diff options
Diffstat (limited to 'arch')
356 files changed, 4224 insertions, 2584 deletions
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index bfc7f5f5d6f2..9acbeba832c0 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -65,6 +65,14 @@ clock-frequency = <33333333>; }; + reg_5v0: regulator-5v0 { + compatible = "regulator-fixed"; + + regulator-name = "5v0-supply"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + cpu_intc: cpu-interrupt-controller { compatible = "snps,archs-intc"; interrupt-controller; @@ -264,6 +272,21 @@ clocks = <&input_clk>; cs-gpios = <&creg_gpio 0 GPIO_ACTIVE_LOW>, <&creg_gpio 1 GPIO_ACTIVE_LOW>; + + spi-flash@0 { + compatible = "sst26wf016b", "jedec,spi-nor"; + reg = <0>; + #address-cells = <1>; + #size-cells = <1>; + spi-max-frequency = <4000000>; + }; + + adc@1 { + compatible = "ti,adc108s102"; + reg = <1>; + vref-supply = <®_5v0>; + spi-max-frequency = <1000000>; + }; }; creg_gpio: gpio@14b0 { diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 9b9a74444ce2..0974226fab55 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -32,6 +32,8 @@ CONFIG_INET=y CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set +CONFIG_MTD=y +CONFIG_MTD_SPI_NOR=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_NETDEVICES=y @@ -55,6 +57,8 @@ CONFIG_GPIO_SYSFS=y CONFIG_GPIO_DWAPB=y CONFIG_GPIO_SNPS_CREG=y # CONFIG_HWMON is not set +CONFIG_REGULATOR=y +CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_DRM=y # CONFIG_DRM_FBDEV_EMULATION is not set CONFIG_DRM_UDL=y @@ -72,6 +76,8 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y CONFIG_DMADEVICES=y CONFIG_DW_AXI_DMAC=y +CONFIG_IIO=y +CONFIG_TI_ADC108S102=y CONFIG_EXT3_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 861a8aea51f9..661fd842ea97 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -614,8 +614,8 @@ static int arc_pmu_device_probe(struct platform_device *pdev) /* loop thru all available h/w condition indexes */ for (i = 0; i < cc_bcr.c; i++) { write_aux_reg(ARC_REG_CC_INDEX, i); - cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0); - cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1); + cc_name.indiv.word0 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME0)); + cc_name.indiv.word1 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME1)); arc_pmu_map_hw_event(i, cc_name.str); arc_pmu_add_raw_event_attr(i, cc_name.str); diff --git a/arch/arm/boot/dts/am335x-icev2.dts b/arch/arm/boot/dts/am335x-icev2.dts index 18f70b35da4c..204bccfcc110 100644 --- a/arch/arm/boot/dts/am335x-icev2.dts +++ b/arch/arm/boot/dts/am335x-icev2.dts @@ -432,7 +432,7 @@ pinctrl-0 = <&mmc0_pins_default>; }; -&gpio0 { +&gpio0_target { /* Do not idle the GPIO used for holding the VTT regulator */ ti,no-reset-on-init; ti,no-idle-on-init; diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index 9915c891e05f..7a9eb2b0d45b 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -127,7 +127,7 @@ ranges = <0x0 0x5000 0x1000>; }; - target-module@7000 { /* 0x44e07000, ap 14 20.0 */ + gpio0_target: target-module@7000 { /* 0x44e07000, ap 14 20.0 */ compatible = "ti,sysc-omap2", "ti,sysc"; ti,hwmods = "gpio1"; reg = <0x7000 0x4>, @@ -2038,7 +2038,9 @@ reg = <0xe000 0x4>, <0xe054 0x4>; reg-names = "rev", "sysc"; - ti,sysc-midle ; + ti,sysc-midle = <SYSC_IDLE_FORCE>, + <SYSC_IDLE_NO>, + <SYSC_IDLE_SMART>; ti,sysc-sidle = <SYSC_IDLE_FORCE>, <SYSC_IDLE_NO>, <SYSC_IDLE_SMART>; diff --git a/arch/arm/boot/dts/am3874-iceboard.dts b/arch/arm/boot/dts/am3874-iceboard.dts index 883fb85135d4..1b4b2b0500e4 100644 --- a/arch/arm/boot/dts/am3874-iceboard.dts +++ b/arch/arm/boot/dts/am3874-iceboard.dts @@ -111,13 +111,13 @@ reg = <0x70>; #address-cells = <1>; #size-cells = <0>; + i2c-mux-idle-disconnect; i2c@0 { /* FMC A */ #address-cells = <1>; #size-cells = <0>; reg = <0>; - i2c-mux-idle-disconnect; }; i2c@1 { @@ -125,7 +125,6 @@ #address-cells = <1>; #size-cells = <0>; reg = <1>; - i2c-mux-idle-disconnect; }; i2c@2 { @@ -133,7 +132,6 @@ #address-cells = <1>; #size-cells = <0>; reg = <2>; - i2c-mux-idle-disconnect; }; i2c@3 { @@ -141,7 +139,6 @@ #address-cells = <1>; #size-cells = <0>; reg = <3>; - i2c-mux-idle-disconnect; }; i2c@4 { @@ -149,14 +146,12 @@ #address-cells = <1>; #size-cells = <0>; reg = <4>; - i2c-mux-idle-disconnect; }; i2c@5 { #address-cells = <1>; #size-cells = <0>; reg = <5>; - i2c-mux-idle-disconnect; ina230@40 { compatible = "ti,ina230"; reg = <0x40>; shunt-resistor = <5000>; }; ina230@41 { compatible = "ti,ina230"; reg = <0x41>; shunt-resistor = <5000>; }; @@ -182,14 +177,12 @@ #address-cells = <1>; #size-cells = <0>; reg = <6>; - i2c-mux-idle-disconnect; }; i2c@7 { #address-cells = <1>; #size-cells = <0>; reg = <7>; - i2c-mux-idle-disconnect; u41: pca9575@20 { compatible = "nxp,pca9575"; diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index 848e2a8884e2..14bbc438055f 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -337,6 +337,8 @@ ti,hwmods = "dss_dispc"; clocks = <&disp_clk>; clock-names = "fck"; + + max-memory-bandwidth = <230000000>; }; rfbi: rfbi@4832a800 { diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts index 09a088f98566..b75af21069f9 100644 --- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts +++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts @@ -113,6 +113,7 @@ #address-cells = <1>; #size-cells = <0>; pinctrl-0 = <&emmc_gpio34 &gpclk2_gpio43>; + bus-width = <4>; mmc-pwrseq = <&wifi_pwrseq>; non-removable; status = "okay"; diff --git a/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi b/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi index 7c3cb7ece6cb..925cb37c22f0 100644 --- a/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi +++ b/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi @@ -9,6 +9,14 @@ reg = <0 0x40000000>; }; + leds { + /* + * Since there is no upstream GPIO driver yet, + * remove the incomplete node. + */ + /delete-node/ act; + }; + reg_3v3: fixed-regulator { compatible = "regulator-fixed"; regulator-name = "3V3"; diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi index ea0e7c19eb4e..5cac2dd58241 100644 --- a/arch/arm/boot/dts/dra7-l4.dtsi +++ b/arch/arm/boot/dts/dra7-l4.dtsi @@ -2732,7 +2732,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 129 1>, <&edma_xbar 128 1>; dma-names = "tx", "rx"; - clocks = <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 22>, + clocks = <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 0>, <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 24>, <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 28>; clock-names = "fck", "ahclkx", "ahclkr"; @@ -2768,8 +2768,8 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 131 1>, <&edma_xbar 130 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 22>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 24>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 0>, + <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 24>, <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 28>; clock-names = "fck", "ahclkx", "ahclkr"; status = "disabled"; @@ -2786,9 +2786,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x68000 0x2000>, @@ -2804,7 +2803,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 133 1>, <&edma_xbar 132 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; @@ -2821,9 +2820,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x6c000 0x2000>, @@ -2839,7 +2837,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 135 1>, <&edma_xbar 134 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; @@ -2856,9 +2854,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x70000 0x2000>, @@ -2874,7 +2871,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 137 1>, <&edma_xbar 136 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; @@ -2891,9 +2888,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x74000 0x2000>, @@ -2909,7 +2905,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 139 1>, <&edma_xbar 138 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; @@ -2926,9 +2922,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x78000 0x2000>, @@ -2944,7 +2939,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 141 1>, <&edma_xbar 140 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; @@ -2961,9 +2956,8 @@ <SYSC_IDLE_SMART>; /* Domains (P, C): l4per_pwrdm, l4per2_clkdm */ clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 0>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 24>, - <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 28>; - clock-names = "fck", "ahclkx", "ahclkr"; + <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 24>; + clock-names = "fck", "ahclkx"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x7c000 0x2000>, @@ -2979,7 +2973,7 @@ interrupt-names = "tx", "rx"; dmas = <&edma_xbar 143 1>, <&edma_xbar 142 1>; dma-names = "tx", "rx"; - clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 22>, + clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 0>, <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 24>; clock-names = "fck", "ahclkx"; status = "disabled"; diff --git a/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi b/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi index 2a6ce87071f9..9e027b9a5f91 100644 --- a/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi +++ b/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi @@ -328,6 +328,10 @@ pinctrl-0 = <&pinctrl_pwm3>; }; +&snvs_pwrkey { + status = "okay"; +}; + &ssi2 { status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6-logicpd-som.dtsi b/arch/arm/boot/dts/imx6-logicpd-som.dtsi index 7ceae3573248..547fb141ec0c 100644 --- a/arch/arm/boot/dts/imx6-logicpd-som.dtsi +++ b/arch/arm/boot/dts/imx6-logicpd-som.dtsi @@ -207,6 +207,10 @@ vin-supply = <&sw1c_reg>; }; +&snvs_poweroff { + status = "okay"; +}; + &iomuxc { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_hog>; diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi index f3404dd10537..cf628465cd0a 100644 --- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi @@ -230,6 +230,8 @@ accelerometer@1c { compatible = "fsl,mma8451"; reg = <0x1c>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_mma8451_int>; interrupt-parent = <&gpio6>; interrupts = <31 IRQ_TYPE_LEVEL_LOW>; }; @@ -628,6 +630,12 @@ >; }; + pinctrl_mma8451_int: mma8451intgrp { + fsl,pins = < + MX6QDL_PAD_EIM_BCLK__GPIO6_IO31 0xb0b1 + >; + }; + pinctrl_pwm3: pwm1grp { fsl,pins = < MX6QDL_PAD_SD4_DAT1__PWM3_OUT 0x1b0b1 diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 710f850e785c..e2e604d6ba0b 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -448,7 +448,7 @@ compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; reg = <0x302d0000 0x10000>; interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_GPT1_ROOT_CLK>, <&clks IMX7D_GPT1_ROOT_CLK>; clock-names = "ipg", "per"; }; @@ -457,7 +457,7 @@ compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; reg = <0x302e0000 0x10000>; interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_GPT2_ROOT_CLK>, <&clks IMX7D_GPT2_ROOT_CLK>; clock-names = "ipg", "per"; status = "disabled"; @@ -467,7 +467,7 @@ compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; reg = <0x302f0000 0x10000>; interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_GPT3_ROOT_CLK>, <&clks IMX7D_GPT3_ROOT_CLK>; clock-names = "ipg", "per"; status = "disabled"; @@ -477,7 +477,7 @@ compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; reg = <0x30300000 0x10000>; interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX7D_CLK_DUMMY>, + clocks = <&clks IMX7D_GPT4_ROOT_CLK>, <&clks IMX7D_GPT4_ROOT_CLK>; clock-names = "ipg", "per"; status = "disabled"; diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index 3fdd0a72f87f..506b118e511a 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -192,3 +192,7 @@ &twl_gpio { ti,use-leds; }; + +&twl_keypad { + status = "disabled"; +}; diff --git a/arch/arm/boot/dts/mt7629-rfb.dts b/arch/arm/boot/dts/mt7629-rfb.dts index 3621b7d2b22a..9980c10c6e29 100644 --- a/arch/arm/boot/dts/mt7629-rfb.dts +++ b/arch/arm/boot/dts/mt7629-rfb.dts @@ -66,9 +66,21 @@ pinctrl-1 = <&ephy_leds_pins>; status = "okay"; + gmac0: mac@0 { + compatible = "mediatek,eth-mac"; + reg = <0>; + phy-mode = "2500base-x"; + fixed-link { + speed = <2500>; + full-duplex; + pause; + }; + }; + gmac1: mac@1 { compatible = "mediatek,eth-mac"; reg = <1>; + phy-mode = "gmii"; phy-handle = <&phy0>; }; @@ -78,7 +90,6 @@ phy0: ethernet-phy@0 { reg = <0>; - phy-mode = "gmii"; }; }; }; diff --git a/arch/arm/boot/dts/mt7629.dtsi b/arch/arm/boot/dts/mt7629.dtsi index 9608bc2ccb3f..867b88103b9d 100644 --- a/arch/arm/boot/dts/mt7629.dtsi +++ b/arch/arm/boot/dts/mt7629.dtsi @@ -468,14 +468,12 @@ compatible = "mediatek,mt7629-sgmiisys", "syscon"; reg = <0x1b128000 0x3000>; #clock-cells = <1>; - mediatek,physpeed = "2500"; }; sgmiisys1: syscon@1b130000 { compatible = "mediatek,mt7629-sgmiisys", "syscon"; reg = <0x1b130000 0x3000>; #clock-cells = <1>; - mediatek,physpeed = "2500"; }; }; }; diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index d01fc8744fd7..b6ef1a7ac8a4 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -124,6 +124,7 @@ spi-max-frequency = <100000>; spi-cpol; spi-cpha; + spi-cs-high; backlight= <&backlight>; label = "lcd"; diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts index 4454449de00c..a40fe8d49da6 100644 --- a/arch/arm/boot/dts/omap4-droid4-xt894.dts +++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts @@ -369,7 +369,7 @@ compatible = "ti,wl1285", "ti,wl1283"; reg = <2>; /* gpio_100 with gpmc_wait2 pad as wakeirq */ - interrupts-extended = <&gpio4 4 IRQ_TYPE_EDGE_RISING>, + interrupts-extended = <&gpio4 4 IRQ_TYPE_LEVEL_HIGH>, <&omap4_pmx_core 0x4e>; interrupt-names = "irq", "wakeup"; ref-clock-frequency = <26000000>; diff --git a/arch/arm/boot/dts/omap4-panda-common.dtsi b/arch/arm/boot/dts/omap4-panda-common.dtsi index 14be2ecb62b1..55ea8b6189af 100644 --- a/arch/arm/boot/dts/omap4-panda-common.dtsi +++ b/arch/arm/boot/dts/omap4-panda-common.dtsi @@ -474,7 +474,7 @@ compatible = "ti,wl1271"; reg = <2>; /* gpio_53 with gpmc_ncs3 pad as wakeup */ - interrupts-extended = <&gpio2 21 IRQ_TYPE_EDGE_RISING>, + interrupts-extended = <&gpio2 21 IRQ_TYPE_LEVEL_HIGH>, <&omap4_pmx_core 0x3a>; interrupt-names = "irq", "wakeup"; ref-clock-frequency = <38400000>; diff --git a/arch/arm/boot/dts/omap4-sdp.dts b/arch/arm/boot/dts/omap4-sdp.dts index 3c274965ff40..91480ac1f328 100644 --- a/arch/arm/boot/dts/omap4-sdp.dts +++ b/arch/arm/boot/dts/omap4-sdp.dts @@ -512,7 +512,7 @@ compatible = "ti,wl1281"; reg = <2>; interrupt-parent = <&gpio1>; - interrupts = <21 IRQ_TYPE_EDGE_RISING>; /* gpio 53 */ + interrupts = <21 IRQ_TYPE_LEVEL_HIGH>; /* gpio 53 */ ref-clock-frequency = <26000000>; tcxo-clock-frequency = <26000000>; }; diff --git a/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi b/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi index 6dbbc9b3229c..d0032213101e 100644 --- a/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi +++ b/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi @@ -69,7 +69,7 @@ compatible = "ti,wl1271"; reg = <2>; interrupt-parent = <&gpio2>; - interrupts = <9 IRQ_TYPE_EDGE_RISING>; /* gpio 41 */ + interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; /* gpio 41 */ ref-clock-frequency = <38400000>; }; }; diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 7fff555ee394..68ac04641bdb 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -362,7 +362,7 @@ pinctrl-names = "default"; pinctrl-0 = <&wlcore_irq_pin>; interrupt-parent = <&gpio1>; - interrupts = <14 IRQ_TYPE_EDGE_RISING>; /* gpio 14 */ + interrupts = <14 IRQ_TYPE_LEVEL_HIGH>; /* gpio 14 */ ref-clock-frequency = <26000000>; }; }; diff --git a/arch/arm/boot/dts/omap54xx-clocks.dtsi b/arch/arm/boot/dts/omap54xx-clocks.dtsi index fac2e57dcca9..4791834dacb2 100644 --- a/arch/arm/boot/dts/omap54xx-clocks.dtsi +++ b/arch/arm/boot/dts/omap54xx-clocks.dtsi @@ -1146,7 +1146,7 @@ }; }; - gpu_cm: clock-controller@1500 { + gpu_cm: gpu_cm@1500 { compatible = "ti,omap4-cm"; reg = <0x1500 0x100>; #address-cells = <1>; diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi index a53657b83288..bda454d12150 100644 --- a/arch/arm/boot/dts/ste-dbx5x0.dtsi +++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi @@ -8,6 +8,7 @@ #include <dt-bindings/mfd/dbx500-prcmu.h> #include <dt-bindings/arm/ux500_pm_domains.h> #include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/thermal/thermal.h> / { #address-cells = <1>; @@ -59,8 +60,12 @@ * cooling. */ cpu_thermal: cpu-thermal { - polling-delay-passive = <0>; - polling-delay = <1000>; + polling-delay-passive = <250>; + /* + * This sensor fires interrupts to update the thermal + * zone, so no polling is needed. + */ + polling-delay = <0>; thermal-sensors = <&thermal>; @@ -79,7 +84,7 @@ cooling-maps { trip = <&cpu_alert>; - cooling-device = <&CPU0 0 2>; + cooling-device = <&CPU0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; contribution = <100>; }; }; diff --git a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi index e4a0d51ec3a8..0a3a7d66737b 100644 --- a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi +++ b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi @@ -609,13 +609,13 @@ <STM32_PINMUX('F', 6, AF9)>; /* QSPI_BK1_IO3 */ bias-disable; drive-push-pull; - slew-rate = <3>; + slew-rate = <1>; }; pins2 { pinmux = <STM32_PINMUX('B', 6, AF10)>; /* QSPI_BK1_NCS */ bias-pull-up; drive-push-pull; - slew-rate = <3>; + slew-rate = <1>; }; }; @@ -637,13 +637,13 @@ <STM32_PINMUX('G', 7, AF11)>; /* QSPI_BK2_IO3 */ bias-disable; drive-push-pull; - slew-rate = <3>; + slew-rate = <1>; }; pins2 { pinmux = <STM32_PINMUX('C', 0, AF10)>; /* QSPI_BK2_NCS */ bias-pull-up; drive-push-pull; - slew-rate = <3>; + slew-rate = <1>; }; }; diff --git a/arch/arm/boot/dts/stm32mp157c-ev1.dts b/arch/arm/boot/dts/stm32mp157c-ev1.dts index 89d29b50c3f4..91fc0a315c49 100644 --- a/arch/arm/boot/dts/stm32mp157c-ev1.dts +++ b/arch/arm/boot/dts/stm32mp157c-ev1.dts @@ -183,14 +183,12 @@ ov5640: camera@3c { compatible = "ovti,ov5640"; - pinctrl-names = "default"; - pinctrl-0 = <&ov5640_pins>; reg = <0x3c>; clocks = <&clk_ext_camera>; clock-names = "xclk"; DOVDD-supply = <&v2v8>; - powerdown-gpios = <&stmfx_pinctrl 18 GPIO_ACTIVE_HIGH>; - reset-gpios = <&stmfx_pinctrl 19 GPIO_ACTIVE_LOW>; + powerdown-gpios = <&stmfx_pinctrl 18 (GPIO_ACTIVE_HIGH | GPIO_PUSH_PULL)>; + reset-gpios = <&stmfx_pinctrl 19 (GPIO_ACTIVE_LOW | GPIO_PUSH_PULL)>; rotation = <180>; status = "okay"; @@ -223,15 +221,8 @@ joystick_pins: joystick { pins = "gpio0", "gpio1", "gpio2", "gpio3", "gpio4"; - drive-push-pull; bias-pull-down; }; - - ov5640_pins: camera { - pins = "agpio2", "agpio3"; /* stmfx pins 18 & 19 */ - drive-push-pull; - output-low; - }; }; }; }; diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi index 9b11654a0a39..f98e0370c0bc 100644 --- a/arch/arm/boot/dts/stm32mp157c.dtsi +++ b/arch/arm/boot/dts/stm32mp157c.dtsi @@ -932,7 +932,7 @@ interrupt-names = "int0", "int1"; clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>; clock-names = "hclk", "cclk"; - bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>; + bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>; status = "disabled"; }; @@ -945,7 +945,7 @@ interrupt-names = "int0", "int1"; clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>; clock-names = "hclk", "cclk"; - bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>; + bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index ce823c44e98a..4c268b70b735 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -520,6 +520,7 @@ interrupts = <39>; clocks = <&ccu CLK_AHB_EHCI0>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -529,6 +530,7 @@ interrupts = <64>; clocks = <&ccu CLK_USB_OHCI0>, <&ccu CLK_AHB_OHCI0>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -608,6 +610,7 @@ interrupts = <40>; clocks = <&ccu CLK_AHB_EHCI1>; phys = <&usbphy 2>; + phy-names = "usb"; status = "disabled"; }; @@ -617,6 +620,7 @@ interrupts = <65>; clocks = <&ccu CLK_USB_OHCI1>, <&ccu CLK_AHB_OHCI1>; phys = <&usbphy 2>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi index cfb1efc8828c..6befa236ba99 100644 --- a/arch/arm/boot/dts/sun5i.dtsi +++ b/arch/arm/boot/dts/sun5i.dtsi @@ -391,6 +391,7 @@ interrupts = <39>; clocks = <&ccu CLK_AHB_EHCI>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -400,6 +401,7 @@ interrupts = <40>; clocks = <&ccu CLK_USB_OHCI>, <&ccu CLK_AHB_OHCI>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index bbeb743633c6..ac7638078420 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -545,6 +545,7 @@ clocks = <&ccu CLK_AHB1_EHCI0>; resets = <&ccu RST_AHB1_EHCI0>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -555,6 +556,7 @@ clocks = <&ccu CLK_AHB1_OHCI0>, <&ccu CLK_USB_OHCI0>; resets = <&ccu RST_AHB1_OHCI0>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -565,6 +567,7 @@ clocks = <&ccu CLK_AHB1_EHCI1>; resets = <&ccu RST_AHB1_EHCI1>; phys = <&usbphy 2>; + phy-names = "usb"; status = "disabled"; }; @@ -575,6 +578,7 @@ clocks = <&ccu CLK_AHB1_OHCI1>, <&ccu CLK_USB_OHCI1>; resets = <&ccu RST_AHB1_OHCI1>; phys = <&usbphy 2>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 49380de754a9..8aebefd6accf 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -380,9 +380,8 @@ compatible = "allwinner,sun7i-a20-csi0"; reg = <0x01c09000 0x1000>; interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI0>, - <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>; - clock-names = "bus", "mod", "isp", "ram"; + clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>; + clock-names = "bus", "isp", "ram"; resets = <&ccu RST_CSI0>; status = "disabled"; }; @@ -623,6 +622,7 @@ interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>; clocks = <&ccu CLK_AHB_EHCI0>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -632,6 +632,7 @@ interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>; clocks = <&ccu CLK_USB_OHCI0>, <&ccu CLK_AHB_OHCI0>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -714,6 +715,7 @@ interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>; clocks = <&ccu CLK_AHB_EHCI1>; phys = <&usbphy 2>; + phy-names = "usb"; status = "disabled"; }; @@ -723,6 +725,7 @@ interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>; clocks = <&ccu CLK_USB_OHCI1>, <&ccu CLK_AHB_OHCI1>; phys = <&usbphy 2>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun8i-a23-a33.dtsi b/arch/arm/boot/dts/sun8i-a23-a33.dtsi index 52eed0ae3607..f292f96ab39b 100644 --- a/arch/arm/boot/dts/sun8i-a23-a33.dtsi +++ b/arch/arm/boot/dts/sun8i-a23-a33.dtsi @@ -307,6 +307,7 @@ clocks = <&ccu CLK_BUS_EHCI>; resets = <&ccu RST_BUS_EHCI>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -317,6 +318,7 @@ clocks = <&ccu CLK_BUS_OHCI>, <&ccu CLK_USB_OHCI>; resets = <&ccu RST_BUS_OHCI>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts index 568b90ece342..3bec3e0a81b2 100644 --- a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts +++ b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts @@ -192,6 +192,7 @@ vqmmc-supply = <®_dldo1>; non-removable; wakeup-source; + keep-power-in-suspend; status = "okay"; brcmf: wifi@1 { diff --git a/arch/arm/boot/dts/sun8i-a83t.dtsi b/arch/arm/boot/dts/sun8i-a83t.dtsi index 523be6611c50..74bb053cf23c 100644 --- a/arch/arm/boot/dts/sun8i-a83t.dtsi +++ b/arch/arm/boot/dts/sun8i-a83t.dtsi @@ -632,6 +632,7 @@ clocks = <&ccu CLK_BUS_EHCI0>; resets = <&ccu RST_BUS_EHCI0>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -643,6 +644,7 @@ clocks = <&ccu CLK_BUS_OHCI0>, <&ccu CLK_USB_OHCI0>; resets = <&ccu RST_BUS_OHCI0>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -654,6 +656,7 @@ clocks = <&ccu CLK_BUS_EHCI1>; resets = <&ccu RST_BUS_EHCI1>; phys = <&usbphy 2>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun8i-r40.dtsi b/arch/arm/boot/dts/sun8i-r40.dtsi index bde068111b85..c9c2688db66d 100644 --- a/arch/arm/boot/dts/sun8i-r40.dtsi +++ b/arch/arm/boot/dts/sun8i-r40.dtsi @@ -273,6 +273,7 @@ clocks = <&ccu CLK_BUS_EHCI1>; resets = <&ccu RST_BUS_EHCI1>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -284,6 +285,7 @@ <&ccu CLK_USB_OHCI1>; resets = <&ccu RST_BUS_OHCI1>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -294,6 +296,7 @@ clocks = <&ccu CLK_BUS_EHCI2>; resets = <&ccu RST_BUS_EHCI2>; phys = <&usbphy 2>; + phy-names = "usb"; status = "disabled"; }; @@ -305,6 +308,7 @@ <&ccu CLK_USB_OHCI2>; resets = <&ccu RST_BUS_OHCI2>; phys = <&usbphy 2>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun9i-a80.dtsi b/arch/arm/boot/dts/sun9i-a80.dtsi index c34d505c7efe..b9b6fb00be28 100644 --- a/arch/arm/boot/dts/sun9i-a80.dtsi +++ b/arch/arm/boot/dts/sun9i-a80.dtsi @@ -346,6 +346,7 @@ clocks = <&usb_clocks CLK_BUS_HCI0>; resets = <&usb_clocks RST_USB0_HCI>; phys = <&usbphy1>; + phy-names = "usb"; status = "disabled"; }; @@ -357,6 +358,7 @@ <&usb_clocks CLK_USB_OHCI0>; resets = <&usb_clocks RST_USB0_HCI>; phys = <&usbphy1>; + phy-names = "usb"; status = "disabled"; }; @@ -378,6 +380,7 @@ clocks = <&usb_clocks CLK_BUS_HCI1>; resets = <&usb_clocks RST_USB1_HCI>; phys = <&usbphy2>; + phy-names = "usb"; status = "disabled"; }; @@ -407,6 +410,7 @@ clocks = <&usb_clocks CLK_BUS_HCI2>; resets = <&usb_clocks RST_USB2_HCI>; phys = <&usbphy3>; + phy-names = "usb"; status = "disabled"; }; @@ -418,6 +422,7 @@ <&usb_clocks CLK_USB_OHCI2>; resets = <&usb_clocks RST_USB2_HCI>; phys = <&usbphy3>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sunxi-h3-h5.dtsi b/arch/arm/boot/dts/sunxi-h3-h5.dtsi index eba190b3f9de..107eeafad20a 100644 --- a/arch/arm/boot/dts/sunxi-h3-h5.dtsi +++ b/arch/arm/boot/dts/sunxi-h3-h5.dtsi @@ -304,6 +304,7 @@ clocks = <&ccu CLK_BUS_EHCI1>, <&ccu CLK_BUS_OHCI1>; resets = <&ccu RST_BUS_EHCI1>, <&ccu RST_BUS_OHCI1>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -315,6 +316,7 @@ <&ccu CLK_USB_OHCI1>; resets = <&ccu RST_BUS_EHCI1>, <&ccu RST_BUS_OHCI1>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -325,6 +327,7 @@ clocks = <&ccu CLK_BUS_EHCI2>, <&ccu CLK_BUS_OHCI2>; resets = <&ccu RST_BUS_EHCI2>, <&ccu RST_BUS_OHCI2>; phys = <&usbphy 2>; + phy-names = "usb"; status = "disabled"; }; @@ -336,6 +339,7 @@ <&ccu CLK_USB_OHCI2>; resets = <&ccu RST_BUS_EHCI2>, <&ccu RST_BUS_OHCI2>; phys = <&usbphy 2>; + phy-names = "usb"; status = "disabled"; }; @@ -346,6 +350,7 @@ clocks = <&ccu CLK_BUS_EHCI3>, <&ccu CLK_BUS_OHCI3>; resets = <&ccu RST_BUS_EHCI3>, <&ccu RST_BUS_OHCI3>; phys = <&usbphy 3>; + phy-names = "usb"; status = "disabled"; }; @@ -357,6 +362,7 @@ <&ccu CLK_USB_OHCI3>; resets = <&ccu RST_BUS_EHCI3>, <&ccu RST_BUS_OHCI3>; phys = <&usbphy 3>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/vf610-zii-scu4-aib.dts b/arch/arm/boot/dts/vf610-zii-scu4-aib.dts index dc8a5f37a1ef..c8ebb23c4e02 100644 --- a/arch/arm/boot/dts/vf610-zii-scu4-aib.dts +++ b/arch/arm/boot/dts/vf610-zii-scu4-aib.dts @@ -602,6 +602,7 @@ #address-cells = <1>; #size-cells = <0>; reg = <0x70>; + i2c-mux-idle-disconnect; sff0_i2c: i2c@1 { #address-cells = <1>; @@ -640,6 +641,7 @@ reg = <0x71>; #address-cells = <1>; #size-cells = <0>; + i2c-mux-idle-disconnect; sff5_i2c: i2c@1 { #address-cells = <1>; diff --git a/arch/arm/configs/badge4_defconfig b/arch/arm/configs/badge4_defconfig index 5ae5b5228467..ef484c4cfd1a 100644 --- a/arch/arm/configs/badge4_defconfig +++ b/arch/arm/configs/badge4_defconfig @@ -91,7 +91,6 @@ CONFIG_USB_SERIAL_PL2303=m CONFIG_USB_SERIAL_CYBERJACK=m CONFIG_USB_SERIAL_XIRCOM=m CONFIG_USB_SERIAL_OMNINET=m -CONFIG_USB_RIO500=m CONFIG_EXT2_FS=m CONFIG_EXT3_FS=m CONFIG_MSDOS_FS=y diff --git a/arch/arm/configs/corgi_defconfig b/arch/arm/configs/corgi_defconfig index e4f6442588e7..4fec2ec379ad 100644 --- a/arch/arm/configs/corgi_defconfig +++ b/arch/arm/configs/corgi_defconfig @@ -195,7 +195,6 @@ CONFIG_USB_SERIAL_XIRCOM=m CONFIG_USB_SERIAL_OMNINET=m CONFIG_USB_EMI62=m CONFIG_USB_EMI26=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYTHERM=m diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig index b34970ce6b31..231f8973bbb2 100644 --- a/arch/arm/configs/davinci_all_defconfig +++ b/arch/arm/configs/davinci_all_defconfig @@ -167,6 +167,7 @@ CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_DA8XX=y CONFIG_BACKLIGHT_PWM=m +CONFIG_BACKLIGHT_GPIO=m CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m @@ -228,7 +229,7 @@ CONFIG_RTC_DRV_OMAP=m CONFIG_DMADEVICES=y CONFIG_TI_EDMA=y CONFIG_COMMON_CLK_PWM=m -CONFIG_REMOTEPROC=m +CONFIG_REMOTEPROC=y CONFIG_DA8XX_REMOTEPROC=m CONFIG_MEMORY=y CONFIG_TI_AEMIF=m diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 9bfffbe22d53..0f7381ee0c37 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -276,6 +276,7 @@ CONFIG_VIDEO_OV5640=m CONFIG_VIDEO_OV5645=m CONFIG_IMX_IPUV3_CORE=y CONFIG_DRM=y +CONFIG_DRM_MSM=y CONFIG_DRM_PANEL_LVDS=y CONFIG_DRM_PANEL_SIMPLE=y CONFIG_DRM_PANEL_SEIKO_43WVF1G=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 13ba53286901..e4c8def9a0a5 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -415,7 +415,7 @@ CONFIG_SPI_SH_MSIOF=m CONFIG_SPI_SH_HSPI=y CONFIG_SPI_SIRF=y CONFIG_SPI_STM32=m -CONFIG_SPI_STM32_QSPI=m +CONFIG_SPI_STM32_QSPI=y CONFIG_SPI_SUN4I=y CONFIG_SPI_SUN6I=y CONFIG_SPI_TEGRA114=y @@ -933,7 +933,7 @@ CONFIG_BCM2835_MBOX=y CONFIG_ROCKCHIP_IOMMU=y CONFIG_TEGRA_IOMMU_GART=y CONFIG_TEGRA_IOMMU_SMMU=y -CONFIG_REMOTEPROC=m +CONFIG_REMOTEPROC=y CONFIG_ST_REMOTEPROC=m CONFIG_RPMSG_VIRTIO=m CONFIG_ASPEED_LPC_CTRL=m diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 64eb896907bf..40d7f1a4fc45 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -356,14 +356,15 @@ CONFIG_DRM_OMAP_CONNECTOR_HDMI=m CONFIG_DRM_OMAP_CONNECTOR_ANALOG_TV=m CONFIG_DRM_OMAP_PANEL_DPI=m CONFIG_DRM_OMAP_PANEL_DSI_CM=m -CONFIG_DRM_OMAP_PANEL_SONY_ACX565AKM=m -CONFIG_DRM_OMAP_PANEL_LGPHILIPS_LB035Q02=m -CONFIG_DRM_OMAP_PANEL_SHARP_LS037V7DW01=m -CONFIG_DRM_OMAP_PANEL_TPO_TD028TTEC1=m -CONFIG_DRM_OMAP_PANEL_TPO_TD043MTEA1=m -CONFIG_DRM_OMAP_PANEL_NEC_NL8048HL11=m CONFIG_DRM_TILCDC=m CONFIG_DRM_PANEL_SIMPLE=m +CONFIG_DRM_TI_TFP410=m +CONFIG_DRM_PANEL_LG_LB035Q02=m +CONFIG_DRM_PANEL_NEC_NL8048HL11=m +CONFIG_DRM_PANEL_SHARP_LS037V7DW01=m +CONFIG_DRM_PANEL_SONY_ACX565AKM=m +CONFIG_DRM_PANEL_TPO_TD028TTEC1=m +CONFIG_DRM_PANEL_TPO_TD043MTEA1=m CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_MODE_HELPERS=y @@ -423,6 +424,7 @@ CONFIG_USB_SERIAL_GENERIC=y CONFIG_USB_SERIAL_SIMPLE=m CONFIG_USB_SERIAL_FTDI_SIO=m CONFIG_USB_SERIAL_PL2303=m +CONFIG_USB_SERIAL_OPTION=m CONFIG_USB_TEST=m CONFIG_NOP_USB_XCEIV=m CONFIG_AM335X_PHY_USB=m @@ -460,6 +462,7 @@ CONFIG_MMC_SDHCI_OMAP=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=m CONFIG_LEDS_CPCAP=m +CONFIG_LEDS_LM3532=m CONFIG_LEDS_GPIO=m CONFIG_LEDS_PCA963X=m CONFIG_LEDS_PWM=m @@ -481,7 +484,7 @@ CONFIG_RTC_DRV_OMAP=m CONFIG_RTC_DRV_CPCAP=m CONFIG_DMADEVICES=y CONFIG_OMAP_IOMMU=y -CONFIG_REMOTEPROC=m +CONFIG_REMOTEPROC=y CONFIG_OMAP_REMOTEPROC=m CONFIG_WKUP_M3_RPROC=m CONFIG_SOC_TI=y diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index 787c3f9be414..b817c57f05f1 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -581,7 +581,6 @@ CONFIG_USB_SERIAL_XIRCOM=m CONFIG_USB_SERIAL_OMNINET=m CONFIG_USB_EMI62=m CONFIG_USB_EMI26=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYTHERM=m diff --git a/arch/arm/configs/s3c2410_defconfig b/arch/arm/configs/s3c2410_defconfig index 95b5a4ffddea..73ed73a8785a 100644 --- a/arch/arm/configs/s3c2410_defconfig +++ b/arch/arm/configs/s3c2410_defconfig @@ -327,7 +327,6 @@ CONFIG_USB_EMI62=m CONFIG_USB_EMI26=m CONFIG_USB_ADUTUX=m CONFIG_USB_SEVSEG=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYPRESS_CY7C63=m diff --git a/arch/arm/configs/spitz_defconfig b/arch/arm/configs/spitz_defconfig index 4fb51d665abb..a1cdbfa064c5 100644 --- a/arch/arm/configs/spitz_defconfig +++ b/arch/arm/configs/spitz_defconfig @@ -189,7 +189,6 @@ CONFIG_USB_SERIAL_XIRCOM=m CONFIG_USB_SERIAL_OMNINET=m CONFIG_USB_EMI62=m CONFIG_USB_EMI26=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYTHERM=m diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig index b24df84a1d7a..043b0b18bf7e 100644 --- a/arch/arm/crypto/Kconfig +++ b/arch/arm/crypto/Kconfig @@ -98,6 +98,7 @@ config CRYPTO_AES_ARM_CE tristate "Accelerated AES using ARMv8 Crypto Extensions" depends on KERNEL_MODE_NEON select CRYPTO_BLKCIPHER + select CRYPTO_LIB_AES select CRYPTO_SIMD help Use an implementation of AES in CBC, CTR and XTS modes that uses diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S index b978cdf133af..4d1707388d94 100644 --- a/arch/arm/crypto/aes-ce-core.S +++ b/arch/arm/crypto/aes-ce-core.S @@ -9,6 +9,7 @@ #include <asm/assembler.h> .text + .arch armv8-a .fpu crypto-neon-fp-armv8 .align 3 diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h index 567dbede4785..f1d0a7807cd0 100644 --- a/arch/arm/include/asm/domain.h +++ b/arch/arm/include/asm/domain.h @@ -82,7 +82,7 @@ #ifndef __ASSEMBLY__ #ifdef CONFIG_CPU_CP15_MMU -static inline unsigned int get_domain(void) +static __always_inline unsigned int get_domain(void) { unsigned int domain; @@ -94,7 +94,7 @@ static inline unsigned int get_domain(void) return domain; } -static inline void set_domain(unsigned val) +static __always_inline void set_domain(unsigned int val) { asm volatile( "mcr p15, 0, %0, c3, c0 @ set domain" @@ -102,12 +102,12 @@ static inline void set_domain(unsigned val) isb(); } #else -static inline unsigned int get_domain(void) +static __always_inline unsigned int get_domain(void) { return 0; } -static inline void set_domain(unsigned val) +static __always_inline void set_domain(unsigned int val) { } #endif diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 303248e5b990..98c6b91be4a8 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -22,7 +22,7 @@ * perform such accesses (eg, via list poison values) which could then * be exploited for priviledge escalation. */ -static inline unsigned int uaccess_save_and_enable(void) +static __always_inline unsigned int uaccess_save_and_enable(void) { #ifdef CONFIG_CPU_SW_DOMAIN_PAN unsigned int old_domain = get_domain(); @@ -37,7 +37,7 @@ static inline unsigned int uaccess_save_and_enable(void) #endif } -static inline void uaccess_restore(unsigned int flags) +static __always_inline void uaccess_restore(unsigned int flags) { #ifdef CONFIG_CPU_SW_DOMAIN_PAN /* Restore the user access mask */ diff --git a/arch/arm/include/asm/xen/xen-ops.h b/arch/arm/include/asm/xen/xen-ops.h deleted file mode 100644 index ec154e719b11..000000000000 --- a/arch/arm/include/asm/xen/xen-ops.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _ASM_XEN_OPS_H -#define _ASM_XEN_OPS_H - -void xen_efi_runtime_setup(void); - -#endif /* _ASM_XEN_OPS_H */ diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S index a7810be07da1..4a3982812a40 100644 --- a/arch/arm/kernel/head-common.S +++ b/arch/arm/kernel/head-common.S @@ -68,7 +68,7 @@ ENDPROC(__vet_atags) * The following fragment of code is executed with the MMU on in MMU mode, * and uses absolute addresses; this is not position independent. * - * r0 = cp#15 control register + * r0 = cp#15 control register (exc_ret for M-class) * r1 = machine ID * r2 = atags/dtb pointer * r9 = processor ID @@ -137,7 +137,8 @@ __mmap_switched_data: #ifdef CONFIG_CPU_CP15 .long cr_alignment @ r3 #else - .long 0 @ r3 +M_CLASS(.long exc_ret) @ r3 +AR_CLASS(.long 0) @ r3 #endif .size __mmap_switched_data, . - __mmap_switched_data diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index afa350f44dea..0fc814bbc34b 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -201,6 +201,8 @@ M_CLASS(streq r3, [r12, #PMSAv8_MAIR1]) bic r0, r0, #V7M_SCB_CCR_IC #endif str r0, [r12, V7M_SCB_CCR] + /* Pass exc_ret to __mmap_switched */ + mov r0, r10 #endif /* CONFIG_CPU_CP15 elif CONFIG_CPU_V7M */ ret lr ENDPROC(__after_proc_init) diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c index 8062412be70f..9fc5c73cc0be 100644 --- a/arch/arm/mach-davinci/dm365.c +++ b/arch/arm/mach-davinci/dm365.c @@ -462,8 +462,8 @@ static s8 dm365_queue_priority_mapping[][2] = { }; static const struct dma_slave_map dm365_edma_map[] = { - { "davinci-mcbsp.0", "tx", EDMA_FILTER_PARAM(0, 2) }, - { "davinci-mcbsp.0", "rx", EDMA_FILTER_PARAM(0, 3) }, + { "davinci-mcbsp", "tx", EDMA_FILTER_PARAM(0, 2) }, + { "davinci-mcbsp", "rx", EDMA_FILTER_PARAM(0, 3) }, { "davinci_voicecodec", "tx", EDMA_FILTER_PARAM(0, 2) }, { "davinci_voicecodec", "rx", EDMA_FILTER_PARAM(0, 3) }, { "spi_davinci.2", "tx", EDMA_FILTER_PARAM(0, 10) }, diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c index dd939e1325c6..29fd13684a68 100644 --- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c @@ -763,7 +763,8 @@ static struct omap_hwmod_class_sysconfig am33xx_timer_sysc = { .rev_offs = 0x0000, .sysc_offs = 0x0010, .syss_offs = 0x0014, - .sysc_flags = (SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET), + .sysc_flags = SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET | + SYSC_HAS_RESET_STATUS, .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART | SIDLE_SMART_WKUP), .sysc_fields = &omap_hwmod_sysc_type2, diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c index 2bcb6345b873..54524775f278 100644 --- a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c @@ -231,8 +231,9 @@ static struct omap_hwmod am33xx_control_hwmod = { static struct omap_hwmod_class_sysconfig lcdc_sysc = { .rev_offs = 0x0, .sysc_offs = 0x54, - .sysc_flags = (SYSC_HAS_SIDLEMODE | SYSC_HAS_MIDLEMODE), - .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART), + .sysc_flags = SYSC_HAS_SIDLEMODE | SYSC_HAS_MIDLEMODE, + .idlemodes = SIDLE_FORCE | SIDLE_NO | SIDLE_SMART | + MSTANDBY_FORCE | MSTANDBY_NO | MSTANDBY_SMART, .sysc_fields = &omap_hwmod_sysc_type2, }; diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index d942a3357090..2efd18e8824c 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -89,6 +89,13 @@ static struct iommu_platform_data omap3_iommu_pdata = { .reset_name = "mmu", .assert_reset = omap_device_assert_hardreset, .deassert_reset = omap_device_deassert_hardreset, + .device_enable = omap_device_enable, + .device_idle = omap_device_idle, +}; + +static struct iommu_platform_data omap3_iommu_isp_pdata = { + .device_enable = omap_device_enable, + .device_idle = omap_device_idle, }; static int omap3_sbc_t3730_twl_callback(struct device *dev, @@ -424,6 +431,8 @@ static struct iommu_platform_data omap4_iommu_pdata = { .reset_name = "mmu_cache", .assert_reset = omap_device_assert_hardreset, .deassert_reset = omap_device_deassert_hardreset, + .device_enable = omap_device_enable, + .device_idle = omap_device_idle, }; #endif @@ -617,6 +626,8 @@ static struct of_dev_auxdata omap_auxdata_lookup[] = { #ifdef CONFIG_ARCH_OMAP3 OF_DEV_AUXDATA("ti,omap2-iommu", 0x5d000000, "5d000000.mmu", &omap3_iommu_pdata), + OF_DEV_AUXDATA("ti,omap2-iommu", 0x480bd400, "480bd400.mmu", + &omap3_iommu_isp_pdata), OF_DEV_AUXDATA("ti,omap3-smartreflex-core", 0x480cb000, "480cb000.smartreflex", &omap_sr_pdata[OMAP_SR_CORE]), OF_DEV_AUXDATA("ti,omap3-smartreflex-mpu-iva", 0x480c9000, diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c index 1fde1bf53fb6..7ac9af56762d 100644 --- a/arch/arm/mach-omap2/pm.c +++ b/arch/arm/mach-omap2/pm.c @@ -74,83 +74,6 @@ int omap_pm_clkdms_setup(struct clockdomain *clkdm, void *unused) return 0; } -/* - * This API is to be called during init to set the various voltage - * domains to the voltage as per the opp table. Typically we boot up - * at the nominal voltage. So this function finds out the rate of - * the clock associated with the voltage domain, finds out the correct - * opp entry and sets the voltage domain to the voltage specified - * in the opp entry - */ -static int __init omap2_set_init_voltage(char *vdd_name, char *clk_name, - const char *oh_name) -{ - struct voltagedomain *voltdm; - struct clk *clk; - struct dev_pm_opp *opp; - unsigned long freq, bootup_volt; - struct device *dev; - - if (!vdd_name || !clk_name || !oh_name) { - pr_err("%s: invalid parameters\n", __func__); - goto exit; - } - - if (!strncmp(oh_name, "mpu", 3)) - /* - * All current OMAPs share voltage rail and clock - * source, so CPU0 is used to represent the MPU-SS. - */ - dev = get_cpu_device(0); - else - dev = omap_device_get_by_hwmod_name(oh_name); - - if (IS_ERR(dev)) { - pr_err("%s: Unable to get dev pointer for hwmod %s\n", - __func__, oh_name); - goto exit; - } - - voltdm = voltdm_lookup(vdd_name); - if (!voltdm) { - pr_err("%s: unable to get vdd pointer for vdd_%s\n", - __func__, vdd_name); - goto exit; - } - - clk = clk_get(NULL, clk_name); - if (IS_ERR(clk)) { - pr_err("%s: unable to get clk %s\n", __func__, clk_name); - goto exit; - } - - freq = clk_get_rate(clk); - clk_put(clk); - - opp = dev_pm_opp_find_freq_ceil(dev, &freq); - if (IS_ERR(opp)) { - pr_err("%s: unable to find boot up OPP for vdd_%s\n", - __func__, vdd_name); - goto exit; - } - - bootup_volt = dev_pm_opp_get_voltage(opp); - dev_pm_opp_put(opp); - - if (!bootup_volt) { - pr_err("%s: unable to find voltage corresponding to the bootup OPP for vdd_%s\n", - __func__, vdd_name); - goto exit; - } - - voltdm_scale(voltdm, bootup_volt); - return 0; - -exit: - pr_err("%s: unable to set vdd_%s\n", __func__, vdd_name); - return -EINVAL; -} - #ifdef CONFIG_SUSPEND static int omap_pm_enter(suspend_state_t suspend_state) { @@ -208,25 +131,6 @@ void omap_common_suspend_init(void *pm_suspend) } #endif /* CONFIG_SUSPEND */ -static void __init omap3_init_voltages(void) -{ - if (!soc_is_omap34xx()) - return; - - omap2_set_init_voltage("mpu_iva", "dpll1_ck", "mpu"); - omap2_set_init_voltage("core", "l3_ick", "l3_main"); -} - -static void __init omap4_init_voltages(void) -{ - if (!soc_is_omap44xx()) - return; - - omap2_set_init_voltage("mpu", "dpll_mpu_ck", "mpu"); - omap2_set_init_voltage("core", "l3_div_ck", "l3_main_1"); - omap2_set_init_voltage("iva", "dpll_iva_m5x2_ck", "iva"); -} - int __maybe_unused omap_pm_nop_init(void) { return 0; @@ -246,10 +150,6 @@ int __init omap2_common_pm_late_init(void) omap4_twl_init(); omap_voltage_late_init(); - /* Initialize the voltages */ - omap3_init_voltages(); - omap4_init_voltages(); - /* Smartreflex device init */ omap_devinit_smartreflex(); diff --git a/arch/arm/mach-sunxi/mc_smp.c b/arch/arm/mach-sunxi/mc_smp.c index 239084cf8192..26cbce135338 100644 --- a/arch/arm/mach-sunxi/mc_smp.c +++ b/arch/arm/mach-sunxi/mc_smp.c @@ -481,14 +481,18 @@ static void sunxi_mc_smp_cpu_die(unsigned int l_cpu) static int sunxi_cpu_powerdown(unsigned int cpu, unsigned int cluster) { u32 reg; + int gating_bit = cpu; pr_debug("%s: cluster %u cpu %u\n", __func__, cluster, cpu); if (cpu >= SUNXI_CPUS_PER_CLUSTER || cluster >= SUNXI_NR_CLUSTERS) return -EINVAL; + if (is_a83t && cpu == 0) + gating_bit = 4; + /* gate processor power */ reg = readl(prcm_base + PRCM_PWROFF_GATING_REG(cluster)); - reg |= PRCM_PWROFF_GATING_REG_CORE(cpu); + reg |= PRCM_PWROFF_GATING_REG_CORE(gating_bit); writel(reg, prcm_base + PRCM_PWROFF_GATING_REG(cluster)); udelay(20); diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 04b36436cbc0..788c5cf46de5 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -324,7 +324,7 @@ union offset_union { __put32_unaligned_check("strbt", val, addr) static void -do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs *regs, union offset_union offset) +do_alignment_finish_ldst(unsigned long addr, u32 instr, struct pt_regs *regs, union offset_union offset) { if (!LDST_U_BIT(instr)) offset.un = -offset.un; @@ -337,7 +337,7 @@ do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs } static int -do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *regs) +do_alignment_ldrhstrh(unsigned long addr, u32 instr, struct pt_regs *regs) { unsigned int rd = RD_BITS(instr); @@ -386,8 +386,7 @@ do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *r } static int -do_alignment_ldrdstrd(unsigned long addr, unsigned long instr, - struct pt_regs *regs) +do_alignment_ldrdstrd(unsigned long addr, u32 instr, struct pt_regs *regs) { unsigned int rd = RD_BITS(instr); unsigned int rd2; @@ -449,7 +448,7 @@ do_alignment_ldrdstrd(unsigned long addr, unsigned long instr, } static int -do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *regs) +do_alignment_ldrstr(unsigned long addr, u32 instr, struct pt_regs *regs) { unsigned int rd = RD_BITS(instr); @@ -498,7 +497,7 @@ do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *reg * PU = 10 A B */ static int -do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *regs) +do_alignment_ldmstm(unsigned long addr, u32 instr, struct pt_regs *regs) { unsigned int rd, rn, correction, nr_regs, regbits; unsigned long eaddr, newaddr; @@ -539,7 +538,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg * processor for us. */ if (addr != eaddr) { - pr_err("LDMSTM: PC = %08lx, instr = %08lx, " + pr_err("LDMSTM: PC = %08lx, instr = %08x, " "addr = %08lx, eaddr = %08lx\n", instruction_pointer(regs), instr, addr, eaddr); show_regs(regs); @@ -716,10 +715,10 @@ thumb2arm(u16 tinstr) * 2. Register name Rt from ARMv7 is same as Rd from ARMv6 (Rd is Rt) */ static void * -do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs, +do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs, union offset_union *poffset) { - unsigned long instr = *pinstr; + u32 instr = *pinstr; u16 tinst1 = (instr >> 16) & 0xffff; u16 tinst2 = instr & 0xffff; @@ -767,17 +766,48 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs, return NULL; } +static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst) +{ + u32 instr = 0; + int fault; + + if (user_mode(regs)) + fault = get_user(instr, ip); + else + fault = probe_kernel_address(ip, instr); + + *inst = __mem_to_opcode_arm(instr); + + return fault; +} + +static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst) +{ + u16 instr = 0; + int fault; + + if (user_mode(regs)) + fault = get_user(instr, ip); + else + fault = probe_kernel_address(ip, instr); + + *inst = __mem_to_opcode_thumb16(instr); + + return fault; +} + static int do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) { union offset_union uninitialized_var(offset); - unsigned long instr = 0, instrptr; - int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs); + unsigned long instrptr; + int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs); unsigned int type; - unsigned int fault; + u32 instr = 0; u16 tinstr = 0; int isize = 4; int thumb2_32b = 0; + int fault; if (interrupts_enabled(regs)) local_irq_enable(); @@ -786,15 +816,14 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (thumb_mode(regs)) { u16 *ptr = (u16 *)(instrptr & ~1); - fault = probe_kernel_address(ptr, tinstr); - tinstr = __mem_to_opcode_thumb16(tinstr); + + fault = alignment_get_thumb(regs, ptr, &tinstr); if (!fault) { if (cpu_architecture() >= CPU_ARCH_ARMv7 && IS_T32(tinstr)) { /* Thumb-2 32-bit */ - u16 tinst2 = 0; - fault = probe_kernel_address(ptr + 1, tinst2); - tinst2 = __mem_to_opcode_thumb16(tinst2); + u16 tinst2; + fault = alignment_get_thumb(regs, ptr + 1, &tinst2); instr = __opcode_thumb32_compose(tinstr, tinst2); thumb2_32b = 1; } else { @@ -803,8 +832,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) } } } else { - fault = probe_kernel_address((void *)instrptr, instr); - instr = __mem_to_opcode_arm(instr); + fault = alignment_get_arm(regs, (void *)instrptr, &instr); } if (fault) { @@ -926,7 +954,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) * Oops, we didn't handle the instruction. */ pr_err("Alignment trap: not handling instruction " - "%0*lx at [<%08lx>]\n", + "%0*x at [<%08lx>]\n", isize << 1, isize == 2 ? tinstr : instr, instrptr); ai_skipped += 1; @@ -936,7 +964,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) ai_user += 1; if (ai_usermode & UM_WARN) - printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*lx " + printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*x " "Address=0x%08lx FSR 0x%03x\n", current->comm, task_pid_nr(current), instrptr, isize << 1, diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 9a07916af8dd..54d87506d3b5 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/arm-smccc.h> #include <linux/kernel.h> -#include <linux/psci.h> #include <linux/smp.h> #include <asm/cp15.h> @@ -75,11 +74,8 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A72: { struct arm_smccc_res res; - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) - break; - - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); if ((int)res.a0 != 0) @@ -90,7 +86,7 @@ static void cpu_v7_spectre_init(void) spectre_v2_method = "hypervisor"; break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); if ((int)res.a0 != 0) diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S index 1448f144e7fb..1a49d503eafc 100644 --- a/arch/arm/mm/proc-v7m.S +++ b/arch/arm/mm/proc-v7m.S @@ -132,13 +132,11 @@ __v7m_setup_cont: dsb mov r6, lr @ save LR ldr sp, =init_thread_union + THREAD_START_SP - stmia sp, {r0-r3, r12} cpsie i svc #0 1: cpsid i - ldr r0, =exc_ret - orr lr, lr, #EXC_RET_THREADMODE_PROCESSSTACK - str lr, [r0] + /* Calculate exc_ret */ + orr r10, lr, #EXC_RET_THREADMODE_PROCESSSTACK ldmia sp, {r0-r3, r12} str r5, [r12, #11 * 4] @ restore the original SVC vector entry mov lr, r6 @ restore LR diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile index 7ed28982c4c3..c32d04713ba0 100644 --- a/arch/arm/xen/Makefile +++ b/arch/arm/xen/Makefile @@ -1,3 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := enlighten.o hypercall.o grant-table.o p2m.o mm.o -obj-$(CONFIG_XEN_EFI) += efi.o diff --git a/arch/arm/xen/efi.c b/arch/arm/xen/efi.c deleted file mode 100644 index d687a73044bf..000000000000 --- a/arch/arm/xen/efi.c +++ /dev/null @@ -1,28 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (c) 2015, Linaro Limited, Shannon Zhao - */ - -#include <linux/efi.h> -#include <xen/xen-ops.h> -#include <asm/xen/xen-ops.h> - -/* Set XEN EFI runtime services function pointers. Other fields of struct efi, - * e.g. efi.systab, will be set like normal EFI. - */ -void __init xen_efi_runtime_setup(void) -{ - efi.get_time = xen_efi_get_time; - efi.set_time = xen_efi_set_time; - efi.get_wakeup_time = xen_efi_get_wakeup_time; - efi.set_wakeup_time = xen_efi_set_wakeup_time; - efi.get_variable = xen_efi_get_variable; - efi.get_next_variable = xen_efi_get_next_variable; - efi.set_variable = xen_efi_set_variable; - efi.query_variable_info = xen_efi_query_variable_info; - efi.update_capsule = xen_efi_update_capsule; - efi.query_capsule_caps = xen_efi_query_capsule_caps; - efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; - efi.reset_system = xen_efi_reset_system; -} -EXPORT_SYMBOL_GPL(xen_efi_runtime_setup); diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 1e57692552d9..dd6804a64f1a 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -15,7 +15,6 @@ #include <xen/xen-ops.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> -#include <asm/xen/xen-ops.h> #include <asm/system_misc.h> #include <asm/efi.h> #include <linux/interrupt.h> @@ -437,7 +436,7 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op); EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op); EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op); EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op); -EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op_raw); EXPORT_SYMBOL_GPL(HYPERVISOR_multicall); EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist); EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op); diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 2b2c208408bb..38fa917c8585 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -28,7 +28,10 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order) for_each_memblock(memory, reg) { if (reg->base < (phys_addr_t)0xffffffff) { - flags |= __GFP_DMA; + if (IS_ENABLED(CONFIG_ZONE_DMA32)) + flags |= __GFP_DMA32; + else + flags |= __GFP_DMA; break; } } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 41a9b4257b72..d66a9727344d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -110,7 +110,6 @@ config ARM64 select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY - select GENERIC_COMPAT_VDSO if (!CPU_BIG_ENDIAN && COMPAT) select HANDLE_DOMAIN_IRQ select HARDIRQS_SW_RESEND select HAVE_PCI @@ -144,6 +143,8 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_REGS \ + if $(cc-option,-fpatchable-function-entry=2) select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD @@ -267,6 +268,10 @@ config GENERIC_CSUM config GENERIC_CALIBRATE_DELAY def_bool y +config ZONE_DMA + bool "Support DMA zone" if EXPERT + default y + config ZONE_DMA32 bool "Support DMA32 zone" if EXPERT default y @@ -539,6 +544,16 @@ config ARM64_ERRATUM_1286807 invalidated has been observed by other observers. The workaround repeats the TLBI+DSB operation. +config ARM64_ERRATUM_1319367 + bool "Cortex-A57/A72: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation" + default y + help + This option adds work arounds for ARM Cortex-A57 erratum 1319537 + and A72 erratum 1319367 + + Cortex-A57 and A72 cores could end-up with corrupted TLBs by + speculating an AT instruction during a guest context switch. + If unsure, say Y. config ARM64_ERRATUM_1463225 @@ -559,6 +574,22 @@ config ARM64_ERRATUM_1463225 If unsure, say Y. +config ARM64_ERRATUM_1542419 + bool "Neoverse-N1: workaround mis-ordering of instruction fetches" + default y + help + This option adds a workaround for ARM Neoverse-N1 erratum + 1542419. + + Affected Neoverse-N1 cores could execute a stale instruction when + modified by another CPU. The workaround depends on a firmware + counterpart. + + Workaround the issue by hiding the DIC feature from EL0. This + forces user-space to perform cache maintenance. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y @@ -617,6 +648,23 @@ config CAVIUM_ERRATUM_30115 If unsure, say Y. +config CAVIUM_TX2_ERRATUM_219 + bool "Cavium ThunderX2 erratum 219: PRFM between TTBR change and ISB fails" + default y + help + On Cavium ThunderX2, a load, store or prefetch instruction between a + TTBR update and the corresponding context synchronizing operation can + cause a spurious Data Abort to be delivered to any hardware thread in + the CPU core. + + Work around the issue by avoiding the problematic code sequence and + trapping KVM guest TTBRx_EL1 writes to EL2 when SMT is enabled. The + trap handler performs the corresponding register access, skips the + instruction and ensures context synchronization by virtue of the + exception return. + + If unsure, say Y. + config QCOM_FALKOR_ERRATUM_1003 bool "Falkor E1003: Incorrect translation due to ASID change" default y @@ -829,10 +877,26 @@ config ARM64_PA_BITS default 48 if ARM64_PA_BITS_48 default 52 if ARM64_PA_BITS_52 +choice + prompt "Endianness" + default CPU_LITTLE_ENDIAN + help + Select the endianness of data accesses performed by the CPU. Userspace + applications will need to be compiled and linked for the endianness + that is selected here. + config CPU_BIG_ENDIAN bool "Build big-endian kernel" help - Say Y if you plan on running a kernel in big-endian mode. + Say Y if you plan on running a kernel with a big-endian userspace. + +config CPU_LITTLE_ENDIAN + bool "Build little-endian kernel" + help + Say Y if you plan on running a kernel with a little-endian userspace. + This is usually the case for distributions targeting arm64. + +endchoice config SCHED_MC bool "Multi-core scheduler support" @@ -1159,7 +1223,7 @@ menuconfig COMPAT if COMPAT config KUSER_HELPERS - bool "Enable kuser helpers page for 32 bit applications" + bool "Enable kuser helpers page for 32-bit applications" default y help Warning: disabling this option may break 32-bit user programs. @@ -1185,6 +1249,18 @@ config KUSER_HELPERS Say N here only if you are absolutely certain that you do not need these helpers; otherwise, the safe option is to say Y. +config COMPAT_VDSO + bool "Enable vDSO for 32-bit applications" + depends on !CPU_BIG_ENDIAN && "$(CROSS_COMPILE_COMPAT)" != "" + select GENERIC_COMPAT_VDSO + default y + help + Place in the process address space of 32-bit applications an + ELF shared object providing fast implementations of gettimeofday + and clock_gettime. + + You must have a 32-bit build of glibc 2.22 or later for programs + to seamlessly take advantage of this. menuconfig ARMV8_DEPRECATED bool "Emulate deprecated/obsolete ARMv8 instructions" @@ -1569,6 +1645,7 @@ config CMDLINE config CMDLINE_FORCE bool "Always use the default kernel command string" + depends on CMDLINE != "" help Always use the default kernel command string, even if the boot loader passes other arguments to the kernel. diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 84a3d502c5a5..1fbe24d4fdb6 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -53,22 +53,6 @@ $(warning Detected assembler with broken .inst; disassembly will be unreliable) endif endif -ifeq ($(CONFIG_GENERIC_COMPAT_VDSO), y) - CROSS_COMPILE_COMPAT ?= $(CONFIG_CROSS_COMPILE_COMPAT_VDSO:"%"=%) - - ifeq ($(CONFIG_CC_IS_CLANG), y) - $(warning CROSS_COMPILE_COMPAT is clang, the compat vDSO will not be built) - else ifeq ($(strip $(CROSS_COMPILE_COMPAT)),) - $(warning CROSS_COMPILE_COMPAT not defined or empty, the compat vDSO will not be built) - else ifeq ($(shell which $(CROSS_COMPILE_COMPAT)gcc 2> /dev/null),) - $(error $(CROSS_COMPILE_COMPAT)gcc not found, check CROSS_COMPILE_COMPAT) - else - export CROSS_COMPILE_COMPAT - export CONFIG_COMPAT_VDSO := y - compat_vdso := -DCONFIG_COMPAT_VDSO=1 - endif -endif - KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) $(brokengasinst) \ $(compat_vdso) $(cc_has_k_constraint) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables @@ -111,6 +95,11 @@ ifeq ($(CONFIG_ARM64_MODULE_PLTS),y) KBUILD_LDS_MODULE += $(srctree)/arch/arm64/kernel/module.lds endif +ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y) + KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY + CC_FLAGS_FTRACE := -fpatchable-function-entry=2 +endif + # Default value head-y := arch/arm64/kernel/head.o diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts index 24f1aac366d6..d5b6e8159a33 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts @@ -63,3 +63,12 @@ reg = <1>; }; }; + +®_dc1sw { + /* + * Ethernet PHY needs 30ms to properly power up and some more + * to initialize. 100ms should be plenty of time to finish + * whole process. + */ + regulator-enable-ramp-delay = <100000>; +}; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts index 2b6345db7dc0..78c82a665c84 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts @@ -104,6 +104,7 @@ &ehci0 { phys = <&usbphy 0>; + phy-names = "usb"; status = "okay"; }; @@ -150,6 +151,7 @@ &ohci0 { phys = <&usbphy 0>; + phy-names = "usb"; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts index e6fb9683f213..25099202c52c 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts @@ -159,6 +159,12 @@ }; ®_dc1sw { + /* + * Ethernet PHY needs 30ms to properly power up and some more + * to initialize. 100ms should be plenty of time to finish + * whole process. + */ + regulator-enable-ramp-delay = <100000>; regulator-name = "vcc-phy"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index 69128a6dfc46..70f4cce6be43 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -142,15 +142,6 @@ clock-output-names = "ext-osc32k"; }; - pmu { - compatible = "arm,cortex-a53-pmu"; - interrupts = <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>; - interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>; - }; - psci { compatible = "arm,psci-0.2"; method = "smc"; @@ -553,6 +544,7 @@ resets = <&ccu RST_BUS_OHCI1>, <&ccu RST_BUS_EHCI1>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; @@ -564,6 +556,7 @@ <&ccu CLK_USB_OHCI1>; resets = <&ccu RST_BUS_OHCI1>; phys = <&usbphy 1>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi index 4020a1aafa3e..0d5ea19336a1 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi @@ -547,6 +547,7 @@ resets = <&ccu RST_BUS_OHCI3>, <&ccu RST_BUS_EHCI3>; phys = <&usb2phy 3>; + phy-names = "usb"; status = "disabled"; }; @@ -558,6 +559,7 @@ <&ccu CLK_USB_OHCI3>; resets = <&ccu RST_BUS_OHCI3>; phys = <&usb2phy 3>; + phy-names = "usb"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi index 8a3a770e8f2c..56789ccf9454 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi @@ -42,13 +42,14 @@ pinmux: pinmux@14029c { compatible = "pinctrl-single"; - reg = <0x0014029c 0x250>; + reg = <0x0014029c 0x26c>; #address-cells = <1>; #size-cells = <1>; pinctrl-single,register-width = <32>; pinctrl-single,function-mask = <0xf>; pinctrl-single,gpio-range = < - &range 0 154 MODE_GPIO + &range 0 91 MODE_GPIO + &range 95 60 MODE_GPIO >; range: gpio-range { #pinctrl-single,gpio-range-cells = <3>; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi index 71e2e34400d4..0098dfdef96c 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi @@ -464,8 +464,7 @@ <&pinmux 108 16 27>, <&pinmux 135 77 6>, <&pinmux 141 67 4>, - <&pinmux 145 149 6>, - <&pinmux 151 91 4>; + <&pinmux 145 149 6>; }; i2c1: i2c@e0000 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts index d98346da01df..078a5010228c 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts @@ -127,7 +127,7 @@ status = "okay"; i2c-mux@77 { - compatible = "nxp,pca9847"; + compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index 408e0ecdce6a..b032f3890c8c 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -33,7 +33,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster0_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@1 { @@ -49,7 +49,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster0_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@100 { @@ -65,7 +65,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster1_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@101 { @@ -81,7 +81,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster1_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@200 { @@ -97,7 +97,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster2_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@201 { @@ -113,7 +113,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster2_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@300 { @@ -129,7 +129,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster3_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@301 { @@ -145,7 +145,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster3_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@400 { @@ -161,7 +161,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster4_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@401 { @@ -177,7 +177,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster4_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@500 { @@ -193,7 +193,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster5_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@501 { @@ -209,7 +209,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster5_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@600 { @@ -225,7 +225,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster6_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@601 { @@ -241,7 +241,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster6_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@700 { @@ -257,7 +257,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster7_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cpu@701 { @@ -273,7 +273,7 @@ i-cache-line-size = <64>; i-cache-sets = <192>; next-level-cache = <&cluster7_l2>; - cpu-idle-states = <&cpu_pw20>; + cpu-idle-states = <&cpu_pw15>; }; cluster0_l2: l2-cache0 { @@ -340,9 +340,9 @@ cache-level = <2>; }; - cpu_pw20: cpu-pw20 { + cpu_pw15: cpu-pw15 { compatible = "arm,idle-state"; - idle-state-name = "PW20"; + idle-state-name = "PW15"; arm,psci-suspend-param = <0x0>; entry-latency-us = <2000>; exit-latency-us = <2000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index 5f9d0da196e1..23c8fad7932b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -394,7 +394,7 @@ }; sdma2: dma-controller@302c0000 { - compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma"; reg = <0x302c0000 0x10000>; interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MM_CLK_SDMA2_ROOT>, @@ -405,7 +405,7 @@ }; sdma3: dma-controller@302b0000 { - compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma"; reg = <0x302b0000 0x10000>; interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MM_CLK_SDMA3_ROOT>, @@ -694,7 +694,7 @@ compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b40000 0x10000>; interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MM_CLK_DUMMY>, + clocks = <&clk IMX8MM_CLK_IPG_ROOT>, <&clk IMX8MM_CLK_NAND_USDHC_BUS>, <&clk IMX8MM_CLK_USDHC1_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -710,7 +710,7 @@ compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b50000 0x10000>; interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MM_CLK_DUMMY>, + clocks = <&clk IMX8MM_CLK_IPG_ROOT>, <&clk IMX8MM_CLK_NAND_USDHC_BUS>, <&clk IMX8MM_CLK_USDHC2_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -724,7 +724,7 @@ compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b60000 0x10000>; interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MM_CLK_DUMMY>, + clocks = <&clk IMX8MM_CLK_IPG_ROOT>, <&clk IMX8MM_CLK_NAND_USDHC_BUS>, <&clk IMX8MM_CLK_USDHC3_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -737,7 +737,7 @@ }; sdma1: dma-controller@30bd0000 { - compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma"; reg = <0x30bd0000 0x10000>; interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MM_CLK_SDMA1_ROOT>, diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 785f4c420fa4..43c4db312146 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -288,7 +288,7 @@ }; sdma3: dma-controller@302b0000 { - compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma"; reg = <0x302b0000 0x10000>; interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SDMA3_ROOT>, @@ -299,7 +299,7 @@ }; sdma2: dma-controller@302c0000 { - compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma"; reg = <0x302c0000 0x10000>; interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SDMA2_ROOT>, @@ -569,7 +569,7 @@ compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b40000 0x10000>; interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MN_CLK_DUMMY>, + clocks = <&clk IMX8MN_CLK_IPG_ROOT>, <&clk IMX8MN_CLK_NAND_USDHC_BUS>, <&clk IMX8MN_CLK_USDHC1_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -585,7 +585,7 @@ compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b50000 0x10000>; interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MN_CLK_DUMMY>, + clocks = <&clk IMX8MN_CLK_IPG_ROOT>, <&clk IMX8MN_CLK_NAND_USDHC_BUS>, <&clk IMX8MN_CLK_USDHC2_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -599,7 +599,7 @@ compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc"; reg = <0x30b60000 0x10000>; interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MN_CLK_DUMMY>, + clocks = <&clk IMX8MN_CLK_IPG_ROOT>, <&clk IMX8MN_CLK_NAND_USDHC_BUS>, <&clk IMX8MN_CLK_USDHC3_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -612,7 +612,7 @@ }; sdma1: dma-controller@30bd0000 { - compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma"; + compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma"; reg = <0x30bd0000 0x10000>; interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SDMA1_ROOT>, diff --git a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi index af99473ada04..32ce14936b01 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi @@ -88,9 +88,9 @@ regulator-name = "0V9_ARM"; regulator-min-microvolt = <900000>; regulator-max-microvolt = <1000000>; - gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>; - states = <1000000 0x0 - 900000 0x1>; + gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>; + states = <1000000 0x1 + 900000 0x0>; regulator-always-on; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 04115ca6bfb5..55a3d1c4bdf0 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -850,7 +850,7 @@ "fsl,imx7d-usdhc"; reg = <0x30b40000 0x10000>; interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MQ_CLK_DUMMY>, + clocks = <&clk IMX8MQ_CLK_IPG_ROOT>, <&clk IMX8MQ_CLK_NAND_USDHC_BUS>, <&clk IMX8MQ_CLK_USDHC1_ROOT>; clock-names = "ipg", "ahb", "per"; @@ -867,7 +867,7 @@ "fsl,imx7d-usdhc"; reg = <0x30b50000 0x10000>; interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clk IMX8MQ_CLK_DUMMY>, + clocks = <&clk IMX8MQ_CLK_IPG_ROOT>, <&clk IMX8MQ_CLK_NAND_USDHC_BUS>, <&clk IMX8MQ_CLK_USDHC2_ROOT>; clock-names = "ipg", "ahb", "per"; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts index d105986c6be1..5f350cc71a2f 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts @@ -60,11 +60,6 @@ gpio = <&gpiosb 0 GPIO_ACTIVE_HIGH>; }; - usb3_phy: usb3-phy { - compatible = "usb-nop-xceiv"; - vcc-supply = <&exp_usb3_vbus>; - }; - vsdc_reg: vsdc-reg { compatible = "regulator-gpio"; regulator-name = "vsdc"; @@ -255,10 +250,16 @@ status = "okay"; }; +&comphy2 { + connector { + compatible = "usb-a-connector"; + phy-supply = <&exp_usb3_vbus>; + }; +}; + &usb3 { status = "okay"; phys = <&comphy2 0>; - usb-phy = <&usb3_phy>; }; &mdio { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts index e152b0ca0290..b8066868a3fe 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts @@ -44,7 +44,7 @@ power-supply = <&pp3300_disp>; panel-timing { - clock-frequency = <266604720>; + clock-frequency = <266666667>; hactive = <2400>; hfront-porch = <48>; hback-porch = <84>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts b/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts index 0d1f5f9a0de9..c133e8d64b2a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts @@ -644,7 +644,7 @@ status = "okay"; u2phy0_host: host-port { - phy-supply = <&vcc5v0_host>; + phy-supply = <&vcc5v0_typec>; status = "okay"; }; @@ -712,7 +712,7 @@ &usbdrd_dwc3_0 { status = "okay"; - dr_mode = "otg"; + dr_mode = "host"; }; &usbdrd3_1 { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts index 0401d4ec1f45..e544deb61d28 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts @@ -173,7 +173,7 @@ regulator-always-on; regulator-boot-on; regulator-min-microvolt = <800000>; - regulator-max-microvolt = <1400000>; + regulator-max-microvolt = <1700000>; vin-supply = <&vcc5v0_sys>; }; }; @@ -247,8 +247,8 @@ rk808: pmic@1b { compatible = "rockchip,rk808"; reg = <0x1b>; - interrupt-parent = <&gpio1>; - interrupts = <21 IRQ_TYPE_LEVEL_LOW>; + interrupt-parent = <&gpio3>; + interrupts = <10 IRQ_TYPE_LEVEL_LOW>; #clock-cells = <1>; clock-output-names = "xin32k", "rk808-clkout2"; pinctrl-names = "default"; @@ -574,7 +574,7 @@ pmic { pmic_int_l: pmic-int-l { - rockchip,pins = <1 RK_PC5 RK_FUNC_GPIO &pcfg_pull_up>; + rockchip,pins = <3 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up>; }; vsel1_gpio: vsel1-gpio { @@ -624,7 +624,6 @@ &sdmmc { bus-width = <4>; - cap-mmc-highspeed; cap-sd-highspeed; cd-gpios = <&gpio0 7 GPIO_ACTIVE_LOW>; disable-wp; @@ -636,8 +635,7 @@ &sdhci { bus-width = <8>; - mmc-hs400-1_8v; - mmc-hs400-enhanced-strobe; + mmc-hs200-1_8v; non-removable; status = "okay"; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 8e05c39eab08..c9a867ac32d4 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -723,7 +723,7 @@ CONFIG_TEGRA_IOMMU_SMMU=y CONFIG_ARM_SMMU=y CONFIG_ARM_SMMU_V3=y CONFIG_QCOM_IOMMU=y -CONFIG_REMOTEPROC=m +CONFIG_REMOTEPROC=y CONFIG_QCOM_Q6V5_MSS=m CONFIG_QCOM_Q6V5_PAS=m CONFIG_QCOM_SYSMON=m diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h index f74909ba29bd..f68a0e64482a 100644 --- a/arch/arm64/include/asm/asm-uaccess.h +++ b/arch/arm64/include/asm/asm-uaccess.h @@ -58,30 +58,4 @@ alternative_else_nop_endif .endm #endif -/* - * These macros are no-ops when UAO is present. - */ - .macro uaccess_disable_not_uao, tmp1, tmp2 - uaccess_ttbr0_disable \tmp1, \tmp2 -alternative_if ARM64_ALT_PAN_NOT_UAO - SET_PSTATE_PAN(1) -alternative_else_nop_endif - .endm - - .macro uaccess_enable_not_uao, tmp1, tmp2, tmp3 - uaccess_ttbr0_enable \tmp1, \tmp2, \tmp3 -alternative_if ARM64_ALT_PAN_NOT_UAO - SET_PSTATE_PAN(0) -alternative_else_nop_endif - .endm - -/* - * Remove the address tag from a virtual address, if present. - */ - .macro clear_address_tag, dst, addr - tst \addr, #(1 << 55) - bic \dst, \addr, #(0xff << 56) - csel \dst, \dst, \addr, eq - .endm - #endif diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index c6bd87d2915b..574808b9df4c 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -321,7 +321,8 @@ static inline s64 __lse_atomic64_dec_if_positive(atomic64_t *v) } #define __CMPXCHG_CASE(w, sfx, name, sz, mb, cl...) \ -static inline u##sz __lse__cmpxchg_case_##name##sz(volatile void *ptr, \ +static __always_inline u##sz \ +__lse__cmpxchg_case_##name##sz(volatile void *ptr, \ u##sz old, \ u##sz new) \ { \ @@ -362,7 +363,8 @@ __CMPXCHG_CASE(x, , mb_, 64, al, "memory") #undef __CMPXCHG_CASE #define __CMPXCHG_DBL(name, mb, cl...) \ -static inline long __lse__cmpxchg_double##name(unsigned long old1, \ +static __always_inline long \ +__lse__cmpxchg_double##name(unsigned long old1, \ unsigned long old2, \ unsigned long new1, \ unsigned long new2, \ diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index e0e2b1946f42..7d9cc5ec4971 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -29,6 +29,18 @@ SB_BARRIER_INSN"nop\n", \ ARM64_HAS_SB)) +#ifdef CONFIG_ARM64_PSEUDO_NMI +#define pmr_sync() \ + do { \ + extern struct static_key_false gic_pmr_sync; \ + \ + if (static_branch_unlikely(&gic_pmr_sync)) \ + dsb(sy); \ + } while(0) +#else +#define pmr_sync() do {} while (0) +#endif + #define mb() dsb(sy) #define rmb() dsb(ld) #define wmb() dsb(st) diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index 43da6dd29592..806e9dc2a852 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -11,6 +11,7 @@ #define CTR_L1IP_MASK 3 #define CTR_DMINLINE_SHIFT 16 #define CTR_IMINLINE_SHIFT 0 +#define CTR_IMINLINE_MASK 0xf #define CTR_ERG_SHIFT 20 #define CTR_CWG_SHIFT 24 #define CTR_CWG_MASK 15 @@ -18,7 +19,7 @@ #define CTR_DIC_SHIFT 29 #define CTR_CACHE_MINLINE_MASK \ - (0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT) + (0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT) #define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK) diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index f19fe4b9acc4..b92683871119 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -52,7 +52,11 @@ #define ARM64_HAS_IRQ_PRIO_MASKING 42 #define ARM64_HAS_DCPODP 43 #define ARM64_WORKAROUND_1463225 44 +#define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM 45 +#define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM 46 +#define ARM64_WORKAROUND_1542419 47 +#define ARM64_WORKAROUND_1319367 48 -#define ARM64_NCAPS 45 +#define ARM64_NCAPS 49 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 9cde5d2e768f..4261d55e8506 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -659,6 +659,20 @@ static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange) default: return CONFIG_ARM64_PA_BITS; } } + +/* Check whether hardware update of the Access flag is supported */ +static inline bool cpu_has_hw_af(void) +{ + u64 mmfr1; + + if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM)) + return false; + + mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); + return cpuid_feature_extract_unsigned_field(mmfr1, + ID_AA64MMFR1_HADBS_SHIFT); +} + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index b1454d117cd2..aca07c2f6e6e 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -79,6 +79,7 @@ #define CAVIUM_CPU_PART_THUNDERX_83XX 0x0A3 #define CAVIUM_CPU_PART_THUNDERX2 0x0AF +#define BRCM_CPU_PART_BRAHMA_B53 0x100 #define BRCM_CPU_PART_VULCAN 0x516 #define QCOM_CPU_PART_FALKOR_V1 0x800 @@ -105,6 +106,7 @@ #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) #define MIDR_CAVIUM_THUNDERX2 MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX2) +#define MIDR_BRAHMA_B53 MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_BRAHMA_B53) #define MIDR_BRCM_VULCAN MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_VULCAN) #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index 063c964af705..72acd2db167f 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -8,7 +8,9 @@ #include <linux/irqflags.h> #include <asm/arch_gicv3.h> +#include <asm/barrier.h> #include <asm/cpufeature.h> +#include <asm/ptrace.h> #define DAIF_PROCCTX 0 #define DAIF_PROCCTX_NOIRQ PSR_I_BIT @@ -65,7 +67,7 @@ static inline void local_daif_restore(unsigned long flags) if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON); - dsb(sy); + pmr_sync(); } } else if (system_uses_irq_prio_masking()) { u64 pmr; @@ -109,4 +111,19 @@ static inline void local_daif_restore(unsigned long flags) trace_hardirqs_off(); } +/* + * Called by synchronous exception handlers to restore the DAIF bits that were + * modified by taking an exception. + */ +static inline void local_daif_inherit(struct pt_regs *regs) +{ + unsigned long flags = regs->pstate & DAIF_MASK; + + /* + * We can't use local_daif_restore(regs->pstate) here as + * system_has_prio_mask_debugging() won't restore the I bit if it can + * use the pmr instead. + */ + write_sysreg(flags, daif); +} #endif diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index a17393ff6677..4d5f3b5f50cd 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -8,14 +8,15 @@ #define __ASM_EXCEPTION_H #include <asm/esr.h> +#include <asm/kprobes.h> +#include <asm/ptrace.h> #include <linux/interrupt.h> -#define __exception __attribute__((section(".exception.text"))) #ifdef CONFIG_FUNCTION_GRAPH_TRACER #define __exception_irq_entry __irq_entry #else -#define __exception_irq_entry __exception +#define __exception_irq_entry __kprobes #endif static inline u32 disr_to_esr(u64 disr) @@ -31,5 +32,22 @@ static inline u32 disr_to_esr(u64 disr) } asmlinkage void enter_from_user_mode(void); +void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void do_undefinstr(struct pt_regs *regs); +asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr); +void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, + struct pt_regs *regs); +void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs); +void do_sve_acc(unsigned int esr, struct pt_regs *regs); +void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs); +void do_sysinstr(unsigned int esr, struct pt_regs *regs); +void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr); +void do_cp15instr(unsigned int esr, struct pt_regs *regs); +void el0_svc_handler(struct pt_regs *regs); +void el0_svc_compat_handler(struct pt_regs *regs); +void do_el0_ia_bp_hardening(unsigned long addr, unsigned int esr, + struct pt_regs *regs); #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index d48667b04c41..91fa4baa1a93 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -11,9 +11,20 @@ #include <asm/insn.h> #define HAVE_FUNCTION_GRAPH_FP_TEST + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#define ARCH_SUPPORTS_FTRACE_OPS 1 +#else #define MCOUNT_ADDR ((unsigned long)_mcount) +#endif + +/* The BL at the callsite's adjusted rec->ip */ #define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE +#define FTRACE_PLT_IDX 0 +#define FTRACE_REGS_PLT_IDX 1 +#define NR_FTRACE_PLTS 2 + /* * Currently, gcc tends to save the link register after the local variables * on the stack. This causes the max stack tracer to report the function @@ -44,12 +55,24 @@ extern void return_to_handler(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { /* + * Adjust addr to point at the BL in the callsite. + * See ftrace_init_nop() for the callsite sequence. + */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + return addr + AARCH64_INSN_SIZE; + /* * addr is the address of the mcount call instruction. * recordmcount does the necessary offset calculation. */ return addr; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +struct dyn_ftrace; +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop +#endif + #define ftrace_return_address(n) return_address(n) /* diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 39e7780bedd6..bb313dde58a4 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -440,6 +440,9 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, int shift, enum aarch64_insn_variant variant, enum aarch64_insn_logic_type type); +u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_variant variant); u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type, enum aarch64_insn_variant variant, enum aarch64_insn_register Rn, diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index 1a59f0ed1ae3..aa4b6521ef14 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -6,6 +6,7 @@ #define __ASM_IRQFLAGS_H #include <asm/alternative.h> +#include <asm/barrier.h> #include <asm/ptrace.h> #include <asm/sysreg.h> @@ -34,14 +35,14 @@ static inline void arch_local_irq_enable(void) } asm volatile(ALTERNATIVE( - "msr daifclr, #2 // arch_local_irq_enable\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", + "msr daifclr, #2 // arch_local_irq_enable", + __msr_s(SYS_ICC_PMR_EL1, "%0"), ARM64_HAS_IRQ_PRIO_MASKING) : : "r" ((unsigned long) GIC_PRIO_IRQON) : "memory"); + + pmr_sync(); } static inline void arch_local_irq_disable(void) @@ -116,14 +117,14 @@ static inline unsigned long arch_local_irq_save(void) static inline void arch_local_irq_restore(unsigned long flags) { asm volatile(ALTERNATIVE( - "msr daif, %0\n" - "nop", - __msr_s(SYS_ICC_PMR_EL1, "%0") - "dsb sy", - ARM64_HAS_IRQ_PRIO_MASKING) + "msr daif, %0", + __msr_s(SYS_ICC_PMR_EL1, "%0"), + ARM64_HAS_IRQ_PRIO_MASKING) : : "r" (flags) : "memory"); + + pmr_sync(); } #endif /* __ASM_IRQFLAGS_H */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f656169db8c3..5ecb091c8576 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -600,8 +600,7 @@ static inline void kvm_arm_vhe_guest_enter(void) * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. */ - if (system_uses_irq_prio_masking()) - dsb(sy); + pmr_sync(); } static inline void kvm_arm_vhe_guest_exit(void) diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 86825aa20852..97f21cc66657 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -47,30 +47,6 @@ #define read_sysreg_el2(r) read_sysreg_elx(r, _EL2, _EL1) #define write_sysreg_el2(v,r) write_sysreg_elx(v, r, _EL2, _EL1) -/** - * hyp_alternate_select - Generates patchable code sequences that are - * used to switch between two implementations of a function, depending - * on the availability of a feature. - * - * @fname: a symbol name that will be defined as a function returning a - * function pointer whose type will match @orig and @alt - * @orig: A pointer to the default function, as returned by @fname when - * @cond doesn't hold - * @alt: A pointer to the alternate function, as returned by @fname - * when @cond holds - * @cond: a CPU feature (as described in asm/cpufeature.h) - */ -#define hyp_alternate_select(fname, orig, alt, cond) \ -typeof(orig) * __hyp_text fname(void) \ -{ \ - typeof(alt) *val = orig; \ - asm volatile(ALTERNATIVE("nop \n", \ - "mov %0, %1 \n", \ - cond) \ - : "+r" (val) : "r" (alt)); \ - return val; \ -} - int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu); void __vgic_v3_save_state(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index b61b50bf68b1..a4f9ca5479b0 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -69,12 +69,6 @@ #define KERNEL_START _text #define KERNEL_END _end -#ifdef CONFIG_ARM64_VA_BITS_52 -#define MAX_USER_VA_BITS 52 -#else -#define MAX_USER_VA_BITS VA_BITS -#endif - /* * Generic and tag-based KASAN require 1/8th and 1/16th of the kernel virtual * address space for the shadow region respectively. They can bloat the stack @@ -215,12 +209,18 @@ static inline unsigned long kaslr_offset(void) * up with a tagged userland pointer. Clear the tag to get a sane pointer to * pass on to access_ok(), for instance. */ -#define untagged_addr(addr) \ +#define __untagged_addr(addr) \ ((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55)) +#define untagged_addr(addr) ({ \ + u64 __addr = (__force u64)addr; \ + __addr &= __untagged_addr(__addr); \ + (__force __typeof__(addr))__addr; \ +}) + #ifdef CONFIG_KASAN_SW_TAGS #define __tag_shifted(tag) ((u64)(tag) << 56) -#define __tag_reset(addr) untagged_addr(addr) +#define __tag_reset(addr) __untagged_addr(addr) #define __tag_get(addr) (__u8)((u64)(addr) >> 56) #else #define __tag_shifted(tag) 0UL diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index f80e13cbf8ec..1e93de68c044 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -21,7 +21,7 @@ struct mod_arch_specific { struct mod_plt_sec init; /* for CONFIG_DYNAMIC_FTRACE */ - struct plt_entry *ftrace_trampoline; + struct plt_entry *ftrace_trampolines; }; #endif diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 3df60f97da1f..d9fbd433cc17 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -69,7 +69,7 @@ #define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS) #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) -#define PTRS_PER_PGD (1 << (MAX_USER_VA_BITS - PGDIR_SHIFT)) +#define PTRS_PER_PGD (1 << (VA_BITS - PGDIR_SHIFT)) /* * Section address mask and size definitions. diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 9a21b84536f2..8dc6c5cdabe6 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -32,11 +32,11 @@ #define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) #define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) -#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) -#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) -#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) -#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) -#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) @@ -80,8 +80,9 @@ #define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) -#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) -#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) +/* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */ +#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) +#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE) #define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7576df00eb50..5d15b4735a0e 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -17,7 +17,7 @@ * VMALLOC range. * * VMALLOC_START: beginning of the kernel vmalloc space - * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space + * VMALLOC_END: extends to the available space below vmemmap, PCI I/O space * and fixed mappings */ #define VMALLOC_START (MODULES_END) @@ -283,23 +283,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, set_pte(ptep, pte); } -#define __HAVE_ARCH_PTE_SAME -static inline int pte_same(pte_t pte_a, pte_t pte_b) -{ - pteval_t lhs, rhs; - - lhs = pte_val(pte_a); - rhs = pte_val(pte_b); - - if (pte_present(pte_a)) - lhs &= ~PTE_RDONLY; - - if (pte_present(pte_b)) - rhs &= ~PTE_RDONLY; - - return (lhs == rhs); -} - /* * Huge pte definitions. */ @@ -876,15 +859,26 @@ static inline void update_mmu_cache(struct vm_area_struct *vma, #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) -#define kc_vaddr_to_offset(v) ((v) & ~PAGE_END) -#define kc_offset_to_vaddr(o) ((o) | PAGE_END) - #ifdef CONFIG_ARM64_PA_BITS_52 #define phys_to_ttbr(addr) (((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52) #else #define phys_to_ttbr(addr) (addr) #endif +/* + * On arm64 without hardware Access Flag, copying from user will fail because + * the pte is old and cannot be marked young. So we always end up with zeroed + * page after fork() + CoW for pfn mappings. We don't always have a + * hardware-managed access flag on arm64. + */ +static inline bool arch_faults_on_old_pte(void) +{ + WARN_ON(preemptible()); + + return !cpu_has_hw_af(); +} +#define arch_faults_on_old_pte arch_faults_on_old_pte + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 5623685c7d13..5ba63204d078 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -9,7 +9,7 @@ #define __ASM_PROCESSOR_H #define KERNEL_DS UL(-1) -#define USER_DS ((UL(1) << MAX_USER_VA_BITS) - 1) +#define USER_DS ((UL(1) << VA_BITS) - 1) /* * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is @@ -26,10 +26,12 @@ #include <linux/init.h> #include <linux/stddef.h> #include <linux/string.h> +#include <linux/thread_info.h> #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/hw_breakpoint.h> +#include <asm/kasan.h> #include <asm/lse.h> #include <asm/pgtable-hwdef.h> #include <asm/pointer_auth.h> @@ -214,6 +216,18 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc, regs->sp = sp; } +static inline bool is_ttbr0_addr(unsigned long addr) +{ + /* entry assembly clears tags for TTBR0 addrs */ + return addr < TASK_SIZE; +} + +static inline bool is_ttbr1_addr(unsigned long addr) +{ + /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ + return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; +} + #ifdef CONFIG_COMPAT static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h index 06d880b3526c..b383b4802a7b 100644 --- a/arch/arm64/include/asm/syscall_wrapper.h +++ b/arch/arm64/include/asm/syscall_wrapper.h @@ -66,24 +66,18 @@ struct pt_regs; } \ static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#ifndef SYSCALL_DEFINE0 #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused); \ ALLOW_ERROR_INJECTION(__arm64_sys_##sname, ERRNO); \ asmlinkage long __arm64_sys_##sname(const struct pt_regs *__unused) -#endif -#ifndef COND_SYSCALL #define COND_SYSCALL(name) \ asmlinkage long __weak __arm64_sys_##name(const struct pt_regs *regs) \ { \ return sys_ni_syscall(); \ } -#endif -#ifndef SYS_NI #define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers); -#endif #endif /* __ASM_SYSCALL_WRAPPER_H */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 972d196c7714..6e919fafb43d 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -212,7 +212,7 @@ #define SYS_FAR_EL1 sys_reg(3, 0, 6, 0, 0) #define SYS_PAR_EL1 sys_reg(3, 0, 7, 4, 0) -#define SYS_PAR_EL1_F BIT(1) +#define SYS_PAR_EL1_F BIT(0) #define SYS_PAR_EL1_FST GENMASK(6, 1) /*** Statistical Profiling Extension ***/ diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index 59690613ac31..cee5928e1b7d 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -42,16 +42,6 @@ static inline int __in_irqentry_text(unsigned long ptr) ptr < (unsigned long)&__irqentry_text_end; } -static inline int in_exception_text(unsigned long ptr) -{ - int in; - - in = ptr >= (unsigned long)&__exception_text_start && - ptr < (unsigned long)&__exception_text_end; - - return in ? : __in_irqentry_text(ptr); -} - static inline int in_entry_text(unsigned long ptr) { return ptr >= (unsigned long)&__entry_text_start && diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 097d6bfac0b7..127712b0b970 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -378,20 +378,34 @@ do { \ extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n); #define raw_copy_from_user(to, from, n) \ ({ \ - __arch_copy_from_user((to), __uaccess_mask_ptr(from), (n)); \ + unsigned long __acfu_ret; \ + uaccess_enable_not_uao(); \ + __acfu_ret = __arch_copy_from_user((to), \ + __uaccess_mask_ptr(from), (n)); \ + uaccess_disable_not_uao(); \ + __acfu_ret; \ }) extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n); #define raw_copy_to_user(to, from, n) \ ({ \ - __arch_copy_to_user(__uaccess_mask_ptr(to), (from), (n)); \ + unsigned long __actu_ret; \ + uaccess_enable_not_uao(); \ + __actu_ret = __arch_copy_to_user(__uaccess_mask_ptr(to), \ + (from), (n)); \ + uaccess_disable_not_uao(); \ + __actu_ret; \ }) extern unsigned long __must_check __arch_copy_in_user(void __user *to, const void __user *from, unsigned long n); #define raw_copy_in_user(to, from, n) \ ({ \ - __arch_copy_in_user(__uaccess_mask_ptr(to), \ - __uaccess_mask_ptr(from), (n)); \ + unsigned long __aciu_ret; \ + uaccess_enable_not_uao(); \ + __aciu_ret = __arch_copy_in_user(__uaccess_mask_ptr(to), \ + __uaccess_mask_ptr(from), (n)); \ + uaccess_disable_not_uao(); \ + __aciu_ret; \ }) #define INLINE_COPY_TO_USER @@ -400,8 +414,11 @@ extern unsigned long __must_check __arch_copy_in_user(void __user *to, const voi extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned long n); static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n) { - if (access_ok(to, n)) + if (access_ok(to, n)) { + uaccess_enable_not_uao(); n = __arch_clear_user(__uaccess_mask_ptr(to), n); + uaccess_disable_not_uao(); + } return n; } #define clear_user __clear_user diff --git a/arch/arm64/include/asm/vdso/compat_barrier.h b/arch/arm64/include/asm/vdso/compat_barrier.h index fb60a88b5ed4..3fd8fd6d8fc2 100644 --- a/arch/arm64/include/asm/vdso/compat_barrier.h +++ b/arch/arm64/include/asm/vdso/compat_barrier.h @@ -20,7 +20,7 @@ #define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory") -#if __LINUX_ARM_ARCH__ >= 8 +#if __LINUX_ARM_ARCH__ >= 8 && defined(CONFIG_AS_DMB_ISHLD) #define aarch32_smp_mb() dmb(ish) #define aarch32_smp_rmb() dmb(ishld) #define aarch32_smp_wmb() dmb(ishst) diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h index 0c731bfc7c8c..0c20a7c1bee5 100644 --- a/arch/arm64/include/asm/vdso/vsyscall.h +++ b/arch/arm64/include/asm/vdso/vsyscall.h @@ -31,13 +31,6 @@ int __arm64_get_clock_mode(struct timekeeper *tk) #define __arch_get_clock_mode __arm64_get_clock_mode static __always_inline -int __arm64_use_vsyscall(struct vdso_data *vdata) -{ - return !vdata[CS_HRES_COARSE].clock_mode; -} -#define __arch_use_vsyscall __arm64_use_vsyscall - -static __always_inline void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk) { vdata[CS_HRES_COARSE].mask = VDSO_PRECISION_MASK; diff --git a/arch/arm64/include/asm/vdso_datapage.h b/arch/arm64/include/asm/vdso_datapage.h deleted file mode 100644 index 1f38bf330a6e..000000000000 --- a/arch/arm64/include/asm/vdso_datapage.h +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 ARM Limited - */ -#ifndef __ASM_VDSO_DATAPAGE_H -#define __ASM_VDSO_DATAPAGE_H - -#ifndef __ASSEMBLY__ - -struct vdso_data { - __u64 cs_cycle_last; /* Timebase at clocksource init */ - __u64 raw_time_sec; /* Raw time */ - __u64 raw_time_nsec; - __u64 xtime_clock_sec; /* Kernel time */ - __u64 xtime_clock_nsec; - __u64 xtime_coarse_sec; /* Coarse time */ - __u64 xtime_coarse_nsec; - __u64 wtm_clock_sec; /* Wall to monotonic time */ - __u64 wtm_clock_nsec; - __u32 tb_seq_count; /* Timebase sequence counter */ - /* cs_* members must be adjacent and in this order (ldp accesses) */ - __u32 cs_mono_mult; /* NTP-adjusted clocksource multiplier */ - __u32 cs_shift; /* Clocksource shift (mono = raw) */ - __u32 cs_raw_mult; /* Raw clocksource multiplier */ - __u32 tz_minuteswest; /* Whacky timezone stuff */ - __u32 tz_dsttime; - __u32 use_syscall; - __u32 hrtimer_res; -}; - -#endif /* !__ASSEMBLY__ */ - -#endif /* __ASM_VDSO_DATAPAGE_H */ diff --git a/arch/arm64/include/asm/xen/xen-ops.h b/arch/arm64/include/asm/xen/xen-ops.h deleted file mode 100644 index e6e784051932..000000000000 --- a/arch/arm64/include/asm/xen/xen-ops.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_XEN_OPS_H -#define _ASM_XEN_OPS_H - -void xen_efi_runtime_setup(void); - -#endif /* _ASM_XEN_OPS_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 478491f07b4f..fc6488660f64 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -13,9 +13,9 @@ CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) # Object file lists. obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ - entry-fpsimd.o process.o ptrace.o setup.o signal.o \ - sys.o stacktrace.o time.o traps.o io.o vdso.o \ - hyp-stub.o psci.o cpu_ops.o insn.o \ + entry-common.o entry-fpsimd.o process.o ptrace.o \ + setup.o signal.o sys.o stacktrace.o time.o traps.o \ + io.o vdso.o hyp-stub.o psci.o cpu_ops.o insn.o \ return_address.o cpuinfo.o cpu_errata.o \ cpufeature.o alternative.o cacheinfo.o \ smp.o smp_spin_table.o topology.o smccc-call.o \ diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 2ec09debc2bb..ca158be21f83 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -174,6 +174,9 @@ static void __init register_insn_emulation(struct insn_emulation_ops *ops) struct insn_emulation *insn; insn = kzalloc(sizeof(*insn), GFP_KERNEL); + if (!insn) + return; + insn->ops = ops; insn->min = INSN_UNDEF; @@ -233,6 +236,8 @@ static void __init register_insn_emulation_sysctl(void) insns_sysctl = kcalloc(nr_insn_emulated + 1, sizeof(*sysctl), GFP_KERNEL); + if (!insns_sysctl) + return; raw_spin_lock_irqsave(&insn_emulation_lock, flags); list_for_each_entry(insn, &insn_emulation, node) { diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 214685760e1c..a5bdce8af65b 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -56,6 +56,7 @@ int main(void) DEFINE(S_X24, offsetof(struct pt_regs, regs[24])); DEFINE(S_X26, offsetof(struct pt_regs, regs[26])); DEFINE(S_X28, offsetof(struct pt_regs, regs[28])); + DEFINE(S_FP, offsetof(struct pt_regs, regs[29])); DEFINE(S_LR, offsetof(struct pt_regs, regs[30])); DEFINE(S_SP, offsetof(struct pt_regs, sp)); DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 1e43ba5c79b7..bbdc95ee4642 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -6,12 +6,12 @@ */ #include <linux/arm-smccc.h> -#include <linux/psci.h> #include <linux/types.h> #include <linux/cpu.h> #include <asm/cpu.h> #include <asm/cputype.h> #include <asm/cpufeature.h> +#include <asm/smp_plat.h> static bool __maybe_unused is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope) @@ -87,13 +87,21 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry, } static void -cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused) +cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap) { u64 mask = arm64_ftr_reg_ctrel0.strict_mask; + bool enable_uct_trap = false; /* Trap CTR_EL0 access on this CPU, only if it has a mismatch */ if ((read_cpuid_cachetype() & mask) != (arm64_ftr_reg_ctrel0.sys_val & mask)) + enable_uct_trap = true; + + /* ... or if the system is affected by an erratum */ + if (cap->capability == ARM64_WORKAROUND_1542419) + enable_uct_trap = true; + + if (enable_uct_trap) sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0); } @@ -128,8 +136,8 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, int cpu, slot = -1; /* - * enable_smccc_arch_workaround_1() passes NULL for the hyp_vecs - * start/end if we're a guest. Skip the hyp-vectors work. + * detect_harden_bp_fw() passes NULL for the hyp_vecs start/end if + * we're a guest. Skip the hyp-vectors work. */ if (!hyp_vecs_start) { __this_cpu_write(bp_hardening_data.fn, fn); @@ -166,9 +174,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, } #endif /* CONFIG_KVM_INDIRECT_VECTORS */ -#include <uapi/linux/psci.h> #include <linux/arm-smccc.h> -#include <linux/psci.h> static void call_smc_arch_workaround_1(void) { @@ -212,11 +218,8 @@ static int detect_harden_bp_fw(void) struct arm_smccc_res res; u32 midr = read_cpuid_id(); - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) - return -1; - - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); switch ((int)res.a0) { @@ -234,7 +237,7 @@ static int detect_harden_bp_fw(void) } break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_1, &res); switch ((int)res.a0) { @@ -308,11 +311,11 @@ void __init arm64_update_smccc_conduit(struct alt_instr *alt, BUG_ON(nr_inst != 1); - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: insn = aarch64_insn_get_hvc_value(); break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: insn = aarch64_insn_get_smc_value(); break; default: @@ -351,12 +354,12 @@ void arm64_set_ssbd_mitigation(bool state) return; } - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL); break; @@ -390,20 +393,13 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry, goto out_printmsg; } - if (psci_ops.smccc_version == SMCCC_VERSION_1_0) { - ssbd_state = ARM64_SSBD_UNKNOWN; - if (!this_cpu_safe) - __ssb_safe = false; - return false; - } - - switch (psci_ops.conduit) { - case PSCI_CONDUIT_HVC: + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_2, &res); break; - case PSCI_CONDUIT_SMC: + case SMCCC_CONDUIT_SMC: arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, ARM_SMCCC_ARCH_WORKAROUND_2, &res); break; @@ -488,6 +484,7 @@ static const struct midr_range arm64_ssb_cpus[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), {}, }; @@ -572,6 +569,7 @@ static const struct midr_range spectre_v2_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), { /* sentinel */ } }; @@ -623,9 +621,45 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope) return (need_wa > 0); } -#ifdef CONFIG_HARDEN_EL2_VECTORS +static const __maybe_unused struct midr_range tx2_family_cpus[] = { + MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), + MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), + {}, +}; + +static bool __maybe_unused +needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry, + int scope) +{ + int i; + + if (!is_affected_midr_range_list(entry, scope) || + !is_hyp_mode_available()) + return false; + + for_each_possible_cpu(i) { + if (MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0) != 0) + return true; + } -static const struct midr_range arm64_harden_el2_vectors[] = { + return false; +} + +static bool __maybe_unused +has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry, + int scope) +{ + u32 midr = read_cpuid_id(); + bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT); + const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1); + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + return is_midr_in_range(midr, &range) && has_dic; +} + +#if defined(CONFIG_HARDEN_EL2_VECTORS) || defined(CONFIG_ARM64_ERRATUM_1319367) + +static const struct midr_range ca57_a72[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), {}, @@ -634,17 +668,23 @@ static const struct midr_range arm64_harden_el2_vectors[] = { #endif #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI - -static const struct midr_range arm64_repeat_tlbi_cpus[] = { +static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = { #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009 - MIDR_RANGE(MIDR_QCOM_FALKOR_V1, 0, 0, 0, 0), + { + ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0) + }, + { + .midr_range.model = MIDR_QCOM_KRYO, + .matches = is_kryo_midr, + }, #endif #ifdef CONFIG_ARM64_ERRATUM_1286807 - MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0), + { + ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0), + }, #endif {}, }; - #endif #ifdef CONFIG_CAVIUM_ERRATUM_27456 @@ -712,6 +752,33 @@ static const struct midr_range erratum_1418040_list[] = { }; #endif +#ifdef CONFIG_ARM64_ERRATUM_845719 +static const struct midr_range erratum_845719_list[] = { + /* Cortex-A53 r0p[01234] */ + MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), + /* Brahma-B53 r0p[0] */ + MIDR_REV(MIDR_BRAHMA_B53, 0, 0), + {}, +}; +#endif + +#ifdef CONFIG_ARM64_ERRATUM_843419 +static const struct arm64_cpu_capabilities erratum_843419_list[] = { + { + /* Cortex-A53 r0p[01234] */ + .matches = is_affected_midr_range, + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), + MIDR_FIXED(0x4, BIT(8)), + }, + { + /* Brahma-B53 r0p[0] */ + .matches = is_affected_midr_range, + ERRATA_MIDR_REV(MIDR_BRAHMA_B53, 0, 0), + }, + {}, +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -743,19 +810,18 @@ const struct arm64_cpu_capabilities arm64_errata[] = { #endif #ifdef CONFIG_ARM64_ERRATUM_843419 { - /* Cortex-A53 r0p[01234] */ .desc = "ARM erratum 843419", .capability = ARM64_WORKAROUND_843419, - ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), - MIDR_FIXED(0x4, BIT(8)), + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = cpucap_multi_entry_cap_matches, + .match_list = erratum_843419_list, }, #endif #ifdef CONFIG_ARM64_ERRATUM_845719 { - /* Cortex-A53 r0p[01234] */ .desc = "ARM erratum 845719", .capability = ARM64_WORKAROUND_845719, - ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), + ERRATA_MIDR_RANGE_LIST(erratum_845719_list), }, #endif #ifdef CONFIG_CAVIUM_ERRATUM_23154 @@ -791,6 +857,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "Qualcomm Technologies Falkor/Kryo erratum 1003", .capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .matches = cpucap_multi_entry_cap_matches, .match_list = qcom_erratum_1003_list, }, @@ -799,7 +866,9 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "Qualcomm erratum 1009, ARM erratum 1286807", .capability = ARM64_WORKAROUND_REPEAT_TLBI, - ERRATA_MIDR_RANGE_LIST(arm64_repeat_tlbi_cpus), + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = cpucap_multi_entry_cap_matches, + .match_list = arm64_repeat_tlbi_list, }, #endif #ifdef CONFIG_ARM64_ERRATUM_858921 @@ -819,7 +888,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "EL2 vector hardening", .capability = ARM64_HARDEN_EL2_VECTORS, - ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors), + ERRATA_MIDR_RANGE_LIST(ca57_a72), }, #endif { @@ -852,6 +921,36 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .matches = has_cortex_a76_erratum_1463225, }, #endif +#ifdef CONFIG_CAVIUM_TX2_ERRATUM_219 + { + .desc = "Cavium ThunderX2 erratum 219 (KVM guest sysreg trapping)", + .capability = ARM64_WORKAROUND_CAVIUM_TX2_219_TVM, + ERRATA_MIDR_RANGE_LIST(tx2_family_cpus), + .matches = needs_tx2_tvm_workaround, + }, + { + .desc = "Cavium ThunderX2 erratum 219 (PRFM removal)", + .capability = ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM, + ERRATA_MIDR_RANGE_LIST(tx2_family_cpus), + }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_1542419 + { + /* we depend on the firmware portion for correctness */ + .desc = "ARM erratum 1542419 (kernel portion)", + .capability = ARM64_WORKAROUND_1542419, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = has_neoverse_n1_erratum_1542419, + .cpu_enable = cpu_enable_trap_ctr_access, + }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_1319367 + { + .desc = "ARM erratum 1319367", + .capability = ARM64_WORKAROUND_1319367, + ERRATA_MIDR_RANGE_LIST(ca57_a72), + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 9323bcc40a58..04cf64e9f0c9 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -136,6 +136,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FRINTTS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_GPI_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), @@ -175,11 +176,16 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -976,6 +982,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), { /* sentinel */ } }; char const *str = "kpti command line option"; diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 05933c065732..56bba746da1c 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -329,7 +329,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_cntfrq = arch_timer_get_cntfrq(); /* * Use the effective value of the CTR_EL0 than the raw value - * exposed by the CPU. CTR_E0.IDC field value must be interpreted + * exposed by the CPU. CTR_EL0.IDC field value must be interpreted * with the CLIDR_EL1 fields to avoid triggering false warnings * when there is a mismatch across the CPUs. Keep track of the * effective value of the CTR_EL0 in our internal records for diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c new file mode 100644 index 000000000000..5dce5e56995a --- /dev/null +++ b/arch/arm64/kernel/entry-common.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Exception handling code + * + * Copyright (C) 2019 ARM Ltd. + */ + +#include <linux/context_tracking.h> +#include <linux/ptrace.h> +#include <linux/thread_info.h> + +#include <asm/cpufeature.h> +#include <asm/daifflags.h> +#include <asm/esr.h> +#include <asm/exception.h> +#include <asm/kprobes.h> +#include <asm/mmu.h> +#include <asm/sysreg.h> + +static void notrace el1_abort(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + local_daif_inherit(regs); + far = untagged_addr(far); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_abort); + +static void notrace el1_pc(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + local_daif_inherit(regs); + do_sp_pc_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_pc); + +static void el1_undef(struct pt_regs *regs) +{ + local_daif_inherit(regs); + do_undefinstr(regs); +} +NOKPROBE_SYMBOL(el1_undef); + +static void el1_inv(struct pt_regs *regs, unsigned long esr) +{ + local_daif_inherit(regs); + bad_mode(regs, 0, esr); +} +NOKPROBE_SYMBOL(el1_inv); + +static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + /* + * The CPU masked interrupts, and we are leaving them masked during + * do_debug_exception(). Update PMR as if we had called + * local_mask_daif(). + */ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + do_debug_exception(far, esr, regs); +} +NOKPROBE_SYMBOL(el1_dbg); + +asmlinkage void notrace el1_sync_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_DABT_CUR: + case ESR_ELx_EC_IABT_CUR: + el1_abort(regs, esr); + break; + /* + * We don't handle ESR_ELx_EC_SP_ALIGN, since we will have hit a + * recursive exception when trying to push the initial pt_regs. + */ + case ESR_ELx_EC_PC_ALIGN: + el1_pc(regs, esr); + break; + case ESR_ELx_EC_SYS64: + case ESR_ELx_EC_UNKNOWN: + el1_undef(regs); + break; + case ESR_ELx_EC_BREAKPT_CUR: + case ESR_ELx_EC_SOFTSTP_CUR: + case ESR_ELx_EC_WATCHPT_CUR: + case ESR_ELx_EC_BRK64: + el1_dbg(regs, esr); + break; + default: + el1_inv(regs, esr); + }; +} +NOKPROBE_SYMBOL(el1_sync_handler); + +static void notrace el0_da(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + far = untagged_addr(far); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_da); + +static void notrace el0_ia(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + /* + * We've taken an instruction abort from userspace and not yet + * re-enabled IRQs. If the address is a kernel address, apply + * BP hardening prior to enabling IRQs and pre-emption. + */ + if (!is_ttbr0_addr(far)) + arm64_apply_bp_hardening(); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_mem_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_ia); + +static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_fpsimd_acc(esr, regs); +} +NOKPROBE_SYMBOL(el0_fpsimd_acc); + +static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sve_acc(esr, regs); +} +NOKPROBE_SYMBOL(el0_sve_acc); + +static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_fpsimd_exc(esr, regs); +} +NOKPROBE_SYMBOL(el0_fpsimd_exc); + +static void notrace el0_sys(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sysinstr(esr, regs); +} +NOKPROBE_SYMBOL(el0_sys); + +static void notrace el0_pc(struct pt_regs *regs, unsigned long esr) +{ + unsigned long far = read_sysreg(far_el1); + + if (!is_ttbr0_addr(instruction_pointer(regs))) + arm64_apply_bp_hardening(); + + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_sp_pc_abort(far, esr, regs); +} +NOKPROBE_SYMBOL(el0_pc); + +static void notrace el0_sp(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX_NOIRQ); + do_sp_pc_abort(regs->sp, esr, regs); +} +NOKPROBE_SYMBOL(el0_sp); + +static void notrace el0_undef(struct pt_regs *regs) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_undefinstr(regs); +} +NOKPROBE_SYMBOL(el0_undef); + +static void notrace el0_inv(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + bad_el0_sync(regs, 0, esr); +} +NOKPROBE_SYMBOL(el0_inv); + +static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr) +{ + /* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */ + unsigned long far = read_sysreg(far_el1); + + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + user_exit_irqoff(); + do_debug_exception(far, esr, regs); + local_daif_restore(DAIF_PROCCTX_NOIRQ); +} +NOKPROBE_SYMBOL(el0_dbg); + +static void notrace el0_svc(struct pt_regs *regs) +{ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + el0_svc_handler(regs); +} +NOKPROBE_SYMBOL(el0_svc); + +asmlinkage void notrace el0_sync_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_SVC64: + el0_svc(regs); + break; + case ESR_ELx_EC_DABT_LOW: + el0_da(regs, esr); + break; + case ESR_ELx_EC_IABT_LOW: + el0_ia(regs, esr); + break; + case ESR_ELx_EC_FP_ASIMD: + el0_fpsimd_acc(regs, esr); + break; + case ESR_ELx_EC_SVE: + el0_sve_acc(regs, esr); + break; + case ESR_ELx_EC_FP_EXC64: + el0_fpsimd_exc(regs, esr); + break; + case ESR_ELx_EC_SYS64: + case ESR_ELx_EC_WFx: + el0_sys(regs, esr); + break; + case ESR_ELx_EC_SP_ALIGN: + el0_sp(regs, esr); + break; + case ESR_ELx_EC_PC_ALIGN: + el0_pc(regs, esr); + break; + case ESR_ELx_EC_UNKNOWN: + el0_undef(regs); + break; + case ESR_ELx_EC_BREAKPT_LOW: + case ESR_ELx_EC_SOFTSTP_LOW: + case ESR_ELx_EC_WATCHPT_LOW: + case ESR_ELx_EC_BRK64: + el0_dbg(regs, esr); + break; + default: + el0_inv(regs, esr); + } +} +NOKPROBE_SYMBOL(el0_sync_handler); + +#ifdef CONFIG_COMPAT +static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr) +{ + user_exit_irqoff(); + local_daif_restore(DAIF_PROCCTX); + do_cp15instr(esr, regs); +} +NOKPROBE_SYMBOL(el0_cp15); + +static void notrace el0_svc_compat(struct pt_regs *regs) +{ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + + el0_svc_compat_handler(regs); +} +NOKPROBE_SYMBOL(el0_svc_compat); + +asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs) +{ + unsigned long esr = read_sysreg(esr_el1); + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_SVC32: + el0_svc_compat(regs); + break; + case ESR_ELx_EC_DABT_LOW: + el0_da(regs, esr); + break; + case ESR_ELx_EC_IABT_LOW: + el0_ia(regs, esr); + break; + case ESR_ELx_EC_FP_ASIMD: + el0_fpsimd_acc(regs, esr); + break; + case ESR_ELx_EC_FP_EXC32: + el0_fpsimd_exc(regs, esr); + break; + case ESR_ELx_EC_PC_ALIGN: + el0_pc(regs, esr); + break; + case ESR_ELx_EC_UNKNOWN: + case ESR_ELx_EC_CP14_MR: + case ESR_ELx_EC_CP14_LS: + case ESR_ELx_EC_CP14_64: + el0_undef(regs); + break; + case ESR_ELx_EC_CP15_32: + case ESR_ELx_EC_CP15_64: + el0_cp15(regs, esr); + break; + case ESR_ELx_EC_BREAKPT_LOW: + case ESR_ELx_EC_SOFTSTP_LOW: + case ESR_ELx_EC_WATCHPT_LOW: + case ESR_ELx_EC_BKPT32: + el0_dbg(regs, esr); + break; + default: + el0_inv(regs, esr); + } +} +NOKPROBE_SYMBOL(el0_sync_compat_handler); +#endif /* CONFIG_COMPAT */ diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 33d003d80121..4fe1514fcbfd 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -7,10 +7,137 @@ */ #include <linux/linkage.h> +#include <asm/asm-offsets.h> #include <asm/assembler.h> #include <asm/ftrace.h> #include <asm/insn.h> +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +/* + * Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before + * the regular function prologue. For an enabled callsite, ftrace_init_nop() and + * ftrace_make_call() have patched those NOPs to: + * + * MOV X9, LR + * BL <entry> + * + * ... where <entry> is either ftrace_caller or ftrace_regs_caller. + * + * Each instrumented function follows the AAPCS, so here x0-x8 and x19-x30 are + * live, and x9-x18 are safe to clobber. + * + * We save the callsite's context into a pt_regs before invoking any ftrace + * callbacks. So that we can get a sensible backtrace, we create a stack record + * for the callsite and the ftrace entry assembly. This is not sufficient for + * reliable stacktrace: until we create the callsite stack record, its caller + * is missing from the LR and existing chain of frame records. + */ + .macro ftrace_regs_entry, allregs=0 + /* Make room for pt_regs, plus a callee frame */ + sub sp, sp, #(S_FRAME_SIZE + 16) + + /* Save function arguments (and x9 for simplicity) */ + stp x0, x1, [sp, #S_X0] + stp x2, x3, [sp, #S_X2] + stp x4, x5, [sp, #S_X4] + stp x6, x7, [sp, #S_X6] + stp x8, x9, [sp, #S_X8] + + /* Optionally save the callee-saved registers, always save the FP */ + .if \allregs == 1 + stp x10, x11, [sp, #S_X10] + stp x12, x13, [sp, #S_X12] + stp x14, x15, [sp, #S_X14] + stp x16, x17, [sp, #S_X16] + stp x18, x19, [sp, #S_X18] + stp x20, x21, [sp, #S_X20] + stp x22, x23, [sp, #S_X22] + stp x24, x25, [sp, #S_X24] + stp x26, x27, [sp, #S_X26] + stp x28, x29, [sp, #S_X28] + .else + str x29, [sp, #S_FP] + .endif + + /* Save the callsite's SP and LR */ + add x10, sp, #(S_FRAME_SIZE + 16) + stp x9, x10, [sp, #S_LR] + + /* Save the PC after the ftrace callsite */ + str x30, [sp, #S_PC] + + /* Create a frame record for the callsite above pt_regs */ + stp x29, x9, [sp, #S_FRAME_SIZE] + add x29, sp, #S_FRAME_SIZE + + /* Create our frame record within pt_regs. */ + stp x29, x30, [sp, #S_STACKFRAME] + add x29, sp, #S_STACKFRAME + .endm + +ENTRY(ftrace_regs_caller) + ftrace_regs_entry 1 + b ftrace_common +ENDPROC(ftrace_regs_caller) + +ENTRY(ftrace_caller) + ftrace_regs_entry 0 + b ftrace_common +ENDPROC(ftrace_caller) + +ENTRY(ftrace_common) + sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn) + mov x1, x9 // parent_ip (callsite's LR) + ldr_l x2, function_trace_op // op + mov x3, sp // regs + +GLOBAL(ftrace_call) + bl ftrace_stub + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); + nop // If enabled, this will be replaced + // "b ftrace_graph_caller" +#endif + +/* + * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved + * x19-x29 per the AAPCS, and we created frame records upon entry, so we need + * to restore x0-x8, x29, and x30. + */ +ftrace_common_return: + /* Restore function arguments */ + ldp x0, x1, [sp] + ldp x2, x3, [sp, #S_X2] + ldp x4, x5, [sp, #S_X4] + ldp x6, x7, [sp, #S_X6] + ldr x8, [sp, #S_X8] + + /* Restore the callsite's FP, LR, PC */ + ldr x29, [sp, #S_FP] + ldr x30, [sp, #S_LR] + ldr x9, [sp, #S_PC] + + /* Restore the callsite's SP */ + add sp, sp, #S_FRAME_SIZE + 16 + + ret x9 +ENDPROC(ftrace_common) + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + ldr x0, [sp, #S_PC] + sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) + add x1, sp, #S_LR // parent_ip (callsite's LR) + ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP) + bl prepare_ftrace_return + b ftrace_common_return +ENDPROC(ftrace_graph_caller) +#else +#endif + +#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + /* * Gcc with -pg will put the following code in the beginning of each function: * mov x0, x30 @@ -160,11 +287,6 @@ GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); mcount_exit ENDPROC(ftrace_caller) -#endif /* CONFIG_DYNAMIC_FTRACE */ - -ENTRY(ftrace_stub) - ret -ENDPROC(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* @@ -184,7 +306,15 @@ ENTRY(ftrace_graph_caller) mcount_exit ENDPROC(ftrace_graph_caller) +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ + +ENTRY(ftrace_stub) + ret +ENDPROC(ftrace_stub) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER /* * void return_to_handler(void) * diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 84a822748c84..583f71abbe98 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -269,8 +269,10 @@ alternative_else_nop_endif alternative_if ARM64_HAS_IRQ_PRIO_MASKING ldr x20, [sp, #S_PMR_SAVE] msr_s SYS_ICC_PMR_EL1, x20 - /* Ensure priority change is seen by redistributor */ - dsb sy + mrs_s x21, SYS_ICC_CTLR_EL1 + tbz x21, #6, .L__skip_pmr_sync\@ // Check for ICC_CTLR_EL1.PMHE + dsb sy // Ensure priority change is seen by redistributor +.L__skip_pmr_sync\@: alternative_else_nop_endif ldp x21, x22, [sp, #S_PC] // load ELR, SPSR @@ -578,76 +580,9 @@ ENDPROC(el1_error_invalid) .align 6 el1_sync: kernel_entry 1 - mrs x1, esr_el1 // read the syndrome register - lsr x24, x1, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_DABT_CUR // data abort in EL1 - b.eq el1_da - cmp x24, #ESR_ELx_EC_IABT_CUR // instruction abort in EL1 - b.eq el1_ia - cmp x24, #ESR_ELx_EC_SYS64 // configurable trap - b.eq el1_undef - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el1_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL1 - b.eq el1_undef - cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 - b.ge el1_dbg - b el1_inv - -el1_ia: - /* - * Fall through to the Data abort case - */ -el1_da: - /* - * Data abort handling - */ - mrs x3, far_el1 - inherit_daif pstate=x23, tmp=x2 - clear_address_tag x0, x3 - mov x2, sp // struct pt_regs - bl do_mem_abort - - kernel_exit 1 -el1_pc: - /* - * PC alignment exception handling. We don't handle SP alignment faults, - * since we will have hit a recursive exception when trying to push the - * initial pt_regs. - */ - mrs x0, far_el1 - inherit_daif pstate=x23, tmp=x2 - mov x2, sp - bl do_sp_pc_abort - ASM_BUG() -el1_undef: - /* - * Undefined instruction - */ - inherit_daif pstate=x23, tmp=x2 mov x0, sp - bl do_undefinstr + bl el1_sync_handler kernel_exit 1 -el1_dbg: - /* - * Debug exception handling - */ - cmp x24, #ESR_ELx_EC_BRK64 // if BRK64 - cinc x24, x24, eq // set bit '0' - tbz x24, #0, el1_inv // EL1 only - gic_prio_kentry_setup tmp=x3 - mrs x0, far_el1 - mov x2, sp // struct pt_regs - bl do_debug_exception - kernel_exit 1 -el1_inv: - // TODO: add support for undefined instructions in kernel mode - inherit_daif pstate=x23, tmp=x2 - mov x0, sp - mov x2, x1 - mov x1, #BAD_SYNC - bl bad_mode - ASM_BUG() ENDPROC(el1_sync) .align 6 @@ -680,7 +615,7 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING orr x24, x24, x0 alternative_else_nop_endif cbnz x24, 1f // preempt count != 0 || NMI return path - bl preempt_schedule_irq // irq en/disable is done inside + bl arm64_preempt_schedule_irq // irq en/disable is done inside 1: #endif @@ -714,70 +649,18 @@ ENDPROC(el1_irq) .align 6 el0_sync: kernel_entry 0 - mrs x25, esr_el1 // read the syndrome register - lsr x24, x25, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_SVC64 // SVC in 64-bit state - b.eq el0_svc - cmp x24, #ESR_ELx_EC_DABT_LOW // data abort in EL0 - b.eq el0_da - cmp x24, #ESR_ELx_EC_IABT_LOW // instruction abort in EL0 - b.eq el0_ia - cmp x24, #ESR_ELx_EC_FP_ASIMD // FP/ASIMD access - b.eq el0_fpsimd_acc - cmp x24, #ESR_ELx_EC_SVE // SVE access - b.eq el0_sve_acc - cmp x24, #ESR_ELx_EC_FP_EXC64 // FP/ASIMD exception - b.eq el0_fpsimd_exc - cmp x24, #ESR_ELx_EC_SYS64 // configurable trap - ccmp x24, #ESR_ELx_EC_WFx, #4, ne - b.eq el0_sys - cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception - b.eq el0_sp - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 - b.eq el0_undef - cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0 - b.ge el0_dbg - b el0_inv + mov x0, sp + bl el0_sync_handler + b ret_to_user #ifdef CONFIG_COMPAT .align 6 el0_sync_compat: kernel_entry 0, 32 - mrs x25, esr_el1 // read the syndrome register - lsr x24, x25, #ESR_ELx_EC_SHIFT // exception class - cmp x24, #ESR_ELx_EC_SVC32 // SVC in 32-bit state - b.eq el0_svc_compat - cmp x24, #ESR_ELx_EC_DABT_LOW // data abort in EL0 - b.eq el0_da - cmp x24, #ESR_ELx_EC_IABT_LOW // instruction abort in EL0 - b.eq el0_ia - cmp x24, #ESR_ELx_EC_FP_ASIMD // FP/ASIMD access - b.eq el0_fpsimd_acc - cmp x24, #ESR_ELx_EC_FP_EXC32 // FP/ASIMD exception - b.eq el0_fpsimd_exc - cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_pc - cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap - b.eq el0_cp15 - cmp x24, #ESR_ELx_EC_CP15_64 // CP15 MRRC/MCRR trap - b.eq el0_cp15 - cmp x24, #ESR_ELx_EC_CP14_MR // CP14 MRC/MCR trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP14_LS // CP14 LDC/STC trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_CP14_64 // CP14 MRRC/MCRR trap - b.eq el0_undef - cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0 - b.ge el0_dbg - b el0_inv -el0_svc_compat: mov x0, sp - bl el0_svc_compat_handler + bl el0_sync_compat_handler b ret_to_user +ENDPROC(el0_sync) .align 6 el0_irq_compat: @@ -787,140 +670,8 @@ el0_irq_compat: el0_error_compat: kernel_entry 0, 32 b el0_error_naked - -el0_cp15: - /* - * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_cp15instr - b ret_to_user #endif -el0_da: - /* - * Data abort handling - */ - mrs x26, far_el1 - ct_user_exit_irqoff - enable_daif - clear_address_tag x0, x26 - mov x1, x25 - mov x2, sp - bl do_mem_abort - b ret_to_user -el0_ia: - /* - * Instruction abort handling - */ - mrs x26, far_el1 - gic_prio_kentry_setup tmp=x0 - ct_user_exit_irqoff - enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - mov x0, x26 - mov x1, x25 - mov x2, sp - bl do_el0_ia_bp_hardening - b ret_to_user -el0_fpsimd_acc: - /* - * Floating Point or Advanced SIMD access - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_fpsimd_acc - b ret_to_user -el0_sve_acc: - /* - * Scalable Vector Extension access - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_sve_acc - b ret_to_user -el0_fpsimd_exc: - /* - * Floating Point, Advanced SIMD or SVE exception - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_fpsimd_exc - b ret_to_user -el0_sp: - ldr x26, [sp, #S_SP] - b el0_sp_pc -el0_pc: - mrs x26, far_el1 -el0_sp_pc: - /* - * Stack or PC alignment exception handling - */ - gic_prio_kentry_setup tmp=x0 - ct_user_exit_irqoff - enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS - bl trace_hardirqs_off -#endif - mov x0, x26 - mov x1, x25 - mov x2, sp - bl do_sp_pc_abort - b ret_to_user -el0_undef: - /* - * Undefined instruction - */ - ct_user_exit_irqoff - enable_daif - mov x0, sp - bl do_undefinstr - b ret_to_user -el0_sys: - /* - * System instructions, for trapped cache maintenance instructions - */ - ct_user_exit_irqoff - enable_daif - mov x0, x25 - mov x1, sp - bl do_sysinstr - b ret_to_user -el0_dbg: - /* - * Debug exception handling - */ - tbnz x24, #0, el0_inv // EL0 only - mrs x24, far_el1 - gic_prio_kentry_setup tmp=x3 - ct_user_exit_irqoff - mov x0, x24 - mov x1, x25 - mov x2, sp - bl do_debug_exception - enable_da_f - b ret_to_user -el0_inv: - ct_user_exit_irqoff - enable_daif - mov x0, sp - mov x1, #BAD_SYNC - mov x2, x25 - bl bad_el0_sync - b ret_to_user -ENDPROC(el0_sync) - .align 6 el0_irq: kernel_entry 0 @@ -998,17 +749,6 @@ finish_ret_to_user: kernel_exit 0 ENDPROC(ret_to_user) -/* - * SVC handler. - */ - .align 6 -el0_svc: - gic_prio_kentry_setup tmp=x1 - mov x0, sp - bl el0_svc_handler - b ret_to_user -ENDPROC(el0_svc) - .popsection // .entry.text #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 @@ -1070,7 +810,9 @@ alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003 #else ldr x30, =vectors #endif +alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM prfm plil1strm, [x30, #(1b - tramp_vectors)] +alternative_else_nop_endif msr vbar_el1, x30 add x30, x30, #(1b - tramp_vectors) isb diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 37d3912cfe06..3eb338f14386 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -920,7 +920,7 @@ void fpsimd_release_task(struct task_struct *dead_task) * would have disabled the SVE access trap for userspace during * ret_to_user, making an SVE access trap impossible in that case. */ -asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) +void do_sve_acc(unsigned int esr, struct pt_regs *regs) { /* Even if we chose not to use SVE, the hardware could still trap: */ if (unlikely(!system_supports_sve()) || WARN_ON(is_compat_task())) { @@ -947,7 +947,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) /* * Trapped FP/ASIMD access. */ -asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) +void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) { /* TODO: implement lazy context saving/restoring */ WARN_ON(1); @@ -956,7 +956,7 @@ asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs) /* * Raise a SIGFPE for the current process. */ -asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) +void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) { unsigned int si_code = FPE_FLTUNK; diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 171773257974..8618faa82e6d 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -62,6 +62,19 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ftrace_modify_code(pc, 0, new, false); } +static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) +{ +#ifdef CONFIG_ARM64_MODULE_PLTS + struct plt_entry *plt = mod->arch.ftrace_trampolines; + + if (addr == FTRACE_ADDR) + return &plt[FTRACE_PLT_IDX]; + if (addr == FTRACE_REGS_ADDR && IS_ENABLED(CONFIG_FTRACE_WITH_REGS)) + return &plt[FTRACE_REGS_PLT_IDX]; +#endif + return NULL; +} + /* * Turn on the call to ftrace_caller() in instrumented function */ @@ -72,9 +85,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) long offset = (long)pc - (long)addr; if (offset < -SZ_128M || offset >= SZ_128M) { -#ifdef CONFIG_ARM64_MODULE_PLTS - struct plt_entry trampoline, *dst; struct module *mod; + struct plt_entry *plt; + + if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + return -EINVAL; /* * On kernels that support module PLTs, the offset between the @@ -93,43 +108,13 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (WARN_ON(!mod)) return -EINVAL; - /* - * There is only one ftrace trampoline per module. For now, - * this is not a problem since on arm64, all dynamic ftrace - * invocations are routed via ftrace_caller(). This will need - * to be revisited if support for multiple ftrace entry points - * is added in the future, but for now, the pr_err() below - * deals with a theoretical issue only. - * - * Note that PLTs are place relative, and plt_entries_equal() - * checks whether they point to the same target. Here, we need - * to check if the actual opcodes are in fact identical, - * regardless of the offset in memory so use memcmp() instead. - */ - dst = mod->arch.ftrace_trampoline; - trampoline = get_plt_entry(addr, dst); - if (memcmp(dst, &trampoline, sizeof(trampoline))) { - if (plt_entry_is_initialized(dst)) { - pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); - return -EINVAL; - } - - /* point the trampoline to our ftrace entry point */ - module_disable_ro(mod); - *dst = trampoline; - module_enable_ro(mod, true); - - /* - * Ensure updated trampoline is visible to instruction - * fetch before we patch in the branch. - */ - __flush_icache_range((unsigned long)&dst[0], - (unsigned long)&dst[1]); + plt = get_ftrace_plt(mod, addr); + if (!plt) { + pr_err("ftrace: no module PLT for %ps\n", (void *)addr); + return -EINVAL; } - addr = (unsigned long)dst; -#else /* CONFIG_ARM64_MODULE_PLTS */ - return -EINVAL; -#endif /* CONFIG_ARM64_MODULE_PLTS */ + + addr = (unsigned long)plt; } old = aarch64_insn_gen_nop(); @@ -138,6 +123,55 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return ftrace_modify_code(pc, old, new, true); } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + unsigned long pc = rec->ip; + u32 old, new; + + old = aarch64_insn_gen_branch_imm(pc, old_addr, + AARCH64_INSN_BRANCH_LINK); + new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); + + return ftrace_modify_code(pc, old, new, true); +} + +/* + * The compiler has inserted two NOPs before the regular function prologue. + * All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live, + * and x9-x18 are free for our use. + * + * At runtime we want to be able to swing a single NOP <-> BL to enable or + * disable the ftrace call. The BL requires us to save the original LR value, + * so here we insert a <MOV X9, LR> over the first NOP so the instructions + * before the regular prologue are: + * + * | Compiled | Disabled | Enabled | + * +----------+------------+------------+ + * | NOP | MOV X9, LR | MOV X9, LR | + * | NOP | NOP | BL <entry> | + * + * The LR value will be recovered by ftrace_regs_entry, and restored into LR + * before returning to the regular function prologue. When a function is not + * being traced, the MOV is not harmful given x9 is not live per the AAPCS. + * + * Note: ftrace_process_locs() has pre-adjusted rec->ip to be the address of + * the BL. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + unsigned long pc = rec->ip - AARCH64_INSN_SIZE; + u32 old, new; + + old = aarch64_insn_gen_nop(); + new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9, + AARCH64_INSN_REG_LR, + AARCH64_INSN_VARIANT_64BIT); + return ftrace_modify_code(pc, old, new, true); +} +#endif + /* * Turn off the call to ftrace_caller() in instrumented function */ @@ -150,9 +184,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, long offset = (long)pc - (long)addr; if (offset < -SZ_128M || offset >= SZ_128M) { -#ifdef CONFIG_ARM64_MODULE_PLTS u32 replaced; + if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + return -EINVAL; + /* * 'mod' is only set at module load time, but if we end up * dealing with an out-of-range condition, we can assume it @@ -183,9 +219,6 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return -EINVAL; validate = false; -#else /* CONFIG_ARM64_MODULE_PLTS */ - return -EINVAL; -#endif /* CONFIG_ARM64_MODULE_PLTS */ } else { old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index e0a7fce0e01c..a96b2921d22c 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -201,6 +201,7 @@ static int create_safe_exec_page(void *src_start, size_t length, gfp_t mask) { int rc = 0; + pgd_t *trans_pgd; pgd_t *pgdp; pud_t *pudp; pmd_t *pmdp; @@ -215,7 +216,13 @@ static int create_safe_exec_page(void *src_start, size_t length, memcpy((void *)dst, src_start, length); __flush_icache_range(dst, dst + length); - pgdp = pgd_offset_raw(allocator(mask), dst_addr); + trans_pgd = allocator(mask); + if (!trans_pgd) { + rc = -ENOMEM; + goto out; + } + + pgdp = pgd_offset_raw(trans_pgd, dst_addr); if (pgd_none(READ_ONCE(*pgdp))) { pudp = allocator(mask); if (!pudp) { diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index d801a7094076..513b29c3e735 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -1268,6 +1268,19 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift); } +/* + * MOV (register) is architecturally an alias of ORR (shifted register) where + * MOV <*d>, <*m> is equivalent to ORR <*d>, <*ZR>, <*m> + */ +u32 aarch64_insn_gen_move_reg(enum aarch64_insn_register dst, + enum aarch64_insn_register src, + enum aarch64_insn_variant variant) +{ + return aarch64_insn_gen_logical_shifted_reg(dst, AARCH64_INSN_REG_ZR, + src, 0, variant, + AARCH64_INSN_LOGIC_ORR); +} + u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr, enum aarch64_insn_register reg, enum aarch64_insn_adr_type type) diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 416f537bf614..2a11a962e571 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -19,6 +19,14 @@ #include <asm/pgtable.h> #include <asm/sections.h> +enum kaslr_status { + KASLR_ENABLED, + KASLR_DISABLED_CMDLINE, + KASLR_DISABLED_NO_SEED, + KASLR_DISABLED_FDT_REMAP, +}; + +static enum kaslr_status __initdata kaslr_status; u64 __ro_after_init module_alloc_base; u16 __initdata memstart_offset_seed; @@ -91,15 +99,15 @@ u64 __init kaslr_early_init(u64 dt_phys) */ early_fixmap_init(); fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); - if (!fdt) + if (!fdt) { + kaslr_status = KASLR_DISABLED_FDT_REMAP; return 0; + } /* * Retrieve (and wipe) the seed from the FDT */ seed = get_kaslr_seed(fdt); - if (!seed) - return 0; /* * Check if 'nokaslr' appears on the command line, and @@ -107,8 +115,15 @@ u64 __init kaslr_early_init(u64 dt_phys) */ cmdline = kaslr_get_cmdline(fdt); str = strstr(cmdline, "nokaslr"); - if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) + if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) { + kaslr_status = KASLR_DISABLED_CMDLINE; + return 0; + } + + if (!seed) { + kaslr_status = KASLR_DISABLED_NO_SEED; return 0; + } /* * OK, so we are proceeding with KASLR enabled. Calculate a suitable @@ -170,3 +185,24 @@ u64 __init kaslr_early_init(u64 dt_phys) return offset; } + +static int __init kaslr_init(void) +{ + switch (kaslr_status) { + case KASLR_ENABLED: + pr_info("KASLR enabled\n"); + break; + case KASLR_DISABLED_CMDLINE: + pr_info("KASLR disabled on command line\n"); + break; + case KASLR_DISABLED_NO_SEED: + pr_warn("KASLR disabled due to lack of seed\n"); + break; + case KASLR_DISABLED_FDT_REMAP: + pr_warn("KASLR disabled due to FDT remapping failure\n"); + break; + } + + return 0; +} +core_initcall(kaslr_init) diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index b182442b87a3..65b08a74aec6 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -4,6 +4,7 @@ */ #include <linux/elf.h> +#include <linux/ftrace.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/sort.h> @@ -330,7 +331,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, tramp->sh_type = SHT_NOBITS; tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC; tramp->sh_addralign = __alignof__(struct plt_entry); - tramp->sh_size = sizeof(struct plt_entry); + tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry); } return 0; diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 03ff15bffbb6..1cd1a4d0ed30 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -9,6 +9,7 @@ #include <linux/bitops.h> #include <linux/elf.h> +#include <linux/ftrace.h> #include <linux/gfp.h> #include <linux/kasan.h> #include <linux/kernel.h> @@ -470,22 +471,58 @@ overflow: return -ENOEXEC; } -int module_finalize(const Elf_Ehdr *hdr, - const Elf_Shdr *sechdrs, - struct module *me) +static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + const char *name) { const Elf_Shdr *s, *se; const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) { - if (strcmp(".altinstructions", secstrs + s->sh_name) == 0) - apply_alternatives_module((void *)s->sh_addr, s->sh_size); -#ifdef CONFIG_ARM64_MODULE_PLTS - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) && - !strcmp(".text.ftrace_trampoline", secstrs + s->sh_name)) - me->arch.ftrace_trampoline = (void *)s->sh_addr; -#endif + if (strcmp(name, secstrs + s->sh_name) == 0) + return s; } + return NULL; +} + +static inline void __init_plt(struct plt_entry *plt, unsigned long addr) +{ + *plt = get_plt_entry(addr, plt); +} + +static int module_init_ftrace_plt(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *mod) +{ +#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE) + const Elf_Shdr *s; + struct plt_entry *plts; + + s = find_section(hdr, sechdrs, ".text.ftrace_trampoline"); + if (!s) + return -ENOEXEC; + + plts = (void *)s->sh_addr; + + __init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR); + + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + __init_plt(&plts[FTRACE_REGS_PLT_IDX], FTRACE_REGS_ADDR); + + mod->arch.ftrace_trampolines = plts; +#endif return 0; } + +int module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + const Elf_Shdr *s; + s = find_section(hdr, sechdrs, ".altinstructions"); + if (s) + apply_alternatives_module((void *)s->sh_addr, s->sh_size); + + return module_init_ftrace_plt(hdr, sechdrs, me); +} diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index a0b4f1bca491..e40b65645c86 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -158,133 +158,74 @@ armv8pmu_events_sysfs_show(struct device *dev, return sprintf(page, "event=0x%03llx\n", pmu_attr->id); } -#define ARMV8_EVENT_ATTR(name, config) \ - PMU_EVENT_ATTR(name, armv8_event_attr_##name, \ - config, armv8pmu_events_sysfs_show) - -ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR); -ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL); -ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL); -ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE); -ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL); -ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED); -ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED); -ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED); -ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN); -ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN); -ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED); -ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED); -ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED); -ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED); -ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED); -ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED); -ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES); -ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED); -ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS); -ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE); -ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB); -ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE); -ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB); -ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS); -ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR); -ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC); -ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED); -ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES); -/* Don't expose the chain event in /sys, since it's useless in isolation */ -ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED); -ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED); -ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND); -ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND); -ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB); -ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB); -ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE); -ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL); -ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE); -ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL); -ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE); -ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB); -ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL); -ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL); -ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB); -ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB); -ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS); -ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE); -ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS); -ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK); -ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK); -ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD); -ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD); -ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD); -ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP); -ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED); -ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE); -ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION); +#define ARMV8_EVENT_ATTR(name, config) \ + (&((struct perf_pmu_events_attr) { \ + .attr = __ATTR(name, 0444, armv8pmu_events_sysfs_show, NULL), \ + .id = config, \ + }).attr.attr) static struct attribute *armv8_pmuv3_event_attrs[] = { - &armv8_event_attr_sw_incr.attr.attr, - &armv8_event_attr_l1i_cache_refill.attr.attr, - &armv8_event_attr_l1i_tlb_refill.attr.attr, - &armv8_event_attr_l1d_cache_refill.attr.attr, - &armv8_event_attr_l1d_cache.attr.attr, - &armv8_event_attr_l1d_tlb_refill.attr.attr, - &armv8_event_attr_ld_retired.attr.attr, - &armv8_event_attr_st_retired.attr.attr, - &armv8_event_attr_inst_retired.attr.attr, - &armv8_event_attr_exc_taken.attr.attr, - &armv8_event_attr_exc_return.attr.attr, - &armv8_event_attr_cid_write_retired.attr.attr, - &armv8_event_attr_pc_write_retired.attr.attr, - &armv8_event_attr_br_immed_retired.attr.attr, - &armv8_event_attr_br_return_retired.attr.attr, - &armv8_event_attr_unaligned_ldst_retired.attr.attr, - &armv8_event_attr_br_mis_pred.attr.attr, - &armv8_event_attr_cpu_cycles.attr.attr, - &armv8_event_attr_br_pred.attr.attr, - &armv8_event_attr_mem_access.attr.attr, - &armv8_event_attr_l1i_cache.attr.attr, - &armv8_event_attr_l1d_cache_wb.attr.attr, - &armv8_event_attr_l2d_cache.attr.attr, - &armv8_event_attr_l2d_cache_refill.attr.attr, - &armv8_event_attr_l2d_cache_wb.attr.attr, - &armv8_event_attr_bus_access.attr.attr, - &armv8_event_attr_memory_error.attr.attr, - &armv8_event_attr_inst_spec.attr.attr, - &armv8_event_attr_ttbr_write_retired.attr.attr, - &armv8_event_attr_bus_cycles.attr.attr, - &armv8_event_attr_l1d_cache_allocate.attr.attr, - &armv8_event_attr_l2d_cache_allocate.attr.attr, - &armv8_event_attr_br_retired.attr.attr, - &armv8_event_attr_br_mis_pred_retired.attr.attr, - &armv8_event_attr_stall_frontend.attr.attr, - &armv8_event_attr_stall_backend.attr.attr, - &armv8_event_attr_l1d_tlb.attr.attr, - &armv8_event_attr_l1i_tlb.attr.attr, - &armv8_event_attr_l2i_cache.attr.attr, - &armv8_event_attr_l2i_cache_refill.attr.attr, - &armv8_event_attr_l3d_cache_allocate.attr.attr, - &armv8_event_attr_l3d_cache_refill.attr.attr, - &armv8_event_attr_l3d_cache.attr.attr, - &armv8_event_attr_l3d_cache_wb.attr.attr, - &armv8_event_attr_l2d_tlb_refill.attr.attr, - &armv8_event_attr_l2i_tlb_refill.attr.attr, - &armv8_event_attr_l2d_tlb.attr.attr, - &armv8_event_attr_l2i_tlb.attr.attr, - &armv8_event_attr_remote_access.attr.attr, - &armv8_event_attr_ll_cache.attr.attr, - &armv8_event_attr_ll_cache_miss.attr.attr, - &armv8_event_attr_dtlb_walk.attr.attr, - &armv8_event_attr_itlb_walk.attr.attr, - &armv8_event_attr_ll_cache_rd.attr.attr, - &armv8_event_attr_ll_cache_miss_rd.attr.attr, - &armv8_event_attr_remote_access_rd.attr.attr, - &armv8_event_attr_sample_pop.attr.attr, - &armv8_event_attr_sample_feed.attr.attr, - &armv8_event_attr_sample_filtrate.attr.attr, - &armv8_event_attr_sample_collision.attr.attr, + ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR), + ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL), + ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL), + ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE), + ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL), + ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED), + ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED), + ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED), + ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN), + ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN), + ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED), + ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED), + ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED), + ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED), + ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED), + ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED), + ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES), + ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED), + ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS), + ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE), + ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB), + ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE), + ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB), + ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS), + ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR), + ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC), + ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED), + ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES), + /* Don't expose the chain event in /sys, since it's useless in isolation */ + ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED), + ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED), + ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND), + ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND), + ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB), + ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB), + ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE), + ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL), + ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE), + ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL), + ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE), + ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB), + ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL), + ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL), + ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB), + ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB), + ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS), + ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE), + ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS), + ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK), + ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK), + ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD), + ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD), + ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD), + ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP), + ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED), + ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE), + ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION), NULL, }; diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index c4452827419b..d1c95dcf1d78 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -455,10 +455,6 @@ int __init arch_populate_kprobe_blacklist(void) (unsigned long)__irqentry_text_end); if (ret) return ret; - ret = kprobe_add_area_blacklist((unsigned long)__exception_text_start, - (unsigned long)__exception_text_end); - if (ret) - return ret; ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start, (unsigned long)__idmap_text_end); if (ret) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index a47462def04b..71f788cd2b18 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -17,6 +17,7 @@ #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/kernel.h> +#include <linux/lockdep.h> #include <linux/mm.h> #include <linux/stddef.h> #include <linux/sysctl.h> @@ -44,6 +45,7 @@ #include <asm/alternative.h> #include <asm/arch_gicv3.h> #include <asm/compat.h> +#include <asm/cpufeature.h> #include <asm/cacheflush.h> #include <asm/exec.h> #include <asm/fpsimd.h> @@ -332,22 +334,27 @@ void arch_release_task_struct(struct task_struct *tsk) fpsimd_release_task(tsk); } -/* - * src and dst may temporarily have aliased sve_state after task_struct - * is copied. We cannot fix this properly here, because src may have - * live SVE state and dst's thread_info may not exist yet, so tweaking - * either src's or dst's TIF_SVE is not safe. - * - * The unaliasing is done in copy_thread() instead. This works because - * dst is not schedulable or traceable until both of these functions - * have been called. - */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { if (current->mm) fpsimd_preserve_current_state(); *dst = *src; + /* We rely on the above assignment to initialize dst's thread_flags: */ + BUILD_BUG_ON(!IS_ENABLED(CONFIG_THREAD_INFO_IN_TASK)); + + /* + * Detach src's sve_state (if any) from dst so that it does not + * get erroneously used or freed prematurely. dst's sve_state + * will be allocated on demand later on if dst uses SVE. + * For consistency, also clear TIF_SVE here: this could be done + * later in copy_process(), but to avoid tripping up future + * maintainers it is best not to leave TIF_SVE and sve_state in + * an inconsistent state, even temporarily. + */ + dst->thread.sve_state = NULL; + clear_tsk_thread_flag(dst, TIF_SVE); + return 0; } @@ -361,13 +368,6 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context)); /* - * Unalias p->thread.sve_state (if any) from the parent task - * and disable discard SVE state for p: - */ - clear_tsk_thread_flag(p, TIF_SVE); - p->thread.sve_state = NULL; - - /* * In case p was allocated the same task_struct pointer as some * other recently-exited task, make sure p is disassociated from * any cpu that may have run that now-exited task recently. @@ -633,3 +633,19 @@ static int __init tagged_addr_init(void) core_initcall(tagged_addr_init); #endif /* CONFIG_ARM64_TAGGED_ADDR_ABI */ + +asmlinkage void __sched arm64_preempt_schedule_irq(void) +{ + lockdep_assert_irqs_disabled(); + + /* + * Preempting a task from an IRQ means we leave copies of PSTATE + * on the stack. cpufeature's enable calls may modify PSTATE, but + * resuming one of these preempted tasks would undo those changes. + * + * Only allow a task to be preempted once cpufeatures have been + * enabled. + */ + if (static_branch_likely(&arm64_const_caps_ready)) + preempt_schedule_irq(); +} diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index c9f72b2665f1..43ae4e0c968f 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -81,7 +81,8 @@ static void cpu_psci_cpu_die(unsigned int cpu) static int cpu_psci_cpu_kill(unsigned int cpu) { - int err, i; + int err; + unsigned long start, end; if (!psci_ops.affinity_info) return 0; @@ -91,16 +92,18 @@ static int cpu_psci_cpu_kill(unsigned int cpu) * while it is dying. So, try again a few times. */ - for (i = 0; i < 10; i++) { + start = jiffies; + end = start + msecs_to_jiffies(100); + do { err = psci_ops.affinity_info(cpu_logical_map(cpu), 0); if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) { - pr_info("CPU%d killed.\n", cpu); + pr_info("CPU%d killed (polled %d ms)\n", cpu, + jiffies_to_msecs(jiffies - start)); return 0; } - msleep(10); - pr_info("Retrying again to check for CPU kill\n"); - } + usleep_range(100, 1000); + } while (time_before(jiffies, end)); pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n", cpu, err); diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index ea94cf8f9dc6..d6259dac62b6 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -2,6 +2,7 @@ // Copyright (C) 2017 Arm Ltd. #define pr_fmt(fmt) "sdei: " fmt +#include <linux/arm-smccc.h> #include <linux/arm_sdei.h> #include <linux/hardirq.h> #include <linux/irqflags.h> @@ -161,7 +162,7 @@ unsigned long sdei_arch_get_entry_point(int conduit) return 0; } - sdei_exit_mode = (conduit == CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; + sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 if (arm64_kernel_unmapped_at_el0()) { diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index f1cb64959427..3c18c2454089 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -8,6 +8,7 @@ */ #include <linux/compat.h> +#include <linux/cpufeature.h> #include <linux/personality.h> #include <linux/sched.h> #include <linux/sched/signal.h> @@ -17,6 +18,7 @@ #include <asm/cacheflush.h> #include <asm/system_misc.h> +#include <asm/tlbflush.h> #include <asm/unistd.h> static long @@ -30,6 +32,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end) if (fatal_signal_pending(current)) return 0; + if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) { + /* + * The workaround requires an inner-shareable tlbi. + * We pick the reserved-ASID to minimise the impact. + */ + __tlbi(aside1is, __TLBI_VADDR(0, 0)); + dsb(ish); + } + ret = __flush_cache_user_range(start, start + chunk); if (ret) return ret; diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 871c739f060a..9a9d98a443fc 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -154,14 +154,14 @@ static inline void sve_user_discard(void) sve_user_disable(); } -asmlinkage void el0_svc_handler(struct pt_regs *regs) +void el0_svc_handler(struct pt_regs *regs) { sve_user_discard(); el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } #ifdef CONFIG_COMPAT -asmlinkage void el0_svc_compat_handler(struct pt_regs *regs) +void el0_svc_compat_handler(struct pt_regs *regs) { el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls, compat_sys_call_table); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 34739e80211b..73caf35c2262 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -35,6 +35,7 @@ #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/insn.h> +#include <asm/kprobes.h> #include <asm/traps.h> #include <asm/smp.h> #include <asm/stack_pointer.h> @@ -393,7 +394,7 @@ void arm64_notify_segfault(unsigned long addr) force_signal_inject(SIGSEGV, code, addr); } -asmlinkage void __exception do_undefinstr(struct pt_regs *regs) +void do_undefinstr(struct pt_regs *regs) { /* check for AArch32 breakpoint instructions */ if (!aarch32_break_handler(regs)) @@ -405,6 +406,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) BUG_ON(!user_mode(regs)); force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc); } +NOKPROBE_SYMBOL(do_undefinstr); #define __user_cache_maint(insn, address, res) \ if (address >= user_addr_max()) { \ @@ -470,6 +472,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs) int rt = ESR_ELx_SYS64_ISS_RT(esr); unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0); + if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) { + /* Hide DIC so that we can trap the unnecessary maintenance...*/ + val &= ~BIT(CTR_DIC_SHIFT); + + /* ... and fake IminLine to reduce the number of traps. */ + val &= ~CTR_IMINLINE_MASK; + val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK; + } + pt_regs_write_reg(regs, rt, val); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); @@ -667,7 +678,7 @@ static const struct sys64_hook cp15_64_hooks[] = { {}, }; -asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs) +void do_cp15instr(unsigned int esr, struct pt_regs *regs) { const struct sys64_hook *hook, *hook_base; @@ -705,9 +716,10 @@ asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs) */ do_undefinstr(regs); } +NOKPROBE_SYMBOL(do_cp15instr); #endif -asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) +void do_sysinstr(unsigned int esr, struct pt_regs *regs) { const struct sys64_hook *hook; @@ -724,6 +736,7 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) */ do_undefinstr(regs); } +NOKPROBE_SYMBOL(do_sysinstr); static const char *esr_class_str[] = { [0 ... ESR_ELx_EC_MAX] = "UNRECOGNIZED EC", @@ -793,7 +806,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) * bad_el0_sync handles unexpected, but potentially recoverable synchronous * exceptions taken from EL0. Unlike bad_mode, this returns. */ -asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) +void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) { void __user *pc = (void __user *)instruction_pointer(regs); diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ /dev/null diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 1fba0776ed40..76b327f88fbb 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -8,15 +8,21 @@ ARCH_REL_TYPE_ABS := R_ARM_JUMP_SLOT|R_ARM_GLOB_DAT|R_ARM_ABS32 include $(srctree)/lib/vdso/Makefile -COMPATCC := $(CROSS_COMPILE_COMPAT)gcc +# Same as cc-*option, but using CC_COMPAT instead of CC +ifeq ($(CONFIG_CC_IS_CLANG), y) +CC_COMPAT ?= $(CC) +else +CC_COMPAT ?= $(CROSS_COMPILE_COMPAT)gcc +endif -# Same as cc-*option, but using COMPATCC instead of CC cc32-option = $(call try-run,\ - $(COMPATCC) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2)) + $(CC_COMPAT) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2)) cc32-disable-warning = $(call try-run,\ - $(COMPATCC) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1))) + $(CC_COMPAT) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1))) cc32-ldoption = $(call try-run,\ - $(COMPATCC) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2)) + $(CC_COMPAT) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2)) +cc32-as-instr = $(call try-run,\ + printf "%b\n" "$(1)" | $(CC_COMPAT) $(VDSO_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3)) # We cannot use the global flags to compile the vDSO files, the main reason # being that the 32-bit compiler may be older than the main (64-bit) compiler @@ -25,22 +31,21 @@ cc32-ldoption = $(call try-run,\ # arm64 one. # As a result we set our own flags here. -# From top-level Makefile -# NOSTDINC_FLAGS -VDSO_CPPFLAGS := -nostdinc -isystem $(shell $(COMPATCC) -print-file-name=include) +# KBUILD_CPPFLAGS and NOSTDINC_FLAGS from top-level Makefile +VDSO_CPPFLAGS := -D__KERNEL__ -nostdinc -isystem $(shell $(CC_COMPAT) -print-file-name=include) VDSO_CPPFLAGS += $(LINUXINCLUDE) -VDSO_CPPFLAGS += $(KBUILD_CPPFLAGS) # Common C and assembly flags # From top-level Makefile VDSO_CAFLAGS := $(VDSO_CPPFLAGS) +ifneq ($(shell $(CC_COMPAT) --version 2>&1 | head -n 1 | grep clang),) +VDSO_CAFLAGS += --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%)) +endif + VDSO_CAFLAGS += $(call cc32-option,-fno-PIE) ifdef CONFIG_DEBUG_INFO VDSO_CAFLAGS += -g endif -ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(COMPATCC)), y) -VDSO_CAFLAGS += -DCC_HAVE_ASM_GOTO -endif # From arm Makefile VDSO_CAFLAGS += $(call cc32-option,-fno-dwarf2-cfi-asm) @@ -55,6 +60,7 @@ endif VDSO_CAFLAGS += -fPIC -fno-builtin -fno-stack-protector VDSO_CAFLAGS += -DDISABLE_BRANCH_PROFILING + # Try to compile for ARMv8. If the compiler is too old and doesn't support it, # fall back to v7. There is no easy way to check for what architecture the code # is being compiled, so define a macro specifying that (see arch/arm/Makefile). @@ -91,6 +97,12 @@ VDSO_CFLAGS += -Wno-int-to-pointer-cast VDSO_AFLAGS := $(VDSO_CAFLAGS) VDSO_AFLAGS += -D__ASSEMBLY__ +# Check for binutils support for dmb ishld +dmbinstr := $(call cc32-as-instr,dmb ishld,-DCONFIG_AS_DMB_ISHLD=1) + +VDSO_CFLAGS += $(dmbinstr) +VDSO_AFLAGS += $(dmbinstr) + VDSO_LDFLAGS := $(VDSO_CPPFLAGS) # From arm vDSO Makefile VDSO_LDFLAGS += -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 @@ -159,14 +171,14 @@ quiet_cmd_vdsold_and_vdso_check = LD32 $@ cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check) quiet_cmd_vdsold = LD32 $@ - cmd_vdsold = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \ + cmd_vdsold = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \ -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@ quiet_cmd_vdsocc = CC32 $@ - cmd_vdsocc = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $< + cmd_vdsocc = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $< quiet_cmd_vdsocc_gettimeofday = CC32 $@ - cmd_vdsocc_gettimeofday = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $< + cmd_vdsocc_gettimeofday = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $< quiet_cmd_vdsoas = AS32 $@ - cmd_vdsoas = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $< + cmd_vdsoas = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $< quiet_cmd_vdsomunge = MUNGE $@ cmd_vdsomunge = $(obj)/$(munge) $< $@ diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index aa76f7259668..009057517bdd 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -111,9 +111,6 @@ SECTIONS } .text : { /* Real text segment */ _stext = .; /* Text and read-only data */ - __exception_text_start = .; - *(.exception.text) - __exception_text_end = .; IRQENTRY_TEXT SOFTIRQENTRY_TEXT ENTRY_TEXT diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index bd978ad71936..72fbbd86eb5e 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -12,7 +12,7 @@ #include <kvm/arm_psci.h> -#include <asm/arch_gicv3.h> +#include <asm/barrier.h> #include <asm/cpufeature.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> @@ -118,12 +118,29 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) } write_sysreg(val, cptr_el2); + + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; + + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * configured and enabled. We can now restore the guest's S1 + * configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + } } static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) { u64 hcr = vcpu->arch.hcr_el2; + if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM)) + hcr |= HCR_TVM; + write_sysreg(hcr, hcr_el2); if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) @@ -156,6 +173,23 @@ static void __hyp_text __deactivate_traps_nvhe(void) { u64 mdcr_el2 = read_sysreg(mdcr_el2); + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + u64 val; + + /* + * Set the TCR and SCTLR registers in the exact opposite + * sequence as __activate_traps_nvhe (first prevent walks, + * then force the MMU on). A generous sprinkling of isb() + * ensure that things happen in this exact order. + */ + val = read_sysreg_el1(SYS_TCR); + write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR); + isb(); + val = read_sysreg_el1(SYS_SCTLR); + write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR); + isb(); + } + __deactivate_traps_common(); mdcr_el2 &= MDCR_EL2_HPMN_MASK; @@ -174,8 +208,10 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu) * the crucial bit is "On taking a vSError interrupt, * HCR_EL2.VSE is cleared to 0." */ - if (vcpu->arch.hcr_el2 & HCR_VSE) - vcpu->arch.hcr_el2 = read_sysreg(hcr_el2); + if (vcpu->arch.hcr_el2 & HCR_VSE) { + vcpu->arch.hcr_el2 &= ~HCR_VSE; + vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE; + } if (has_vhe()) deactivate_traps_vhe(); @@ -229,20 +265,6 @@ static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu) } } -static bool __hyp_text __true_value(void) -{ - return true; -} - -static bool __hyp_text __false_value(void) -{ - return false; -} - -static hyp_alternate_select(__check_arm_834220, - __false_value, __true_value, - ARM64_WORKAROUND_834220); - static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar) { u64 par, tmp; @@ -298,7 +320,8 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) * resolve the IPA using the AT instruction. */ if (!(esr & ESR_ELx_S1PTW) && - (__check_arm_834220()() || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { + (cpus_have_const_cap(ARM64_WORKAROUND_834220) || + (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { if (!__translate_far_to_hpfar(far, &hpfar)) return false; } else { @@ -393,6 +416,61 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu) return true; } +static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu) +{ + u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu)); + int rt = kvm_vcpu_sys_get_rt(vcpu); + u64 val = vcpu_get_reg(vcpu, rt); + + /* + * The normal sysreg handling code expects to see the traps, + * let's not do anything here. + */ + if (vcpu->arch.hcr_el2 & HCR_TVM) + return false; + + switch (sysreg) { + case SYS_SCTLR_EL1: + write_sysreg_el1(val, SYS_SCTLR); + break; + case SYS_TTBR0_EL1: + write_sysreg_el1(val, SYS_TTBR0); + break; + case SYS_TTBR1_EL1: + write_sysreg_el1(val, SYS_TTBR1); + break; + case SYS_TCR_EL1: + write_sysreg_el1(val, SYS_TCR); + break; + case SYS_ESR_EL1: + write_sysreg_el1(val, SYS_ESR); + break; + case SYS_FAR_EL1: + write_sysreg_el1(val, SYS_FAR); + break; + case SYS_AFSR0_EL1: + write_sysreg_el1(val, SYS_AFSR0); + break; + case SYS_AFSR1_EL1: + write_sysreg_el1(val, SYS_AFSR1); + break; + case SYS_MAIR_EL1: + write_sysreg_el1(val, SYS_MAIR); + break; + case SYS_AMAIR_EL1: + write_sysreg_el1(val, SYS_AMAIR); + break; + case SYS_CONTEXTIDR_EL1: + write_sysreg_el1(val, SYS_CONTEXTIDR); + break; + default: + return false; + } + + __kvm_skip_instr(vcpu); + return true; +} + /* * Return true when we were able to fixup the guest exit and should return to * the guest, false when we should restore the host state and return to the @@ -412,6 +490,11 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) if (*exit_code != ARM_EXCEPTION_TRAP) goto exit; + if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && + kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 && + handle_tx2_tvm(vcpu)) + return true; + /* * We trap the first access to the FP/SIMD to save the host context * and restore the guest context lazily. @@ -605,7 +688,7 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) */ if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - dsb(sy); + pmr_sync(); } vcpu = kern_hyp_va(vcpu); @@ -618,18 +701,23 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) __sysreg_save_state_nvhe(host_ctxt); - __activate_vm(kern_hyp_va(vcpu->kvm)); - __activate_traps(vcpu); - - __hyp_vgic_restore_state(vcpu); - __timer_enable_traps(vcpu); - /* * We must restore the 32-bit state before the sysregs, thanks * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). + * + * Also, and in order to be able to deal with erratum #1319537 (A57) + * and #1319367 (A72), we must ensure that all VM-related sysreg are + * restored before we enable S2 translation. */ __sysreg32_restore_state(vcpu); __sysreg_restore_state_nvhe(guest_ctxt); + + __activate_vm(kern_hyp_va(vcpu->kvm)); + __activate_traps(vcpu); + + __hyp_vgic_restore_state(vcpu); + __timer_enable_traps(vcpu); + __debug_switch_to_guest(vcpu); __set_guest_arch_workaround_state(vcpu); diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 7ddbc849b580..22b8128d19f6 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -117,12 +117,26 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2); write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1); - write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + + if (!cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + } else if (!ctxt->__hyp_running_vcpu) { + /* + * Must only be done for guest registers, hence the context + * test. We're coming from the host, so SCTLR.M is already + * set. Pairs with __activate_traps_nvhe(). + */ + write_sysreg_el1((ctxt->sys_regs[TCR_EL1] | + TCR_EPD1_MASK | TCR_EPD0_MASK), + SYS_TCR); + isb(); + } + write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1); write_sysreg_el1(ctxt->sys_regs[CPACR_EL1], SYS_CPACR); write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1], SYS_TTBR0); write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1], SYS_TTBR1); - write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); write_sysreg_el1(ctxt->sys_regs[ESR_EL1], SYS_ESR); write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1], SYS_AFSR0); write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1], SYS_AFSR1); @@ -135,6 +149,23 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1); write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1); + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367) && + ctxt->__hyp_running_vcpu) { + /* + * Must only be done for host registers, hence the context + * test. Pairs with __deactivate_traps_nvhe(). + */ + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * deconfigured and disabled. We can now restore the host's + * S1 configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); + } + write_sysreg(ctxt->gp_regs.sp_el1, sp_el1); write_sysreg_el1(ctxt->gp_regs.elr_el1, SYS_ELR); write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR); diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index c466060b76d6..c2bc17ca6430 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -63,14 +63,34 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm, static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm, struct tlb_inv_context *cxt) { + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + u64 val; + + /* + * For CPUs that are affected by ARM 1319367, we need to + * avoid a host Stage-1 walk while we have the guest's + * VMID set in the VTTBR in order to invalidate TLBs. + * We're guaranteed that the S1 MMU is enabled, so we can + * simply set the EPD bits to avoid any further TLB fill. + */ + val = cxt->tcr = read_sysreg_el1(SYS_TCR); + val |= TCR_EPD1_MASK | TCR_EPD0_MASK; + write_sysreg_el1(val, SYS_TCR); + isb(); + } + __load_guest_stage2(kvm); isb(); } -static hyp_alternate_select(__tlb_switch_to_guest, - __tlb_switch_to_guest_nvhe, - __tlb_switch_to_guest_vhe, - ARM64_HAS_VIRT_HOST_EXTN); +static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm, + struct tlb_inv_context *cxt) +{ + if (has_vhe()) + __tlb_switch_to_guest_vhe(kvm, cxt); + else + __tlb_switch_to_guest_nvhe(kvm, cxt); +} static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm, struct tlb_inv_context *cxt) @@ -96,12 +116,23 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm, struct tlb_inv_context *cxt) { write_sysreg(0, vttbr_el2); + + if (cpus_have_const_cap(ARM64_WORKAROUND_1319367)) { + /* Ensure write of the host VMID */ + isb(); + /* Restore the host's TCR_EL1 */ + write_sysreg_el1(cxt->tcr, SYS_TCR); + } } -static hyp_alternate_select(__tlb_switch_to_host, - __tlb_switch_to_host_nvhe, - __tlb_switch_to_host_vhe, - ARM64_HAS_VIRT_HOST_EXTN); +static void __hyp_text __tlb_switch_to_host(struct kvm *kvm, + struct tlb_inv_context *cxt) +{ + if (has_vhe()) + __tlb_switch_to_host_vhe(kvm, cxt); + else + __tlb_switch_to_host_nvhe(kvm, cxt); +} void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { @@ -111,7 +142,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - __tlb_switch_to_guest()(kvm, &cxt); + __tlb_switch_to_guest(kvm, &cxt); /* * We could do so much better if we had the VA as well. @@ -154,7 +185,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) if (!has_vhe() && icache_is_vpipt()) __flush_icache_all(); - __tlb_switch_to_host()(kvm, &cxt); + __tlb_switch_to_host(kvm, &cxt); } void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) @@ -165,13 +196,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - __tlb_switch_to_guest()(kvm, &cxt); + __tlb_switch_to_guest(kvm, &cxt); __tlbi(vmalls12e1is); dsb(ish); isb(); - __tlb_switch_to_host()(kvm, &cxt); + __tlb_switch_to_host(kvm, &cxt); } void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) @@ -180,13 +211,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) struct tlb_inv_context cxt; /* Switch to requested VMID */ - __tlb_switch_to_guest()(kvm, &cxt); + __tlb_switch_to_guest(kvm, &cxt); __tlbi(vmalle1); dsb(nsh); isb(); - __tlb_switch_to_host()(kvm, &cxt); + __tlb_switch_to_host(kvm, &cxt); } void __hyp_text __kvm_flush_vm_context(void) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 2071260a275b..46822afc57e0 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -632,6 +632,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) */ val = ((pmcr & ~ARMV8_PMU_PMCR_MASK) | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E); + if (!system_supports_32bit_el0()) + val |= ARMV8_PMU_PMCR_LC; __vcpu_sys_reg(vcpu, r->reg) = val; } @@ -682,6 +684,8 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, val = __vcpu_sys_reg(vcpu, PMCR_EL0); val &= ~ARMV8_PMU_PMCR_MASK; val |= p->regval & ARMV8_PMU_PMCR_MASK; + if (!system_supports_32bit_el0()) + val |= ARMV8_PMU_PMCR_LC; __vcpu_sys_reg(vcpu, PMCR_EL0) = val; kvm_pmu_handle_pmcr(vcpu, val); kvm_vcpu_pmu_restore_guest(vcpu); diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 10415572e82f..aeafc03e961a 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -20,7 +20,6 @@ * Alignment fixed up by hardware. */ ENTRY(__arch_clear_user) - uaccess_enable_not_uao x2, x3, x4 mov x2, x1 // save the size for fixup return subs x1, x1, #8 b.mi 2f @@ -40,7 +39,6 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2 b.mi 5f uao_user_alternative 9f, strb, sttrb, wzr, x0, 0 5: mov x0, #0 - uaccess_disable_not_uao x2, x3 ret ENDPROC(__arch_clear_user) EXPORT_SYMBOL(__arch_clear_user) diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 680e74409ff9..ebb3c06cbb5d 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -54,10 +54,8 @@ end .req x5 ENTRY(__arch_copy_from_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 // Nothing to copy ret ENDPROC(__arch_copy_from_user) diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 0bedae3f3792..3d8153a1ebce 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -56,10 +56,8 @@ end .req x5 ENTRY(__arch_copy_in_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 ret ENDPROC(__arch_copy_in_user) diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index 2d88c736e8f2..357eae2c18eb 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -53,10 +53,8 @@ end .req x5 ENTRY(__arch_copy_to_user) - uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" - uaccess_disable_not_uao x3, x4 mov x0, #0 ret ENDPROC(__arch_copy_to_user) diff --git a/arch/arm64/lib/uaccess_flushcache.c b/arch/arm64/lib/uaccess_flushcache.c index cbfcbe6470a5..bfa30b75b2b8 100644 --- a/arch/arm64/lib/uaccess_flushcache.c +++ b/arch/arm64/lib/uaccess_flushcache.c @@ -28,7 +28,11 @@ void memcpy_page_flushcache(char *to, struct page *page, size_t offset, unsigned long __copy_user_flushcache(void *to, const void __user *from, unsigned long n) { - unsigned long rc = __arch_copy_from_user(to, from, n); + unsigned long rc; + + uaccess_enable_not_uao(); + rc = __arch_copy_from_user(to, from, n); + uaccess_disable_not_uao(); /* See above */ __clean_dcache_area_pop(to, n - rc); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 115d7a0e4b08..077b02a2d4d3 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -32,7 +32,8 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> -#include <asm/kasan.h> +#include <asm/kprobes.h> +#include <asm/processor.h> #include <asm/sysreg.h> #include <asm/system_misc.h> #include <asm/pgtable.h> @@ -101,16 +102,13 @@ static void mem_abort_decode(unsigned int esr) data_abort_decode(esr); } -static inline bool is_ttbr0_addr(unsigned long addr) +static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm) { - /* entry assembly clears tags for TTBR0 addrs */ - return addr < TASK_SIZE; -} + /* Either init_pg_dir or swapper_pg_dir */ + if (mm == &init_mm) + return __pa_symbol(mm->pgd); -static inline bool is_ttbr1_addr(unsigned long addr) -{ - /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ - return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; + return (unsigned long)virt_to_phys(mm->pgd); } /* @@ -141,7 +139,7 @@ static void show_pte(unsigned long addr) pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, - vabits_actual, (unsigned long)virt_to_phys(mm->pgd)); + vabits_actual, mm_to_pgd_phys(mm)); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); @@ -259,14 +257,18 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, par = read_sysreg(par_el1); local_irq_restore(flags); + /* + * If we now have a valid translation, treat the translation fault as + * spurious. + */ if (!(par & SYS_PAR_EL1_F)) - return false; + return true; /* * If we got a different type of fault from the AT instruction, * treat the translation fault as spurious. */ - dfsc = FIELD_PREP(SYS_PAR_EL1_FST, par); + dfsc = FIELD_GET(SYS_PAR_EL1_FST, par); return (dfsc & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT; } @@ -305,6 +307,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; + else if (is_el1_instruction_abort(esr)) + msg = "execute from non-executable memory"; else msg = "read from unreadable memory"; } else if (addr < PAGE_SIZE) { @@ -723,8 +727,7 @@ static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; -asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, - struct pt_regs *regs) +void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); @@ -740,43 +743,21 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, arm64_notify_die(inf->name, regs, inf->sig, inf->code, (void __user *)addr, esr); } +NOKPROBE_SYMBOL(do_mem_abort); -asmlinkage void __exception do_el0_irq_bp_hardening(void) +void do_el0_irq_bp_hardening(void) { /* PC has already been checked in entry.S */ arm64_apply_bp_hardening(); } +NOKPROBE_SYMBOL(do_el0_irq_bp_hardening); -asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr, - unsigned int esr, - struct pt_regs *regs) -{ - /* - * We've taken an instruction abort from userspace and not yet - * re-enabled IRQs. If the address is a kernel address, apply - * BP hardening prior to enabling IRQs and pre-emption. - */ - if (!is_ttbr0_addr(addr)) - arm64_apply_bp_hardening(); - - local_daif_restore(DAIF_PROCCTX); - do_mem_abort(addr, esr, regs); -} - - -asmlinkage void __exception do_sp_pc_abort(unsigned long addr, - unsigned int esr, - struct pt_regs *regs) +void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - if (user_mode(regs)) { - if (!is_ttbr0_addr(instruction_pointer(regs))) - arm64_apply_bp_hardening(); - local_daif_restore(DAIF_PROCCTX); - } - arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN, (void __user *)addr, esr); } +NOKPROBE_SYMBOL(do_sp_pc_abort); int __init early_brk64(unsigned long addr, unsigned int esr, struct pt_regs *regs); @@ -859,8 +840,7 @@ NOKPROBE_SYMBOL(debug_exception_exit); #ifdef CONFIG_ARM64_ERRATUM_1463225 DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); -static int __exception -cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { if (user_mode(regs)) return 0; @@ -879,16 +859,15 @@ cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) return 1; } #else -static int __exception -cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static int cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { return 0; } #endif /* CONFIG_ARM64_ERRATUM_1463225 */ +NOKPROBE_SYMBOL(cortex_a76_erratum_1463225_debug_handler); -asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, - unsigned int esr, - struct pt_regs *regs) +void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, + struct pt_regs *regs) { const struct fault_info *inf = esr_to_debug_fault_info(esr); unsigned long pc = instruction_pointer(regs); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 45c00a54909c..be9481cdf3b9 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -20,6 +20,7 @@ #include <linux/sort.h> #include <linux/of.h> #include <linux/of_fdt.h> +#include <linux/dma-direct.h> #include <linux/dma-mapping.h> #include <linux/dma-contiguous.h> #include <linux/efi.h> @@ -41,6 +42,8 @@ #include <asm/tlb.h> #include <asm/alternative.h> +#define ARM64_ZONE_DMA_BITS 30 + /* * We need to be able to catch inadvertent references to memstart_addr * that occur (potentially in generic code) before arm64_memblock_init() @@ -56,7 +59,14 @@ EXPORT_SYMBOL(physvirt_offset); struct page *vmemmap __ro_after_init; EXPORT_SYMBOL(vmemmap); +/* + * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of + * memory as some devices, namely the Raspberry Pi 4, have peripherals with + * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32 + * bit addressable memory area. + */ phys_addr_t arm64_dma_phys_limit __ro_after_init; +static phys_addr_t arm64_dma32_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE /* @@ -81,7 +91,7 @@ static void __init reserve_crashkernel(void) if (crash_base == 0) { /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT, + crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit, crash_size, SZ_2M); if (crash_base == 0) { pr_warn("cannot allocate crashkernel (size:0x%llx)\n", @@ -169,15 +179,16 @@ static void __init reserve_elfcorehdr(void) { } #endif /* CONFIG_CRASH_DUMP */ + /* - * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It - * currently assumes that for memory starting above 4G, 32-bit devices will - * use a DMA offset. + * Return the maximum physical address for a zone with a given address size + * limit. It currently assumes that for memory starting above 4G, 32-bit + * devices will use a DMA offset. */ -static phys_addr_t __init max_zone_dma_phys(void) +static phys_addr_t __init max_zone_phys(unsigned int zone_bits) { - phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32); - return min(offset + (1ULL << 32), memblock_end_of_DRAM()); + phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, zone_bits); + return min(offset + (1ULL << zone_bits), memblock_end_of_DRAM()); } #ifdef CONFIG_NUMA @@ -186,8 +197,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; +#ifdef CONFIG_ZONE_DMA + max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); +#endif #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys()); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit); #endif max_zone_pfns[ZONE_NORMAL] = max; @@ -200,16 +214,21 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) { struct memblock_region *reg; unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES]; - unsigned long max_dma = min; + unsigned long max_dma32 = min; + unsigned long __maybe_unused max_dma = min; memset(zone_size, 0, sizeof(zone_size)); - /* 4GB maximum for 32-bit only capable devices */ -#ifdef CONFIG_ZONE_DMA32 +#ifdef CONFIG_ZONE_DMA max_dma = PFN_DOWN(arm64_dma_phys_limit); - zone_size[ZONE_DMA32] = max_dma - min; + zone_size[ZONE_DMA] = max_dma - min; + max_dma32 = max_dma; +#endif +#ifdef CONFIG_ZONE_DMA32 + max_dma32 = PFN_DOWN(arm64_dma32_phys_limit); + zone_size[ZONE_DMA32] = max_dma32 - max_dma; #endif - zone_size[ZONE_NORMAL] = max - max_dma; + zone_size[ZONE_NORMAL] = max - max_dma32; memcpy(zhole_size, zone_size, sizeof(zhole_size)); @@ -219,16 +238,22 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) if (start >= max) continue; - -#ifdef CONFIG_ZONE_DMA32 +#ifdef CONFIG_ZONE_DMA if (start < max_dma) { - unsigned long dma_end = min(end, max_dma); - zhole_size[ZONE_DMA32] -= dma_end - start; + unsigned long dma_end = min_not_zero(end, max_dma); + zhole_size[ZONE_DMA] -= dma_end - start; } #endif - if (end > max_dma) { +#ifdef CONFIG_ZONE_DMA32 + if (start < max_dma32) { + unsigned long dma32_end = min(end, max_dma32); + unsigned long dma32_start = max(start, max_dma); + zhole_size[ZONE_DMA32] -= dma32_end - dma32_start; + } +#endif + if (end > max_dma32) { unsigned long normal_end = min(end, max); - unsigned long normal_start = max(start, max_dma); + unsigned long normal_start = max(start, max_dma32); zhole_size[ZONE_NORMAL] -= normal_end - normal_start; } } @@ -418,11 +443,15 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - /* 4GB maximum for 32-bit only capable devices */ + if (IS_ENABLED(CONFIG_ZONE_DMA)) { + zone_dma_bits = ARM64_ZONE_DMA_BITS; + arm64_dma_phys_limit = max_zone_phys(ARM64_ZONE_DMA_BITS); + } + if (IS_ENABLED(CONFIG_ZONE_DMA32)) - arm64_dma_phys_limit = max_zone_dma_phys(); + arm64_dma32_phys_limit = max_zone_phys(32); else - arm64_dma_phys_limit = PHYS_MASK + 1; + arm64_dma32_phys_limit = PHYS_MASK + 1; reserve_crashkernel(); @@ -430,7 +459,7 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; - dma_contiguous_reserve(arm64_dma_phys_limit); + dma_contiguous_reserve(arm64_dma32_phys_limit); } void __init bootmem_init(void) @@ -534,7 +563,7 @@ static void __init free_unused_memmap(void) void __init mem_init(void) { if (swiotlb_force == SWIOTLB_FORCE || - max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT)) + max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit)) swiotlb_init(1); else swiotlb_force = SWIOTLB_NO_FORCE; @@ -571,7 +600,7 @@ void free_initmem(void) { free_reserved_area(lm_alias(__init_begin), lm_alias(__init_end), - 0, "unused kernel"); + POISON_FREE_INITMEM, "unused kernel"); /* * Unmap the __init region but leave the VM area in place. This * prevents the region from being reused for kernel modules, which @@ -580,18 +609,6 @@ void free_initmem(void) unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin)); } -#ifdef CONFIG_BLK_DEV_INITRD -void __init free_initrd_mem(unsigned long start, unsigned long end) -{ - unsigned long aligned_start, aligned_end; - - aligned_start = __virt_to_phys(start) & PAGE_MASK; - aligned_end = PAGE_ALIGN(__virt_to_phys(end)); - memblock_free(aligned_start, aligned_end - aligned_start); - free_reserved_area((void *)start, (void *)end, 0, "initrd"); -} -#endif - /* * Dump out memory limit information on panic. */ diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 60c929f3683b..a9f541912289 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -338,7 +338,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, phys_addr_t (*pgtable_alloc)(int), int flags) { - unsigned long addr, length, end, next; + unsigned long addr, end, next; pgd_t *pgdp = pgd_offset_raw(pgdir, virt); /* @@ -350,9 +350,8 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, phys &= PAGE_MASK; addr = virt & PAGE_MASK; - length = PAGE_ALIGN(size + (virt & ~PAGE_MASK)); + end = PAGE_ALIGN(virt + size); - end = addr + length; do { next = pgd_addr_end(addr, end); alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc, diff --git a/arch/arm64/xen/Makefile b/arch/arm64/xen/Makefile index a4fc65f3928d..b66215e8658e 100644 --- a/arch/arm64/xen/Makefile +++ b/arch/arm64/xen/Makefile @@ -1,4 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only xen-arm-y += $(addprefix ../../arm/xen/, enlighten.o grant-table.o p2m.o mm.o) obj-y := xen-arm.o hypercall.o -obj-$(CONFIG_XEN_EFI) += $(addprefix ../../arm/xen/, efi.o) diff --git a/arch/mips/bcm63xx/prom.c b/arch/mips/bcm63xx/prom.c index 77a836e661c9..df69eaa453a1 100644 --- a/arch/mips/bcm63xx/prom.c +++ b/arch/mips/bcm63xx/prom.c @@ -84,7 +84,7 @@ void __init prom_init(void) * Here we will start up CPU1 in the background and ask it to * reconfigure itself then go back to sleep. */ - memcpy((void *)0xa0000200, &bmips_smp_movevec, 0x20); + memcpy((void *)0xa0000200, bmips_smp_movevec, 0x20); __sync(); set_c0_cause(C_SW0); cpumask_set_cpu(1, &bmips_booted_mask); diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi index 63a9f33aa43e..5cfc9d347826 100644 --- a/arch/mips/boot/dts/qca/ar9331.dtsi +++ b/arch/mips/boot/dts/qca/ar9331.dtsi @@ -99,7 +99,7 @@ miscintc: interrupt-controller@18060010 { compatible = "qca,ar7240-misc-intc"; - reg = <0x18060010 0x4>; + reg = <0x18060010 0x8>; interrupt-parent = <&cpuintc>; interrupts = <6>; diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index 16bef819fe98..914af125a7fa 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -571,7 +571,6 @@ CONFIG_USB_SERIAL_OMNINET=m CONFIG_USB_EMI62=m CONFIG_USB_EMI26=m CONFIG_USB_ADUTUX=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYPRESS_CY7C63=m diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig index 8762e75f5d5f..2c7adea7638f 100644 --- a/arch/mips/configs/rm200_defconfig +++ b/arch/mips/configs/rm200_defconfig @@ -314,7 +314,6 @@ CONFIG_USB_SERIAL_SAFE_PADDED=y CONFIG_USB_SERIAL_CYBERJACK=m CONFIG_USB_SERIAL_XIRCOM=m CONFIG_USB_SERIAL_OMNINET=m -CONFIG_USB_RIO500=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_CYTHERM=m diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c index af44b35d79a1..b4328b3b5288 100644 --- a/arch/mips/fw/arc/memory.c +++ b/arch/mips/fw/arc/memory.c @@ -160,7 +160,6 @@ void __init prom_meminit(void) void __init prom_free_prom_memory(void) { - unsigned long addr; int i; if (prom_flags & PROM_FLAG_DONT_FREE_TEMP) diff --git a/arch/mips/fw/sni/sniprom.c b/arch/mips/fw/sni/sniprom.c index 8772617b64ce..80112f2298b6 100644 --- a/arch/mips/fw/sni/sniprom.c +++ b/arch/mips/fw/sni/sniprom.c @@ -43,7 +43,7 @@ /* O32 stack has to be 8-byte aligned. */ static u64 o32_stk[4096]; -#define O32_STK &o32_stk[sizeof(o32_stk)] +#define O32_STK (&o32_stk[ARRAY_SIZE(o32_stk)]) #define __PROM_O32(fun, arg) fun arg __asm__(#fun); \ __asm__(#fun " = call_o32") diff --git a/arch/mips/include/asm/bmips.h b/arch/mips/include/asm/bmips.h index bf6a8afd7ad2..581a6a3c66e4 100644 --- a/arch/mips/include/asm/bmips.h +++ b/arch/mips/include/asm/bmips.h @@ -75,11 +75,11 @@ static inline int register_bmips_smp_ops(void) #endif } -extern char bmips_reset_nmi_vec; -extern char bmips_reset_nmi_vec_end; -extern char bmips_smp_movevec; -extern char bmips_smp_int_vec; -extern char bmips_smp_int_vec_end; +extern char bmips_reset_nmi_vec[]; +extern char bmips_reset_nmi_vec_end[]; +extern char bmips_smp_movevec[]; +extern char bmips_smp_int_vec[]; +extern char bmips_smp_int_vec_end[]; extern int bmips_smp_enabled; extern int bmips_cpu_offset; diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index 79bf34efbc04..f6136871561d 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -77,8 +77,8 @@ extern unsigned long __xchg_called_with_bad_pointer(void) extern unsigned long __xchg_small(volatile void *ptr, unsigned long val, unsigned int size); -static inline unsigned long __xchg(volatile void *ptr, unsigned long x, - int size) +static __always_inline +unsigned long __xchg(volatile void *ptr, unsigned long x, int size) { switch (size) { case 1: @@ -153,8 +153,9 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x, extern unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old, unsigned long new, unsigned int size); -static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, - unsigned long new, unsigned int size) +static __always_inline +unsigned long __cmpxchg(volatile void *ptr, unsigned long old, + unsigned long new, unsigned int size) { switch (size) { case 1: diff --git a/arch/mips/include/asm/octeon/cvmx-ipd.h b/arch/mips/include/asm/octeon/cvmx-ipd.h index cbdc14b77435..adab7b54c3b4 100644 --- a/arch/mips/include/asm/octeon/cvmx-ipd.h +++ b/arch/mips/include/asm/octeon/cvmx-ipd.h @@ -36,6 +36,7 @@ #include <asm/octeon/octeon-feature.h> #include <asm/octeon/cvmx-ipd-defs.h> +#include <asm/octeon/cvmx-pip-defs.h> enum cvmx_ipd_mode { CVMX_IPD_OPC_MODE_STT = 0LL, /* All blocks DRAM, not cached in L2 */ diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index 071053ece677..5d70babfc9ee 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -52,6 +52,7 @@ # endif #define __ARCH_WANT_SYS_FORK #define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 /* whitelists for checksyscalls */ #define __IGNORE_fadvise64_64 diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h index e78462e8ca2e..b08825531e9f 100644 --- a/arch/mips/include/asm/vdso/gettimeofday.h +++ b/arch/mips/include/asm/vdso/gettimeofday.h @@ -24,6 +24,8 @@ #define VDSO_HAS_CLOCK_GETRES 1 +#define __VDSO_USE_SYSCALL ULLONG_MAX + #ifdef CONFIG_MIPS_CLOCK_VSYSCALL static __always_inline long gettimeofday_fallback( @@ -205,7 +207,7 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) break; #endif default: - cycle_now = 0; + cycle_now = __VDSO_USE_SYSCALL; break; } diff --git a/arch/mips/include/asm/vdso/vsyscall.h b/arch/mips/include/asm/vdso/vsyscall.h index 195314732233..00d41b94ba31 100644 --- a/arch/mips/include/asm/vdso/vsyscall.h +++ b/arch/mips/include/asm/vdso/vsyscall.h @@ -28,13 +28,6 @@ int __mips_get_clock_mode(struct timekeeper *tk) } #define __arch_get_clock_mode __mips_get_clock_mode -static __always_inline -int __mips_use_vsyscall(struct vdso_data *vdata) -{ - return (vdata[CS_HRES_COARSE].clock_mode != VDSO_CLOCK_NONE); -} -#define __arch_use_vsyscall __mips_use_vsyscall - /* The asm-generic header needs to be included after the definitions above */ #include <asm-generic/vdso/vsyscall.h> diff --git a/arch/mips/include/uapi/asm/hwcap.h b/arch/mips/include/uapi/asm/hwcap.h index a2aba4b059e6..1ade1daa4921 100644 --- a/arch/mips/include/uapi/asm/hwcap.h +++ b/arch/mips/include/uapi/asm/hwcap.h @@ -6,5 +6,16 @@ #define HWCAP_MIPS_R6 (1 << 0) #define HWCAP_MIPS_MSA (1 << 1) #define HWCAP_MIPS_CRC32 (1 << 2) +#define HWCAP_MIPS_MIPS16 (1 << 3) +#define HWCAP_MIPS_MDMX (1 << 4) +#define HWCAP_MIPS_MIPS3D (1 << 5) +#define HWCAP_MIPS_SMARTMIPS (1 << 6) +#define HWCAP_MIPS_DSP (1 << 7) +#define HWCAP_MIPS_DSP2 (1 << 8) +#define HWCAP_MIPS_DSP3 (1 << 9) +#define HWCAP_MIPS_MIPS16E2 (1 << 10) +#define HWCAP_LOONGSON_MMI (1 << 11) +#define HWCAP_LOONGSON_EXT (1 << 12) +#define HWCAP_LOONGSON_EXT2 (1 << 13) #endif /* _UAPI_ASM_HWCAP_H */ diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/cpu-bugs64.c index fa62cd1dff93..6a7afe7ef4d3 100644 --- a/arch/mips/kernel/cpu-bugs64.c +++ b/arch/mips/kernel/cpu-bugs64.c @@ -24,7 +24,8 @@ static char r4kwar[] __initdata = static char daddiwar[] __initdata = "Enable CPU_DADDI_WORKAROUNDS to rectify."; -static inline void align_mod(const int align, const int mod) +static __always_inline __init +void align_mod(const int align, const int mod) { asm volatile( ".set push\n\t" @@ -38,8 +39,9 @@ static inline void align_mod(const int align, const int mod) : "n"(align), "n"(mod)); } -static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w, - const int align, const int mod) +static __always_inline __init +void mult_sh_align_mod(long *v1, long *v2, long *w, + const int align, const int mod) { unsigned long flags; int m1, m2; @@ -113,7 +115,7 @@ static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w, *w = lw; } -static inline void check_mult_sh(void) +static __always_inline __init void check_mult_sh(void) { long v1[8], v2[8], w[8]; int bug, fix, i; @@ -176,7 +178,7 @@ asmlinkage void __init do_daddi_ov(struct pt_regs *regs) exception_exit(prev_state); } -static inline void check_daddi(void) +static __init void check_daddi(void) { extern asmlinkage void handle_daddi_ov(void); unsigned long flags; @@ -242,7 +244,7 @@ static inline void check_daddi(void) int daddiu_bug = IS_ENABLED(CONFIG_CPU_MIPSR6) ? 0 : -1; -static inline void check_daddiu(void) +static __init void check_daddiu(void) { long v, w, tmp; diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index c2eb392597bf..f521cbf934e7 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -2180,6 +2180,39 @@ void cpu_probe(void) elf_hwcap |= HWCAP_MIPS_MSA; } + if (cpu_has_mips16) + elf_hwcap |= HWCAP_MIPS_MIPS16; + + if (cpu_has_mdmx) + elf_hwcap |= HWCAP_MIPS_MDMX; + + if (cpu_has_mips3d) + elf_hwcap |= HWCAP_MIPS_MIPS3D; + + if (cpu_has_smartmips) + elf_hwcap |= HWCAP_MIPS_SMARTMIPS; + + if (cpu_has_dsp) + elf_hwcap |= HWCAP_MIPS_DSP; + + if (cpu_has_dsp2) + elf_hwcap |= HWCAP_MIPS_DSP2; + + if (cpu_has_dsp3) + elf_hwcap |= HWCAP_MIPS_DSP3; + + if (cpu_has_mips16e2) + elf_hwcap |= HWCAP_MIPS_MIPS16E2; + + if (cpu_has_loongson_mmi) + elf_hwcap |= HWCAP_LOONGSON_MMI; + + if (cpu_has_loongson_ext) + elf_hwcap |= HWCAP_LOONGSON_EXT; + + if (cpu_has_loongson_ext2) + elf_hwcap |= HWCAP_LOONGSON_EXT2; + if (cpu_has_vz) cpu_probe_vz(c); diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index b8249c233754..5eec13b8d222 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -108,6 +108,9 @@ void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type) return; } + if (start < PHYS_OFFSET) + return; + memblock_add(start, size); /* Reserve any memory except the ordinary RAM ranges. */ switch (type) { @@ -321,7 +324,7 @@ static void __init bootmem_init(void) * Reserve any memory between the start of RAM and PHYS_OFFSET */ if (ramstart > PHYS_OFFSET) - memblock_reserve(PHYS_OFFSET, PFN_UP(ramstart) - PHYS_OFFSET); + memblock_reserve(PHYS_OFFSET, ramstart - PHYS_OFFSET); if (PFN_UP(ramstart) > ARCH_PFN_OFFSET) { pr_info("Wasting %lu bytes for tracking %lu unused pages\n", diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 76fae9b79f13..712c15de6ab9 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -464,10 +464,10 @@ static void bmips_wr_vec(unsigned long dst, char *start, char *end) static inline void bmips_nmi_handler_setup(void) { - bmips_wr_vec(BMIPS_NMI_RESET_VEC, &bmips_reset_nmi_vec, - &bmips_reset_nmi_vec_end); - bmips_wr_vec(BMIPS_WARM_RESTART_VEC, &bmips_smp_int_vec, - &bmips_smp_int_vec_end); + bmips_wr_vec(BMIPS_NMI_RESET_VEC, bmips_reset_nmi_vec, + bmips_reset_nmi_vec_end); + bmips_wr_vec(BMIPS_WARM_RESTART_VEC, bmips_smp_int_vec, + bmips_smp_int_vec_end); } struct reset_vec_info { diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index b0e25e913bdb..3f16f3823031 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -80,6 +80,7 @@ SYSCALL_DEFINE6(mips_mmap2, unsigned long, addr, unsigned long, len, save_static_function(sys_fork); save_static_function(sys_clone); +save_static_function(sys_clone3); SYSCALL_DEFINE1(set_thread_area, unsigned long, addr) { diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index c9c879ec9b6d..e7c5ab38e403 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -373,4 +373,4 @@ 432 n32 fsmount sys_fsmount 433 n32 fspick sys_fspick 434 n32 pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 n32 clone3 __sys_clone3 diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index bbce9159caa1..13cd66581f3b 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -349,4 +349,4 @@ 432 n64 fsmount sys_fsmount 433 n64 fspick sys_fspick 434 n64 pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 n64 clone3 __sys_clone3 diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 9653591428ec..353539ea4140 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -422,4 +422,4 @@ 432 o32 fsmount sys_fsmount 433 o32 fspick sys_fspick 434 o32 pidfd_open sys_pidfd_open -# 435 reserved for clone3 +435 o32 clone3 __sys_clone3 diff --git a/arch/mips/loongson64/Platform b/arch/mips/loongson64/Platform index c1a4d4dc4665..9f79908f5063 100644 --- a/arch/mips/loongson64/Platform +++ b/arch/mips/loongson64/Platform @@ -66,6 +66,10 @@ else $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) endif +# Some -march= flags enable MMI instructions, and GCC complains about that +# support being enabled alongside -msoft-float. Thus explicitly disable MMI. +cflags-y += $(call cc-option,-mno-loongson-mmi) + # # Loongson Machines' Support # diff --git a/arch/mips/loongson64/common/mem.c b/arch/mips/loongson64/common/mem.c index 4abb92e0fc39..4254ac4ec616 100644 --- a/arch/mips/loongson64/common/mem.c +++ b/arch/mips/loongson64/common/mem.c @@ -3,6 +3,7 @@ */ #include <linux/fs.h> #include <linux/fcntl.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <asm/bootinfo.h> @@ -64,24 +65,22 @@ void __init prom_init_memory(void) node_id = loongson_memmap->map[i].node_id; mem_type = loongson_memmap->map[i].mem_type; - if (node_id == 0) { - switch (mem_type) { - case SYSTEM_RAM_LOW: - add_memory_region(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20, - BOOT_MEM_RAM); - break; - case SYSTEM_RAM_HIGH: - add_memory_region(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20, - BOOT_MEM_RAM); - break; - case SYSTEM_RAM_RESERVED: - add_memory_region(loongson_memmap->map[i].mem_start, - (u64)loongson_memmap->map[i].mem_size << 20, - BOOT_MEM_RESERVED); - break; - } + if (node_id != 0) + continue; + + switch (mem_type) { + case SYSTEM_RAM_LOW: + memblock_add(loongson_memmap->map[i].mem_start, + (u64)loongson_memmap->map[i].mem_size << 20); + break; + case SYSTEM_RAM_HIGH: + memblock_add(loongson_memmap->map[i].mem_start, + (u64)loongson_memmap->map[i].mem_size << 20); + break; + case SYSTEM_RAM_RESERVED: + memblock_reserve(loongson_memmap->map[i].mem_start, + (u64)loongson_memmap->map[i].mem_size << 20); + break; } } } diff --git a/arch/mips/loongson64/common/serial.c b/arch/mips/loongson64/common/serial.c index ffefc1cb2612..98c3a7feb10f 100644 --- a/arch/mips/loongson64/common/serial.c +++ b/arch/mips/loongson64/common/serial.c @@ -110,7 +110,7 @@ static int __init serial_init(void) } module_init(serial_init); -static void __init serial_exit(void) +static void __exit serial_exit(void) { platform_device_unregister(&uart8250_device); } diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c index 414e97de5dc0..8f20d2cb3767 100644 --- a/arch/mips/loongson64/loongson-3/numa.c +++ b/arch/mips/loongson64/loongson-3/numa.c @@ -142,8 +142,6 @@ static void __init szmem(unsigned int node) (u32)node_id, mem_type, mem_start, mem_size); pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); - add_memory_region((node_id << 44) + mem_start, - (u64)mem_size << 20, BOOT_MEM_RAM); memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn), node); break; @@ -156,16 +154,12 @@ static void __init szmem(unsigned int node) (u32)node_id, mem_type, mem_start, mem_size); pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); - add_memory_region((node_id << 44) + mem_start, - (u64)mem_size << 20, BOOT_MEM_RAM); memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn), node); break; case SYSTEM_RAM_RESERVED: pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", (u32)node_id, mem_type, mem_start, mem_size); - add_memory_region((node_id << 44) + mem_start, - (u64)mem_size << 20, BOOT_MEM_RESERVED); memblock_reserve(((node_id << 44) + mem_start), mem_size << 20); break; @@ -191,8 +185,6 @@ static void __init node_mem_init(unsigned int node) NODE_DATA(node)->node_start_pfn = start_pfn; NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn; - free_bootmem_with_active_regions(node, end_pfn); - if (node == 0) { /* kernel end address */ unsigned long kernel_end_pfn = PFN_UP(__pa_symbol(&_end)); @@ -209,8 +201,6 @@ static void __init node_mem_init(unsigned int node) memblock_reserve((node_addrspace_offset | 0xfe000000), 32 << 20); } - - sparse_memory_present_with_active_regions(node); } static __init void prom_meminit(void) @@ -227,6 +217,7 @@ static __init void prom_meminit(void) cpumask_clear(&__node_data[(node)]->cpumask); } } + memblocks_present(); max_low_pfn = PHYS_PFN(memblock_end_of_DRAM()); for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) { diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index e01cb33bfa1a..41bb91f05688 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -653,6 +653,13 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r, int restore_scratch) { if (restore_scratch) { + /* + * Ensure the MFC0 below observes the value written to the + * KScratch register by the prior MTC0. + */ + if (scratch_reg >= 0) + uasm_i_ehb(p); + /* Reset default page size */ if (PM_DEFAULT_MASK >> 16) { uasm_i_lui(p, tmp, PM_DEFAULT_MASK >> 16); @@ -667,12 +674,10 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r, uasm_i_mtc0(p, 0, C0_PAGEMASK); uasm_il_b(p, r, lid); } - if (scratch_reg >= 0) { - uasm_i_ehb(p); + if (scratch_reg >= 0) UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg); - } else { + else UASM_i_LW(p, 1, scratchpad_offset(0), 0); - } } else { /* Reset default page size */ if (PM_DEFAULT_MASK >> 16) { @@ -921,6 +926,10 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, } if (mode != not_refill && check_for_high_segbits) { uasm_l_large_segbits_fault(l, *p); + + if (mode == refill_scratch && scratch_reg >= 0) + uasm_i_ehb(p); + /* * We get here if we are an xsseg address, or if we are * an xuseg address above (PGDIR_SHIFT+PGDIR_BITS) boundary. @@ -939,12 +948,10 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, uasm_i_jr(p, ptr); if (mode == refill_scratch) { - if (scratch_reg >= 0) { - uasm_i_ehb(p); + if (scratch_reg >= 0) UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg); - } else { + else UASM_i_LW(p, 1, scratchpad_offset(0), 0); - } } else { uasm_i_nop(p); } diff --git a/arch/mips/pmcs-msp71xx/msp_prom.c b/arch/mips/pmcs-msp71xx/msp_prom.c index dfb527961a27..800a21b8b8b0 100644 --- a/arch/mips/pmcs-msp71xx/msp_prom.c +++ b/arch/mips/pmcs-msp71xx/msp_prom.c @@ -61,6 +61,7 @@ int init_debug = 1; /* memory blocks */ struct prom_pmemblock mdesc[PROM_MAX_PMEMBLOCKS]; +#define MAX_PROM_MEM 5 static phys_addr_t prom_mem_base[MAX_PROM_MEM] __initdata; static phys_addr_t prom_mem_size[MAX_PROM_MEM] __initdata; static unsigned int nr_prom_mem __initdata; @@ -358,7 +359,7 @@ void __init prom_meminit(void) p++; if (type == BOOT_MEM_ROM_DATA) { - if (nr_prom_mem >= 5) { + if (nr_prom_mem >= MAX_PROM_MEM) { pr_err("Too many ROM DATA regions"); continue; } @@ -377,7 +378,6 @@ void __init prom_free_prom_memory(void) char *ptr; int len = 0; int i; - unsigned long addr; /* * preserve environment variables and command line from pmon/bbload diff --git a/arch/mips/sgi-ip27/Kconfig b/arch/mips/sgi-ip27/Kconfig index ef3847e7aee0..e5b6cadbec85 100644 --- a/arch/mips/sgi-ip27/Kconfig +++ b/arch/mips/sgi-ip27/Kconfig @@ -38,10 +38,3 @@ config REPLICATE_KTEXT Say Y here to enable replicating the kernel text across multiple nodes in a NUMA cluster. This trades memory for speed. -config REPLICATE_EXHANDLERS - bool "Exception handler replication support" - depends on SGI_IP27 - help - Say Y here to enable replicating the kernel exception handlers - across multiple nodes in a NUMA cluster. This trades memory for - speed. diff --git a/arch/mips/sgi-ip27/ip27-init.c b/arch/mips/sgi-ip27/ip27-init.c index 59d5375c9021..79a52c472782 100644 --- a/arch/mips/sgi-ip27/ip27-init.c +++ b/arch/mips/sgi-ip27/ip27-init.c @@ -69,23 +69,14 @@ static void per_hub_init(cnodeid_t cnode) hub_rtc_init(cnode); -#ifdef CONFIG_REPLICATE_EXHANDLERS - /* - * If this is not a headless node initialization, - * copy over the caliased exception handlers. - */ - if (get_compact_nodeid() == cnode) { - extern char except_vec2_generic, except_vec3_generic; - extern void build_tlb_refill_handler(void); - - memcpy((void *)(CKSEG0 + 0x100), &except_vec2_generic, 0x80); - memcpy((void *)(CKSEG0 + 0x180), &except_vec3_generic, 0x80); - build_tlb_refill_handler(); - memcpy((void *)(CKSEG0 + 0x100), (void *) CKSEG0, 0x80); - memcpy((void *)(CKSEG0 + 0x180), &except_vec3_generic, 0x100); + if (nasid) { + /* copy exception handlers from first node to current node */ + memcpy((void *)NODE_OFFSET_TO_K0(nasid, 0), + (void *)CKSEG0, 0x200); __flush_cache_all(); + /* switch to node local exception handlers */ + REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_8K); } -#endif } void per_cpu_init(void) diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index fb077a947575..8624a885d95b 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -332,11 +332,7 @@ static void __init mlreset(void) * thinks it is a node 0 address. */ REMOTE_HUB_S(nasid, PI_REGION_PRESENT, (region_mask | 1)); -#ifdef CONFIG_REPLICATE_EXHANDLERS - REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_8K); -#else REMOTE_HUB_S(nasid, PI_CALIAS_SIZE, PI_CALIAS_SIZE_0); -#endif #ifdef LATER /* diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 69cfa0a5339e..996a934ece7d 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -15,6 +15,7 @@ ccflags-vdso := \ $(filter -mmicromips,$(KBUILD_CFLAGS)) \ $(filter -march=%,$(KBUILD_CFLAGS)) \ $(filter -m%-float,$(KBUILD_CFLAGS)) \ + $(filter -mno-loongson-%,$(KBUILD_CFLAGS)) \ -D__VDSO__ ifdef CONFIG_CC_IS_CLANG @@ -59,7 +60,7 @@ CFLAGS_REMOVE_vgettimeofday.o = -pg ifndef CONFIG_CPU_MIPSR6 ifeq ($(call ld-ifversion, -lt, 225000000, y),y) $(warning MIPS VDSO requires binutils >= 2.25) - obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y)) + obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y)) ccflags-vdso += -DDISABLE_MIPS_VDSO endif endif diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c deleted file mode 100644 index e8243c7fd5b5..000000000000 --- a/arch/mips/vdso/gettimeofday.c +++ /dev/null @@ -1,269 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (C) 2015 Imagination Technologies - * Author: Alex Smith <alex.smith@imgtec.com> - */ - -#include "vdso.h" - -#include <linux/compiler.h> -#include <linux/time.h> - -#include <asm/clocksource.h> -#include <asm/io.h> -#include <asm/unistd.h> -#include <asm/vdso.h> - -#ifdef CONFIG_MIPS_CLOCK_VSYSCALL - -static __always_inline long gettimeofday_fallback(struct timeval *_tv, - struct timezone *_tz) -{ - register struct timezone *tz asm("a1") = _tz; - register struct timeval *tv asm("a0") = _tv; - register long ret asm("v0"); - register long nr asm("v0") = __NR_gettimeofday; - register long error asm("a3"); - - asm volatile( - " syscall\n" - : "=r" (ret), "=r" (error) - : "r" (tv), "r" (tz), "r" (nr) - : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13", - "$14", "$15", "$24", "$25", "hi", "lo", "memory"); - - return error ? -ret : ret; -} - -#endif - -static __always_inline long clock_gettime_fallback(clockid_t _clkid, - struct timespec *_ts) -{ - register struct timespec *ts asm("a1") = _ts; - register clockid_t clkid asm("a0") = _clkid; - register long ret asm("v0"); - register long nr asm("v0") = __NR_clock_gettime; - register long error asm("a3"); - - asm volatile( - " syscall\n" - : "=r" (ret), "=r" (error) - : "r" (clkid), "r" (ts), "r" (nr) - : "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13", - "$14", "$15", "$24", "$25", "hi", "lo", "memory"); - - return error ? -ret : ret; -} - -static __always_inline int do_realtime_coarse(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - - do { - start_seq = vdso_data_read_begin(data); - - ts->tv_sec = data->xtime_sec; - ts->tv_nsec = data->xtime_nsec >> data->cs_shift; - } while (vdso_data_read_retry(data, start_seq)); - - return 0; -} - -static __always_inline int do_monotonic_coarse(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - u64 to_mono_sec; - u64 to_mono_nsec; - - do { - start_seq = vdso_data_read_begin(data); - - ts->tv_sec = data->xtime_sec; - ts->tv_nsec = data->xtime_nsec >> data->cs_shift; - - to_mono_sec = data->wall_to_mono_sec; - to_mono_nsec = data->wall_to_mono_nsec; - } while (vdso_data_read_retry(data, start_seq)); - - ts->tv_sec += to_mono_sec; - timespec_add_ns(ts, to_mono_nsec); - - return 0; -} - -#ifdef CONFIG_CSRC_R4K - -static __always_inline u64 read_r4k_count(void) -{ - unsigned int count; - - __asm__ __volatile__( - " .set push\n" - " .set mips32r2\n" - " rdhwr %0, $2\n" - " .set pop\n" - : "=r" (count)); - - return count; -} - -#endif - -#ifdef CONFIG_CLKSRC_MIPS_GIC - -static __always_inline u64 read_gic_count(const union mips_vdso_data *data) -{ - void __iomem *gic = get_gic(data); - u32 hi, hi2, lo; - - do { - hi = __raw_readl(gic + sizeof(lo)); - lo = __raw_readl(gic); - hi2 = __raw_readl(gic + sizeof(lo)); - } while (hi2 != hi); - - return (((u64)hi) << 32) + lo; -} - -#endif - -static __always_inline u64 get_ns(const union mips_vdso_data *data) -{ - u64 cycle_now, delta, nsec; - - switch (data->clock_mode) { -#ifdef CONFIG_CSRC_R4K - case VDSO_CLOCK_R4K: - cycle_now = read_r4k_count(); - break; -#endif -#ifdef CONFIG_CLKSRC_MIPS_GIC - case VDSO_CLOCK_GIC: - cycle_now = read_gic_count(data); - break; -#endif - default: - return 0; - } - - delta = (cycle_now - data->cs_cycle_last) & data->cs_mask; - - nsec = (delta * data->cs_mult) + data->xtime_nsec; - nsec >>= data->cs_shift; - - return nsec; -} - -static __always_inline int do_realtime(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - u64 ns; - - do { - start_seq = vdso_data_read_begin(data); - - if (data->clock_mode == VDSO_CLOCK_NONE) - return -ENOSYS; - - ts->tv_sec = data->xtime_sec; - ns = get_ns(data); - } while (vdso_data_read_retry(data, start_seq)); - - ts->tv_nsec = 0; - timespec_add_ns(ts, ns); - - return 0; -} - -static __always_inline int do_monotonic(struct timespec *ts, - const union mips_vdso_data *data) -{ - u32 start_seq; - u64 ns; - u64 to_mono_sec; - u64 to_mono_nsec; - - do { - start_seq = vdso_data_read_begin(data); - - if (data->clock_mode == VDSO_CLOCK_NONE) - return -ENOSYS; - - ts->tv_sec = data->xtime_sec; - ns = get_ns(data); - - to_mono_sec = data->wall_to_mono_sec; - to_mono_nsec = data->wall_to_mono_nsec; - } while (vdso_data_read_retry(data, start_seq)); - - ts->tv_sec += to_mono_sec; - ts->tv_nsec = 0; - timespec_add_ns(ts, ns + to_mono_nsec); - - return 0; -} - -#ifdef CONFIG_MIPS_CLOCK_VSYSCALL - -/* - * This is behind the ifdef so that we don't provide the symbol when there's no - * possibility of there being a usable clocksource, because there's nothing we - * can do without it. When libc fails the symbol lookup it should fall back on - * the standard syscall path. - */ -int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz) -{ - const union mips_vdso_data *data = get_vdso_data(); - struct timespec ts; - int ret; - - ret = do_realtime(&ts, data); - if (ret) - return gettimeofday_fallback(tv, tz); - - if (tv) { - tv->tv_sec = ts.tv_sec; - tv->tv_usec = ts.tv_nsec / 1000; - } - - if (tz) { - tz->tz_minuteswest = data->tz_minuteswest; - tz->tz_dsttime = data->tz_dsttime; - } - - return 0; -} - -#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */ - -int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts) -{ - const union mips_vdso_data *data = get_vdso_data(); - int ret = -1; - - switch (clkid) { - case CLOCK_REALTIME_COARSE: - ret = do_realtime_coarse(ts, data); - break; - case CLOCK_MONOTONIC_COARSE: - ret = do_monotonic_coarse(ts, data); - break; - case CLOCK_REALTIME: - ret = do_realtime(ts, data); - break; - case CLOCK_MONOTONIC: - ret = do_monotonic(ts, data); - break; - default: - break; - } - - if (ret) - ret = clock_gettime_fallback(clkid, ts); - - return ret; -} diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 36b834f1c933..dca8f2de8cf5 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -60,7 +60,6 @@ KBUILD_CFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY=1 \ -DFTRACE_PATCHABLE_FUNCTION_SIZE=$(NOP_COUNT) CC_FLAGS_FTRACE := -fpatchable-function-entry=$(NOP_COUNT),$(shell echo $$(($(NOP_COUNT)-1))) -KBUILD_LDS_MODULE += $(srctree)/arch/parisc/kernel/module.lds endif OBJCOPY_FLAGS =-O binary -R .note -R .comment -S diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h index 73ca89a47f49..e5de3f897633 100644 --- a/arch/parisc/include/asm/cache.h +++ b/arch/parisc/include/asm/cache.h @@ -22,7 +22,7 @@ #define ARCH_DMA_MINALIGN L1_CACHE_BYTES -#define __read_mostly __attribute__((__section__(".data..read_mostly"))) +#define __read_mostly __section(.data..read_mostly) void parisc_cache_init(void); /* initializes cache-flushing */ void disable_sr_hashing_asm(int); /* low level support for above */ diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h index 3eb4bfc1fb36..e080143e79a3 100644 --- a/arch/parisc/include/asm/ldcw.h +++ b/arch/parisc/include/asm/ldcw.h @@ -52,7 +52,7 @@ }) #ifdef CONFIG_SMP -# define __lock_aligned __attribute__((__section__(".data..lock_aligned"))) +# define __lock_aligned __section(.data..lock_aligned) #endif #endif /* __PARISC_LDCW_H */ diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index 1d1d748c227f..b96d74496977 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -2125,7 +2125,7 @@ ftrace_regs_caller: copy %rp, %r26 LDREG -FTRACE_FRAME_SIZE-PT_SZ_ALGN(%sp), %r25 ldo -8(%r25), %r25 - copy %r3, %arg2 + ldo -FTRACE_FRAME_SIZE(%r1), %arg2 b,l ftrace_function_trampoline, %rp copy %r1, %arg3 /* struct pt_regs */ diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index ac5f34993b53..1c50093e2ebe 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -43,6 +43,7 @@ #include <linux/elf.h> #include <linux/vmalloc.h> #include <linux/fs.h> +#include <linux/ftrace.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/bug.h> @@ -862,7 +863,7 @@ int module_finalize(const Elf_Ehdr *hdr, const char *strtab = NULL; const Elf_Shdr *s; char *secstrings; - int err, symindex = -1; + int symindex = -1; Elf_Sym *newptr, *oldptr; Elf_Shdr *symhdr = NULL; #ifdef DEBUG @@ -946,11 +947,13 @@ int module_finalize(const Elf_Ehdr *hdr, /* patch .altinstructions */ apply_alternatives(aseg, aseg + s->sh_size, me->name); +#ifdef CONFIG_DYNAMIC_FTRACE /* For 32 bit kernels we're compiling modules with * -ffunction-sections so we must relocate the addresses in the - *__mcount_loc section. + * ftrace callsite section. */ - if (symindex != -1 && !strcmp(secname, "__mcount_loc")) { + if (symindex != -1 && !strcmp(secname, FTRACE_CALLSITE_SECTION)) { + int err; if (s->sh_type == SHT_REL) err = apply_relocate((Elf_Shdr *)sechdrs, strtab, symindex, @@ -962,6 +965,7 @@ int module_finalize(const Elf_Ehdr *hdr, if (err) return err; } +#endif } return 0; } diff --git a/arch/parisc/kernel/module.lds b/arch/parisc/kernel/module.lds deleted file mode 100644 index 1a9a92aca5c8..000000000000 --- a/arch/parisc/kernel/module.lds +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -SECTIONS { - __mcount_loc : { - *(__patchable_function_entries) - } -} diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c index 92a9b5f12f98..f29f682352f0 100644 --- a/arch/parisc/mm/ioremap.c +++ b/arch/parisc/mm/ioremap.c @@ -3,7 +3,7 @@ * arch/parisc/mm/ioremap.c * * (C) Copyright 1995 1996 Linus Torvalds - * (C) Copyright 2001-2006 Helge Deller <deller@gmx.de> + * (C) Copyright 2001-2019 Helge Deller <deller@gmx.de> * (C) Copyright 2005 Kyle McMartin <kyle@parisc-linux.org> */ @@ -84,7 +84,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l addr = (void __iomem *) area->addr; if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size, phys_addr, pgprot)) { - vfree(addr); + vunmap(addr); return NULL; } @@ -92,9 +92,11 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l } EXPORT_SYMBOL(__ioremap); -void iounmap(const volatile void __iomem *addr) +void iounmap(const volatile void __iomem *io_addr) { - if (addr > high_memory) - return vfree((void *) (PAGE_MASK & (unsigned long __force) addr)); + unsigned long addr = (unsigned long)io_addr & PAGE_MASK; + + if (is_vmalloc_addr((void *)addr)) + vunmap((void *)addr); } EXPORT_SYMBOL(iounmap); diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 6841bd52738b..dfbd7f22eef5 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -50,7 +50,7 @@ endif BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc -BOOTARFLAGS := -cr$(KBUILD_ARFLAGS) +BOOTARFLAGS := -crD ifdef CONFIG_CC_IS_CLANG BOOTCFLAGS += $(CLANG_FLAGS) diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index 677e9babef80..f9dc597b0b86 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -91,6 +91,7 @@ static inline void kuap_update_sr(u32 sr, u32 addr, u32 end) { + addr &= 0xf0000000; /* align addr to start of segment */ barrier(); /* make sure thread.kuap is updated before playing with SRs */ while (addr < end) { mtsrin(sr, addr); diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 4ce795d30377..ca8db193ae38 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -35,6 +35,10 @@ static inline void radix__flush_all_lpid(unsigned int lpid) { WARN_ON(1); } +static inline void radix__flush_all_lpid_guest(unsigned int lpid) +{ + WARN_ON(1); +} #endif extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index 409c9bfb43d9..57c229a86f08 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -175,4 +175,7 @@ do { \ ARCH_DLINFO_CACHE_GEOMETRY; \ } while (0) +/* Relocate the kernel image to @final_address */ +void relocate(unsigned long final_address); + #endif /* _ASM_POWERPC_ELF_H */ diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index c8bb14ff4713..f6c562acc3f8 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -329,13 +329,4 @@ struct vm_area_struct; #endif /* __ASSEMBLY__ */ #include <asm/slice.h> -/* - * Allow 30-bit DMA for very limited Broadcom wifi chips on many powerbooks. - */ -#ifdef CONFIG_PPC32 -#define ARCH_ZONE_DMA_BITS 30 -#else -#define ARCH_ZONE_DMA_BITS 31 -#endif - #endif /* _ASM_POWERPC_PAGE_H */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index a4e7762dd286..100f1b57ec2f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -3249,7 +3249,20 @@ static void setup_secure_guest(unsigned long kbase, unsigned long fdt) /* Switch to secure mode. */ prom_printf("Switching to secure mode.\n"); + /* + * The ultravisor will do an integrity check of the kernel image but we + * relocated it so the check will fail. Restore the original image by + * relocating it back to the kernel virtual base address. + */ + if (IS_ENABLED(CONFIG_RELOCATABLE)) + relocate(KERNELBASE); + ret = enter_secure_mode(kbase, fdt); + + /* Relocate the kernel again. */ + if (IS_ENABLED(CONFIG_RELOCATABLE)) + relocate(kbase); + if (ret != U_SUCCESS) { prom_printf("Returned %d from switching to secure mode.\n", ret); prom_rtas_os_term("Switch to secure mode failed.\n"); diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh index 78bab17b1396..b183ab9c5107 100644 --- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -26,7 +26,8 @@ _end enter_prom $MEM_FUNCS reloc_offset __secondary_hold __secondary_hold_acknowledge __secondary_hold_spinloop __start logo_linux_clut224 btext_prepare_BAT reloc_got2 kernstart_addr memstart_addr linux_banner _stext -__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC." +__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC. +relocate" NM="$1" OBJ="$2" diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index d7fcdfa7fee4..ec2547cc5ecb 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -36,8 +36,8 @@ #include "book3s.h" #include "trace.h" -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ +#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ /* #define EXIT_DEBUG */ @@ -69,8 +69,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "pthru_all", VCPU_STAT(pthru_all) }, { "pthru_host", VCPU_STAT(pthru_host) }, { "pthru_bad_aff", VCPU_STAT(pthru_bad_aff) }, - { "largepages_2M", VM_STAT(num_2M_pages) }, - { "largepages_1G", VM_STAT(num_1G_pages) }, + { "largepages_2M", VM_STAT(num_2M_pages, .mode = 0444) }, + { "largepages_1G", VM_STAT(num_1G_pages, .mode = 0444) }, { NULL } }; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 74a9cfe84aee..faebcbb8c4db 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1921,6 +1921,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mtspr SPRN_PCR, r6 18: /* Signal secondary CPUs to continue */ + li r0, 0 stb r0,VCORE_IN_GUEST(r5) 19: lis r8,0x7fff /* MAX_INT@h */ mtspr SPRN_HDEC,r8 diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 591bfb4bfd0f..a3f9c665bb5b 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1217,6 +1217,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, struct kvmppc_xive *xive = dev->private; struct kvmppc_xive_vcpu *xc; int i, r = -EBUSY; + u32 vp_id; pr_devel("connect_vcpu(cpu=%d)\n", cpu); @@ -1228,25 +1229,32 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev, return -EPERM; if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT) return -EBUSY; - if (kvmppc_xive_find_server(vcpu->kvm, cpu)) { - pr_devel("Duplicate !\n"); - return -EEXIST; - } if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) { pr_devel("Out of bounds !\n"); return -EINVAL; } - xc = kzalloc(sizeof(*xc), GFP_KERNEL); - if (!xc) - return -ENOMEM; /* We need to synchronize with queue provisioning */ mutex_lock(&xive->lock); + + vp_id = kvmppc_xive_vp(xive, cpu); + if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) { + pr_devel("Duplicate !\n"); + r = -EEXIST; + goto bail; + } + + xc = kzalloc(sizeof(*xc), GFP_KERNEL); + if (!xc) { + r = -ENOMEM; + goto bail; + } + vcpu->arch.xive_vcpu = xc; xc->xive = xive; xc->vcpu = vcpu; xc->server_num = cpu; - xc->vp_id = kvmppc_xive_vp(xive, cpu); + xc->vp_id = vp_id; xc->mfrr = 0xff; xc->valid = true; diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index 955b820ffd6d..fe3ed50e0818 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -220,6 +220,18 @@ static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server) return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server); } +static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id) +{ + struct kvm_vcpu *vcpu = NULL; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id) + return true; + } + return false; +} + /* * Mapping between guest priorities and host priorities * is as follow. diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 248c1ea9e788..78b906ffa0d2 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -106,6 +106,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, struct kvmppc_xive *xive = dev->private; struct kvmppc_xive_vcpu *xc = NULL; int rc; + u32 vp_id; pr_devel("native_connect_vcpu(server=%d)\n", server_num); @@ -124,7 +125,8 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, mutex_lock(&xive->lock); - if (kvmppc_xive_find_server(vcpu->kvm, server_num)) { + vp_id = kvmppc_xive_vp(xive, server_num); + if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) { pr_devel("Duplicate !\n"); rc = -EEXIST; goto bail; @@ -141,7 +143,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev, xc->vcpu = vcpu; xc->server_num = server_num; - xc->vp_id = kvmppc_xive_vp(xive, server_num); + xc->vp_id = vp_id; xc->valid = true; vcpu->arch.irq_type = KVMPPC_IRQ_XIVE; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index be941d382c8d..c95b7fe9f298 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -31,6 +31,7 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/memremap.h> +#include <linux/dma-direct.h> #include <asm/pgalloc.h> #include <asm/prom.h> @@ -201,10 +202,10 @@ static int __init mark_nonram_nosave(void) * everything else. GFP_DMA32 page allocations automatically fall back to * ZONE_DMA. * - * By using 31-bit unconditionally, we can exploit ARCH_ZONE_DMA_BITS to - * inform the generic DMA mapping code. 32-bit only devices (if not handled - * by an IOMMU anyway) will take a first dip into ZONE_NORMAL and get - * otherwise served by ZONE_DMA. + * By using 31-bit unconditionally, we can exploit zone_dma_bits to inform the + * generic DMA mapping code. 32-bit only devices (if not handled by an IOMMU + * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by + * ZONE_DMA. */ static unsigned long max_zone_pfns[MAX_NR_ZONES]; @@ -237,9 +238,18 @@ void __init paging_init(void) printk(KERN_DEBUG "Memory hole size: %ldMB\n", (long int)((top_of_ram - total_ram) >> 20)); + /* + * Allow 30-bit DMA for very limited Broadcom wifi chips on many + * powerbooks. + */ + if (IS_ENABLED(CONFIG_PPC32)) + zone_dma_bits = 30; + else + zone_dma_bits = 31; + #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(max_low_pfn, - 1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT)); + 1UL << (zone_dma_bits - PAGE_SHIFT)); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 02a59946a78a..be3517ef0574 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -1142,6 +1142,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) } /* + * If we have seen a tail call, we need a second pass. + * This is because bpf_jit_emit_common_epilogue() is called + * from bpf_jit_emit_tail_call() with a not yet stable ctx->seen. + */ + if (cgctx.seen & SEEN_TAILCALL) { + cgctx.idx = 0; + if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) { + fp = org_fp; + goto out_addrs; + } + } + + /* * Pretend to build prologue, given the features we've seen. This will * update ctgtx.idx as it pretends to output instructions, then we can * calculate total size from idx. diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 1d93e55a2de1..2dd452a047cd 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -761,6 +761,7 @@ static int spufs_init_fs_context(struct fs_context *fc) ctx->gid = current_gid(); ctx->mode = 0755; + fc->fs_private = ctx; fc->s_fs_info = sbi; fc->ops = &spufs_context_ops; return 0; diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 6bc24a47e9ef..6f300ab7f0e9 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -42,7 +42,7 @@ void pnv_pcibios_bus_add_device(struct pci_dev *pdev) { struct pci_dn *pdn = pci_get_pdn(pdev); - if (eeh_has_flag(EEH_FORCE_DISABLED)) + if (!pdn || eeh_has_flag(EEH_FORCE_DISABLED)) return; dev_dbg(&pdev->dev, "EEH: Setting up device\n"); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index fbd6e6b7bbf2..13e251699346 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -146,20 +146,25 @@ static int pnv_smp_cpu_disable(void) return 0; } +static void pnv_flush_interrupts(void) +{ + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (xive_enabled()) + xive_flush_interrupt(); + else + icp_opal_flush_interrupt(); + } else { + icp_native_flush_interrupt(); + } +} + static void pnv_smp_cpu_kill_self(void) { + unsigned long srr1, unexpected_mask, wmask; unsigned int cpu; - unsigned long srr1, wmask; u64 lpcr_val; /* Standard hot unplug procedure */ - /* - * This hard disables local interurpts, ensuring we have no lazy - * irqs pending. - */ - WARN_ON(irqs_disabled()); - hard_irq_disable(); - WARN_ON(lazy_irq_pending()); idle_task_exit(); current->active_mm = NULL; /* for sanity */ @@ -173,6 +178,27 @@ static void pnv_smp_cpu_kill_self(void) wmask = SRR1_WAKEMASK_P8; /* + * This turns the irq soft-disabled state we're called with, into a + * hard-disabled state with pending irq_happened interrupts cleared. + * + * PACA_IRQ_DEC - Decrementer should be ignored. + * PACA_IRQ_HMI - Can be ignored, processing is done in real mode. + * PACA_IRQ_DBELL, EE, PMI - Unexpected. + */ + hard_irq_disable(); + if (generic_check_cpu_restart(cpu)) + goto out; + + unexpected_mask = ~(PACA_IRQ_DEC | PACA_IRQ_HMI | PACA_IRQ_HARD_DIS); + if (local_paca->irq_happened & unexpected_mask) { + if (local_paca->irq_happened & PACA_IRQ_EE) + pnv_flush_interrupts(); + DBG("CPU%d Unexpected exit while offline irq_happened=%lx!\n", + cpu, local_paca->irq_happened); + } + local_paca->irq_happened = PACA_IRQ_HARD_DIS; + + /* * We don't want to take decrementer interrupts while we are * offline, so clear LPCR:PECE1. We keep PECE2 (and * LPCR_PECE_HVEE on P9) enabled so as to let IPIs in. @@ -197,6 +223,7 @@ static void pnv_smp_cpu_kill_self(void) srr1 = pnv_cpu_offline(cpu); + WARN_ON_ONCE(!irqs_disabled()); WARN_ON(lazy_irq_pending()); /* @@ -212,13 +239,7 @@ static void pnv_smp_cpu_kill_self(void) */ if (((srr1 & wmask) == SRR1_WAKEEE) || ((srr1 & wmask) == SRR1_WAKEHVI)) { - if (cpu_has_feature(CPU_FTR_ARCH_300)) { - if (xive_enabled()) - xive_flush_interrupt(); - else - icp_opal_flush_interrupt(); - } else - icp_native_flush_interrupt(); + pnv_flush_interrupts(); } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) { unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); asm volatile(PPC_MSGCLR(%0) : : "r" (msg)); @@ -266,7 +287,7 @@ static void pnv_smp_cpu_kill_self(void) */ lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1; pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val); - +out: DBG("CPU%d coming online...\n", cpu); } diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index b53359258d99..f87a5c64e24d 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1419,6 +1419,9 @@ void __init pseries_lpar_read_hblkrm_characteristics(void) unsigned char local_buffer[SPLPAR_TLB_BIC_MAXLENGTH]; int call_status, len, idx, bpsize; + if (!firmware_has_feature(FW_FEATURE_BLOCK_REMOVE)) + return; + spin_lock(&rtas_data_buf_lock); memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE); call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1, diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 104d334511cd..88cfcb96bf23 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -13,6 +13,7 @@ compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000"; chosen { + stdout-path = "serial0"; }; cpus { diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 5a02b7d50940..9c992a88d858 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -22,6 +22,7 @@ #define REG_L __REG_SEL(ld, lw) #define REG_S __REG_SEL(sd, sw) +#define REG_SC __REG_SEL(sc.d, sc.w) #define SZREG __REG_SEL(8, 4) #define LGREG __REG_SEL(3, 2) diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h index 07ceee8b1747..75604fec1b1b 100644 --- a/arch/riscv/include/asm/bug.h +++ b/arch/riscv/include/asm/bug.h @@ -12,7 +12,6 @@ #include <asm/asm.h> -#ifdef CONFIG_GENERIC_BUG #define __INSN_LENGTH_MASK _UL(0x3) #define __INSN_LENGTH_32 _UL(0x3) #define __COMPRESSED_INSN_MASK _UL(0xffff) @@ -20,7 +19,6 @@ #define __BUG_INSN_32 _UL(0x00100073) /* ebreak */ #define __BUG_INSN_16 _UL(0x9002) /* c.ebreak */ -#ifndef __ASSEMBLY__ typedef u32 bug_insn_t; #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS @@ -43,6 +41,7 @@ typedef u32 bug_insn_t; RISCV_SHORT " %2" #endif +#ifdef CONFIG_GENERIC_BUG #define __BUG_FLAGS(flags) \ do { \ __asm__ __volatile__ ( \ @@ -58,14 +57,10 @@ do { \ "i" (flags), \ "i" (sizeof(struct bug_entry))); \ } while (0) - -#endif /* !__ASSEMBLY__ */ #else /* CONFIG_GENERIC_BUG */ -#ifndef __ASSEMBLY__ #define __BUG_FLAGS(flags) do { \ __asm__ __volatile__ ("ebreak\n"); \ } while (0) -#endif /* !__ASSEMBLY__ */ #endif /* CONFIG_GENERIC_BUG */ #define BUG() do { \ @@ -79,15 +74,10 @@ do { \ #include <asm-generic/bug.h> -#ifndef __ASSEMBLY__ - struct pt_regs; struct task_struct; -extern void die(struct pt_regs *regs, const char *str); -extern void do_trap(struct pt_regs *regs, int signo, int code, - unsigned long addr); - -#endif /* !__ASSEMBLY__ */ +void die(struct pt_regs *regs, const char *str); +void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr); #endif /* _ASM_RISCV_BUG_H */ diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h index fc1189ad3777..3ba4d93721d3 100644 --- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -13,6 +13,7 @@ #include <linux/types.h> #include <asm/mmiowb.h> +#include <asm/pgtable.h> extern void __iomem *ioremap(phys_addr_t offset, unsigned long size); @@ -162,6 +163,12 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) #endif /* + * I/O port access constants. + */ +#define IO_SPACE_LIMIT (PCI_IO_SIZE - 1) +#define PCI_IOBASE ((void __iomem *)PCI_IO_START) + +/* * Emulation routines for the port-mapped IO space used by some PCI drivers. * These are defined as being "fully synchronous", but also "not guaranteed to * be fully ordered with respect to other memory and I/O operations". We're diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h index 75576424c0f7..6e1b0e0325eb 100644 --- a/arch/riscv/include/asm/irq.h +++ b/arch/riscv/include/asm/irq.h @@ -7,6 +7,9 @@ #ifndef _ASM_RISCV_IRQ_H #define _ASM_RISCV_IRQ_H +#include <linux/interrupt.h> +#include <linux/linkage.h> + #define NR_IRQS 0 void riscv_timer_interrupt(void); diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 7255f2d8395b..d3221017194d 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -7,6 +7,7 @@ #define _ASM_RISCV_PGTABLE_H #include <linux/mmzone.h> +#include <linux/sizes.h> #include <asm/pgtable-bits.h> @@ -86,14 +87,7 @@ extern pgd_t swapper_pg_dir[]; #define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) #define VMALLOC_END (PAGE_OFFSET - 1) #define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) - -#define FIXADDR_TOP VMALLOC_START -#ifdef CONFIG_64BIT -#define FIXADDR_SIZE PMD_SIZE -#else -#define FIXADDR_SIZE PGDIR_SIZE -#endif -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define PCI_IO_SIZE SZ_16M /* * Roughly size the vmemmap space to be large enough to fit enough @@ -108,6 +102,17 @@ extern pgd_t swapper_pg_dir[]; #define vmemmap ((struct page *)VMEMMAP_START) +#define PCI_IO_END VMEMMAP_START +#define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) +#define FIXADDR_TOP PCI_IO_START + +#ifdef CONFIG_64BIT +#define FIXADDR_SIZE PMD_SIZE +#else +#define FIXADDR_SIZE PGDIR_SIZE +#endif +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) + /* * ZERO_PAGE is a global shared page that is always zero, * used for zero-mapped memory areas, etc. @@ -184,10 +189,7 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) return __pte((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot)); } -static inline pte_t mk_pte(struct page *page, pgprot_t prot) -{ - return pfn_pte(page_to_pfn(page), prot); -} +#define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) #define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) @@ -428,9 +430,7 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#ifdef CONFIG_FLATMEM #define kern_addr_valid(addr) (1) /* FIXME */ -#endif extern void *dtb_early_va; extern void setup_bootmem(void); diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index f0227bdce0f0..ee4f0ac62c9d 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -6,6 +6,7 @@ #ifndef _ASM_RISCV_SWITCH_TO_H #define _ASM_RISCV_SWITCH_TO_H +#include <linux/sched/task_stack.h> #include <asm/processor.h> #include <asm/ptrace.h> #include <asm/csr.h> diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index 37ae4e367ad2..f02188a5b0f4 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -10,10 +10,6 @@ #include <linux/mm_types.h> #include <asm/smp.h> -/* - * Flush entire local TLB. 'sfence.vma' implicitly fences with the instruction - * cache as well, so a 'fence.i' is not necessary. - */ static inline void local_flush_tlb_all(void) { __asm__ __volatile__ ("sfence.vma" : : : "memory"); diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index b1ade9a49347..a5ad00043104 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -10,6 +10,7 @@ #include <asm/processor.h> #include <asm/hwcap.h> #include <asm/smp.h> +#include <asm/switch_to.h> unsigned long elf_hwcap __read_mostly; #ifdef CONFIG_FPU diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index da7aa88113c2..8ca479831142 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -98,7 +98,26 @@ _save_context: */ .macro RESTORE_ALL REG_L a0, PT_SSTATUS(sp) - REG_L a2, PT_SEPC(sp) + /* + * The current load reservation is effectively part of the processor's + * state, in the sense that load reservations cannot be shared between + * different hart contexts. We can't actually save and restore a load + * reservation, so instead here we clear any existing reservation -- + * it's always legal for implementations to clear load reservations at + * any point (as long as the forward progress guarantee is kept, but + * we'll ignore that here). + * + * Dangling load reservations can be the result of taking a trap in the + * middle of an LR/SC sequence, but can also be the result of a taken + * forward branch around an SC -- which is how we implement CAS. As a + * result we need to clear reservations between the last CAS and the + * jump back to the new context. While it is unlikely the store + * completes, implementations are allowed to expand reservations to be + * arbitrarily large. + */ + REG_L a2, PT_SEPC(sp) + REG_SC x0, a2, PT_SEPC(sp) + csrw CSR_SSTATUS, a0 csrw CSR_SEPC, a2 @@ -254,12 +273,11 @@ restore_all: resume_kernel: REG_L s0, TASK_TI_PREEMPT_COUNT(tp) bnez s0, restore_all -need_resched: REG_L s0, TASK_TI_FLAGS(tp) andi s0, s0, _TIF_NEED_RESCHED beqz s0, restore_all call preempt_schedule_irq - j need_resched + j restore_all #endif work_pending: diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h new file mode 100644 index 000000000000..105fb0496b24 --- /dev/null +++ b/arch/riscv/kernel/head.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 SiFive, Inc. + */ +#ifndef __ASM_HEAD_H +#define __ASM_HEAD_H + +#include <linux/linkage.h> +#include <linux/init.h> + +extern atomic_t hart_lottery; + +asmlinkage void do_page_fault(struct pt_regs *regs); +asmlinkage void __init setup_vm(uintptr_t dtb_pa); + +extern void *__cpu_up_stack_pointer[]; +extern void *__cpu_up_task_pointer[]; + +void __init parse_dtb(void); + +#endif /* __ASM_HEAD_H */ diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c index 6d8659388c49..fffac6ddb0e0 100644 --- a/arch/riscv/kernel/irq.c +++ b/arch/riscv/kernel/irq.c @@ -24,7 +24,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) return 0; } -asmlinkage void __irq_entry do_IRQ(struct pt_regs *regs) +asmlinkage __visible void __irq_entry do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c index c9ae48333114..e264e59e596e 100644 --- a/arch/riscv/kernel/module-sections.c +++ b/arch/riscv/kernel/module-sections.c @@ -8,6 +8,7 @@ #include <linux/elf.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/moduleloader.h> unsigned long module_emit_got_entry(struct module *mod, unsigned long val) { diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index fb3a082362eb..85e3c39bb60b 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -7,6 +7,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> @@ -19,6 +20,7 @@ #include <asm/csr.h> #include <asm/string.h> #include <asm/switch_to.h> +#include <asm/thread_info.h> extern asmlinkage void ret_from_fork(void); extern asmlinkage void ret_from_kernel_thread(void); diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 368751438366..1252113ef8b2 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -148,7 +148,7 @@ long arch_ptrace(struct task_struct *child, long request, * Allows PTRACE_SYSCALL to work. These are called from entry.S in * {handle,ret_from}_syscall. */ -void do_syscall_trace_enter(struct pt_regs *regs) +__visible void do_syscall_trace_enter(struct pt_regs *regs) { if (test_thread_flag(TIF_SYSCALL_TRACE)) if (tracehook_report_syscall_entry(regs)) @@ -162,7 +162,7 @@ void do_syscall_trace_enter(struct pt_regs *regs) audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3); } -void do_syscall_trace_exit(struct pt_regs *regs) +__visible void do_syscall_trace_exit(struct pt_regs *regs) { audit_syscall_exit(regs); diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c index d0fe623bfb8f..aa56bb135ec4 100644 --- a/arch/riscv/kernel/reset.c +++ b/arch/riscv/kernel/reset.c @@ -4,6 +4,7 @@ */ #include <linux/reboot.h> +#include <linux/pm.h> #include <asm/sbi.h> static void default_power_off(void) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index a990a6cb184f..845ae0e12115 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -24,6 +24,8 @@ #include <asm/tlbflush.h> #include <asm/thread_info.h> +#include "head.h" + #ifdef CONFIG_DUMMY_CONSOLE struct screen_info screen_info = { .orig_video_lines = 30, diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index b14d7647d800..d0f6f212f5df 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -26,7 +26,7 @@ struct rt_sigframe { #ifdef CONFIG_FPU static long restore_fp_state(struct pt_regs *regs, - union __riscv_fp_state *sc_fpregs) + union __riscv_fp_state __user *sc_fpregs) { long err; struct __riscv_d_ext_state __user *state = &sc_fpregs->d; @@ -53,7 +53,7 @@ static long restore_fp_state(struct pt_regs *regs, } static long save_fp_state(struct pt_regs *regs, - union __riscv_fp_state *sc_fpregs) + union __riscv_fp_state __user *sc_fpregs) { long err; struct __riscv_d_ext_state __user *state = &sc_fpregs->d; @@ -292,8 +292,8 @@ static void do_signal(struct pt_regs *regs) * notification of userspace execution resumption * - triggered by the _TIF_WORK_MASK flags */ -asmlinkage void do_notify_resume(struct pt_regs *regs, - unsigned long thread_info_flags) +asmlinkage __visible void do_notify_resume(struct pt_regs *regs, + unsigned long thread_info_flags) { /* Handle pending signal delivery */ if (thread_info_flags & _TIF_SIGPENDING) diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index b18cd6c8e8fb..5c9ec78422c2 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -8,7 +8,9 @@ * Copyright (C) 2017 SiFive */ +#include <linux/cpu.h> #include <linux/interrupt.h> +#include <linux/profile.h> #include <linux/smp.h> #include <linux/sched.h> #include <linux/seq_file.h> diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 18ae6da5115e..261f4087cc39 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -29,6 +29,9 @@ #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/sbi.h> +#include <asm/smp.h> + +#include "head.h" void *__cpu_up_stack_pointer[NR_CPUS]; void *__cpu_up_task_pointer[NR_CPUS]; @@ -130,7 +133,7 @@ void __init smp_cpus_done(unsigned int max_cpus) /* * C entry point for a secondary processor. */ -asmlinkage void __init smp_callin(void) +asmlinkage __visible void __init smp_callin(void) { struct mm_struct *mm = &init_mm; diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c index e5dd52d8f633..f1ead9df96ca 100644 --- a/arch/riscv/kernel/syscall_table.c +++ b/arch/riscv/kernel/syscall_table.c @@ -8,6 +8,7 @@ #include <linux/syscalls.h> #include <asm-generic/syscalls.h> #include <asm/vdso.h> +#include <asm/syscall.h> #undef __SYSCALL #define __SYSCALL(nr, call) [nr] = (call), diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 9dd1f2e64db1..6a53c02e9c73 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -7,6 +7,7 @@ #include <linux/clocksource.h> #include <linux/delay.h> #include <asm/sbi.h> +#include <asm/processor.h> unsigned long riscv_timebase; EXPORT_SYMBOL_GPL(riscv_timebase); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 424eb72d56b1..473de3ae8bb7 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -3,6 +3,7 @@ * Copyright (C) 2012 Regents of the University of California */ +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/sched.h> @@ -83,7 +84,7 @@ static void do_trap_error(struct pt_regs *regs, int signo, int code, } #define DO_ERROR_INFO(name, signo, code, str) \ -asmlinkage void name(struct pt_regs *regs) \ +asmlinkage __visible void name(struct pt_regs *regs) \ { \ do_trap_error(regs, signo, code, regs->sepc, "Oops - " str); \ } @@ -111,7 +112,6 @@ DO_ERROR_INFO(do_trap_ecall_s, DO_ERROR_INFO(do_trap_ecall_m, SIGILL, ILL_ILLTRP, "environment call from M-mode"); -#ifdef CONFIG_GENERIC_BUG static inline unsigned long get_break_insn_length(unsigned long pc) { bug_insn_t insn; @@ -120,28 +120,15 @@ static inline unsigned long get_break_insn_length(unsigned long pc) return 0; return (((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) ? 4UL : 2UL); } -#endif /* CONFIG_GENERIC_BUG */ -asmlinkage void do_trap_break(struct pt_regs *regs) +asmlinkage __visible void do_trap_break(struct pt_regs *regs) { -#ifdef CONFIG_GENERIC_BUG - if (!user_mode(regs)) { - enum bug_trap_type type; - - type = report_bug(regs->sepc, regs); - switch (type) { - case BUG_TRAP_TYPE_NONE: - break; - case BUG_TRAP_TYPE_WARN: - regs->sepc += get_break_insn_length(regs->sepc); - break; - case BUG_TRAP_TYPE_BUG: - die(regs, "Kernel BUG"); - } - } -#endif /* CONFIG_GENERIC_BUG */ - - force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)(regs->sepc)); + if (user_mode(regs)) + force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->sepc); + else if (report_bug(regs->sepc, regs) == BUG_TRAP_TYPE_WARN) + regs->sepc += get_break_insn_length(regs->sepc); + else + die(regs, "Kernel BUG"); } #ifdef CONFIG_GENERIC_BUG diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index c9c21e0d5641..484d95a70907 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -6,6 +6,7 @@ * Copyright (C) 2015 Regents of the University of California */ +#include <linux/elf.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/binfmts.h> @@ -25,7 +26,7 @@ static union { struct vdso_data data; u8 page[PAGE_SIZE]; } vdso_data_store __page_aligned_data; -struct vdso_data *vdso_data = &vdso_data_store.data; +static struct vdso_data *vdso_data = &vdso_data_store.data; static int __init vdso_init(void) { diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c index beeb5d7f92ea..ca66d44156b6 100644 --- a/arch/riscv/mm/context.c +++ b/arch/riscv/mm/context.c @@ -7,6 +7,7 @@ #include <linux/mm.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> +#include <asm/mmu_context.h> /* * When necessary, performs a deferred icache flush for the given MM context, diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 96add1427a75..247b8c859c44 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -18,6 +18,8 @@ #include <asm/ptrace.h> #include <asm/tlbflush.h> +#include "../kernel/head.h" + /* * This routine handles page faults. It determines the address and the * problem, and then passes it off to one of the appropriate routines. diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index f0ba71304b6e..573463d1c799 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -11,6 +11,7 @@ #include <linux/swap.h> #include <linux/sizes.h> #include <linux/of_fdt.h> +#include <linux/libfdt.h> #include <asm/fixmap.h> #include <asm/tlbflush.h> @@ -18,6 +19,8 @@ #include <asm/pgtable.h> #include <asm/io.h> +#include "../kernel/head.h" + unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); @@ -82,6 +85,8 @@ disable: } #endif /* CONFIG_BLK_DEV_INITRD */ +static phys_addr_t dtb_early_pa __initdata; + void __init setup_bootmem(void) { struct memblock_region *reg; @@ -117,7 +122,12 @@ void __init setup_bootmem(void) setup_initrd(); #endif /* CONFIG_BLK_DEV_INITRD */ - early_init_fdt_reserve_self(); + /* + * Avoid using early_init_fdt_reserve_self() since __pa() does + * not work for DTB pointers that are fixmap addresses + */ + memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); + early_init_fdt_scan_reserved_mem(); memblock_allow_resize(); memblock_dump_all(); @@ -329,8 +339,7 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size) */ #ifndef __riscv_cmodel_medany -#error "setup_vm() is called from head.S before relocate so it should " - "not use absolute addressing." +#error "setup_vm() is called from head.S before relocate so it should not use absolute addressing." #endif asmlinkage void __init setup_vm(uintptr_t dtb_pa) @@ -393,6 +402,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) /* Save pointer to DTB for early FDT parsing */ dtb_early_va = (void *)fix_to_virt(FIX_FDT) + (dtb_pa & ~PAGE_MASK); + /* Save physical address for memblock reservation */ + dtb_early_pa = dtb_pa; } static void __init setup_vm_final(void) @@ -448,7 +459,7 @@ void __init paging_init(void) zone_sizes_init(); } -#ifdef CONFIG_SPARSEMEM +#ifdef CONFIG_SPARSEMEM_VMEMMAP int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { diff --git a/arch/riscv/mm/sifive_l2_cache.c b/arch/riscv/mm/sifive_l2_cache.c index 2e637ad71c05..a9ffff3277c7 100644 --- a/arch/riscv/mm/sifive_l2_cache.c +++ b/arch/riscv/mm/sifive_l2_cache.c @@ -142,7 +142,7 @@ static irqreturn_t l2_int_handler(int irq, void *device) return IRQ_HANDLED; } -int __init sifive_l2_init(void) +static int __init sifive_l2_init(void) { struct device_node *np; struct resource res; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 43a81d0ad507..f0df9e48e651 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -246,8 +246,8 @@ choice config MARCH_Z900 bool "IBM zSeries model z800 and z900" - depends on !CC_IS_CLANG select HAVE_MARCH_Z900_FEATURES + depends on $(cc-option,-march=z900) help Select this to enable optimizations for model z800/z900 (2064 and 2066 series). This will enable some optimizations that are not @@ -255,8 +255,8 @@ config MARCH_Z900 config MARCH_Z990 bool "IBM zSeries model z890 and z990" - depends on !CC_IS_CLANG select HAVE_MARCH_Z990_FEATURES + depends on $(cc-option,-march=z990) help Select this to enable optimizations for model z890/z990 (2084 and 2086 series). The kernel will be slightly faster but will not work @@ -264,8 +264,8 @@ config MARCH_Z990 config MARCH_Z9_109 bool "IBM System z9" - depends on !CC_IS_CLANG select HAVE_MARCH_Z9_109_FEATURES + depends on $(cc-option,-march=z9-109) help Select this to enable optimizations for IBM System z9 (2094 and 2096 series). The kernel will be slightly faster but will not work @@ -274,6 +274,7 @@ config MARCH_Z9_109 config MARCH_Z10 bool "IBM System z10" select HAVE_MARCH_Z10_FEATURES + depends on $(cc-option,-march=z10) help Select this to enable optimizations for IBM System z10 (2097 and 2098 series). The kernel will be slightly faster but will not work @@ -282,6 +283,7 @@ config MARCH_Z10 config MARCH_Z196 bool "IBM zEnterprise 114 and 196" select HAVE_MARCH_Z196_FEATURES + depends on $(cc-option,-march=z196) help Select this to enable optimizations for IBM zEnterprise 114 and 196 (2818 and 2817 series). The kernel will be slightly faster but will @@ -290,6 +292,7 @@ config MARCH_Z196 config MARCH_ZEC12 bool "IBM zBC12 and zEC12" select HAVE_MARCH_ZEC12_FEATURES + depends on $(cc-option,-march=zEC12) help Select this to enable optimizations for IBM zBC12 and zEC12 (2828 and 2827 series). The kernel will be slightly faster but will not work on @@ -298,6 +301,7 @@ config MARCH_ZEC12 config MARCH_Z13 bool "IBM z13s and z13" select HAVE_MARCH_Z13_FEATURES + depends on $(cc-option,-march=z13) help Select this to enable optimizations for IBM z13s and z13 (2965 and 2964 series). The kernel will be slightly faster but will not work on @@ -306,6 +310,7 @@ config MARCH_Z13 config MARCH_Z14 bool "IBM z14 ZR1 and z14" select HAVE_MARCH_Z14_FEATURES + depends on $(cc-option,-march=z14) help Select this to enable optimizations for IBM z14 ZR1 and z14 (3907 and 3906 series). The kernel will be slightly faster but will not @@ -314,6 +319,7 @@ config MARCH_Z14 config MARCH_Z15 bool "IBM z15" select HAVE_MARCH_Z15_FEATURES + depends on $(cc-option,-march=z15) help Select this to enable optimizations for IBM z15 (8562 and 8561 series). The kernel will be slightly faster but will not @@ -367,33 +373,39 @@ config TUNE_DEFAULT config TUNE_Z900 bool "IBM zSeries model z800 and z900" - depends on !CC_IS_CLANG + depends on $(cc-option,-mtune=z900) config TUNE_Z990 bool "IBM zSeries model z890 and z990" - depends on !CC_IS_CLANG + depends on $(cc-option,-mtune=z990) config TUNE_Z9_109 bool "IBM System z9" - depends on !CC_IS_CLANG + depends on $(cc-option,-mtune=z9-109) config TUNE_Z10 bool "IBM System z10" + depends on $(cc-option,-mtune=z10) config TUNE_Z196 bool "IBM zEnterprise 114 and 196" + depends on $(cc-option,-mtune=z196) config TUNE_ZEC12 bool "IBM zBC12 and zEC12" + depends on $(cc-option,-mtune=zEC12) config TUNE_Z13 - bool "IBM z13" + bool "IBM z13s and z13" + depends on $(cc-option,-mtune=z13) config TUNE_Z14 - bool "IBM z14" + bool "IBM z14 ZR1 and z14" + depends on $(cc-option,-mtune=z14) config TUNE_Z15 bool "IBM z15" + depends on $(cc-option,-mtune=z15) endchoice diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 596ca7cc4d7b..fbd341ea03b8 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -46,7 +46,7 @@ struct diag_ops __bootdata_preserved(diag_dma_ops) = { .diag0c = _diag0c_dma, .diag308_reset = _diag308_reset_dma }; -static struct diag210 _diag210_tmp_dma __section(".dma.data"); +static struct diag210 _diag210_tmp_dma __section(.dma.data); struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma; void _swsusp_reset_dma(void); unsigned long __bootdata_preserved(__swsusp_reset_dma) = __pa(_swsusp_reset_dma); @@ -101,10 +101,18 @@ static void handle_relocs(unsigned long offset) dynsym = (Elf64_Sym *) vmlinux.dynsym_start; for (rela = rela_start; rela < rela_end; rela++) { loc = rela->r_offset + offset; - val = rela->r_addend + offset; + val = rela->r_addend; r_sym = ELF64_R_SYM(rela->r_info); - if (r_sym) - val += dynsym[r_sym].st_value; + if (r_sym) { + if (dynsym[r_sym].st_shndx != SHN_UNDEF) + val += dynsym[r_sym].st_value + offset; + } else { + /* + * 0 == undefined symbol table index (STN_UNDEF), + * used for R_390_RELATIVE, only add KASLR offset + */ + val += offset; + } r_type = ELF64_R_TYPE(rela->r_info); rc = arch_kexec_do_relocs(r_type, (void *) loc, val, 0); if (rc) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 347f48702edb..38d64030aacf 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -44,6 +44,7 @@ CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y @@ -69,12 +70,13 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG=y CONFIG_MODULE_SIG_SHA256=y +CONFIG_UNUSED_SYMBOLS=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP_IOCOST=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -370,6 +372,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y CONFIG_PCI_DEBUG=y CONFIG_HOTPLUG_PCI=y @@ -424,6 +427,7 @@ CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -435,6 +439,7 @@ CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m +CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_NETDEVICES=y CONFIG_BONDING=m @@ -489,6 +494,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_NVIDIA is not set # CONFIG_NET_VENDOR_OKI is not set # CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_PENSANDO is not set # CONFIG_NET_VENDOR_QLOGIC is not set # CONFIG_NET_VENDOR_QUALCOMM is not set # CONFIG_NET_VENDOR_RDC is not set @@ -538,15 +544,16 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m -CONFIG_DRM=y -CONFIG_DRM_VIRTIO_GPU=y +CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_ACCESS=m CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m +CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m CONFIG_VFIO_MDEV=m @@ -580,6 +587,8 @@ CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y +CONFIG_FS_VERITY=y +CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA_NETLINK_INTERFACE=y @@ -589,6 +598,7 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m +CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m @@ -648,12 +658,15 @@ CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_LOCKDOWN_LSM=y +CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y +CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m @@ -664,10 +677,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -739,7 +748,6 @@ CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 -CONFIG_UNUSED_SYMBOLS=y CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 8514b8b9500f..25f799849582 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -44,6 +44,7 @@ CONFIG_NUMA=y # CONFIG_NUMA_EMU is not set CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_SIG=y CONFIG_EXPOLINE=y CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y @@ -66,11 +67,12 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_MODULE_SIG=y CONFIG_MODULE_SIG_SHA256=y +CONFIG_UNUSED_SYMBOLS=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y +CONFIG_BLK_CGROUP_IOCOST=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -363,6 +365,7 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m +# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y @@ -418,6 +421,7 @@ CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_THIN_PROVISIONING=m CONFIG_DM_WRITECACHE=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m CONFIG_DM_LOG_USERSPACE=m CONFIG_DM_RAID=m @@ -429,6 +433,7 @@ CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m CONFIG_DM_VERITY=m +CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_DM_INTEGRITY=m CONFIG_NETDEVICES=y @@ -484,6 +489,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_NVIDIA is not set # CONFIG_NET_VENDOR_OKI is not set # CONFIG_NET_VENDOR_PACKET_ENGINES is not set +# CONFIG_NET_VENDOR_PENSANDO is not set # CONFIG_NET_VENDOR_QLOGIC is not set # CONFIG_NET_VENDOR_QUALCOMM is not set # CONFIG_NET_VENDOR_RDC is not set @@ -533,16 +539,16 @@ CONFIG_WATCHDOG_CORE=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m -CONFIG_DRM=y -CONFIG_DRM_VIRTIO_GPU=y -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set +CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_ACCESS=m CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m +CONFIG_SYNC_FILE=y CONFIG_VFIO=m CONFIG_VFIO_PCI=m CONFIG_VFIO_MDEV=m @@ -573,6 +579,8 @@ CONFIG_NILFS2_FS=m CONFIG_FS_DAX=y CONFIG_EXPORTFS_BLOCK_OPS=y CONFIG_FS_ENCRYPTION=y +CONFIG_FS_VERITY=y +CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA_NETLINK_INTERFACE=y @@ -581,6 +589,7 @@ CONFIG_QFMT_V2=m CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=y CONFIG_CUSE=m +CONFIG_VIRTIO_FS=m CONFIG_OVERLAY_FS=m CONFIG_FSCACHE=m CONFIG_CACHEFILES=m @@ -639,12 +648,15 @@ CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_LOCKDOWN_LSM=y +CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y +CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set @@ -656,10 +668,6 @@ CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m -CONFIG_CRYPTO_AEGIS128L=m -CONFIG_CRYPTO_AEGIS256=m -CONFIG_CRYPTO_MORUS640=m -CONFIG_CRYPTO_MORUS1280=m CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_OFB=m @@ -727,7 +735,6 @@ CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y CONFIG_GDB_SCRIPTS=y CONFIG_FRAME_WARN=1024 -CONFIG_UNUSED_SYMBOLS=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index be09a208b608..20c51e5d9353 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -61,7 +61,7 @@ CONFIG_RAW_DRIVER=y CONFIG_CONFIGFS_FS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set -# CONFIG_DIMLIB is not set +CONFIG_LSM="yama,loadpin,safesetid,integrity" CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y diff --git a/arch/s390/crypto/sha_common.c b/arch/s390/crypto/sha_common.c index d39e0f079217..686fe7aa192f 100644 --- a/arch/s390/crypto/sha_common.c +++ b/arch/s390/crypto/sha_common.c @@ -74,14 +74,17 @@ int s390_sha_final(struct shash_desc *desc, u8 *out) struct s390_sha_ctx *ctx = shash_desc_ctx(desc); unsigned int bsize = crypto_shash_blocksize(desc->tfm); u64 bits; - unsigned int n, mbl_offset; + unsigned int n; + int mbl_offset; n = ctx->count % bsize; bits = ctx->count * 8; - mbl_offset = s390_crypto_shash_parmsize(ctx->func) / sizeof(u32); + mbl_offset = s390_crypto_shash_parmsize(ctx->func); if (mbl_offset < 0) return -EINVAL; + mbl_offset = mbl_offset / sizeof(u32); + /* set total msg bit length (mbl) in CPACF parmblock */ switch (ctx->func) { case CPACF_KLMD_SHA_1: diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h index c2cf7bcdef9b..1c8a38f762a3 100644 --- a/arch/s390/include/asm/alternative.h +++ b/arch/s390/include/asm/alternative.h @@ -139,10 +139,10 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end); * without volatile and memory clobber. */ #define alternative(oldinstr, altinstr, facility) \ - asm volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory") + asm_inline volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory") #define alternative_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \ - asm volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1, \ + asm_inline volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1, \ altinstr2, facility2) ::: "memory") #endif /* __ASSEMBLY__ */ diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h index d3f09526ee19..61467b9eecc7 100644 --- a/arch/s390/include/asm/atomic_ops.h +++ b/arch/s390/include/asm/atomic_ops.h @@ -41,7 +41,7 @@ __ATOMIC_OPS(__atomic64_xor, long, "laxg") #undef __ATOMIC_OP #define __ATOMIC_CONST_OP(op_name, op_type, op_string, op_barrier) \ -static inline void op_name(op_type val, op_type *ptr) \ +static __always_inline void op_name(op_type val, op_type *ptr) \ { \ asm volatile( \ op_string " %[ptr],%[val]\n" \ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index b8833ac983fa..eb7eed43e780 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -56,7 +56,7 @@ __bitops_byte(unsigned long nr, volatile unsigned long *ptr) return ((unsigned char *)ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3); } -static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) +static __always_inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -77,7 +77,7 @@ static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_or(mask, (long *)addr); } -static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) +static __always_inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; @@ -98,8 +98,8 @@ static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) __atomic64_and(mask, (long *)addr); } -static inline void arch_change_bit(unsigned long nr, - volatile unsigned long *ptr) +static __always_inline void arch_change_bit(unsigned long nr, + volatile unsigned long *ptr) { unsigned long *addr = __bitops_word(nr, ptr); unsigned long mask; diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index 713fc9735ffb..a2b11ac00f60 100644 --- a/arch/s390/include/asm/bug.h +++ b/arch/s390/include/asm/bug.h @@ -9,7 +9,7 @@ #ifdef CONFIG_DEBUG_BUGVERBOSE #define __EMIT_BUG(x) do { \ - asm volatile( \ + asm_inline volatile( \ "0: j 0b+2\n" \ "1:\n" \ ".section .rodata.str,\"aMS\",@progbits,1\n" \ @@ -28,7 +28,7 @@ #else /* CONFIG_DEBUG_BUGVERBOSE */ #define __EMIT_BUG(x) do { \ - asm volatile( \ + asm_inline volatile( \ "0: j 0b+2\n" \ "1:\n" \ ".section __bug_table,\"awM\",@progbits,%1\n" \ diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h index a092f63aac6a..c0f3bfeddcbe 100644 --- a/arch/s390/include/asm/cpacf.h +++ b/arch/s390/include/asm/cpacf.h @@ -171,7 +171,7 @@ typedef struct { unsigned char bytes[16]; } cpacf_mask_t; * * Returns 1 if @func is available for @opcode, 0 otherwise */ -static inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) +static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask) { register unsigned long r0 asm("0") = 0; /* query function */ register unsigned long r1 asm("1") = (unsigned long) mask; diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index ceeb552d3472..819803a97c2b 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -28,6 +28,8 @@ asm(".include \"asm/cpu_mf-insn.h\"\n"); CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA| \ CPU_MF_INT_SF_LSDA) +#define CPU_MF_SF_RIBM_NOTAV 0x1 /* Sampling unavailable */ + /* CPU measurement facility support */ static inline int cpum_cf_avail(void) { @@ -69,7 +71,8 @@ struct hws_qsi_info_block { /* Bit(s) */ unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/ unsigned long tear; /* 24-31: TEAR contents */ unsigned long dear; /* 32-39: DEAR contents */ - unsigned int rsvrd0; /* 40-43: reserved */ + unsigned int rsvrd0:24; /* 40-42: reserved */ + unsigned int ribm:8; /* 43: Reserved by IBM */ unsigned int cpu_speed; /* 44-47: CPU speed */ unsigned long long rsvrd1; /* 48-55: reserved */ unsigned long long rsvrd2; /* 56-63: reserved */ @@ -220,7 +223,8 @@ enum stcctm_ctr_set { MT_DIAG = 5, MT_DIAG_CLEARING = 9, /* clears loss-of-MT-ctr-data alert */ }; -static inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest) + +static __always_inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest) { int cc; diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h index 60f907516335..ed5efbb531c4 100644 --- a/arch/s390/include/asm/ctl_reg.h +++ b/arch/s390/include/asm/ctl_reg.h @@ -11,6 +11,7 @@ #include <linux/bits.h> #define CR0_CLOCK_COMPARATOR_SIGN BIT(63 - 10) +#define CR0_LOW_ADDRESS_PROTECTION BIT(63 - 35) #define CR0_EMERGENCY_SIGNAL_SUBMASK BIT(63 - 49) #define CR0_EXTERNAL_CALL_SUBMASK BIT(63 - 50) #define CR0_CLOCK_COMPARATOR_SUBMASK BIT(63 - 52) diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index bb59dd964590..de8f0bf5f238 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -12,8 +12,6 @@ #include <asm/page.h> #include <asm/pgtable.h> - -#define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range free_pgd_range #define hugepages_supported() (MACHINE_HAS_EDAT1) @@ -23,6 +21,13 @@ pte_t huge_ptep_get(pte_t *ptep); pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +static inline bool is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, + unsigned long len) +{ + return false; +} + /* * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h index e548ec1ec12c..39f747d63758 100644 --- a/arch/s390/include/asm/jump_label.h +++ b/arch/s390/include/asm/jump_label.h @@ -20,7 +20,7 @@ * We use a brcl 0,2 instruction for jump labels at compile time so it * can be easily distinguished from a hotpatch generated instruction. */ -static inline bool arch_static_branch(struct static_key *key, bool branch) +static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("0: brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n" ".pushsection __jump_table,\"aw\"\n" @@ -34,7 +34,7 @@ label: return true; } -static inline bool arch_static_branch_jump(struct static_key *key, bool branch) +static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { asm_volatile_goto("0: brcl 15,%l[label]\n" ".pushsection __jump_table,\"aw\"\n" diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 823578c6b9e2..a4d38092530a 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -177,8 +177,6 @@ static inline int devmem_is_allowed(unsigned long pfn) #define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) -#define ARCH_ZONE_DMA_BITS 31 - #include <asm-generic/memory_model.h> #include <asm-generic/getorder.h> diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index bccb8f4a63e2..77606c4acd58 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -56,7 +56,12 @@ static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long address) crst_table_init(table, _REGION2_ENTRY_EMPTY); return (p4d_t *) table; } -#define p4d_free(mm, p4d) crst_table_free(mm, (unsigned long *) p4d) + +static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) +{ + if (!mm_p4d_folded(mm)) + crst_table_free(mm, (unsigned long *) p4d); +} static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { @@ -65,7 +70,12 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) crst_table_init(table, _REGION3_ENTRY_EMPTY); return (pud_t *) table; } -#define pud_free(mm, pud) crst_table_free(mm, (unsigned long *) pud) + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + if (!mm_pud_folded(mm)) + crst_table_free(mm, (unsigned long *) pud); +} static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) { @@ -83,6 +93,8 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr) static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { + if (mm_pmd_folded(mm)) + return; pgtable_pmd_page_dtor(virt_to_page(pmd)); crst_table_free(mm, (unsigned long *) pmd); } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 36c578c0ff96..7b03037a8475 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -266,11 +266,9 @@ static inline int is_module_addr(void *addr) #endif #define _REGION_ENTRY_BITS 0xfffffffffffff22fUL -#define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL /* Bits in the segment table entry */ #define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL -#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL #define _SEGMENT_ENTRY_HARDWARE_BITS 0xfffffffffffffe30UL #define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE 0xfffffffffff00730UL #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address */ @@ -699,10 +697,8 @@ static inline int pmd_large(pmd_t pmd) static inline int pmd_bad(pmd_t pmd) { - if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0) + if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0 || pmd_large(pmd)) return 1; - if (pmd_large(pmd)) - return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0; return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0; } @@ -710,12 +706,10 @@ static inline int pud_bad(pud_t pud) { unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK; - if (type > _REGION_ENTRY_TYPE_R3) + if (type > _REGION_ENTRY_TYPE_R3 || pud_large(pud)) return 1; if (type < _REGION_ENTRY_TYPE_R3) return 0; - if (pud_large(pud)) - return (pud_val(pud) & ~_REGION_ENTRY_BITS_LARGE) != 0; return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0; } @@ -758,18 +752,12 @@ static inline int pmd_write(pmd_t pmd) static inline int pmd_dirty(pmd_t pmd) { - int dirty = 1; - if (pmd_large(pmd)) - dirty = (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0; - return dirty; + return (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0; } static inline int pmd_young(pmd_t pmd) { - int young = 1; - if (pmd_large(pmd)) - young = (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0; - return young; + return (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0; } static inline int pte_present(pte_t pte) @@ -997,9 +985,9 @@ static inline pte_t pte_mkhuge(pte_t pte) #define IPTE_NODAT 0x400 #define IPTE_GUEST_ASCE 0x800 -static inline void __ptep_ipte(unsigned long address, pte_t *ptep, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __ptep_ipte(unsigned long address, pte_t *ptep, + unsigned long opt, unsigned long asce, + int local) { unsigned long pto = (unsigned long) ptep; @@ -1020,8 +1008,8 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep, : [r1] "a" (pto), [m4] "i" (local) : "memory"); } -static inline void __ptep_ipte_range(unsigned long address, int nr, - pte_t *ptep, int local) +static __always_inline void __ptep_ipte_range(unsigned long address, int nr, + pte_t *ptep, int local) { unsigned long pto = (unsigned long) ptep; @@ -1173,8 +1161,6 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { - if (!MACHINE_HAS_NX) - pte_val(entry) &= ~_PAGE_NOEXEC; if (pte_present(entry)) pte_val(entry) &= ~_PAGE_UNUSED; if (mm_has_pgste(mm)) @@ -1191,6 +1177,8 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) { pte_t __pte; pte_val(__pte) = physpage + pgprot_val(pgprot); + if (!MACHINE_HAS_NX) + pte_val(__pte) &= ~_PAGE_NOEXEC; return pte_mkyoung(__pte); } @@ -1269,7 +1257,8 @@ static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address) #define pte_offset_kernel(pmd, address) pte_offset(pmd, address) #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address) -#define pte_unmap(pte) do { } while (0) + +static inline void pte_unmap(pte_t *pte) { } static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { @@ -1296,29 +1285,23 @@ static inline pmd_t pmd_wrprotect(pmd_t pmd) static inline pmd_t pmd_mkwrite(pmd_t pmd) { pmd_val(pmd) |= _SEGMENT_ENTRY_WRITE; - if (pmd_large(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) - return pmd; - pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; + if (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; return pmd; } static inline pmd_t pmd_mkclean(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY; - pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; - } + pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY; + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; return pmd; } static inline pmd_t pmd_mkdirty(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY | - _SEGMENT_ENTRY_SOFT_DIRTY; - if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) - pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; - } + pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_SOFT_DIRTY; + if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; return pmd; } @@ -1332,29 +1315,23 @@ static inline pud_t pud_wrprotect(pud_t pud) static inline pud_t pud_mkwrite(pud_t pud) { pud_val(pud) |= _REGION3_ENTRY_WRITE; - if (pud_large(pud) && !(pud_val(pud) & _REGION3_ENTRY_DIRTY)) - return pud; - pud_val(pud) &= ~_REGION_ENTRY_PROTECT; + if (pud_val(pud) & _REGION3_ENTRY_DIRTY) + pud_val(pud) &= ~_REGION_ENTRY_PROTECT; return pud; } static inline pud_t pud_mkclean(pud_t pud) { - if (pud_large(pud)) { - pud_val(pud) &= ~_REGION3_ENTRY_DIRTY; - pud_val(pud) |= _REGION_ENTRY_PROTECT; - } + pud_val(pud) &= ~_REGION3_ENTRY_DIRTY; + pud_val(pud) |= _REGION_ENTRY_PROTECT; return pud; } static inline pud_t pud_mkdirty(pud_t pud) { - if (pud_large(pud)) { - pud_val(pud) |= _REGION3_ENTRY_DIRTY | - _REGION3_ENTRY_SOFT_DIRTY; - if (pud_val(pud) & _REGION3_ENTRY_WRITE) - pud_val(pud) &= ~_REGION_ENTRY_PROTECT; - } + pud_val(pud) |= _REGION3_ENTRY_DIRTY | _REGION3_ENTRY_SOFT_DIRTY; + if (pud_val(pud) & _REGION3_ENTRY_WRITE) + pud_val(pud) &= ~_REGION_ENTRY_PROTECT; return pud; } @@ -1378,38 +1355,29 @@ static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot) static inline pmd_t pmd_mkyoung(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; - if (pmd_val(pmd) & _SEGMENT_ENTRY_READ) - pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID; - } + pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; + if (pmd_val(pmd) & _SEGMENT_ENTRY_READ) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID; return pmd; } static inline pmd_t pmd_mkold(pmd_t pmd) { - if (pmd_large(pmd)) { - pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG; - pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; - } + pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG; + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; return pmd; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - if (pmd_large(pmd)) { - pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE | - _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG | - _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY; - pmd_val(pmd) |= massage_pgprot_pmd(newprot); - if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) - pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; - if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG)) - pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; - return pmd; - } - pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN; + pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE | + _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG | + _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY; pmd_val(pmd) |= massage_pgprot_pmd(newprot); + if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; + if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG)) + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; return pmd; } @@ -1435,9 +1403,9 @@ static inline void __pmdp_csp(pmd_t *pmdp) #define IDTE_NODAT 0x1000 #define IDTE_GUEST_ASCE 0x2000 -static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, + unsigned long opt, unsigned long asce, + int local) { unsigned long sto; @@ -1461,9 +1429,9 @@ static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp, } } -static inline void __pudp_idte(unsigned long addr, pud_t *pudp, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __pudp_idte(unsigned long addr, pud_t *pudp, + unsigned long opt, unsigned long asce, + int local) { unsigned long r3o; diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 51a0e4a2dc96..881fc37c11c6 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -206,7 +206,7 @@ unsigned long get_wchan(struct task_struct *p); /* Has task runtime instrumentation enabled ? */ #define is_ri_task(tsk) (!!(tsk)->thread.ri_cb) -static inline unsigned long current_stack_pointer(void) +static __always_inline unsigned long current_stack_pointer(void) { unsigned long sp; diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 78e8a888306d..71e3f0146cda 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -111,7 +111,7 @@ struct qib { /* private: */ u8 res[88]; /* public: */ - u8 parm[QDIO_MAX_BUFFERS_PER_Q]; + u8 parm[128]; } __attribute__ ((packed, aligned(256))); /** @@ -276,6 +276,7 @@ struct qdio_outbuf_state { #define CHSC_AC2_MULTI_BUFFER_AVAILABLE 0x0080 #define CHSC_AC2_MULTI_BUFFER_ENABLED 0x0040 #define CHSC_AC2_DATA_DIV_AVAILABLE 0x0010 +#define CHSC_AC2_SNIFFER_AVAILABLE 0x0008 #define CHSC_AC2_DATA_DIV_ENABLED 0x0002 #define CHSC_AC3_FORMAT2_CQ_AVAILABLE 0x8000 diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index c02bff33f6c7..3a37172d5398 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -85,7 +85,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lp) static inline void arch_spin_unlock(arch_spinlock_t *lp) { typecheck(int, lp->lock); - asm volatile( + asm_inline volatile( ALTERNATIVE("", ".long 0xb2fa0070", 49) /* NIAI 7 */ " sth %1,%0\n" : "=Q" (((unsigned short *) &lp->lock)[1]) diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 0ae4bbf7779c..fee40212af11 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -38,7 +38,7 @@ static inline unsigned long get_stack_pointer(struct task_struct *task, { if (regs) return (unsigned long) kernel_stack_pointer(regs); - if (task == current) + if (!task || task == current) return current_stack_pointer(); return (unsigned long) task->thread.ksp; } diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 64539c221672..6da8885251d6 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -10,8 +10,9 @@ #ifndef _ASM_S390_TIMEX_H #define _ASM_S390_TIMEX_H -#include <asm/lowcore.h> +#include <linux/preempt.h> #include <linux/time64.h> +#include <asm/lowcore.h> /* The value of the TOD clock for 1.1.1970. */ #define TOD_UNIX_EPOCH 0x7d91048bca000000ULL @@ -179,22 +180,24 @@ static inline cycles_t get_cycles(void) int get_phys_clock(unsigned long *clock); void init_cpu_timer(void); -unsigned long long monotonic_clock(void); extern unsigned char tod_clock_base[16] __aligned(8); /** * get_clock_monotonic - returns current time in clock rate units * - * The caller must ensure that preemption is disabled. * The clock and tod_clock_base get changed via stop_machine. - * Therefore preemption must be disabled when calling this - * function, otherwise the returned value is not guaranteed to - * be monotonic. + * Therefore preemption must be disabled, otherwise the returned + * value is not guaranteed to be monotonic. */ static inline unsigned long long get_tod_clock_monotonic(void) { - return get_tod_clock() - *(unsigned long long *) &tod_clock_base[1]; + unsigned long long tod; + + preempt_disable(); + tod = get_tod_clock() - *(unsigned long long *) &tod_clock_base[1]; + preempt_enable(); + return tod; } /** diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index bd2fd9a7821d..a470f1fa9f2a 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -83,7 +83,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n); __rc; \ }) -static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) +static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) { unsigned long spec = 0x010000UL; int rc; @@ -113,7 +113,7 @@ static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) return rc; } -static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size) +static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size) { unsigned long spec = 0x01UL; int rc; diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h index d827b5b9a32c..eaaefeceef6f 100644 --- a/arch/s390/include/asm/unwind.h +++ b/arch/s390/include/asm/unwind.h @@ -35,6 +35,7 @@ struct unwind_state { struct task_struct *task; struct pt_regs *regs; unsigned long sp, ip; + bool reuse_sp; int graph_idx; bool reliable; bool error; diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 7abe6ae261b4..f304802ecf7b 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -461,10 +461,11 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr) ptr += sprintf(ptr, "%%c%i", value); else if (operand->flags & OPERAND_VR) ptr += sprintf(ptr, "%%v%i", value); - else if (operand->flags & OPERAND_PCREL) - ptr += sprintf(ptr, "%lx", (signed int) value - + addr); - else if (operand->flags & OPERAND_SIGNED) + else if (operand->flags & OPERAND_PCREL) { + void *pcrel = (void *)((int)value + addr); + + ptr += sprintf(ptr, "%px", pcrel); + } else if (operand->flags & OPERAND_SIGNED) ptr += sprintf(ptr, "%i", value); else ptr += sprintf(ptr, "%u", value); @@ -536,7 +537,7 @@ void show_code(struct pt_regs *regs) else *ptr++ = ' '; addr = regs->psw.addr + start - 32; - ptr += sprintf(ptr, "%016lx: ", addr); + ptr += sprintf(ptr, "%px: ", (void *)addr); if (start + opsize >= end) break; for (i = 0; i < opsize; i++) @@ -564,7 +565,7 @@ void print_fn_code(unsigned char *code, unsigned long len) opsize = insn_length(*code); if (opsize > len) break; - ptr += sprintf(ptr, "%p: ", code); + ptr += sprintf(ptr, "%px: ", code); for (i = 0; i < opsize; i++) ptr += sprintf(ptr, "%02x", code[i]); *ptr++ = '\t'; diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index b432d63d0b37..db32a55daaec 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -30,6 +30,7 @@ #include <asm/sclp.h> #include <asm/facility.h> #include <asm/boot_data.h> +#include <asm/switch_to.h> #include "entry.h" static void __init reset_tod_clock(void) @@ -238,7 +239,7 @@ static __init void detect_machine_facilities(void) S390_lowcore.machine_flags |= MACHINE_FLAG_VX; __ctl_set_bit(0, 17); } - if (test_facility(130)) { + if (test_facility(130) && !noexec_disabled) { S390_lowcore.machine_flags |= MACHINE_FLAG_NX; __ctl_set_bit(0, 20); } @@ -260,6 +261,24 @@ static inline void save_vector_registers(void) #endif } +static inline void setup_control_registers(void) +{ + unsigned long reg; + + __ctl_store(reg, 0, 0); + reg |= CR0_LOW_ADDRESS_PROTECTION; + reg |= CR0_EMERGENCY_SIGNAL_SUBMASK; + reg |= CR0_EXTERNAL_CALL_SUBMASK; + __ctl_load(reg, 0, 0); +} + +static inline void setup_access_registers(void) +{ + unsigned int acrs[NUM_ACRS] = { 0 }; + + restore_access_regs(acrs); +} + static int __init disable_vector_extension(char *str) { S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX; @@ -268,21 +287,6 @@ static int __init disable_vector_extension(char *str) } early_param("novx", disable_vector_extension); -static int __init noexec_setup(char *str) -{ - bool enabled; - int rc; - - rc = kstrtobool(str, &enabled); - if (!rc && !enabled) { - /* Disable no-execute support */ - S390_lowcore.machine_flags &= ~MACHINE_FLAG_NX; - __ctl_clear_bit(0, 20); - } - return rc; -} -early_param("noexec", noexec_setup); - static int __init cad_setup(char *str) { bool enabled; @@ -332,5 +336,7 @@ void __init startup_init(void) save_vector_registers(); setup_topology(); sclp_early_detect(); + setup_control_registers(); + setup_access_registers(); lockdep_on(); } diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 0d9ee198f4eb..b9e585f528a6 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -26,8 +26,6 @@ ENTRY(startup_continue) 0: larl %r1,tod_clock_base mvc 0(16,%r1),__LC_BOOT_CLOCK larl %r13,.LPG1 # get base - larl %r0,boot_vdso_data - stg %r0,__LC_VDSO_PER_CPU # # Setup stack # @@ -37,19 +35,8 @@ ENTRY(startup_continue) #ifdef CONFIG_KASAN brasl %r14,kasan_early_init #endif -# -# Early machine initialization and detection functions. -# - brasl %r14,startup_init - -# check control registers - stctg %c0,%c15,0(%r15) - oi 6(%r15),0x60 # enable sigp emergency & external call - oi 4(%r15),0x10 # switch on low address proctection - lctlg %c0,%c15,0(%r15) - - lam 0,15,.Laregs-.LPG1(%r13) # load acrs needed by uaccess - brasl %r14,start_kernel # go to C code + brasl %r14,startup_init # s390 specific early init + brasl %r14,start_kernel # common init code # # We returned from start_kernel ?!? PANIK # @@ -59,4 +46,3 @@ ENTRY(startup_continue) .align 16 .LPG1: .Ldw: .quad 0x0002000180000000,0x0000000000000000 -.Laregs:.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index b9d8fe45737a..8f8456816d83 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -69,18 +69,26 @@ DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL); static ssize_t show_idle_time(struct device *dev, struct device_attribute *attr, char *buf) { + unsigned long long now, idle_time, idle_enter, idle_exit, in_idle; struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id); - unsigned long long now, idle_time, idle_enter, idle_exit; unsigned int seq; do { - now = get_tod_clock(); seq = read_seqcount_begin(&idle->seqcount); idle_time = READ_ONCE(idle->idle_time); idle_enter = READ_ONCE(idle->clock_idle_enter); idle_exit = READ_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; + in_idle = 0; + now = get_tod_clock(); + if (idle_enter) { + if (idle_exit) { + in_idle = idle_exit - idle_enter; + } else if (now > idle_enter) { + in_idle = now - idle_enter; + } + } + idle_time += in_idle; return sprintf(buf, "%llu\n", idle_time >> 12); } DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); @@ -88,17 +96,24 @@ DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); u64 arch_cpu_idle_time(int cpu) { struct s390_idle_data *idle = &per_cpu(s390_idle, cpu); - unsigned long long now, idle_enter, idle_exit; + unsigned long long now, idle_enter, idle_exit, in_idle; unsigned int seq; do { - now = get_tod_clock(); seq = read_seqcount_begin(&idle->seqcount); idle_enter = READ_ONCE(idle->clock_idle_enter); idle_exit = READ_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - - return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0); + in_idle = 0; + now = get_tod_clock(); + if (idle_enter) { + if (idle_exit) { + in_idle = idle_exit - idle_enter; + } else if (now > idle_enter) { + in_idle = now - idle_enter; + } + } + return cputime_to_nsecs(in_idle); } void arch_cpu_idle_enter(void) diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c index 3b664cb3ec4d..d5035de9020e 100644 --- a/arch/s390/kernel/machine_kexec_reloc.c +++ b/arch/s390/kernel/machine_kexec_reloc.c @@ -27,6 +27,7 @@ int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val, *(u32 *)loc = val; break; case R_390_64: /* Direct 64 bit. */ + case R_390_GLOB_DAT: *(u64 *)loc = val; break; case R_390_PC16: /* PC relative 16 bit. */ diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 48d48b6187c0..0eb1d1cc53a8 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -199,7 +199,7 @@ static const int cpumf_generic_events_user[] = { [PERF_COUNT_HW_BUS_CYCLES] = -1, }; -static int __hw_perf_event_init(struct perf_event *event) +static int __hw_perf_event_init(struct perf_event *event, unsigned int type) { struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; @@ -207,7 +207,7 @@ static int __hw_perf_event_init(struct perf_event *event) int err = 0; u64 ev; - switch (attr->type) { + switch (type) { case PERF_TYPE_RAW: /* Raw events are used to access counters directly, * hence do not permit excludes */ @@ -294,17 +294,16 @@ static int __hw_perf_event_init(struct perf_event *event) static int cpumf_pmu_event_init(struct perf_event *event) { + unsigned int type = event->attr.type; int err; - switch (event->attr.type) { - case PERF_TYPE_HARDWARE: - case PERF_TYPE_HW_CACHE: - case PERF_TYPE_RAW: - err = __hw_perf_event_init(event); - break; - default: + if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW) + err = __hw_perf_event_init(event, type); + else if (event->pmu->type == type) + /* Registered as unknown PMU */ + err = __hw_perf_event_init(event, PERF_TYPE_RAW); + else return -ENOENT; - } if (unlikely(err) && event->destroy) event->destroy(event); @@ -553,7 +552,7 @@ static int __init cpumf_pmu_init(void) return -ENODEV; cpumf_pmu.attr_groups = cpumf_cf_event_group(); - rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW); + rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", -1); if (rc) pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc); return rc; diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c index 5f1fd1581330..e949ab832ed7 100644 --- a/arch/s390/kernel/perf_cpum_cf_diag.c +++ b/arch/s390/kernel/perf_cpum_cf_diag.c @@ -243,13 +243,13 @@ static int cf_diag_event_init(struct perf_event *event) int err = -ENOENT; debug_sprintf_event(cf_diag_dbg, 5, - "%s event %p cpu %d config %#llx " + "%s event %p cpu %d config %#llx type:%u " "sample_type %#llx cf_diag_events %d\n", __func__, - event, event->cpu, attr->config, attr->sample_type, - atomic_read(&cf_diag_events)); + event, event->cpu, attr->config, event->pmu->type, + attr->sample_type, atomic_read(&cf_diag_events)); if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG || - event->attr.type != PERF_TYPE_RAW) + event->attr.type != event->pmu->type) goto out; /* Raw events are used to access counters directly, @@ -390,7 +390,7 @@ static size_t cf_diag_getctrset(struct cf_ctrset_entry *ctrdata, int ctrset, debug_sprintf_event(cf_diag_dbg, 6, "%s ctrset %d ctrset_size %zu cfvn %d csvn %d" - " need %zd rc:%d\n", + " need %zd rc %d\n", __func__, ctrset, ctrset_size, cpuhw->info.cfvn, cpuhw->info.csvn, need, rc); return need; @@ -567,7 +567,7 @@ static int cf_diag_add(struct perf_event *event, int flags) int err = 0; debug_sprintf_event(cf_diag_dbg, 5, - "%s event %p cpu %d flags %#x cpuhw:%p\n", + "%s event %p cpu %d flags %#x cpuhw %p\n", __func__, event, event->cpu, flags, cpuhw); if (cpuhw->flags & PMU_F_IN_USE) { @@ -693,7 +693,7 @@ static int __init cf_diag_init(void) } debug_register_view(cf_diag_dbg, &debug_sprintf_view); - rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW); + rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1); if (rc) { debug_unregister_view(cf_diag_dbg, &debug_sprintf_view); debug_unregister(cf_diag_dbg); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 544a02e944c6..69506fdbd9a1 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -156,8 +156,8 @@ static void free_sampling_buffer(struct sf_buffer *sfb) } } - debug_sprintf_event(sfdbg, 5, - "free_sampling_buffer: freed sdbt=%p\n", sfb->sdbt); + debug_sprintf_event(sfdbg, 5, "%s freed sdbt %p\n", __func__, + sfb->sdbt); memset(sfb, 0, sizeof(*sfb)); } @@ -212,10 +212,10 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb, * the sampling buffer origin. */ if (sfb->sdbt != get_next_sdbt(tail)) { - debug_sprintf_event(sfdbg, 3, "realloc_sampling_buffer: " - "sampling buffer is not linked: origin=%p" - "tail=%p\n", - (void *) sfb->sdbt, (void *) tail); + debug_sprintf_event(sfdbg, 3, "%s: " + "sampling buffer is not linked: origin %p" + " tail %p\n", __func__, + (void *)sfb->sdbt, (void *)tail); return -EINVAL; } @@ -252,7 +252,7 @@ static int realloc_sampling_buffer(struct sf_buffer *sfb, sfb->tail = tail; debug_sprintf_event(sfdbg, 4, "realloc_sampling_buffer: new buffer" - " settings: sdbt=%lu sdb=%lu\n", + " settings: sdbt %lu sdb %lu\n", sfb->num_sdbt, sfb->num_sdb); return rc; } @@ -293,11 +293,11 @@ static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb) if (rc) { free_sampling_buffer(sfb); debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: " - "realloc_sampling_buffer failed with rc=%i\n", rc); + "realloc_sampling_buffer failed with rc %i\n", rc); } else debug_sprintf_event(sfdbg, 4, - "alloc_sampling_buffer: tear=%p dear=%p\n", - sfb->sdbt, (void *) *sfb->sdbt); + "alloc_sampling_buffer: tear %p dear %p\n", + sfb->sdbt, (void *)*sfb->sdbt); return rc; } @@ -404,8 +404,8 @@ static int allocate_buffers(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc) return 0; debug_sprintf_event(sfdbg, 3, - "allocate_buffers: rate=%lu f=%lu sdb=%lu/%lu" - " sample_size=%lu cpuhw=%p\n", + "%s: rate %lu f %lu sdb %lu/%lu" + " sample_size %lu cpuhw %p\n", __func__, SAMPL_RATE(hwc), freq, n_sdb, sfb_max_limit(hwc), sample_size, cpuhw); @@ -465,8 +465,8 @@ static void sfb_account_overflows(struct cpu_hw_sf *cpuhw, if (num) sfb_account_allocs(num, hwc); - debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow=%llu ratio=%lu" - " num=%lu\n", OVERFLOW_REG(hwc), ratio, num); + debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow %llu ratio %lu" + " num %lu\n", OVERFLOW_REG(hwc), ratio, num); OVERFLOW_REG(hwc) = 0; } @@ -505,11 +505,11 @@ static void extend_sampling_buffer(struct sf_buffer *sfb, rc = realloc_sampling_buffer(sfb, num, GFP_ATOMIC); if (rc) debug_sprintf_event(sfdbg, 5, "sfb: extend: realloc " - "failed with rc=%i\n", rc); + "failed with rc %i\n", rc); if (sfb_has_pending_allocs(sfb, hwc)) debug_sprintf_event(sfdbg, 5, "sfb: extend: " - "req=%lu alloc=%lu remaining=%lu\n", + "req %lu alloc %lu remaining %lu\n", num, sfb->num_sdb - num_old, sfb_pending_allocs(sfb, hwc)); } @@ -538,20 +538,22 @@ static void setup_pmc_cpu(void *flags) err = sf_disable(); if (err) pr_err("Switching off the sampling facility failed " - "with rc=%i\n", err); + "with rc %i\n", err); debug_sprintf_event(sfdbg, 5, - "setup_pmc_cpu: initialized: cpuhw=%p\n", cpusf); + "%s: initialized: cpuhw %p\n", __func__, + cpusf); break; case PMC_RELEASE: cpusf->flags &= ~PMU_F_RESERVED; err = sf_disable(); if (err) { pr_err("Switching off the sampling facility failed " - "with rc=%i\n", err); + "with rc %i\n", err); } else deallocate_buffers(cpusf); debug_sprintf_event(sfdbg, 5, - "setup_pmc_cpu: released: cpuhw=%p\n", cpusf); + "%s: released: cpuhw %p\n", __func__, + cpusf); break; } if (err) @@ -744,7 +746,7 @@ static int __hw_perf_event_init_rate(struct perf_event *event, SAMPL_RATE(hwc) = rate; hw_init_period(hwc, SAMPL_RATE(hwc)); debug_sprintf_event(sfdbg, 4, "__hw_perf_event_init_rate:" - "cpu:%d period:%llx freq:%d,%#lx\n", event->cpu, + "cpu:%d period:%#llx freq:%d,%#lx\n", event->cpu, event->attr.sample_period, event->attr.freq, SAMPLE_FREQ_MODE(hwc)); return 0; @@ -803,6 +805,12 @@ static int __hw_perf_event_init(struct perf_event *event) goto out; } + if (si.ribm & CPU_MF_SF_RIBM_NOTAV) { + pr_warn("CPU Measurement Facility sampling is temporarily not available\n"); + err = -EBUSY; + goto out; + } + /* Always enable basic sampling */ SAMPL_FLAGS(hwc) = PERF_CPUM_SF_BASIC_MODE; @@ -895,7 +903,7 @@ static int cpumsf_pmu_event_init(struct perf_event *event) /* Check online status of the CPU to which the event is pinned */ if (event->cpu >= 0 && !cpu_online(event->cpu)) - return -ENODEV; + return -ENODEV; /* Force reset of idle/hv excludes regardless of what the * user requested. @@ -957,7 +965,7 @@ static void cpumsf_pmu_enable(struct pmu *pmu) err = lsctl(&cpuhw->lsctl); if (err) { cpuhw->flags &= ~PMU_F_ENABLED; - pr_err("Loading sampling controls failed: op=%i err=%i\n", + pr_err("Loading sampling controls failed: op %i err %i\n", 1, err); return; } @@ -965,8 +973,8 @@ static void cpumsf_pmu_enable(struct pmu *pmu) /* Load current program parameter */ lpp(&S390_lowcore.lpp); - debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i " - "interval:%lx tear=%p dear=%p\n", + debug_sprintf_event(sfdbg, 6, "pmu_enable: es %i cs %i ed %i cd %i " + "interval %#lx tear %p dear %p\n", cpuhw->lsctl.es, cpuhw->lsctl.cs, cpuhw->lsctl.ed, cpuhw->lsctl.cd, cpuhw->lsctl.interval, (void *) cpuhw->lsctl.tear, @@ -993,13 +1001,14 @@ static void cpumsf_pmu_disable(struct pmu *pmu) err = lsctl(&inactive); if (err) { - pr_err("Loading sampling controls failed: op=%i err=%i\n", + pr_err("Loading sampling controls failed: op %i err %i\n", 2, err); return; } /* Save state of TEAR and DEAR register contents */ - if (!qsi(&si)) { + err = qsi(&si); + if (!err) { /* TEAR/DEAR values are valid only if the sampling facility is * enabled. Note that cpumsf_pmu_disable() might be called even * for a disabled sampling facility because cpumsf_pmu_enable() @@ -1011,7 +1020,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu) } } else debug_sprintf_event(sfdbg, 3, "cpumsf_pmu_disable: " - "qsi() failed with err=%i\n", err); + "qsi() failed with err %i\n", err); cpuhw->flags &= ~PMU_F_ENABLED; } @@ -1124,15 +1133,6 @@ static void perf_event_count_update(struct perf_event *event, u64 count) local64_add(count, &event->count); } -static void debug_sample_entry(struct hws_basic_entry *sample, - struct hws_trailer_entry *te) -{ - debug_sprintf_event(sfdbg, 4, "hw_collect_samples: Found unknown " - "sampling data entry: te->f=%i basic.def=%04x " - "(%p)\n", - te->f, sample->def, sample); -} - /* hw_collect_samples() - Walk through a sample-data-block and collect samples * @event: The perf event * @sdbt: Sample-data-block table @@ -1186,7 +1186,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, /* Count discarded samples */ *overflow += 1; } else { - debug_sample_entry(sample, te); + debug_sprintf_event(sfdbg, 4, + "%s: Found unknown" + " sampling data entry: te->f %i" + " basic.def %#4x (%p)\n", __func__, + te->f, sample->def, sample); /* Sample slot is not yet written or other record. * * This condition can occur if the buffer was reused @@ -1261,9 +1265,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) sampl_overflow += te->overflow; /* Timestamps are valid for full sample-data-blocks only */ - debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p " - "overflow=%llu timestamp=%#llx\n", - sdbt, te->overflow, + debug_sprintf_event(sfdbg, 6, "%s: sdbt %p " + "overflow %llu timestamp %#llx\n", + __func__, sdbt, te->overflow, (te->f) ? trailer_timestamp(te) : 0ULL); /* Collect all samples from a single sample-data-block and @@ -1307,9 +1311,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) + sampl_overflow, 1 + num_sdb); if (sampl_overflow || event_overflow) - debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: " - "overflow stats: sample=%llu event=%llu\n", - sampl_overflow, event_overflow); + debug_sprintf_event(sfdbg, 4, "%s: " + "overflow stats: sample %llu event %llu\n", + __func__, sampl_overflow, event_overflow); } #define AUX_SDB_INDEX(aux, i) ((i) % aux->sfb.num_sdb) @@ -1362,7 +1366,7 @@ static void aux_output_end(struct perf_output_handle *handle) te = aux_sdb_trailer(aux, aux->alert_mark); te->flags &= ~SDB_TE_ALERT_REQ_MASK; - debug_sprintf_event(sfdbg, 6, "aux_output_end: collect %lx SDBs\n", i); + debug_sprintf_event(sfdbg, 6, "%s: collect %#lx SDBs\n", __func__, i); } /* @@ -1422,8 +1426,8 @@ static int aux_output_begin(struct perf_output_handle *handle, debug_sprintf_event(sfdbg, 6, "aux_output_begin: " "head->alert_mark->empty_mark (num_alert, range)" - "[%lx -> %lx -> %lx] (%lx, %lx) " - "tear index %lx, tear %lx dear %lx\n", + "[%#lx -> %#lx -> %#lx] (%#lx, %#lx) " + "tear index %#lx, tear %#lx dear %#lx\n", aux->head, aux->alert_mark, aux->empty_mark, AUX_SDB_NUM_ALERT(aux), range, head / CPUM_SF_SDB_PER_TABLE, @@ -1590,13 +1594,13 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) perf_aux_output_end(&cpuhw->handle, size); pr_err("Sample data caused the AUX buffer with %lu " "pages to overflow\n", num_sdb); - debug_sprintf_event(sfdbg, 1, "head %lx range %lx " - "overflow %llx\n", + debug_sprintf_event(sfdbg, 1, "head %#lx range %#lx " + "overflow %#llx\n", aux->head, range, overflow); } else { size = AUX_SDB_NUM_ALERT(aux) << PAGE_SHIFT; perf_aux_output_end(&cpuhw->handle, size); - debug_sprintf_event(sfdbg, 6, "head %lx alert %lx " + debug_sprintf_event(sfdbg, 6, "head %#lx alert %#lx " "already full, try another\n", aux->head, aux->alert_mark); } @@ -1604,7 +1608,7 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) if (done) debug_sprintf_event(sfdbg, 6, "aux_reset_buffer: " - "[%lx -> %lx -> %lx] (%lx, %lx)\n", + "[%#lx -> %#lx -> %#lx] (%#lx, %#lx)\n", aux->head, aux->alert_mark, aux->empty_mark, AUX_SDB_NUM_ALERT(aux), range); } @@ -1794,7 +1798,7 @@ static int cpumsf_pmu_check_period(struct perf_event *event, u64 value) SAMPL_RATE(&event->hw) = rate; hw_init_period(&event->hw, SAMPL_RATE(&event->hw)); debug_sprintf_event(sfdbg, 4, "cpumsf_pmu_check_period:" - "cpu:%d value:%llx period:%llx freq:%d\n", + "cpu:%d value:%#llx period:%#llx freq:%d\n", event->cpu, value, event->attr.sample_period, do_freq); return 0; @@ -2105,7 +2109,7 @@ static int param_set_sfb_size(const char *val, const struct kernel_param *kp) sfb_set_limits(min, max); pr_info("The sampling buffer limits have changed to: " - "min=%lu max=%lu (diag=x%lu)\n", + "min %lu max %lu (diag %lu)\n", CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB, CPUM_SF_SDB_DIAG_FACTOR); return 0; } @@ -2123,7 +2127,7 @@ static const struct kernel_param_ops param_ops_sfb_size = { static void __init pr_cpumsf_err(unsigned int reason) { pr_err("Sampling facility support for perf is not available: " - "reason=%04x\n", reason); + "reason %#x\n", reason); } static int __init init_cpum_sampling_pmu(void) diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index fcb6c2e92b07..1e75cc983546 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -224,9 +224,13 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct unwind_state state; + unsigned long addr; - unwind_for_each_frame(&state, current, regs, 0) - perf_callchain_store(entry, state.ip); + unwind_for_each_frame(&state, current, regs, 0) { + addr = unwind_get_return_address(&state); + if (!addr || perf_callchain_store(entry, addr)) + return; + } } /* Perf definitions for PMU event attributes in sysfs */ diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index b0afec673f77..6ccef5f29761 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -40,6 +40,7 @@ #include <asm/stacktrace.h> #include <asm/switch_to.h> #include <asm/runtime_instr.h> +#include <asm/unwind.h> #include "entry.h" asmlinkage void ret_from_fork(void) asm ("ret_from_fork"); @@ -178,9 +179,8 @@ EXPORT_SYMBOL(dump_fpu); unsigned long get_wchan(struct task_struct *p) { - struct stack_frame *sf, *low, *high; - unsigned long return_address; - int count; + struct unwind_state state; + unsigned long ip = 0; if (!p || p == current || p->state == TASK_RUNNING || !task_stack_page(p)) return 0; @@ -188,26 +188,22 @@ unsigned long get_wchan(struct task_struct *p) if (!try_get_task_stack(p)) return 0; - low = task_stack_page(p); - high = (struct stack_frame *) task_pt_regs(p); - sf = (struct stack_frame *) p->thread.ksp; - if (sf <= low || sf > high) { - return_address = 0; - goto out; - } - for (count = 0; count < 16; count++) { - sf = (struct stack_frame *)READ_ONCE_NOCHECK(sf->back_chain); - if (sf <= low || sf > high) { - return_address = 0; - goto out; + unwind_for_each_frame(&state, p, NULL, 0) { + if (state.stack_info.type != STACK_TYPE_TASK) { + ip = 0; + break; } - return_address = READ_ONCE_NOCHECK(sf->gprs[8]); - if (!in_sched_functions(return_address)) - goto out; + + ip = unwind_get_return_address(&state); + if (!ip) + break; + + if (!in_sched_functions(ip)) + break; } -out: + put_task_stack(p); - return return_address; + return ip; } unsigned long arch_align_stack(unsigned long sp) diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 44974654cbd0..6acdcf1d4074 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -724,39 +724,67 @@ static void __ref smp_get_core_info(struct sclp_core_info *info, int early) static int smp_add_present_cpu(int cpu); -static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add) +static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail, + bool configured, bool early) { struct pcpu *pcpu; - cpumask_t avail; - int cpu, nr, i, j; + int cpu, nr, i; u16 address; nr = 0; - cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask); - cpu = cpumask_first(&avail); - for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) { - if (sclp.has_core_type && info->core[i].type != boot_core_type) + if (sclp.has_core_type && core->type != boot_core_type) + return nr; + cpu = cpumask_first(avail); + address = core->core_id << smp_cpu_mt_shift; + for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) { + if (pcpu_find_address(cpu_present_mask, address + i)) continue; - address = info->core[i].core_id << smp_cpu_mt_shift; - for (j = 0; j <= smp_cpu_mtid; j++) { - if (pcpu_find_address(cpu_present_mask, address + j)) - continue; - pcpu = pcpu_devices + cpu; - pcpu->address = address + j; - pcpu->state = - (cpu >= info->configured*(smp_cpu_mtid + 1)) ? - CPU_STATE_STANDBY : CPU_STATE_CONFIGURED; - smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); - set_cpu_present(cpu, true); - if (sysfs_add && smp_add_present_cpu(cpu) != 0) - set_cpu_present(cpu, false); - else - nr++; - cpu = cpumask_next(cpu, &avail); - if (cpu >= nr_cpu_ids) + pcpu = pcpu_devices + cpu; + pcpu->address = address + i; + if (configured) + pcpu->state = CPU_STATE_CONFIGURED; + else + pcpu->state = CPU_STATE_STANDBY; + smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN); + set_cpu_present(cpu, true); + if (!early && smp_add_present_cpu(cpu) != 0) + set_cpu_present(cpu, false); + else + nr++; + cpumask_clear_cpu(cpu, avail); + cpu = cpumask_next(cpu, avail); + } + return nr; +} + +static int __smp_rescan_cpus(struct sclp_core_info *info, bool early) +{ + struct sclp_core_entry *core; + cpumask_t avail; + bool configured; + u16 core_id; + int nr, i; + + nr = 0; + cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask); + /* + * Add IPL core first (which got logical CPU number 0) to make sure + * that all SMT threads get subsequent logical CPU numbers. + */ + if (early) { + core_id = pcpu_devices[0].address >> smp_cpu_mt_shift; + for (i = 0; i < info->configured; i++) { + core = &info->core[i]; + if (core->core_id == core_id) { + nr += smp_add_core(core, &avail, true, early); break; + } } } + for (i = 0; i < info->combined; i++) { + configured = i < info->configured; + nr += smp_add_core(&info->core[i], &avail, configured, early); + } return nr; } @@ -805,7 +833,7 @@ void __init smp_detect_cpus(void) /* Add CPUs present at boot */ get_online_cpus(); - __smp_rescan_cpus(info, 0); + __smp_rescan_cpus(info, true); put_online_cpus(); memblock_free_early((unsigned long)info, sizeof(*info)); } @@ -1148,7 +1176,7 @@ int __ref smp_rescan_cpus(void) smp_get_core_info(info, 0); get_online_cpus(); mutex_lock(&smp_cpu_state_mutex); - nr = __smp_rescan_cpus(info, 1); + nr = __smp_rescan_cpus(info, false); mutex_unlock(&smp_cpu_state_mutex); put_online_cpus(); kfree(info); diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index e8766beee5ad..f9d070d016e3 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -110,15 +110,6 @@ unsigned long long notrace sched_clock(void) } NOKPROBE_SYMBOL(sched_clock); -/* - * Monotonic_clock - returns # of nanoseconds passed since time_init() - */ -unsigned long long monotonic_clock(void) -{ - return sched_clock(); -} -EXPORT_SYMBOL(monotonic_clock); - static void ext_to_timespec64(unsigned char *clk, struct timespec64 *xt) { unsigned long long high, low, rem, sec, nsec; diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c index 8fc9daae47a2..fa111d3d378f 100644 --- a/arch/s390/kernel/unwind_bc.c +++ b/arch/s390/kernel/unwind_bc.c @@ -46,10 +46,15 @@ bool unwind_next_frame(struct unwind_state *state) regs = state->regs; if (unlikely(regs)) { - sp = READ_ONCE_NOCHECK(regs->gprs[15]); - if (unlikely(outside_of_stack(state, sp))) { - if (!update_stack_info(state, sp)) - goto out_err; + if (state->reuse_sp) { + sp = state->sp; + state->reuse_sp = false; + } else { + sp = READ_ONCE_NOCHECK(regs->gprs[15]); + if (unlikely(outside_of_stack(state, sp))) { + if (!update_stack_info(state, sp)) + goto out_err; + } } sf = (struct stack_frame *) sp; ip = READ_ONCE_NOCHECK(sf->gprs[8]); @@ -80,12 +85,7 @@ bool unwind_next_frame(struct unwind_state *state) } } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* Decode any ftrace redirection */ - if (ip == (unsigned long) return_to_handler) - ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, - ip, (void *) sp); -#endif + ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, (void *) sp); /* Update unwind state */ state->sp = sp; @@ -107,9 +107,9 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, { struct stack_info *info = &state->stack_info; unsigned long *mask = &state->stack_mask; + bool reliable, reuse_sp; struct stack_frame *sf; unsigned long ip; - bool reliable; memset(state, 0, sizeof(*state)); state->task = task; @@ -134,22 +134,20 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, if (regs) { ip = READ_ONCE_NOCHECK(regs->psw.addr); reliable = true; + reuse_sp = true; } else { sf = (struct stack_frame *) sp; ip = READ_ONCE_NOCHECK(sf->gprs[8]); reliable = false; + reuse_sp = false; } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* Decode any ftrace redirection */ - if (ip == (unsigned long) return_to_handler) - ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, - ip, NULL); -#endif + ip = ftrace_graph_ret_addr(state->task, &state->graph_idx, ip, NULL); /* Update unwind state */ state->sp = sp; state->ip = ip; state->reliable = reliable; + state->reuse_sp = reuse_sp; } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f6db0f1bc867..d047e846e1b9 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -332,7 +332,7 @@ static inline int plo_test_bit(unsigned char nr) return cc == 0; } -static inline void __insn32_query(unsigned int opcode, u8 query[32]) +static __always_inline void __insn32_query(unsigned int opcode, u8 *query) { register unsigned long r0 asm("0") = 0; /* query function */ register unsigned long r1 asm("1") = (unsigned long) query; @@ -340,9 +340,9 @@ static inline void __insn32_query(unsigned int opcode, u8 query[32]) asm volatile( /* Parameter regs are ignored */ " .insn rrf,%[opc] << 16,2,4,6,0\n" - : "=m" (*query) + : : "d" (r0), "a" (r1), [opc] "i" (opcode) - : "cc"); + : "cc", "memory"); } #define INSN_SORTL 0xb938 diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index 30a7c8c29964..ce1e4bbe53aa 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -74,7 +74,7 @@ static inline int arch_load_niai4(int *lock) { int owner; - asm volatile( + asm_inline volatile( ALTERNATIVE("", ".long 0xb2fa0040", 49) /* NIAI 4 */ " l %0,%1\n" : "=d" (owner) : "Q" (*lock) : "memory"); @@ -85,7 +85,7 @@ static inline int arch_cmpxchg_niai8(int *lock, int old, int new) { int expected = old; - asm volatile( + asm_inline volatile( ALTERNATIVE("", ".long 0xb2fa0080", 49) /* NIAI 8 */ " cs %0,%3,%1\n" : "=d" (old), "=Q" (*lock) diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 510a18299196..a51c892f14f3 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -298,16 +298,16 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write, } if (write) { - len = *lenp; - if (copy_from_user(buf, buffer, - len > sizeof(buf) ? sizeof(buf) : len)) + len = min(*lenp, sizeof(buf)); + if (copy_from_user(buf, buffer, len)) return -EFAULT; - buf[sizeof(buf) - 1] = '\0'; + buf[len - 1] = '\0'; cmm_skip_blanks(buf, &p); nr = simple_strtoul(p, &p, 0); cmm_skip_blanks(p, &p); seconds = simple_strtoul(p, &p, 0); cmm_set_timeout(nr, seconds); + *ppos += *lenp; } else { len = sprintf(buf, "%ld %ld\n", cmm_timeout_pages, cmm_timeout_seconds); @@ -315,9 +315,9 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write, len = *lenp; if (copy_to_user(buffer, buf, len)) return -EFAULT; + *lenp = len; + *ppos += len; } - *lenp = len; - *ppos += len; return 0; } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index a124f19f7b3c..f0ce22220565 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -118,6 +118,7 @@ void __init paging_init(void) sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); + zone_dma_bits = 31; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS); max_zone_pfns[ZONE_NORMAL] = max_low_pfn; diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 1864a8bb9622..59ad7997fed1 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -70,7 +70,7 @@ void notrace s390_kernel_write(void *dst, const void *src, size_t size) spin_unlock_irqrestore(&s390_kernel_write_lock, flags); } -static int __memcpy_real(void *dest, void *src, size_t count) +static int __no_sanitize_address __memcpy_real(void *dest, void *src, size_t count) { register unsigned long _dest asm("2") = (unsigned long) dest; register unsigned long _len1 asm("3") = (unsigned long) count; @@ -91,19 +91,23 @@ static int __memcpy_real(void *dest, void *src, size_t count) return rc; } -static unsigned long _memcpy_real(unsigned long dest, unsigned long src, - unsigned long count) +static unsigned long __no_sanitize_address _memcpy_real(unsigned long dest, + unsigned long src, + unsigned long count) { int irqs_disabled, rc; unsigned long flags; if (!count) return 0; - flags = __arch_local_irq_stnsm(0xf8UL); + flags = arch_local_irq_save(); irqs_disabled = arch_irqs_disabled_flags(flags); if (!irqs_disabled) trace_hardirqs_off(); + __arch_local_irq_stnsm(0xf8); // disable DAT rc = __memcpy_real((void *) dest, (void *) src, (size_t) count); + if (flags & PSW_MASK_DAT) + __arch_local_irq_stosm(0x04); // enable DAT if (!irqs_disabled) trace_hardirqs_on(); __arch_local_irq_ssm(flags); diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 9bdff4defef1..e585a62d6530 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -66,7 +66,7 @@ static inline int clp_get_ilp(unsigned long *ilp) /* * Call Logical Processor with c=0, the give constant lps and an lpcb request. */ -static inline int clp_req(void *data, unsigned int lps) +static __always_inline int clp_req(void *data, unsigned int lps) { struct { u8 _[CLP_BLK_SIZE]; } *req = data; u64 ignored; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index fbc1aecf0f94..eb24cb1afc11 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -29,7 +29,6 @@ config SPARC select RTC_DRV_M48T59 select RTC_SYSTOHC select HAVE_ARCH_JUMP_LABEL if SPARC64 - select HAVE_FAST_GUP if SPARC64 select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION select GENERIC_PCI_IOMAP diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index 324a23947585..997ffe46e953 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -65,14 +65,14 @@ $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(SPARC_REG_CFLAGS # # vDSO code runs in userspace and -pg doesn't help with profiling anyway. # -CFLAGS_REMOVE_vdso-note.o = -pg CFLAGS_REMOVE_vclock_gettime.o = -pg +CFLAGS_REMOVE_vdso32/vclock_gettime.o = -pg $(obj)/%.so: OBJCOPYFLAGS := -S $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) -CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) +CPPFLAGS_vdso32/vdso32.lds = $(CPPFLAGS_vdso.lds) VDSO_LDFLAGS_vdso32.lds = -m elf32_sparc -soname linux-gate.so.1 #This makes sure the $(obj) subdirectory exists even though vdso32/ diff --git a/arch/um/configs/kunit_defconfig b/arch/um/configs/kunit_defconfig new file mode 100644 index 000000000000..9235b7d42d38 --- /dev/null +++ b/arch/um/configs/kunit_defconfig @@ -0,0 +1,3 @@ +CONFIG_KUNIT=y +CONFIG_KUNIT_TEST=y +CONFIG_KUNIT_EXAMPLE_TEST=y diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 612535cd9706..6627d7c30f37 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1403,8 +1403,12 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, spin_unlock_irq(&ubd_dev->lock); - if (ret < 0) - blk_mq_requeue_request(req, true); + if (ret < 0) { + if (ret == -ENOMEM) + res = BLK_STS_RESOURCE; + else + res = BLK_STS_DEV_RESOURCE; + } return res; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d6e1faa28c58..8ef85139553f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1940,6 +1940,51 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS If unsure, say y. +choice + prompt "TSX enable mode" + depends on CPU_SUP_INTEL + default X86_INTEL_TSX_MODE_OFF + help + Intel's TSX (Transactional Synchronization Extensions) feature + allows to optimize locking protocols through lock elision which + can lead to a noticeable performance boost. + + On the other hand it has been shown that TSX can be exploited + to form side channel attacks (e.g. TAA) and chances are there + will be more of those attacks discovered in the future. + + Therefore TSX is not enabled by default (aka tsx=off). An admin + might override this decision by tsx=on the command line parameter. + Even with TSX enabled, the kernel will attempt to enable the best + possible TAA mitigation setting depending on the microcode available + for the particular machine. + + This option allows to set the default tsx mode between tsx=on, =off + and =auto. See Documentation/admin-guide/kernel-parameters.txt for more + details. + + Say off if not sure, auto if TSX is in use but it should be used on safe + platforms or on if TSX is in use and the security aspect of tsx is not + relevant. + +config X86_INTEL_TSX_MODE_OFF + bool "off" + help + TSX is disabled if possible - equals to tsx=off command line parameter. + +config X86_INTEL_TSX_MODE_ON + bool "on" + help + TSX is always enabled on TSX capable HW - equals the tsx=on command + line parameter. + +config X86_INTEL_TSX_MODE_AUTO + bool "auto" + help + TSX is enabled on TSX capable HW that is believed to be safe against + side channel attacks- equals the tsx=auto command line parameter. +endchoice + config EFI bool "EFI runtime service support" depends on ACPI diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 149795c369f2..25019d42ae93 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -21,30 +21,6 @@ struct mem_vector immovable_mem[MAX_NUMNODES*2]; /* - * Max length of 64-bit hex address string is 19, prefix "0x" + 16 hex - * digits, and '\0' for termination. - */ -#define MAX_ADDR_LEN 19 - -static acpi_physical_address get_cmdline_acpi_rsdp(void) -{ - acpi_physical_address addr = 0; - -#ifdef CONFIG_KEXEC - char val[MAX_ADDR_LEN] = { }; - int ret; - - ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN); - if (ret < 0) - return 0; - - if (kstrtoull(val, 16, &addr)) - return 0; -#endif - return addr; -} - -/* * Search EFI system tables for RSDP. If both ACPI_20_TABLE_GUID and * ACPI_TABLE_GUID are found, take the former, which has more features. */ @@ -298,6 +274,30 @@ acpi_physical_address get_rsdp_addr(void) } #if defined(CONFIG_RANDOMIZE_BASE) && defined(CONFIG_MEMORY_HOTREMOVE) +/* + * Max length of 64-bit hex address string is 19, prefix "0x" + 16 hex + * digits, and '\0' for termination. + */ +#define MAX_ADDR_LEN 19 + +static acpi_physical_address get_cmdline_acpi_rsdp(void) +{ + acpi_physical_address addr = 0; + +#ifdef CONFIG_KEXEC + char val[MAX_ADDR_LEN] = { }; + int ret; + + ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN); + if (ret < 0) + return 0; + + if (kstrtoull(val, 16, &addr)) + return 0; +#endif + return addr; +} + /* Compute SRAT address from RSDP. */ static unsigned long get_acpi_srat_table(void) { diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index d6662fdef300..82bc60c8acb2 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -13,6 +13,7 @@ #include <asm/e820/types.h> #include <asm/setup.h> #include <asm/desc.h> +#include <asm/boot.h> #include "../string.h" #include "eboot.h" @@ -813,7 +814,8 @@ efi_main(struct efi_config *c, struct boot_params *boot_params) status = efi_relocate_kernel(sys_table, &bzimage_addr, hdr->init_size, hdr->init_size, hdr->pref_address, - hdr->kernel_alignment); + hdr->kernel_alignment, + LOAD_PHYSICAL_ADDR); if (status != EFI_SUCCESS) { efi_printk(sys_table, "efi_relocate_kernel() failed!\n"); goto fail; diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 53ac0cb2396d..9652d5c2afda 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -345,6 +345,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, { const unsigned long kernel_total_size = VO__end - VO__text; unsigned long virt_addr = LOAD_PHYSICAL_ADDR; + unsigned long needed_size; /* Retain x86 boot parameters pointer passed from startup_32/64. */ boot_params = rmode; @@ -379,26 +380,38 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; + /* + * The memory hole needed for the kernel is the larger of either + * the entire decompressed kernel plus relocation table, or the + * entire decompressed kernel plus .bss and .brk sections. + * + * On X86_64, the memory is mapped with PMD pages. Round the + * size up so that the full extent of PMD pages mapped is + * included in the check against the valid memory table + * entries. This ensures the full mapped area is usable RAM + * and doesn't include any reserved areas. + */ + needed_size = max(output_len, kernel_total_size); +#ifdef CONFIG_X86_64 + needed_size = ALIGN(needed_size, MIN_KERNEL_ALIGN); +#endif + /* Report initial kernel position details. */ debug_putaddr(input_data); debug_putaddr(input_len); debug_putaddr(output); debug_putaddr(output_len); debug_putaddr(kernel_total_size); + debug_putaddr(needed_size); #ifdef CONFIG_X86_64 /* Report address of 32-bit trampoline */ debug_putaddr(trampoline_32bit); #endif - /* - * The memory hole needed for the kernel is the larger of either - * the entire decompressed kernel plus relocation table, or the - * entire decompressed kernel plus .bss and .brk sections. - */ choose_random_location((unsigned long)input_data, input_len, (unsigned long *)&output, - max(output_len, kernel_total_size), + needed_size, &virt_addr); /* Validate memory location choices. */ diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index e7d35f60d53f..64c3e70b0556 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -5,12 +5,14 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/delay.h> +#include <linux/jiffies.h> #include <asm/apicdef.h> #include <asm/nmi.h> #include "../perf_event.h" -static DEFINE_PER_CPU(unsigned int, perf_nmi_counter); +static DEFINE_PER_CPU(unsigned long, perf_nmi_tstamp); +static unsigned long perf_nmi_window; static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] @@ -641,11 +643,12 @@ static void amd_pmu_disable_event(struct perf_event *event) * handler when multiple PMCs are active or PMC overflow while handling some * other source of an NMI. * - * Attempt to mitigate this by using the number of active PMCs to determine - * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset - * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the - * number of active PMCs or 2. The value of 2 is used in case an NMI does not - * arrive at the LAPIC in time to be collapsed into an already pending NMI. + * Attempt to mitigate this by creating an NMI window in which un-handled NMIs + * received during this window will be claimed. This prevents extending the + * window past when it is possible that latent NMIs should be received. The + * per-CPU perf_nmi_tstamp will be set to the window end time whenever perf has + * handled a counter. When an un-handled NMI is received, it will be claimed + * only if arriving within that window. */ static int amd_pmu_handle_irq(struct pt_regs *regs) { @@ -663,21 +666,19 @@ static int amd_pmu_handle_irq(struct pt_regs *regs) handled = x86_pmu_handle_irq(regs); /* - * If a counter was handled, record the number of possible remaining - * NMIs that can occur. + * If a counter was handled, record a timestamp such that un-handled + * NMIs will be claimed if arriving within that window. */ if (handled) { - this_cpu_write(perf_nmi_counter, - min_t(unsigned int, 2, active)); + this_cpu_write(perf_nmi_tstamp, + jiffies + perf_nmi_window); return handled; } - if (!this_cpu_read(perf_nmi_counter)) + if (time_after(jiffies, this_cpu_read(perf_nmi_tstamp))) return NMI_DONE; - this_cpu_dec(perf_nmi_counter); - return NMI_HANDLED; } @@ -909,6 +910,9 @@ static int __init amd_core_pmu_init(void) if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) return 0; + /* Avoid calulating the value each time in the NMI handler */ + perf_nmi_window = msecs_to_jiffies(100); + switch (boot_cpu_data.x86) { case 0x15: pr_cont("Fam15h "); diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 5b35b7ea5d72..26c36357c4c9 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -377,7 +377,8 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs, struct hw_perf_event *hwc, u64 config) { config &= ~perf_ibs->cnt_mask; - wrmsrl(hwc->config_base, config); + if (boot_cpu_data.x86 == 0x10) + wrmsrl(hwc->config_base, config); config &= ~perf_ibs->enable_mask; wrmsrl(hwc->config_base, config); } @@ -553,7 +554,8 @@ static struct perf_ibs perf_ibs_op = { }, .msr = MSR_AMD64_IBSOPCTL, .config_mask = IBS_OP_CONFIG_MASK, - .cnt_mask = IBS_OP_MAX_CNT, + .cnt_mask = IBS_OP_MAX_CNT | IBS_OP_CUR_CNT | + IBS_OP_CUR_CNT_RAND, .enable_mask = IBS_OP_ENABLE, .valid_mask = IBS_OP_VAL, .max_period = IBS_OP_MAX_CNT << 4, @@ -614,7 +616,7 @@ fail: if (event->attr.sample_type & PERF_SAMPLE_RAW) offset_max = perf_ibs->offset_max; else if (check_rip) - offset_max = 2; + offset_max = 3; else offset_max = 1; do { diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 27ee47a7be66..fcef678c3423 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4983,6 +4983,8 @@ __init int intel_pmu_init(void) case INTEL_FAM6_SKYLAKE: case INTEL_FAM6_KABYLAKE_L: case INTEL_FAM6_KABYLAKE: + case INTEL_FAM6_COMETLAKE_L: + case INTEL_FAM6_COMETLAKE: x86_add_quirk(intel_pebs_isolation_quirk); x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -5031,6 +5033,8 @@ __init int intel_pmu_init(void) /* fall through */ case INTEL_FAM6_ICELAKE_L: case INTEL_FAM6_ICELAKE: + case INTEL_FAM6_TIGERLAKE_L: + case INTEL_FAM6_TIGERLAKE: x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 9f2f39003d96..e1daf4151e11 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -45,46 +45,49 @@ * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM, - CNL + * CNL,KBL,CML * Scope: Core * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, - * SKL,KNL,GLM,CNL + * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 - * Available model: SNB,IVB,HSW,BDW,SKL,CNL + * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, + * ICL,TGL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 - * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL + * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, + * KBL,CML,ICL,TGL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, - * GLM,CNL + * GLM,CNL,KBL,CML,ICL,TGL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW - * SKL,KNL,GLM,CNL + * SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 - * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, + * KBL,CML,ICL,TGL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 - * Available model: HSW ULT,KBL,CNL + * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 - * Available model: HSW ULT,KBL,CNL + * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 - * Available model: HSW ULT,KBL,GLM,CNL + * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL * Scope: Package (physical package) * */ @@ -544,6 +547,19 @@ static const struct cstate_model cnl_cstates __initconst = { BIT(PERF_CSTATE_PKG_C10_RES), }; +static const struct cstate_model icl_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C6_RES) | + BIT(PERF_CSTATE_CORE_C7_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES) | + BIT(PERF_CSTATE_PKG_C8_RES) | + BIT(PERF_CSTATE_PKG_C9_RES) | + BIT(PERF_CSTATE_PKG_C10_RES), +}; + static const struct cstate_model slm_cstates __initconst = { .core_events = BIT(PERF_CSTATE_CORE_C1_RES) | BIT(PERF_CSTATE_CORE_C6_RES), @@ -614,6 +630,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_L, hswult_cstates), X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE, hswult_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE_L, hswult_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE, hswult_cstates), X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_L, cnl_cstates), @@ -625,8 +643,10 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE, icl_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE_L, icl_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE, icl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 74e80ed9c6c4..05e43d0f430b 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -627,7 +627,7 @@ static struct topa *topa_alloc(int cpu, gfp_t gfp) * link as the 2nd entry in the table */ if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) { - TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p); + TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p) >> TOPA_SHIFT; TOPA_ENTRY(&tp->topa, 1)->end = 1; } diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 6fc2e06ab4c6..86467f85c383 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -502,10 +502,8 @@ void uncore_pmu_event_start(struct perf_event *event, int flags) local64_set(&event->hw.prev_count, uncore_read_counter(box, event)); uncore_enable_event(box, event); - if (box->n_active == 1) { - uncore_enable_box(box); + if (box->n_active == 1) uncore_pmu_start_hrtimer(box); - } } void uncore_pmu_event_stop(struct perf_event *event, int flags) @@ -529,10 +527,8 @@ void uncore_pmu_event_stop(struct perf_event *event, int flags) WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; - if (box->n_active == 0) { - uncore_disable_box(box); + if (box->n_active == 0) uncore_pmu_cancel_hrtimer(box); - } } if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { @@ -778,6 +774,40 @@ static int uncore_pmu_event_init(struct perf_event *event) return ret; } +static void uncore_pmu_enable(struct pmu *pmu) +{ + struct intel_uncore_pmu *uncore_pmu; + struct intel_uncore_box *box; + + uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->enable_box) + uncore_pmu->type->ops->enable_box(box); +} + +static void uncore_pmu_disable(struct pmu *pmu) +{ + struct intel_uncore_pmu *uncore_pmu; + struct intel_uncore_box *box; + + uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu); + if (!uncore_pmu) + return; + + box = uncore_pmu_to_box(uncore_pmu, smp_processor_id()); + if (!box) + return; + + if (uncore_pmu->type->ops->disable_box) + uncore_pmu->type->ops->disable_box(box); +} + static ssize_t uncore_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) { @@ -803,6 +833,8 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu) pmu->pmu = (struct pmu) { .attr_groups = pmu->type->attr_groups, .task_ctx_nr = perf_invalid_context, + .pmu_enable = uncore_pmu_enable, + .pmu_disable = uncore_pmu_disable, .event_init = uncore_pmu_event_init, .add = uncore_pmu_event_add, .del = uncore_pmu_event_del, diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index f36f7bebbc1b..bbfdaa720b45 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -441,18 +441,6 @@ static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box, return -EINVAL; } -static inline void uncore_disable_box(struct intel_uncore_box *box) -{ - if (box->pmu->type->ops->disable_box) - box->pmu->type->ops->disable_box(box); -} - -static inline void uncore_enable_box(struct intel_uncore_box *box) -{ - if (box->pmu->type->ops->enable_box) - box->pmu->type->ops->enable_box(box); -} - static inline void uncore_disable_event(struct intel_uncore_box *box, struct perf_event *event) { diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index b1afc77f0704..6f86650b3f77 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -89,7 +89,14 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_KABYLAKE_L: case INTEL_FAM6_KABYLAKE: + case INTEL_FAM6_COMETLAKE_L: + case INTEL_FAM6_COMETLAKE: case INTEL_FAM6_ICELAKE_L: + case INTEL_FAM6_ICELAKE: + case INTEL_FAM6_ICELAKE_X: + case INTEL_FAM6_ICELAKE_D: + case INTEL_FAM6_TIGERLAKE_L: + case INTEL_FAM6_TIGERLAKE: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 5c056b8aebef..e01078e93dd3 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -260,11 +260,21 @@ void __init hv_apic_init(void) } if (ms_hyperv.hints & HV_X64_APIC_ACCESS_RECOMMENDED) { - pr_info("Hyper-V: Using MSR based APIC access\n"); + pr_info("Hyper-V: Using enlightened APIC (%s mode)", + x2apic_enabled() ? "x2apic" : "xapic"); + /* + * With x2apic, architectural x2apic MSRs are equivalent to the + * respective synthetic MSRs, so there's no need to override + * the apic accessors. The only exception is + * hv_apic_eoi_write, because it benefits from lazy EOI when + * available, but it works for both xapic and x2apic modes. + */ apic_set_eoi_write(hv_apic_eoi_write); - apic->read = hv_apic_read; - apic->write = hv_apic_write; - apic->icr_write = hv_apic_icr_write; - apic->icr_read = hv_apic_icr_read; + if (!x2apic_enabled()) { + apic->read = hv_apic_read; + apic->write = hv_apic_write; + apic->icr_write = hv_apic_icr_write; + apic->icr_read = hv_apic_icr_read; + } } } diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index cff3f3f3bfe0..8348f7d69fd5 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPU_ENTRY_AREA_H #define _ASM_X86_CPU_ENTRY_AREA_H diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 0652d3eed9bd..c4fbe379cc0b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -399,5 +399,7 @@ #define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */ #define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */ #define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index f04622500da3..c606c0b70738 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -83,6 +83,9 @@ #define INTEL_FAM6_TIGERLAKE_L 0x8C #define INTEL_FAM6_TIGERLAKE 0x8D +#define INTEL_FAM6_COMETLAKE 0xA5 +#define INTEL_FAM6_COMETLAKE_L 0xA6 + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 23edf56cf577..4fc61483919a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -219,13 +219,6 @@ enum { PFERR_WRITE_MASK | \ PFERR_PRESENT_MASK) -/* - * The mask used to denote special SPTEs, which can be either MMIO SPTEs or - * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting - * with the SVE bit in EPT PTEs. - */ -#define SPTE_SPECIAL_MASK (1ULL << 62) - /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* @@ -319,9 +312,12 @@ struct kvm_rmap_head { struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; + struct list_head lpage_disallowed_link; + bool unsync; u8 mmu_valid_gen; bool mmio_cached; + bool lpage_disallowed; /* Can't be replaced by an equiv large page */ /* * The following two entries are used to key the shadow page in the @@ -866,6 +862,7 @@ struct kvm_arch { */ struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; + struct list_head lpage_disallowed_mmu_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; @@ -940,6 +937,7 @@ struct kvm_arch { bool exception_payload_enabled; struct kvm_pmu_event_filter *pmu_event_filter; + struct task_struct *nx_lpage_recovery_thread; }; struct kvm_vm_stat { @@ -953,6 +951,7 @@ struct kvm_vm_stat { ulong mmu_unsync; ulong remote_tlb_flush; ulong lpages; + ulong nx_lpage_splits; ulong max_mmu_page_hash_collisions; }; @@ -1196,7 +1195,7 @@ struct kvm_x86_ops { int (*set_nested_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, struct kvm_nested_state *kvm_state); - void (*get_vmcs12_pages)(struct kvm_vcpu *vcpu); + bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu); int (*smi_allowed)(struct kvm_vcpu *vcpu); int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 20ce682a2540..6a3124664289 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -93,6 +93,18 @@ * Microarchitectural Data * Sampling (MDS) vulnerabilities. */ +#define ARCH_CAP_PSCHANGE_MC_NO BIT(6) /* + * The processor is not susceptible to a + * machine check error due to modifying the + * code page size along with either the + * physical address or cache type + * without TLB invalidation. + */ +#define ARCH_CAP_TSX_CTRL_MSR BIT(7) /* MSR for TSX control is available. */ +#define ARCH_CAP_TAA_NO BIT(8) /* + * Not susceptible to + * TSX Async Abort (TAA) vulnerabilities. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* @@ -103,6 +115,10 @@ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e +#define MSR_IA32_TSX_CTRL 0x00000122 +#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ +#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ + #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 #define MSR_IA32_SYSENTER_EIP 0x00000176 diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index e28f8b723b5c..9d5252c9685c 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -21,7 +21,7 @@ #define MWAIT_ECX_INTERRUPT_BREAK 0x1 #define MWAITX_ECX_TIMER_ENABLE BIT(1) #define MWAITX_MAX_LOOPS ((u32)-1) -#define MWAITX_DISABLE_CSTATES 0xf +#define MWAITX_DISABLE_CSTATES 0xf0 static inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 80bc209c0708..5c24a7b35166 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -314,7 +314,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear); #include <asm/segment.h> /** - * mds_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the @@ -337,7 +337,7 @@ static inline void mds_clear_cpu_buffers(void) } /** - * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability + * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 0bc530c4eb13..ad97dc155195 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1463,6 +1463,12 @@ static inline bool arch_has_pfn_modify_check(void) return boot_cpu_has_bug(X86_BUG_L1TF); } +#define arch_faults_on_old_pte arch_faults_on_old_pte +static inline bool arch_faults_on_old_pte(void) +{ + return false; +} + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6e0a3b43d027..54f5d54280f6 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -988,4 +988,11 @@ enum mds_mitigations { MDS_MITIGATION_VMWERV, }; +enum taa_mitigations { + TAA_MITIGATION_OFF, + TAA_MITIGATION_UCODE_NEEDED, + TAA_MITIGATION_VERW, + TAA_MITIGATION_TSX_DISABLED, +}; + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h index 5df09a0b80b8..07375b476c4f 100644 --- a/arch/x86/include/asm/pti.h +++ b/arch/x86/include/asm/pti.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PTI_H #define _ASM_X86_PTI_H #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 35c225ede0e4..61d93f062a36 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -734,5 +734,28 @@ do { \ if (unlikely(__gu_err)) goto err_label; \ } while (0) +/* + * We want the unsafe accessors to always be inlined and use + * the error labels - thus the macro games. + */ +#define unsafe_copy_loop(dst, src, len, type, label) \ + while (len >= sizeof(type)) { \ + unsafe_put_user(*(type *)src,(type __user *)dst,label); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } + +#define unsafe_copy_to_user(_dst,_src,_len,label) \ +do { \ + char __user *__ucu_dst = (_dst); \ + const char *__ucu_src = (_src); \ + size_t __ucu_len = (_len); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u64, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u32, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u16, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label); \ +} while (0) + #endif /* _ASM_X86_UACCESS_H */ diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h index e00c9e875933..ac9fc51e2b18 100644 --- a/arch/x86/include/asm/vmware.h +++ b/arch/x86/include/asm/vmware.h @@ -4,6 +4,7 @@ #include <asm/cpufeatures.h> #include <asm/alternative.h> +#include <linux/stringify.h> /* * The hypercall definitions differ in the low word of the %edx argument @@ -20,8 +21,8 @@ */ /* Old port-based version */ -#define VMWARE_HYPERVISOR_PORT "0x5658" -#define VMWARE_HYPERVISOR_PORT_HB "0x5659" +#define VMWARE_HYPERVISOR_PORT 0x5658 +#define VMWARE_HYPERVISOR_PORT_HB 0x5659 /* Current vmcall / vmmcall version */ #define VMWARE_HYPERVISOR_HB BIT(0) @@ -29,7 +30,8 @@ /* The low bandwidth call. The low word of edx is presumed clear. */ #define VMWARE_HYPERCALL \ - ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT ", %%dx; inl (%%dx)", \ + ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \ + "inl (%%dx), %%eax", \ "vmcall", X86_FEATURE_VMCALL, \ "vmmcall", X86_FEATURE_VMW_VMMCALL) @@ -38,7 +40,8 @@ * HB and OUT bits set. */ #define VMWARE_HYPERCALL_HB_OUT \ - ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT_HB ", %%dx; rep outsb", \ + ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \ + "rep outsb", \ "vmcall", X86_FEATURE_VMCALL, \ "vmmcall", X86_FEATURE_VMW_VMMCALL) @@ -47,7 +50,8 @@ * HB bit set. */ #define VMWARE_HYPERCALL_HB_IN \ - ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT_HB ", %%dx; rep insb", \ + ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \ + "rep insb", \ "vmcall", X86_FEATURE_VMCALL, \ "vmmcall", X86_FEATURE_VMW_VMMCALL) #endif diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 9e2dd2b296cd..2b0faf86da1b 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1586,9 +1586,6 @@ static void setup_local_APIC(void) { int cpu = smp_processor_id(); unsigned int value; -#ifdef CONFIG_X86_32 - int logical_apicid, ldr_apicid; -#endif if (disable_apic) { disable_ioapic_support(); @@ -1626,16 +1623,21 @@ static void setup_local_APIC(void) apic->init_apic_ldr(); #ifdef CONFIG_X86_32 - /* - * APIC LDR is initialized. If logical_apicid mapping was - * initialized during get_smp_config(), make sure it matches the - * actual value. - */ - logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); - ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); - WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid); - /* always use the value from LDR */ - early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + if (apic->dest_logical) { + int logical_apicid, ldr_apicid; + + /* + * APIC LDR is initialized. If logical_apicid mapping was + * initialized during get_smp_config(), make sure it matches + * the actual value. + */ + logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu); + ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR)); + if (logical_apicid != BAD_APICID) + WARN_ON(logical_apicid != ldr_apicid); + /* Always use the value from LDR. */ + early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid; + } #endif /* diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 45e92cba92f5..b0889c48a2ac 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -156,7 +156,8 @@ static int x2apic_dead_cpu(unsigned int dead_cpu) { struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu); - cpumask_clear_cpu(dead_cpu, &cmsk->mask); + if (cmsk) + cpumask_clear_cpu(dead_cpu, &cmsk->mask); free_cpumask_var(per_cpu(ipi_mask, dead_cpu)); return 0; } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index d7a1e5a9331c..890f60083eca 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -30,7 +30,7 @@ obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o ifdef CONFIG_CPU_SUP_INTEL -obj-y += intel.o intel_pconfig.o +obj-y += intel.o intel_pconfig.o tsx.o obj-$(CONFIG_PM) += intel_epb.o endif obj-$(CONFIG_CPU_SUP_AMD) += amd.o diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 91c2561b905f..4c7b0fa15a19 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void); static void __init ssb_select_mitigation(void); static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); +static void __init taa_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -105,6 +106,7 @@ void __init check_bugs(void) ssb_select_mitigation(); l1tf_select_mitigation(); mds_select_mitigation(); + taa_select_mitigation(); arch_smt_update(); @@ -269,6 +271,100 @@ static int __init mds_cmdline(char *str) early_param("mds", mds_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "TAA: " fmt + +/* Default mitigation for TAA-affected CPUs */ +static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW; +static bool taa_nosmt __ro_after_init; + +static const char * const taa_strings[] = { + [TAA_MITIGATION_OFF] = "Vulnerable", + [TAA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [TAA_MITIGATION_VERW] = "Mitigation: Clear CPU buffers", + [TAA_MITIGATION_TSX_DISABLED] = "Mitigation: TSX disabled", +}; + +static void __init taa_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_TAA)) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TSX previously disabled by tsx=off */ + if (!boot_cpu_has(X86_FEATURE_RTM)) { + taa_mitigation = TAA_MITIGATION_TSX_DISABLED; + goto out; + } + + if (cpu_mitigations_off()) { + taa_mitigation = TAA_MITIGATION_OFF; + return; + } + + /* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */ + if (taa_mitigation == TAA_MITIGATION_OFF) + goto out; + + if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) + taa_mitigation = TAA_MITIGATION_VERW; + else + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1. + * A microcode update fixes this behavior to clear CPU buffers. It also + * adds support for MSR_IA32_TSX_CTRL which is enumerated by the + * ARCH_CAP_TSX_CTRL_MSR bit. + * + * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode + * update is required. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ( (ia32_cap & ARCH_CAP_MDS_NO) && + !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; + + /* + * TSX is enabled, select alternate mitigation for TAA which is + * the same as MDS. Enable MDS static branch to clear CPU buffers. + * + * For guests that can't determine whether the correct microcode is + * present on host, enable the mitigation for UCODE_NEEDED as well. + */ + static_branch_enable(&mds_user_clear); + + if (taa_nosmt || cpu_mitigations_auto_nosmt()) + cpu_smt_disable(false); + +out: + pr_info("%s\n", taa_strings[taa_mitigation]); +} + +static int __init tsx_async_abort_parse_cmdline(char *str) +{ + if (!boot_cpu_has_bug(X86_BUG_TAA)) + return 0; + + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + taa_mitigation = TAA_MITIGATION_OFF; + } else if (!strcmp(str, "full")) { + taa_mitigation = TAA_MITIGATION_VERW; + } else if (!strcmp(str, "full,nosmt")) { + taa_mitigation = TAA_MITIGATION_VERW; + taa_nosmt = true; + } + + return 0; +} +early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -786,13 +882,10 @@ static void update_mds_branch_idle(void) } #define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" +#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" void cpu_bugs_smt_update(void) { - /* Enhanced IBRS implies STIBP. No update required. */ - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) - return; - mutex_lock(&spec_ctrl_mutex); switch (spectre_v2_user) { @@ -819,6 +912,17 @@ void cpu_bugs_smt_update(void) break; } + switch (taa_mitigation) { + case TAA_MITIGATION_VERW: + case TAA_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(TAA_MSG_SMT); + break; + case TAA_MITIGATION_TSX_DISABLED: + case TAA_MITIGATION_OFF: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -1149,6 +1253,9 @@ void x86_spec_ctrl_setup_ap(void) x86_amd_ssb_disable(); } +bool itlb_multihit_kvm_mitigation; +EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation); + #undef pr_fmt #define pr_fmt(fmt) "L1TF: " fmt @@ -1304,11 +1411,24 @@ static ssize_t l1tf_show_state(char *buf) l1tf_vmx_states[l1tf_vmx_mitigation], sched_smt_active() ? "vulnerable" : "disabled"); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + if (itlb_multihit_kvm_mitigation) + return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + else + return sprintf(buf, "KVM: Vulnerable\n"); +} #else static ssize_t l1tf_show_state(char *buf) { return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); } + +static ssize_t itlb_multihit_show_state(char *buf) +{ + return sprintf(buf, "Processor vulnerable\n"); +} #endif static ssize_t mds_show_state(char *buf) @@ -1328,6 +1448,21 @@ static ssize_t mds_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t tsx_async_abort_show_state(char *buf) +{ + if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || + (taa_mitigation == TAA_MITIGATION_OFF)) + return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + return sprintf(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); + } + + return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); +} + static char *stibp_state(void) { if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) @@ -1398,6 +1533,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_MDS: return mds_show_state(buf); + case X86_BUG_TAA: + return tsx_async_abort_show_state(buf); + + case X86_BUG_ITLB_MULTIHIT: + return itlb_multihit_show_state(buf); + default: break; } @@ -1434,4 +1575,14 @@ ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_MDS); } + +ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_TAA); +} + +ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9ae7d1bcd4f4..fffe21945374 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1016,13 +1016,14 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #endif } -#define NO_SPECULATION BIT(0) -#define NO_MELTDOWN BIT(1) -#define NO_SSB BIT(2) -#define NO_L1TF BIT(3) -#define NO_MDS BIT(4) -#define MSBDS_ONLY BIT(5) -#define NO_SWAPGS BIT(6) +#define NO_SPECULATION BIT(0) +#define NO_MELTDOWN BIT(1) +#define NO_SSB BIT(2) +#define NO_L1TF BIT(3) +#define NO_MDS BIT(4) +#define MSBDS_ONLY BIT(5) +#define NO_SWAPGS BIT(6) +#define NO_ITLB_MULTIHIT BIT(7) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -1043,27 +1044,27 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION), /* Intel Family 6 */ - VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION), - VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION), - VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION), - - VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS), + VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT), + + VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(CORE_YONAH, NO_SSB), - VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS), - VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS), + VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), /* * Technically, swapgs isn't serializing on AMD (despite it previously @@ -1073,15 +1074,17 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { * good enough for our purposes. */ + VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT), + /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), {} }; @@ -1092,19 +1095,30 @@ static bool __init cpu_matches(unsigned long which) return m && !!(m->driver_data & which); } -static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +u64 x86_read_arch_cap_msr(void) { u64 ia32_cap = 0; + if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + + return ia32_cap; +} + +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ + if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); + if (cpu_matches(NO_SPECULATION)) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); - if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); @@ -1121,6 +1135,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (!cpu_matches(NO_SWAPGS)) setup_force_cpu_bug(X86_BUG_SWAPGS); + /* + * When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when: + * - TSX is supported or + * - TSX_CTRL is present + * + * TSX_CTRL check is needed for cases when TSX could be disabled before + * the kernel boot e.g. kexec. + * TSX_CTRL check alone is not sufficient for cases when the microcode + * update is not present or running as guest that don't get TSX_CTRL. + */ + if (!(ia32_cap & ARCH_CAP_TAA_NO) && + (cpu_has(c, X86_FEATURE_RTM) || + (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + setup_force_cpu_bug(X86_BUG_TAA); + if (cpu_matches(NO_MELTDOWN)) return; @@ -1554,6 +1583,8 @@ void __init identify_boot_cpu(void) #endif cpu_detect_tlb(&boot_cpu_data); setup_cr_pinning(); + + tsx_init(); } void identify_secondary_cpu(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index c0e2407abdd6..38ab6e115eac 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -44,6 +44,22 @@ struct _tlb_table { extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; +#ifdef CONFIG_CPU_SUP_INTEL +enum tsx_ctrl_states { + TSX_CTRL_ENABLE, + TSX_CTRL_DISABLE, + TSX_CTRL_NOT_SUPPORTED, +}; + +extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; + +extern void __init tsx_init(void); +extern void tsx_enable(void); +extern void tsx_disable(void); +#else +static inline void tsx_init(void) { } +#endif /* CONFIG_CPU_SUP_INTEL */ + extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void get_cpu_address_sizes(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); @@ -62,4 +78,6 @@ unsigned int aperfmperf_get_khz(int cpu); extern void x86_spec_ctrl_setup_ap(void); +extern u64 x86_read_arch_cap_msr(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index c2fdc00df163..11d5c5950e2d 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -762,6 +762,11 @@ static void init_intel(struct cpuinfo_x86 *c) detect_tme(c); init_intel_misc_features(c); + + if (tsx_ctrl_state == TSX_CTRL_ENABLE) + tsx_enable(); + if (tsx_ctrl_state == TSX_CTRL_DISABLE) + tsx_disable(); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index a0e52bd00ecc..3f6b137ef4e6 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -567,7 +567,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) void reload_ucode_amd(void) { struct microcode_amd *mc; - u32 rev, dummy; + u32 rev, dummy __always_unused; mc = (struct microcode_amd *)amd_ucode_patch; @@ -673,7 +673,7 @@ static enum ucode_state apply_microcode_amd(int cpu) struct ucode_cpu_info *uci; struct ucode_patch *p; enum ucode_state ret; - u32 rev, dummy; + u32 rev, dummy __always_unused; BUG_ON(raw_smp_processor_id() != cpu); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index cb0fdcaf1415..7019d4b2df0c 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -63,11 +63,6 @@ LIST_HEAD(microcode_cache); */ static DEFINE_MUTEX(microcode_mutex); -/* - * Serialize late loading so that CPUs get updated one-by-one. - */ -static DEFINE_RAW_SPINLOCK(update_lock); - struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; struct cpu_info_ctx { @@ -566,11 +561,18 @@ static int __reload_late(void *info) if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC)) return -1; - raw_spin_lock(&update_lock); - apply_microcode_local(&err); - raw_spin_unlock(&update_lock); + /* + * On an SMT system, it suffices to load the microcode on one sibling of + * the core because the microcode engine is shared between the threads. + * Synchronization still needs to take place so that no concurrent + * loading attempts happen on multiple threads of an SMT core. See + * below. + */ + if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu) + apply_microcode_local(&err); + else + goto wait_for_siblings; - /* siblings return UCODE_OK because their engine got updated already */ if (err > UCODE_NFOUND) { pr_warn("Error reloading microcode on CPU %d\n", cpu); ret = -1; @@ -578,14 +580,18 @@ static int __reload_late(void *info) ret = 1; } +wait_for_siblings: + if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC)) + panic("Timeout during microcode update!\n"); + /* - * Increase the wait timeout to a safe value here since we're - * serializing the microcode update and that could take a while on a - * large number of CPUs. And that is fine as the *actual* timeout will - * be determined by the last CPU finished updating and thus cut short. + * At least one thread has completed update on each core. + * For others, simply call the update to make sure the + * per-cpu cpuinfo can be updated with right microcode + * revision. */ - if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus())) - panic("Timeout during microcode update!\n"); + if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu) + apply_microcode_local(&err); return ret; } diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index ce799cfe9434..6a99535d7f37 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -791,6 +791,7 @@ static enum ucode_state apply_microcode_intel(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); + bool bsp = c->cpu_index == boot_cpu_data.cpu_index; struct microcode_intel *mc; enum ucode_state ret; static int prev_rev; @@ -836,7 +837,7 @@ static enum ucode_state apply_microcode_intel(int cpu) return UCODE_ERROR; } - if (rev != prev_rev) { + if (bsp && rev != prev_rev) { pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n", rev, mc->hdr.date & 0xffff, @@ -852,7 +853,7 @@ out: c->microcode = rev; /* Update boot_cpu_data's revision too, if we're on the BSP: */ - if (c->cpu_index == boot_cpu_data.cpu_index) + if (bsp) boot_cpu_data.microcode = rev; return ret; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 267daad8c036..c656d92cd708 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -216,6 +216,10 @@ static void __init ms_hyperv_init_platform(void) int hv_host_info_ecx; int hv_host_info_edx; +#ifdef CONFIG_PARAVIRT + pv_info.name = "Hyper-V"; +#endif + /* * Extract the features and hints */ diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index efbd54cc4e69..055c8613b531 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -522,6 +522,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + ret = -ENOENT; + goto out; + } md.priv = of->kn->priv; resid = md.u.rid; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index a46dee8e78db..2e3b06d6bbc6 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -461,10 +461,8 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, } rdtgrp = rdtgroup_kn_lock_live(of->kn); - rdt_last_cmd_clear(); if (!rdtgrp) { ret = -ENOENT; - rdt_last_cmd_puts("Directory was removed\n"); goto unlock; } @@ -2648,10 +2646,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, int ret; prdtgrp = rdtgroup_kn_lock_live(prgrp_kn); - rdt_last_cmd_clear(); if (!prdtgrp) { ret = -ENODEV; - rdt_last_cmd_puts("Directory was removed\n"); goto out_unlock; } diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c new file mode 100644 index 000000000000..3e20d322bc98 --- /dev/null +++ b/arch/x86/kernel/cpu/tsx.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Transactional Synchronization Extensions (TSX) control. + * + * Copyright (C) 2019 Intel Corporation + * + * Author: + * Pawan Gupta <pawan.kumar.gupta@linux.intel.com> + */ + +#include <linux/cpufeature.h> + +#include <asm/cmdline.h> + +#include "cpu.h" + +enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; + +void tsx_disable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Force all transactions to immediately abort */ + tsx |= TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is not enumerated in CPUID. + * This is visible to userspace and will ensure they + * do not waste resources trying TSX transactions that + * will always abort. + */ + tsx |= TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +void tsx_enable(void) +{ + u64 tsx; + + rdmsrl(MSR_IA32_TSX_CTRL, tsx); + + /* Enable the RTM feature in the cpu */ + tsx &= ~TSX_CTRL_RTM_DISABLE; + + /* + * Ensure TSX support is enumerated in CPUID. + * This is visible to userspace and will ensure they + * can enumerate and use the TSX feature. + */ + tsx &= ~TSX_CTRL_CPUID_CLEAR; + + wrmsrl(MSR_IA32_TSX_CTRL, tsx); +} + +static bool __init tsx_ctrl_is_supported(void) +{ + u64 ia32_cap = x86_read_arch_cap_msr(); + + /* + * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this + * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. + * + * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a + * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES + * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get + * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, + * tsx= cmdline requests will do nothing on CPUs without + * MSR_IA32_TSX_CTRL support. + */ + return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR); +} + +static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) +{ + if (boot_cpu_has_bug(X86_BUG_TAA)) + return TSX_CTRL_DISABLE; + + return TSX_CTRL_ENABLE; +} + +void __init tsx_init(void) +{ + char arg[5] = {}; + int ret; + + if (!tsx_ctrl_is_supported()) + return; + + ret = cmdline_find_option(boot_command_line, "tsx", arg, sizeof(arg)); + if (ret >= 0) { + if (!strcmp(arg, "on")) { + tsx_ctrl_state = TSX_CTRL_ENABLE; + } else if (!strcmp(arg, "off")) { + tsx_ctrl_state = TSX_CTRL_DISABLE; + } else if (!strcmp(arg, "auto")) { + tsx_ctrl_state = x86_get_tsx_auto_mode(); + } else { + tsx_ctrl_state = TSX_CTRL_DISABLE; + pr_err("tsx: invalid option, defaulting to off\n"); + } + } else { + /* tsx= not provided */ + if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_AUTO)) + tsx_ctrl_state = x86_get_tsx_auto_mode(); + else if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_OFF)) + tsx_ctrl_state = TSX_CTRL_DISABLE; + else + tsx_ctrl_state = TSX_CTRL_ENABLE; + } + + if (tsx_ctrl_state == TSX_CTRL_DISABLE) { + tsx_disable(); + + /* + * tsx_disable() will change the state of the + * RTM CPUID bit. Clear it here since it is now + * expected to be not set. + */ + setup_clear_cpu_cap(X86_FEATURE_RTM); + } else if (tsx_ctrl_state == TSX_CTRL_ENABLE) { + + /* + * HW defaults TSX to be enabled at bootup. + * We may still need the TSX enable support + * during init for special cases like + * kexec after TSX is disabled. + */ + tsx_enable(); + + /* + * tsx_enable() will change the state of the + * RTM CPUID bit. Force it here since it is now + * expected to be set. + */ + setup_force_cpu_cap(X86_FEATURE_RTM); + } +} diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 9735139cfdf8..46d732696c1c 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -49,7 +49,7 @@ #define VMWARE_CMD_VCPU_RESERVED 31 #define VMWARE_PORT(cmd, eax, ebx, ecx, edx) \ - __asm__("inl (%%dx)" : \ + __asm__("inl (%%dx), %%eax" : \ "=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) : \ "a"(VMWARE_HYPERVISOR_MAGIC), \ "c"(VMWARE_CMD_##cmd), \ diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 753b8cfe8b8a..87b97897a881 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -94,6 +94,13 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); begin = (unsigned long)__this_cpu_read(cea_exception_stacks); + /* + * Handle the case where stack trace is collected _before_ + * cea_exception_stacks had been initialized. + */ + if (!begin) + return false; + end = begin + sizeof(struct cea_exception_stacks); /* Bail if @stack is outside the exception stack area. */ if (stk < begin || stk >= end) diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 6f6b1d04dadf..4cba91ec8049 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -710,6 +710,8 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_INTEL, 0x3ec4, + PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, { PCI_VENDOR_ID_BROADCOM, 0x4331, PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 29ffa495bd1c..206a4b6144c2 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -222,13 +222,31 @@ unsigned long __head __startup_64(unsigned long physaddr, * we might write invalid pmds, when the kernel is relocated * cleanup_highmap() fixes this up along with the mappings * beyond _end. + * + * Only the region occupied by the kernel image has so far + * been checked against the table of usable memory regions + * provided by the firmware, so invalidate pages outside that + * region. A page table entry that maps to a reserved area of + * memory would allow processor speculation into that area, + * and on some hardware (particularly the UV platform) even + * speculative access to some reserved areas is caught as an + * error, causing the BIOS to halt the system. */ pmd = fixup_pointer(level2_kernel_pgt, physaddr); - for (i = 0; i < PTRS_PER_PMD; i++) { + + /* invalidate pages before the kernel image */ + for (i = 0; i < pmd_index((unsigned long)_text); i++) + pmd[i] &= ~_PAGE_PRESENT; + + /* fixup pages that are part of the kernel image */ + for (; i <= pmd_index((unsigned long)_end); i++) if (pmd[i] & _PAGE_PRESENT) pmd[i] += load_delta; - } + + /* invalidate pages after the kernel image */ + for (; i < PTRS_PER_PMD; i++) + pmd[i] &= ~_PAGE_PRESENT; /* * Fixup phys_base - remove the memory encryption mask to obtain diff --git a/arch/x86/kernel/process.h b/arch/x86/kernel/process.h index 320ab978fb1f..1d0797b2338a 100644 --- a/arch/x86/kernel/process.h +++ b/arch/x86/kernel/process.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ // // Code shared between 32 and 64 bit diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c59454c382fd..7e322e2daaf5 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1505,6 +1505,9 @@ void __init tsc_init(void) return; } + if (tsc_clocksource_reliable || no_tsc_watchdog) + clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 63316036f85a..f68c0c753c38 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -363,7 +363,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index) /* cpuid 7.0.ecx*/ const u32 kvm_cpuid_7_0_ecx_x86_features = - F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | + F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/; @@ -485,6 +485,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, /* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = + F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON); @@ -618,16 +619,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function, */ case 0x1f: case 0xb: { - int i, level_type; + int i; - /* read more entries until level_type is zero */ - for (i = 1; ; ++i) { + /* + * We filled in entry[0] for CPUID(EAX=<function>, + * ECX=00H) above. If its level type (ECX[15:8]) is + * zero, then the leaf is unimplemented, and we're + * done. Otherwise, continue to populate entries + * until the level type (ECX[15:8]) of the previously + * added entry is zero. + */ + for (i = 1; entry[i - 1].ecx & 0xff00; ++i) { if (*nent >= maxnent) goto out; - level_type = entry[i - 1].ecx & 0xff00; - if (!level_type) - break; do_host_cpuid(&entry[i], function, i); ++*nent; } @@ -969,53 +974,66 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); /* - * If no match is found, check whether we exceed the vCPU's limit - * and return the content of the highest valid _standard_ leaf instead. - * This is to satisfy the CPUID specification. + * If the basic or extended CPUID leaf requested is higher than the + * maximum supported basic or extended leaf, respectively, then it is + * out of range. */ -static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, - u32 function, u32 index) +static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function) { - struct kvm_cpuid_entry2 *maxlevel; - - maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); - if (!maxlevel || maxlevel->eax >= function) - return NULL; - if (function & 0x80000000) { - maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0); - if (!maxlevel) - return NULL; - } - return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); + struct kvm_cpuid_entry2 *max; + + max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); + return max && function <= max->eax; } bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool check_limit) { u32 function = *eax, index = *ecx; - struct kvm_cpuid_entry2 *best; - bool entry_found = true; - - best = kvm_find_cpuid_entry(vcpu, function, index); - - if (!best) { - entry_found = false; - if (!check_limit) - goto out; + struct kvm_cpuid_entry2 *entry; + struct kvm_cpuid_entry2 *max; + bool found; - best = check_cpuid_limit(vcpu, function, index); + entry = kvm_find_cpuid_entry(vcpu, function, index); + found = entry; + /* + * Intel CPUID semantics treats any query for an out-of-range + * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were + * requested. AMD CPUID semantics returns all zeroes for any + * undefined leaf, whether or not the leaf is in range. + */ + if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) && + !cpuid_function_in_range(vcpu, function)) { + max = kvm_find_cpuid_entry(vcpu, 0, 0); + if (max) { + function = max->eax; + entry = kvm_find_cpuid_entry(vcpu, function, index); + } } - -out: - if (best) { - *eax = best->eax; - *ebx = best->ebx; - *ecx = best->ecx; - *edx = best->edx; - } else + if (entry) { + *eax = entry->eax; + *ebx = entry->ebx; + *ecx = entry->ecx; + *edx = entry->edx; + } else { *eax = *ebx = *ecx = *edx = 0; - trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found); - return entry_found; + /* + * When leaf 0BH or 1FH is defined, CL is pass-through + * and EDX is always the x2APIC ID, even for undefined + * subleaves. Index 1 will exist iff the leaf is + * implemented, so we pass through CL iff leaf 1 + * exists. EDX can be copied from any existing index. + */ + if (function == 0xb || function == 0x1f) { + entry = kvm_find_cpuid_entry(vcpu, function, 1); + if (entry) { + *ecx = index & 0xff; + *edx = entry->edx; + } + } + } + trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found); + return found; } EXPORT_SYMBOL_GPL(kvm_cpuid); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3a3a6854dcca..b29d00b661ff 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -66,9 +66,10 @@ #define X2APIC_BROADCAST 0xFFFFFFFFul static bool lapic_timer_advance_dynamic __read_mostly; -#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 -#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 5000 -#define LAPIC_TIMER_ADVANCE_ADJUST_INIT 1000 +#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 /* clock cycles */ +#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 10000 /* clock cycles */ +#define LAPIC_TIMER_ADVANCE_NS_INIT 1000 +#define LAPIC_TIMER_ADVANCE_NS_MAX 5000 /* step-by-step approximation to mitigate fluctuation */ #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8 @@ -110,11 +111,6 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) -static inline u8 kvm_xapic_id(struct kvm_lapic *apic) -{ - return kvm_lapic_get_reg(apic, APIC_ID) >> 24; -} - static inline u32 kvm_x2apic_id(struct kvm_lapic *apic) { return apic->vcpu->vcpu_id; @@ -1504,8 +1500,8 @@ static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu, timer_advance_ns += ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP; } - if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_ADJUST_MAX)) - timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; + if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_NS_MAX)) + timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; apic->lapic_timer.timer_advance_ns = timer_advance_ns; } @@ -2302,7 +2298,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) HRTIMER_MODE_ABS_HARD); apic->lapic_timer.timer.function = apic_timer_fn; if (timer_advance_ns == -1) { - apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT; + apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; lapic_timer_advance_dynamic = true; } else { apic->lapic_timer.timer_advance_ns = timer_advance_ns; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 2aad7e226fc0..1f5014852e20 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -242,4 +242,9 @@ static inline enum lapic_mode kvm_apic_mode(u64 apic_base) return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); } +static inline u8 kvm_xapic_id(struct kvm_lapic *apic) +{ + return kvm_lapic_get_reg(apic, APIC_ID) >> 24; +} + #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 5269aa057dfa..2ce9da58611e 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -37,6 +37,7 @@ #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/kern_levels.h> +#include <linux/kthread.h> #include <asm/page.h> #include <asm/pat.h> @@ -47,6 +48,35 @@ #include <asm/kvm_page_track.h> #include "trace.h" +extern bool itlb_multihit_kvm_mitigation; + +static int __read_mostly nx_huge_pages = -1; +#ifdef CONFIG_PREEMPT_RT +/* Recovery can cause latency spikes, disable it for PREEMPT_RT. */ +static uint __read_mostly nx_huge_pages_recovery_ratio = 0; +#else +static uint __read_mostly nx_huge_pages_recovery_ratio = 60; +#endif + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp); +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp); + +static struct kernel_param_ops nx_huge_pages_ops = { + .set = set_nx_huge_pages, + .get = param_get_bool, +}; + +static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = { + .set = set_nx_huge_pages_recovery_ratio, + .get = param_get_uint, +}; + +module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644); +__MODULE_PARM_TYPE(nx_huge_pages, "bool"); +module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops, + &nx_huge_pages_recovery_ratio, 0644); +__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint"); + /* * When setting this variable to true it enables Two-Dimensional-Paging * where the hardware walks 2 page tables: @@ -83,7 +113,17 @@ module_param(dbg, bool, 0644); #define PTE_PREFETCH_NUM 8 #define PT_FIRST_AVAIL_BITS_SHIFT 10 -#define PT64_SECOND_AVAIL_BITS_SHIFT 52 +#define PT64_SECOND_AVAIL_BITS_SHIFT 54 + +/* + * The mask used to denote special SPTEs, which can be either MMIO SPTEs or + * Access Tracking SPTEs. + */ +#define SPTE_SPECIAL_MASK (3ULL << 52) +#define SPTE_AD_ENABLED_MASK (0ULL << 52) +#define SPTE_AD_DISABLED_MASK (1ULL << 52) +#define SPTE_AD_WRPROT_ONLY_MASK (2ULL << 52) +#define SPTE_MMIO_MASK (3ULL << 52) #define PT64_LEVEL_BITS 9 @@ -219,12 +259,11 @@ static u64 __read_mostly shadow_present_mask; static u64 __read_mostly shadow_me_mask; /* - * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value. - * Non-present SPTEs with shadow_acc_track_value set are in place for access - * tracking. + * SPTEs used by MMUs without A/D bits are marked with SPTE_AD_DISABLED_MASK; + * shadow_acc_track_mask is the set of bits to be cleared in non-accessed + * pages. */ static u64 __read_mostly shadow_acc_track_mask; -static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK; /* * The mask/shift to use for saving the original R/X bits when marking the PTE @@ -304,7 +343,7 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask) { BUG_ON((u64)(unsigned)access_mask != access_mask); BUG_ON((mmio_mask & mmio_value) != mmio_value); - shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK; + shadow_mmio_value = mmio_value | SPTE_MMIO_MASK; shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; shadow_mmio_access_mask = access_mask; } @@ -320,10 +359,32 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) return sp->role.ad_disabled; } +static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu) +{ + /* + * When using the EPT page-modification log, the GPAs in the log + * would come from L2 rather than L1. Therefore, we need to rely + * on write protection to record dirty pages. This also bypasses + * PML, since writes now result in a vmexit. + */ + return vcpu->arch.mmu == &vcpu->arch.guest_mmu; +} + static inline bool spte_ad_enabled(u64 spte) { MMU_WARN_ON(is_mmio_spte(spte)); - return !(spte & shadow_acc_track_value); + return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_DISABLED_MASK; +} + +static inline bool spte_ad_need_write_protect(u64 spte) +{ + MMU_WARN_ON(is_mmio_spte(spte)); + return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK; +} + +static bool is_nx_huge_page_enabled(void) +{ + return READ_ONCE(nx_huge_pages); } static inline u64 spte_shadow_accessed_mask(u64 spte) @@ -461,7 +522,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, { BUG_ON(!dirty_mask != !accessed_mask); BUG_ON(!accessed_mask && !acc_track_mask); - BUG_ON(acc_track_mask & shadow_acc_track_value); + BUG_ON(acc_track_mask & SPTE_SPECIAL_MASK); shadow_user_mask = user_mask; shadow_accessed_mask = accessed_mask; @@ -1164,6 +1225,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_disallow_lpage(slot, gfn); } +static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + if (sp->lpage_disallowed) + return; + + ++kvm->stat.nx_lpage_splits; + list_add_tail(&sp->lpage_disallowed_link, + &kvm->arch.lpage_disallowed_mmu_pages); + sp->lpage_disallowed = true; +} + static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { struct kvm_memslots *slots; @@ -1181,6 +1253,13 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_allow_lpage(slot, gfn); } +static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + --kvm->stat.nx_lpage_splits; + sp->lpage_disallowed = false; + list_del(&sp->lpage_disallowed_link); +} + static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level, struct kvm_memory_slot *slot) { @@ -1589,16 +1668,16 @@ static bool spte_clear_dirty(u64 *sptep) rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep); + MMU_WARN_ON(!spte_ad_enabled(spte)); spte &= ~shadow_dirty_mask; - return mmu_spte_update(sptep, spte); } -static bool wrprot_ad_disabled_spte(u64 *sptep) +static bool spte_wrprot_for_clear_dirty(u64 *sptep) { bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT, (unsigned long *)sptep); - if (was_writable) + if (was_writable && !spte_ad_enabled(*sptep)) kvm_set_pfn_dirty(spte_to_pfn(*sptep)); return was_writable; @@ -1617,10 +1696,10 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - if (spte_ad_enabled(*sptep)) - flush |= spte_clear_dirty(sptep); + if (spte_ad_need_write_protect(*sptep)) + flush |= spte_wrprot_for_clear_dirty(sptep); else - flush |= wrprot_ad_disabled_spte(sptep); + flush |= spte_clear_dirty(sptep); return flush; } @@ -1631,6 +1710,11 @@ static bool spte_set_dirty(u64 *sptep) rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep); + /* + * Similar to the !kvm_x86_ops->slot_disable_log_dirty case, + * do not bother adding back write access to pages marked + * SPTE_AD_WRPROT_ONLY_MASK. + */ spte |= shadow_dirty_mask; return mmu_spte_update(sptep, spte); @@ -2622,7 +2706,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, shadow_user_mask | shadow_x_mask | shadow_me_mask; if (sp_ad_disabled(sp)) - spte |= shadow_acc_track_value; + spte |= SPTE_AD_DISABLED_MASK; else spte |= shadow_accessed_mask; @@ -2761,6 +2845,9 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, kvm_reload_remote_mmus(kvm); } + if (sp->lpage_disallowed) + unaccount_huge_nx_page(kvm, sp); + sp->role.invalid = 1; return list_unstable; } @@ -2968,7 +3055,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, sp = page_header(__pa(sptep)); if (sp_ad_disabled(sp)) - spte |= shadow_acc_track_value; + spte |= SPTE_AD_DISABLED_MASK; + else if (kvm_vcpu_ad_need_write_protect(vcpu)) + spte |= SPTE_AD_WRPROT_ONLY_MASK; /* * For the EPT case, shadow_present_mask is 0 if hardware @@ -2980,6 +3069,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (!speculative) spte |= spte_shadow_accessed_mask(spte); + if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) && + is_nx_huge_page_enabled()) { + pte_access &= ~ACC_EXEC_MASK; + } + if (pte_access & ACC_EXEC_MASK) spte |= shadow_x_mask; else @@ -3200,9 +3294,32 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } +static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it, + gfn_t gfn, kvm_pfn_t *pfnp, int *levelp) +{ + int level = *levelp; + u64 spte = *it.sptep; + + if (it.level == level && level > PT_PAGE_TABLE_LEVEL && + is_nx_huge_page_enabled() && + is_shadow_present_pte(spte) && + !is_large_pte(spte)) { + /* + * A small SPTE exists for this pfn, but FNAME(fetch) + * and __direct_map would like to create a large PTE + * instead: just force them to go down another level, + * patching back for them into pfn the next 9 bits of + * the address. + */ + u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1); + *pfnp |= gfn & page_mask; + (*levelp)--; + } +} + static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, int map_writable, int level, kvm_pfn_t pfn, - bool prefault) + bool prefault, bool lpage_disallowed) { struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; @@ -3215,6 +3332,12 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, trace_kvm_mmu_spte_requested(gpa, level, pfn); for_each_shadow_entry(vcpu, gpa, it) { + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &level); + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); if (it.level == level) break; @@ -3225,6 +3348,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write, it.level - 1, true, ACC_ALL); link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); } } @@ -3273,7 +3398,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, * here. */ if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && - level == PT_PAGE_TABLE_LEVEL && + !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && PageTransCompoundMap(pfn_to_page(pfn)) && !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; @@ -3517,11 +3642,14 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, { int r; int level; - bool force_pt_level = false; + bool force_pt_level; kvm_pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + force_pt_level = lpage_disallowed; level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { /* @@ -3555,7 +3683,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, goto out_unlock; if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, pfn, prefault); + r = __direct_map(vcpu, v, write, map_writable, level, pfn, + prefault, false); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); @@ -4141,6 +4270,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, unsigned long mmu_seq; int write = error_code & PFERR_WRITE_MASK; bool map_writable; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)); @@ -4151,8 +4282,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (r) return r; - force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn, - PT_DIRECTORY_LEVEL); + force_pt_level = + lpage_disallowed || + !check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL); level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { if (level > PT_DIRECTORY_LEVEL && @@ -4181,7 +4313,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, goto out_unlock; if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, gfn, &pfn, &level); - r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault); + r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, + prefault, lpage_disallowed); out_unlock: spin_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); @@ -5881,9 +6014,9 @@ restart: * the guest, and the guest page table is using 4K page size * mapping if the indirect sp has level = 1. */ - if (sp->role.direct && - !kvm_is_reserved_pfn(pfn) && - PageTransCompoundMap(pfn_to_page(pfn))) { + if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && + !kvm_is_zone_device_pfn(pfn) && + PageTransCompoundMap(pfn_to_page(pfn))) { pte_list_remove(rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) @@ -6122,10 +6255,59 @@ static void kvm_set_mmio_spte_mask(void) kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK); } +static bool get_nx_auto_mode(void) +{ + /* Return true when CPU has the bug, and mitigations are ON */ + return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off(); +} + +static void __set_nx_huge_pages(bool val) +{ + nx_huge_pages = itlb_multihit_kvm_mitigation = val; +} + +static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) +{ + bool old_val = nx_huge_pages; + bool new_val; + + /* In "auto" mode deploy workaround only if CPU has the bug. */ + if (sysfs_streq(val, "off")) + new_val = 0; + else if (sysfs_streq(val, "force")) + new_val = 1; + else if (sysfs_streq(val, "auto")) + new_val = get_nx_auto_mode(); + else if (strtobool(val, &new_val) < 0) + return -EINVAL; + + __set_nx_huge_pages(new_val); + + if (new_val != old_val) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) { + mutex_lock(&kvm->slots_lock); + kvm_mmu_zap_all_fast(kvm); + mutex_unlock(&kvm->slots_lock); + + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + } + mutex_unlock(&kvm_lock); + } + + return 0; +} + int kvm_mmu_module_init(void) { int ret = -ENOMEM; + if (nx_huge_pages == -1) + __set_nx_huge_pages(get_nx_auto_mode()); + /* * MMU roles use union aliasing which is, generally speaking, an * undefined behavior. However, we supposedly know how compilers behave @@ -6205,3 +6387,116 @@ void kvm_mmu_module_exit(void) unregister_shrinker(&mmu_shrinker); mmu_audit_disable(); } + +static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp) +{ + unsigned int old_val; + int err; + + old_val = nx_huge_pages_recovery_ratio; + err = param_set_uint(val, kp); + if (err) + return err; + + if (READ_ONCE(nx_huge_pages) && + !old_val && nx_huge_pages_recovery_ratio) { + struct kvm *kvm; + + mutex_lock(&kvm_lock); + + list_for_each_entry(kvm, &vm_list, vm_list) + wake_up_process(kvm->arch.nx_lpage_recovery_thread); + + mutex_unlock(&kvm_lock); + } + + return err; +} + +static void kvm_recover_nx_lpages(struct kvm *kvm) +{ + int rcu_idx; + struct kvm_mmu_page *sp; + unsigned int ratio; + LIST_HEAD(invalid_list); + ulong to_zap; + + rcu_idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + + ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; + while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) { + /* + * We use a separate list instead of just using active_mmu_pages + * because the number of lpage_disallowed pages is expected to + * be relatively small compared to the total. + */ + sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages, + struct kvm_mmu_page, + lpage_disallowed_link); + WARN_ON_ONCE(!sp->lpage_disallowed); + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); + WARN_ON_ONCE(sp->lpage_disallowed); + + if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) { + kvm_mmu_commit_zap_page(kvm, &invalid_list); + if (to_zap) + cond_resched_lock(&kvm->mmu_lock); + } + } + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, rcu_idx); +} + +static long get_nx_lpage_recovery_timeout(u64 start_time) +{ + return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio) + ? start_time + 60 * HZ - get_jiffies_64() + : MAX_SCHEDULE_TIMEOUT; +} + +static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) +{ + u64 start_time; + long remaining_time; + + while (true) { + start_time = get_jiffies_64(); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop() && remaining_time > 0) { + schedule_timeout(remaining_time); + remaining_time = get_nx_lpage_recovery_timeout(start_time); + set_current_state(TASK_INTERRUPTIBLE); + } + + set_current_state(TASK_RUNNING); + + if (kthread_should_stop()) + return 0; + + kvm_recover_nx_lpages(kvm); + } +} + +int kvm_mmu_post_init_vm(struct kvm *kvm) +{ + int err; + + err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0, + "kvm-nx-lpage-recovery", + &kvm->arch.nx_lpage_recovery_thread); + if (!err) + kthread_unpark(kvm->arch.nx_lpage_recovery_thread); + + return err; +} + +void kvm_mmu_pre_destroy_vm(struct kvm *kvm) +{ + if (kvm->arch.nx_lpage_recovery_thread) + kthread_stop(kvm->arch.nx_lpage_recovery_thread); +} diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 11f8ec89433b..d55674f44a18 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -210,4 +210,8 @@ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); + +int kvm_mmu_post_init_vm(struct kvm *kvm); +void kvm_mmu_pre_destroy_vm(struct kvm *kvm); + #endif diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 7d5cdb3af594..97b21e7fd013 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -614,13 +614,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int write_fault, int hlevel, - kvm_pfn_t pfn, bool map_writable, bool prefault) + kvm_pfn_t pfn, bool map_writable, bool prefault, + bool lpage_disallowed) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; int top_level, ret; - gfn_t base_gfn; + gfn_t gfn, base_gfn; direct_access = gw->pte_access; @@ -665,13 +666,25 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(vcpu, it.sptep, sp); } - base_gfn = gw->gfn; + /* + * FNAME(page_fault) might have clobbered the bottom bits of + * gw->gfn, restore them from the virtual address. + */ + gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT); + base_gfn = gfn; trace_kvm_mmu_spte_requested(addr, gw->level, pfn); for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { clear_sp_write_flooding_count(it.sptep); - base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + + /* + * We cannot overwrite existing page tables with an NX + * large page, as the leaf could be executable. + */ + disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel); + + base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); if (it.level == hlevel) break; @@ -683,6 +696,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, sp = kvm_mmu_get_page(vcpu, base_gfn, addr, it.level - 1, true, direct_access); link_shadow_page(vcpu, it.sptep, sp); + if (lpage_disallowed) + account_huge_nx_page(vcpu->kvm, sp); } } @@ -759,9 +774,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int r; kvm_pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; - bool force_pt_level = false; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; + bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) && + is_nx_huge_page_enabled(); + bool force_pt_level = lpage_disallowed; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); @@ -851,7 +868,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (!force_pt_level) transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level); r = FNAME(fetch)(vcpu, addr, &walker, write_fault, - level, pfn, map_writable, prefault); + level, pfn, map_writable, prefault, lpage_disallowed); kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); out_unlock: diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f8ecb6df5106..c5673bda4b66 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -734,8 +734,14 @@ static int get_npt_level(struct kvm_vcpu *vcpu) static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { vcpu->arch.efer = efer; - if (!npt_enabled && !(efer & EFER_LMA)) - efer &= ~EFER_LME; + + if (!npt_enabled) { + /* Shadow paging assumes NX to be available. */ + efer |= EFER_NX; + + if (!(efer & EFER_LMA)) + efer &= ~EFER_LME; + } to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); @@ -4591,6 +4597,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) int ret = 0; struct vcpu_svm *svm = to_svm(vcpu); u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); + u32 id = kvm_xapic_id(vcpu->arch.apic); if (ldr == svm->ldr_reg) return 0; @@ -4598,7 +4605,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) avic_invalidate_logical_id_entry(vcpu); if (ldr) - ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr); + ret = avic_ldr_write(vcpu, id, ldr); if (!ret) svm->ldr_reg = ldr; @@ -4610,8 +4617,7 @@ static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu) { u64 *old, *new; struct vcpu_svm *svm = to_svm(vcpu); - u32 apic_id_reg = kvm_lapic_get_reg(vcpu->arch.apic, APIC_ID); - u32 id = (apic_id_reg >> 24) & 0xff; + u32 id = kvm_xapic_id(vcpu->arch.apic); if (vcpu->vcpu_id == id) return 0; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 41abc62c9a8a..0e7c9301fe86 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2610,7 +2610,7 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu, /* VM-entry exception error code */ if (CC(has_error_code && - vmcs12->vm_entry_exception_error_code & GENMASK(31, 15))) + vmcs12->vm_entry_exception_error_code & GENMASK(31, 16))) return -EINVAL; /* VM-entry interruption-info field: reserved bits */ @@ -2917,7 +2917,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12); -static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) +static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -2937,19 +2937,18 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) vmx->nested.apic_access_page = NULL; } page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr); - /* - * If translation failed, no matter: This feature asks - * to exit when accessing the given address, and if it - * can never be accessed, this feature won't do - * anything anyway. - */ if (!is_error_page(page)) { vmx->nested.apic_access_page = page; hpa = page_to_phys(vmx->nested.apic_access_page); vmcs_write64(APIC_ACCESS_ADDR, hpa); } else { - secondary_exec_controls_clearbit(vmx, - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); + pr_debug_ratelimited("%s: no backing 'struct page' for APIC-access address in vmcs12\n", + __func__); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return false; } } @@ -2994,6 +2993,7 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS); else exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS); + return true; } /* @@ -3032,13 +3032,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, /* * If from_vmentry is false, this is being called from state restore (either RSM * or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume. -+ * -+ * Returns: -+ * 0 - success, i.e. proceed with actual VMEnter -+ * 1 - consistency check VMExit -+ * -1 - consistency check VMFail + * + * Returns: + * NVMX_ENTRY_SUCCESS: Entered VMX non-root mode + * NVMX_ENTRY_VMFAIL: Consistency check VMFail + * NVMX_ENTRY_VMEXIT: Consistency check VMExit + * NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error */ -int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) +enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, + bool from_vmentry) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -3081,11 +3083,12 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) prepare_vmcs02_early(vmx, vmcs12); if (from_vmentry) { - nested_get_vmcs12_pages(vcpu); + if (unlikely(!nested_get_vmcs12_pages(vcpu))) + return NVMX_VMENTRY_KVM_INTERNAL_ERROR; if (nested_vmx_check_vmentry_hw(vcpu)) { vmx_switch_vmcs(vcpu, &vmx->vmcs01); - return -1; + return NVMX_VMENTRY_VMFAIL; } if (nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual)) @@ -3149,7 +3152,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) * returned as far as L1 is concerned. It will only return (and set * the success flag) when L2 exits (see nested_vmx_vmexit()). */ - return 0; + return NVMX_VMENTRY_SUCCESS; /* * A failed consistency check that leads to a VMExit during L1's @@ -3165,14 +3168,14 @@ vmentry_fail_vmexit: vmx_switch_vmcs(vcpu, &vmx->vmcs01); if (!from_vmentry) - return 1; + return NVMX_VMENTRY_VMEXIT; load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY; vmcs12->exit_qualification = exit_qual; if (enable_shadow_vmcs || vmx->nested.hv_evmcs) vmx->nested.need_vmcs12_to_shadow_sync = true; - return 1; + return NVMX_VMENTRY_VMEXIT; } /* @@ -3182,9 +3185,9 @@ vmentry_fail_vmexit: static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) { struct vmcs12 *vmcs12; + enum nvmx_vmentry_status status; struct vcpu_vmx *vmx = to_vmx(vcpu); u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu); - int ret; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -3244,13 +3247,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * the nested entry. */ vmx->nested.nested_run_pending = 1; - ret = nested_vmx_enter_non_root_mode(vcpu, true); - vmx->nested.nested_run_pending = !ret; - if (ret > 0) - return 1; - else if (ret) - return nested_vmx_failValid(vcpu, - VMXERR_ENTRY_INVALID_CONTROL_FIELD); + status = nested_vmx_enter_non_root_mode(vcpu, true); + if (unlikely(status != NVMX_VMENTRY_SUCCESS)) + goto vmentry_failed; /* Hide L1D cache contents from the nested guest. */ vmx->vcpu.arch.l1tf_flush_l1d = true; @@ -3281,6 +3280,15 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return kvm_vcpu_halt(vcpu); } return 1; + +vmentry_failed: + vmx->nested.nested_run_pending = 0; + if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR) + return 0; + if (status == NVMX_VMENTRY_VMEXIT) + return 1; + WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL); + return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); } /* diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 187d39bf0bf1..6280f33e5fa6 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -6,6 +6,16 @@ #include "vmcs12.h" #include "vmx.h" +/* + * Status returned by nested_vmx_enter_non_root_mode(): + */ +enum nvmx_vmentry_status { + NVMX_VMENTRY_SUCCESS, /* Entered VMX non-root mode */ + NVMX_VMENTRY_VMFAIL, /* Consistency check VMFail */ + NVMX_VMENTRY_VMEXIT, /* Consistency check VMExit */ + NVMX_VMENTRY_KVM_INTERNAL_ERROR,/* KVM internal error */ +}; + void vmx_leave_nested(struct kvm_vcpu *vcpu); void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, bool apicv); @@ -13,7 +23,8 @@ void nested_vmx_hardware_unsetup(void); __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)); void nested_vmx_vcpu_setup(void); void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu); -int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry); +enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, + bool from_vmentry); bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason); void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, u32 exit_intr_info, unsigned long exit_qualification); diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 4dea0e0e7e39..3e9c059099e9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -262,6 +262,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static void intel_pmu_refresh(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct x86_pmu_capability x86_pmu; struct kvm_cpuid_entry2 *entry; union cpuid10_eax eax; union cpuid10_edx edx; @@ -283,8 +284,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) if (!pmu->version) return; + perf_get_x86_pmu_capability(&x86_pmu); + pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, - INTEL_PMC_MAX_GENERIC); + x86_pmu.num_counters_gp); pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; pmu->available_event_types = ~entry->ebx & ((1ull << eax.split.mask_length) - 1); @@ -294,7 +297,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) } else { pmu->nr_arch_fixed_counters = min_t(int, edx.split.num_counters_fixed, - INTEL_PMC_MAX_FIXED); + x86_pmu.num_counters_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << edx.split.bit_width_fixed) - 1; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d4575ffb3cec..04a8212704c1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -209,6 +209,11 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf) struct page *page; unsigned int i; + if (!boot_cpu_has_bug(X86_BUG_L1TF)) { + l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED; + return 0; + } + if (!enable_ept) { l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED; return 0; @@ -964,17 +969,9 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) u64 guest_efer = vmx->vcpu.arch.efer; u64 ignore_bits = 0; - if (!enable_ept) { - /* - * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing - * host CPUID is more efficient than testing guest CPUID - * or CR4. Host SMEP is anyway a requirement for guest SMEP. - */ - if (boot_cpu_has(X86_FEATURE_SMEP)) - guest_efer |= EFER_NX; - else if (!(guest_efer & EFER_NX)) - ignore_bits |= EFER_NX; - } + /* Shadow paging assumes NX to be available. */ + if (!enable_ept) + guest_efer |= EFER_NX; /* * LMA and LME handled by hardware; SCE meaningless outside long mode. @@ -1271,6 +1268,18 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; + /* + * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change + * PI.NDST: pi_post_block is the one expected to change PID.NDST and the + * wakeup handler expects the vCPU to be on the blocked_vcpu_list that + * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up + * correctly. + */ + if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) { + pi_clear_sn(pi_desc); + goto after_clear_sn; + } + /* The full case. */ do { old.control = new.control = pi_desc->control; @@ -1286,6 +1295,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) } while (cmpxchg64(&pi_desc->control, old.control, new.control) != old.control); +after_clear_sn: + /* * Clear SN before reading the bitmap. The VT-d firmware * writes the bitmap and reads SN atomically (5.2.3 in the @@ -1294,7 +1305,7 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) */ smp_mb__after_atomic(); - if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS)) + if (!pi_is_pir_empty(pi_desc)) pi_set_on(pi_desc); } @@ -5538,14 +5549,6 @@ static int handle_encls(struct kvm_vcpu *vcpu) return 1; } -static int handle_unexpected_vmexit(struct kvm_vcpu *vcpu) -{ - kvm_skip_emulated_instruction(vcpu); - WARN_ONCE(1, "Unexpected VM-Exit Reason = 0x%x", - vmcs_read32(VM_EXIT_REASON)); - return 1; -} - /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -5597,15 +5600,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_INVVPID] = handle_vmx_instruction, [EXIT_REASON_RDRAND] = handle_invalid_op, [EXIT_REASON_RDSEED] = handle_invalid_op, - [EXIT_REASON_XSAVES] = handle_unexpected_vmexit, - [EXIT_REASON_XRSTORS] = handle_unexpected_vmexit, [EXIT_REASON_PML_FULL] = handle_pml_full, [EXIT_REASON_INVPCID] = handle_invpcid, [EXIT_REASON_VMFUNC] = handle_vmx_instruction, [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer, [EXIT_REASON_ENCLS] = handle_encls, - [EXIT_REASON_UMWAIT] = handle_unexpected_vmexit, - [EXIT_REASON_TPAUSE] = handle_unexpected_vmexit, }; static const int kvm_vmx_max_exit_handlers = @@ -6152,7 +6151,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) if (pi_test_on(&vmx->pi_desc)) { pi_clear_on(&vmx->pi_desc); /* - * IOMMU can write to PIR.ON, so the barrier matters even on UP. + * IOMMU can write to PID.ON, so the barrier matters even on UP. * But on x86 this is just a compiler barrier anyway. */ smp_mb__after_atomic(); @@ -6182,7 +6181,10 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) { - return pi_test_on(vcpu_to_pi_desc(vcpu)); + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + return pi_test_on(pi_desc) || + (pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc)); } static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) @@ -7995,12 +7997,10 @@ static int __init vmx_init(void) * contain 'auto' which will be turned into the default 'cond' * mitigation mode. */ - if (boot_cpu_has(X86_BUG_L1TF)) { - r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); - return r; - } + r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); + if (r) { + vmx_exit(); + return r; } #ifdef CONFIG_KEXEC_CORE diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index bee16687dc0b..5a0f34b1e226 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -355,6 +355,11 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } +static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) +{ + return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS); +} + static inline void pi_set_sn(struct pi_desc *pi_desc) { set_bit(POSTED_INTR_SN, @@ -373,6 +378,12 @@ static inline void pi_clear_on(struct pi_desc *pi_desc) (unsigned long *)&pi_desc->control); } +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + static inline int pi_test_on(struct pi_desc *pi_desc) { return test_bit(POSTED_INTR_ON, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0ed07d8d2caa..5d530521f11d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -92,8 +92,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif -#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM -#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ +#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \ KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK) @@ -212,7 +212,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "mmu_cache_miss", VM_STAT(mmu_cache_miss) }, { "mmu_unsync", VM_STAT(mmu_unsync) }, { "remote_tlb_flush", VM_STAT(remote_tlb_flush) }, - { "largepages", VM_STAT(lpages) }, + { "largepages", VM_STAT(lpages, .mode = 0444) }, + { "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) }, { "max_mmu_page_hash_collisions", VM_STAT(max_mmu_page_hash_collisions) }, { NULL } @@ -360,8 +361,7 @@ EXPORT_SYMBOL_GPL(kvm_set_apic_base); asmlinkage __visible void kvm_spurious_fault(void) { /* Fault while not rebooting. We want the trace. */ - if (!kvm_rebooting) - BUG(); + BUG_ON(!kvm_rebooting); } EXPORT_SYMBOL_GPL(kvm_spurious_fault); @@ -885,34 +885,42 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) } EXPORT_SYMBOL_GPL(kvm_set_xcr); -int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - unsigned long old_cr4 = kvm_read_cr4(vcpu); - unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; - if (cr4 & CR4_RESERVED_BITS) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57)) - return 1; + return -EINVAL; if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP)) + return -EINVAL; + + return 0; +} + +int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + unsigned long old_cr4 = kvm_read_cr4(vcpu); + unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + + if (kvm_valid_cr4(vcpu, cr4)) return 1; if (is_long_mode(vcpu)) { @@ -1125,13 +1133,15 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. * - * This list is modified at module load time to reflect the + * The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features) + * extract the supported MSRs from the related const lists. + * msrs_to_save is selected from the msrs_to_save_all to reflect the * capabilities of the host cpu. This capabilities test skips MSRs that are - * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs + * kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs * may depend on host virtualization features rather than host cpu features. */ -static u32 msrs_to_save[] = { +static const u32 msrs_to_save_all[] = { MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -1161,13 +1171,6 @@ static u32 msrs_to_save[] = { MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13, MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15, MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17, - MSR_ARCH_PERFMON_PERFCTR0 + 18, MSR_ARCH_PERFMON_PERFCTR0 + 19, - MSR_ARCH_PERFMON_PERFCTR0 + 20, MSR_ARCH_PERFMON_PERFCTR0 + 21, - MSR_ARCH_PERFMON_PERFCTR0 + 22, MSR_ARCH_PERFMON_PERFCTR0 + 23, - MSR_ARCH_PERFMON_PERFCTR0 + 24, MSR_ARCH_PERFMON_PERFCTR0 + 25, - MSR_ARCH_PERFMON_PERFCTR0 + 26, MSR_ARCH_PERFMON_PERFCTR0 + 27, - MSR_ARCH_PERFMON_PERFCTR0 + 28, MSR_ARCH_PERFMON_PERFCTR0 + 29, - MSR_ARCH_PERFMON_PERFCTR0 + 30, MSR_ARCH_PERFMON_PERFCTR0 + 31, MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1, MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3, MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5, @@ -1177,18 +1180,12 @@ static u32 msrs_to_save[] = { MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13, MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15, MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17, - MSR_ARCH_PERFMON_EVENTSEL0 + 18, MSR_ARCH_PERFMON_EVENTSEL0 + 19, - MSR_ARCH_PERFMON_EVENTSEL0 + 20, MSR_ARCH_PERFMON_EVENTSEL0 + 21, - MSR_ARCH_PERFMON_EVENTSEL0 + 22, MSR_ARCH_PERFMON_EVENTSEL0 + 23, - MSR_ARCH_PERFMON_EVENTSEL0 + 24, MSR_ARCH_PERFMON_EVENTSEL0 + 25, - MSR_ARCH_PERFMON_EVENTSEL0 + 26, MSR_ARCH_PERFMON_EVENTSEL0 + 27, - MSR_ARCH_PERFMON_EVENTSEL0 + 28, MSR_ARCH_PERFMON_EVENTSEL0 + 29, - MSR_ARCH_PERFMON_EVENTSEL0 + 30, MSR_ARCH_PERFMON_EVENTSEL0 + 31, }; +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; static unsigned num_msrs_to_save; -static u32 emulated_msrs[] = { +static const u32 emulated_msrs_all[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, @@ -1227,7 +1224,7 @@ static u32 emulated_msrs[] = { * by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs. * We always support the "true" VMX control MSRs, even if the host * processor does not, so I am putting these registers here rather - * than in msrs_to_save. + * than in msrs_to_save_all. */ MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, @@ -1246,13 +1243,14 @@ static u32 emulated_msrs[] = { MSR_KVM_POLL_CONTROL, }; +static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; static unsigned num_emulated_msrs; /* * List of msr numbers which are used to expose MSR-based features that * can be used by a hypervisor to validate requested CPU features. */ -static u32 msr_based_features[] = { +static const u32 msr_based_features_all[] = { MSR_IA32_VMX_BASIC, MSR_IA32_VMX_TRUE_PINBASED_CTLS, MSR_IA32_VMX_PINBASED_CTLS, @@ -1277,6 +1275,7 @@ static u32 msr_based_features[] = { MSR_IA32_ARCH_CAPABILITIES, }; +static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)]; static unsigned int num_msr_based_features; static u64 kvm_get_arch_capabilities(void) @@ -1287,6 +1286,14 @@ static u64 kvm_get_arch_capabilities(void) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data); /* + * If nx_huge_pages is enabled, KVM's shadow paging will ensure that + * the nested hypervisor runs with NX huge pages. If it is not, + * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other + * L1 guests, so it need not worry about its own (L2) guests. + */ + data |= ARCH_CAP_PSCHANGE_MC_NO; + + /* * If we're doing cache flushes (either "always" or "cond") * we will do one whenever the guest does a vmlaunch/vmresume. * If an outer hypervisor is doing the cache flush for us @@ -1305,6 +1312,25 @@ static u64 kvm_get_arch_capabilities(void) if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + /* + * On TAA affected systems, export MDS_NO=0 when: + * - TSX is enabled on the host, i.e. X86_FEATURE_RTM=1. + * - Updated microcode is present. This is detected by + * the presence of ARCH_CAP_TSX_CTRL_MSR and ensures + * that VERW clears CPU buffers. + * + * When MDS_NO=0 is exported, guests deploy clear CPU buffer + * mitigation and don't complain: + * + * "Vulnerable: Clear CPU buffers attempted, no microcode" + * + * If TSX is disabled on the system, guests are also mitigated against + * TAA and clear CPU buffer mitigation is not required for guests. + */ + if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) && + (data & ARCH_CAP_TSX_CTRL_MSR)) + data &= ~ARCH_CAP_MDS_NO; + return data; } @@ -2543,6 +2569,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { vcpu->arch.pv_time_enabled = false; + vcpu->arch.time = 0; } static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) @@ -2708,8 +2735,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_KVM_SYSTEM_TIME: { struct kvm_arch *ka = &vcpu->kvm->arch; - kvmclock_reset(vcpu); - if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) { bool tmp = (msr == MSR_KVM_SYSTEM_TIME); @@ -2723,14 +2748,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); /* we verify if the enable bit is set... */ + vcpu->arch.pv_time_enabled = false; if (!(data & 1)) break; - if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + if (!kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_time, data & ~1ULL, sizeof(struct pvclock_vcpu_time_info))) - vcpu->arch.pv_time_enabled = false; - else vcpu->arch.pv_time_enabled = true; break; @@ -5097,23 +5121,28 @@ out: static void kvm_init_msr_list(void) { + struct x86_pmu_capability x86_pmu; u32 dummy[2]; - unsigned i, j; + unsigned i; BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4, - "Please update the fixed PMCs in msrs_to_save[]"); - BUILD_BUG_ON_MSG(INTEL_PMC_MAX_GENERIC != 32, - "Please update the generic perfctr/eventsel MSRs in msrs_to_save[]"); + "Please update the fixed PMCs in msrs_to_saved_all[]"); + + perf_get_x86_pmu_capability(&x86_pmu); + + num_msrs_to_save = 0; + num_emulated_msrs = 0; + num_msr_based_features = 0; - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { - if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) + for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) { + if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0) continue; /* * Even MSRs that are valid in the host may not be exposed * to the guests in some cases. */ - switch (msrs_to_save[i]) { + switch (msrs_to_save_all[i]) { case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported()) continue; @@ -5141,43 +5170,43 @@ static void kvm_init_msr_list(void) break; case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: { if (!kvm_x86_ops->pt_supported() || - msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >= + msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >= intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) continue; break; + case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17: + if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >= + min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + continue; + break; + case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17: + if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= + min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp)) + continue; } default: break; } - if (j < i) - msrs_to_save[j] = msrs_to_save[i]; - j++; + msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i]; } - num_msrs_to_save = j; - for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { - if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i])) + for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { + if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i])) continue; - if (j < i) - emulated_msrs[j] = emulated_msrs[i]; - j++; + emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; } - num_emulated_msrs = j; - for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) { + for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) { struct kvm_msr_entry msr; - msr.index = msr_based_features[i]; + msr.index = msr_based_features_all[i]; if (kvm_get_msr_feature(&msr)) continue; - if (j < i) - msr_based_features[j] = msr_based_features[i]; - j++; + msr_based_features[num_msr_based_features++] = msr_based_features_all[i]; } - num_msr_based_features = j; } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, @@ -7937,8 +7966,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_immediate_exit = false; if (kvm_request_pending(vcpu)) { - if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) - kvm_x86_ops->get_vmcs12_pages(vcpu); + if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) { + if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) { + r = 0; + goto out; + } + } if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) kvm_mmu_unload(vcpu); if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) @@ -8714,10 +8747,6 @@ EXPORT_SYMBOL_GPL(kvm_task_switch); static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && - (sregs->cr4 & X86_CR4_OSXSAVE)) - return -EINVAL; - if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) { /* * When EFER.LME and CR0.PG are set, the processor is in @@ -8736,7 +8765,7 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) return -EINVAL; } - return 0; + return kvm_valid_cr4(vcpu, sregs->cr4); } static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) @@ -9427,6 +9456,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); + INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); @@ -9455,6 +9485,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return kvm_x86_ops->vm_init(kvm); } +int kvm_arch_post_init_vm(struct kvm *kvm) +{ + return kvm_mmu_post_init_vm(kvm); +} + static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { vcpu_load(vcpu); @@ -9556,6 +9591,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) } EXPORT_SYMBOL_GPL(x86_set_memory_region); +void kvm_arch_pre_destroy_vm(struct kvm *kvm) +{ + kvm_mmu_pre_destroy_vm(kvm); +} + void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index b7375dc6898f..c126571e5e2e 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -113,8 +113,8 @@ static void delay_mwaitx(unsigned long __loops) __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); /* - * AMD, like Intel, supports the EAX hint and EAX=0xf - * means, do not enter any deep C-state and we use it + * AMD, like Intel's MWAIT version, supports the EAX hint and + * EAX=0xf0 means, do not enter any deep C-state and we use it * here in delay() to minimize wakeup latency. */ __mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index c202e1b07e29..425e025341db 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -917,9 +917,6 @@ static void __init kexec_enter_virtual_mode(void) if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX)) runtime_code_page_mkexec(); - - /* clean DUMMY object */ - efi_delete_dummy_variable(); #endif } diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c index 0d3365cb64de..a04551ee5568 100644 --- a/arch/x86/xen/efi.c +++ b/arch/x86/xen/efi.c @@ -57,19 +57,7 @@ static efi_system_table_t __init *xen_efi_probe(void) return NULL; /* Here we know that Xen runs on EFI platform. */ - - efi.get_time = xen_efi_get_time; - efi.set_time = xen_efi_set_time; - efi.get_wakeup_time = xen_efi_get_wakeup_time; - efi.set_wakeup_time = xen_efi_set_wakeup_time; - efi.get_variable = xen_efi_get_variable; - efi.get_next_variable = xen_efi_get_next_variable; - efi.set_variable = xen_efi_set_variable; - efi.query_variable_info = xen_efi_query_variable_info; - efi.update_capsule = xen_efi_update_capsule; - efi.query_capsule_caps = xen_efi_query_capsule_caps; - efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; - efi.reset_system = xen_efi_reset_system; + xen_efi_runtime_setup(); efi_systab_xen.tables = info->cfg.addr; efi_systab_xen.nr_tables = info->cfg.nent; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 750f46ad018a..205b1176084f 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -269,19 +269,41 @@ void xen_reboot(int reason) BUG(); } +static int reboot_reason = SHUTDOWN_reboot; +static bool xen_legacy_crash; void xen_emergency_restart(void) { - xen_reboot(SHUTDOWN_reboot); + xen_reboot(reboot_reason); } static int xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) { - if (!kexec_crash_loaded()) - xen_reboot(SHUTDOWN_crash); + if (!kexec_crash_loaded()) { + if (xen_legacy_crash) + xen_reboot(SHUTDOWN_crash); + + reboot_reason = SHUTDOWN_crash; + + /* + * If panic_timeout==0 then we are supposed to wait forever. + * However, to preserve original dom0 behavior we have to drop + * into hypervisor. (domU behavior is controlled by its + * config file) + */ + if (panic_timeout == 0) + panic_timeout = -1; + } return NOTIFY_DONE; } +static int __init parse_xen_legacy_crash(char *arg) +{ + xen_legacy_crash = true; + return 0; +} +early_param("xen_legacy_crash", parse_xen_legacy_crash); + static struct notifier_block xen_panic_block = { .notifier_call = xen_panic_event, .priority = INT_MIN diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 58f79ab32358..5bfea374a160 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -117,6 +117,14 @@ static void __init xen_banner(void) printk(KERN_INFO "Xen version: %d.%d%s%s\n", version >> 16, version & 0xffff, extra.extraversion, xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); + +#ifdef CONFIG_X86_32 + pr_warn("WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n" + "Support for running as 32-bit PV-guest under Xen will soon be removed\n" + "from the Linux kernel!\n" + "Please use either a 64-bit kernel or switch to HVM or PVH mode!\n" + "WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n"); +#endif } static void __init xen_pv_init_platform(void) diff --git a/arch/xtensa/boot/dts/virt.dts b/arch/xtensa/boot/dts/virt.dts index a9dcd87b6eb1..611b98a02a65 100644 --- a/arch/xtensa/boot/dts/virt.dts +++ b/arch/xtensa/boot/dts/virt.dts @@ -56,7 +56,7 @@ reg = <0xf0100000 0x03f00000>; // BUS_ADDRESS(3) CPU_PHYSICAL(1) SIZE(2) - ranges = <0x01000000 0x0 0xf0000000 0xf0000000 0x0 0x00010000>, + ranges = <0x01000000 0x0 0x00000000 0xf0000000 0x0 0x00010000>, <0x02000000 0x0 0xf4000000 0xf4000000 0x0 0x08000000>; // PCI_DEVICE(3) INT#(1) CONTROLLER(PHANDLE) CONTROLLER_DATA(2) diff --git a/arch/xtensa/include/asm/bitops.h b/arch/xtensa/include/asm/bitops.h index aeb15f4c755b..be8b2be5a98b 100644 --- a/arch/xtensa/include/asm/bitops.h +++ b/arch/xtensa/include/asm/bitops.h @@ -148,7 +148,7 @@ static inline void change_bit(unsigned int bit, volatile unsigned long *p) " getex %0\n" " beqz %0, 1b\n" : "=&a" (tmp) - : "a" (~mask), "a" (p) + : "a" (mask), "a" (p) : "memory"); } diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index 6792928ba84a..3f80386f1883 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -100,7 +100,7 @@ do { \ case 4: __put_user_asm(x, ptr, retval, 4, "s32i", __cb); break; \ case 8: { \ __typeof__(*ptr) __v64 = x; \ - retval = __copy_to_user(ptr, &__v64, 8); \ + retval = __copy_to_user(ptr, &__v64, 8) ? -EFAULT : 0; \ break; \ } \ default: __put_user_bad(); \ @@ -132,14 +132,14 @@ do { \ #define __check_align_1 "" #define __check_align_2 \ - " _bbci.l %3, 0, 1f \n" \ - " movi %0, %4 \n" \ + " _bbci.l %[addr], 0, 1f \n" \ + " movi %[err], %[efault] \n" \ " _j 2f \n" #define __check_align_4 \ - " _bbsi.l %3, 0, 0f \n" \ - " _bbci.l %3, 1, 1f \n" \ - "0: movi %0, %4 \n" \ + " _bbsi.l %[addr], 0, 0f \n" \ + " _bbci.l %[addr], 1, 1f \n" \ + "0: movi %[err], %[efault] \n" \ " _j 2f \n" @@ -151,40 +151,40 @@ do { \ * WARNING: If you modify this macro at all, verify that the * __check_align_* macros still work. */ -#define __put_user_asm(x, addr, err, align, insn, cb) \ +#define __put_user_asm(x_, addr_, err_, align, insn, cb)\ __asm__ __volatile__( \ __check_align_##align \ - "1: "insn" %2, %3, 0 \n" \ + "1: "insn" %[x], %[addr], 0 \n" \ "2: \n" \ " .section .fixup,\"ax\" \n" \ " .align 4 \n" \ " .literal_position \n" \ "5: \n" \ - " movi %1, 2b \n" \ - " movi %0, %4 \n" \ - " jx %1 \n" \ + " movi %[tmp], 2b \n" \ + " movi %[err], %[efault] \n" \ + " jx %[tmp] \n" \ " .previous \n" \ " .section __ex_table,\"a\" \n" \ " .long 1b, 5b \n" \ " .previous" \ - :"=r" (err), "=r" (cb) \ - :"r" ((int)(x)), "r" (addr), "i" (-EFAULT), "0" (err)) + :[err] "+r"(err_), [tmp] "=r"(cb) \ + :[x] "r"(x_), [addr] "r"(addr_), [efault] "i"(-EFAULT)) #define __get_user_nocheck(x, ptr, size) \ ({ \ - long __gu_err, __gu_val; \ - __get_user_size(__gu_val, (ptr), (size), __gu_err); \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ + long __gu_err; \ + __get_user_size((x), (ptr), (size), __gu_err); \ __gu_err; \ }) #define __get_user_check(x, ptr, size) \ ({ \ - long __gu_err = -EFAULT, __gu_val = 0; \ + long __gu_err = -EFAULT; \ const __typeof__(*(ptr)) *__gu_addr = (ptr); \ - if (access_ok(__gu_addr, size)) \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ + if (access_ok(__gu_addr, size)) \ + __get_user_size((x), __gu_addr, (size), __gu_err); \ + else \ + (x) = 0; \ __gu_err; \ }) @@ -198,8 +198,17 @@ do { \ case 1: __get_user_asm(x, ptr, retval, 1, "l8ui", __cb); break;\ case 2: __get_user_asm(x, ptr, retval, 2, "l16ui", __cb); break;\ case 4: __get_user_asm(x, ptr, retval, 4, "l32i", __cb); break;\ - case 8: retval = __copy_from_user(&x, ptr, 8); break; \ - default: (x) = __get_user_bad(); \ + case 8: { \ + u64 __x; \ + if (unlikely(__copy_from_user(&__x, ptr, 8))) { \ + retval = -EFAULT; \ + (x) = 0; \ + } else { \ + (x) = *(__force __typeof__((ptr)))&__x; \ + } \ + break; \ + } \ + default: (x) = 0; __get_user_bad(); \ } \ } while (0) @@ -208,25 +217,28 @@ do { \ * WARNING: If you modify this macro at all, verify that the * __check_align_* macros still work. */ -#define __get_user_asm(x, addr, err, align, insn, cb) \ -__asm__ __volatile__( \ - __check_align_##align \ - "1: "insn" %2, %3, 0 \n" \ - "2: \n" \ - " .section .fixup,\"ax\" \n" \ - " .align 4 \n" \ - " .literal_position \n" \ - "5: \n" \ - " movi %1, 2b \n" \ - " movi %2, 0 \n" \ - " movi %0, %4 \n" \ - " jx %1 \n" \ - " .previous \n" \ - " .section __ex_table,\"a\" \n" \ - " .long 1b, 5b \n" \ - " .previous" \ - :"=r" (err), "=r" (cb), "=r" (x) \ - :"r" (addr), "i" (-EFAULT), "0" (err)) +#define __get_user_asm(x_, addr_, err_, align, insn, cb) \ +do { \ + u32 __x = 0; \ + __asm__ __volatile__( \ + __check_align_##align \ + "1: "insn" %[x], %[addr], 0 \n" \ + "2: \n" \ + " .section .fixup,\"ax\" \n" \ + " .align 4 \n" \ + " .literal_position \n" \ + "5: \n" \ + " movi %[tmp], 2b \n" \ + " movi %[err], %[efault] \n" \ + " jx %[tmp] \n" \ + " .previous \n" \ + " .section __ex_table,\"a\" \n" \ + " .long 1b, 5b \n" \ + " .previous" \ + :[err] "+r"(err_), [tmp] "=r"(cb), [x] "+r"(__x) \ + :[addr] "r"(addr_), [efault] "i"(-EFAULT)); \ + (x_) = (__force __typeof__(*(addr_)))__x; \ +} while (0) /* diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 04f19de46700..4092555828b1 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -119,13 +119,6 @@ EXPORT_SYMBOL(__invalidate_icache_range); // FIXME EXPORT_SYMBOL(screen_info); #endif -EXPORT_SYMBOL(outsb); -EXPORT_SYMBOL(outsw); -EXPORT_SYMBOL(outsl); -EXPORT_SYMBOL(insb); -EXPORT_SYMBOL(insw); -EXPORT_SYMBOL(insl); - extern long common_exception_return; EXPORT_SYMBOL(common_exception_return); |