - if (!ret) - nctrl->tagset = set; - return ret; -} - static void nvme_tcp_free_admin_queue(struct nvme_ctrl *ctrl) { if (to_tcp_ctrl(ctrl)->async_req.pdu) { @@ -1759,11 +1711,12 @@ static void nvme_tcp_stop_io_queues(struct nvme_ctrl *ctrl) nvme_tcp_stop_queue(ctrl, i); } -static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl) +static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl, + int first, int last) { int i, ret; - for (i = 1; i < ctrl->queue_count; i++) { + for (i = first; i < last; i++) { ret = nvme_tcp_start_queue(ctrl, i); if (ret) goto out_stop_queues; @@ -1772,7 +1725,7 @@ static int nvme_tcp_start_io_queues(struct nvme_ctrl *ctrl) return 0; out_stop_queues: - for (i--; i >= 1; i--) + for (i--; i >= first; i--) nvme_tcp_stop_queue(ctrl, i); return ret; } @@ -1781,7 +1734,7 @@ static int nvme_tcp_alloc_admin_queue(struct nvme_ctrl *ctrl) { int ret; - ret = nvme_tcp_alloc_queue(ctrl, 0, NVME_AQ_DEPTH); + ret = nvme_tcp_alloc_queue(ctrl, 0); if (ret) return ret; @@ -1801,7 +1754,7 @@ static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) int i, ret; for (i = 1; i < ctrl->queue_count; i++) { - ret = nvme_tcp_alloc_queue(ctrl, i, ctrl->sqsize + 1); + ret = nvme_tcp_alloc_queue(ctrl, i); if (ret) goto out_free_queues; } @@ -1889,32 +1842,35 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) static void nvme_tcp_destroy_io_queues(struct nvme_ctrl *ctrl, bool remove) { nvme_tcp_stop_io_queues(ctrl); - if (remove) { - blk_mq_destroy_queue(ctrl->connect_q); - blk_mq_free_tag_set(ctrl->tagset); - } + if (remove) + nvme_remove_io_tag_set(ctrl); nvme_tcp_free_io_queues(ctrl); } static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) { - int ret; + int ret, nr_queues; ret = nvme_tcp_alloc_io_queues(ctrl); if (ret) return ret; if (new) { - ret = nvme_tcp_alloc_tag_set(ctrl); + ret = nvme_alloc_io_tag_set(ctrl, &to_tcp_ctrl(ctrl)->tag_set, + &nvme_tcp_mq_ops, + BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING, + sizeof(struct nvme_tcp_request)); if (ret) goto out_free_io_queues; - - ret = nvme_ctrl_init_connect_q(ctrl); - if (ret) - goto out_free_tag_set; } - ret = nvme_tcp_start_io_queues(ctrl); + /* + * Only start IO queues for which we have allocated the tagset + * and limitted it to the available queues. On reconnects, the + * queue number might have changed. + */ + nr_queues = min(ctrl->tagset->nr_hw_queues + 1, ctrl->queue_count); + ret = nvme_tcp_start_io_queues(ctrl, 1, nr_queues); if (ret) goto out_cleanup_connect_q; @@ -1934,6 +1890,15 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) nvme_unfreeze(ctrl); } + /* + * If the number of queues has increased (reconnect case) + * start all new queues now. + */ + ret = nvme_tcp_start_io_queues(ctrl, nr_queues, + ctrl->tagset->nr_hw_queues + 1); + if (ret) + goto out_wait_freeze_timed_out; + return 0; out_wait_freeze_timed_out: @@ -1943,10 +1908,7 @@ out_wait_freeze_timed_out: out_cleanup_connect_q: nvme_cancel_tagset(ctrl); if (new) - blk_mq_destroy_queue(ctrl->connect_q); -out_free_tag_set: - if (new) - blk_mq_free_tag_set(ctrl->tagset); + nvme_remove_io_tag_set(ctrl); out_free_io_queues: nvme_tcp_free_io_queues(ctrl); return ret; @@ -1955,11 +1917,8 @@ out_free_io_queues: static void nvme_tcp_destroy_admin_queue(struct nvme_ctrl *ctrl, bool remove) { nvme_tcp_stop_queue(ctrl, 0); - if (remove) { - blk_mq_destroy_queue(ctrl->admin_q); - blk_mq_destroy_queue(ctrl->fabrics_q); - blk_mq_free_tag_set(ctrl->admin_tagset); - } + if (remove) + nvme_remove_admin_tag_set(ctrl); nvme_tcp_free_admin_queue(ctrl); } @@ -1972,26 +1931,17 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new) return error; if (new) { - error = nvme_tcp_alloc_admin_tag_set(ctrl); + error = nvme_alloc_admin_tag_set(ctrl, + &to_tcp_ctrl(ctrl)->admin_tag_set, + &nvme_tcp_admin_mq_ops, BLK_MQ_F_BLOCKING, + sizeof(struct nvme_tcp_request)); if (error) goto out_free_queue; - - ctrl->fabrics_q = blk_mq_init_queue(ctrl->admin_tagset); - if (IS_ERR(ctrl->fabrics_q)) { - error = PTR_ERR(ctrl->fabrics_q); - goto out_free_tagset; - } - - ctrl->admin_q = blk_mq_init_queue(ctrl->admin_tagset); - if (IS_ERR(ctrl->admin_q)) { - error = PTR_ERR(ctrl->admin_q); - goto out_cleanup_fabrics_q; - } } error = nvme_tcp_start_queue(ctrl, 0); if (error) - goto out_cleanup_queue; + goto out_cleanup_tagset; error = nvme_enable_ctrl(ctrl); if (error) @@ -2011,15 +1961,9 @@ out_quiesce_queue: out_stop_queue: nvme_tcp_stop_queue(ctrl, 0); nvme_cancel_admin_tagset(ctrl); -out_cleanup_queue: - if (new) - blk_mq_destroy_queue(ctrl->admin_q); -out_cleanup_fabrics_q: +out_cleanup_tagset: if (new) - blk_mq_destroy_queue(ctrl->fabrics_q); -out_free_tagset: - if (new) - blk_mq_free_tag_set(ctrl->admin_tagset); + nvme_remove_admin_tag_set(ctrl); out_free_queue: nvme_tcp_free_admin_queue(ctrl); return error; @@ -2468,9 +2412,9 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } -static int nvme_tcp_map_queues(struct blk_mq_tag_set *set) +static void nvme_tcp_map_queues(struct blk_mq_tag_set *set) { - struct nvme_tcp_ctrl *ctrl = set->driver_data; + struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(set->driver_data); struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; if (opts->nr_write_queues && ctrl->io_queues[HCTX_TYPE_READ]) { @@ -2509,8 +2453,6 @@ static int nvme_tcp_map_queues(struct blk_mq_tag_set *set) ctrl->io_queues[HCTX_TYPE_DEFAULT], ctrl->io_queues[HCTX_TYPE_READ], ctrl->io_queues[HCTX_TYPE_POLL]); - - return 0; } static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) @@ -2529,6 +2471,25 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) return queue->nr_cqe; } +static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size) +{ + struct nvme_tcp_queue *queue = &to_tcp_ctrl(ctrl)->queues[0]; + struct sockaddr_storage src_addr; + int ret, len; + + len = nvmf_get_address(ctrl, buf, size); + + ret = kernel_getsockname(queue->sock, (struct sockaddr *)&src_addr); + if (ret > 0) { + if (len > 0) + len--; /* strip trailing newline */ + len += scnprintf(buf + len, size - len, "%ssrc_addr=%pISc\n", + (len) ? "," : "", &src_addr); + } + + return len; +} + static const struct blk_mq_ops nvme_tcp_mq_ops = { .queue_rq = nvme_tcp_queue_rq, .commit_rqs = nvme_tcp_commit_rqs, @@ -2560,7 +2521,7 @@ static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = { .free_ctrl = nvme_tcp_free_ctrl, .submit_async_event = nvme_tcp_submit_async_event, .delete_ctrl = nvme_tcp_delete_ctrl, - .get_address = nvmf_get_address, + .get_address = nvme_tcp_get_address, .stop_ctrl = nvme_tcp_stop_ctrl, }; diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index fc8a957fad0a..c8a061ce3ee5 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -449,7 +449,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) if (req->port->inline_data_size) id->sgls |= cpu_to_le32(1 << 20); - strlcpy(id->subnqn, ctrl->subsys->subsysnqn, sizeof(id->subnqn)); + strscpy(id->subnqn, ctrl->subsys->subsysnqn, sizeof(id->subnqn)); /* * Max command capsule size is sqe + in-capsule data size. diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 2bcd60758919..e34a2896fedb 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -1281,6 +1281,34 @@ static ssize_t nvmet_subsys_attr_pi_enable_store(struct config_item *item, CONFIGFS_ATTR(nvmet_subsys_, attr_pi_enable); #endif +static ssize_t nvmet_subsys_attr_qid_max_show(struct config_item *item, + char *page) +{ + return snprintf(page, PAGE_SIZE, "%u\n", to_subsys(item)->max_qid); +} + +static ssize_t nvmet_subsys_attr_qid_max_store(struct config_item *item, + const char *page, size_t cnt) +{ + struct nvmet_port *port = to_nvmet_port(item); + u16 qid_max; + + if (nvmet_is_port_enabled(port, __func__)) + return -EACCES; + + if (sscanf(page, "%hu\n", &qid_max) != 1) + return -EINVAL; + + if (qid_max < 1 || qid_max > NVMET_NR_QUEUES) + return -EINVAL; + + down_write(&nvmet_config_sem); + to_subsys(item)->max_qid = qid_max; + up_write(&nvmet_config_sem); + return cnt; +} +CONFIGFS_ATTR(nvmet_subsys_, attr_qid_max); + static struct configfs_attribute *nvmet_subsys_attrs[] = { &nvmet_subsys_attr_attr_allow_any_host, &nvmet_subsys_attr_attr_version, @@ -1288,6 +1316,7 @@ static struct configfs_attribute *nvmet_subsys_attrs[] = { &nvmet_subsys_attr_attr_cntlid_min, &nvmet_subsys_attr_attr_cntlid_max, &nvmet_subsys_attr_attr_model, + &nvmet_subsys_attr_attr_qid_max, #ifdef CONFIG_BLK_DEV_INTEGRITY &nvmet_subsys_attr_attr_pi_enable, #endif diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 7f4083cf953a..14677145bbba 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -832,6 +832,7 @@ int nvmet_sq_init(struct nvmet_sq *sq) } init_completion(&sq->free_done); init_completion(&sq->confirm_done); + nvmet_auth_sq_init(sq); return 0; } diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index c2162eef8ce1..668d257fa986 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -292,7 +292,7 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req) id->oaes = cpu_to_le32(NVMET_DISC_AEN_CFG_OPTIONAL); - strlcpy(id->subnqn, ctrl->subsys->subsysnqn, sizeof(id->subnqn)); + strscpy(id->subnqn, ctrl->subsys->subsysnqn, sizeof(id->subnqn)); status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id)); diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index ebdf9aa81041..7970a7640e58 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -23,17 +23,12 @@ static void nvmet_auth_expired_work(struct work_struct *work) sq->dhchap_tid = -1; } -void nvmet_init_auth(struct nvmet_ctrl *ctrl, struct nvmet_req *req) +void nvmet_auth_sq_init(struct nvmet_sq *sq) { - u32 result = le32_to_cpu(req->cqe->result.u32); - /* Initialize in-band authentication */ - INIT_DELAYED_WORK(&req->sq->auth_expired_work, - nvmet_auth_expired_work); - req->sq->authenticated = false; - req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE; - result |= (u32)NVME_CONNECT_AUTHREQ_ATR << 16; - req->cqe->result.u32 = cpu_to_le32(result); + INIT_DELAYED_WORK(&sq->auth_expired_work, nvmet_auth_expired_work); + sq->authenticated = false; + sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE; } static u16 nvmet_auth_negotiate(struct nvmet_req *req, void *d) @@ -177,7 +172,7 @@ static u16 nvmet_auth_reply(struct nvmet_req *req, void *d) return 0; } -static u16 nvmet_auth_failure2(struct nvmet_req *req, void *d) +static u16 nvmet_auth_failure2(void *d) { struct nvmf_auth_dhchap_failure_data *data = d; @@ -229,10 +224,8 @@ void nvmet_execute_auth_send(struct nvmet_req *req) } status = nvmet_copy_from_sgl(req, 0, d, tl); - if (status) { - kfree(d); - goto done; - } + if (status) + goto done_kfree; data = d; pr_debug("%s: ctrl %d qid %d type %d id %d step %x\n", __func__, @@ -310,7 +303,7 @@ void nvmet_execute_auth_send(struct nvmet_req *req) goto done_kfree; break; case NVME_AUTH_DHCHAP_MESSAGE_FAILURE2: - status = nvmet_auth_failure2(req, d); + status = nvmet_auth_failure2(d); if (status) { pr_warn("ctrl %d qid %d: authentication failed (%d)\n", ctrl->cntlid, req->sq->qid, status); diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index f91a56180d3d..43b5bd8bb6a5 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -198,6 +198,12 @@ err: return ret; } +static u32 nvmet_connect_result(struct nvmet_ctrl *ctrl) +{ + return (u32)ctrl->cntlid | + (nvmet_has_auth(ctrl) ? NVME_CONNECT_AUTHREQ_ATR : 0); +} + static void nvmet_execute_admin_connect(struct nvmet_req *req) { struct nvmf_connect_command *c = &req->cmd->connect; @@ -269,10 +275,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn, ctrl->pi_support ? " T10-PI is enabled" : "", nvmet_has_auth(ctrl) ? " with DH-HMAC-CHAP" : ""); - req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid); - - if (nvmet_has_auth(ctrl)) - nvmet_init_auth(ctrl, req); + req->cqe->result.u32 = cpu_to_le32(nvmet_connect_result(ctrl)); out: kfree(d); complete: @@ -328,14 +331,8 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) if (status) goto out_ctrl_put; - /* pass back cntlid for successful completion */ - req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid); - pr_debug("adding queue %d to ctrl %d.\n", qid, ctrl->cntlid); - req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid); - if (nvmet_has_auth(ctrl)) - nvmet_init_auth(ctrl, req); - + req->cqe->result.u32 = cpu_to_le32(nvmet_connect_result(ctrl)); out: kfree(d); complete: diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 2dc1c1035626..c2d6cea0236b 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -12,11 +12,9 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) { - const struct queue_limits *ql = &bdev_get_queue(bdev)->limits; - /* Number of logical blocks per physical block. */ - const u32 lpp = ql->physical_block_size / ql->logical_block_size; /* Logical blocks per physical block, 0's based. */ - const __le16 lpp0b = to0based(lpp); + const __le16 lpp0b = to0based(bdev_physical_block_size(bdev) / + bdev_logical_block_size(bdev)); /* * For NVMe 1.2 and later, bit 1 indicates that the fields NAWUN, @@ -42,11 +40,12 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) /* NPWA = Namespace Preferred Write Alignment. 0's based */ id->npwa = id->npwg; /* NPDG = Namespace Preferred Deallocate Granularity. 0's based */ - id->npdg = to0based(ql->discard_granularity / ql->logical_block_size); + id->npdg = to0based(bdev_discard_granularity(bdev) / + bdev_logical_block_size(bdev)); /* NPDG = Namespace Preferred Deallocate Alignment */ id->npda = id->npdg; /* NOWS = Namespace Optimal Write Size */ - id->nows = to0based(ql->io_opt / ql->logical_block_size); + id->nows = to0based(bdev_io_opt(bdev) / bdev_logical_block_size(bdev)); } void nvmet_bdev_ns_disable(struct nvmet_ns *ns) @@ -334,6 +333,11 @@ static void nvmet_bdev_execute_flush(struct nvmet_req *req) { struct bio *bio = &req->b.inline_bio; + if (!bdev_write_cache(req->ns->bdev)) { + nvmet_req_complete(req, NVME_SC_SUCCESS); + return; + } + if (!nvmet_check_transfer_len(req, 0)) return; @@ -347,6 +351,9 @@ static void nvmet_bdev_execute_flush(struct nvmet_req *req) u16 nvmet_bdev_flush(struct nvmet_req *req) { + if (!bdev_write_cache(req->ns->bdev)) + return 0; + if (blkdev_issue_flush(req->ns->bdev)) return NVME_SC_INTERNAL | NVME_SC_DNR; return 0; diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 9750a7fca268..b45fe3adf015 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -204,7 +204,7 @@ static int nvme_loop_init_request(struct blk_mq_tag_set *set, struct request *req, unsigned int hctx_idx, unsigned int numa_node) { - struct nvme_loop_ctrl *ctrl = set->driver_data; + struct nvme_loop_ctrl *ctrl = to_loop_ctrl(set->driver_data); struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req); nvme_req(req)->ctrl = &ctrl->ctrl; @@ -218,7 +218,7 @@ static struct lock_class_key loop_hctx_fq_lock_key; static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { - struct nvme_loop_ctrl *ctrl = data; + struct nvme_loop_ctrl *ctrl = to_loop_ctrl(data); struct nvme_loop_queue *queue = &ctrl->queues[hctx_idx + 1]; BUG_ON(hctx_idx >= ctrl->ctrl.queue_count); @@ -238,7 +238,7 @@ static int nvme_loop_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, static int nvme_loop_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { - struct nvme_loop_ctrl *ctrl = data; + struct nvme_loop_ctrl *ctrl = to_loop_ctrl(data); struct nvme_loop_queue *queue = &ctrl->queues[0]; BUG_ON(hctx_idx != 0); @@ -266,9 +266,7 @@ static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl) if (!test_and_clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags)) return; nvmet_sq_destroy(&ctrl->queues[0].nvme_sq); - blk_mq_destroy_queue(ctrl->ctrl.admin_q); - blk_mq_destroy_queue(ctrl->ctrl.fabrics_q); - blk_mq_free_tag_set(&ctrl->admin_tag_set); + nvme_remove_admin_tag_set(&ctrl->ctrl); } static void nvme_loop_free_ctrl(struct nvme_ctrl *nctrl) @@ -282,10 +280,8 @@ static void nvme_loop_free_ctrl(struct nvme_ctrl *nctrl) list_del(&ctrl->list); mutex_unlock(&nvme_loop_ctrl_mutex); - if (nctrl->tagset) { - blk_mq_destroy_queue(ctrl->ctrl.connect_q); - blk_mq_free_tag_set(&ctrl->tag_set); - } + if (nctrl->tagset) + nvme_remove_io_tag_set(nctrl); kfree(ctrl->queues); nvmf_free_options(nctrl->opts); free_ctrl: @@ -350,52 +346,31 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) { int error; - memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set)); - ctrl->admin_tag_set.ops = &nvme_loop_admin_mq_ops; - ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH; - ctrl->admin_tag_set.reserved_tags = NVMF_RESERVED_TAGS; - ctrl->admin_tag_set.numa_node = ctrl->ctrl.numa_node; - ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) + - NVME_INLINE_SG_CNT * sizeof(struct scatterlist); - ctrl->admin_tag_set.driver_data = ctrl; - ctrl->admin_tag_set.nr_hw_queues = 1; - ctrl->admin_tag_set.timeout = NVME_ADMIN_TIMEOUT; - ctrl->admin_tag_set.flags = BLK_MQ_F_NO_SCHED; - ctrl->queues[0].ctrl = ctrl; error = nvmet_sq_init(&ctrl->queues[0].nvme_sq); if (error) return error; ctrl->ctrl.queue_count = 1; - error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set); + error = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set, + &nvme_loop_admin_mq_ops, BLK_MQ_F_NO_SCHED, + sizeof(struct nvme_loop_iod) + + NVME_INLINE_SG_CNT * sizeof(struct scatterlist)); if (error) goto out_free_sq; - ctrl->ctrl.admin_tagset = &ctrl->admin_tag_set; - ctrl->ctrl.fabrics_q = blk_mq_init_queue(&ctrl->admin_tag_set); - if (IS_ERR(ctrl->ctrl.fabrics_q)) { - error = PTR_ERR(ctrl->ctrl.fabrics_q); - goto out_free_tagset; - } - - ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set); - if (IS_ERR(ctrl->ctrl.admin_q)) { - error = PTR_ERR(ctrl->ctrl.admin_q); - goto out_cleanup_fabrics_q; - } /* reset stopped state for the fresh admin queue */ clear_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->ctrl.flags); error = nvmf_connect_admin_queue(&ctrl->ctrl); if (error) - goto out_cleanup_queue; + goto out_cleanup_tagset; set_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags); error = nvme_enable_ctrl(&ctrl->ctrl); if (error) - goto out_cleanup_queue; + goto out_cleanup_tagset; ctrl->ctrl.max_hw_sectors = (NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9); @@ -404,17 +379,13 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) error = nvme_init_ctrl_finish(&ctrl->ctrl); if (error) - goto out_cleanup_queue; + goto out_cleanup_tagset; return 0; -out_cleanup_queue: +out_cleanup_tagset: clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags); - blk_mq_destroy_queue(ctrl->ctrl.admin_q); -out_cleanup_fabrics_q: - blk_mq_destroy_queue(ctrl->ctrl.fabrics_q); -out_free_tagset: - blk_mq_free_tag_set(&ctrl->admin_tag_set); + nvme_remove_admin_tag_set(&ctrl->ctrl); out_free_sq: nvmet_sq_destroy(&ctrl->queues[0].nvme_sq); return error; @@ -522,37 +493,21 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl) if (ret) return ret; - memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set)); - ctrl->tag_set.ops = &nvme_loop_mq_ops; - ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size; - ctrl->tag_set.reserved_tags = NVMF_RESERVED_TAGS; - ctrl->tag_set.numa_node = ctrl->ctrl.numa_node; - ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; - ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) + - NVME_INLINE_SG_CNT * sizeof(struct scatterlist); - ctrl->tag_set.driver_data = ctrl; - ctrl->tag_set.nr_hw_queues = ctrl->ctrl.queue_count - 1; - ctrl->tag_set.timeout = NVME_IO_TIMEOUT; - ctrl->ctrl.tagset = &ctrl->tag_set; - - ret = blk_mq_alloc_tag_set(&ctrl->tag_set); + ret = nvme_alloc_io_tag_set(&ctrl->ctrl, &ctrl->tag_set, + &nvme_loop_mq_ops, BLK_MQ_F_SHOULD_MERGE, + sizeof(struct nvme_loop_iod) + + NVME_INLINE_SG_CNT * sizeof(struct scatterlist)); if (ret) goto out_destroy_queues; - ret = nvme_ctrl_init_connect_q(&(ctrl->ctrl)); - if (ret) - goto out_free_tagset; - ret = nvme_loop_connect_io_queues(ctrl); if (ret) - goto out_cleanup_connect_q; + goto out_cleanup_tagset; return 0; -out_cleanup_connect_q: - blk_mq_destroy_queue(ctrl->ctrl.connect_q); -out_free_tagset: - blk_mq_free_tag_set(&ctrl->tag_set); +out_cleanup_tagset: + nvme_remove_io_tag_set(&ctrl->ctrl); out_destroy_queues: nvme_loop_destroy_io_queues(ctrl); return ret; @@ -601,7 +556,6 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, ret = -ENOMEM; - ctrl->ctrl.sqsize = opts->queue_size - 1; ctrl->ctrl.kato = opts->kato; ctrl->port = nvme_loop_find_port(&ctrl->ctrl); @@ -621,6 +575,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, opts->queue_size, ctrl->ctrl.maxcmd); opts->queue_size = ctrl->ctrl.maxcmd; } + ctrl->ctrl.sqsize = opts->queue_size - 1; if (opts->nr_io_queues) { ret = nvme_loop_create_io_queues(ctrl); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 6ffeeb0a1c49..dfe3894205aa 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -704,7 +704,7 @@ int nvmet_auth_set_key(struct nvmet_host *host, const char *secret, bool set_ctrl); int nvmet_auth_set_host_hash(struct nvmet_host *host, const char *hash); int nvmet_setup_auth(struct nvmet_ctrl *ctrl); -void nvmet_init_auth(struct nvmet_ctrl *ctrl, struct nvmet_req *req); +void nvmet_auth_sq_init(struct nvmet_sq *sq); void nvmet_destroy_auth(struct nvmet_ctrl *ctrl); void nvmet_auth_sq_free(struct nvmet_sq *sq); int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id); @@ -726,8 +726,9 @@ static inline int nvmet_setup_auth(struct nvmet_ctrl *ctrl) { return 0; } -static inline void nvmet_init_auth(struct nvmet_ctrl *ctrl, - struct nvmet_req *req) {}; +static inline void nvmet_auth_sq_init(struct nvmet_sq *sq) +{ +} static inline void nvmet_destroy_auth(struct nvmet_ctrl *ctrl) {}; static inline void nvmet_auth_sq_free(struct nvmet_sq *sq) {}; static inline bool nvmet_check_auth_status(struct nvmet_req *req) diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 6f39a29828b1..94d3153bae54 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -215,9 +215,11 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) { struct nvmet_req *req = container_of(w, struct nvmet_req, p.work); struct request *rq = req->p.rq; + struct nvme_ctrl *ctrl = nvme_req(rq)->ctrl; + u32 effects; int status; - status = nvme_execute_passthru_rq(rq); + status = nvme_execute_passthru_rq(rq, &effects); if (status == NVME_SC_SUCCESS && req->cmd->common.opcode == nvme_admin_identify) { @@ -238,6 +240,9 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) req->cqe->result = nvme_req(rq)->result; nvmet_req_complete(req, status); blk_mq_free_request(rq); + + if (effects) + nvme_passthru_end(ctrl, effects, req->cmd, status); } static void nvmet_passthru_req_done(struct request *rq, diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index a3694a32f6d5..6c1476e086ef 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -77,9 +77,8 @@ struct nvmet_tcp_cmd { u32 pdu_len; u32 pdu_recv; int sg_idx; - int nr_mapped; struct msghdr recv_msg; - struct kvec *iov; + struct bio_vec *iov; u32 flags; struct list_head entry; @@ -165,9 +164,7 @@ static DEFINE_MUTEX(nvmet_tcp_queue_mutex); static struct workqueue_struct *nvmet_tcp_wq; static const struct nvmet_fabrics_ops nvmet_tcp_ops; static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c); -static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd); static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd); -static void nvmet_tcp_unmap_pdu_iovec(struct nvmet_tcp_cmd *cmd); static inline u16 nvmet_tcp_cmd_tag(struct nvmet_tcp_queue *queue, struct nvmet_tcp_cmd *cmd) @@ -301,35 +298,21 @@ static int nvmet_tcp_check_ddgst(struct nvmet_tcp_queue *queue, void *pdu) static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd) { - WARN_ON(unlikely(cmd->nr_mapped > 0)); - kfree(cmd->iov); sgl_free(cmd->req.sg); cmd->iov = NULL; cmd->req.sg = NULL; } -static void nvmet_tcp_unmap_pdu_iovec(struct nvmet_tcp_cmd *cmd) -{ - struct scatterlist *sg; - int i; - - sg = &cmd->req.sg[cmd->sg_idx]; - - for (i = 0; i < cmd->nr_mapped; i++) - kunmap(sg_page(&sg[i])); - - cmd->nr_mapped = 0; -} - -static void nvmet_tcp_map_pdu_iovec(struct nvmet_tcp_cmd *cmd) +static void nvmet_tcp_build_pdu_iovec(struct nvmet_tcp_cmd *cmd) { - struct kvec *iov = cmd->iov; + struct bio_vec *iov = cmd->iov; struct scatterlist *sg; u32 length, offset, sg_offset; + int nr_pages; length = cmd->pdu_len; - cmd->nr_mapped = DIV_ROUND_UP(length, PAGE_SIZE); + nr_pages = DIV_ROUND_UP(length, PAGE_SIZE); offset = cmd->rbytes_done; cmd->sg_idx = offset / PAGE_SIZE; sg_offset = offset % PAGE_SIZE; @@ -338,8 +321,9 @@ static void nvmet_tcp_map_pdu_iovec(struct nvmet_tcp_cmd *cmd) while (length) { u32 iov_len = min_t(u32, length, sg->length - sg_offset); - iov->iov_base = kmap(sg_page(sg)) + sg->offset + sg_offset; - iov->iov_len = iov_len; + iov->bv_page = sg_page(sg); + iov->bv_len = sg->length; + iov->bv_offset = sg->offset + sg_offset; length -= iov_len; sg = sg_next(sg); @@ -347,8 +331,8 @@ static void nvmet_tcp_map_pdu_iovec(struct nvmet_tcp_cmd *cmd) sg_offset = 0; } - iov_iter_kvec(&cmd->recv_msg.msg_iter, READ, cmd->iov, - cmd->nr_mapped, cmd->pdu_len); + iov_iter_bvec(&cmd->recv_msg.msg_iter, READ, cmd->iov, + nr_pages, cmd->pdu_len); } static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue) @@ -926,7 +910,7 @@ static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, } queue->rcv_state = NVMET_TCP_RECV_DATA; - nvmet_tcp_map_pdu_iovec(cmd); + nvmet_tcp_build_pdu_iovec(cmd); cmd->flags |= NVMET_TCP_F_INIT_FAILED; } @@ -935,10 +919,17 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) struct nvme_tcp_data_pdu *data = &queue->pdu.data; struct nvmet_tcp_cmd *cmd; - if (likely(queue->nr_cmds)) + if (likely(queue->nr_cmds)) { + if (unlikely(data->ttag >= queue->nr_cmds)) { + pr_err("queue %d: received out of bound ttag %u, nr_cmds %u\n", + queue->idx, data->ttag, queue->nr_cmds); + nvmet_tcp_fatal_error(queue); + return -EPROTO; + } cmd = &queue->cmds[data->ttag]; - else + } else { cmd = &queue->connect; + } if (le32_to_cpu(data->data_offset) != cmd->rbytes_done) { pr_err("ttag %u unexpected data offset %u (expected %u)\n", @@ -952,7 +943,7 @@ static int nvmet_tcp_handle_h2c_data_pdu(struct nvmet_tcp_queue *queue) cmd->pdu_len = le32_to_cpu(data->data_length); cmd->pdu_recv = 0; - nvmet_tcp_map_pdu_iovec(cmd); + nvmet_tcp_build_pdu_iovec(cmd); queue->cmd = cmd; queue->rcv_state = NVMET_TCP_RECV_DATA; @@ -976,6 +967,13 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) return nvmet_tcp_handle_icreq(queue); } + if (unlikely(hdr->type == nvme_tcp_icreq)) { + pr_err("queue %d: received icreq pdu in state %d\n", + queue->idx, queue->state); + nvmet_tcp_fatal_error(queue); + return -EPROTO; + } + if (hdr->type == nvme_tcp_h2c_data) { ret = nvmet_tcp_handle_h2c_data_pdu(queue); if (unlikely(ret)) @@ -1021,7 +1019,7 @@ static int nvmet_tcp_done_recv_pdu(struct nvmet_tcp_queue *queue) if (nvmet_tcp_need_data_in(queue->cmd)) { if (nvmet_tcp_has_inline_data(queue->cmd)) { queue->rcv_state = NVMET_TCP_RECV_DATA; - nvmet_tcp_map_pdu_iovec(queue->cmd); + nvmet_tcp_build_pdu_iovec(queue->cmd); return 0; } /* send back R2T */ @@ -1141,7 +1139,6 @@ static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue) cmd->rbytes_done += ret; } - nvmet_tcp_unmap_pdu_iovec(cmd); if (queue->data_digest) { nvmet_tcp_prep_recv_ddgst(cmd); return 0; @@ -1179,7 +1176,8 @@ static int nvmet_tcp_try_recv_ddgst(struct nvmet_tcp_queue *queue) queue->idx, cmd->req.cmd->common.command_id, queue->pdu.cmd.hdr.type, le32_to_cpu(cmd->recv_ddgst), le32_to_cpu(cmd->exp_ddgst)); - nvmet_tcp_finish_cmd(cmd); + nvmet_req_uninit(&cmd->req); + nvmet_tcp_free_cmd_buffers(cmd); nvmet_tcp_fatal_error(queue); ret = -EPROTO; goto out; @@ -1408,13 +1406,6 @@ static void nvmet_tcp_restore_socket_callbacks(struct nvmet_tcp_queue *queue) write_unlock_bh(&sock->sk->sk_callback_lock); } -static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd) -{ - nvmet_req_uninit(&cmd->req); - nvmet_tcp_unmap_pdu_iovec(cmd); - nvmet_tcp_free_cmd_buffers(cmd); -} - static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue) { struct nvmet_tcp_cmd *cmd = queue->cmds; @@ -1423,15 +1414,26 @@ static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue) for (i = 0; i < queue->nr_cmds; i++, cmd++) { if (nvmet_tcp_need_data_in(cmd)) nvmet_req_uninit(&cmd->req); - - nvmet_tcp_unmap_pdu_iovec(cmd); - nvmet_tcp_free_cmd_buffers(cmd); } if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect)) { /* failed in connect */ - nvmet_tcp_finish_cmd(&queue->connect); + nvmet_req_uninit(&queue->connect.req); + } +} + +static void nvmet_tcp_free_cmd_data_in_buffers(struct nvmet_tcp_queue *queue) +{ + struct nvmet_tcp_cmd *cmd = queue->cmds; + int i; + + for (i = 0; i < queue->nr_cmds; i++, cmd++) { + if (nvmet_tcp_need_data_in(cmd)) + nvmet_tcp_free_cmd_buffers(cmd); } + + if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect)) + nvmet_tcp_free_cmd_buffers(&queue->connect); } static void nvmet_tcp_release_queue_work(struct work_struct *w) @@ -1452,6 +1454,7 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w) nvmet_tcp_uninit_data_in_cmds(queue); nvmet_sq_destroy(&queue->nvme_sq); cancel_work_sync(&queue->io_work); + nvmet_tcp_free_cmd_data_in_buffers(queue); sock_release(queue->sock); nvmet_tcp_free_cmds(queue); if (queue->hdr_digest || queue->data_digest) diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c index 835bfda86fcf..1254cf57e008 100644 --- a/drivers/nvme/target/zns.c +++ b/drivers/nvme/target/zns.c @@ -400,7 +400,6 @@ static u16 nvmet_bdev_zone_mgmt_emulate_all(struct nvmet_req *req) { struct block_device *bdev = req->ns->bdev; unsigned int nr_zones = bdev_nr_zones(bdev); - struct request_queue *q = bdev_get_queue(bdev); struct bio *bio = NULL; sector_t sector = 0; int ret; @@ -409,7 +408,7 @@ static u16 nvmet_bdev_zone_mgmt_emulate_all(struct nvmet_req *req) }; d.zbitmap = kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(*(d.zbitmap)), - GFP_NOIO, q->node); + GFP_NOIO, bdev->bd_disk->node_id); if (!d.zbitmap) { ret = -ENOMEM; goto out; diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 77d1ba3a4154..e87567dbe99f 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -873,7 +873,7 @@ int dev_pm_opp_config_clks_simple(struct device *dev, } } - return ret; + return 0; } EXPORT_SYMBOL_GPL(dev_pm_opp_config_clks_simple); diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index 80d8309652a4..b80a9b74662b 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -36,7 +36,7 @@ #define CMN_CI_CHILD_COUNT GENMASK_ULL(15, 0) #define CMN_CI_CHILD_PTR_OFFSET GENMASK_ULL(31, 16) -#define CMN_CHILD_NODE_ADDR GENMASK(27, 0) +#define CMN_CHILD_NODE_ADDR GENMASK(29, 0) #define CMN_CHILD_NODE_EXTERNAL BIT(31) #define CMN_MAX_DIMENSION 12 diff --git a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c index a4d7d9bd100d..67712c77d806 100644 --- a/drivers/phy/marvell/phy-mvebu-a3700-comphy.c +++ b/drivers/phy/marvell/phy-mvebu-a3700-comphy.c @@ -274,7 +274,6 @@ struct mvebu_a3700_comphy_lane { int submode; bool invert_tx; bool invert_rx; - bool needs_reset; }; struct gbe_phy_init_data_fix { @@ -1097,40 +1096,12 @@ mvebu_a3700_comphy_pcie_power_off(struct mvebu_a3700_comphy_lane *lane) 0x0, PU_PLL_BIT | PU_RX_BIT | PU_TX_BIT); } -static int mvebu_a3700_comphy_reset(struct phy *phy) +static void mvebu_a3700_comphy_usb3_power_off(struct mvebu_a3700_comphy_lane *lane) { - struct mvebu_a3700_comphy_lane *lane = phy_get_drvdata(phy); - u16 mask, data; - - dev_dbg(lane->dev, "resetting lane %d\n", lane->id); - - /* COMPHY reset for internal logic */ - comphy_lane_reg_set(lane, COMPHY_SFT_RESET, - SFT_RST_NO_REG, SFT_RST_NO_REG); - - /* COMPHY register reset (cleared automatically) */ - comphy_lane_reg_set(lane, COMPHY_SFT_RESET, SFT_RST, SFT_RST); - - /* PIPE soft and register reset */ - data = PIPE_SOFT_RESET | PIPE_REG_RESET; - mask = data; - comphy_lane_reg_set(lane, COMPHY_PIPE_RST_CLK_CTRL, data, mask); - - /* Release PIPE register reset */ - comphy_lane_reg_set(lane, COMPHY_PIPE_RST_CLK_CTRL, - 0x0, PIPE_REG_RESET); - - /* Reset SB configuration register (only for lanes 0 and 1) */ - if (lane->id == 0 || lane->id == 1) { - u32 mask, data; - - data = PIN_RESET_CORE_BIT | PIN_RESET_COMPHY_BIT | - PIN_PU_PLL_BIT | PIN_PU_RX_BIT | PIN_PU_TX_BIT; - mask = data | PIN_PU_IVREF_BIT | PIN_TX_IDLE_BIT; - comphy_periph_reg_set(lane, COMPHY_PHY_CFG1, data, mask); - } - - return 0; + /* + * The USB3 MAC sets the USB3 PHY to low state, so we do not + * need to power off USB3 PHY again. + */ } static bool mvebu_a3700_comphy_check_mode(int lane, @@ -1171,10 +1142,6 @@ static int mvebu_a3700_comphy_set_mode(struct phy *phy, enum phy_mode mode, (lane->mode != mode || lane->submode != submode)) return -EBUSY; - /* If changing mode, ensure reset is called */ - if (lane->mode != PHY_MODE_INVALID && lane->mode != mode) - lane->needs_reset = true; - /* Just remember the mode, ->power_on() will do the real setup */ lane->mode = mode; lane->submode = submode; @@ -1185,7 +1152,6 @@ static int mvebu_a3700_comphy_set_mode(struct phy *phy, enum phy_mode mode, static int mvebu_a3700_comphy_power_on(struct phy *phy) { struct mvebu_a3700_comphy_lane *lane = phy_get_drvdata(phy); - int ret; if (!mvebu_a3700_comphy_check_mode(lane->id, lane->mode, lane->submode)) { @@ -1193,14 +1159,6 @@ static int mvebu_a3700_comphy_power_on(struct phy *phy) return -EINVAL; } - if (lane->needs_reset) { - ret = mvebu_a3700_comphy_reset(phy); - if (ret) - return ret; - - lane->needs_reset = false; - } - switch (lane->mode) { case PHY_MODE_USB_HOST_SS: dev_dbg(lane->dev, "set lane %d to USB3 host mode\n", lane->id); @@ -1224,38 +1182,28 @@ static int mvebu_a3700_comphy_power_off(struct phy *phy) { struct mvebu_a3700_comphy_lane *lane = phy_get_drvdata(phy); - switch (lane->mode) { - case PHY_MODE_USB_HOST_SS: - /* - * The USB3 MAC sets the USB3 PHY to low state, so we do not - * need to power off USB3 PHY again. - */ - break; - - case PHY_MODE_SATA: - mvebu_a3700_comphy_sata_power_off(lane); - break; - - case PHY_MODE_ETHERNET: + switch (lane->id) { + case 0: + mvebu_a3700_comphy_usb3_power_off(lane); mvebu_a3700_comphy_ethernet_power_off(lane); - break; - - case PHY_MODE_PCIE: + return 0; + case 1: mvebu_a3700_comphy_pcie_power_off(lane); - break; - + mvebu_a3700_comphy_ethernet_power_off(lane); + return 0; + case 2: + mvebu_a3700_comphy_usb3_power_off(lane); + mvebu_a3700_comphy_sata_power_off(lane); + return 0; default: dev_err(lane->dev, "invalid COMPHY mode\n"); return -EINVAL; } - - return 0; } static const struct phy_ops mvebu_a3700_comphy_ops = { .power_on = mvebu_a3700_comphy_power_on, .power_off = mvebu_a3700_comphy_power_off, - .reset = mvebu_a3700_comphy_reset, .set_mode = mvebu_a3700_comphy_set_mode, .owner = THIS_MODULE, }; @@ -1393,8 +1341,7 @@ static int mvebu_a3700_comphy_probe(struct platform_device *pdev) * To avoid relying on the bootloader/firmware configuration, * power off all comphys. */ - mvebu_a3700_comphy_reset(phy); - lane->needs_reset = false; + mvebu_a3700_comphy_power_off(phy); } provider = devm_of_phy_provider_register(&pdev->dev, diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index ea82821599f6..5a6d9c15395f 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -41,15 +41,6 @@ #define DASD_DIAG_MOD "dasd_diag_mod" -static unsigned int queue_depth = 32; -static unsigned int nr_hw_queues = 4; - -module_param(queue_depth, uint, 0444); -MODULE_PARM_DESC(queue_depth, "Default queue depth for new DASD devices"); - -module_param(nr_hw_queues, uint, 0444); -MODULE_PARM_DESC(nr_hw_queues, "Default number of hardware queues for new DASD devices"); - /* * SECTION: exported variables of dasd.c */ @@ -68,8 +59,6 @@ MODULE_LICENSE("GPL"); /* * SECTION: prototypes for static functions of dasd.c */ -static int dasd_alloc_queue(struct dasd_block *); -static void dasd_free_queue(struct dasd_block *); static int dasd_flush_block_queue(struct dasd_block *); static void dasd_device_tasklet(unsigned long); static void dasd_block_tasklet(unsigned long); @@ -198,21 +187,11 @@ EXPORT_SYMBOL_GPL(dasd_free_block); */ static int dasd_state_new_to_known(struct dasd_device *device) { - int rc; - /* * As long as the device is not in state DASD_STATE_NEW we want to * keep the reference count > 0. */ dasd_get_device(device); - - if (device->block) { - rc = dasd_alloc_queue(device->block); - if (rc) { - dasd_put_device(device); - return rc; - } - } device->state = DASD_STATE_KNOWN; return 0; } @@ -226,9 +205,6 @@ static int dasd_state_known_to_new(struct dasd_device *device) dasd_eer_disable(device); device->state = DASD_STATE_NEW; - if (device->block) - dasd_free_queue(device->block); - /* Give up reference we took in dasd_state_new_to_known. */ dasd_put_device(device); return 0; @@ -1591,9 +1567,8 @@ void dasd_generic_handle_state_change(struct dasd_device *device) dasd_schedule_device_bh(device); if (device->block) { dasd_schedule_block_bh(device->block); - if (device->block->request_queue) - blk_mq_run_hw_queues(device->block->request_queue, - true); + if (device->block->gdp) + blk_mq_run_hw_queues(device->block->gdp->queue, true); } } EXPORT_SYMBOL_GPL(dasd_generic_handle_state_change); @@ -2691,7 +2666,7 @@ static void dasd_block_timeout(struct timer_list *t) dasd_device_remove_stop_bits(block->base, DASD_STOPPED_PENDING); spin_unlock_irqrestore(get_ccwdev_lock(block->base->cdev), flags); dasd_schedule_block_bh(block); - blk_mq_run_hw_queues(block->request_queue, true); + blk_mq_run_hw_queues(block->gdp->queue, true); } /* @@ -3239,7 +3214,7 @@ static void dasd_request_done(struct request *req) blk_mq_run_hw_queues(req->q, true); } -static struct blk_mq_ops dasd_mq_ops = { +struct blk_mq_ops dasd_mq_ops = { .queue_rq = do_dasd_request, .complete = dasd_request_done, .timeout = dasd_times_out, @@ -3247,45 +3222,6 @@ static struct blk_mq_ops dasd_mq_ops = { .exit_hctx = dasd_exit_hctx, }; -/* - * Allocate and initialize request queue and default I/O scheduler. - */ -static int dasd_alloc_queue(struct dasd_block *block) -{ - int rc; - - block->tag_set.ops = &dasd_mq_ops; - block->tag_set.cmd_size = sizeof(struct dasd_ccw_req); - block->tag_set.nr_hw_queues = nr_hw_queues; - block->tag_set.queue_depth = queue_depth; - block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; - block->tag_set.numa_node = NUMA_NO_NODE; - - rc = blk_mq_alloc_tag_set(&block->tag_set); - if (rc) - return rc; - - block->request_queue = blk_mq_init_queue(&block->tag_set); - if (IS_ERR(block->request_queue)) - return PTR_ERR(block->request_queue); - - block->request_queue->queuedata = block; - - return 0; -} - -/* - * Deactivate and free request queue. - */ -static void dasd_free_queue(struct dasd_block *block) -{ - if (block->request_queue) { - blk_mq_destroy_queue(block->request_queue); - blk_mq_free_tag_set(&block->tag_set); - block->request_queue = NULL; - } -} - static int dasd_open(struct block_device *bdev, fmode_t mode) { struct dasd_device *base; @@ -3762,10 +3698,9 @@ int dasd_generic_path_operational(struct dasd_device *device) dasd_schedule_device_bh(device); if (device->block) { dasd_schedule_block_bh(device->block); - if (device->block->request_queue) - blk_mq_run_hw_queues(device->block->request_queue, - true); - } + if (device->block->gdp) + blk_mq_run_hw_queues(device->block->gdp->queue, true); + } if (!device->stopped) wake_up(&generic_waitq); @@ -3916,8 +3851,8 @@ void dasd_generic_space_avail(struct dasd_device *device) if (device->block) { dasd_schedule_block_bh(device->block); - if (device->block->request_queue) - blk_mq_run_hw_queues(device->block->request_queue, true); + if (device->block->gdp) + blk_mq_run_hw_queues(device->block->gdp->queue, true); } if (!device->stopped) wake_up(&generic_waitq); @@ -3927,7 +3862,7 @@ EXPORT_SYMBOL_GPL(dasd_generic_space_avail); /* * clear active requests and requeue them to block layer if possible */ -static int dasd_generic_requeue_all_requests(struct dasd_device *device) +int dasd_generic_requeue_all_requests(struct dasd_device *device) { struct list_head requeue_queue; struct dasd_ccw_req *cqr, *n; @@ -4001,6 +3936,7 @@ static int dasd_generic_requeue_all_requests(struct dasd_device *device) dasd_schedule_device_bh(device); return rc; } +EXPORT_SYMBOL_GPL(dasd_generic_requeue_all_requests); static void do_requeue_requests(struct work_struct *work) { diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c index 299001ad9a32..81d283b3cd3b 100644 --- a/drivers/s390/block/dasd_3990_erp.c +++ b/drivers/s390/block/dasd_3990_erp.c @@ -1050,6 +1050,11 @@ dasd_3990_erp_com_rej(struct dasd_ccw_req * erp, char *sense) dev_err(&device->cdev->dev, "An I/O request was rejected" " because writing is inhibited\n"); erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED); + } else if (sense[7] & SNS7_INVALID_ON_SEC) { + dev_err(&device->cdev->dev, "An I/O request was rejected on a copy pair secondary device\n"); + /* suppress dump of sense data for this error */ + set_bit(DASD_CQR_SUPPRESS_CR, &erp->refers->flags); + erp = dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED); } else { /* fatal error - set status to FAILED internal error 09 - Command Reject */ diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index dc78a523a69f..b6b938aa6615 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -675,12 +675,12 @@ int dasd_alias_remove_device(struct dasd_device *device) struct dasd_device *dasd_alias_get_start_dev(struct dasd_device *base_device) { struct dasd_eckd_private *alias_priv, *private = base_device->private; - struct alias_pav_group *group = private->pavgroup; struct alias_lcu *lcu = private->lcu; struct dasd_device *alias_device; + struct alias_pav_group *group; unsigned long flags; - if (!group || !lcu) + if (!lcu) return NULL; if (lcu->pav == NO_PAV || lcu->flags & (NEED_UAC_UPDATE | UPDATE_PENDING)) @@ -697,6 +697,11 @@ struct dasd_device *dasd_alias_get_start_dev(struct dasd_device *base_device) } spin_lock_irqsave(&lcu->lock, flags); + group = private->pavgroup; + if (!group) { + spin_unlock_irqrestore(&lcu->lock, flags); + return NULL; + } alias_device = group->next; if (!alias_device) { if (list_empty(&group->aliaslist)) { diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c index 811e79c9f59c..1beb596d1434 100644 --- a/drivers/s390/block/dasd_devmap.c +++ b/drivers/s390/block/dasd_devmap.c @@ -26,7 +26,6 @@ /* This is ugly... */ #define PRINTK_HEADER "dasd_devmap:" -#define DASD_BUS_ID_SIZE 20 #define DASD_MAX_PARAMS 256 #include "dasd_int.h" @@ -50,6 +49,7 @@ struct dasd_devmap { unsigned int devindex; unsigned short features; struct dasd_device *device; + struct dasd_copy_relation *copy; }; /* @@ -130,7 +130,7 @@ __setup ("dasd=", dasd_call_setup); /* * Read a device busid/devno from a string. */ -static int __init dasd_busid(char *str, int *id0, int *id1, int *devno) +static int dasd_busid(char *str, int *id0, int *id1, int *devno) { unsigned int val; char *tok; @@ -438,16 +438,12 @@ dasd_add_busid(const char *bus_id, int features) return devmap; } -/* - * Find devmap for device with given bus_id. - */ static struct dasd_devmap * -dasd_find_busid(const char *bus_id) +dasd_find_busid_locked(const char *bus_id) { struct dasd_devmap *devmap, *tmp; int hash; - spin_lock(&dasd_devmap_lock); devmap = ERR_PTR(-ENODEV); hash = dasd_hash_busid(bus_id); list_for_each_entry(tmp, &dasd_hashlists[hash], list) { @@ -456,6 +452,19 @@ dasd_find_busid(const char *bus_id) break; } } + return devmap; +} + +/* + * Find devmap for device with given bus_id. + */ +static struct dasd_devmap * +dasd_find_busid(const char *bus_id) +{ + struct dasd_devmap *devmap; + + spin_lock(&dasd_devmap_lock); + devmap = dasd_find_busid_locked(bus_id); spin_unlock(&dasd_devmap_lock); return devmap; } @@ -585,6 +594,238 @@ dasd_create_device(struct ccw_device *cdev) } /* + * allocate a PPRC data structure and call the discipline function to fill + */ +static int dasd_devmap_get_pprc_status(struct dasd_device *device, + struct dasd_pprc_data_sc4 **data) +{ + struct dasd_pprc_data_sc4 *temp; + + if (!device->discipline || !device->discipline->pprc_status) { + dev_warn(&device->cdev->dev, "Unable to query copy relation status\n"); + return -EOPNOTSUPP; + } + temp = kzalloc(sizeof(*temp), GFP_KERNEL); + if (!temp) + return -ENOMEM; + + /* get PPRC information from storage */ + if (device->discipline->pprc_status(device, temp)) { + dev_warn(&device->cdev->dev, "Error during copy relation status query\n"); + kfree(temp); + return -EINVAL; + } + *data = temp; + + return 0; +} + +/* + * find an entry in a PPRC device_info array by a given UID + * depending on the primary/secondary state of the device it has to be + * matched with the respective fields + */ +static int dasd_devmap_entry_from_pprc_data(struct dasd_pprc_data_sc4 *data, + struct dasd_uid uid, + bool primary) +{ + int i; + + for (i = 0; i < DASD_CP_ENTRIES; i++) { + if (primary) { + if (data->dev_info[i].prim_cu_ssid == uid.ssid && + data->dev_info[i].primary == uid.real_unit_addr) + return i; + } else { + if (data->dev_info[i].sec_cu_ssid == uid.ssid && + data->dev_info[i].secondary == uid.real_unit_addr) + return i; + } + } + return -1; +} + +/* + * check the consistency of a specified copy relation by checking + * the following things: + * + * - is the given device part of a copy pair setup + * - does the state of the device match the state in the PPRC status data + * - does the device UID match with the UID in the PPRC status data + * - to prevent misrouted IO check if the given device is present in all + * related PPRC status data + */ +static int dasd_devmap_check_copy_relation(struct dasd_device *device, + struct dasd_copy_entry *entry, + struct dasd_pprc_data_sc4 *data, + struct dasd_copy_relation *copy) +{ + struct dasd_pprc_data_sc4 *tmp_dat; + struct dasd_device *tmp_dev; + struct dasd_uid uid; + int i, j; + + if (!device->discipline || !device->discipline->get_uid || + device->discipline->get_uid(device, &uid)) + return 1; + + i = dasd_devmap_entry_from_pprc_data(data, uid, entry->primary); + if (i < 0) { + dev_warn(&device->cdev->dev, "Device not part of a copy relation\n"); + return 1; + } + + /* double check which role the current device has */ + if (entry->primary) { + if (data->dev_info[i].flags & 0x80) { + dev_warn(&device->cdev->dev, "Copy pair secondary is setup as primary\n"); + return 1; + } + if (data->dev_info[i].prim_cu_ssid != uid.ssid || + data->dev_info[i].primary != uid.real_unit_addr) { + dev_warn(&device->cdev->dev, + "Primary device %s does not match copy pair status primary device %04x\n", + dev_name(&device->cdev->dev), + data->dev_info[i].prim_cu_ssid | + data->dev_info[i].primary); + return 1; + } + } else { + if (!(data->dev_info[i].flags & 0x80)) { + dev_warn(&device->cdev->dev, "Copy pair primary is setup as secondary\n"); + return 1; + } + if (data->dev_info[i].sec_cu_ssid != uid.ssid || + data->dev_info[i].secondary != uid.real_unit_addr) { + dev_warn(&device->cdev->dev, + "Secondary device %s does not match copy pair status secondary device %04x\n", + dev_name(&device->cdev->dev), + data->dev_info[i].sec_cu_ssid | + data->dev_info[i].secondary); + return 1; + } + } + + /* + * the current device has to be part of the copy relation of all + * entries to prevent misrouted IO to another copy pair + */ + for (j = 0; j < DASD_CP_ENTRIES; j++) { + if (entry == ©->entry[j]) + tmp_dev = device; + else + tmp_dev = copy->entry[j].device; + + if (!tmp_dev) + continue; + + if (dasd_devmap_get_pprc_status(tmp_dev, &tmp_dat)) + return 1; + + if (dasd_devmap_entry_from_pprc_data(tmp_dat, uid, entry->primary) < 0) { + dev_warn(&tmp_dev->cdev->dev, + "Copy pair relation does not contain device: %s\n", + dev_name(&device->cdev->dev)); + kfree(tmp_dat); + return 1; + } + kfree(tmp_dat); + } + return 0; +} + +/* delete device from copy relation entry */ +static void dasd_devmap_delete_copy_relation_device(struct dasd_device *device) +{ + struct dasd_copy_relation *copy; + int i; + + if (!device->copy) + return; + + copy = device->copy; + for (i = 0; i < DASD_CP_ENTRIES; i++) { + if (copy->entry[i].device == device) + copy->entry[i].device = NULL; + } + dasd_put_device(device); + device->copy = NULL; +} + +/* + * read all required information for a copy relation setup and setup the device + * accordingly + */ +int dasd_devmap_set_device_copy_relation(struct ccw_device *cdev, + bool pprc_enabled) +{ + struct dasd_pprc_data_sc4 *data = NULL; + struct dasd_copy_entry *entry = NULL; + struct dasd_copy_relation *copy; + struct dasd_devmap *devmap; + struct dasd_device *device; + int i, rc = 0; + + devmap = dasd_devmap_from_cdev(cdev); + if (IS_ERR(devmap)) + return PTR_ERR(devmap); + + device = devmap->device; + if (!device) + return -ENODEV; + + copy = devmap->copy; + /* no copy pair setup for this device */ + if (!copy) + goto out; + + rc = dasd_devmap_get_pprc_status(device, &data); + if (rc) + return rc; + + /* print error if PPRC is requested but not enabled on storage server */ + if (!pprc_enabled) { + dev_err(&cdev->dev, "Copy relation not enabled on storage server\n"); + rc = -EINVAL; + goto out; + } + + if (!data->dev_info[0].state) { + dev_warn(&device->cdev->dev, "Copy pair setup requested for device not in copy relation\n"); + rc = -EINVAL; + goto out; + } + /* find entry */ + for (i = 0; i < DASD_CP_ENTRIES; i++) { + if (copy->entry[i].configured && + strncmp(dev_name(&cdev->dev), + copy->entry[i].busid, DASD_BUS_ID_SIZE) == 0) { + entry = ©->entry[i]; + break; + } + } + if (!entry) { + dev_warn(&device->cdev->dev, "Copy relation entry not found\n"); + rc = -EINVAL; + goto out; + } + /* check if the copy relation is valid */ + if (dasd_devmap_check_copy_relation(device, entry, data, copy)) { + dev_warn(&device->cdev->dev, "Copy relation faulty\n"); + rc = -EINVAL; + goto out; + } + + dasd_get_device(device); + copy->entry[i].device = device; + device->copy = copy; +out: + kfree(data); + return rc; +} +EXPORT_SYMBOL_GPL(dasd_devmap_set_device_copy_relation); + +/* * Wait queue for dasd_delete_device waits. */ static DECLARE_WAIT_QUEUE_HEAD(dasd_delete_wq); @@ -617,6 +858,8 @@ dasd_delete_device(struct dasd_device *device) dev_set_drvdata(&device->cdev->dev, NULL); spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags); + /* Removve copy relation */ + dasd_devmap_delete_copy_relation_device(device); /* * Drop ref_count by 3, one for the devmap reference, one for * the cdev reference and one for the passed reference. @@ -694,6 +937,7 @@ void dasd_add_link_to_gendisk(struct gendisk *gdp, struct dasd_device *device) gdp->private_data = devmap; spin_unlock(&dasd_devmap_lock); } +EXPORT_SYMBOL(dasd_add_link_to_gendisk); struct dasd_device *dasd_device_from_gendisk(struct gendisk *gdp) { @@ -1334,7 +1578,6 @@ dasd_timeout_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct dasd_device *device; - struct request_queue *q; unsigned long val; device = dasd_device_from_cdev(to_ccwdev(dev)); @@ -1346,15 +1589,13 @@ dasd_timeout_store(struct device *dev, struct device_attribute *attr, dasd_put_device(device); return -EINVAL; } - q = device->block->request_queue; - if (!q) { + if (!device->block->gdp) { dasd_put_device(device); return -ENODEV; } device->blk_timeout = val; - - blk_queue_rq_timeout(q, device->blk_timeout * HZ); + blk_queue_rq_timeout(device->block->gdp->queue, val * HZ); dasd_put_device(device); return count; @@ -1683,6 +1924,347 @@ dasd_path_fcs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) static struct kobj_attribute path_fcs_attribute = __ATTR(fc_security, 0444, dasd_path_fcs_show, NULL); +/* + * print copy relation in the form + * primary,secondary[1] primary,secondary[2], ... + */ +static ssize_t +dasd_copy_pair_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + char prim_busid[DASD_BUS_ID_SIZE]; + struct dasd_copy_relation *copy; + struct dasd_devmap *devmap; + int len = 0; + int i; + + devmap = dasd_find_busid(dev_name(dev)); + if (IS_ERR(devmap)) + return -ENODEV; + + if (!devmap->copy) + return -ENODEV; + + copy = devmap->copy; + /* find primary */ + for (i = 0; i < DASD_CP_ENTRIES; i++) { + if (copy->entry[i].configured && copy->entry[i].primary) { + strscpy(prim_busid, copy->entry[i].busid, + DASD_BUS_ID_SIZE); + break; + } + } + if (!copy->entry[i].primary) + goto out; + + /* print all secondary */ + for (i = 0; i < DASD_CP_ENTRIES; i++) { + if (copy->entry[i].configured && !copy->entry[i].primary) + len += sysfs_emit_at(buf, len, "%s,%s ", prim_busid, + copy->entry[i].busid); + } + + len += sysfs_emit_at(buf, len, "\n"); +out: + return len; +} + +static int dasd_devmap_set_copy_relation(struct dasd_devmap *devmap, + struct dasd_copy_relation *copy, + char *busid, bool primary) +{ + int i; + + /* find free entry */ + for (i = 0; i < DASD_CP_ENTRIES; i++) { + /* current bus_id already included, nothing to do */ + if (copy->entry[i].configured && + strncmp(copy->entry[i].busid, busid, DASD_BUS_ID_SIZE) == 0) + return 0; + + if (!copy->entry[i].configured) + break; + } + if (i == DASD_CP_ENTRIES) + return -EINVAL; + + copy->entry[i].configured = true; + strscpy(copy->entry[i].busid, busid, DASD_BUS_ID_SIZE); + if (primary) { + copy->active = ©->entry[i]; + copy->entry[i].primary = true; + } + if (!devmap->copy) + devmap->copy = copy; + + return 0; +} + +static void dasd_devmap_del_copy_relation(struct dasd_copy_relation *copy, + char *busid) +{ + int i; + + spin_lock(&dasd_devmap_lock); + /* find entry */ + for (i = 0; i < DASD_CP_ENTRIES; i++) { + if (copy->entry[i].configured && + strncmp(copy->entry[i].busid, busid, DASD_BUS_ID_SIZE) == 0) + break; + } + if (i == DASD_CP_ENTRIES || !copy->entry[i].configured) { + spin_unlock(&dasd_devmap_lock); + return; + } + + copy->entry[i].configured = false; + memset(copy->entry[i].busid, 0, DASD_BUS_ID_SIZE); + if (copy->active == ©->entry[i]) { + copy->active = NULL; + copy->entry[i].primary = false; + } + spin_unlock(&dasd_devmap_lock); +} + +static int dasd_devmap_clear_copy_relation(struct device *dev) +{ + struct dasd_copy_relation *copy; + struct dasd_devmap *devmap; + int i, rc = 1; + + devmap = dasd_devmap_from_cdev(to_ccwdev(dev)); + if (IS_ERR(devmap)) + return 1; + + spin_lock(&dasd_devmap_lock); + if (!devmap->copy) + goto out; + + copy = devmap->copy; + /* first check if all secondary devices are offline*/ + for (i = 0; i < DASD_CP_ENTRIES; i++) { + if (!copy->entry[i].configured) + continue; + + if (copy->entry[i].device == copy->active->device) + continue; + + if (copy->entry[i].device) + goto out; + } + /* clear all devmap entries */ + for (i = 0; i < DASD_CP_ENTRIES; i++) { + if (strlen(copy->entry[i].busid) == 0) + continue; + if (copy->entry[i].device) { + dasd_put_device(copy->entry[i].device); + copy->entry[i].device->copy = NULL; + copy->entry[i].device = NULL; + } + devmap = dasd_find_busid_locked(copy->entry[i].busid); + devmap->copy = NULL; + memset(copy->entry[i].busid, 0, DASD_BUS_ID_SIZE); + } + kfree(copy); + rc = 0; +out: + spin_unlock(&dasd_devmap_lock); + return rc; +} + +/* + * parse BUSIDs from a copy pair + */ +static int dasd_devmap_parse_busid(const char *buf, char *prim_busid, + char *sec_busid) +{ + char *primary, *secondary, *tmp, *pt; + int id0, id1, id2; + + pt = kstrdup(buf, GFP_KERNEL); + tmp = pt; + if (!tmp) + return -ENOMEM; + + primary = strsep(&tmp, ","); + if (!primary) { + kfree(pt); + return -EINVAL; + } + secondary = strsep(&tmp, ","); + if (!secondary) { + kfree(pt); + return -EINVAL; + } + if (dasd_busid(primary, &id0, &id1, &id2)) { + kfree(pt); + return -EINVAL; + } + sprintf(prim_busid, "%01x.%01x.%04x", id0, id1, id2); + if (dasd_busid(secondary, &id0, &id1, &id2)) { + kfree(pt); + return -EINVAL; + } + sprintf(sec_busid, "%01x.%01x.%04x", id0, id1, id2); + kfree(pt); + + return 0; +} + +static ssize_t dasd_copy_pair_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct dasd_devmap *prim_devmap, *sec_devmap; + char prim_busid[DASD_BUS_ID_SIZE]; + char sec_busid[DASD_BUS_ID_SIZE]; + struct dasd_copy_relation *copy; + struct dasd_device *device; + bool pprc_enabled; + int rc; + + if (strncmp(buf, "clear", strlen("clear")) == 0) { + if (dasd_devmap_clear_copy_relation(dev)) + return -EINVAL; + return count; + } + + rc = dasd_devmap_parse_busid(buf, prim_busid, sec_busid); + if (rc) + return rc; + + if (strncmp(dev_name(dev), prim_busid, DASD_BUS_ID_SIZE) != 0 && + strncmp(dev_name(dev), sec_busid, DASD_BUS_ID_SIZE) != 0) + return -EINVAL; + + /* allocate primary devmap if needed */ + prim_devmap = dasd_find_busid(prim_busid); + if (IS_ERR(prim_devmap)) + prim_devmap = dasd_add_busid(prim_busid, DASD_FEATURE_DEFAULT); + + /* allocate secondary devmap if needed */ + sec_devmap = dasd_find_busid(sec_busid); + if (IS_ERR(sec_devmap)) + sec_devmap = dasd_add_busid(sec_busid, DASD_FEATURE_DEFAULT); + + /* setting copy relation is only allowed for offline secondary */ + if (sec_devmap->device) + return -EINVAL; + + if (prim_devmap->copy) { + copy = prim_devmap->copy; + } else if (sec_devmap->copy) { + copy = sec_devmap->copy; + } else { + copy = kzalloc(sizeof(*copy), GFP_KERNEL); + if (!copy) + return -ENOMEM; + } + spin_lock(&dasd_devmap_lock); + rc = dasd_devmap_set_copy_relation(prim_devmap, copy, prim_busid, true); + if (rc) { + spin_unlock(&dasd_devmap_lock); + return rc; + } + rc = dasd_devmap_set_copy_relation(sec_devmap, copy, sec_busid, false); + if (rc) { + spin_unlock(&dasd_devmap_lock); + return rc; + } + spin_unlock(&dasd_devmap_lock); + + /* if primary device is already online call device setup directly */ + if (prim_devmap->device && !prim_devmap->device->copy) { + device = prim_devmap->device; + if (device->discipline->pprc_enabled) { + pprc_enabled = device->discipline->pprc_enabled(device); + rc = dasd_devmap_set_device_copy_relation(device->cdev, + pprc_enabled); + } else { + rc = -EOPNOTSUPP; + } + } + if (rc) { + dasd_devmap_del_copy_relation(copy, prim_busid); + dasd_devmap_del_copy_relation(copy, sec_busid); + count = rc; + } + + return count; +} +static DEVICE_ATTR(copy_pair, 0644, dasd_copy_pair_show, + dasd_copy_pair_store); + +static ssize_t +dasd_copy_role_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct dasd_copy_relation *copy; + struct dasd_device *device; + int len, i; + + device = dasd_device_from_cdev(to_ccwdev(dev)); + if (IS_ERR(device)) + return -ENODEV; + + if (!device->copy) { + len = sysfs_emit(buf, "none\n"); + goto out; + } + copy = device->copy; + /* only the active device is primary */ + if (copy->active->device == device) { + len = sysfs_emit(buf, "primary\n"); + goto out; + } + for (i = 0; i < DASD_CP_ENTRIES; i++) { + if (copy->entry[i].device == device) { + len = sysfs_emit(buf, "secondary\n"); + goto out; + } + } + /* not in the list, no COPY role */ + len = sysfs_emit(buf, "none\n"); +out: + dasd_put_device(device); + return len; +} +static DEVICE_ATTR(copy_role, 0444, dasd_copy_role_show, NULL); + +static ssize_t dasd_device_ping(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct dasd_device *device; + size_t rc; + + device = dasd_device_from_cdev(to_ccwdev(dev)); + if (IS_ERR(device)) + return -ENODEV; + + /* + * do not try during offline processing + * early check only + * the sleep_on function itself checks for offline + * processing again + */ + if (test_bit(DASD_FLAG_OFFLINE, &device->flags)) { + rc = -EBUSY; + goto out; + } + if (!device->discipline || !device->discipline->device_ping) { + rc = -EOPNOTSUPP; + goto out; + } + rc = device->discipline->device_ping(device); + if (!rc) + rc = count; +out: + dasd_put_device(device); + return rc; +} +static DEVICE_ATTR(ping, 0200, NULL, dasd_device_ping); + #define DASD_DEFINE_ATTR(_name, _func) \ static ssize_t dasd_##_name##_show(struct device *dev, \ struct device_attribute *attr, \ @@ -1739,6 +2321,9 @@ static struct attribute * dasd_attrs[] = { &dev_attr_hpf.attr, &dev_attr_ese.attr, &dev_attr_fc_security.attr, + &dev_attr_copy_pair.attr, + &dev_attr_copy_role.attr, + &dev_attr_ping.attr, NULL, }; diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c index 94ee59864971..f956a4ac9881 100644 --- a/drivers/s390/block/dasd_diag.c +++ b/drivers/s390/block/dasd_diag.c @@ -627,7 +627,7 @@ dasd_diag_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req, static void dasd_diag_setup_blk_queue(struct dasd_block *block) { unsigned int logical_block_size = block->bp_block; - struct request_queue *q = block->request_queue; + struct request_queue *q = block->gdp->queue; int max; max = DIAG_MAX_BLOCKS << block->s2b_shift; diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 3cc93e2e4e15..662730f3b027 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -2013,6 +2013,49 @@ static void dasd_eckd_kick_validate_server(struct dasd_device *device) } /* + * return if the device is the copy relation primary if a copy relation is active + */ +static int dasd_device_is_primary(struct dasd_device *device) +{ + if (!device->copy) + return 1; + + if (device->copy->active->device == device) + return 1; + + return 0; +} + +static int dasd_eckd_alloc_block(struct dasd_device *device) +{ + struct dasd_block *block; + struct dasd_uid temp_uid; + + if (!dasd_device_is_primary(device)) + return 0; + + dasd_eckd_get_uid(device, &temp_uid); + if (temp_uid.type == UA_BASE_DEVICE) { + block = dasd_alloc_block(); + if (IS_ERR(block)) { + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", + "could not allocate dasd block structure"); + return PTR_ERR(block); + } + device->block = block; + block->base = device; + } + return 0; +} + +static bool dasd_eckd_pprc_enabled(struct dasd_device *device) +{ + struct dasd_eckd_private *private = device->private; + + return private->rdc_data.facilities.PPRC_enabled; +} + +/* * Check device characteristics. * If the device is accessible using ECKD discipline, the device is enabled. */ @@ -2020,8 +2063,6 @@ static int dasd_eckd_check_characteristics(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; - struct dasd_block *block; - struct dasd_uid temp_uid; int rc, i; int readonly; unsigned long value; @@ -2079,20 +2120,29 @@ dasd_eckd_check_characteristics(struct dasd_device *device) device->default_expires = value; } - dasd_eckd_get_uid(device, &temp_uid); - if (temp_uid.type == UA_BASE_DEVICE) { - block = dasd_alloc_block(); - if (IS_ERR(block)) { - DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", - "could not allocate dasd " - "block structure"); - rc = PTR_ERR(block); - goto out_err1; - } - device->block = block; - block->base = device; + /* Read Device Characteristics */ + rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC, + &private->rdc_data, 64); + if (rc) { + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, + "Read device characteristic failed, rc=%d", rc); + goto out_err1; + } + + /* setup PPRC for device from devmap */ + rc = dasd_devmap_set_device_copy_relation(device->cdev, + dasd_eckd_pprc_enabled(device)); + if (rc) { + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, + "copy relation setup failed, rc=%d", rc); + goto out_err1; } + /* check if block device is needed and allocate in case */ + rc = dasd_eckd_alloc_block(device); + if (rc) + goto out_err1; + /* register lcu with alias handling, enable PAV */ rc = dasd_alias_make_device_known_to_lcu(device); if (rc) @@ -2117,15 +2167,6 @@ dasd_eckd_check_characteristics(struct dasd_device *device) /* Read Extent Pool Information */ dasd_eckd_read_ext_pool_info(device); - /* Read Device Characteristics */ - rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC, - &private->rdc_data, 64); - if (rc) { - DBF_EVENT_DEVID(DBF_WARNING, device->cdev, - "Read device characteristic failed, rc=%d", rc); - goto out_err3; - } - if ((device->features & DASD_FEATURE_USERAW) && !(private->rdc_data.facilities.RT_in_LR)) { dev_err(&device->cdev->dev, "The storage server does not " @@ -6078,6 +6119,207 @@ static int dasd_hosts_print(struct dasd_device *device, struct seq_file *m) return 0; } +static struct dasd_device +*copy_relation_find_device(struct dasd_copy_relation *copy, + char *busid) +{ + int i; + + for (i = 0; i < DASD_CP_ENTRIES; i++) { + if (copy->entry[i].configured && + strncmp(copy->entry[i].busid, busid, DASD_BUS_ID_SIZE) == 0) + return copy->entry[i].device; + } + return NULL; +} + +/* + * set the new active/primary device + */ +static void copy_pair_set_active(struct dasd_copy_relation *copy, char *new_busid, + char *old_busid) +{ + int i; + + for (i = 0; i < DASD_CP_ENTRIES; i++) { + if (copy->entry[i].configured && + strncmp(copy->entry[i].busid, new_busid, + DASD_BUS_ID_SIZE) == 0) { + copy->active = ©->entry[i]; + copy->entry[i].primary = true; + } else if (copy->entry[i].configured && + strncmp(copy->entry[i].busid, old_busid, + DASD_BUS_ID_SIZE) == 0) { + copy->entry[i].primary = false; + } + } +} + +/* + * The function will swap the role of a given copy pair. + * During the swap operation the relation of the blockdevice is disconnected + * from the old primary and connected to the new. + * + * IO is paused on the block queue before swap and may be resumed afterwards. + */ +static int dasd_eckd_copy_pair_swap(struct dasd_device *device, char *prim_busid, + char *sec_busid) +{ + struct dasd_device *primary, *secondary; + struct dasd_copy_relation *copy; + struct dasd_block *block; + struct gendisk *gdp; + + copy = device->copy; + if (!copy) + return DASD_COPYPAIRSWAP_INVALID; + primary = copy->active->device; + if (!primary) + return DASD_COPYPAIRSWAP_INVALID; + /* double check if swap has correct primary */ + if (strncmp(dev_name(&primary->cdev->dev), prim_busid, DASD_BUS_ID_SIZE) != 0) + return DASD_COPYPAIRSWAP_PRIMARY; + + secondary = copy_relation_find_device(copy, sec_busid); + if (!secondary) + return DASD_COPYPAIRSWAP_SECONDARY; + + /* + * usually the device should be quiesced for swap + * for paranoia stop device and requeue requests again + */ + dasd_device_set_stop_bits(primary, DASD_STOPPED_PPRC); + dasd_device_set_stop_bits(secondary, DASD_STOPPED_PPRC); + dasd_generic_requeue_all_requests(primary); + + /* swap DASD internal device <> block assignment */ + block = primary->block; + primary->block = NULL; + secondary->block = block; + block->base = secondary; + /* set new primary device in COPY relation */ + copy_pair_set_active(copy, sec_busid, prim_busid); + + /* swap blocklayer device link */ + gdp = block->gdp; + dasd_add_link_to_gendisk(gdp, secondary); + + /* re-enable device */ + dasd_device_remove_stop_bits(primary, DASD_STOPPED_PPRC); + dasd_device_remove_stop_bits(secondary, DASD_STOPPED_PPRC); + dasd_schedule_device_bh(secondary); + + return DASD_COPYPAIRSWAP_SUCCESS; +} + +/* + * Perform Subsystem Function - Peer-to-Peer Remote Copy Extended Query + */ +static int dasd_eckd_query_pprc_status(struct dasd_device *device, + struct dasd_pprc_data_sc4 *data) +{ + struct dasd_pprc_data_sc4 *pprc_data; + struct dasd_psf_prssd_data *prssdp; + struct dasd_ccw_req *cqr; + struct ccw1 *ccw; + int rc; + + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1 /* PSF */ + 1 /* RSSD */, + sizeof(*prssdp) + sizeof(*pprc_data) + 1, + device, NULL); + if (IS_ERR(cqr)) { + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", + "Could not allocate query PPRC status request"); + return PTR_ERR(cqr); + } + cqr->startdev = device; + cqr->memdev = device; + cqr->block = NULL; + cqr->retries = 256; + cqr->expires = 10 * HZ; + + /* Prepare for Read Subsystem Data */ + prssdp = (struct dasd_psf_prssd_data *)cqr->data; + memset(prssdp, 0, sizeof(struct dasd_psf_prssd_data)); + prssdp->order = PSF_ORDER_PRSSD; + prssdp->suborder = PSF_SUBORDER_PPRCEQ; + prssdp->varies[0] = PPRCEQ_SCOPE_4; + pprc_data = (struct dasd_pprc_data_sc4 *)(prssdp + 1); + + ccw = cqr->cpaddr; + ccw->cmd_code = DASD_ECKD_CCW_PSF; + ccw->count = sizeof(struct dasd_psf_prssd_data); + ccw->flags |= CCW_FLAG_CC; + ccw->flags |= CCW_FLAG_SLI; + ccw->cda = (__u32)(addr_t)prssdp; + + /* Read Subsystem Data - query host access */ + ccw++; + ccw->cmd_code = DASD_ECKD_CCW_RSSD; + ccw->count = sizeof(*pprc_data); + ccw->flags |= CCW_FLAG_SLI; + ccw->cda = (__u32)(addr_t)pprc_data; + + cqr->buildclk = get_tod_clock(); + cqr->status = DASD_CQR_FILLED; + + rc = dasd_sleep_on_interruptible(cqr); + if (rc == 0) { + *data = *pprc_data; + } else { + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, + "PPRC Extended Query failed with rc=%d\n", + rc); + rc = -EOPNOTSUPP; + } + + dasd_sfree_request(cqr, cqr->memdev); + return rc; +} + +/* + * ECKD NOP - no operation + */ +static int dasd_eckd_nop(struct dasd_device *device) +{ + struct dasd_ccw_req *cqr; + struct ccw1 *ccw; + int rc; + + cqr = dasd_smalloc_request(DASD_ECKD_MAGIC, 1, 1, device, NULL); + if (IS_ERR(cqr)) { + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "%s", + "Could not allocate NOP request"); + return PTR_ERR(cqr); + } + cqr->startdev = device; + cqr->memdev = device; + cqr->block = NULL; + cqr->retries = 1; + cqr->expires = 10 * HZ; + + ccw = cqr->cpaddr; + ccw->cmd_code = DASD_ECKD_CCW_NOP; + ccw->flags |= CCW_FLAG_SLI; + + cqr->buildclk = get_tod_clock(); + cqr->status = DASD_CQR_FILLED; + + rc = dasd_sleep_on_interruptible(cqr); + if (rc != 0) { + DBF_EVENT_DEVID(DBF_WARNING, device->cdev, + "NOP failed with rc=%d\n", rc); + rc = -EOPNOTSUPP; + } + dasd_sfree_request(cqr, cqr->memdev); + return rc; +} + +static int dasd_eckd_device_ping(struct dasd_device *device) +{ + return dasd_eckd_nop(device); +} + /* * Perform Subsystem Function - CUIR response */ @@ -6602,7 +6844,7 @@ static void dasd_eckd_handle_hpf_error(struct dasd_device *device, static void dasd_eckd_setup_blk_queue(struct dasd_block *block) { unsigned int logical_block_size = block->bp_block; - struct request_queue *q = block->request_queue; + struct request_queue *q = block->gdp->queue; struct dasd_device *device = block->base; int max; @@ -6697,6 +6939,10 @@ static struct dasd_discipline dasd_eckd_discipline = { .ext_pool_exhaust = dasd_eckd_ext_pool_exhaust, .ese_format = dasd_eckd_ese_format, .ese_read = dasd_eckd_ese_read, + .pprc_status = dasd_eckd_query_pprc_status, + .pprc_enabled = dasd_eckd_pprc_enabled, + .copy_pair_swap = dasd_eckd_copy_pair_swap, + .device_ping = dasd_eckd_device_ping, }; static int __init diff --git a/drivers/s390/block/dasd_eckd.h b/drivers/s390/block/dasd_eckd.h index a91b265441cc..f9299bd184ba 100644 --- a/drivers/s390/block/dasd_eckd.h +++ b/drivers/s390/block/dasd_eckd.h @@ -13,6 +13,7 @@ /***************************************************************************** * SECTION: CCW Definitions ****************************************************************************/ +#define DASD_ECKD_CCW_NOP 0x03 #define DASD_ECKD_CCW_WRITE 0x05 #define DASD_ECKD_CCW_READ 0x06 #define DASD_ECKD_CCW_WRITE_HOME_ADDRESS 0x09 @@ -66,10 +67,16 @@ * Perform Subsystem Function / Sub-Orders */ #define PSF_SUBORDER_QHA 0x1C /* Query Host Access */ +#define PSF_SUBORDER_PPRCEQ 0x50 /* PPRC Extended Query */ #define PSF_SUBORDER_VSQ 0x52 /* Volume Storage Query */ #define PSF_SUBORDER_LCQ 0x53 /* Logical Configuration Query */ /* + * PPRC Extended Query Scopes + */ +#define PPRCEQ_SCOPE_4 0x04 /* Scope 4 for PPRC Extended Query */ + +/* * CUIR response condition codes */ #define PSF_CUIR_INVALID 0x00 @@ -261,7 +268,7 @@ struct dasd_eckd_characteristics { unsigned char reserved3:8; unsigned char defect_wr:1; unsigned char XRC_supported:1; - unsigned char reserved4:1; + unsigned char PPRC_enabled:1; unsigned char striping:1; unsigned char reserved5:4; unsigned char cfw:1; diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index 60be7f7bf2d1..cddfb01a3dca 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -767,7 +767,7 @@ dasd_fba_dump_sense(struct dasd_device *device, struct dasd_ccw_req * req, static void dasd_fba_setup_blk_queue(struct dasd_block *block) { unsigned int logical_block_size = block->bp_block; - struct request_queue *q = block->request_queue; + struct request_queue *q = block->gdp->queue; unsigned int max_bytes, max_discard_sectors; int max; diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 5a83f0a39901..998a961e1704 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -25,7 +25,14 @@ #include "dasd_int.h" -static struct lock_class_key dasd_bio_compl_lkclass; +static unsigned int queue_depth = 32; +static unsigned int nr_hw_queues = 4; + +module_param(queue_depth, uint, 0444); +MODULE_PARM_DESC(queue_depth, "Default queue depth for new DASD devices"); + +module_param(nr_hw_queues, uint, 0444); +MODULE_PARM_DESC(nr_hw_queues, "Default number of hardware queues for new DASD devices"); /* * Allocate and register gendisk structure for device. @@ -41,10 +48,21 @@ int dasd_gendisk_alloc(struct dasd_block *block) if (base->devindex >= DASD_PER_MAJOR) return -EBUSY; - gdp = blk_mq_alloc_disk_for_queue(block->request_queue, - &dasd_bio_compl_lkclass); - if (!gdp) - return -ENOMEM; + block->tag_set.ops = &dasd_mq_ops; + block->tag_set.cmd_size = sizeof(struct dasd_ccw_req); + block->tag_set.nr_hw_queues = nr_hw_queues; + block->tag_set.queue_depth = queue_depth; + block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + block->tag_set.numa_node = NUMA_NO_NODE; + rc = blk_mq_alloc_tag_set(&block->tag_set); + if (rc) + return rc; + + gdp = blk_mq_alloc_disk(&block->tag_set, block); + if (IS_ERR(gdp)) { + blk_mq_free_tag_set(&block->tag_set); + return PTR_ERR(gdp); + } /* Initialize gendisk structure. */ gdp->major = DASD_MAJOR; @@ -100,6 +118,7 @@ void dasd_gendisk_free(struct dasd_block *block) block->gdp->private_data = NULL; put_disk(block->gdp); block->gdp = NULL; + blk_mq_free_tag_set(&block->tag_set); } } diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 333a399f754e..97adc8a7ae6b 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -260,6 +260,55 @@ struct dasd_uid { }; /* + * PPRC Status data + */ +struct dasd_pprc_header { + __u8 entries; /* 0 Number of device entries */ + __u8 unused; /* 1 unused */ + __u16 entry_length; /* 2-3 Length of device entry */ + __u32 unused2; /* 4-7 unused */ +} __packed; + +struct dasd_pprc_dev_info { + __u8 state; /* 0 Copy State */ + __u8 flags; /* 1 Flags */ + __u8 reserved1[2]; /* 2-3 reserved */ + __u8 prim_lss; /* 4 Primary device LSS */ + __u8 primary; /* 5 Primary device address */ + __u8 sec_lss; /* 6 Secondary device LSS */ + __u8 secondary; /* 7 Secondary device address */ + __u16 pprc_id; /* 8-9 Peer-to-Peer Remote Copy ID */ + __u8 reserved2[12]; /* 10-21 reserved */ + __u16 prim_cu_ssid; /* 22-23 Pimary Control Unit SSID */ + __u8 reserved3[12]; /* 24-35 reserved */ + __u16 sec_cu_ssid; /* 36-37 Secondary Control Unit SSID */ + __u8 reserved4[90]; /* 38-127 reserved */ +} __packed; + +struct dasd_pprc_data_sc4 { + struct dasd_pprc_header header; + struct dasd_pprc_dev_info dev_info[5]; +} __packed; + +#define DASD_BUS_ID_SIZE 20 +#define DASD_CP_ENTRIES 5 + +struct dasd_copy_entry { + char busid[DASD_BUS_ID_SIZE]; + struct dasd_device *device; + bool primary; + bool configured; +}; + +struct dasd_copy_relation { + struct dasd_copy_entry entry[DASD_CP_ENTRIES]; + struct dasd_copy_entry *active; +}; + +int dasd_devmap_set_device_copy_relation(struct ccw_device *, + bool pprc_enabled); + +/* * the struct dasd_discipline is * sth like a table of virtual functions, if you think of dasd_eckd * inheriting dasd... @@ -387,6 +436,10 @@ struct dasd_discipline { struct dasd_ccw_req *(*ese_format)(struct dasd_device *, struct dasd_ccw_req *, struct irb *); int (*ese_read)(struct dasd_ccw_req *, struct irb *); + int (*pprc_status)(struct dasd_device *, struct dasd_pprc_data_sc4 *); + bool (*pprc_enabled)(struct dasd_device *); + int (*copy_pair_swap)(struct dasd_device *, char *, char *); + int (*device_ping)(struct dasd_device *); }; extern struct dasd_discipline *dasd_diag_discipline_pointer; @@ -583,12 +636,12 @@ struct dasd_device { struct dasd_profile profile; struct dasd_format_entry format_entry; struct kset *paths_info; + struct dasd_copy_relation *copy; }; struct dasd_block { /* Block device stuff. */ struct gendisk *gdp; - struct request_queue *request_queue; spinlock_t request_queue_lock; struct blk_mq_tag_set tag_set; struct block_device *bdev; @@ -629,6 +682,7 @@ struct dasd_queue { #define DASD_STOPPED_PENDING 4 /* long busy */ #define DASD_STOPPED_DC_WAIT 8 /* disconnected, wait */ #define DASD_STOPPED_SU 16 /* summary unit check handling */ +#define DASD_STOPPED_PPRC 32 /* PPRC swap */ #define DASD_STOPPED_NOSPC 128 /* no space left */ /* per device flags */ @@ -654,6 +708,22 @@ struct dasd_queue { void dasd_put_device_wake(struct dasd_device *); /* + * return values to be returned from the copy pair swap function + * 0x00: swap successful + * 0x01: swap data invalid + * 0x02: no active device found + * 0x03: wrong primary specified + * 0x04: secondary device not found + * 0x05: swap already running + */ +#define DASD_COPYPAIRSWAP_SUCCESS 0 +#define DASD_COPYPAIRSWAP_INVALID 1 +#define DASD_COPYPAIRSWAP_NOACTIVE 2 +#define DASD_COPYPAIRSWAP_PRIMARY 3 +#define DASD_COPYPAIRSWAP_SECONDARY 4 +#define DASD_COPYPAIRSWAP_MULTIPLE 5 + +/* * Reference count inliners */ static inline void @@ -779,6 +849,7 @@ extern debug_info_t *dasd_debug_area; extern struct dasd_profile dasd_global_profile; extern unsigned int dasd_global_profile_level; extern const struct block_device_operations dasd_device_operations; +extern struct blk_mq_ops dasd_mq_ops; extern struct kmem_cache *dasd_page_cache; @@ -837,6 +908,8 @@ int dasd_generic_verify_path(struct dasd_device *, __u8); void dasd_generic_space_exhaust(struct dasd_device *, struct dasd_ccw_req *); void dasd_generic_space_avail(struct dasd_device *); +int dasd_generic_requeue_all_requests(struct dasd_device *); + int dasd_generic_read_dev_chars(struct dasd_device *, int, void *, int); char *dasd_get_sense(struct irb *); diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 95349f95758c..d0ddf2cc9786 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -379,6 +379,56 @@ out_err: return rc; } +/* + * Swap driver iternal copy relation. + */ +static int +dasd_ioctl_copy_pair_swap(struct block_device *bdev, void __user *argp) +{ + struct dasd_copypair_swap_data_t data; + struct dasd_device *device; + int rc; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + device = dasd_device_from_gendisk(bdev->bd_disk); + if (!device) + return -ENODEV; + + if (copy_from_user(&data, argp, sizeof(struct dasd_copypair_swap_data_t))) { + dasd_put_device(device); + return -EFAULT; + } + if (memchr_inv(data.reserved, 0, sizeof(data.reserved))) { + pr_warn("%s: Ivalid swap data specified.\n", + dev_name(&device->cdev->dev)); + dasd_put_device(device); + return DASD_COPYPAIRSWAP_INVALID; + } + if (bdev_is_partition(bdev)) { + pr_warn("%s: The specified DASD is a partition and cannot be swapped\n", + dev_name(&device->cdev->dev)); + dasd_put_device(device); + return DASD_COPYPAIRSWAP_INVALID; + } + if (!device->copy) { + pr_warn("%s: The specified DASD has no copy pair set up\n", + dev_name(&device->cdev->dev)); + dasd_put_device(device); + return -ENODEV; + } + if (!device->discipline->copy_pair_swap) { + dasd_put_device(device); + return -EOPNOTSUPP; + } + rc = device->discipline->copy_pair_swap(device, data.primary, + data.secondary); + dasd_put_device(device); + + return rc; +} + #ifdef CONFIG_DASD_PROFILE /* * Reset device profile information @@ -637,6 +687,9 @@ int dasd_ioctl(struct block_device *bdev, fmode_t mode, case BIODASDRAS: rc = dasd_ioctl_release_space(bdev, argp); break; + case BIODASDCOPYPAIRSWAP: + rc = dasd_ioctl_copy_pair_swap(bdev, argp); + break; default: /* if the discipline has an ioctl method try it. */ rc = -ENOTTY; diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 6c8c41fac4e1..ee82207b4e60 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -984,6 +984,11 @@ static ssize_t assign_adapter_store(struct device *dev, goto done; } + if (test_bit_inv(apid, matrix_mdev->matrix.apm)) { + ret = count; + goto done; + } + set_bit_inv(apid, matrix_mdev->matrix.apm); ret = vfio_ap_mdev_validate_masks(matrix_mdev); @@ -1109,6 +1114,11 @@ static ssize_t unassign_adapter_store(struct device *dev, goto done; } + if (!test_bit_inv(apid, matrix_mdev->matrix.apm)) { + ret = count; + goto done; + } + clear_bit_inv((unsigned long)apid, matrix_mdev->matrix.apm); vfio_ap_mdev_hot_unplug_adapter(matrix_mdev, apid); ret = count; @@ -1183,6 +1193,11 @@ static ssize_t assign_domain_store(struct device *dev, goto done; } + if (test_bit_inv(apqi, matrix_mdev->matrix.aqm)) { + ret = count; + goto done; + } + set_bit_inv(apqi, matrix_mdev->matrix.aqm); ret = vfio_ap_mdev_validate_masks(matrix_mdev); @@ -1286,6 +1301,11 @@ static ssize_t unassign_domain_store(struct device *dev, goto done; } + if (!test_bit_inv(apqi, matrix_mdev->matrix.aqm)) { + ret = count; + goto done; + } + clear_bit_inv((unsigned long)apqi, matrix_mdev->matrix.aqm); vfio_ap_mdev_hot_unplug_domain(matrix_mdev, apqi); ret = count; @@ -1329,6 +1349,11 @@ static ssize_t assign_control_domain_store(struct device *dev, goto done; } + if (test_bit_inv(id, matrix_mdev->matrix.adm)) { + ret = count; + goto done; + } + /* Set the bit in the ADM (bitmask) corresponding to the AP control * domain number (id). The bits in the mask, from most significant to * least significant, correspond to IDs 0 up to the one less than the @@ -1378,6 +1403,11 @@ static ssize_t unassign_control_domain_store(struct device *dev, goto done; } + if (!test_bit_inv(domid, matrix_mdev->matrix.adm)) { + ret = count; + goto done; + } + clear_bit_inv(domid, matrix_mdev->matrix.adm); if (test_bit_inv(domid, matrix_mdev->shadow_apcb.adm)) { diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 70e401fd432a..c37027276162 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -3537,7 +3537,7 @@ static struct attribute *host_v2_hw_attrs[] = { ATTRIBUTE_GROUPS(host_v2_hw); -static int map_queues_v2_hw(struct Scsi_Host *shost) +static void map_queues_v2_hw(struct Scsi_Host *shost) { struct hisi_hba *hisi_hba = shost_priv(shost); struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; @@ -3552,9 +3552,6 @@ static int map_queues_v2_hw(struct Scsi_Host *shost) for_each_cpu(cpu, mask) qmap->mq_map[cpu] = qmap->queue_offset + queue; } - - return 0; - } static struct scsi_host_template sht_v2_hw = { diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index efe8c5be5870..d716e5632d0f 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -3171,13 +3171,12 @@ static int debugfs_set_bist_v3_hw(struct hisi_hba *hisi_hba, bool enable) return 0; } -static int hisi_sas_map_queues(struct Scsi_Host *shost) +static void hisi_sas_map_queues(struct Scsi_Host *shost) { struct hisi_hba *hisi_hba = shost_priv(shost); struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; - return blk_mq_pci_map_queues(qmap, hisi_hba->pci_dev, - BASE_VECTORS_V3_HW); + blk_mq_pci_map_queues(qmap, hisi_hba->pci_dev, BASE_VECTORS_V3_HW); } static struct scsi_host_template sht_v3_hw = { diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index f6c37a97544e..4ae85d590801 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -3174,7 +3174,7 @@ megasas_bios_param(struct scsi_device *sdev, struct block_device *bdev, return 0; } -static int megasas_map_queues(struct Scsi_Host *shost) +static void megasas_map_queues(struct Scsi_Host *shost) { struct megasas_instance *instance; int qoff = 0, offset; @@ -3183,7 +3183,7 @@ static int megasas_map_queues(struct Scsi_Host *shost) instance = (struct megasas_instance *)shost->hostdata; if (shost->nr_hw_queues == 1) - return 0; + return; offset = instance->low_latency_index_start; @@ -3209,8 +3209,6 @@ static int megasas_map_queues(struct Scsi_Host *shost) map->queue_offset = qoff; blk_mq_map_queues(map); } - - return 0; } static void megasas_aen_polling(struct work_struct *work); diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index bfa1165e23b6..9681c8bf24ed 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -3464,7 +3464,7 @@ static int mpi3mr_bios_param(struct scsi_device *sdev, * * Return: return zero. */ -static int mpi3mr_map_queues(struct Scsi_Host *shost) +static void mpi3mr_map_queues(struct Scsi_Host *shost) { struct mpi3mr_ioc *mrioc = shost_priv(shost); int i, qoff, offset; @@ -3500,9 +3500,6 @@ static int mpi3mr_map_queues(struct Scsi_Host *shost) qoff += map->nr_queues; offset += map->nr_queues; } - - return 0; - } /** diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 565339a0811d..331e896d8225 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2993,7 +2993,7 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4 || ioc->use_32bit_dma || - dma_get_required_mask(&pdev->dev) <= 32) + dma_get_required_mask(&pdev->dev) <= DMA_BIT_MASK(32)) ioc->dma_mask = 32; /* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */ else if (ioc->hba_mpi_version_belonged > MPI2_VERSION) diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index bd6a5f1bd532..791a406b4f8e 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -11872,7 +11872,7 @@ out: * scsih_map_queues - map reply queues with request queues * @shost: SCSI host pointer */ -static int scsih_map_queues(struct Scsi_Host *shost) +static void scsih_map_queues(struct Scsi_Host *shost) { struct MPT3SAS_ADAPTER *ioc = (struct MPT3SAS_ADAPTER *)shost->hostdata; @@ -11882,7 +11882,7 @@ static int scsih_map_queues(struct Scsi_Host *shost) int iopoll_q_count = ioc->reply_queue_count - nr_msix_vectors; if (shost->nr_hw_queues == 1) - return 0; + return; for (i = 0, qoff = 0; i < shost->nr_maps; i++) { map = &shost->tag_set.map[i]; @@ -11910,7 +11910,6 @@ static int scsih_map_queues(struct Scsi_Host *shost) qoff += map->nr_queues; } - return 0; } /* shost template for SAS 2.0 HBA devices */ diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index a0028e130a7e..2ff2fac1e403 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -81,7 +81,7 @@ LIST_HEAD(hba_list); struct workqueue_struct *pm8001_wq; -static int pm8001_map_queues(struct Scsi_Host *shost) +static void pm8001_map_queues(struct Scsi_Host *shost) { struct sas_ha_struct *sha = SHOST_TO_SAS_HA(shost); struct pm8001_hba_info *pm8001_ha = sha->lldd_ha; diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 3d6b137314f3..bbc4d5890ae6 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -3686,11 +3686,6 @@ err2: err1: scsi_host_put(lport->host); err0: - if (qedf) { - QEDF_INFO(&qedf->dbg_ctx, QEDF_LOG_DISC, "Probe done.\n"); - - clear_bit(QEDF_PROBING, &qedf->flags); - } return rc; } diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 7450c3458be7..02fdeb0d31ec 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -684,12 +684,8 @@ static void qla_nvme_map_queues(struct nvme_fc_local_port *lport, struct blk_mq_queue_map *map) { struct scsi_qla_host *vha = lport->private; - int rc; - rc = blk_mq_pci_map_queues(map, vha->hw->pdev, vha->irq_offset); - if (rc) - ql_log(ql_log_warn, vha, 0x21de, - "pci map queue failed 0x%x", rc); + blk_mq_pci_map_queues(map, vha->hw->pdev, vha->irq_offset); } static void qla_nvme_localport_delete(struct nvme_fc_local_port *lport) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 0bd0fd1042df..87a93892deac 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -350,7 +350,7 @@ MODULE_PARM_DESC(ql2xrspq_follow_inptr_legacy, static void qla2x00_clear_drv_active(struct qla_hw_data *); static void qla2x00_free_device(scsi_qla_host_t *); -static int qla2xxx_map_queues(struct Scsi_Host *shost); +static void qla2xxx_map_queues(struct Scsi_Host *shost); static void qla2x00_destroy_deferred_work(struct qla_hw_data *); u32 ql2xnvme_queues = DEF_NVME_HW_QUEUES; @@ -7994,17 +7994,15 @@ qla_pci_reset_done(struct pci_dev *pdev) clear_bit(ABORT_ISP_ACTIVE, &base_vha->dpc_flags); } -static int qla2xxx_map_queues(struct Scsi_Host *shost) +static void qla2xxx_map_queues(struct Scsi_Host *shost) { - int rc; scsi_qla_host_t *vha = (scsi_qla_host_t *)shost->hostdata; struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; if (USER_CTRL_IRQ(vha->hw) || !vha->hw->mqiobase) - rc = blk_mq_map_queues(qmap); + blk_mq_map_queues(qmap); else - rc = blk_mq_pci_map_queues(qmap, vha->hw->pdev, vha->irq_offset); - return rc; + blk_mq_pci_map_queues(qmap, vha->hw->pdev, vha->irq_offset); } struct scsi_host_template qla2xxx_driver_template = { diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 62666df1a59e..4acff4e84b90 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -2151,8 +2151,10 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha, abort_cmd = ha->tgt.tgt_ops->find_cmd_by_tag(sess, le32_to_cpu(abts->exchange_addr_to_abort)); - if (!abort_cmd) + if (!abort_cmd) { + mempool_free(mcmd, qla_tgt_mgmt_cmd_mempool); return -EIO; + } mcmd->unpacked_lun = abort_cmd->se_cmd.orig_fe_lun; if (abort_cmd->qpair) { diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index b8a76b89f85a..697fc57bc711 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -7474,12 +7474,12 @@ static int resp_not_ready(struct scsi_cmnd *scp, struct sdebug_dev_info *devip) return check_condition_result; } -static int sdebug_map_queues(struct Scsi_Host *shost) +static void sdebug_map_queues(struct Scsi_Host *shost) { int i, qoff; if (shost->nr_hw_queues == 1) - return 0; + return; for (i = 0, qoff = 0; i < HCTX_MAX_TYPES; i++) { struct blk_mq_queue_map *map = &shost->tag_set.map[i]; @@ -7501,9 +7501,6 @@ static int sdebug_map_queues(struct Scsi_Host *shost) qoff += map->nr_queues; } - - return 0; - } static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 96e7e3eaca29..d7ec4ab2b111 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1856,13 +1856,13 @@ static int scsi_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, return 0; } -static int scsi_map_queues(struct blk_mq_tag_set *set) +static void scsi_map_queues(struct blk_mq_tag_set *set) { struct Scsi_Host *shost = container_of(set, struct Scsi_Host, tag_set); if (shost->hostt->map_queues) return shost->hostt->map_queues(shost); - return blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); + blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); } void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q) diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 7a8c2c75acba..b971fbe3b3a1 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -6436,12 +6436,12 @@ static int pqi_slave_alloc(struct scsi_device *sdev) return 0; } -static int pqi_map_queues(struct Scsi_Host *shost) +static void pqi_map_queues(struct Scsi_Host *shost) { struct pqi_ctrl_info *ctrl_info = shost_to_hba(shost); - return blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], - ctrl_info->pci_dev, 0); + blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], + ctrl_info->pci_dev, 0); } static inline bool pqi_is_tape_changer_device(struct pqi_scsi_dev *device) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 578c4b6d0f7d..077a8e24bd28 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -711,12 +711,12 @@ static int virtscsi_abort(struct scsi_cmnd *sc) return virtscsi_tmf(vscsi, cmd); } -static int virtscsi_map_queues(struct Scsi_Host *shost) +static void virtscsi_map_queues(struct Scsi_Host *shost) { struct virtio_scsi *vscsi = shost_priv(shost); struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; - return blk_mq_virtio_map_queues(qmap, vscsi->vdev, 2); + blk_mq_virtio_map_queues(qmap, vscsi->vdev, 2); } static void virtscsi_commit_rqs(struct Scsi_Host *shost, u16 hwq) diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index ae38f0d25a8d..572b5896caa3 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -2529,6 +2529,7 @@ struct tb *icm_probe(struct tb_nhi *nhi) tb->cm_ops = &icm_icl_ops; break; + case PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_2C_NHI: case PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_4C_NHI: icm->is_supported = icm_tgl_is_supported; icm->get_mode = icm_ar_get_mode; diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index f09da5b62233..01190d9ced16 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -55,6 +55,7 @@ extern const struct tb_nhi_ops icl_nhi_ops; * need for the PCI quirk anymore as we will use ICM also on Apple * hardware. */ +#define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_2C_NHI 0x1134 #define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_4C_NHI 0x1137 #define PCI_DEVICE_ID_INTEL_WIN_RIDGE_2C_NHI 0x157d #define PCI_DEVICE_ID_INTEL_WIN_RIDGE_2C_BRIDGE 0x157e diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 0dcecbbc3967..f7fbef83583c 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -1334,6 +1334,7 @@ static int omap8250_probe(struct platform_device *pdev) up.port.throttle = omap_8250_throttle; up.port.unthrottle = omap_8250_unthrottle; up.port.rs485_config = serial8250_em485_config; + up.port.rs485_supported = serial8250_em485_supported; up.rs485_start_tx = serial8250_em485_start_tx; up.rs485_stop_tx = serial8250_em485_stop_tx; up.port.has_sysrq = IS_ENABLED(CONFIG_SERIAL_8250_CONSOLE); diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index b20f6f2fa51c..fbc4b071b330 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2724,14 +2724,15 @@ static int lpuart_probe(struct platform_device *pdev) lpuart_reg.cons = LPUART_CONSOLE; handler = lpuart_int; } - ret = uart_add_one_port(&lpuart_reg, &sport->port); - if (ret) - goto failed_attach_port; ret = lpuart_global_reset(sport); if (ret) goto failed_reset; + ret = uart_add_one_port(&lpuart_reg, &sport->port); + if (ret) + goto failed_attach_port; + ret = uart_get_rs485_mode(&sport->port); if (ret) goto failed_get_rs485; @@ -2747,9 +2748,9 @@ static int lpuart_probe(struct platform_device *pdev) failed_irq_request: failed_get_rs485: -failed_reset: uart_remove_one_port(&lpuart_reg, &sport->port); failed_attach_port: +failed_reset: lpuart_disable_clks(sport); return ret; } diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index ad4f3567ff90..a5748e41483b 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -525,7 +525,7 @@ static void tegra_uart_tx_dma_complete(void *args) count = tup->tx_bytes_requested - state.residue; async_tx_ack(tup->tx_dma_desc); spin_lock_irqsave(&tup->uport.lock, flags); - xmit->tail = (xmit->tail + count) & (UART_XMIT_SIZE - 1); + uart_xmit_advance(&tup->uport, count); tup->tx_in_progress = 0; if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) uart_write_wakeup(&tup->uport); @@ -613,7 +613,6 @@ static unsigned int tegra_uart_tx_empty(struct uart_port *u) static void tegra_uart_stop_tx(struct uart_port *u) { struct tegra_uart_port *tup = to_tegra_uport(u); - struct circ_buf *xmit = &tup->uport.state->xmit; struct dma_tx_state state; unsigned int count; @@ -624,7 +623,7 @@ static void tegra_uart_stop_tx(struct uart_port *u) dmaengine_tx_status(tup->tx_dma_chan, tup->tx_cookie, &state); count = tup->tx_bytes_requested - state.residue; async_tx_ack(tup->tx_dma_desc); - xmit->tail = (xmit->tail + count) & (UART_XMIT_SIZE - 1); + uart_xmit_advance(&tup->uport, count); tup->tx_in_progress = 0; } diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c index 5c3a07546a58..4b1d4fe8458e 100644 --- a/drivers/tty/serial/sifive.c +++ b/drivers/tty/serial/sifive.c @@ -945,7 +945,7 @@ static int sifive_serial_probe(struct platform_device *pdev) return PTR_ERR(base); } - clk = devm_clk_get(&pdev->dev, NULL); + clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(clk)) { dev_err(&pdev->dev, "unable to find controller clock\n"); return PTR_ERR(clk); diff --git a/drivers/tty/serial/tegra-tcu.c b/drivers/tty/serial/tegra-tcu.c index 4877c54c613d..889b701ba7c6 100644 --- a/drivers/tty/serial/tegra-tcu.c +++ b/drivers/tty/serial/tegra-tcu.c @@ -101,7 +101,7 @@ static void tegra_tcu_uart_start_tx(struct uart_port *port) break; tegra_tcu_write(tcu, &xmit->buf[xmit->tail], count); - xmit->tail = (xmit->tail + count) & (UART_XMIT_SIZE - 1); + uart_xmit_advance(port, count); } uart_write_wakeup(port); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index a202d7d5240d..9538832b03a0 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2701,9 +2701,9 @@ static inline bool is_device_wlun(struct scsi_device *sdev) * Associate the UFS controller queue with the default and poll HCTX types. * Initialize the mq_map[] arrays. */ -static int ufshcd_map_queues(struct Scsi_Host *shost) +static void ufshcd_map_queues(struct Scsi_Host *shost) { - int i, ret; + int i; for (i = 0; i < shost->nr_maps; i++) { struct blk_mq_queue_map *map = &shost->tag_set.map[i]; @@ -2720,11 +2720,8 @@ static int ufshcd_map_queues(struct Scsi_Host *shost) WARN_ON_ONCE(true); } map->queue_offset = 0; - ret = blk_mq_map_queues(map); - WARN_ON_ONCE(ret); + blk_mq_map_queues(map); } - - return 0; } static void ufshcd_init_lrb(struct ufs_hba *hba, struct ufshcd_lrb *lrb, int i) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index d4b1e70d1498..bbab424b0d55 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -6039,7 +6039,7 @@ re_enumerate: * * Return: The same as for usb_reset_and_verify_device(). * However, if a reset is already in progress (for instance, if a - * driver doesn't have pre_ or post_reset() callbacks, and while + * driver doesn't have pre_reset() or post_reset() callbacks, and while * being unbound or re-bound during the ongoing reset its disconnect() * or probe() routine tries to perform a second, nested reset), the * routine returns -EINPROGRESS. diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 8c8e32651473..d0237b30c9be 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1752,12 +1752,6 @@ static int dwc3_probe(struct platform_device *pdev) dwc3_get_properties(dwc); - if (!dwc->sysdev_is_parent) { - ret = dma_set_mask_and_coherent(dwc->sysdev, DMA_BIT_MASK(64)); - if (ret) - return ret; - } - dwc->reset = devm_reset_control_array_get_optional_shared(dev); if (IS_ERR(dwc->reset)) return PTR_ERR(dwc->reset); @@ -1823,6 +1817,13 @@ static int dwc3_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dwc); dwc3_cache_hwparams(dwc); + if (!dwc->sysdev_is_parent && + DWC3_GHWPARAMS0_AWIDTH(dwc->hwparams.hwparams0) == 64) { + ret = dma_set_mask_and_coherent(dwc->sysdev, DMA_BIT_MASK(64)); + if (ret) + goto disable_clks; + } + spin_lock_init(&dwc->lock); mutex_init(&dwc->mutex); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index a5e8374a8d71..697683e3fbff 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -256,6 +256,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EM060K 0x030b #define QUECTEL_PRODUCT_EM12 0x0512 #define QUECTEL_PRODUCT_RM500Q 0x0800 +#define QUECTEL_PRODUCT_RM520N 0x0801 #define QUECTEL_PRODUCT_EC200S_CN 0x6002 #define QUECTEL_PRODUCT_EC200T 0x6026 #define QUECTEL_PRODUCT_RM500K 0x7001 @@ -1138,6 +1139,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0xff, 0xff), .driver_info = NUMEP2 }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG95, 0xff, 0, 0) }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, 0x0203, 0xff), /* BG95-M3 */ + .driver_info = ZLP }, { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_BG96), .driver_info = RSVD(4) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff), @@ -1159,6 +1162,9 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10), .driver_info = ZLP }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) }, diff --git a/drivers/usb/typec/Kconfig b/drivers/usb/typec/Kconfig index 5defdfead653..831e7049977d 100644 --- a/drivers/usb/typec/Kconfig +++ b/drivers/usb/typec/Kconfig @@ -56,6 +56,7 @@ config TYPEC_ANX7411 tristate "Analogix ANX7411 Type-C DRP Port controller driver" depends on I2C depends on USB_ROLE_SWITCH + depends on POWER_SUPPLY help Say Y or M here if your system has Analogix ANX7411 Type-C DRP Port controller driver. diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index d5f3f763717e..d4b251925796 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -382,9 +382,10 @@ int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr, unsigned long ring_size = nr_pages * XEN_PAGE_SIZE; grant_ref_t gref_head; unsigned int i; + void *addr; int ret; - *vaddr = alloc_pages_exact(ring_size, gfp | __GFP_ZERO); + addr = *vaddr = alloc_pages_exact(ring_size, gfp | __GFP_ZERO); if (!*vaddr) { ret = -ENOMEM; goto err; @@ -401,13 +402,15 @@ int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr, unsigned long gfn; if (is_vmalloc_addr(*vaddr)) - gfn = pfn_to_gfn(vmalloc_to_pfn(vaddr[i])); + gfn = pfn_to_gfn(vmalloc_to_pfn(addr)); else - gfn = virt_to_gfn(vaddr[i]); + gfn = virt_to_gfn(addr); grefs[i] = gnttab_claim_grant_reference(&gref_head); gnttab_grant_foreign_access_ref(grefs[i], dev->otherend_id, gfn, 0); + + addr += XEN_PAGE_SIZE; } return 0; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index e84d22c5c6a8..370788b9b124 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -15,6 +15,7 @@ #include <linux/string.h> #include <linux/backing-dev.h> #include <linux/writeback.h> +#include <linux/psi.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/log2.h> @@ -519,7 +520,8 @@ static u64 bio_end_offset(struct bio *bio) */ static noinline int add_ra_bio_pages(struct inode *inode, u64 compressed_end, - struct compressed_bio *cb) + struct compressed_bio *cb, + unsigned long *pflags) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); unsigned long end_index; @@ -588,6 +590,9 @@ static noinline int add_ra_bio_pages(struct inode *inode, continue; } + if (PageWorkingset(page)) + psi_memstall_enter(pflags); + ret = set_page_extent_mapped(page); if (ret < 0) { unlock_page(page); @@ -674,6 +679,8 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, u64 em_len; u64 em_start; struct extent_map *em; + /* Initialize to 1 to make skip psi_memstall_leave unless needed */ + unsigned long pflags = 1; blk_status_t ret; int ret2; int i; @@ -729,7 +736,7 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, goto fail; } - add_ra_bio_pages(inode, em_start + em_len, cb); + add_ra_bio_pages(inode, em_start + em_len, cb, &pflags); /* include any pages we added in add_ra-bio_pages */ cb->len = bio->bi_iter.bi_size; @@ -810,6 +817,9 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, } } + if (!pflags) + psi_memstall_leave(&pflags); + if (refcount_dec_and_test(&cb->pending_ios)) finish_compressed_bio_read(cb); return; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 1af28b066b42..2633137c3e9f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4475,6 +4475,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); /* + * If we had UNFINISHED_DROPS we could still be processing them, so + * clear that bit and wake up relocation so it can stop. + * We must do this before stopping the block group reclaim task, because + * at btrfs_relocate_block_group() we wait for this bit, and after the + * wait we stop with -EINTR if btrfs_fs_closing() returns non-zero - we + * have just set BTRFS_FS_CLOSING_START, so btrfs_fs_closing() will + * return 1. + */ + btrfs_wake_unfinished_drop(fs_info); + + /* * We may have the reclaim task running and relocating a data block group, * in which case it may create delayed iputs. So stop it before we park * the cleaner kthread otherwise we can get new delayed iputs after @@ -4492,12 +4503,6 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) */ kthread_park(fs_info->cleaner_kthread); - /* - * If we had UNFINISHED_DROPS we could still be processing them, so - * clear that bit and wake up relocation so it can stop. - */ - btrfs_wake_unfinished_drop(fs_info); - /* wait for the qgroup rescan worker to stop */ btrfs_qgroup_wait_for_completion(fs_info, false); @@ -4520,6 +4525,31 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) /* clear out the rbtree of defraggable inodes */ btrfs_cleanup_defrag_inodes(fs_info); + /* + * After we parked the cleaner kthread, ordered extents may have + * completed and created new delayed iputs. If one of the async reclaim + * tasks is running and in the RUN_DELAYED_IPUTS flush state, then we + * can hang forever trying to stop it, because if a delayed iput is + * added after it ran btrfs_run_delayed_iputs() and before it called + * btrfs_wait_on_delayed_iputs(), it will hang forever since there is + * no one else to run iputs. + * + * So wait for all ongoing ordered extents to complete and then run + * delayed iputs. This works because once we reach this point no one + * can either create new ordered extents nor create delayed iputs + * through some other means. + * + * Also note that btrfs_wait_ordered_roots() is not safe here, because + * it waits for BTRFS_ORDERED_COMPLETE to be set on an ordered extent, + * but the delayed iput for the respective inode is made only when doing + * the final btrfs_put_ordered_extent() (which must happen at + * btrfs_finish_ordered_io() when we are unmounting). + */ + btrfs_flush_workqueue(fs_info->endio_write_workers); + /* Ordered extents for free space inodes. */ + btrfs_flush_workqueue(fs_info->endio_freespace_worker); + btrfs_run_delayed_iputs(fs_info); + cancel_work_sync(&fs_info->async_reclaim_work); cancel_work_sync(&fs_info->async_data_reclaim_work); cancel_work_sync(&fs_info->preempt_reclaim_work); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 62e7007a7e46..73c6929f7be6 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1918,10 +1918,44 @@ out_unlock: return ret; } +static void wait_eb_writebacks(struct btrfs_block_group *block_group) +{ + struct btrfs_fs_info *fs_info = block_group->fs_info; + const u64 end = block_group->start + block_group->length; + struct radix_tree_iter iter; + struct extent_buffer *eb; + void __rcu **slot; + + rcu_read_lock(); + radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, + block_group->start >> fs_info->sectorsize_bits) { + eb = radix_tree_deref_slot(slot); + if (!eb) + continue; + if (radix_tree_deref_retry(eb)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + if (eb->start < block_group->start) + continue; + if (eb->start >= end) + break; + + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); + wait_on_extent_buffer_writeback(eb); + rcu_read_lock(); + } + rcu_read_unlock(); +} + static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct map_lookup *map; + const bool is_metadata = (block_group->flags & + (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)); int ret = 0; int i; @@ -1932,8 +1966,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ } /* Check if we have unwritten allocated space */ - if ((block_group->flags & - (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_SYSTEM)) && + if (is_metadata && block_group->start + block_group->alloc_offset > block_group->meta_write_pointer) { spin_unlock(&block_group->lock); return -EAGAIN; @@ -1958,6 +1991,9 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ /* No need to wait for NOCOW writers. Zoned mode does not allow that */ btrfs_wait_ordered_roots(fs_info, U64_MAX, block_group->start, block_group->length); + /* Wait for extent buffers to be written. */ + if (is_metadata) + wait_eb_writebacks(block_group); spin_lock(&block_group->lock); @@ -1445,6 +1445,9 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, loff_t done = 0; int ret; + if (!iomi.len) + return 0; + if (iov_iter_rw(iter) == WRITE) { lockdep_assert_held_write(&iomi.inode->i_rwsem); iomi.flags |= IOMAP_WRITE; diff --git a/fs/direct-io.c b/fs/direct-io.c index f669163d5860..03d381377ae1 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -421,8 +421,6 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) unsigned long flags; bio->bi_private = dio; - /* don't account direct I/O as memory stall */ - bio_clear_flag(bio, BIO_WORKINGSET); spin_lock_irqsave(&dio->bio_lock, flags); dio->refcount++; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 5792ca9e0d5e..143a101a3688 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -7,6 +7,7 @@ #include "zdata.h" #include "compress.h" #include <linux/prefetch.h> +#include <linux/psi.h> #include <trace/events/erofs.h> @@ -1365,6 +1366,8 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, struct block_device *last_bdev; unsigned int nr_bios = 0; struct bio *bio = NULL; + /* initialize to 1 to make skip psi_memstall_leave unless needed */ + unsigned long pflags = 1; bi_private = jobqueueset_init(sb, q, fgq, force_fg); qtail[JQ_BYPASS] = &q[JQ_BYPASS]->head; @@ -1414,10 +1417,15 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, if (bio && (cur != last_index + 1 || last_bdev != mdev.m_bdev)) { submit_bio_retry: + if (!pflags) + psi_memstall_leave(&pflags); submit_bio(bio); bio = NULL; } + if (unlikely(PageWorkingset(page))) + psi_memstall_enter(&pflags); + if (!bio) { bio = bio_alloc(mdev.m_bdev, BIO_MAX_VECS, REQ_OP_READ, GFP_NOIO); @@ -1445,8 +1453,11 @@ submit_bio_retry: move_to_bypass_jobqueue(pcl, qtail, owned_head); } while (owned_head != Z_EROFS_PCLUSTER_TAIL); - if (bio) + if (bio) { + if (!pflags) + psi_memstall_leave(&pflags); submit_bio(bio); + } /* * although background is preferred, no one is pending for submission. diff --git a/fs/exec.c b/fs/exec.c index 9a5ca7b82bfc..d046dbb9cbd0 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -65,7 +65,6 @@ #include <linux/io_uring.h> #include <linux/syscall_user_dispatch.h> #include <linux/coredump.h> -#include <linux/time_namespace.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> @@ -979,12 +978,10 @@ static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; struct mm_struct *old_mm, *active_mm; - bool vfork; int ret; /* Notify parent that we're no longer interested in the old VM */ tsk = current; - vfork = !!tsk->vfork_done; old_mm = current->mm; exec_mm_release(tsk, old_mm); if (old_mm) @@ -1029,10 +1026,6 @@ static int exec_mmap(struct mm_struct *mm) tsk->mm->vmacache_seqnum = 0; vmacache_flush(tsk); task_unlock(tsk); - - if (vfork) - timens_on_fork(tsk->nsproxy, tsk); - if (old_mm) { mmap_read_unlock(old_mm); BUG_ON(active_mm != old_mm); diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index ee0b7cf51157..41ae4cce1f42 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -270,8 +270,7 @@ int exfat_zeroed_cluster(struct inode *dir, unsigned int clu) struct super_block *sb = dir->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct buffer_head *bh; - sector_t blknr, last_blknr; - int i; + sector_t blknr, last_blknr, i; blknr = exfat_cluster_to_sector(sbi, clu); last_blknr = blknr + sbi->sect_per_clus; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9bca5565547b..3bf9a6926798 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -167,8 +167,6 @@ enum SHIFT_DIRECTION { #define EXT4_MB_CR0_OPTIMIZED 0x8000 /* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */ #define EXT4_MB_CR1_OPTIMIZED 0x00010000 -/* Perform linear traversal for one group */ -#define EXT4_MB_SEARCH_NEXT_LINEAR 0x00020000 struct ext4_allocation_request { /* target inode for block we're allocating */ struct inode *inode; @@ -1600,8 +1598,8 @@ struct ext4_sb_info { struct list_head s_discard_list; struct work_struct s_discard_work; atomic_t s_retry_alloc_pending; - struct rb_root s_mb_avg_fragment_size_root; - rwlock_t s_mb_rb_lock; + struct list_head *s_mb_avg_fragment_size; + rwlock_t *s_mb_avg_fragment_size_locks; struct list_head *s_mb_largest_free_orders; rwlock_t *s_mb_largest_free_orders_locks; @@ -3413,6 +3411,8 @@ struct ext4_group_info { ext4_grpblk_t bb_first_free; /* first free block */ ext4_grpblk_t bb_free; /* total free blocks */ ext4_grpblk_t bb_fragments; /* nr of freespace fragments */ + int bb_avg_fragment_size_order; /* order of average + fragment in BG */ ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */ ext4_group_t bb_group; /* Group number */ struct list_head bb_prealloc_list; @@ -3420,7 +3420,7 @@ struct ext4_group_info { void *bb_bitmap; #endif struct rw_semaphore alloc_sem; - struct rb_node bb_avg_fragment_size_rb; + struct list_head bb_avg_fragment_size_node; struct list_head bb_largest_free_order_node; ext4_grpblk_t bb_counters[]; /* Nr of free power-of-two-block * regions, index is order. diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c148bb97b527..5235974126bd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -460,6 +460,10 @@ static int __ext4_ext_check(const char *function, unsigned int line, error_msg = "invalid eh_entries"; goto corrupted; } + if (unlikely((eh->eh_entries == 0) && (depth > 0))) { + error_msg = "eh_entries is 0 but eh_depth is > 0"; + goto corrupted; + } if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index f73e5eb43eae..208b87ce8858 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -510,7 +510,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, goto fallback; } - max_dirs = ndirs / ngroups + inodes_per_group / 16; + max_dirs = ndirs / ngroups + inodes_per_group*flex_size / 16; min_inodes = avefreei - inodes_per_group*flex_size / 4; if (min_inodes < 1) min_inodes = 1; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index bd8f8b5c3d30..71f5b67d7f28 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -140,13 +140,15 @@ * number of buddy bitmap orders possible) number of lists. Group-infos are * placed in appropriate lists. * - * 2) Average fragment size rb tree (sbi->s_mb_avg_fragment_size_root) + * 2) Average fragment size lists (sbi->s_mb_avg_fragment_size) * - * Locking: sbi->s_mb_rb_lock (rwlock) + * Locking: sbi->s_mb_avg_fragment_size_locks(array of rw locks) * - * This is a red black tree consisting of group infos and the tree is sorted - * by average fragment sizes (which is calculated as ext4_group_info->bb_free - * / ext4_group_info->bb_fragments). + * This is an array of lists where in the i-th list there are groups with + * average fragment size >= 2^i and < 2^(i+1). The average fragment size + * is computed as ext4_group_info->bb_free / ext4_group_info->bb_fragments. + * Note that we don't bother with a special list for completely empty groups + * so we only have MB_NUM_ORDERS(sb) lists. * * When "mb_optimize_scan" mount option is set, mballoc consults the above data * structures to decide the order in which groups are to be traversed for @@ -160,7 +162,8 @@ * * At CR = 1, we only consider groups where average fragment size > request * size. So, we lookup a group which has average fragment size just above or - * equal to request size using our rb tree (data structure 2) in O(log N) time. + * equal to request size using our average fragment size group lists (data + * structure 2) in O(1) time. * * If "mb_optimize_scan" mount option is not set, mballoc traverses groups in * linear order which requires O(N) search time for each CR 0 and CR 1 phase. @@ -802,65 +805,51 @@ static void ext4_mb_mark_free_simple(struct super_block *sb, } } -static void ext4_mb_rb_insert(struct rb_root *root, struct rb_node *new, - int (*cmp)(struct rb_node *, struct rb_node *)) +static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len) { - struct rb_node **iter = &root->rb_node, *parent = NULL; + int order; - while (*iter) { - parent = *iter; - if (cmp(new, *iter) > 0) - iter = &((*iter)->rb_left); - else - iter = &((*iter)->rb_right); - } - - rb_link_node(new, parent, iter); - rb_insert_color(new, root); -} - -static int -ext4_mb_avg_fragment_size_cmp(struct rb_node *rb1, struct rb_node *rb2) -{ - struct ext4_group_info *grp1 = rb_entry(rb1, - struct ext4_group_info, - bb_avg_fragment_size_rb); - struct ext4_group_info *grp2 = rb_entry(rb2, - struct ext4_group_info, - bb_avg_fragment_size_rb); - int num_frags_1, num_frags_2; - - num_frags_1 = grp1->bb_fragments ? - grp1->bb_free / grp1->bb_fragments : 0; - num_frags_2 = grp2->bb_fragments ? - grp2->bb_free / grp2->bb_fragments : 0; - - return (num_frags_2 - num_frags_1); + /* + * We don't bother with a special lists groups with only 1 block free + * extents and for completely empty groups. + */ + order = fls(len) - 2; + if (order < 0) + return 0; + if (order == MB_NUM_ORDERS(sb)) + order--; + return order; } -/* - * Reinsert grpinfo into the avg_fragment_size tree with new average - * fragment size. - */ +/* Move group to appropriate avg_fragment_size list */ static void mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); + int new_order; if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0) return; - write_lock(&sbi->s_mb_rb_lock); - if (!RB_EMPTY_NODE(&grp->bb_avg_fragment_size_rb)) { - rb_erase(&grp->bb_avg_fragment_size_rb, - &sbi->s_mb_avg_fragment_size_root); - RB_CLEAR_NODE(&grp->bb_avg_fragment_size_rb); - } + new_order = mb_avg_fragment_size_order(sb, + grp->bb_free / grp->bb_fragments); + if (new_order == grp->bb_avg_fragment_size_order) + return; - ext4_mb_rb_insert(&sbi->s_mb_avg_fragment_size_root, - &grp->bb_avg_fragment_size_rb, - ext4_mb_avg_fragment_size_cmp); - write_unlock(&sbi->s_mb_rb_lock); + if (grp->bb_avg_fragment_size_order != -1) { + write_lock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + list_del(&grp->bb_avg_fragment_size_node); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + } + grp->bb_avg_fragment_size_order = new_order; + write_lock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); + list_add_tail(&grp->bb_avg_fragment_size_node, + &sbi->s_mb_avg_fragment_size[grp->bb_avg_fragment_size_order]); + write_unlock(&sbi->s_mb_avg_fragment_size_locks[ + grp->bb_avg_fragment_size_order]); } /* @@ -909,86 +898,56 @@ static void ext4_mb_choose_next_group_cr0(struct ext4_allocation_context *ac, *new_cr = 1; } else { *group = grp->bb_group; - ac->ac_last_optimal_group = *group; ac->ac_flags |= EXT4_MB_CR0_OPTIMIZED; } } /* - * Choose next group by traversing average fragment size tree. Updates *new_cr - * if cr lvel needs an update. Sets EXT4_MB_SEARCH_NEXT_LINEAR to indicate that - * the linear search should continue for one iteration since there's lock - * contention on the rb tree lock. + * Choose next group by traversing average fragment size list of suitable + * order. Updates *new_cr if cr level needs an update. */ static void ext4_mb_choose_next_group_cr1(struct ext4_allocation_context *ac, int *new_cr, ext4_group_t *group, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); - int avg_fragment_size, best_so_far; - struct rb_node *node, *found; - struct ext4_group_info *grp; - - /* - * If there is contention on the lock, instead of waiting for the lock - * to become available, just continue searching lineraly. We'll resume - * our rb tree search later starting at ac->ac_last_optimal_group. - */ - if (!read_trylock(&sbi->s_mb_rb_lock)) { - ac->ac_flags |= EXT4_MB_SEARCH_NEXT_LINEAR; - return; - } + struct ext4_group_info *grp, *iter; + int i; if (unlikely(ac->ac_flags & EXT4_MB_CR1_OPTIMIZED)) { if (sbi->s_mb_stats) atomic_inc(&sbi->s_bal_cr1_bad_suggestions); - /* We have found something at CR 1 in the past */ - grp = ext4_get_group_info(ac->ac_sb, ac->ac_last_optimal_group); - for (found = rb_next(&grp->bb_avg_fragment_size_rb); found != NULL; - found = rb_next(found)) { - grp = rb_entry(found, struct ext4_group_info, - bb_avg_fragment_size_rb); + } + + for (i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); + i < MB_NUM_ORDERS(ac->ac_sb); i++) { + if (list_empty(&sbi->s_mb_avg_fragment_size[i])) + continue; + read_lock(&sbi->s_mb_avg_fragment_size_locks[i]); + if (list_empty(&sbi->s_mb_avg_fragment_size[i])) { + read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]); + continue; + } + grp = NULL; + list_for_each_entry(iter, &sbi->s_mb_avg_fragment_size[i], + bb_avg_fragment_size_node) { if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[1]); - if (likely(ext4_mb_good_group(ac, grp->bb_group, 1))) + if (likely(ext4_mb_good_group(ac, iter->bb_group, 1))) { + grp = iter; break; - } - goto done; - } - - node = sbi->s_mb_avg_fragment_size_root.rb_node; - best_so_far = 0; - found = NULL; - - while (node) { - grp = rb_entry(node, struct ext4_group_info, - bb_avg_fragment_size_rb); - avg_fragment_size = 0; - if (ext4_mb_good_group(ac, grp->bb_group, 1)) { - avg_fragment_size = grp->bb_fragments ? - grp->bb_free / grp->bb_fragments : 0; - if (!best_so_far || avg_fragment_size < best_so_far) { - best_so_far = avg_fragment_size; - found = node; } } - if (avg_fragment_size > ac->ac_g_ex.fe_len) - node = node->rb_right; - else - node = node->rb_left; + read_unlock(&sbi->s_mb_avg_fragment_size_locks[i]); + if (grp) + break; } -done: - if (found) { - grp = rb_entry(found, struct ext4_group_info, - bb_avg_fragment_size_rb); + if (grp) { *group = grp->bb_group; ac->ac_flags |= EXT4_MB_CR1_OPTIMIZED; } else { *new_cr = 2; } - - read_unlock(&sbi->s_mb_rb_lock); - ac->ac_last_optimal_group = *group; } static inline int should_optimize_scan(struct ext4_allocation_context *ac) @@ -1017,11 +976,6 @@ next_linear_group(struct ext4_allocation_context *ac, int group, int ngroups) goto inc_and_return; } - if (ac->ac_flags & EXT4_MB_SEARCH_NEXT_LINEAR) { - ac->ac_flags &= ~EXT4_MB_SEARCH_NEXT_LINEAR; - goto inc_and_return; - } - return group; inc_and_return: /* @@ -1049,8 +1003,10 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac, { *new_cr = ac->ac_criteria; - if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) + if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) { + *group = next_linear_group(ac, *group, ngroups); return; + } if (*new_cr == 0) { ext4_mb_choose_next_group_cr0(ac, new_cr, group, ngroups); @@ -1075,23 +1031,25 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) struct ext4_sb_info *sbi = EXT4_SB(sb); int i; - if (test_opt2(sb, MB_OPTIMIZE_SCAN) && grp->bb_largest_free_order >= 0) { + for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) + if (grp->bb_counters[i] > 0) + break; + /* No need to move between order lists? */ + if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || + i == grp->bb_largest_free_order) { + grp->bb_largest_free_order = i; + return; + } + + if (grp->bb_largest_free_order >= 0) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_del_init(&grp->bb_largest_free_order_node); write_unlock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); } - grp->bb_largest_free_order = -1; /* uninit */ - - for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--) { - if (grp->bb_counters[i] > 0) { - grp->bb_largest_free_order = i; - break; - } - } - if (test_opt2(sb, MB_OPTIMIZE_SCAN) && - grp->bb_largest_free_order >= 0 && grp->bb_free) { + grp->bb_largest_free_order = i; + if (grp->bb_largest_free_order >= 0 && grp->bb_free) { write_lock(&sbi->s_mb_largest_free_orders_locks[ grp->bb_largest_free_order]); list_add_tail(&grp->bb_largest_free_order_node, @@ -1148,13 +1106,13 @@ void ext4_mb_generate_buddy(struct super_block *sb, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_set_largest_free_order(sb, grp); + mb_update_avg_fragment_size(sb, grp); clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; atomic_inc(&sbi->s_mb_buddies_generated); atomic64_add(period, &sbi->s_mb_generation_time); - mb_update_avg_fragment_size(sb, grp); } /* The buddy information is attached the buddy cache inode @@ -2636,7 +2594,7 @@ static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t prefetch_grp = 0, ngroups, group, i; - int cr = -1; + int cr = -1, new_cr; int err = 0, first_err = 0; unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; @@ -2707,17 +2665,14 @@ repeat: * from the goal value specified */ group = ac->ac_g_ex.fe_group; - ac->ac_last_optimal_group = group; ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups; prefetch_grp = group; - for (i = 0; i < ngroups; group = next_linear_group(ac, group, ngroups), - i++) { - int ret = 0, new_cr; + for (i = 0, new_cr = cr; i < ngroups; i++, + ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups)) { + int ret = 0; cond_resched(); - - ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups); if (new_cr != cr) { cr = new_cr; goto repeat; @@ -2991,9 +2946,7 @@ __acquires(&EXT4_SB(sb)->s_mb_rb_lock) struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; - read_lock(&EXT4_SB(sb)->s_mb_rb_lock); - - if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1) + if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); @@ -3005,7 +2958,7 @@ static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, lof unsigned long position; ++*pos; - if (*pos < 0 || *pos >= MB_NUM_ORDERS(sb) + 1) + if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); @@ -3017,29 +2970,22 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long position = ((unsigned long) v); struct ext4_group_info *grp; - struct rb_node *n; - unsigned int count, min, max; + unsigned int count; position--; if (position >= MB_NUM_ORDERS(sb)) { - seq_puts(seq, "fragment_size_tree:\n"); - n = rb_first(&sbi->s_mb_avg_fragment_size_root); - if (!n) { - seq_puts(seq, "\ttree_min: 0\n\ttree_max: 0\n\ttree_nodes: 0\n"); - return 0; - } - grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb); - min = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0; - count = 1; - while (rb_next(n)) { - count++; - n = rb_next(n); - } - grp = rb_entry(n, struct ext4_group_info, bb_avg_fragment_size_rb); - max = grp->bb_fragments ? grp->bb_free / grp->bb_fragments : 0; + position -= MB_NUM_ORDERS(sb); + if (position == 0) + seq_puts(seq, "avg_fragment_size_lists:\n"); - seq_printf(seq, "\ttree_min: %u\n\ttree_max: %u\n\ttree_nodes: %u\n", - min, max, count); + count = 0; + read_lock(&sbi->s_mb_avg_fragment_size_locks[position]); + list_for_each_entry(grp, &sbi->s_mb_avg_fragment_size[position], + bb_avg_fragment_size_node) + count++; + read_unlock(&sbi->s_mb_avg_fragment_size_locks[position]); + seq_printf(seq, "\tlist_order_%u_groups: %u\n", + (unsigned int)position, count); return 0; } @@ -3049,9 +2995,11 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) seq_puts(seq, "max_free_order_lists:\n"); } count = 0; + read_lock(&sbi->s_mb_largest_free_orders_locks[position]); list_for_each_entry(grp, &sbi->s_mb_largest_free_orders[position], bb_largest_free_order_node) count++; + read_unlock(&sbi->s_mb_largest_free_orders_locks[position]); seq_printf(seq, "\tlist_order_%u_groups: %u\n", (unsigned int)position, count); @@ -3059,11 +3007,7 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) } static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v) -__releases(&EXT4_SB(sb)->s_mb_rb_lock) { - struct super_block *sb = pde_data(file_inode(seq->file)); - - read_unlock(&EXT4_SB(sb)->s_mb_rb_lock); } const struct seq_operations ext4_mb_seq_structs_summary_ops = { @@ -3176,8 +3120,9 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, init_rwsem(&meta_group_info[i]->alloc_sem); meta_group_info[i]->bb_free_root = RB_ROOT; INIT_LIST_HEAD(&meta_group_info[i]->bb_largest_free_order_node); - RB_CLEAR_NODE(&meta_group_info[i]->bb_avg_fragment_size_rb); + INIT_LIST_HEAD(&meta_group_info[i]->bb_avg_fragment_size_node); meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ + meta_group_info[i]->bb_avg_fragment_size_order = -1; /* uninit */ meta_group_info[i]->bb_group = group; mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); @@ -3426,7 +3371,24 @@ int ext4_mb_init(struct super_block *sb) i++; } while (i < MB_NUM_ORDERS(sb)); - sbi->s_mb_avg_fragment_size_root = RB_ROOT; + sbi->s_mb_avg_fragment_size = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), + GFP_KERNEL); + if (!sbi->s_mb_avg_fragment_size) { + ret = -ENOMEM; + goto out; + } + sbi->s_mb_avg_fragment_size_locks = + kmalloc_array(MB_NUM_ORDERS(sb), sizeof(rwlock_t), + GFP_KERNEL); + if (!sbi->s_mb_avg_fragment_size_locks) { + ret = -ENOMEM; + goto out; + } + for (i = 0; i < MB_NUM_ORDERS(sb); i++) { + INIT_LIST_HEAD(&sbi->s_mb_avg_fragment_size[i]); + rwlock_init(&sbi->s_mb_avg_fragment_size_locks[i]); + } sbi->s_mb_largest_free_orders = kmalloc_array(MB_NUM_ORDERS(sb), sizeof(struct list_head), GFP_KERNEL); @@ -3445,7 +3407,6 @@ int ext4_mb_init(struct super_block *sb) INIT_LIST_HEAD(&sbi->s_mb_largest_free_orders[i]); rwlock_init(&sbi->s_mb_largest_free_orders_locks[i]); } - rwlock_init(&sbi->s_mb_rb_lock); spin_lock_init(&sbi->s_md_lock); sbi->s_mb_free_pending = 0; @@ -3516,6 +3477,8 @@ out_free_locality_groups: free_percpu(sbi->s_locality_groups); sbi->s_locality_groups = NULL; out: + kfree(sbi->s_mb_avg_fragment_size); + kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); @@ -3582,6 +3545,8 @@ int ext4_mb_release(struct super_block *sb) kvfree(group_info); rcu_read_unlock(); } + kfree(sbi->s_mb_avg_fragment_size); + kfree(sbi->s_mb_avg_fragment_size_locks); kfree(sbi->s_mb_largest_free_orders); kfree(sbi->s_mb_largest_free_orders_locks); kfree(sbi->s_mb_offsets); @@ -5193,6 +5158,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits = ac->ac_sb->s_blocksize_bits; loff_t size, isize; + bool inode_pa_eligible, group_pa_eligible; if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; @@ -5200,25 +5166,27 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; + group_pa_eligible = sbi->s_mb_group_prealloc > 0; + inode_pa_eligible = true; size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; + /* No point in using inode preallocation for closed files */ if ((size == isize) && !ext4_fs_is_busy(sbi) && - !inode_is_open_for_write(ac->ac_inode)) { - ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; - return; - } + !inode_is_open_for_write(ac->ac_inode)) + inode_pa_eligible = false; - if (sbi->s_mb_group_prealloc <= 0) { - ac->ac_flags |= EXT4_MB_STREAM_ALLOC; - return; - } - - /* don't use group allocation for large files */ size = max(size, isize); - if (size > sbi->s_mb_stream_request) { - ac->ac_flags |= EXT4_MB_STREAM_ALLOC; + /* Don't use group allocation for large files */ + if (size > sbi->s_mb_stream_request) + group_pa_eligible = false; + + if (!group_pa_eligible) { + if (inode_pa_eligible) + ac->ac_flags |= EXT4_MB_STREAM_ALLOC; + else + ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; return; } @@ -5565,6 +5533,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, ext4_fsblk_t block = 0; unsigned int inquota = 0; unsigned int reserv_clstrs = 0; + int retries = 0; u64 seq; might_sleep(); @@ -5667,7 +5636,8 @@ repeat: ar->len = ac->ac_b_ex.fe_len; } } else { - if (ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) + if (++retries < 3 && + ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) goto repeat; /* * If block allocation fails then the pa allocated above diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 39da92ceabf8..dcda2a943cee 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -178,7 +178,6 @@ struct ext4_allocation_context { /* copy of the best found extent taken before preallocation efforts */ struct ext4_free_extent ac_f_ex; - ext4_group_t ac_last_optimal_group; __u32 ac_groups_considered; __u32 ac_flags; /* allocation hints */ __u16 ac_groups_scanned; diff --git a/fs/open.c b/fs/open.c index 8a813fa5ca56..cf7e5c350a54 100644 --- a/fs/open.c +++ b/fs/open.c @@ -716,6 +716,8 @@ int chown_common(const struct path *path, uid_t user, gid_t group) fs_userns = i_user_ns(inode); retry_deleg: + newattrs.ia_vfsuid = INVALID_VFSUID; + newattrs.ia_vfsgid = INVALID_VFSGID; newattrs.ia_valid = ATTR_CTIME; if ((user != (uid_t)-1) && !setattr_vfsuid(&newattrs, uid)) return -EINVAL; diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 7515a465ec03..7c90b1ab3e00 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -543,10 +543,9 @@ */ #ifdef CONFIG_CFI_CLANG #define TEXT_CFI_JT \ - . = ALIGN(PMD_SIZE); \ + ALIGN_FUNCTION(); \ __cfi_jt_start = .; \ *(.text..L.cfi.jumptable .text..L.cfi.jumptable.*) \ - . = ALIGN(PMD_SIZE); \ __cfi_jt_end = .; #else #define TEXT_CFI_JT diff --git a/include/linux/bio.h b/include/linux/bio.h index ca22b06700a9..2c5806997bbf 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -509,7 +509,7 @@ static inline void bio_set_dev(struct bio *bio, struct block_device *bdev) { bio_clear_flag(bio, BIO_REMAPPED); if (bio->bi_bdev != bdev) - bio_clear_flag(bio, BIO_THROTTLED); + bio_clear_flag(bio, BIO_BPS_THROTTLED); bio->bi_bdev = bdev; bio_associate_blkg(bio); } diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 9f40dbc65f82..dd5841a42c33 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -18,14 +18,14 @@ struct bio; struct cgroup_subsys_state; -struct request_queue; +struct gendisk; #define FC_APPID_LEN 129 #ifdef CONFIG_BLK_CGROUP extern struct cgroup_subsys_state * const blkcg_root_css; -void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); +void blkcg_schedule_throttle(struct gendisk *disk, bool use_memdelay); void blkcg_maybe_throttle_current(void); bool blk_cgroup_congested(void); void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); @@ -39,7 +39,6 @@ struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio); static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } -static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { return NULL; diff --git a/include/linux/blk-mq-pci.h b/include/linux/blk-mq-pci.h index 0b1f45c62623..ca544e1d3508 100644 --- a/include/linux/blk-mq-pci.h +++ b/include/linux/blk-mq-pci.h @@ -5,7 +5,7 @@ struct blk_mq_queue_map; struct pci_dev; -int blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, - int offset); +void blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev, + int offset); #endif /* _LINUX_BLK_MQ_PCI_H */ diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h index 5cc5f0f36218..53b58c610e76 100644 --- a/include/linux/blk-mq-rdma.h +++ b/include/linux/blk-mq-rdma.h @@ -5,7 +5,7 @@ struct blk_mq_tag_set; struct ib_device; -int blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, +void blk_mq_rdma_map_queues(struct blk_mq_queue_map *map, struct ib_device *dev, int first_vec); #endif /* _LINUX_BLK_MQ_RDMA_H */ diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h index 687ae287e1dc..13226e9b22dd 100644 --- a/include/linux/blk-mq-virtio.h +++ b/include/linux/blk-mq-virtio.h @@ -5,7 +5,7 @@ struct blk_mq_queue_map; struct virtio_device; -int blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, +void blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap, struct virtio_device *vdev, int first_vec); #endif /* _LINUX_BLK_MQ_VIRTIO_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index de384f5d2c37..00a15808c137 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -268,9 +268,16 @@ static inline void rq_list_move(struct request **src, struct request **dst, rq_list_add(dst, rq); } +/** + * enum blk_eh_timer_return - How the timeout handler should proceed + * @BLK_EH_DONE: The block driver completed the command or will complete it at + * a later time. + * @BLK_EH_RESET_TIMER: Reset the request timer and continue waiting for the + * request to complete. + */ enum blk_eh_timer_return { - BLK_EH_DONE, /* drivers has completed the command */ - BLK_EH_RESET_TIMER, /* reset timer and try again */ + BLK_EH_DONE, + BLK_EH_RESET_TIMER, }; #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ @@ -630,7 +637,7 @@ struct blk_mq_ops { * @map_queues: This allows drivers specify their own queue mapping by * overriding the setup-time function that builds the mq_map. */ - int (*map_queues)(struct blk_mq_tag_set *set); + void (*map_queues)(struct blk_mq_tag_set *set); #ifdef CONFIG_BLK_DEBUG_FS /** @@ -880,7 +887,7 @@ void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); -int blk_mq_map_queues(struct blk_mq_queue_map *qmap); +void blk_mq_map_queues(struct blk_mq_queue_map *qmap); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); @@ -963,11 +970,11 @@ blk_status_t blk_insert_cloned_request(struct request *rq); struct rq_map_data { struct page **pages; - int page_order; - int nr_entries; unsigned long offset; - int null_mapped; - int from_user; + unsigned short page_order; + unsigned short nr_entries; + bool null_mapped; + bool from_user; }; int blk_rq_map_user(struct request_queue *, struct request *, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1ef99790f6ed..e0b098089ef2 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -321,11 +321,10 @@ enum { BIO_NO_PAGE_REF, /* don't put release vec pages */ BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ - BIO_WORKINGSET, /* contains userspace workingset pages */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ BIO_REFFED, /* bio has elevated ->bi_cnt */ - BIO_THROTTLED, /* This bio has already been subjected to + BIO_BPS_THROTTLED, /* This bio has already been subjected to * throttling rules. Don't do it again. */ BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 84b13fdd34a7..49373d002631 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -618,7 +618,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) -#define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) #define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); @@ -1280,6 +1279,11 @@ static inline bool bdev_fua(struct block_device *bdev) return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); } +static inline bool bdev_nowait(struct block_device *bdev) +{ + return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags); +} + static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); @@ -1300,6 +1304,15 @@ static inline bool bdev_is_zoned(struct block_device *bdev) return false; } +static inline bool bdev_op_is_zoned_write(struct block_device *bdev, + blk_opf_t op) +{ + if (!bdev_is_zoned(bdev)) + return false; + + return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES; +} + static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index bd047864c7ac..e8ad12b5b9d2 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -1127,9 +1127,10 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, * cover a worst-case of every other cpu being on one of two nodes for a * very large NR_CPUS. * - * Use PAGE_SIZE as a minimum for smaller configurations. + * Use PAGE_SIZE as a minimum for smaller configurations while avoiding + * unsigned comparison to -1. */ -#define CPUMAP_FILE_MAX_BYTES ((((NR_CPUS * 9)/32 - 1) > PAGE_SIZE) \ +#define CPUMAP_FILE_MAX_BYTES (((NR_CPUS * 9)/32 > PAGE_SIZE) \ ? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE) #define CPULIST_FILE_MAX_BYTES (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE) diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 8917a32173c4..d81a51978d01 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -65,7 +65,6 @@ struct dmar_pci_notify_info { extern struct rw_semaphore dmar_global_lock; extern struct list_head dmar_drhd_units; -extern int intel_iommu_enabled; #define for_each_drhd_unit(drhd) \ list_for_each_entry_rcu(drhd, &dmar_drhd_units, list, \ @@ -89,8 +88,7 @@ extern int intel_iommu_enabled; static inline bool dmar_rcu_check(void) { return rwsem_is_locked(&dmar_global_lock) || - system_state == SYSTEM_BOOTING || - (IS_ENABLED(CONFIG_INTEL_IOMMU) && !intel_iommu_enabled); + system_state == SYSTEM_BOOTING; } #define dmar_rcu_dereference(p) rcu_dereference_check((p), dmar_rcu_check()) diff --git a/include/linux/nvme.h b/include/linux/nvme.h index ae53d74f3696..050d7d0cd81b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -1482,8 +1482,8 @@ struct nvmf_connect_command { }; enum { - NVME_CONNECT_AUTHREQ_ASCR = (1 << 2), - NVME_CONNECT_AUTHREQ_ATR = (1 << 1), + NVME_CONNECT_AUTHREQ_ASCR = (1U << 18), + NVME_CONNECT_AUTHREQ_ATR = (1U << 17), }; struct nvmf_connect_data { diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0178b2040ea3..201dc7281640 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1173,6 +1173,8 @@ struct readahead_control { pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; + bool _workingset; + unsigned long _pflags; }; #define DEFINE_READAHEAD(ractl, f, r, m, i) \ diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 8f5a86e210b9..4d2d5205ab58 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -575,8 +575,9 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq); * sbitmap_queue_wake_up() - Wake up some of waiters in one waitqueue * on a &struct sbitmap_queue. * @sbq: Bitmap queue to wake up. + * @nr: Number of bits cleared. */ -void sbitmap_queue_wake_up(struct sbitmap_queue *sbq); +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr); /** * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index a193884ecf2b..4f765bc788ff 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -84,7 +84,7 @@ struct scmi_protocol_handle; struct scmi_clk_proto_ops { int (*count_get)(const struct scmi_protocol_handle *ph); - const struct scmi_clock_info *(*info_get) + const struct scmi_clock_info __must_check *(*info_get) (const struct scmi_protocol_handle *ph, u32 clk_id); int (*rate_get)(const struct scmi_protocol_handle *ph, u32 clk_id, u64 *rate); @@ -466,7 +466,7 @@ enum scmi_sensor_class { */ struct scmi_sensor_proto_ops { int (*count_get)(const struct scmi_protocol_handle *ph); - const struct scmi_sensor_info *(*info_get) + const struct scmi_sensor_info __must_check *(*info_get) (const struct scmi_protocol_handle *ph, u32 sensor_id); int (*trip_point_config)(const struct scmi_protocol_handle *ph, u32 sensor_id, u8 trip_id, u64 trip_value); diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 1ac0d712a9c3..6f837bb6c715 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -43,6 +43,7 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_MBR_DONE: case IOC_OPAL_WRITE_SHADOW_MBR: case IOC_OPAL_GENERIC_TABLE_RW: + case IOC_OPAL_GET_STATUS: return true; } return false; diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 6e4f4765d209..1eaea9fe44d8 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -624,6 +624,23 @@ struct uart_state { /* number of characters left in xmit buffer before we ask for more */ #define WAKEUP_CHARS 256 +/** + * uart_xmit_advance - Advance xmit buffer and account Tx'ed chars + * @up: uart_port structure describing the port + * @chars: number of characters sent + * + * This function advances the tail of circular xmit buffer by the number of + * @chars transmitted and handles accounting of transmitted bytes (into + * @up's icount.tx). + */ +static inline void uart_xmit_advance(struct uart_port *up, unsigned int chars) +{ + struct circ_buf *xmit = &up->state->xmit; + + xmit->tail = (xmit->tail + chars) & (UART_XMIT_SIZE - 1); + up->icount.tx += chars; +} + struct module; struct tty_driver; diff --git a/include/net/bluetooth/hci_sock.h b/include/net/bluetooth/hci_sock.h index 0520e21ab698..9949870f7d78 100644 --- a/include/net/bluetooth/hci_sock.h +++ b/include/net/bluetooth/hci_sock.h @@ -124,8 +124,6 @@ struct hci_dev_info { __u16 acl_pkts; __u16 sco_mtu; __u16 sco_pkts; - __u16 iso_mtu; - __u16 iso_pkts; struct hci_dev_stats stat; }; diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index be2992e6de5d..a016f275cb01 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -15,8 +15,6 @@ #define PKT_TYPE_LACPDU cpu_to_be16(ETH_P_SLOW) #define AD_TIMER_INTERVAL 100 /*msec*/ -#define MULTICAST_LACPDU_ADDR {0x01, 0x80, 0xC2, 0x00, 0x00, 0x02} - #define AD_LACP_SLOW 0 #define AD_LACP_FAST 1 diff --git a/include/net/bonding.h b/include/net/bonding.h index afd606df149a..e999f851738b 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -786,6 +786,9 @@ extern struct rtnl_link_ops bond_link_ops; /* exported from bond_sysfs_slave.c */ extern const struct sysfs_ops slave_sysfs_ops; +/* exported from bond_3ad.c */ +extern const u8 lacpdu_mcast_addr[]; + static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { dev_core_stats_tx_dropped_inc(dev); diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index d0d188c3294b..a8994f307fc3 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -15,6 +15,22 @@ #ifndef IEEE802154_NETDEVICE_H #define IEEE802154_NETDEVICE_H +#define IEEE802154_REQUIRED_SIZE(struct_type, member) \ + (offsetof(typeof(struct_type), member) + \ + sizeof(((typeof(struct_type) *)(NULL))->member)) + +#define IEEE802154_ADDR_OFFSET \ + offsetof(typeof(struct sockaddr_ieee802154), addr) + +#define IEEE802154_MIN_NAMELEN (IEEE802154_ADDR_OFFSET + \ + IEEE802154_REQUIRED_SIZE(struct ieee802154_addr_sa, addr_type)) + +#define IEEE802154_NAMELEN_SHORT (IEEE802154_ADDR_OFFSET + \ + IEEE802154_REQUIRED_SIZE(struct ieee802154_addr_sa, short_addr)) + +#define IEEE802154_NAMELEN_LONG (IEEE802154_ADDR_OFFSET + \ + IEEE802154_REQUIRED_SIZE(struct ieee802154_addr_sa, hwaddr)) + #include <net/af_ieee802154.h> #include <linux/netdevice.h> #include <linux/skbuff.h> @@ -165,6 +181,27 @@ static inline void ieee802154_devaddr_to_raw(void *raw, __le64 addr) memcpy(raw, &temp, IEEE802154_ADDR_LEN); } +static inline int +ieee802154_sockaddr_check_size(struct sockaddr_ieee802154 *daddr, int len) +{ + struct ieee802154_addr_sa *sa; + + sa = &daddr->addr; + if (len < IEEE802154_MIN_NAMELEN) + return -EINVAL; + switch (sa->addr_type) { + case IEEE802154_ADDR_SHORT: + if (len < IEEE802154_NAMELEN_SHORT) + return -EINVAL; + break; + case IEEE802154_ADDR_LONG: + if (len < IEEE802154_NAMELEN_LONG) + return -EINVAL; + break; + } + return 0; +} + static inline void ieee802154_addr_from_sa(struct ieee802154_addr *a, const struct ieee802154_addr_sa *sa) { diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index 9b0a028bf053..fcf25f1642a3 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -276,7 +276,7 @@ struct scsi_host_template { * * Status: OPTIONAL */ - int (* map_queues)(struct Scsi_Host *shost); + void (* map_queues)(struct Scsi_Host *shost); /* * SCSI interface of blk_poll - poll for IO completions. diff --git a/include/trace/events/scmi.h b/include/trace/events/scmi.h index 65016a767b7a..f160d68f961d 100644 --- a/include/trace/events/scmi.h +++ b/include/trace/events/scmi.h @@ -27,9 +27,9 @@ TRACE_EVENT(scmi_fc_call, __entry->val2 = val2; ), - TP_printk("[0x%02X]:[0x%02X]:[%08X]:%u:%u", - __entry->protocol_id, __entry->msg_id, - __entry->res_id, __entry->val1, __entry->val2) + TP_printk("pt=%02X msg_id=%02X res_id:%u vals=%u:%u", + __entry->protocol_id, __entry->msg_id, + __entry->res_id, __entry->val1, __entry->val2) ); TRACE_EVENT(scmi_xfer_begin, @@ -53,9 +53,9 @@ TRACE_EVENT(scmi_xfer_begin, __entry->poll = poll; ), - TP_printk("transfer_id=%d msg_id=%u protocol_id=%u seq=%u poll=%u", - __entry->transfer_id, __entry->msg_id, __entry->protocol_id, - __entry->seq, __entry->poll) + TP_printk("pt=%02X msg_id=%02X seq=%04X transfer_id=%X poll=%u", + __entry->protocol_id, __entry->msg_id, __entry->seq, + __entry->transfer_id, __entry->poll) ); TRACE_EVENT(scmi_xfer_response_wait, @@ -81,9 +81,9 @@ TRACE_EVENT(scmi_xfer_response_wait, __entry->poll = poll; ), - TP_printk("transfer_id=%d msg_id=%u protocol_id=%u seq=%u tmo_ms=%u poll=%u", - __entry->transfer_id, __entry->msg_id, __entry->protocol_id, - __entry->seq, __entry->timeout, __entry->poll) + TP_printk("pt=%02X msg_id=%02X seq=%04X transfer_id=%X tmo_ms=%u poll=%u", + __entry->protocol_id, __entry->msg_id, __entry->seq, + __entry->transfer_id, __entry->timeout, __entry->poll) ); TRACE_EVENT(scmi_xfer_end, @@ -107,9 +107,9 @@ TRACE_EVENT(scmi_xfer_end, __entry->status = status; ), - TP_printk("transfer_id=%d msg_id=%u protocol_id=%u seq=%u status=%d", - __entry->transfer_id, __entry->msg_id, __entry->protocol_id, - __entry->seq, __entry->status) + TP_printk("pt=%02X msg_id=%02X seq=%04X transfer_id=%X s=%d", + __entry->protocol_id, __entry->msg_id, __entry->seq, + __entry->transfer_id, __entry->status) ); TRACE_EVENT(scmi_rx_done, @@ -133,9 +133,9 @@ TRACE_EVENT(scmi_rx_done, __entry->msg_type = msg_type; ), - TP_printk("transfer_id=%d msg_id=%u protocol_id=%u seq=%u msg_type=%u", - __entry->transfer_id, __entry->msg_id, __entry->protocol_id, - __entry->seq, __entry->msg_type) + TP_printk("pt=%02X msg_id=%02X seq=%04X transfer_id=%X msg_type=%u", + __entry->protocol_id, __entry->msg_id, __entry->seq, + __entry->transfer_id, __entry->msg_type) ); TRACE_EVENT(scmi_msg_dump, diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h index 6f5af1a84213..2573772e2fb3 100644 --- a/include/uapi/linux/sed-opal.h +++ b/include/uapi/linux/sed-opal.h @@ -132,6 +132,18 @@ struct opal_read_write_table { __u64 priv; }; +#define OPAL_FL_SUPPORTED 0x00000001 +#define OPAL_FL_LOCKING_SUPPORTED 0x00000002 +#define OPAL_FL_LOCKING_ENABLED 0x00000004 +#define OPAL_FL_LOCKED 0x00000008 +#define OPAL_FL_MBR_ENABLED 0x00000010 +#define OPAL_FL_MBR_DONE 0x00000020 + +struct opal_status { + __u32 flags; + __u32 reserved; +}; + #define IOC_OPAL_SAVE _IOW('p', 220, struct opal_lock_unlock) #define IOC_OPAL_LOCK_UNLOCK _IOW('p', 221, struct opal_lock_unlock) #define IOC_OPAL_TAKE_OWNERSHIP _IOW('p', 222, struct opal_key) @@ -148,5 +160,6 @@ struct opal_read_write_table { #define IOC_OPAL_MBR_DONE _IOW('p', 233, struct opal_mbr_done) #define IOC_OPAL_WRITE_SHADOW_MBR _IOW('p', 234, struct opal_shadow_mbr) #define IOC_OPAL_GENERIC_TABLE_RW _IOW('p', 235, struct opal_read_write_table) +#define IOC_OPAL_GET_STATUS _IOR('p', 236, struct opal_status) #endif /* _UAPI_SED_OPAL_H */ diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 677edaab2b66..8f88e3a29998 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -17,7 +17,8 @@ #define UBLK_CMD_STOP_DEV 0x07 #define UBLK_CMD_SET_PARAMS 0x08 #define UBLK_CMD_GET_PARAMS 0x09 - +#define UBLK_CMD_START_USER_RECOVERY 0x10 +#define UBLK_CMD_END_USER_RECOVERY 0x11 /* * IO commands, issued by ublk server, and handled by ublk driver. * @@ -74,9 +75,14 @@ */ #define UBLK_F_NEED_GET_DATA (1UL << 2) +#define UBLK_F_USER_RECOVERY (1UL << 3) + +#define UBLK_F_USER_RECOVERY_REISSUE (1UL << 4) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 +#define UBLK_S_DEV_QUIESCED 2 /* shipped via sqe->cmd of io_uring command */ struct ublksrv_ctrl_cmd { diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 62d1f55fde55..6e44186ba695 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1540,7 +1540,7 @@ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags) static bool io_bdev_nowait(struct block_device *bdev) { - return !bdev || blk_queue_nowait(bdev_get_queue(bdev)); + return !bdev || bdev_nowait(bdev); } /* @@ -2818,6 +2818,9 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_kill_timeouts(ctx, NULL, true); /* if we failed setting up the ctx, we might not have any rings */ io_iopoll_try_reap_events(ctx); + /* drop cached put refs after potentially doing completions */ + if (current->io_uring) + io_uring_drop_tctx_refs(current); } INIT_WORK(&ctx->exit_work, io_ring_exit_work); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e4bb5d57f4d1..5f2090d051ac 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6049,6 +6049,9 @@ struct cgroup *cgroup_get_from_id(u64 id) if (!kn) goto out; + if (kernfs_type(kn) != KERNFS_DIR) + goto put; + rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); @@ -6056,7 +6059,7 @@ struct cgroup *cgroup_get_from_id(u64 id) cgrp = NULL; rcu_read_unlock(); - +put: kernfs_put(kn); out: return cgrp; diff --git a/kernel/fork.c b/kernel/fork.c index 8a9e92068b15..2b6bd511c6ed 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2047,11 +2047,8 @@ static __latent_entropy struct task_struct *copy_process( /* * If the new process will be in a different time namespace * do not allow it to share VM or a thread group with the forking task. - * - * On vfork, the child process enters the target time namespace only - * after exec. */ - if ((clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM) { + if (clone_flags & (CLONE_THREAD | CLONE_VM)) { if (nsp->time_ns != nsp->time_ns_for_children) return ERR_PTR(-EINVAL); } diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index b4cbb406bc28..eec72ca962e2 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -179,8 +179,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) if (IS_ERR(new_ns)) return PTR_ERR(new_ns); - if ((flags & CLONE_VM) == 0) - timens_on_fork(new_ns, tsk); + timens_on_fork(new_ns, tsk); tsk->nsproxy = new_ns; return 0; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ecb4b4ff4ce0..7f6030091aee 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -917,6 +917,7 @@ void psi_memstall_enter(unsigned long *flags) rq_unlock_irq(rq, &rf); } +EXPORT_SYMBOL_GPL(psi_memstall_enter); /** * psi_memstall_leave - mark the end of an memory stall section @@ -946,6 +947,7 @@ void psi_memstall_leave(unsigned long *flags) rq_unlock_irq(rq, &rf); } +EXPORT_SYMBOL_GPL(psi_memstall_leave); #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgroup) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index aeea9731ef80..39060a5d0905 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3066,10 +3066,8 @@ static bool __flush_work(struct work_struct *work, bool from_cancel) if (WARN_ON(!work->func)) return false; - if (!from_cancel) { - lock_map_acquire(&work->lockdep_map); - lock_map_release(&work->lockdep_map); - } + lock_map_acquire(&work->lockdep_map); + lock_map_release(&work->lockdep_map); if (start_flush_work(work, &barr, from_cancel)) { wait_for_completion(&barr.done); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index bcbe60d6c80c..d3e5f36bb01e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -264,8 +264,10 @@ config DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT config DEBUG_INFO_DWARF4 bool "Generate DWARF Version 4 debuginfo" select DEBUG_INFO + depends on !CC_IS_CLANG || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502))) help - Generate DWARF v4 debug info. This requires gcc 4.5+ and gdb 7.0+. + Generate DWARF v4 debug info. This requires gcc 4.5+, binutils 2.35.2 + if using clang without clang's integrated assembler, and gdb 7.0+. If you have consumers of DWARF debug info that are not ready for newer revisions of DWARF, you may wish to choose this or have your diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 29eb0484215a..a8108a962dfd 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -533,21 +533,20 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, nr = find_first_zero_bit(&map->word, map_depth); if (nr + nr_tags <= map_depth) { atomic_long_t *ptr = (atomic_long_t *) &map->word; - int map_tags = min_t(int, nr_tags, map_depth); - unsigned long val, ret; + unsigned long val; - get_mask = ((1UL << map_tags) - 1) << nr; + get_mask = ((1UL << nr_tags) - 1) << nr; + val = READ_ONCE(map->word); do { - val = READ_ONCE(map->word); if ((val & ~get_mask) != val) goto next; - ret = atomic_long_cmpxchg(ptr, val, get_mask | val); - } while (ret != val); - get_mask = (get_mask & ~ret) >> nr; + } while (!atomic_long_try_cmpxchg(ptr, &val, + get_mask | val)); + get_mask = (get_mask & ~val) >> nr; if (get_mask) { *offset = nr + (index << sb->shift); update_alloc_hint_after_get(sb, depth, hint, - *offset + map_tags - 1); + *offset + nr_tags - 1); return get_mask; } } @@ -588,7 +587,7 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) for (i = 0; i < SBQ_WAIT_QUEUES; i++) { struct sbq_wait_state *ws = &sbq->ws[wake_index]; - if (waitqueue_active(&ws->wait)) { + if (waitqueue_active(&ws->wait) && atomic_read(&ws->wait_cnt)) { if (wake_index != atomic_read(&sbq->wake_index)) atomic_set(&sbq->wake_index, wake_index); return ws; @@ -600,50 +599,82 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) return NULL; } -static bool __sbq_wake_up(struct sbitmap_queue *sbq) +static bool __sbq_wake_up(struct sbitmap_queue *sbq, int *nr) { struct sbq_wait_state *ws; unsigned int wake_batch; - int wait_cnt; + int wait_cnt, cur, sub; + bool ret; + + if (*nr <= 0) + return false; ws = sbq_wake_ptr(sbq); if (!ws) return false; - wait_cnt = atomic_dec_return(&ws->wait_cnt); - if (wait_cnt <= 0) { - int ret; - - wake_batch = READ_ONCE(sbq->wake_batch); - + cur = atomic_read(&ws->wait_cnt); + do { /* - * Pairs with the memory barrier in sbitmap_queue_resize() to - * ensure that we see the batch size update before the wait - * count is reset. + * For concurrent callers of this, callers should call this + * function again to wakeup a new batch on a different 'ws'. */ - smp_mb__before_atomic(); + if (cur == 0) + return true; + sub = min(*nr, cur); + wait_cnt = cur - sub; + } while (!atomic_try_cmpxchg(&ws->wait_cnt, &cur, wait_cnt)); - /* - * For concurrent callers of this, the one that failed the - * atomic_cmpxhcg() race should call this function again - * to wakeup a new batch on a different 'ws'. - */ - ret = atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wake_batch); - if (ret == wait_cnt) { - sbq_index_atomic_inc(&sbq->wake_index); - wake_up_nr(&ws->wait, wake_batch); - return false; - } + /* + * If we decremented queue without waiters, retry to avoid lost + * wakeups. + */ + if (wait_cnt > 0) + return !waitqueue_active(&ws->wait); - return true; - } + *nr -= sub; - return false; + /* + * When wait_cnt == 0, we have to be particularly careful as we are + * responsible to reset wait_cnt regardless whether we've actually + * woken up anybody. But in case we didn't wakeup anybody, we still + * need to retry. + */ + ret = !waitqueue_active(&ws->wait); + wake_batch = READ_ONCE(sbq->wake_batch); + + /* + * Wake up first in case that concurrent callers decrease wait_cnt + * while waitqueue is empty. + */ + wake_up_nr(&ws->wait, wake_batch); + + /* + * Pairs with the memory barrier in sbitmap_queue_resize() to + * ensure that we see the batch size update before the wait + * count is reset. + * + * Also pairs with the implicit barrier between decrementing wait_cnt + * and checking for waitqueue_active() to make sure waitqueue_active() + * sees result of the wakeup if atomic_dec_return() has seen the result + * of atomic_set(). + */ + smp_mb__before_atomic(); + + /* + * Increase wake_index before updating wait_cnt, otherwise concurrent + * callers can see valid wait_cnt in old waitqueue, which can cause + * invalid wakeup on the old waitqueue. + */ + sbq_index_atomic_inc(&sbq->wake_index); + atomic_set(&ws->wait_cnt, wake_batch); + + return ret || *nr; } -void sbitmap_queue_wake_up(struct sbitmap_queue *sbq) +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq, int nr) { - while (__sbq_wake_up(sbq)) + while (__sbq_wake_up(sbq, &nr)) ; } EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up); @@ -683,7 +714,7 @@ void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset, atomic_long_andnot(mask, (atomic_long_t *) addr); smp_mb__after_atomic(); - sbitmap_queue_wake_up(sbq); + sbitmap_queue_wake_up(sbq, nr_tags); sbitmap_update_cpu_hint(&sbq->sb, raw_smp_processor_id(), tags[nr_tags - 1] - offset); } @@ -711,7 +742,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, * waiter. See the comment on waitqueue_active(). */ smp_mb__after_atomic(); - sbitmap_queue_wake_up(sbq); + sbitmap_queue_wake_up(sbq, 1); sbitmap_update_cpu_hint(&sbq->sb, cpu, nr); } EXPORT_SYMBOL_GPL(sbitmap_queue_clear); diff --git a/mm/filemap.c b/mm/filemap.c index 15800334147b..c943d1b90cc2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2382,6 +2382,8 @@ retry: static int filemap_read_folio(struct file *file, filler_t filler, struct folio *folio) { + bool workingset = folio_test_workingset(folio); + unsigned long pflags; int error; /* @@ -2390,8 +2392,13 @@ static int filemap_read_folio(struct file *file, filler_t filler, * fails. */ folio_clear_error(folio); + /* Start the actual read. The read will unlock the page. */ + if (unlikely(workingset)) + psi_memstall_enter(&pflags); error = filler(file, folio); + if (unlikely(workingset)) + psi_memstall_leave(&pflags); if (error) return error; diff --git a/mm/readahead.c b/mm/readahead.c index fdcd28cbd92d..b10f0cf81d80 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -122,6 +122,7 @@ #include <linux/task_io_accounting_ops.h> #include <linux/pagevec.h> #include <linux/pagemap.h> +#include <linux/psi.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> @@ -152,6 +153,8 @@ static void read_pages(struct readahead_control *rac) if (!readahead_count(rac)) return; + if (unlikely(rac->_workingset)) + psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { @@ -179,6 +182,9 @@ static void read_pages(struct readahead_control *rac) } blk_finish_plug(&plug); + if (unlikely(rac->_workingset)) + psi_memstall_leave(&rac->_pflags); + rac->_workingset = false; BUG_ON(readahead_count(rac)); } @@ -252,6 +258,7 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, } if (i == nr_to_read - lookahead_size) folio_set_readahead(folio); + ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages++; } @@ -480,11 +487,14 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); - if (err) + if (err) { folio_put(folio); - else - ractl->_nr_pages += 1UL << order; - return err; + return err; + } + + ractl->_nr_pages += 1UL << order; + ractl->_workingset |= folio_test_workingset(folio); + return 0; } void page_cache_ra_order(struct readahead_control *ractl, @@ -826,6 +836,10 @@ void readahead_expand(struct readahead_control *ractl, put_page(page); return; } + if (unlikely(PageWorkingset(page)) && !ractl->_workingset) { + ractl->_workingset = true; + psi_memstall_enter(&ractl->_pflags); + } ractl->_nr_pages++; if (ra) { ra->size++; diff --git a/mm/slab_common.c b/mm/slab_common.c index 07b948288f84..ccc02573588f 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -475,6 +475,7 @@ void slab_kmem_cache_release(struct kmem_cache *s) void kmem_cache_destroy(struct kmem_cache *s) { int refcnt; + bool rcu_set; if (unlikely(!s) || !kasan_check_byte(s)) return; @@ -482,6 +483,8 @@ void kmem_cache_destroy(struct kmem_cache *s) cpus_read_lock(); mutex_lock(&slab_mutex); + rcu_set = s->flags & SLAB_TYPESAFE_BY_RCU; + refcnt = --s->refcount; if (refcnt) goto out_unlock; @@ -492,7 +495,7 @@ void kmem_cache_destroy(struct kmem_cache *s) out_unlock: mutex_unlock(&slab_mutex); cpus_read_unlock(); - if (!refcnt && !(s->flags & SLAB_TYPESAFE_BY_RCU)) + if (!refcnt && !rcu_set) kmem_cache_release(s); } EXPORT_SYMBOL(kmem_cache_destroy); diff --git a/mm/slub.c b/mm/slub.c index 862dbd9af4f5..4b98dff9be8e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -310,6 +310,11 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si) */ static nodemask_t slab_nodes; +/* + * Workqueue used for flush_cpu_slab(). + */ +static struct workqueue_struct *flushwq; + /******************************************************************** * Core slab cache functions *******************************************************************/ @@ -2730,7 +2735,7 @@ static void flush_all_cpus_locked(struct kmem_cache *s) INIT_WORK(&sfw->work, flush_cpu_slab); sfw->skip = false; sfw->s = s; - schedule_work_on(cpu, &sfw->work); + queue_work_on(cpu, flushwq, &sfw->work); } for_each_online_cpu(cpu) { @@ -4858,6 +4863,8 @@ void __init kmem_cache_init(void) void __init kmem_cache_init_late(void) { + flushwq = alloc_workqueue("slub_flushwq", WQ_MEM_RECLAIM, 0); + WARN_ON(!flushwq); } struct kmem_cache * @@ -4926,6 +4933,8 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) /* Honor the call site pointer we received. */ trace_kmalloc(caller, ret, s, size, s->size, gfpflags); + ret = kasan_kmalloc(s, ret, size, gfpflags); + return ret; } EXPORT_SYMBOL(__kmalloc_track_caller); @@ -4957,6 +4966,8 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, /* Honor the call site pointer we received. */ trace_kmalloc_node(caller, ret, s, size, s->size, gfpflags, node); + ret = kasan_kmalloc(s, ret, size, gfpflags); + return ret; } EXPORT_SYMBOL(__kmalloc_node_track_caller); @@ -5890,7 +5901,8 @@ static char *create_unique_id(struct kmem_cache *s) char *name = kmalloc(ID_STR_LENGTH, GFP_KERNEL); char *p = name; - BUG_ON(!name); + if (!name) + return ERR_PTR(-ENOMEM); *p++ = ':'; /* @@ -5948,6 +5960,8 @@ static int sysfs_slab_add(struct kmem_cache *s) * for the symlinks. */ name = create_unique_id(s); + if (IS_ERR(name)) + return PTR_ERR(name); } s->kobj.kset = kset; diff --git a/mm/swapfile.c b/mm/swapfile.c index 1fdccd2f1422..82e62007881d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3655,7 +3655,7 @@ void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { - blkcg_schedule_throttle(bdev_get_queue(si->bdev), true); + blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index b8f8da7ee3de..41c1ad33d009 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -10,6 +10,7 @@ #include <linux/atomic.h> #include <linux/byteorder/generic.h> #include <linux/container_of.h> +#include <linux/errno.h> #include <linux/gfp.h> #include <linux/if.h> #include <linux/if_arp.h> @@ -700,6 +701,9 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, int max_header_len = batadv_max_header_len(); int ret; + if (hard_iface->net_dev->mtu < ETH_MIN_MTU + max_header_len) + return -EINVAL; + if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) goto out; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 9a0ae59cdc50..4f385d52a1c4 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1040,8 +1040,10 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, goto free_iterate; } - if (repl->valid_hooks != t->valid_hooks) + if (repl->valid_hooks != t->valid_hooks) { + ret = -EINVAL; goto free_unlock; + } if (repl->num_counters && repl->num_counters != t->private->nentries) { ret = -EINVAL; diff --git a/net/compat.c b/net/compat.c index fe9be3c56ef7..385f04a6be2f 100644 --- a/net/compat.c +++ b/net/compat.c @@ -52,6 +52,7 @@ int __get_compat_msghdr(struct msghdr *kmsg, kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_control_is_user = true; + kmsg->msg_get_inq = 0; kmsg->msg_control_user = compat_ptr(msg->msg_control); kmsg->msg_controllen = msg->msg_controllen; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 764c4cb3fe8f..5dc3860e9fc7 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1611,9 +1611,8 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) switch (keys->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: - addr_diff = (__force u32)keys->addrs.v4addrs.dst - - (__force u32)keys->addrs.v4addrs.src; - if (addr_diff < 0) + if ((__force u32)keys->addrs.v4addrs.dst < + (__force u32)keys->addrs.v4addrs.src) swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst); if ((__force u16)keys->ports.dst < diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index 718fb77bb372..7889e1ef7fad 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -200,8 +200,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len) int err = 0; struct net_device *dev = NULL; - if (len < sizeof(*uaddr)) - return -EINVAL; + err = ieee802154_sockaddr_check_size(uaddr, len); + if (err < 0) + return err; uaddr = (struct sockaddr_ieee802154 *)_uaddr; if (uaddr->family != AF_IEEE802154) @@ -493,7 +494,8 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) ro->bound = 0; - if (len < sizeof(*addr)) + err = ieee802154_sockaddr_check_size(addr, len); + if (err < 0) goto out; if (addr->family != AF_IEEE802154) @@ -564,8 +566,9 @@ static int dgram_connect(struct sock *sk, struct sockaddr *uaddr, struct dgram_sock *ro = dgram_sk(sk); int err = 0; - if (len < sizeof(*addr)) - return -EINVAL; + err = ieee802154_sockaddr_check_size(addr, len); + if (err < 0) + return err; if (addr->family != AF_IEEE802154) return -EINVAL; @@ -604,6 +607,7 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) struct ieee802154_mac_cb *cb; struct dgram_sock *ro = dgram_sk(sk); struct ieee802154_addr dst_addr; + DECLARE_SOCKADDR(struct sockaddr_ieee802154*, daddr, msg->msg_name); int hlen, tlen; int err; @@ -612,10 +616,20 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) return -EOPNOTSUPP; } - if (!ro->connected && !msg->msg_name) - return -EDESTADDRREQ; - else if (ro->connected && msg->msg_name) - return -EISCONN; + if (msg->msg_name) { + if (ro->connected) + return -EISCONN; + if (msg->msg_namelen < IEEE802154_MIN_NAMELEN) + return -EINVAL; + err = ieee802154_sockaddr_check_size(daddr, msg->msg_namelen); + if (err < 0) + return err; + ieee802154_addr_from_sa(&dst_addr, &daddr->addr); + } else { + if (!ro->connected) + return -EDESTADDRREQ; + dst_addr = ro->dst_addr; + } if (!ro->bound) dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154); @@ -651,16 +665,6 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) cb = mac_cb_init(skb); cb->type = IEEE802154_FC_TYPE_DATA; cb->ackreq = ro->want_ack; - - if (msg->msg_name) { - DECLARE_SOCKADDR(struct sockaddr_ieee802154*, - daddr, msg->msg_name); - - ieee802154_addr_from_sa(&dst_addr, &daddr->addr); - } else { - dst_addr = ro->dst_addr; - } - cb->secen = ro->secen; cb->secen_override = ro->secen_override; cb->seclevel = ro->seclevel; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 73651d17e51f..e11d6b0b62b7 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1004,7 +1004,9 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { + rcu_read_lock(); ip_mr_forward(net, mrt, skb->dev, skb, c, 0); + rcu_read_unlock(); } } } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6cdfce6f2867..e373dde1f46f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1761,19 +1761,28 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; - skb = tcp_recv_skb(sk, seq, &offset); - if (!skb) - return 0; + while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { + u8 tcp_flags; + int used; - __skb_unlink(skb, &sk->sk_receive_queue); - WARN_ON(!skb_set_owner_sk_safe(skb, sk)); - copied = recv_actor(sk, skb); - if (copied >= 0) { - seq += copied; - if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + __skb_unlink(skb, &sk->sk_receive_queue); + WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); + tcp_flags = TCP_SKB_CB(skb)->tcp_flags; + used = recv_actor(sk, skb); + consume_skb(skb); + if (used < 0) { + if (!copied) + copied = used; + break; + } + seq += used; + copied += used; + + if (tcp_flags & TCPHDR_FIN) { ++seq; + break; + } } - consume_skb(skb); WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index cd72158e953a..560d9eadeaa5 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1821,7 +1821,7 @@ int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) continue; } - WARN_ON(!skb_set_owner_sk_safe(skb, sk)); + WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); used = recv_actor(sk, skb); if (used <= 0) { if (!copied) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 2ce0c44d0081..dbb1430d6cc2 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1070,13 +1070,13 @@ static int __init inet6_init(void) for (r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) INIT_LIST_HEAD(r); + raw_hashinfo_init(&raw_v6_hashinfo); + if (disable_ipv6_mod) { pr_info("Loaded, but administratively disabled, reboot required to enable\n"); goto out; } - raw_hashinfo_init(&raw_v6_hashinfo); - err = proto_register(&tcpv6_prot, 1); if (err) goto out; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index a9ba41648e36..858fd8a28b5b 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1028,8 +1028,11 @@ static void ip6mr_cache_resolve(struct net *net, struct mr_table *mrt, ((struct nlmsgerr *)nlmsg_data(nlh))->error = -EMSGSIZE; } rtnl_unicast(skb, net, NETLINK_CB(skb).portid); - } else + } else { + rcu_read_lock(); ip6_mr_forward(net, mrt, skb->dev, skb, c); + rcu_read_unlock(); + } } } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index d398f3810662..969b33a9dd64 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -150,9 +150,15 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq, to->len, MPTCP_SKB_CB(from)->end_seq); MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq; - kfree_skb_partial(from, fragstolen); + + /* note the fwd memory can reach a negative value after accounting + * for the delta, but the later skb free will restore a non + * negative one + */ atomic_add(delta, &sk->sk_rmem_alloc); mptcp_rmem_charge(sk, delta); + kfree_skb_partial(from, fragstolen); + return true; } diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 0d9332e9cf71..617f744a2e3a 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -33,6 +33,7 @@ MODULE_AUTHOR("Rusty Russell <[email protected]>"); MODULE_DESCRIPTION("ftp connection tracking helper"); MODULE_ALIAS("ip_conntrack_ftp"); MODULE_ALIAS_NFCT_HELPER(HELPER_NAME); +static DEFINE_SPINLOCK(nf_ftp_lock); #define MAX_PORTS 8 static u_int16_t ports[MAX_PORTS]; @@ -409,7 +410,8 @@ static int help(struct sk_buff *skb, } datalen = skb->len - dataoff; - spin_lock_bh(&ct->lock); + /* seqadj (nat) uses ct->lock internally, nf_nat_ftp would cause deadlock */ + spin_lock_bh(&nf_ftp_lock); fb_ptr = skb->data + dataoff; ends_in_nl = (fb_ptr[datalen - 1] == '\n'); @@ -538,7 +540,7 @@ out_update_nl: if (ends_in_nl) update_nl_seq(ct, seq, ct_ftp_info, dir, skb); out: - spin_unlock_bh(&ct->lock); + spin_unlock_bh(&nf_ftp_lock); return ret; } diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 992decbcaa5c..5703846bea3b 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -157,15 +157,37 @@ static int help(struct sk_buff *skb, unsigned int protoff, data = ib_ptr; data_limit = ib_ptr + datalen; - /* strlen("\1DCC SENT t AAAAAAAA P\1\n")=24 - * 5+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=14 */ - while (data < data_limit - (19 + MINMATCHLEN)) { - if (memcmp(data, "\1DCC ", 5)) { + /* Skip any whitespace */ + while (data < data_limit - 10) { + if (*data == ' ' || *data == '\r' || *data == '\n') + data++; + else + break; + } + + /* strlen("PRIVMSG x ")=10 */ + if (data < data_limit - 10) { + if (strncasecmp("PRIVMSG ", data, 8)) + goto out; + data += 8; + } + + /* strlen(" :\1DCC SENT t AAAAAAAA P\1\n")=26 + * 7+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=26 + */ + while (data < data_limit - (21 + MINMATCHLEN)) { + /* Find first " :", the start of message */ + if (memcmp(data, " :", 2)) { data++; continue; } + data += 2; + + /* then check that place only for the DCC command */ + if (memcmp(data, "\1DCC ", 5)) + goto out; data += 5; - /* we have at least (19+MINMATCHLEN)-5 bytes valid data left */ + /* we have at least (21+MINMATCHLEN)-(2+5) bytes valid data left */ iph = ip_hdr(skb); pr_debug("DCC found in master %pI4:%u %pI4:%u\n", @@ -181,7 +203,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, pr_debug("DCC %s detected\n", dccprotos[i]); /* we have at least - * (19+MINMATCHLEN)-5-dccprotos[i].matchlen bytes valid + * (21+MINMATCHLEN)-7-dccprotos[i].matchlen bytes valid * data left (== 14/13 bytes) */ if (parse_dcc(data, data_limit, &dcc_ip, &dcc_port, &addr_beg_p, &addr_end_p)) { diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index daf06f71d31c..77f5e82d8e3f 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -477,7 +477,7 @@ static int ct_sip_walk_headers(const struct nf_conn *ct, const char *dptr, return ret; if (ret == 0) break; - dataoff += *matchoff; + dataoff = *matchoff; } *in_header = 0; } @@ -489,7 +489,7 @@ static int ct_sip_walk_headers(const struct nf_conn *ct, const char *dptr, break; if (ret == 0) return ret; - dataoff += *matchoff; + dataoff = *matchoff; } if (in_header) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 816052089b33..63c70141b3e5 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2197,7 +2197,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; - struct nft_stats __percpu *stats = NULL; struct nft_table *table = ctx->table; struct nft_base_chain *basechain; struct net *net = ctx->net; @@ -2212,6 +2211,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, return -EOVERFLOW; if (nla[NFTA_CHAIN_HOOK]) { + struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook; if (flags & NFT_CHAIN_BINDING) @@ -2243,8 +2243,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (err < 0) { nft_chain_release_hook(&hook); kfree(basechain); + free_percpu(stats); return err; } + if (stats) + static_branch_inc(&nft_counters_enabled); } else { if (flags & NFT_CHAIN_BASE) return -EINVAL; @@ -2319,9 +2322,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, goto err_unregister_hook; } - if (stats) - static_branch_inc(&nft_counters_enabled); - table->use++; return 0; diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 0fa2e2030427..ee6840bd5933 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -269,6 +269,7 @@ bool nf_osf_find(const struct sk_buff *skb, struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; struct tcphdr _tcph; + bool found = false; memset(&ctx, 0, sizeof(ctx)); @@ -283,10 +284,11 @@ bool nf_osf_find(const struct sk_buff *skb, data->genre = f->genre; data->version = f->version; + found = true; break; } - return true; + return found; } EXPORT_SYMBOL_GPL(nf_osf_find); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 790d6809be81..51d175f3fbcb 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2137,6 +2137,7 @@ replay: } if (chain->tmplt_ops && chain->tmplt_ops != tp->ops) { + tfilter_put(tp, fh); NL_SET_ERR_MSG(extack, "Chain template is set to a different filter kind"); err = -EINVAL; goto errout; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 0b941dd63d26..86675a79da1e 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -67,6 +67,7 @@ struct taprio_sched { u32 flags; enum tk_offsets tk_offset; int clockid; + bool offloaded; atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+ * speeds it's sub-nanoseconds per byte */ @@ -1279,6 +1280,8 @@ static int taprio_enable_offload(struct net_device *dev, goto done; } + q->offloaded = true; + done: taprio_offload_free(offload); @@ -1293,12 +1296,9 @@ static int taprio_disable_offload(struct net_device *dev, struct tc_taprio_qopt_offload *offload; int err; - if (!FULL_OFFLOAD_IS_ENABLED(q->flags)) + if (!q->offloaded) return 0; - if (!ops->ndo_setup_tc) - return -EOPNOTSUPP; - offload = taprio_offload_alloc(0); if (!offload) { NL_SET_ERR_MSG(extack, @@ -1314,6 +1314,8 @@ static int taprio_disable_offload(struct net_device *dev, goto out; } + q->offloaded = false; + out: taprio_offload_free(offload); @@ -1949,12 +1951,14 @@ start_error: static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) { - struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx = cl - 1; - if (!dev_queue) + if (ntx >= dev->num_tx_queues) return NULL; - return dev_queue->qdisc_sleeping; + return q->qdiscs[ntx]; } static unsigned long taprio_find(struct Qdisc *sch, u32 classid) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index ebf56cdf17db..df89c2e08cbf 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -2239,7 +2239,7 @@ out: static int smcr_buf_map_usable_links(struct smc_link_group *lgr, struct smc_buf_desc *buf_desc, bool is_rmb) { - int i, rc = 0; + int i, rc = 0, cnt = 0; /* protect against parallel link reconfiguration */ mutex_lock(&lgr->llc_conf_mutex); @@ -2252,9 +2252,12 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr, rc = -ENOMEM; goto out; } + cnt++; } out: mutex_unlock(&lgr->llc_conf_mutex); + if (!rc && !cnt) + rc = -EINVAL; return rc; } diff --git a/scripts/Makefile.debug b/scripts/Makefile.debug index 9f39b0130551..8cf1cb22dd93 100644 --- a/scripts/Makefile.debug +++ b/scripts/Makefile.debug @@ -1,20 +1,19 @@ DEBUG_CFLAGS := +debug-flags-y := -g ifdef CONFIG_DEBUG_INFO_SPLIT DEBUG_CFLAGS += -gsplit-dwarf -else -DEBUG_CFLAGS += -g endif -ifndef CONFIG_AS_IS_LLVM -KBUILD_AFLAGS += -Wa,-gdwarf-2 -endif - -ifndef CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT -dwarf-version-$(CONFIG_DEBUG_INFO_DWARF4) := 4 -dwarf-version-$(CONFIG_DEBUG_INFO_DWARF5) := 5 -DEBUG_CFLAGS += -gdwarf-$(dwarf-version-y) +debug-flags-$(CONFIG_DEBUG_INFO_DWARF4) += -gdwarf-4 +debug-flags-$(CONFIG_DEBUG_INFO_DWARF5) += -gdwarf-5 +ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_AS_IS_GNU),yy) +# Clang does not pass -g or -gdwarf-* option down to GAS. +# Add -Wa, prefix to explicitly specify the flags. +KBUILD_AFLAGS += $(addprefix -Wa$(comma), $(debug-flags-y)) endif +DEBUG_CFLAGS += $(debug-flags-y) +KBUILD_AFLAGS += $(debug-flags-y) ifdef CONFIG_DEBUG_INFO_REDUCED DEBUG_CFLAGS += -fno-var-tracking @@ -29,5 +28,5 @@ KBUILD_AFLAGS += -gz=zlib KBUILD_LDFLAGS += --compress-debug-sections=zlib endif -KBUILD_CFLAGS += $(DEBUG_CFLAGS) +KBUILD_CFLAGS += $(DEBUG_CFLAGS) export DEBUG_CFLAGS diff --git a/scripts/clang-tools/run-clang-tools.py b/scripts/clang-tools/run-clang-tools.py index 1337cedca096..bb78c9bde55c 100755 --- a/scripts/clang-tools/run-clang-tools.py +++ b/scripts/clang-tools/run-clang-tools.py @@ -12,7 +12,6 @@ compile_commands.json. import argparse import json import multiprocessing -import os import subprocess import sys diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h index fa8c010aa683..c396aa104090 100644 --- a/scripts/kconfig/lkc.h +++ b/scripts/kconfig/lkc.h @@ -98,7 +98,6 @@ bool menu_is_empty(struct menu *menu); bool menu_is_visible(struct menu *menu); bool menu_has_prompt(struct menu *menu); const char *menu_get_prompt(struct menu *menu); -struct menu *menu_get_root_menu(struct menu *menu); struct menu *menu_get_parent_menu(struct menu *menu); bool menu_has_help(struct menu *menu); const char *menu_get_help(struct menu *menu); diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index 3d6f7cba8846..62b6313f51c8 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -661,11 +661,6 @@ const char *menu_get_prompt(struct menu *menu) return NULL; } -struct menu *menu_get_root_menu(struct menu *menu) -{ - return &rootmenu; -} - struct menu *menu_get_parent_menu(struct menu *menu) { enum prop_type type; diff --git a/sound/core/init.c b/sound/core/init.c index 193dae361fac..5377f94eb211 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -178,10 +178,8 @@ int snd_card_new(struct device *parent, int idx, const char *xid, return -ENOMEM; err = snd_card_init(card, parent, idx, xid, module, extra_size); - if (err < 0) { - kfree(card); - return err; - } + if (err < 0) + return err; /* card is freed by error handler */ *card_ret = card; return 0; @@ -233,7 +231,7 @@ int snd_devm_card_new(struct device *parent, int idx, const char *xid, card->managed = true; err = snd_card_init(card, parent, idx, xid, module, extra_size); if (err < 0) { - devres_free(card); + devres_free(card); /* in managed mode, we need to free manually */ return err; } @@ -297,6 +295,8 @@ static int snd_card_init(struct snd_card *card, struct device *parent, mutex_unlock(&snd_card_mutex); dev_err(parent, "cannot find the slot for index %d (range 0-%i), error: %d\n", idx, snd_ecards_limit - 1, err); + if (!card->managed) + kfree(card); /* manually free here, as no destructor called */ return err; } set_bit(idx, snd_cards_lock); /* lock it */ diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c index cae9a975cbcc..1a868dd9dc4b 100644 --- a/sound/pci/hda/hda_bind.c +++ b/sound/pci/hda/hda_bind.c @@ -157,10 +157,10 @@ static int hda_codec_driver_remove(struct device *dev) return codec->bus->core.ext_ops->hdev_detach(&codec->core); } - refcount_dec(&codec->pcm_ref); snd_hda_codec_disconnect_pcms(codec); snd_hda_jack_tbl_disconnect(codec); - wait_event(codec->remove_sleep, !refcount_read(&codec->pcm_ref)); + if (!refcount_dec_and_test(&codec->pcm_ref)) + wait_event(codec->remove_sleep, !refcount_read(&codec->pcm_ref)); snd_power_sync_ref(codec->bus->card); if (codec->patch_ops.free) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index b20694fd69de..6f30c374f896 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2550,6 +2550,8 @@ static const struct pci_device_id azx_ids[] = { /* 5 Series/3400 */ { PCI_DEVICE(0x8086, 0x3b56), .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_NOPM }, + { PCI_DEVICE(0x8086, 0x3b57), + .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_NOPM }, /* Poulsbo */ { PCI_DEVICE(0x8086, 0x811b), .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_BASE }, diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 6c209cd26c0c..c239d9dbbaef 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -170,6 +170,8 @@ struct hdmi_spec { bool dyn_pcm_no_legacy; /* hdmi interrupt trigger control flag for Nvidia codec */ bool hdmi_intr_trig_ctrl; + bool nv_dp_workaround; /* workaround DP audio infoframe for Nvidia */ + bool intel_hsw_fixup; /* apply Intel platform-specific fixups */ /* * Non-generic VIA/NVIDIA specific @@ -679,15 +681,24 @@ static void hdmi_pin_setup_infoframe(struct hda_codec *codec, int ca, int active_channels, int conn_type) { + struct hdmi_spec *spec = codec->spec; union audio_infoframe ai; memset(&ai, 0, sizeof(ai)); - if (conn_type == 0) { /* HDMI */ + if ((conn_type == 0) || /* HDMI */ + /* Nvidia DisplayPort: Nvidia HW expects same layout as HDMI */ + (conn_type == 1 && spec->nv_dp_workaround)) { struct hdmi_audio_infoframe *hdmi_ai = &ai.hdmi; - hdmi_ai->type = 0x84; - hdmi_ai->ver = 0x01; - hdmi_ai->len = 0x0a; + if (conn_type == 0) { /* HDMI */ + hdmi_ai->type = 0x84; + hdmi_ai->ver = 0x01; + hdmi_ai->len = 0x0a; + } else {/* Nvidia DP */ + hdmi_ai->type = 0x84; + hdmi_ai->ver = 0x1b; + hdmi_ai->len = 0x11 << 2; + } hdmi_ai->CC02_CT47 = active_channels - 1; hdmi_ai->CA = ca; hdmi_checksum_audio_infoframe(hdmi_ai); @@ -1267,6 +1278,7 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo, set_bit(pcm_idx, &spec->pcm_in_use); per_pin = get_pin(spec, pin_idx); per_pin->cvt_nid = per_cvt->cvt_nid; + per_pin->silent_stream = false; hinfo->nid = per_cvt->cvt_nid; /* flip stripe flag for the assigned stream if supported */ @@ -3617,6 +3629,7 @@ static int patch_nvhdmi_2ch(struct hda_codec *codec) spec->pcm_playback.rates = SUPPORTED_RATES; spec->pcm_playback.maxbps = SUPPORTED_MAXBPS; spec->pcm_playback.formats = SUPPORTED_FORMATS; + spec->nv_dp_workaround = true; return 0; } @@ -3756,6 +3769,7 @@ static int patch_nvhdmi(struct hda_codec *codec) spec->chmap.ops.chmap_cea_alloc_validate_get_type = nvhdmi_chmap_cea_alloc_validate_get_type; spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate; + spec->nv_dp_workaround = true; codec->link_down_at_suspend = 1; @@ -3779,6 +3793,7 @@ static int patch_nvhdmi_legacy(struct hda_codec *codec) spec->chmap.ops.chmap_cea_alloc_validate_get_type = nvhdmi_chmap_cea_alloc_validate_get_type; spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate; + spec->nv_dp_workaround = true; codec->link_down_at_suspend = 1; @@ -3984,6 +3999,7 @@ static int tegra_hdmi_init(struct hda_codec *codec) generic_hdmi_init_per_pins(codec); + codec->depop_delay = 10; codec->patch_ops.build_pcms = tegra_hdmi_build_pcms; spec->chmap.ops.chmap_cea_alloc_validate_get_type = nvhdmi_chmap_cea_alloc_validate_get_type; @@ -3992,6 +4008,7 @@ static int tegra_hdmi_init(struct hda_codec *codec) spec->chmap.ops.chmap_cea_alloc_validate_get_type = nvhdmi_chmap_cea_alloc_validate_get_type; spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate; + spec->nv_dp_workaround = true; return 0; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 38930cf5aace..f9d46ae4c7b7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7067,6 +7067,8 @@ enum { ALC294_FIXUP_ASUS_GU502_HP, ALC294_FIXUP_ASUS_GU502_PINS, ALC294_FIXUP_ASUS_GU502_VERBS, + ALC294_FIXUP_ASUS_G513_PINS, + ALC285_FIXUP_ASUS_G533Z_PINS, ALC285_FIXUP_HP_GPIO_LED, ALC285_FIXUP_HP_MUTE_LED, ALC236_FIXUP_HP_GPIO_LED, @@ -8406,6 +8408,24 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc294_fixup_gu502_hp, }, + [ALC294_FIXUP_ASUS_G513_PINS] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, /* front HP mic */ + { 0x1a, 0x03a11c30 }, /* rear external mic */ + { 0x21, 0x03211420 }, /* front HP out */ + { } + }, + }, + [ALC285_FIXUP_ASUS_G533Z_PINS] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x14, 0x90170120 }, + { } + }, + .chained = true, + .chain_id = ALC294_FIXUP_ASUS_G513_PINS, + }, [ALC294_FIXUP_ASUS_COEF_1B] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -9149,6 +9169,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0872, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB), + SND_PCI_QUIRK(0x1028, 0x087d, "Dell Precision 5530", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB), @@ -9165,6 +9186,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { 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, 0x0b19, "Dell XPS 15 9520", ALC289_FIXUP_DUAL_SPK), + SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK), 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), @@ -9292,6 +9314,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8971, "HP EliteBook 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8972, "HP EliteBook 840 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9339,10 +9362,11 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), + SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), + SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS), SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK), - SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS), SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), @@ -9358,14 +9382,16 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), + SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS), + SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS), SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), - SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), - SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), @@ -9569,6 +9595,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD), SND_PCI_QUIRK(0x1849, 0x1233, "ASRock NUC Box 1100", ALC233_FIXUP_NO_AUDIO_JACK), SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS), + SND_PCI_QUIRK(0x19e5, 0x320f, "Huawei WRT-WX9 ", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1b35, 0x1235, "CZC B20", ALC269_FIXUP_CZC_B20), SND_PCI_QUIRK(0x1b35, 0x1236, "CZC TMI", ALC269_FIXUP_CZC_TMI), SND_PCI_QUIRK(0x1b35, 0x1237, "CZC L101", ALC269_FIXUP_CZC_L101), diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 8c8f9a851f89..eb71df9da831 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -758,8 +758,7 @@ bool snd_usb_endpoint_compatible(struct snd_usb_audio *chip, * The endpoint needs to be closed via snd_usb_endpoint_close() later. * * Note that this function doesn't configure the endpoint. The substream - * needs to set it up later via snd_usb_endpoint_set_params() and - * snd_usb_endpoint_prepare(). + * needs to set it up later via snd_usb_endpoint_configure(). */ struct snd_usb_endpoint * snd_usb_endpoint_open(struct snd_usb_audio *chip, @@ -1293,13 +1292,12 @@ out_of_memory: /* * snd_usb_endpoint_set_params: configure an snd_usb_endpoint * - * It's called either from hw_params callback. * Determine the number of URBs to be used on this endpoint. * An endpoint must be configured before it can be started. * An endpoint that is already running can not be reconfigured. */ -int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, - struct snd_usb_endpoint *ep) +static int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, + struct snd_usb_endpoint *ep) { const struct audioformat *fmt = ep->cur_audiofmt; int err; @@ -1382,18 +1380,18 @@ static int init_sample_rate(struct snd_usb_audio *chip, } /* - * snd_usb_endpoint_prepare: Prepare the endpoint + * snd_usb_endpoint_configure: Configure the endpoint * * This function sets up the EP to be fully usable state. - * It's called either from prepare callback. + * It's called either from hw_params or prepare callback. * The function checks need_setup flag, and performs nothing unless needed, * so it's safe to call this multiple times. * * This returns zero if unchanged, 1 if the configuration has changed, * or a negative error code. */ -int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, - struct snd_usb_endpoint *ep) +int snd_usb_endpoint_configure(struct snd_usb_audio *chip, + struct snd_usb_endpoint *ep) { bool iface_first; int err = 0; @@ -1414,6 +1412,9 @@ int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, if (err < 0) goto unlock; } + err = snd_usb_endpoint_set_params(chip, ep); + if (err < 0) + goto unlock; goto done; } @@ -1441,6 +1442,10 @@ int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, if (err < 0) goto unlock; + err = snd_usb_endpoint_set_params(chip, ep); + if (err < 0) + goto unlock; + err = snd_usb_select_mode_quirk(chip, ep->cur_audiofmt); if (err < 0) goto unlock; diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h index e67ea28faa54..6a9af04cf175 100644 --- a/sound/usb/endpoint.h +++ b/sound/usb/endpoint.h @@ -17,10 +17,8 @@ snd_usb_endpoint_open(struct snd_usb_audio *chip, bool is_sync_ep); void snd_usb_endpoint_close(struct snd_usb_audio *chip, struct snd_usb_endpoint *ep); -int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, - struct snd_usb_endpoint *ep); -int snd_usb_endpoint_prepare(struct snd_usb_audio *chip, - struct snd_usb_endpoint *ep); +int snd_usb_endpoint_configure(struct snd_usb_audio *chip, + struct snd_usb_endpoint *ep); int snd_usb_endpoint_get_clock_rate(struct snd_usb_audio *chip, int clock); bool snd_usb_endpoint_compatible(struct snd_usb_audio *chip, diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index b604f7e95e82..d45d1d7e6664 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -443,17 +443,17 @@ static int configure_endpoints(struct snd_usb_audio *chip, if (stop_endpoints(subs, false)) sync_pending_stops(subs); if (subs->sync_endpoint) { - err = snd_usb_endpoint_prepare(chip, subs->sync_endpoint); + err = snd_usb_endpoint_configure(chip, subs->sync_endpoint); if (err < 0) return err; } - err = snd_usb_endpoint_prepare(chip, subs->data_endpoint); + err = snd_usb_endpoint_configure(chip, subs->data_endpoint); if (err < 0) return err; snd_usb_set_format_quirk(subs, subs->cur_audiofmt); } else { if (subs->sync_endpoint) { - err = snd_usb_endpoint_prepare(chip, subs->sync_endpoint); + err = snd_usb_endpoint_configure(chip, subs->sync_endpoint); if (err < 0) return err; } @@ -551,13 +551,7 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream, subs->cur_audiofmt = fmt; mutex_unlock(&chip->mutex); - if (subs->sync_endpoint) { - ret = snd_usb_endpoint_set_params(chip, subs->sync_endpoint); - if (ret < 0) - goto unlock; - } - - ret = snd_usb_endpoint_set_params(chip, subs->data_endpoint); + ret = configure_endpoints(chip, subs); unlock: if (ret < 0) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 235dc85c91c3..ef4775c6db01 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -457,7 +457,8 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ -#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */ -#define X86_BUG_EIBRS_PBRSB X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ +#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 6b1bafe267a4..8ec5b9f344e0 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -441,6 +441,7 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, perf_evlist__for_each_entry(evlist, evsel) { bool overwrite = evsel->attr.write_backward; + enum fdarray_flags flgs; struct perf_mmap *map; int *output, fd, cpu; @@ -504,8 +505,8 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, revent = !overwrite ? POLLIN : 0; - if (!evsel->system_wide && - perf_evlist__add_pollfd(evlist, fd, map, revent, fdarray_flag__default) < 0) { + flgs = evsel->system_wide ? fdarray_flag__nonfilterable : fdarray_flag__default; + if (perf_evlist__add_pollfd(evlist, fd, map, revent, flgs) < 0) { perf_mmap__put(map); return -1; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index f87ef43eb820..0f711f88894c 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -3371,6 +3371,8 @@ static int record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cp return 0; perf_cpu_map__for_each_cpu(cpu, idx, cpus) { + if (cpu.cpu == -1) + continue; /* Return ENODEV is input cpu is greater than max cpu */ if ((unsigned long)cpu.cpu > mask->nbits) return -ENODEV; diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh new file mode 100755 index 000000000000..d724855d097c --- /dev/null +++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh @@ -0,0 +1,83 @@ +#!/bin/sh +# perf stat --bpf-counters --for-each-cgroup test +# SPDX-License-Identifier: GPL-2.0 + +set -e + +test_cgroups= +if [ "$1" = "-v" ]; then + verbose="1" +fi + +# skip if --bpf-counters --for-each-cgroup is not supported +check_bpf_counter() +{ + if ! perf stat -a --bpf-counters --for-each-cgroup / true > /dev/null 2>&1; then + if [ "${verbose}" = "1" ]; then + echo "Skipping: --bpf-counters --for-each-cgroup not supported" + perf --no-pager stat -a --bpf-counters --for-each-cgroup / true || true + fi + exit 2 + fi +} + +# find two cgroups to measure +find_cgroups() +{ + # try usual systemd slices first + if [ -d /sys/fs/cgroup/system.slice -a -d /sys/fs/cgroup/user.slice ]; then + test_cgroups="system.slice,user.slice" + return + fi + + # try root and self cgroups + local self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3) + if [ -z ${self_cgrp} ]; then + # cgroup v2 doesn't specify perf_event + self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3) + fi + + if [ -z ${self_cgrp} ]; then + test_cgroups="/" + else + test_cgroups="/,${self_cgrp}" + fi +} + +# As cgroup events are cpu-wide, we cannot simply compare the result. +# Just check if it runs without failure and has non-zero results. +check_system_wide_counted() +{ + local output + + output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1 2>&1) + if echo ${output} | grep -q -F "<not "; then + echo "Some system-wide events are not counted" + if [ "${verbose}" = "1" ]; then + echo ${output} + fi + exit 1 + fi +} + +check_cpu_list_counted() +{ + local output + + output=$(perf stat -C 1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1 2>&1) + if echo ${output} | grep -q -F "<not "; then + echo "Some CPU events are not counted" + if [ "${verbose}" = "1" ]; then + echo ${output} + fi + exit 1 + fi +} + +check_bpf_counter +find_cgroups + +check_system_wide_counted +check_cpu_list_counted + +exit 0 diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c index 9d4c45184e71..56455da30341 100644 --- a/tools/perf/tests/wp.c +++ b/tools/perf/tests/wp.c @@ -2,7 +2,9 @@ #include <stdlib.h> #include <string.h> #include <unistd.h> +#include <errno.h> #include <sys/ioctl.h> +#include <linux/compiler.h> #include <linux/hw_breakpoint.h> #include <linux/kernel.h> #include "tests.h" @@ -137,8 +139,7 @@ static int test__wp_rw(struct test_suite *test __maybe_unused, #endif } -static int test__wp_modify(struct test_suite *test __maybe_unused, - int subtest __maybe_unused) +static int test__wp_modify(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { #if defined(__s390x__) return TEST_SKIP; @@ -160,6 +161,11 @@ static int test__wp_modify(struct test_suite *test __maybe_unused, new_attr.disabled = 1; ret = ioctl(fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr); if (ret < 0) { + if (errno == ENOTTY) { + test->test_cases[subtest].skip_reason = "missing kernel support"; + ret = TEST_SKIP; + } + pr_debug("ioctl(PERF_EVENT_IOC_MODIFY_ATTRIBUTES) failed\n"); close(fd); return ret; diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index 63b9db657442..3c2df7522f6f 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -95,7 +95,7 @@ static int bperf_load_program(struct evlist *evlist) perf_cpu_map__for_each_cpu(cpu, i, evlist->core.all_cpus) { link = bpf_program__attach_perf_event(skel->progs.on_cgrp_switch, - FD(cgrp_switch, cpu.cpu)); + FD(cgrp_switch, i)); if (IS_ERR(link)) { pr_err("Failed to attach cgroup program\n"); err = PTR_ERR(link); @@ -115,15 +115,15 @@ static int bperf_load_program(struct evlist *evlist) evsel->cgrp = NULL; /* open single copy of the events w/o cgroup */ - err = evsel__open_per_cpu(evsel, evlist->core.all_cpus, -1); + err = evsel__open_per_cpu(evsel, evsel->core.cpus, -1); if (err) { pr_err("Failed to open first cgroup events\n"); goto out; } map_fd = bpf_map__fd(skel->maps.events); - perf_cpu_map__for_each_cpu(cpu, j, evlist->core.all_cpus) { - int fd = FD(evsel, cpu.cpu); + perf_cpu_map__for_each_cpu(cpu, j, evsel->core.cpus) { + int fd = FD(evsel, j); __u32 idx = evsel->core.idx * total_cpus + cpu.cpu; err = bpf_map_update_elem(map_fd, &idx, &fd, @@ -269,7 +269,7 @@ static int bperf_cgrp__read(struct evsel *evsel) goto out; } - perf_cpu_map__for_each_cpu(cpu, i, evlist->core.all_cpus) { + perf_cpu_map__for_each_cpu(cpu, i, evsel->core.cpus) { counts = perf_counts(evsel->counts, i, 0); counts->val = values[cpu.cpu].counter; counts->ena = values[cpu.cpu].enabled; diff --git a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c index 292c430768b5..c72f8ad96f75 100644 --- a/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_cgroup.bpf.c @@ -176,7 +176,7 @@ static int bperf_cgroup_count(void) } // This will be attached to cgroup-switches event for each cpu -SEC("perf_events") +SEC("perf_event") int BPF_PROG(on_cgrp_switch) { return bperf_cgroup_count(); diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c index ed28a0dbcb7f..d81b54563e96 100644 --- a/tools/perf/util/genelf.c +++ b/tools/perf/util/genelf.c @@ -253,6 +253,7 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, Elf_Data *d; Elf_Scn *scn; Elf_Ehdr *ehdr; + Elf_Phdr *phdr; Elf_Shdr *shdr; uint64_t eh_frame_base_offset; char *strsym = NULL; @@ -288,6 +289,19 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym, ehdr->e_shstrndx= unwinding ? 4 : 2; /* shdr index for section name */ /* + * setup program header + */ + phdr = elf_newphdr(e, 1); + phdr[0].p_type = PT_LOAD; + phdr[0].p_offset = 0; + phdr[0].p_vaddr = 0; + phdr[0].p_paddr = 0; + phdr[0].p_filesz = csize; + phdr[0].p_memsz = csize; + phdr[0].p_flags = PF_X | PF_R; + phdr[0].p_align = 8; + + /* * setup text section */ scn = elf_newscn(e); diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index ae138afe6c56..b5c909546e3f 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -53,8 +53,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #if GEN_ELF_CLASS == ELFCLASS64 #define elf_newehdr elf64_newehdr +#define elf_newphdr elf64_newphdr #define elf_getshdr elf64_getshdr #define Elf_Ehdr Elf64_Ehdr +#define Elf_Phdr Elf64_Phdr #define Elf_Shdr Elf64_Shdr #define Elf_Sym Elf64_Sym #define ELF_ST_TYPE(a) ELF64_ST_TYPE(a) @@ -62,8 +64,10 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #define ELF_ST_VIS(a) ELF64_ST_VISIBILITY(a) #else #define elf_newehdr elf32_newehdr +#define elf_newphdr elf32_newphdr #define elf_getshdr elf32_getshdr #define Elf_Ehdr Elf32_Ehdr +#define Elf_Phdr Elf32_Phdr #define Elf_Shdr Elf32_Shdr #define Elf_Sym Elf32_Sym #define ELF_ST_TYPE(a) ELF32_ST_TYPE(a) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 75bec32d4f57..647b7dff8ef3 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -2102,8 +2102,8 @@ static int kcore_copy__compare_file(const char *from_dir, const char *to_dir, * unusual. One significant peculiarity is that the mapping (start -> pgoff) * is not the same for the kernel map and the modules map. That happens because * the data is copied adjacently whereas the original kcore has gaps. Finally, - * kallsyms and modules files are compared with their copies to check that - * modules have not been loaded or unloaded while the copies were taking place. + * kallsyms file is compared with its copy to check that modules have not been + * loaded or unloaded while the copies were taking place. * * Return: %0 on success, %-1 on failure. */ @@ -2166,9 +2166,6 @@ int kcore_copy(const char *from_dir, const char *to_dir) goto out_extract_close; } - if (kcore_copy__compare_file(from_dir, to_dir, "modules")) - goto out_extract_close; - if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms")) goto out_extract_close; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 812424dbf2d5..538790758e24 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -367,13 +367,24 @@ static void perf_record_mmap2__read_build_id(struct perf_record_mmap2 *event, bool is_kernel) { struct build_id bid; + struct nsinfo *nsi; + struct nscookie nc; int rc; - if (is_kernel) + if (is_kernel) { rc = sysfs__read_build_id("/sys/kernel/notes", &bid); - else - rc = filename__read_build_id(event->filename, &bid) > 0 ? 0 : -1; + goto out; + } + + nsi = nsinfo__new(event->pid); + nsinfo__mountns_enter(nsi, &nc); + rc = filename__read_build_id(event->filename, &bid) > 0 ? 0 : -1; + + nsinfo__mountns_exit(&nc); + nsinfo__put(nsi); + +out: if (rc == 0) { memcpy(event->build_id, bid.data, sizeof(bid.data)); event->build_id_size = (u8) bid.size; diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c index 4d1a947367f9..01ceb98c15a0 100644 --- a/tools/testing/nvdimm/test/ndtest.c +++ b/tools/testing/nvdimm/test/ndtest.c @@ -134,39 +134,6 @@ static struct ndtest_mapping region1_mapping[] = { }, }; -static struct ndtest_mapping region2_mapping[] = { - { - .dimm = 0, - .position = 0, - .start = 0, - .size = DIMM_SIZE, - }, -}; - -static struct ndtest_mapping region3_mapping[] = { - { - .dimm = 1, - .start = 0, - .size = DIMM_SIZE, - } -}; - -static struct ndtest_mapping region4_mapping[] = { - { - .dimm = 2, - .start = 0, - .size = DIMM_SIZE, - } -}; - -static struct ndtest_mapping region5_mapping[] = { - { - .dimm = 3, - .start = 0, - .size = DIMM_SIZE, - } -}; - static struct ndtest_region bus0_regions[] = { { .type = ND_DEVICE_NAMESPACE_PMEM, @@ -182,34 +149,6 @@ static struct ndtest_region bus0_regions[] = { .size = DIMM_SIZE * 2, .range_index = 2, }, - { - .type = ND_DEVICE_NAMESPACE_BLK, - .num_mappings = ARRAY_SIZE(region2_mapping), - .mapping = region2_mapping, - .size = DIMM_SIZE, - .range_index = 3, - }, - { - .type = ND_DEVICE_NAMESPACE_BLK, - .num_mappings = ARRAY_SIZE(region3_mapping), - .mapping = region3_mapping, - .size = DIMM_SIZE, - .range_index = 4, - }, - { - .type = ND_DEVICE_NAMESPACE_BLK, - .num_mappings = ARRAY_SIZE(region4_mapping), - .mapping = region4_mapping, - .size = DIMM_SIZE, - .range_index = 5, - }, - { - .type = ND_DEVICE_NAMESPACE_BLK, - .num_mappings = ARRAY_SIZE(region5_mapping), - .mapping = region5_mapping, - .size = DIMM_SIZE, - .range_index = 6, - }, }; static struct ndtest_mapping region6_mapping[] = { @@ -501,21 +440,6 @@ static int ndtest_create_region(struct ndtest_priv *p, nd_set->altcookie = nd_set->cookie1; ndr_desc->nd_set = nd_set; - if (region->type == ND_DEVICE_NAMESPACE_BLK) { - mappings[0].start = 0; - mappings[0].size = DIMM_SIZE; - mappings[0].nvdimm = p->config->dimms[ndimm].nvdimm; - - ndr_desc->mapping = &mappings[0]; - ndr_desc->num_mappings = 1; - ndr_desc->num_lanes = 1; - ndbr_desc.enable = ndtest_blk_region_enable; - ndbr_desc.do_io = ndtest_blk_do_io; - region->region = nvdimm_blk_region_create(p->bus, ndr_desc); - - goto done; - } - for (i = 0; i < region->num_mappings; i++) { ndimm = region->mapping[i].dimm; mappings[i].start = region->mapping[i].start; @@ -527,7 +451,6 @@ static int ndtest_create_region(struct ndtest_priv *p, ndr_desc->num_mappings = region->num_mappings; region->region = nvdimm_pmem_region_create(p->bus, ndr_desc); -done: if (!region->region) { dev_err(&p->pdev.dev, "Error registering region %pR\n", ndr_desc->res); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index c2064a35688b..1fc89b8ef433 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -13,6 +13,7 @@ TARGETS += damon TARGETS += drivers/dma-buf TARGETS += drivers/s390x/uvdevice TARGETS += drivers/net/bonding +TARGETS += drivers/net/team TARGETS += efivarfs TARGETS += exec TARGETS += filesystems diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index ab6c54b12098..1d866658e541 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -1,6 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for net selftests -TEST_PROGS := bond-break-lacpdu-tx.sh +TEST_PROGS := bond-break-lacpdu-tx.sh \ + dev_addr_lists.sh \ + bond-arp-interval-causes-panic.sh + +TEST_FILES := lag_lib.sh include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh new file mode 100755 index 000000000000..71c00bfafbc9 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh @@ -0,0 +1,49 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# cause kernel oops in bond_rr_gen_slave_id +DEBUG=${DEBUG:-0} + +set -e +test ${DEBUG} -ne 0 && set -x + +finish() +{ + ip netns delete server || true + ip netns delete client || true + ip link del link1_1 || true +} + +trap finish EXIT + +client_ip4=192.168.1.198 +server_ip4=192.168.1.254 + +# setup kernel so it reboots after causing the panic +echo 180 >/proc/sys/kernel/panic + +# build namespaces +ip link add dev link1_1 type veth peer name link1_2 + +ip netns add "server" +ip link set dev link1_2 netns server up name eth0 +ip netns exec server ip addr add ${server_ip4}/24 dev eth0 + +ip netns add "client" +ip link set dev link1_1 netns client down name eth0 +ip netns exec client ip link add dev bond0 down type bond mode 1 \ + miimon 100 all_slaves_active 1 +ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev bond0 up +ip netns exec client ip addr add ${client_ip4}/24 dev bond0 +ip netns exec client ping -c 5 $server_ip4 >/dev/null + +ip netns exec client ip link set dev eth0 down nomaster +ip netns exec client ip link set dev bond0 down +ip netns exec client ip link set dev bond0 type bond mode 0 \ + arp_interval 1000 arp_ip_target "+${server_ip4}" +ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev bond0 up +ip netns exec client ping -c 5 $server_ip4 >/dev/null + +exit 0 diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index dc1c22de3c92..70638fa50b2c 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -1 +1,2 @@ CONFIG_BONDING=y +CONFIG_MACVLAN=y diff --git a/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh new file mode 100755 index 000000000000..e6fa24eded5b --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh @@ -0,0 +1,109 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bond device handling of addr lists (dev->uc, mc) +# + +ALL_TESTS=" + bond_cleanup_mode1 + bond_cleanup_mode4 + bond_listen_lacpdu_multicast_case_down + bond_listen_lacpdu_multicast_case_up +" + +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source "$lib_dir"/../../../net/forwarding/lib.sh + +source "$lib_dir"/lag_lib.sh + + +destroy() +{ + local ifnames=(dummy1 dummy2 bond1 mv0) + local ifname + + for ifname in "${ifnames[@]}"; do + ip link del "$ifname" &>/dev/null + done +} + +cleanup() +{ + pre_cleanup + + destroy +} + + +# bond driver control paths vary between modes that have a primary slave +# (bond_uses_primary()) and others. Test both kinds of modes. + +bond_cleanup_mode1() +{ + RET=0 + + test_LAG_cleanup "bonding" "active-backup" +} + +bond_cleanup_mode4() { + RET=0 + + test_LAG_cleanup "bonding" "802.3ad" +} + +bond_listen_lacpdu_multicast() +{ + # Initial state of bond device, up | down + local init_state=$1 + local lacpdu_mc="01:80:c2:00:00:02" + + ip link add dummy1 type dummy + ip link add bond1 "$init_state" type bond mode 802.3ad + ip link set dev dummy1 master bond1 + if [ "$init_state" = "down" ]; then + ip link set dev bond1 up + fi + + grep_bridge_fdb "$lacpdu_mc" bridge fdb show brport dummy1 >/dev/null + check_err $? "LACPDU multicast address not present on slave (1)" + + ip link set dev bond1 down + + not grep_bridge_fdb "$lacpdu_mc" bridge fdb show brport dummy1 >/dev/null + check_err $? "LACPDU multicast address still present on slave" + + ip link set dev bond1 up + + grep_bridge_fdb "$lacpdu_mc" bridge fdb show brport dummy1 >/dev/null + check_err $? "LACPDU multicast address not present on slave (2)" + + cleanup + + log_test "bonding LACPDU multicast address to slave (from bond $init_state)" +} + +# The LACPDU mc addr is added by different paths depending on the initial state +# of the bond when enslaving a device. Test both cases. + +bond_listen_lacpdu_multicast_case_down() +{ + RET=0 + + bond_listen_lacpdu_multicast "down" +} + +bond_listen_lacpdu_multicast_case_up() +{ + RET=0 + + bond_listen_lacpdu_multicast "up" +} + + +trap cleanup EXIT + +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh new file mode 100644 index 000000000000..16c7fb858ac1 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh @@ -0,0 +1,61 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test that a link aggregation device (bonding, team) removes the hardware +# addresses that it adds on its underlying devices. +test_LAG_cleanup() +{ + local driver=$1 + local mode=$2 + local ucaddr="02:00:00:12:34:56" + local addr6="fe80::78:9abc/64" + local mcaddr="33:33:ff:78:9a:bc" + local name + + ip link add dummy1 type dummy + ip link add dummy2 type dummy + if [ "$driver" = "bonding" ]; then + name="bond1" + ip link add "$name" up type bond mode "$mode" + ip link set dev dummy1 master "$name" + ip link set dev dummy2 master "$name" + elif [ "$driver" = "team" ]; then + name="team0" + teamd -d -c ' + { + "device": "'"$name"'", + "runner": { + "name": "'"$mode"'" + }, + "ports": { + "dummy1": + {}, + "dummy2": + {} + } + } + ' + ip link set dev "$name" up + else + check_err 1 + log_test test_LAG_cleanup ": unknown driver \"$driver\"" + return + fi + + # Used to test dev->uc handling + ip link add mv0 link "$name" up address "$ucaddr" type macvlan + # Used to test dev->mc handling + ip address add "$addr6" dev "$name" + ip link set dev "$name" down + ip link del "$name" + + not grep_bridge_fdb "$ucaddr" bridge fdb show >/dev/null + check_err $? "macvlan unicast address still present on a slave" + + not grep_bridge_fdb "$mcaddr" bridge fdb show >/dev/null + check_err $? "IPv6 solicited-node multicast mac address still present on a slave" + + cleanup + + log_test "$driver cleanup mode $mode" +} diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile new file mode 100644 index 000000000000..642d8df1c137 --- /dev/null +++ b/tools/testing/selftests/drivers/net/team/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for net selftests + +TEST_PROGS := dev_addr_lists.sh + +include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config new file mode 100644 index 000000000000..265b6882cc21 --- /dev/null +++ b/tools/testing/selftests/drivers/net/team/config @@ -0,0 +1,3 @@ +CONFIG_NET_TEAM=y +CONFIG_NET_TEAM_MODE_LOADBALANCE=y +CONFIG_MACVLAN=y diff --git a/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh new file mode 100755 index 000000000000..debda7262956 --- /dev/null +++ b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh @@ -0,0 +1,51 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test team device handling of addr lists (dev->uc, mc) +# + +ALL_TESTS=" + team_cleanup +" + +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source "$lib_dir"/../../../net/forwarding/lib.sh + +source "$lib_dir"/../bonding/lag_lib.sh + + +destroy() +{ + local ifnames=(dummy0 dummy1 team0 mv0) + local ifname + + for ifname in "${ifnames[@]}"; do + ip link del "$ifname" &>/dev/null + done +} + +cleanup() +{ + pre_cleanup + + destroy +} + + +team_cleanup() +{ + RET=0 + + test_LAG_cleanup "team" "lacp" +} + + +require_command teamd + +trap cleanup EXIT + +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index fac248a43666..6f88da7e60be 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -227,7 +227,7 @@ int main(int argc, char *argv[]) ucall_init(vm, NULL); pthread_create(&migration_thread, NULL, migration_worker, - (void *)(unsigned long)gettid()); + (void *)(unsigned long)syscall(SYS_gettid)); for (i = 0; !done; i++) { vcpu_run(vcpu); diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile index 02868ac3bc71..6632bfff486b 100644 --- a/tools/testing/selftests/landlock/Makefile +++ b/tools/testing/selftests/landlock/Makefile @@ -1,6 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 +# +# First run: make -C ../../../.. headers_install CFLAGS += -Wall -O2 $(KHDR_INCLUDES) +LDLIBS += -lcap + +LOCAL_HDRS += common.h src_test := $(wildcard *_test.c) @@ -8,14 +13,10 @@ TEST_GEN_PROGS := $(src_test:.c=) TEST_GEN_PROGS_EXTENDED := true -OVERRIDE_TARGETS := 1 -top_srcdir := ../../../.. -include ../lib.mk - -khdr_dir = $(top_srcdir)/usr/include +# Static linking for short targets: +$(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static -$(OUTPUT)/true: true.c - $(LINK.c) $< $(LDLIBS) -o $@ -static +include ../lib.mk -$(OUTPUT)/%_test: %_test.c $(khdr_dir)/linux/landlock.h ../kselftest_harness.h common.h - $(LINK.c) $< $(LDLIBS) -o $@ -lcap -I$(khdr_dir) +# Static linking for targets with $(OUTPUT)/ prefix: +$(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index d44c72b3abe3..9d4cb94cf437 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -42,6 +42,10 @@ endif selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST)))) top_srcdir = $(selfdir)/../../.. +ifeq ($(KHDR_INCLUDES),) +KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include +endif + # The following are built by lib.mk common compile rules. # TEST_CUSTOM_PROGS should be used by tests that require # custom build rule and prevent common build rule use. diff --git a/tools/testing/selftests/net/forwarding/router_multicast.sh b/tools/testing/selftests/net/forwarding/router_multicast.sh index 57e90c873a2c..5a58b1ec8aef 100755 --- a/tools/testing/selftests/net/forwarding/router_multicast.sh +++ b/tools/testing/selftests/net/forwarding/router_multicast.sh @@ -28,7 +28,7 @@ # +------------------+ +------------------+ # -ALL_TESTS="mcast_v4 mcast_v6 rpf_v4 rpf_v6" +ALL_TESTS="mcast_v4 mcast_v6 rpf_v4 rpf_v6 unres_v4 unres_v6" NUM_NETIFS=6 source lib.sh source tc_common.sh @@ -406,6 +406,96 @@ rpf_v6() log_test "RPF IPv6" } +unres_v4() +{ + # Send a multicast packet not corresponding to an installed route, + # causing the kernel to queue the packet for resolution and emit an + # IGMPMSG_NOCACHE notification. smcrouted will react to this + # notification by consulting its (*, G) list and installing an (S, G) + # route, which will be used to forward the queued packet. + + RET=0 + + tc filter add dev $h2 ingress protocol ip pref 1 handle 1 flower \ + dst_ip 225.1.2.3 ip_proto udp dst_port 12345 action drop + tc filter add dev $h3 ingress protocol ip pref 1 handle 1 flower \ + dst_ip 225.1.2.3 ip_proto udp dst_port 12345 action drop + + # Forwarding should fail before installing a matching (*, G). + $MZ $h1 -c 1 -p 128 -t udp "ttl=10,sp=54321,dp=12345" \ + -a 00:11:22:33:44:55 -b 01:00:5e:01:02:03 \ + -A 198.51.100.2 -B 225.1.2.3 -q + + tc_check_packets "dev $h2 ingress" 1 0 + check_err $? "Multicast received on first host when should not" + tc_check_packets "dev $h3 ingress" 1 0 + check_err $? "Multicast received on second host when should not" + + # Create (*, G). Will not be installed in the kernel. + create_mcast_sg $rp1 0.0.0.0 225.1.2.3 $rp2 $rp3 + + $MZ $h1 -c 1 -p 128 -t udp "ttl=10,sp=54321,dp=12345" \ + -a 00:11:22:33:44:55 -b 01:00:5e:01:02:03 \ + -A 198.51.100.2 -B 225.1.2.3 -q + + tc_check_packets "dev $h2 ingress" 1 1 + check_err $? "Multicast not received on first host" + tc_check_packets "dev $h3 ingress" 1 1 + check_err $? "Multicast not received on second host" + + delete_mcast_sg $rp1 0.0.0.0 225.1.2.3 $rp2 $rp3 + + tc filter del dev $h3 ingress protocol ip pref 1 handle 1 flower + tc filter del dev $h2 ingress protocol ip pref 1 handle 1 flower + + log_test "Unresolved queue IPv4" +} + +unres_v6() +{ + # Send a multicast packet not corresponding to an installed route, + # causing the kernel to queue the packet for resolution and emit an + # MRT6MSG_NOCACHE notification. smcrouted will react to this + # notification by consulting its (*, G) list and installing an (S, G) + # route, which will be used to forward the queued packet. + + RET=0 + + tc filter add dev $h2 ingress protocol ipv6 pref 1 handle 1 flower \ + dst_ip ff0e::3 ip_proto udp dst_port 12345 action drop + tc filter add dev $h3 ingress protocol ipv6 pref 1 handle 1 flower \ + dst_ip ff0e::3 ip_proto udp dst_port 12345 action drop + + # Forwarding should fail before installing a matching (*, G). + $MZ $h1 -6 -c 1 -p 128 -t udp "ttl=10,sp=54321,dp=12345" \ + -a 00:11:22:33:44:55 -b 33:33:00:00:00:03 \ + -A 2001:db8:1::2 -B ff0e::3 -q + + tc_check_packets "dev $h2 ingress" 1 0 + check_err $? "Multicast received on first host when should not" + tc_check_packets "dev $h3 ingress" 1 0 + check_err $? "Multicast received on second host when should not" + + # Create (*, G). Will not be installed in the kernel. + create_mcast_sg $rp1 :: ff0e::3 $rp2 $rp3 + + $MZ $h1 -6 -c 1 -p 128 -t udp "ttl=10,sp=54321,dp=12345" \ + -a 00:11:22:33:44:55 -b 33:33:00:00:00:03 \ + -A 2001:db8:1::2 -B ff0e::3 -q + + tc_check_packets "dev $h2 ingress" 1 1 + check_err $? "Multicast not received on first host" + tc_check_packets "dev $h3 ingress" 1 1 + check_err $? "Multicast not received on second host" + + delete_mcast_sg $rp1 :: ff0e::3 $rp2 $rp3 + + tc filter del dev $h3 ingress protocol ipv6 pref 1 handle 1 flower + tc filter del dev $h2 ingress protocol ipv6 pref 1 handle 1 flower + + log_test "Unresolved queue IPv6" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/sch_red.sh b/tools/testing/selftests/net/forwarding/sch_red.sh index e714bae473fb..81f31179ac88 100755 --- a/tools/testing/selftests/net/forwarding/sch_red.sh +++ b/tools/testing/selftests/net/forwarding/sch_red.sh @@ -1,3 +1,4 @@ +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # This test sends one stream of traffic from H1 through a TBF shaper, to a RED diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh index a6991877e50c..e908009576c7 100755 --- a/tools/testing/selftests/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -91,7 +91,7 @@ src start 1 count 5 src_delta 2000 -tools sendip nc bash +tools sendip socat nc bash proto udp race_repeat 3 @@ -116,7 +116,7 @@ src start 10 count 5 src_delta 2000 -tools sendip nc bash +tools sendip socat nc bash proto udp6 race_repeat 3 @@ -141,7 +141,7 @@ src start 1 count 5 src_delta 2000 -tools sendip nc bash +tools sendip socat nc bash proto udp race_repeat 0 @@ -163,7 +163,7 @@ src mac start 10 count 5 src_delta 2000 -tools sendip nc bash +tools sendip socat nc bash proto udp6 race_repeat 0 @@ -185,7 +185,7 @@ src mac proto start 10 count 5 src_delta 2000 -tools sendip nc bash +tools sendip socat nc bash proto udp6 race_repeat 0 @@ -207,7 +207,7 @@ src addr4 start 1 count 5 src_delta 2000 -tools sendip nc bash +tools sendip socat nc bash proto udp race_repeat 3 @@ -227,7 +227,7 @@ src addr6 port start 10 count 5 src_delta 2000 -tools sendip nc +tools sendip socat nc proto udp6 race_repeat 3 @@ -247,7 +247,7 @@ src mac proto addr4 start 1 count 5 src_delta 2000 -tools sendip nc bash +tools sendip socat nc bash proto udp race_repeat 0 @@ -264,7 +264,7 @@ src mac start 1 count 5 src_delta 2000 -tools sendip nc bash +tools sendip socat nc bash proto udp race_repeat 0 @@ -286,7 +286,7 @@ src mac addr4 start 1 count 5 src_delta 2000 -tools sendip nc bash +tools sendip socat nc bash proto udp race_repeat 0 @@ -337,7 +337,7 @@ src addr4 start 1 count 5 src_delta 2000 -tools sendip nc +tools sendip socat nc proto udp race_repeat 3 @@ -363,7 +363,7 @@ src mac start 1 count 1 src_delta 2000 -tools sendip nc bash +tools sendip socat nc bash proto udp race_repeat 0 @@ -541,6 +541,24 @@ setup_send_udp() { dst_port= src_addr4= } + elif command -v socat -v >/dev/null; then + send_udp() { + if [ -n "${src_addr4}" ]; then + B ip addr add "${src_addr4}" dev veth_b + __socatbind=",bind=${src_addr4}" + if [ -n "${src_port}" ];then + __socatbind="${__socatbind}:${src_port}" + fi + fi + + ip addr add "${dst_addr4}" dev veth_a 2>/dev/null + [ -z "${dst_port}" ] && dst_port=12345 + + echo "test4" | B socat -t 0.01 STDIN UDP4-DATAGRAM:${dst_addr4}:${dst_port}"${__socatbind}" + + src_addr4= + src_port= + } elif command -v nc >/dev/null; then if nc -u -w0 1.1.1.1 1 2>/dev/null; then # OpenBSD netcat @@ -606,6 +624,29 @@ setup_send_udp6() { dst_port= src_addr6= } + elif command -v socat -v >/dev/null; then + send_udp6() { + ip -6 addr add "${dst_addr6}" dev veth_a nodad \ + 2>/dev/null + + __socatbind6= + + if [ -n "${src_addr6}" ]; then + if [ -n "${src_addr6} != "${src_addr6_added} ]; then + B ip addr add "${src_addr6}" dev veth_b nodad + + src_addr6_added=${src_addr6} + fi + + __socatbind6=",bind=[${src_addr6}]" + + if [ -n "${src_port}" ] ;then + __socatbind6="${__socatbind6}:${src_port}" + fi + fi + + echo "test6" | B socat -t 0.01 STDIN UDP6-DATAGRAM:[${dst_addr6}]:${dst_port}"${__socatbind6}" + } elif command -v nc >/dev/null && nc -u -w0 1.1.1.1 1 2>/dev/null; then # GNU netcat might not work with IPv6, try next tool send_udp6() { diff --git a/tools/testing/selftests/timens/Makefile b/tools/testing/selftests/timens/Makefile index f0d51d4d2c87..3a5936cc10ab 100644 --- a/tools/testing/selftests/timens/Makefile +++ b/tools/testing/selftests/timens/Makefile @@ -1,4 +1,4 @@ -TEST_GEN_PROGS := timens timerfd timer clock_nanosleep procfs exec futex vfork_exec +TEST_GEN_PROGS := timens timerfd timer clock_nanosleep procfs exec futex TEST_GEN_PROGS_EXTENDED := gettime_perf CFLAGS := -Wall -Werror -pthread diff --git a/tools/testing/selftests/timens/vfork_exec.c b/tools/testing/selftests/timens/vfork_exec.c deleted file mode 100644 index e6ccd900f30a..000000000000 --- a/tools/testing/selftests/timens/vfork_exec.c +++ /dev/null @@ -1,90 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE -#include <errno.h> -#include <fcntl.h> -#include <sched.h> -#include <stdio.h> -#include <stdbool.h> -#include <sys/stat.h> -#include <sys/syscall.h> -#include <sys/types.h> -#include <sys/wait.h> -#include <time.h> -#include <unistd.h> -#include <string.h> - -#include "log.h" -#include "timens.h" - -#define OFFSET (36000) - -int main(int argc, char *argv[]) -{ - struct timespec now, tst; - int status, i; - pid_t pid; - - if (argc > 1) { - if (sscanf(argv[1], "%ld", &now.tv_sec) != 1) - return pr_perror("sscanf"); - - for (i = 0; i < 2; i++) { - _gettime(CLOCK_MONOTONIC, &tst, i); - if (abs(tst.tv_sec - now.tv_sec) > 5) - return pr_fail("%ld %ld\n", now.tv_sec, tst.tv_sec); - } - return 0; - } - - nscheck(); - - ksft_set_plan(1); - - clock_gettime(CLOCK_MONOTONIC, &now); - - if (unshare_timens()) - return 1; - - if (_settime(CLOCK_MONOTONIC, OFFSET)) - return 1; - - for (i = 0; i < 2; i++) { - _gettime(CLOCK_MONOTONIC, &tst, i); - if (abs(tst.tv_sec - now.tv_sec) > 5) - return pr_fail("%ld %ld\n", - now.tv_sec, tst.tv_sec); - } - - pid = vfork(); - if (pid < 0) - return pr_perror("fork"); - - if (pid == 0) { - char now_str[64]; - char *cargv[] = {"exec", now_str, NULL}; - char *cenv[] = {NULL}; - - // Check that we are still in the source timens. - for (i = 0; i < 2; i++) { - _gettime(CLOCK_MONOTONIC, &tst, i); - if (abs(tst.tv_sec - now.tv_sec) > 5) - return pr_fail("%ld %ld\n", - now.tv_sec, tst.tv_sec); - } - - /* Check for proper vvar offsets after execve. */ - snprintf(now_str, sizeof(now_str), "%ld", now.tv_sec + OFFSET); - execve("/proc/self/exe", cargv, cenv); - return pr_perror("execve"); - } - - if (waitpid(pid, &status, 0) != pid) - return pr_perror("waitpid"); - - if (status) - ksft_exit_fail(); - - ksft_test_result_pass("exec\n"); - ksft_exit_pass(); - return 0; -} diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile index fda76282d34b..e95bd56b332f 100644 --- a/tools/testing/selftests/wireguard/qemu/Makefile +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -343,8 +343,10 @@ $(KERNEL_BZIMAGE): $(TOOLCHAIN_PATH)/.installed $(KERNEL_BUILD_PATH)/.config $(B .PHONY: $(KERNEL_BZIMAGE) $(TOOLCHAIN_PATH)/$(CHOST)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config $(TOOLCHAIN_PATH)/.installed +ifneq ($(ARCH),um) rm -rf $(TOOLCHAIN_PATH)/$(CHOST)/include/linux $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(TOOLCHAIN_PATH)/$(CHOST) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install +endif touch $@ $(TOOLCHAIN_PATH)/.installed: $(TOOLCHAIN_TAR) |